Update the replica promotion test

The new one works and is slightly more ergonomic.

Cargo.lock

@@ -1086,25 +1086,6 @@ version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "37b2a672a2cb129a2e41c10b1224bb368f9f37a2b16b612598138befd7b37eb5"
 
-[[package]]
-name = "cbindgen"
-version = "0.28.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "eadd868a2ce9ca38de7eeafdcec9c7065ef89b42b32f0839278d55f35c54d1ff"
-dependencies = [
- "clap",
- "heck 0.4.1",
- "indexmap 2.9.0",
- "log",
- "proc-macro2",
- "quote",
- "serde",
- "serde_json",
- "syn 2.0.100",
- "tempfile",
- "toml",
-]
-
 [[package]]
 name = "cc"
 version = "1.2.16"
@@ -1231,7 +1212,7 @@ version = "4.5.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4ac6a0c7b1a9e9a5186361f67dfa1b88213572f427fb9ab038efb2bd8c582dab"
 dependencies = [
- "heck 0.5.0",
+ "heck",
  "proc-macro2",
  "quote",
  "syn 2.0.100",
@@ -1289,14 +1270,6 @@ dependencies = [
  "unicode-width",
 ]
 
-[[package]]
-name = "communicator"
-version = "0.1.0"
-dependencies = [
- "cbindgen",
- "neon-shmem",
-]
-
 [[package]]
 name = "compute_api"
 version = "0.1.0"
@@ -1963,7 +1936,7 @@ checksum = "0892a17df262a24294c382f0d5997571006e7a4348b4327557c4ff1cd4a8bccc"
 dependencies = [
  "darling",
  "either",
- "heck 0.5.0",
+ "heck",
  "proc-macro2",
  "quote",
  "syn 2.0.100",
@@ -2527,18 +2500,6 @@ dependencies = [
  "wasm-bindgen",
 ]
 
-[[package]]
-name = "getrandom"
-version = "0.3.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "26145e563e54f2cadc477553f1ec5ee650b00862f0a58bcd12cbdc5f0ea2d2f4"
-dependencies = [
- "cfg-if",
- "libc",
- "r-efi",
- "wasi 0.14.2+wasi-0.2.4",
-]
-
 [[package]]
 name = "gettid"
 version = "0.1.3"
@@ -2751,12 +2712,6 @@ dependencies = [
  "http 1.1.0",
 ]
 
-[[package]]
-name = "heck"
-version = "0.4.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "95505c38b4572b2d910cecb0281560f54b440a19336cbbcb27bf6ce6adc6f5a8"
-
 [[package]]
 name = "heck"
 version = "0.5.0"
@@ -3693,7 +3648,7 @@ version = "0.0.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b9e6777fc80a575f9503d908c8b498782a6c3ee88a06cb416dc3941401e43b94"
 dependencies = [
- "heck 0.5.0",
+ "heck",
  "proc-macro2",
  "quote",
  "syn 2.0.100",
@@ -3755,7 +3710,7 @@ dependencies = [
  "procfs",
  "prometheus",
  "rand 0.8.5",
- "rand_distr 0.4.3",
+ "rand_distr",
  "twox-hash",
 ]
 
@@ -3844,8 +3799,6 @@ name = "neon-shmem"
 version = "0.1.0"
 dependencies = [
  "nix 0.30.1",
- "rand 0.9.1",
- "rand_distr 0.5.1",
  "tempfile",
  "thiserror 1.0.69",
  "workspace_hack",
@@ -4283,8 +4236,6 @@ name = "pagebench"
 version = "0.1.0"
 dependencies = [
  "anyhow",
- "async-trait",
- "bytes",
  "camino",
  "clap",
  "futures",
@@ -4293,15 +4244,12 @@ dependencies = [
  "humantime-serde",
  "pageserver_api",
  "pageserver_client",
- "pageserver_page_api",
  "rand 0.8.5",
  "reqwest",
  "serde",
  "serde_json",
  "tokio",
- "tokio-stream",
  "tokio-util",
- "tonic 0.13.1",
  "tracing",
  "utils",
  "workspace_hack",
@@ -4357,7 +4305,6 @@ dependencies = [
  "hashlink",
  "hex",
  "hex-literal",
- "http 1.1.0",
  "http-utils",
  "humantime",
  "humantime-serde",
@@ -4374,7 +4321,6 @@ dependencies = [
  "pageserver_api",
  "pageserver_client",
  "pageserver_compaction",
- "pageserver_page_api",
  "pem",
  "pin-project-lite",
  "postgres-protocol",
@@ -4383,7 +4329,6 @@ dependencies = [
  "postgres_connection",
  "postgres_ffi",
  "postgres_initdb",
- "posthog_client_lite",
  "pprof",
  "pq_proto",
  "procfs",
@@ -4418,9 +4363,6 @@ dependencies = [
  "tokio-tar",
  "tokio-util",
  "toml_edit",
- "tonic 0.13.1",
- "tonic-reflection",
- "tower 0.5.2",
  "tracing",
  "tracing-utils",
  "twox-hash",
@@ -4513,14 +4455,9 @@ dependencies = [
 name = "pageserver_page_api"
 version = "0.1.0"
 dependencies = [
- "bytes",
- "pageserver_api",
- "postgres_ffi",
  "prost 0.13.5",
- "thiserror 1.0.69",
  "tonic 0.13.1",
  "tonic-build",
- "utils",
  "workspace_hack",
 ]
 
@@ -4961,16 +4898,11 @@ name = "posthog_client_lite"
 version = "0.1.0"
 dependencies = [
  "anyhow",
- "arc-swap",
  "reqwest",
  "serde",
  "serde_json",
  "sha2",
  "thiserror 1.0.69",
- "tokio",
- "tokio-util",
- "tracing",
- "tracing-utils",
  "workspace_hack",
 ]
 
@@ -5139,7 +5071,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "22505a5c94da8e3b7c2996394d1c933236c4d743e81a410bcca4e6989fc066a4"
 dependencies = [
  "bytes",
- "heck 0.5.0",
+ "heck",
  "itertools 0.12.1",
  "log",
  "multimap",
@@ -5160,7 +5092,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0c1318b19085f08681016926435853bbf7858f9c082d0999b80550ff5d9abe15"
 dependencies = [
  "bytes",
- "heck 0.5.0",
+ "heck",
  "itertools 0.12.1",
  "log",
  "multimap",
@@ -5285,7 +5217,7 @@ dependencies = [
  "postgres_backend",
  "pq_proto",
  "rand 0.8.5",
- "rand_distr 0.4.3",
+ "rand_distr",
  "rcgen",
  "redis",
  "regex",
@@ -5389,12 +5321,6 @@ dependencies = [
  "proc-macro2",
 ]
 
-[[package]]
-name = "r-efi"
-version = "5.2.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "74765f6d916ee2faa39bc8e68e4f3ed8949b48cccdac59983d287a7cb71ce9c5"
-
 [[package]]
 name = "rand"
 version = "0.7.3"
@@ -5419,16 +5345,6 @@ dependencies = [
  "rand_core 0.6.4",
 ]
 
-[[package]]
-name = "rand"
-version = "0.9.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9fbfd9d094a40bf3ae768db9361049ace4c0e04a4fd6b359518bd7b73a73dd97"
-dependencies = [
- "rand_chacha 0.9.0",
- "rand_core 0.9.3",
-]
-
 [[package]]
 name = "rand_chacha"
 version = "0.2.2"
@@ -5449,16 +5365,6 @@ dependencies = [
  "rand_core 0.6.4",
 ]
 
-[[package]]
-name = "rand_chacha"
-version = "0.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d3022b5f1df60f26e1ffddd6c66e8aa15de382ae63b3a0c1bfc0e4d3e3f325cb"
-dependencies = [
- "ppv-lite86",
- "rand_core 0.9.3",
-]
-
 [[package]]
 name = "rand_core"
 version = "0.5.1"
@@ -5477,15 +5383,6 @@ dependencies = [
  "getrandom 0.2.11",
 ]
 
-[[package]]
-name = "rand_core"
-version = "0.9.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "99d9a13982dcf210057a8a78572b2217b667c3beacbf3a0d8b454f6f82837d38"
-dependencies = [
- "getrandom 0.3.3",
-]
-
 [[package]]
 name = "rand_distr"
 version = "0.4.3"
@@ -5496,16 +5393,6 @@ dependencies = [
  "rand 0.8.5",
 ]
 
-[[package]]
-name = "rand_distr"
-version = "0.5.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6a8615d50dcf34fa31f7ab52692afec947c4dd0ab803cc87cb3b0b4570ff7463"
-dependencies = [
- "num-traits",
- "rand 0.9.1",
-]
-
 [[package]]
 name = "rand_hc"
 version = "0.2.0"
@@ -6992,7 +6879,7 @@ version = "0.26.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4c6bee85a5a24955dc440386795aa378cd9cf82acd5f764469152d2270e581be"
 dependencies = [
- "heck 0.5.0",
+ "heck",
  "proc-macro2",
  "quote",
  "rustversion",
@@ -7633,10 +7520,8 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7e581ba15a835f4d9ea06c55ab1bd4dce26fc53752c69a04aac00703bfb49ba9"
 dependencies = [
  "async-trait",
- "axum",
  "base64 0.22.1",
  "bytes",
- "h2 0.4.4",
  "http 1.1.0",
  "http-body 1.0.0",
  "http-body-util",
@@ -7647,7 +7532,6 @@ dependencies = [
  "pin-project",
  "prost 0.13.5",
  "rustls-native-certs 0.8.0",
- "socket2",
  "tokio",
  "tokio-rustls 0.26.2",
  "tokio-stream",
@@ -7671,19 +7555,6 @@ dependencies = [
  "syn 2.0.100",
 ]
 
-[[package]]
-name = "tonic-reflection"
-version = "0.13.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f9687bd5bfeafebdded2356950f278bba8226f0b32109537c4253406e09aafe1"
-dependencies = [
- "prost 0.13.5",
- "prost-types 0.13.3",
- "tokio",
- "tokio-stream",
- "tonic 0.13.1",
-]
-
 [[package]]
 name = "tower"
 version = "0.4.13"
@@ -8291,15 +8162,6 @@ version = "0.11.0+wasi-snapshot-preview1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
 
-[[package]]
-name = "wasi"
-version = "0.14.2+wasi-0.2.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9683f9a5a998d873c0d21fcbe3c083009670149a8fab228644b8bd36b2c48cb3"
-dependencies = [
- "wit-bindgen-rt",
-]
-
 [[package]]
 name = "wasite"
 version = "0.1.0"
@@ -8657,15 +8519,6 @@ dependencies = [
  "windows-sys 0.48.0",
 ]
 
-[[package]]
-name = "wit-bindgen-rt"
-version = "0.39.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6f42320e61fe2cfd34354ecb597f86f413484a798ba44a8ca1165c58d42da6c1"
-dependencies = [
- "bitflags 2.8.0",
-]
-
 [[package]]
 name = "workspace_hack"
 version = "0.1.0"
@@ -8673,8 +8526,6 @@ dependencies = [
  "ahash",
  "anstream",
  "anyhow",
- "axum",
- "axum-core",
  "base64 0.13.1",
  "base64 0.21.7",
  "base64ct",
@@ -8697,8 +8548,10 @@ dependencies = [
  "fail",
  "form_urlencoded",
  "futures-channel",
+ "futures-core",
  "futures-executor",
  "futures-io",
+ "futures-task",
  "futures-util",
  "generic-array",
  "getrandom 0.2.11",
@@ -8728,6 +8581,7 @@ dependencies = [
  "once_cell",
  "p256 0.13.2",
  "parquet",
+ "percent-encoding",
  "prettyplease",
  "proc-macro2",
  "prost 0.13.5",

Cargo.toml

@@ -44,7 +44,6 @@ members = [
     "libs/proxy/postgres-types2",
     "libs/proxy/tokio-postgres2",
     "endpoint_storage",
-    "pgxn/neon/communicator",
 ]
 
 [workspace.package]
@@ -200,8 +199,7 @@ tokio-tar = "0.3"
 tokio-util = { version = "0.7.10", features = ["io", "rt"] }
 toml = "0.8"
 toml_edit = "0.22"
-tonic = { version = "0.13.1", default-features = false, features = ["channel", "codegen", "prost", "router", "server", "tls-ring", "tls-native-roots"] }
-tonic-reflection = { version = "0.13.1", features = ["server"] }
+tonic = { version = "0.13.1", default-features = false, features = ["channel", "codegen", "prost", "tls-ring", "tls-native-roots"] }
 tower = { version = "0.5.2", default-features = false }
 tower-http = { version = "0.6.2", features = ["auth", "request-id", "trace"] }
 
@@ -248,11 +246,9 @@ azure_storage_blobs = { git = "https://github.com/neondatabase/azure-sdk-for-rus
 ## Local libraries
 compute_api = { version = "0.1", path = "./libs/compute_api/" }
 consumption_metrics = { version = "0.1", path = "./libs/consumption_metrics/" }
-desim = { version = "0.1", path = "./libs/desim" }
 endpoint_storage = { version = "0.0.1", path = "./endpoint_storage/" }
 http-utils = { version = "0.1", path = "./libs/http-utils/" }
 metrics = { version = "0.1", path = "./libs/metrics/" }
-neon-shmem = { version = "0.1", path = "./libs/neon-shmem/" }
 pageserver = { path = "./pageserver" }
 pageserver_api = { version = "0.1", path = "./libs/pageserver_api/" }
 pageserver_client = { path = "./pageserver/client" }
@@ -262,25 +258,24 @@ postgres_backend = { version = "0.1", path = "./libs/postgres_backend/" }
 postgres_connection = { version = "0.1", path = "./libs/postgres_connection/" }
 postgres_ffi = { version = "0.1", path = "./libs/postgres_ffi/" }
 postgres_initdb = { path = "./libs/postgres_initdb" }
-posthog_client_lite = { version = "0.1", path = "./libs/posthog_client_lite" }
 pq_proto = { version = "0.1", path = "./libs/pq_proto/" }
 remote_storage = { version = "0.1", path = "./libs/remote_storage/" }
 safekeeper_api = { version = "0.1", path = "./libs/safekeeper_api" }
 safekeeper_client = { path = "./safekeeper/client" }
+desim = { version = "0.1", path = "./libs/desim" }
 storage_broker = { version = "0.1", path = "./storage_broker/" } # Note: main broker code is inside the binary crate, so linking with the library shouldn't be heavy.
 storage_controller_client = { path = "./storage_controller/client" }
 tenant_size_model = { version = "0.1", path = "./libs/tenant_size_model/" }
 tracing-utils = { version = "0.1", path = "./libs/tracing-utils/" }
 utils = { version = "0.1", path = "./libs/utils/" }
 vm_monitor = { version = "0.1", path = "./libs/vm_monitor/" }
-wal_decoder = { version = "0.1", path = "./libs/wal_decoder" }
 walproposer = { version = "0.1", path = "./libs/walproposer/" }
+wal_decoder = { version = "0.1", path = "./libs/wal_decoder" }
 
 ## Common library dependency
 workspace_hack = { version = "0.1", path = "./workspace_hack/" }
 
 ## Build dependencies
-cbindgen = "0.28.0"
 criterion = "0.5.1"
 rcgen = "0.13"
 rstest = "0.18"

Makefile

@@ -18,12 +18,10 @@ ifeq ($(BUILD_TYPE),release)
 	PG_LDFLAGS = $(LDFLAGS)
 	# Unfortunately, `--profile=...` is a nightly feature
 	CARGO_BUILD_FLAGS += --release
-	NEON_CARGO_ARTIFACT_TARGET_DIR = $(ROOT_PROJECT_DIR)/target/release
 else ifeq ($(BUILD_TYPE),debug)
 	PG_CONFIGURE_OPTS = --enable-debug --with-openssl --enable-cassert --enable-depend
 	PG_CFLAGS += -O0 -g3 $(CFLAGS)
 	PG_LDFLAGS = $(LDFLAGS)
-	NEON_CARGO_ARTIFACT_TARGET_DIR = $(ROOT_PROJECT_DIR)/target/debug
 else
 	$(error Bad build type '$(BUILD_TYPE)', see Makefile for options)
 endif
@@ -182,16 +180,11 @@ postgres-check-%: postgres-%
 
 .PHONY: neon-pg-ext-%
 neon-pg-ext-%: postgres-%
-	+@echo "Compiling communicator $*"
-	$(CARGO_CMD_PREFIX) cargo build -p communicator $(CARGO_BUILD_FLAGS)
-
 	+@echo "Compiling neon $*"
 	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-$*
 	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
-		LIBCOMMUNICATOR_PATH=$(NEON_CARGO_ARTIFACT_TARGET_DIR) \
 		-C $(POSTGRES_INSTALL_DIR)/build/neon-$* \
 		-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile install
-
 	+@echo "Compiling neon_walredo $*"
 	mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$*
 	$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \

build-tools.Dockerfile

@@ -310,13 +310,13 @@ RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux
     . "$HOME/.cargo/env" && \
     cargo --version && rustup --version && \
     rustup component add llvm-tools rustfmt clippy && \
-    cargo install rustfilt            --version ${RUSTFILT_VERSION} --locked && \
-    cargo install cargo-hakari        --version ${CARGO_HAKARI_VERSION} --locked && \
-    cargo install cargo-deny          --version ${CARGO_DENY_VERSION} --locked && \
-    cargo install cargo-hack          --version ${CARGO_HACK_VERSION} --locked && \
-    cargo install cargo-nextest       --version ${CARGO_NEXTEST_VERSION} --locked && \
-    cargo install cargo-chef          --version ${CARGO_CHEF_VERSION} --locked && \
-    cargo install diesel_cli          --version ${CARGO_DIESEL_CLI_VERSION} --locked \
+    cargo install rustfilt            --version ${RUSTFILT_VERSION} && \
+    cargo install cargo-hakari        --version ${CARGO_HAKARI_VERSION} && \
+    cargo install cargo-deny --locked --version ${CARGO_DENY_VERSION} && \
+    cargo install cargo-hack          --version ${CARGO_HACK_VERSION} && \
+    cargo install cargo-nextest       --version ${CARGO_NEXTEST_VERSION} && \
+    cargo install cargo-chef --locked --version ${CARGO_CHEF_VERSION} && \
+    cargo install diesel_cli          --version ${CARGO_DIESEL_CLI_VERSION} \
                                       --features postgres-bundled --no-default-features && \
     rm -rf /home/nonroot/.cargo/registry && \
     rm -rf /home/nonroot/.cargo/git

compute/compute-node.Dockerfile

@@ -297,7 +297,6 @@ RUN ./autogen.sh && \
     ./configure --with-sfcgal=/usr/local/bin/sfcgal-config && \
     make -j $(getconf _NPROCESSORS_ONLN) && \
     make -j $(getconf _NPROCESSORS_ONLN) install && \
-    make staged-install && \
     cd extensions/postgis && \
     make clean && \
     make -j $(getconf _NPROCESSORS_ONLN) install && \
@@ -603,7 +602,7 @@ RUN case "${PG_VERSION:?}" in \
         ;; \
     esac && \
 	wget https://github.com/knizhnik/online_advisor/archive/refs/tags/1.0.tar.gz -O online_advisor.tar.gz && \
-    echo "37dcadf8f7cc8d6cc1f8831276ee245b44f1b0274f09e511e47a67738ba9ed0f online_advisor.tar.gz" | sha256sum --check && \
+    echo "059b7d9e5a90013a58bdd22e9505b88406ce05790675eb2d8434e5b215652d54 online_advisor.tar.gz" | sha256sum --check && \
     mkdir online_advisor-src && cd online_advisor-src && tar xzf ../online_advisor.tar.gz --strip-components=1 -C .
 
 FROM pg-build AS online_advisor-build
@@ -1181,14 +1180,14 @@ RUN cd exts/rag && \
 RUN cd exts/rag_bge_small_en_v15 && \
     sed -i 's/pgrx = "0.14.1"/pgrx = { version = "0.14.1", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
     ORT_LIB_LOCATION=/ext-src/onnxruntime-src/build/Linux \
-        REMOTE_ONNX_URL=http://pg-ext-s3-gateway.pg-ext-s3-gateway.svc.cluster.local/pgrag-data/bge_small_en_v15.onnx \
+        REMOTE_ONNX_URL=http://pg-ext-s3-gateway/pgrag-data/bge_small_en_v15.onnx \
         cargo pgrx install --release --features remote_onnx && \
     echo "trusted = true" >> /usr/local/pgsql/share/extension/rag_bge_small_en_v15.control
 
 RUN cd exts/rag_jina_reranker_v1_tiny_en && \
     sed -i 's/pgrx = "0.14.1"/pgrx = { version = "0.14.1", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
     ORT_LIB_LOCATION=/ext-src/onnxruntime-src/build/Linux \
-        REMOTE_ONNX_URL=http://pg-ext-s3-gateway.pg-ext-s3-gateway.svc.cluster.local/pgrag-data/jina_reranker_v1_tiny_en.onnx \
+        REMOTE_ONNX_URL=http://pg-ext-s3-gateway/pgrag-data/jina_reranker_v1_tiny_en.onnx \
         cargo pgrx install --release --features remote_onnx && \
     echo "trusted = true" >> /usr/local/pgsql/share/extension/rag_jina_reranker_v1_tiny_en.control
 
@@ -1843,27 +1842,12 @@ RUN make PG_VERSION="${PG_VERSION:?}" -C compute
 
 FROM pg-build AS extension-tests
 ARG PG_VERSION
-# This is required for the PostGIS test
-RUN apt-get update && case $DEBIAN_VERSION in \
-      bullseye) \
-        apt-get install -y libproj19 libgdal28 time; \
-      ;; \
-      bookworm) \
-        apt-get install -y libgdal32 libproj25 time; \
-      ;; \
-      *) \
-        echo "Unknown Debian version ${DEBIAN_VERSION}" && exit 1 \
-      ;; \
-    esac
-
 COPY docker-compose/ext-src/ /ext-src/
 
 COPY --from=pg-build /postgres /postgres
-COPY --from=postgis-build /usr/local/pgsql/ /usr/local/pgsql/
-COPY --from=postgis-build /ext-src/postgis-src /ext-src/postgis-src
-COPY --from=postgis-build /sfcgal/* /usr
+#COPY --from=postgis-src /ext-src/ /ext-src/
 COPY --from=plv8-src /ext-src/ /ext-src/
-COPY --from=h3-pg-src /ext-src/h3-pg-src /ext-src/h3-pg-src
+#COPY --from=h3-pg-src /ext-src/ /ext-src/
 COPY --from=postgresql-unit-src /ext-src/ /ext-src/
 COPY --from=pgvector-src /ext-src/ /ext-src/
 COPY --from=pgjwt-src /ext-src/ /ext-src/
@@ -1902,7 +1886,6 @@ COPY compute/patches/pg_repack.patch /ext-src
 RUN cd /ext-src/pg_repack-src && patch -p1 </ext-src/pg_repack.patch && rm -f /ext-src/pg_repack.patch
 
 COPY --chmod=755 docker-compose/run-tests.sh /run-tests.sh
-RUN echo /usr/local/pgsql/lib > /etc/ld.so.conf.d/00-neon.conf && /sbin/ldconfig
 RUN apt-get update && apt-get install -y libtap-parser-sourcehandler-pgtap-perl jq \
    && apt clean && rm -rf /ext-src/*.tar.gz /ext-src/*.patch /var/lib/apt/lists/*
 ENV PATH=/usr/local/pgsql/bin:$PATH

compute/manifest.yaml

@@ -1,121 +0,0 @@
-pg_settings:
-  # Common settings for primaries and replicas of all versions.
-  common:
-    # Check for client disconnection every 1 minute. By default, Postgres will detect the
-    # loss of the connection only at the next interaction with the socket, when it waits
-    # for, receives or sends data, so it will likely waste resources till the end of the
-    # query execution. There should be no drawbacks in setting this for everyone, so enable
-    # it by default. If anyone will complain, we can allow editing it.
-    # https://www.postgresql.org/docs/16/runtime-config-connection.html#GUC-CLIENT-CONNECTION-CHECK-INTERVAL
-    client_connection_check_interval: "60000" # 1 minute
-    # ---- IO ---- 
-    effective_io_concurrency: "20"
-    maintenance_io_concurrency: "100"
-    fsync: "off"
-    hot_standby: "off"
-    # We allow users to change this if needed, but by default we
-    # just don't want to see long-lasting idle transactions, as they
-    # prevent activity monitor from suspending projects.
-    idle_in_transaction_session_timeout: "300000" # 5 minutes
-    listen_addresses: "*"
-    # --- LOGGING ---- helps investigations
-    log_connections: "on"
-    log_disconnections: "on"
-    # 1GB, unit is KB
-    log_temp_files: "1048576"
-    # Disable dumping customer data to logs, both to increase data privacy
-    # and to reduce the amount the logs.
-    log_error_verbosity: "terse"
-    log_min_error_statement: "panic"
-    max_connections: "100"
-    # --- WAL ---
-    # - flush lag is the max amount of WAL that has been generated but not yet stored
-    # to disk in the page server. A smaller value means less delay after a pageserver
-    # restart, but if you set it too small you might again need to slow down writes if the
-    # pageserver cannot flush incoming WAL to disk fast enough. This must be larger
-    # than the pageserver's checkpoint interval, currently 1 GB! Otherwise you get a
-    # a deadlock where the compute node refuses to generate more WAL before the
-    # old WAL has been uploaded to S3, but the pageserver is waiting for more WAL
-    # to be generated before it is uploaded to S3.
-    max_replication_flush_lag: "10GB"
-    max_replication_slots: "10"
-    # Backpressure configuration:
-    # - write lag is the max amount of WAL that has been generated by Postgres but not yet
-    # processed by the page server. Making this smaller reduces the worst case latency
-    # of a GetPage request, if you request a page that was recently modified. On the other
-    # hand, if this is too small, the compute node might need to wait on a write if there is a
-    # hiccup in the network or page server so that the page server has temporarily fallen
-    # behind.
-    #
-    # Previously it was set to 500 MB, but it caused compute being unresponsive under load
-    # https://github.com/neondatabase/neon/issues/2028
-    max_replication_write_lag: "500MB"
-    max_wal_senders: "10"
-    # A Postgres checkpoint is cheap in storage, as doesn't involve any significant amount
-    # of real I/O. Only the SLRU buffers and some other small files are flushed to disk.
-    # However, as long as we have full_page_writes=on, page updates after a checkpoint
-    # include full-page images which bloats the WAL. So may want to bump max_wal_size to
-    # reduce the WAL bloating, but at the same it will increase pg_wal directory size on
-    # compute and can lead to out of disk error on k8s nodes.
-    max_wal_size: "1024"
-    wal_keep_size: "0"
-    wal_level: "replica"
-    # Reduce amount of WAL generated by default.
-    wal_log_hints: "off"
-    # - without wal_sender_timeout set we don't get feedback messages,
-    # required for backpressure.
-    wal_sender_timeout: "10000"
-    # We have some experimental extensions, which we don't want users to install unconsciously.
-    # To install them, users would need to set the `neon.allow_unstable_extensions` setting.
-    # There are two of them currently:
-    # - `pgrag` - https://github.com/neondatabase-labs/pgrag - extension is actually called just `rag`,
-    #                                                          and two dependencies:
-    #                                                          - `rag_bge_small_en_v15`
-    #                                                          - `rag_jina_reranker_v1_tiny_en`
-    # - `pg_mooncake` - https://github.com/Mooncake-Labs/pg_mooncake/  
-    neon.unstable_extensions: "rag,rag_bge_small_en_v15,rag_jina_reranker_v1_tiny_en,pg_mooncake,anon"
-    neon.protocol_version: "3"
-    password_encryption: "scram-sha-256"
-    # This is important to prevent Postgres from trying to perform
-    # a local WAL redo after backend crash. It should exit and let
-    # the systemd or k8s to do a fresh startup with compute_ctl.
-    restart_after_crash: "off"
-    # By default 3. We have the following persistent connections in the VM:
-    # * compute_activity_monitor (from compute_ctl)
-    # * postgres-exporter (metrics collector; it has 2 connections)
-    # * sql_exporter (metrics collector; we have 2 instances [1 for us & users; 1 for autoscaling])
-    # * vm-monitor (to query & change file cache size)
-    # i.e. total of 6. Let's reserve 7, so there's still at least one left over.
-    superuser_reserved_connections: "7"
-    synchronous_standby_names: "walproposer"
-
-  replica:
-    hot_standby: "on"
-
-  per_version:
-    17:
-      common:
-        # PostgreSQL 17 has a new IO system called "read stream", which can combine IOs up to some
-        # size. It still has some issues with readahead, though, so we default to disabled/
-        # "no combining of IOs" to make sure we get the maximum prefetch depth.
-        # See also: https://github.com/neondatabase/neon/pull/9860
-        io_combine_limit: "1"
-      replica:
-        # prefetching of blocks referenced in WAL doesn't make sense for us
-        # Neon hot standby ignores pages that are not in the shared_buffers
-        recovery_prefetch: "off"
-    16:
-      common:
-      replica:
-        # prefetching of blocks referenced in WAL doesn't make sense for us
-        # Neon hot standby ignores pages that are not in the shared_buffers
-        recovery_prefetch: "off"
-    15:
-      common:
-      replica:
-        # prefetching of blocks referenced in WAL doesn't make sense for us
-        # Neon hot standby ignores pages that are not in the shared_buffers
-        recovery_prefetch: "off"
-    14:
-      common:
-      replica:

compute_tools/src/bin/compute_ctl.rs

@@ -40,7 +40,7 @@ use std::sync::mpsc;
 use std::thread;
 use std::time::Duration;
 
-use anyhow::{Context, Result, bail};
+use anyhow::{Context, Result};
 use clap::Parser;
 use compute_api::responses::ComputeConfig;
 use compute_tools::compute::{
@@ -57,15 +57,31 @@ use tracing::{error, info};
 use url::Url;
 use utils::failpoint_support;
 
-#[derive(Debug, Parser)]
+// Compatibility hack: if the control plane specified any remote-ext-config
+// use the default value for extension storage proxy gateway.
+// Remove this once the control plane is updated to pass the gateway URL
+fn parse_remote_ext_base_url(arg: &str) -> Result<String> {
+    const FALLBACK_PG_EXT_GATEWAY_BASE_URL: &str =
+        "http://pg-ext-s3-gateway.pg-ext-s3-gateway.svc.cluster.local";
+
+    Ok(if arg.starts_with("http") {
+        arg
+    } else {
+        FALLBACK_PG_EXT_GATEWAY_BASE_URL
+    }
+    .to_owned())
+}
+
+#[derive(Parser)]
 #[command(rename_all = "kebab-case")]
 struct Cli {
     #[arg(short = 'b', long, default_value = "postgres", env = "POSTGRES_PATH")]
     pub pgbin: String,
 
     /// The base URL for the remote extension storage proxy gateway.
-    #[arg(short = 'r', long, value_parser = Self::parse_remote_ext_base_url)]
-    pub remote_ext_base_url: Option<Url>,
+    /// Should be in the form of `http(s)://<gateway-hostname>[:<port>]`.
+    #[arg(short = 'r', long, value_parser = parse_remote_ext_base_url, alias = "remote-ext-config")]
+    pub remote_ext_base_url: Option<String>,
 
     /// The port to bind the external listening HTTP server to. Clients running
     /// outside the compute will talk to the compute through this port. Keep
@@ -120,29 +136,6 @@ struct Cli {
         requires = "compute-id"
     )]
     pub control_plane_uri: Option<String>,
-
-    /// Interval in seconds for collecting installed extensions statistics
-    #[arg(long, default_value = "3600")]
-    pub installed_extensions_collection_interval: u64,
-}
-
-impl Cli {
-    /// Parse a URL from an argument. By default, this isn't necessary, but we
-    /// want to do some sanity checking.
-    fn parse_remote_ext_base_url(value: &str) -> Result<Url> {
-        // Remove extra trailing slashes, and add one. We use Url::join() later
-        // when downloading remote extensions. If the base URL is something like
-        // http://example.com/pg-ext-s3-gateway, and join() is called with
-        // something like "xyz", the resulting URL is http://example.com/xyz.
-        let value = value.trim_end_matches('/').to_owned() + "/";
-        let url = Url::parse(&value)?;
-
-        if url.query_pairs().count() != 0 {
-            bail!("parameters detected in remote extensions base URL")
-        }
-
-        Ok(url)
-    }
 }
 
 fn main() -> Result<()> {
@@ -186,7 +179,6 @@ fn main() -> Result<()> {
             cgroup: cli.cgroup,
             #[cfg(target_os = "linux")]
             vm_monitor_addr: cli.vm_monitor_addr,
-            installed_extensions_collection_interval: cli.installed_extensions_collection_interval,
         },
         config,
     )?;
@@ -271,8 +263,7 @@ fn handle_exit_signal(sig: i32) {
 
 #[cfg(test)]
 mod test {
-    use clap::{CommandFactory, Parser};
-    use url::Url;
+    use clap::CommandFactory;
 
     use super::Cli;
 
@@ -282,41 +273,16 @@ mod test {
     }
 
     #[test]
-    fn verify_remote_ext_base_url() {
-        let cli = Cli::parse_from([
-            "compute_ctl",
-            "--pgdata=test",
-            "--connstr=test",
-            "--compute-id=test",
-            "--remote-ext-base-url",
-            "https://example.com/subpath",
-        ]);
-        assert_eq!(
-            cli.remote_ext_base_url.unwrap(),
-            Url::parse("https://example.com/subpath/").unwrap()
-        );
+    fn parse_pg_ext_gateway_base_url() {
+        let arg = "http://pg-ext-s3-gateway2";
+        let result = super::parse_remote_ext_base_url(arg).unwrap();
+        assert_eq!(result, arg);
 
-        let cli = Cli::parse_from([
-            "compute_ctl",
-            "--pgdata=test",
-            "--connstr=test",
-            "--compute-id=test",
-            "--remote-ext-base-url",
-            "https://example.com//",
-        ]);
+        let arg = "pg-ext-s3-gateway";
+        let result = super::parse_remote_ext_base_url(arg).unwrap();
         assert_eq!(
-            cli.remote_ext_base_url.unwrap(),
-            Url::parse("https://example.com").unwrap()
+            result,
+            "http://pg-ext-s3-gateway.pg-ext-s3-gateway.svc.cluster.local"
         );
-
-        Cli::try_parse_from([
-            "compute_ctl",
-            "--pgdata=test",
-            "--connstr=test",
-            "--compute-id=test",
-            "--remote-ext-base-url",
-            "https://example.com?hello=world",
-        ])
-        .expect_err("URL parameters are not allowed");
     }
 }

compute_tools/src/bin/fast_import.rs

@@ -339,8 +339,6 @@ async fn run_dump_restore(
     destination_connstring: String,
 ) -> Result<(), anyhow::Error> {
     let dumpdir = workdir.join("dumpdir");
-    let num_jobs = num_cpus::get().to_string();
-    info!("using {num_jobs} jobs for dump/restore");
 
     let common_args = [
         // schema mapping (prob suffices to specify them on one side)
@@ -356,7 +354,7 @@ async fn run_dump_restore(
         "directory".to_string(),
         // concurrency
         "--jobs".to_string(),
-        num_jobs,
+        num_cpus::get().to_string(),
         // progress updates
         "--verbose".to_string(),
     ];

compute_tools/src/compute.rs

@@ -3,7 +3,7 @@ use chrono::{DateTime, Utc};
 use compute_api::privilege::Privilege;
 use compute_api::responses::{
     ComputeConfig, ComputeCtlConfig, ComputeMetrics, ComputeStatus, LfcOffloadState,
-    LfcPrewarmState, TlsConfig,
+    LfcPrewarmState,
 };
 use compute_api::spec::{
     ComputeAudit, ComputeFeature, ComputeMode, ComputeSpec, ExtVersion, PgIdent,
@@ -31,7 +31,6 @@ use std::time::{Duration, Instant};
 use std::{env, fs};
 use tokio::spawn;
 use tracing::{Instrument, debug, error, info, instrument, warn};
-use url::Url;
 use utils::id::{TenantId, TimelineId};
 use utils::lsn::Lsn;
 use utils::measured_stream::MeasuredReader;
@@ -97,10 +96,7 @@ pub struct ComputeNodeParams {
     pub internal_http_port: u16,
 
     /// the address of extension storage proxy gateway
-    pub remote_ext_base_url: Option<Url>,
-
-    /// Interval for installed extensions collection
-    pub installed_extensions_collection_interval: u64,
+    pub remote_ext_base_url: Option<String>,
 }
 
 /// Compute node info shared across several `compute_ctl` threads.
@@ -396,7 +392,7 @@ impl ComputeNode {
         // because QEMU will already have its memory allocated from the host, and
         // the necessary binaries will already be cached.
         if cli_spec.is_none() {
-            this.prewarm_postgres_vm_memory()?;
+            this.prewarm_postgres()?;
         }
 
         // Set the up metric with Empty status before starting the HTTP server.
@@ -603,8 +599,6 @@ impl ComputeNode {
             });
         }
 
-        let tls_config = self.tls_config(&pspec.spec);
-
         // If there are any remote extensions in shared_preload_libraries, start downloading them
         if pspec.spec.remote_extensions.is_some() {
             let (this, spec) = (self.clone(), pspec.spec.clone());
@@ -661,7 +655,7 @@ impl ComputeNode {
             info!("tuning pgbouncer");
 
             let pgbouncer_settings = pgbouncer_settings.clone();
-            let tls_config = tls_config.clone();
+            let tls_config = self.compute_ctl_config.tls.clone();
 
             // Spawn a background task to do the tuning,
             // so that we don't block the main thread that starts Postgres.
@@ -680,10 +674,7 @@ impl ComputeNode {
 
             // Spawn a background task to do the configuration,
             // so that we don't block the main thread that starts Postgres.
-
-            let mut local_proxy = local_proxy.clone();
-            local_proxy.tls = tls_config.clone();
-
+            let local_proxy = local_proxy.clone();
             let _handle = tokio::spawn(async move {
                 if let Err(err) = local_proxy::configure(&local_proxy) {
                     error!("error while configuring local_proxy: {err:?}");
@@ -704,18 +695,25 @@ impl ComputeNode {
                 let log_directory_path = Path::new(&self.params.pgdata).join("log");
                 let log_directory_path = log_directory_path.to_string_lossy().to_string();
 
-                // Add project_id,endpoint_id to identify the logs.
+                // Add project_id,endpoint_id tag to identify the logs.
                 //
                 // These ids are passed from cplane,
-                let endpoint_id = pspec.spec.endpoint_id.as_deref().unwrap_or("");
-                let project_id = pspec.spec.project_id.as_deref().unwrap_or("");
+                // for backwards compatibility (old computes that don't have them),
+                // we set them to None.
+                // TODO: Clean up this code when all computes have them.
+                let tag: Option<String> = match (
+                    pspec.spec.project_id.as_deref(),
+                    pspec.spec.endpoint_id.as_deref(),
+                ) {
+                    (Some(project_id), Some(endpoint_id)) => {
+                        Some(format!("{project_id}/{endpoint_id}"))
+                    }
+                    (Some(project_id), None) => Some(format!("{project_id}/None")),
+                    (None, Some(endpoint_id)) => Some(format!("None,{endpoint_id}")),
+                    (None, None) => None,
+                };
 
-                configure_audit_rsyslog(
-                    log_directory_path.clone(),
-                    endpoint_id,
-                    project_id,
-                    &remote_endpoint,
-                )?;
+                configure_audit_rsyslog(log_directory_path.clone(), tag, &remote_endpoint)?;
 
                 // Launch a background task to clean up the audit logs
                 launch_pgaudit_gc(log_directory_path);
@@ -751,7 +749,17 @@ impl ComputeNode {
 
             let conf = self.get_tokio_conn_conf(None);
             tokio::task::spawn(async {
-                let _ = installed_extensions(conf).await;
+                let res = get_installed_extensions(conf).await;
+                match res {
+                    Ok(extensions) => {
+                        info!(
+                            "[NEON_EXT_STAT] {}",
+                            serde_json::to_string(&extensions)
+                                .expect("failed to serialize extensions list")
+                        );
+                    }
+                    Err(err) => error!("could not get installed extensions: {err:?}"),
+                }
             });
         }
 
@@ -781,10 +789,7 @@ impl ComputeNode {
         // Log metrics so that we can search for slow operations in logs
         info!(?metrics, postmaster_pid = %postmaster_pid, "compute start finished");
 
-        // Spawn the extension stats background task
-        self.spawn_extension_stats_task();
-
-        if pspec.spec.autoprewarm {
+        if pspec.spec.prewarm_lfc_on_startup {
             self.prewarm_lfc();
         }
         Ok(())
@@ -1210,15 +1215,13 @@ impl ComputeNode {
         let spec = &pspec.spec;
         let pgdata_path = Path::new(&self.params.pgdata);
 
-        let tls_config = self.tls_config(&pspec.spec);
-
         // Remove/create an empty pgdata directory and put configuration there.
         self.create_pgdata()?;
         config::write_postgres_conf(
             pgdata_path,
             &pspec.spec,
             self.params.internal_http_port,
-            tls_config,
+            &self.compute_ctl_config.tls,
         )?;
 
         // Syncing safekeepers is only safe with primary nodes: if a primary
@@ -1314,8 +1317,8 @@ impl ComputeNode {
     }
 
     /// Start and stop a postgres process to warm up the VM for startup.
-    pub fn prewarm_postgres_vm_memory(&self) -> Result<()> {
-        info!("prewarming VM memory");
+    pub fn prewarm_postgres(&self) -> Result<()> {
+        info!("prewarming");
 
         // Create pgdata
         let pgdata = &format!("{}.warmup", self.params.pgdata);
@@ -1357,7 +1360,7 @@ impl ComputeNode {
         kill(pm_pid, Signal::SIGQUIT)?;
         info!("sent SIGQUIT signal");
         pg.wait()?;
-        info!("done prewarming vm memory");
+        info!("done prewarming");
 
         // clean up
         let _ok = fs::remove_dir_all(pgdata);
@@ -1543,22 +1546,14 @@ impl ComputeNode {
                 .clone(),
         );
 
-        let mut tls_config = None::<TlsConfig>;
-        if spec.features.contains(&ComputeFeature::TlsExperimental) {
-            tls_config = self.compute_ctl_config.tls.clone();
-        }
-
         let max_concurrent_connections = self.max_service_connections(compute_state, &spec);
 
         // Merge-apply spec & changes to PostgreSQL state.
         self.apply_spec_sql(spec.clone(), conf.clone(), max_concurrent_connections)?;
 
         if let Some(local_proxy) = &spec.clone().local_proxy_config {
-            let mut local_proxy = local_proxy.clone();
-            local_proxy.tls = tls_config.clone();
-
             info!("configuring local_proxy");
-            local_proxy::configure(&local_proxy).context("apply_config local_proxy")?;
+            local_proxy::configure(local_proxy).context("apply_config local_proxy")?;
         }
 
         // Run migrations separately to not hold up cold starts
@@ -1610,13 +1605,11 @@ impl ComputeNode {
     pub fn reconfigure(&self) -> Result<()> {
         let spec = self.state.lock().unwrap().pspec.clone().unwrap().spec;
 
-        let tls_config = self.tls_config(&spec);
-
         if let Some(ref pgbouncer_settings) = spec.pgbouncer_settings {
             info!("tuning pgbouncer");
 
             let pgbouncer_settings = pgbouncer_settings.clone();
-            let tls_config = tls_config.clone();
+            let tls_config = self.compute_ctl_config.tls.clone();
 
             // Spawn a background task to do the tuning,
             // so that we don't block the main thread that starts Postgres.
@@ -1634,7 +1627,7 @@ impl ComputeNode {
             // Spawn a background task to do the configuration,
             // so that we don't block the main thread that starts Postgres.
             let mut local_proxy = local_proxy.clone();
-            local_proxy.tls = tls_config.clone();
+            local_proxy.tls = self.compute_ctl_config.tls.clone();
             tokio::spawn(async move {
                 if let Err(err) = local_proxy::configure(&local_proxy) {
                     error!("error while configuring local_proxy: {err:?}");
@@ -1652,7 +1645,7 @@ impl ComputeNode {
             pgdata_path,
             &spec,
             self.params.internal_http_port,
-            tls_config,
+            &self.compute_ctl_config.tls,
         )?;
 
         if !spec.skip_pg_catalog_updates {
@@ -1772,14 +1765,6 @@ impl ComputeNode {
         }
     }
 
-    pub fn tls_config(&self, spec: &ComputeSpec) -> &Option<TlsConfig> {
-        if spec.features.contains(&ComputeFeature::TlsExperimental) {
-            &self.compute_ctl_config.tls
-        } else {
-            &None::<TlsConfig>
-        }
-    }
-
     /// Update the `last_active` in the shared state, but ensure that it's a more recent one.
     pub fn update_last_active(&self, last_active: Option<DateTime<Utc>>) {
         let mut state = self.state.lock().unwrap();
@@ -2214,41 +2199,6 @@ LIMIT 100",
             info!("Pageserver config changed");
         }
     }
-
-    pub fn spawn_extension_stats_task(&self) {
-        let conf = self.tokio_conn_conf.clone();
-        let installed_extensions_collection_interval =
-            self.params.installed_extensions_collection_interval;
-        tokio::spawn(async move {
-            // An initial sleep is added to ensure that two collections don't happen at the same time.
-            // The first collection happens during compute startup.
-            tokio::time::sleep(tokio::time::Duration::from_secs(
-                installed_extensions_collection_interval,
-            ))
-            .await;
-            let mut interval = tokio::time::interval(tokio::time::Duration::from_secs(
-                installed_extensions_collection_interval,
-            ));
-            loop {
-                interval.tick().await;
-                let _ = installed_extensions(conf.clone()).await;
-            }
-        });
-    }
-}
-
-pub async fn installed_extensions(conf: tokio_postgres::Config) -> Result<()> {
-    let res = get_installed_extensions(conf).await;
-    match res {
-        Ok(extensions) => {
-            info!(
-                "[NEON_EXT_STAT] {}",
-                serde_json::to_string(&extensions).expect("failed to serialize extensions list")
-            );
-        }
-        Err(err) => error!("could not get installed extensions: {err:?}"),
-    }
-    Ok(())
 }
 
 pub fn forward_termination_signal() {

compute_tools/src/config_template/compute_audit_rsyslog_template.conf

@@ -2,24 +2,10 @@
 module(load="imfile")
 
 # Input configuration for log files in the specified directory
-# The messages can be multiline. The start of the message is a timestamp
-# in "%Y-%m-%d %H:%M:%S.%3N GMT" (so timezone hardcoded).
-# Replace log_directory with the directory containing the log files
-input(type="imfile" File="{log_directory}/*.log"
-  Tag="pgaudit_log" Severity="info" Facility="local5"
-  startmsg.regex="^[[:digit:]]{{4}}-[[:digit:]]{{2}}-[[:digit:]]{{2}} [[:digit:]]{{2}}:[[:digit:]]{{2}}:[[:digit:]]{{2}}.[[:digit:]]{{3}} GMT,")
-
+# Replace {log_directory} with the directory containing the log files
+input(type="imfile" File="{log_directory}/*.log" Tag="{tag}" Severity="info" Facility="local0")
 # the directory to store rsyslog state files
 global(workDirectory="/var/log/rsyslog")
 
-# Construct json, endpoint_id and project_id as additional metadata
-set $.json_log!endpoint_id = "{endpoint_id}";
-set $.json_log!project_id = "{project_id}";
-set $.json_log!msg = $msg;
-
-# Template suitable for rfc5424 syslog format
-template(name="PgAuditLog" type="string"
-    string="<%PRI%>1 %TIMESTAMP:::date-rfc3339% %HOSTNAME% - - - - %$.json_log%")
-
-# Forward to remote syslog receiver (@@<hostname>:<port>;format
-local5.info @@{remote_endpoint};PgAuditLog
+# Forward logs to remote syslog server
+*.* @@{remote_endpoint}

compute_tools/src/extension_server.rs

@@ -83,7 +83,6 @@ use reqwest::StatusCode;
 use tar::Archive;
 use tracing::info;
 use tracing::log::warn;
-use url::Url;
 use zstd::stream::read::Decoder;
 
 use crate::metrics::{REMOTE_EXT_REQUESTS_TOTAL, UNKNOWN_HTTP_STATUS};
@@ -159,7 +158,7 @@ fn parse_pg_version(human_version: &str) -> PostgresMajorVersion {
 pub async fn download_extension(
     ext_name: &str,
     ext_path: &RemotePath,
-    remote_ext_base_url: &Url,
+    remote_ext_base_url: &str,
     pgbin: &str,
 ) -> Result<u64> {
     info!("Download extension {:?} from {:?}", ext_name, ext_path);
@@ -271,14 +270,10 @@ pub fn create_control_files(remote_extensions: &RemoteExtSpec, pgbin: &str) {
 }
 
 // Do request to extension storage proxy, e.g.,
-// curl http://pg-ext-s3-gateway.pg-ext-s3-gateway.svc.cluster.local/latest/v15/extensions/anon.tar.zst
+// curl http://pg-ext-s3-gateway/latest/v15/extensions/anon.tar.zst
 // using HTTP GET and return the response body as bytes.
-async fn download_extension_tar(remote_ext_base_url: &Url, ext_path: &str) -> Result<Bytes> {
-    let uri = remote_ext_base_url.join(ext_path).with_context(|| {
-        format!(
-            "failed to create the remote extension URI for {ext_path} using {remote_ext_base_url}"
-        )
-    })?;
+async fn download_extension_tar(remote_ext_base_url: &str, ext_path: &str) -> Result<Bytes> {
+    let uri = format!("{}/{}", remote_ext_base_url, ext_path);
     let filename = Path::new(ext_path)
         .file_name()
         .unwrap_or_else(|| std::ffi::OsStr::new("unknown"))
@@ -288,7 +283,7 @@ async fn download_extension_tar(remote_ext_base_url: &Url, ext_path: &str) -> Re
 
     info!("Downloading extension file '{}' from uri {}", filename, uri);
 
-    match do_extension_server_request(uri).await {
+    match do_extension_server_request(&uri).await {
         Ok(resp) => {
             info!("Successfully downloaded remote extension data {}", ext_path);
             REMOTE_EXT_REQUESTS_TOTAL
@@ -307,7 +302,7 @@ async fn download_extension_tar(remote_ext_base_url: &Url, ext_path: &str) -> Re
 
 // Do a single remote extensions server request.
 // Return result or (error message + stringified status code) in case of any failures.
-async fn do_extension_server_request(uri: Url) -> Result<Bytes, (String, String)> {
+async fn do_extension_server_request(uri: &str) -> Result<Bytes, (String, String)> {
     let resp = reqwest::get(uri).await.map_err(|e| {
         (
             format!(

compute_tools/src/http/mod.rs

@@ -48,9 +48,11 @@ impl JsonResponse {
 
     /// Create an error response related to the compute being in an invalid state
     pub(self) fn invalid_status(status: ComputeStatus) -> Response {
-        Self::error(
+        Self::create_response(
             StatusCode::PRECONDITION_FAILED,
-            format!("invalid compute status: {status}"),
+            &GenericAPIError {
+                error: format!("invalid compute status: {status}"),
+            },
         )
     }
 }

compute_tools/src/http/routes/configure.rs

@@ -22,7 +22,7 @@ pub(in crate::http) async fn configure(
     State(compute): State<Arc<ComputeNode>>,
     request: Json<ConfigurationRequest>,
 ) -> Response {
-    let pspec = match ParsedSpec::try_from(request.0.spec) {
+    let pspec = match ParsedSpec::try_from(request.spec.clone()) {
         Ok(p) => p,
         Err(e) => return JsonResponse::error(StatusCode::BAD_REQUEST, e),
     };

compute_tools/src/monitor.rs

@@ -13,12 +13,6 @@ use crate::metrics::{PG_CURR_DOWNTIME_MS, PG_TOTAL_DOWNTIME_MS};
 
 const MONITOR_CHECK_INTERVAL: Duration = Duration::from_millis(500);
 
-/// Struct to store runtime state of the compute monitor thread.
-/// In theory, this could be a part of `Compute`, but i)
-/// this state is expected to be accessed only by single thread,
-/// so we don't need to care about locking; ii) `Compute` is
-/// already quite big. Thus, it seems to be a good idea to keep
-/// all the activity/health monitoring parts here.
 struct ComputeMonitor {
     compute: Arc<ComputeNode>,
 
@@ -76,36 +70,12 @@ impl ComputeMonitor {
         )
     }
 
-    /// Check if compute is in some terminal or soon-to-be-terminal
-    /// state, then return `true`, signalling the caller that it
-    /// should exit gracefully. Otherwise, return `false`.
-    fn check_interrupts(&mut self) -> bool {
-        let compute_status = self.compute.get_status();
-        if matches!(
-            compute_status,
-            ComputeStatus::Terminated | ComputeStatus::TerminationPending | ComputeStatus::Failed
-        ) {
-            info!(
-                "compute is in {} status, stopping compute monitor",
-                compute_status
-            );
-            return true;
-        }
-
-        false
-    }
-
     /// Spin in a loop and figure out the last activity time in the Postgres.
-    /// Then update it in the shared state. This function currently never
-    /// errors out explicitly, but there is a graceful termination path.
-    /// Every time we receive an error trying to check Postgres, we use
-    /// [`ComputeMonitor::check_interrupts()`] because it could be that
-    /// compute is being terminated already, then we can exit gracefully
-    /// to not produce errors' noise in the log.
+    /// Then update it in the shared state. This function never errors out.
     /// NB: the only expected panic is at `Mutex` unwrap(), all other errors
     /// should be handled gracefully.
     #[instrument(skip_all)]
-    pub fn run(&mut self) -> anyhow::Result<()> {
+    pub fn run(&mut self) {
         // Suppose that `connstr` doesn't change
         let connstr = self.compute.params.connstr.clone();
         let conf = self
@@ -123,10 +93,6 @@ impl ComputeMonitor {
         info!("starting compute monitor for {}", connstr);
 
         loop {
-            if self.check_interrupts() {
-                break;
-            }
-
             match &mut client {
                 Ok(cli) => {
                     if cli.is_closed() {
@@ -134,10 +100,6 @@ impl ComputeMonitor {
                             downtime_info = self.downtime_info(),
                             "connection to Postgres is closed, trying to reconnect"
                         );
-                        if self.check_interrupts() {
-                            break;
-                        }
-
                         self.report_down();
 
                         // Connection is closed, reconnect and try again.
@@ -149,19 +111,15 @@ impl ComputeMonitor {
                                 self.compute.update_last_active(self.last_active);
                             }
                             Err(e) => {
-                                error!(
-                                    downtime_info = self.downtime_info(),
-                                    "could not check Postgres: {}", e
-                                );
-                                if self.check_interrupts() {
-                                    break;
-                                }
-
                                 // Although we have many places where we can return errors in `check()`,
                                 // normally it shouldn't happen. I.e., we will likely return error if
                                 // connection got broken, query timed out, Postgres returned invalid data, etc.
                                 // In all such cases it's suspicious, so let's report this as downtime.
                                 self.report_down();
+                                error!(
+                                    downtime_info = self.downtime_info(),
+                                    "could not check Postgres: {}", e
+                                );
 
                                 // Reconnect to Postgres just in case. During tests, I noticed
                                 // that queries in `check()` can fail with `connection closed`,
@@ -178,10 +136,6 @@ impl ComputeMonitor {
                         downtime_info = self.downtime_info(),
                         "could not connect to Postgres: {}, retrying", e
                     );
-                    if self.check_interrupts() {
-                        break;
-                    }
-
                     self.report_down();
 
                     // Establish a new connection and try again.
@@ -193,9 +147,6 @@ impl ComputeMonitor {
             self.last_checked = Utc::now();
             thread::sleep(MONITOR_CHECK_INTERVAL);
         }
-
-        // Graceful termination path
-        Ok(())
     }
 
     #[instrument(skip_all)]
@@ -478,10 +429,7 @@ pub fn launch_monitor(compute: &Arc<ComputeNode>) -> thread::JoinHandle<()> {
         .spawn(move || {
             let span = span!(Level::INFO, "compute_monitor");
             let _enter = span.enter();
-            match monitor.run() {
-                Ok(_) => info!("compute monitor thread terminated gracefully"),
-                Err(err) => error!("compute monitor thread terminated abnormally {:?}", err),
-            }
+            monitor.run();
         })
         .expect("cannot launch compute monitor thread")
 }

compute_tools/src/rsyslog.rs

@@ -84,15 +84,13 @@ fn restart_rsyslog() -> Result<()> {
 
 pub fn configure_audit_rsyslog(
     log_directory: String,
-    endpoint_id: &str,
-    project_id: &str,
+    tag: Option<String>,
     remote_endpoint: &str,
 ) -> Result<()> {
     let config_content: String = format!(
         include_str!("config_template/compute_audit_rsyslog_template.conf"),
         log_directory = log_directory,
-        endpoint_id = endpoint_id,
-        project_id = project_id,
+        tag = tag.unwrap_or("".to_string()),
         remote_endpoint = remote_endpoint
     );
 

compute_tools/tests/pg_helpers_tests.rs

@@ -30,7 +30,7 @@ mod pg_helpers_tests {
             r#"fsync = off
 wal_level = logical
 hot_standby = on
-autoprewarm = off
+prewarm_lfc_on_startup = off
 neon.safekeepers = '127.0.0.1:6502,127.0.0.1:6503,127.0.0.1:6501'
 wal_log_hints = on
 log_connections = on

control_plane/safekeepers.conf

@@ -2,10 +2,8 @@
 [pageserver]
 listen_pg_addr = '127.0.0.1:64000'
 listen_http_addr = '127.0.0.1:9898'
-listen_grpc_addr = '127.0.0.1:51051'
 pg_auth_type = 'Trust'
 http_auth_type = 'Trust'
-grpc_auth_type = 'Trust'
 
 [[safekeepers]]
 id = 1

control_plane/simple.conf

@@ -4,10 +4,8 @@
 id=1
 listen_pg_addr = '127.0.0.1:64000'
 listen_http_addr = '127.0.0.1:9898'
-listen_grpc_addr = '127.0.0.1:51051'
 pg_auth_type = 'Trust'
 http_auth_type = 'Trust'
-grpc_auth_type = 'Trust'
 
 [[safekeepers]]
 id = 1

control_plane/src/bin/neon_local.rs

@@ -32,7 +32,6 @@ use control_plane::storage_controller::{
 };
 use nix::fcntl::{Flock, FlockArg};
 use pageserver_api::config::{
-    DEFAULT_GRPC_LISTEN_PORT as DEFAULT_PAGESERVER_GRPC_PORT,
     DEFAULT_HTTP_LISTEN_PORT as DEFAULT_PAGESERVER_HTTP_PORT,
     DEFAULT_PG_LISTEN_PORT as DEFAULT_PAGESERVER_PG_PORT,
 };
@@ -1008,16 +1007,13 @@ fn handle_init(args: &InitCmdArgs) -> anyhow::Result<LocalEnv> {
                     let pageserver_id = NodeId(DEFAULT_PAGESERVER_ID.0 + i as u64);
                     let pg_port = DEFAULT_PAGESERVER_PG_PORT + i;
                     let http_port = DEFAULT_PAGESERVER_HTTP_PORT + i;
-                    let grpc_port = DEFAULT_PAGESERVER_GRPC_PORT + i;
                     NeonLocalInitPageserverConf {
                         id: pageserver_id,
                         listen_pg_addr: format!("127.0.0.1:{pg_port}"),
                         listen_http_addr: format!("127.0.0.1:{http_port}"),
                         listen_https_addr: None,
-                        listen_grpc_addr: Some(format!("127.0.0.1:{grpc_port}")),
                         pg_auth_type: AuthType::Trust,
                         http_auth_type: AuthType::Trust,
-                        grpc_auth_type: AuthType::Trust,
                         other: Default::default(),
                         // Typical developer machines use disks with slow fsync, and we don't care
                         // about data integrity: disable disk syncs.
@@ -1279,7 +1275,6 @@ async fn handle_timeline(cmd: &TimelineCmd, env: &mut local_env::LocalEnv) -> Re
                 mode: pageserver_api::models::TimelineCreateRequestMode::Branch {
                     ancestor_timeline_id,
                     ancestor_start_lsn: start_lsn,
-                    read_only: false,
                     pg_version: None,
                 },
             };

control_plane/src/endpoint.rs

@@ -616,19 +616,16 @@ impl Endpoint {
 
     /// Map safekeepers ids to the actual connection strings.
     fn build_safekeepers_connstrs(&self, sk_ids: Vec<NodeId>) -> Result<Vec<String>> {
-        let mut safekeeper_connstrings = Vec::new();
-        if self.mode == ComputeMode::Primary {
-            for sk_id in sk_ids {
-                let sk = self
-                    .env
+        sk_ids.into_iter()
+            .map(|node_id| {
+                self.env
                     .safekeepers
                     .iter()
-                    .find(|node| node.id == sk_id)
-                    .ok_or_else(|| anyhow!("safekeeper {sk_id} does not exist"))?;
-                safekeeper_connstrings.push(format!("127.0.0.1:{}", sk.get_compute_port()));
-            }
-        }
-        Ok(safekeeper_connstrings)
+                    .find(|node| node.id == node_id)
+                    .map(|node| format!("127.0.0.1:{}", node.get_compute_port()))
+                    .ok_or_else(|| anyhow!("safekeeer {node_id} does not exist"))
+            })
+            .collect::<Result<Vec<String>>>()
     }
 
     /// Generate a JWT with the correct claims.
@@ -747,7 +744,7 @@ impl Endpoint {
                 logs_export_host: None::<String>,
                 endpoint_storage_addr: Some(endpoint_storage_addr),
                 endpoint_storage_token: Some(endpoint_storage_token),
-                autoprewarm: false,
+                prewarm_lfc_on_startup: false,
             };
 
             // this strange code is needed to support respec() in tests

control_plane/src/local_env.rs

@@ -278,10 +278,8 @@ pub struct PageServerConf {
     pub listen_pg_addr: String,
     pub listen_http_addr: String,
     pub listen_https_addr: Option<String>,
-    pub listen_grpc_addr: Option<String>,
     pub pg_auth_type: AuthType,
     pub http_auth_type: AuthType,
-    pub grpc_auth_type: AuthType,
     pub no_sync: bool,
 }
 
@@ -292,10 +290,8 @@ impl Default for PageServerConf {
             listen_pg_addr: String::new(),
             listen_http_addr: String::new(),
             listen_https_addr: None,
-            listen_grpc_addr: None,
             pg_auth_type: AuthType::Trust,
             http_auth_type: AuthType::Trust,
-            grpc_auth_type: AuthType::Trust,
             no_sync: false,
         }
     }
@@ -310,10 +306,8 @@ pub struct NeonLocalInitPageserverConf {
     pub listen_pg_addr: String,
     pub listen_http_addr: String,
     pub listen_https_addr: Option<String>,
-    pub listen_grpc_addr: Option<String>,
     pub pg_auth_type: AuthType,
     pub http_auth_type: AuthType,
-    pub grpc_auth_type: AuthType,
     #[serde(default, skip_serializing_if = "std::ops::Not::not")]
     pub no_sync: bool,
     #[serde(flatten)]
@@ -327,10 +321,8 @@ impl From<&NeonLocalInitPageserverConf> for PageServerConf {
             listen_pg_addr,
             listen_http_addr,
             listen_https_addr,
-            listen_grpc_addr,
             pg_auth_type,
             http_auth_type,
-            grpc_auth_type,
             no_sync,
             other: _,
         } = conf;
@@ -339,9 +331,7 @@ impl From<&NeonLocalInitPageserverConf> for PageServerConf {
             listen_pg_addr: listen_pg_addr.clone(),
             listen_http_addr: listen_http_addr.clone(),
             listen_https_addr: listen_https_addr.clone(),
-            listen_grpc_addr: listen_grpc_addr.clone(),
             pg_auth_type: *pg_auth_type,
-            grpc_auth_type: *grpc_auth_type,
             http_auth_type: *http_auth_type,
             no_sync: *no_sync,
         }
@@ -717,10 +707,8 @@ impl LocalEnv {
                     listen_pg_addr: String,
                     listen_http_addr: String,
                     listen_https_addr: Option<String>,
-                    listen_grpc_addr: Option<String>,
                     pg_auth_type: AuthType,
                     http_auth_type: AuthType,
-                    grpc_auth_type: AuthType,
                     #[serde(default)]
                     no_sync: bool,
                 }
@@ -744,10 +732,8 @@ impl LocalEnv {
                     listen_pg_addr,
                     listen_http_addr,
                     listen_https_addr,
-                    listen_grpc_addr,
                     pg_auth_type,
                     http_auth_type,
-                    grpc_auth_type,
                     no_sync,
                 } = config_toml;
                 let IdentityTomlSubset {
@@ -764,10 +750,8 @@ impl LocalEnv {
                     listen_pg_addr,
                     listen_http_addr,
                     listen_https_addr,
-                    listen_grpc_addr,
                     pg_auth_type,
                     http_auth_type,
-                    grpc_auth_type,
                     no_sync,
                 };
                 pageservers.push(conf);

control_plane/src/pageserver.rs

@@ -129,9 +129,7 @@ impl PageServerNode {
             ));
         }
 
-        if [conf.http_auth_type, conf.pg_auth_type, conf.grpc_auth_type]
-            .contains(&AuthType::NeonJWT)
-        {
+        if conf.http_auth_type != AuthType::Trust || conf.pg_auth_type != AuthType::Trust {
             // Keys are generated in the toplevel repo dir, pageservers' workdirs
             // are one level below that, so refer to keys with ../
             overrides.push("auth_validation_public_key_path='../auth_public_key.pem'".to_owned());
@@ -513,6 +511,11 @@ impl PageServerNode {
                 .map(|x| x.parse::<bool>())
                 .transpose()
                 .context("Failed to parse 'timeline_offloading' as bool")?,
+            wal_receiver_protocol_override: settings
+                .remove("wal_receiver_protocol_override")
+                .map(serde_json::from_str)
+                .transpose()
+                .context("parse `wal_receiver_protocol_override` from json")?,
             rel_size_v2_enabled: settings
                 .remove("rel_size_v2_enabled")
                 .map(|x| x.parse::<bool>())

docker-compose/compute_wrapper/Dockerfile

@@ -13,6 +13,6 @@ RUN echo 'Acquire::Retries "5";' > /etc/apt/apt.conf.d/80-retries && \
                        jq   \
                        netcat-openbsd
 #This is required for the pg_hintplan test
-RUN mkdir -p /ext-src/pg_hint_plan-src /postgres/contrib/file_fdw /ext-src/postgis-src/ && chown postgres /ext-src/pg_hint_plan-src /postgres/contrib/file_fdw /ext-src/postgis-src
+RUN mkdir -p /ext-src/pg_hint_plan-src /postgres/contrib/file_fdw && chown postgres /ext-src/pg_hint_plan-src /postgres/contrib/file_fdw
 
 USER postgres

docker-compose/compute_wrapper/shell/compute.sh

@@ -1,18 +1,18 @@
-#!/usr/bin/env bash
+#!/bin/bash
 set -eux
 
 # Generate a random tenant or timeline ID
 #
 # Takes a variable name as argument. The result is stored in that variable.
 generate_id() {
-    local -n resvar=${1}
-    printf -v resvar '%08x%08x%08x%08x' ${SRANDOM} ${SRANDOM} ${SRANDOM} ${SRANDOM}
+    local -n resvar=$1
+    printf -v resvar '%08x%08x%08x%08x' $SRANDOM $SRANDOM $SRANDOM $SRANDOM
 }
 
 PG_VERSION=${PG_VERSION:-14}
 
-readonly CONFIG_FILE_ORG=/var/db/postgres/configs/config.json
-readonly CONFIG_FILE=/tmp/config.json
+CONFIG_FILE_ORG=/var/db/postgres/configs/config.json
+CONFIG_FILE=/tmp/config.json
 
 # Test that the first library path that the dynamic loader looks in is the path
 # that we use for custom compiled software
@@ -20,17 +20,17 @@ first_path="$(ldconfig --verbose 2>/dev/null \
     | grep --invert-match ^$'\t' \
     | cut --delimiter=: --fields=1 \
     | head --lines=1)"
-test "${first_path}" = '/usr/local/lib'
+test "$first_path" == '/usr/local/lib' || true # Remove the || true in a follow-up PR. Needed for backwards compat.
 
 echo "Waiting pageserver become ready."
 while ! nc -z pageserver 6400; do
-     sleep 1
+     sleep 1;
 done
 echo "Page server is ready."
 
-cp "${CONFIG_FILE_ORG}" "${CONFIG_FILE}"
+cp ${CONFIG_FILE_ORG} ${CONFIG_FILE}
 
- if [[ -n "${TENANT_ID:-}" && -n "${TIMELINE_ID:-}" ]]; then
+ if [ -n "${TENANT_ID:-}" ] && [ -n "${TIMELINE_ID:-}" ]; then
    tenant_id=${TENANT_ID}
    timeline_id=${TIMELINE_ID}
 else
@@ -41,7 +41,7 @@ else
        "http://pageserver:9898/v1/tenant"
   )
   tenant_id=$(curl "${PARAMS[@]}" | jq -r .[0].id)
-  if [[ -z "${tenant_id}" || "${tenant_id}" = null ]]; then
+  if [ -z "${tenant_id}" ] || [ "${tenant_id}" = null ]; then
     echo "Create a tenant"
     generate_id tenant_id
     PARAMS=(
@@ -51,7 +51,7 @@ else
         "http://pageserver:9898/v1/tenant/${tenant_id}/location_config"
     )
     result=$(curl "${PARAMS[@]}")
-    printf '%s\n' "${result}" | jq .
+    echo $result | jq .
   fi
 
   echo "Check if a timeline present"
@@ -61,7 +61,7 @@ else
        "http://pageserver:9898/v1/tenant/${tenant_id}/timeline"
   )
   timeline_id=$(curl "${PARAMS[@]}" | jq -r .[0].timeline_id)
-  if [[ -z "${timeline_id}" || "${timeline_id}" = null ]]; then
+  if [ -z "${timeline_id}" ] || [ "${timeline_id}" = null ]; then
     generate_id timeline_id
     PARAMS=(
         -sbf
@@ -71,7 +71,7 @@ else
         "http://pageserver:9898/v1/tenant/${tenant_id}/timeline/"
     )
     result=$(curl "${PARAMS[@]}")
-    printf '%s\n' "${result}" | jq .
+    echo $result | jq .
   fi
 fi
 
@@ -82,10 +82,10 @@ else
 fi
 echo "Adding pgx_ulid"
 shared_libraries=$(jq -r '.spec.cluster.settings[] | select(.name=="shared_preload_libraries").value' ${CONFIG_FILE})
-sed -i "s|${shared_libraries}|${shared_libraries},${ulid_extension}|" ${CONFIG_FILE}
+sed -i "s/${shared_libraries}/${shared_libraries},${ulid_extension}/" ${CONFIG_FILE}
 echo "Overwrite tenant id and timeline id in spec file"
-sed -i "s|TENANT_ID|${tenant_id}|" ${CONFIG_FILE}
-sed -i "s|TIMELINE_ID|${timeline_id}|" ${CONFIG_FILE}
+sed -i "s/TENANT_ID/${tenant_id}/" ${CONFIG_FILE}
+sed -i "s/TIMELINE_ID/${timeline_id}/" ${CONFIG_FILE}
 
 cat ${CONFIG_FILE}
 
@@ -93,5 +93,5 @@ echo "Start compute node"
 /usr/local/bin/compute_ctl --pgdata /var/db/postgres/compute \
      -C "postgresql://cloud_admin@localhost:55433/postgres"  \
      -b /usr/local/bin/postgres                              \
-     --compute-id "compute-${RANDOM}"                          \
-     --config "${CONFIG_FILE}"
+     --compute-id "compute-$RANDOM"                          \
+     --config "$CONFIG_FILE"

docker-compose/docker-compose.yml

@@ -186,14 +186,13 @@ services:
 
   neon-test-extensions:
     profiles: ["test-extensions"]
-    image: ${REPOSITORY:-ghcr.io/neondatabase}/neon-test-extensions-v${PG_TEST_VERSION:-${PG_VERSION:-16}}:${TEST_EXTENSIONS_TAG:-${TAG:-latest}}
+    image: ${REPOSITORY:-ghcr.io/neondatabase}/neon-test-extensions-v${PG_TEST_VERSION:-16}:${TEST_EXTENSIONS_TAG:-${TAG:-latest}}
     environment:
-      - PGUSER=${PGUSER:-cloud_admin}
-      - PGPASSWORD=${PGPASSWORD:-cloud_admin}
+      - PGPASSWORD=cloud_admin
     entrypoint:
       - "/bin/bash"
       - "-c"
     command:
-      - sleep 3600
+      - sleep 1800
     depends_on:
       - compute

docker-compose/docker_compose_test.sh

@@ -54,15 +54,6 @@ for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
         # It cannot be moved to Dockerfile now because the database directory is created after the start of the container
         echo Adding dummy config
         docker compose exec compute touch /var/db/postgres/compute/compute_ctl_temp_override.conf
-        # Prepare for the PostGIS test
-        docker compose exec compute mkdir -p /tmp/pgis_reg/pgis_reg_tmp
-        TMPDIR=$(mktemp -d)
-        docker compose cp neon-test-extensions:/ext-src/postgis-src/raster/test "${TMPDIR}"
-        docker compose cp neon-test-extensions:/ext-src/postgis-src/regress/00-regress-install "${TMPDIR}"
-        docker compose exec compute mkdir -p /ext-src/postgis-src/raster /ext-src/postgis-src/regress /ext-src/postgis-src/regress/00-regress-install
-        docker compose cp "${TMPDIR}/test" compute:/ext-src/postgis-src/raster/test
-        docker compose cp "${TMPDIR}/00-regress-install" compute:/ext-src/postgis-src/regress
-        rm -rf "${TMPDIR}"
         # The following block copies the files for the pg_hintplan test to the compute node for the extension test in an isolated docker-compose environment
         TMPDIR=$(mktemp -d)
         docker compose cp neon-test-extensions:/ext-src/pg_hint_plan-src/data "${TMPDIR}/data"
@@ -77,7 +68,7 @@ for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
         docker compose exec -T neon-test-extensions bash -c "(cd /postgres && patch -p1)" <"../compute/patches/contrib_pg${pg_version}.patch"
         # We are running tests now
         rm -f testout.txt testout_contrib.txt
-        docker compose exec -e USE_PGXS=1 -e SKIP=timescaledb-src,rdkit-src,pg_jsonschema-src,kq_imcx-src,wal2json_2_5-src,rag_jina_reranker_v1_tiny_en-src,rag_bge_small_en_v15-src \
+        docker compose exec -e USE_PGXS=1 -e SKIP=timescaledb-src,rdkit-src,postgis-src,pg_jsonschema-src,kq_imcx-src,wal2json_2_5-src,rag_jina_reranker_v1_tiny_en-src,rag_bge_small_en_v15-src \
         neon-test-extensions /run-tests.sh /ext-src | tee testout.txt && EXT_SUCCESS=1 || EXT_SUCCESS=0
         docker compose exec -e SKIP=start-scripts,postgres_fdw,ltree_plpython,jsonb_plpython,jsonb_plperl,hstore_plpython,hstore_plperl,dblink,bool_plperl \
         neon-test-extensions /run-tests.sh /postgres/contrib | tee testout_contrib.txt && CONTRIB_SUCCESS=1 || CONTRIB_SUCCESS=0

docker-compose/ext-src/h3-pg-src/neon-test.sh

@@ -1,16 +0,0 @@
-#!/usr/bin/env bash
-set -ex
-cd "$(dirname "${0}")"
-PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
-dropdb --if-exists contrib_regression
-createdb contrib_regression
-cd h3_postgis/test
-psql -d contrib_regression -c "CREATE EXTENSION postgis" -c "CREATE EXTENSION postgis_raster" -c "CREATE EXTENSION h3" -c "CREATE EXTENSION h3_postgis"
-TESTS=$(echo sql/* | sed 's|sql/||g; s|\.sql||g')
-${PG_REGRESS} --use-existing --dbname contrib_regression ${TESTS}
-cd ../../h3/test
-TESTS=$(echo sql/* | sed 's|sql/||g; s|\.sql||g')
-dropdb --if-exists contrib_regression
-createdb contrib_regression
-psql -d contrib_regression -c "CREATE EXTENSION h3"
-${PG_REGRESS} --use-existing --dbname contrib_regression ${TESTS}

docker-compose/ext-src/h3-pg-src/test-upgrade.sh

@@ -1,7 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname ${0})"
-PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
-cd h3/test
-TESTS=$(echo sql/* | sed 's|sql/||g; s|\.sql||g')
-${PG_REGRESS} --use-existing --inputdir=./ --bindir='/usr/local/pgsql/bin'  --dbname=contrib_regression  ${TESTS}

docker-compose/ext-src/online_advisor-src/neon-test.sh

@@ -1,6 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname "${0}")"
-if [ -f Makefile ]; then
-  make installcheck
-fi

docker-compose/ext-src/online_advisor-src/regular-test.sh

@@ -1,9 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname ${0})"
-[ -f Makefile ] || exit 0
-dropdb --if-exist contrib_regression
-createdb contrib_regression
-PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
-TESTS=$(echo sql/* | sed 's|sql/||g; s|\.sql||g')
-${PG_REGRESS} --use-existing --inputdir=./ --bindir='/usr/local/pgsql/bin' --dbname=contrib_regression ${TESTS}

docker-compose/ext-src/postgis-src/README-Neon.md

@@ -1,70 +0,0 @@
-# PostGIS Testing in Neon
-
-This directory contains configuration files and patches for running PostGIS tests in the Neon database environment.
-
-## Overview
-
-PostGIS is a spatial database extension for PostgreSQL that adds support for geographic objects. Testing PostGIS compatibility ensures that Neon's modifications to PostgreSQL don't break compatibility with this critical extension.
-
-## PostGIS Versions
-
-- PostgreSQL v17: PostGIS 3.5.0
-- PostgreSQL v14/v15/v16: PostGIS 3.3.3
-
-## Test Configuration
-
-The test setup includes:
-
-- `postgis-no-upgrade-test.patch`: Disables upgrade tests by removing the upgrade test section from regress/runtest.mk
-- `postgis-regular-v16.patch`: Version-specific patch for PostgreSQL v16
-- `postgis-regular-v17.patch`: Version-specific patch for PostgreSQL v17
-- `regular-test.sh`: Script to run PostGIS tests as a regular user
-- `neon-test.sh`: Script to handle version-specific test configurations
-- `raster_outdb_template.sql`: Template for raster tests with explicit file paths
-
-## Excluded Tests
-
-**Important Note:** The test exclusions listed below are specifically for regular-user tests against staging instances. These exclusions are necessary because staging instances run with limited privileges and cannot perform operations requiring superuser access. Docker-compose based tests are not affected by these exclusions.
-
-### Tests Requiring Superuser Permissions
-
-These tests cannot be run as a regular user:
-- `estimatedextent`
-- `regress/core/legacy`
-- `regress/core/typmod`
-- `regress/loader/TestSkipANALYZE`
-- `regress/loader/TestANALYZE`
-
-### Tests Requiring Filesystem Access
-
-These tests need direct filesystem access that is only possible for superusers:
-- `loader/load_outdb`
-
-### Tests with Flaky Results
-
-These tests have assumptions that don't always hold true:
-- `regress/core/computed_columns` - Assumes computed columns always outperform alternatives, which is not consistently true
-
-### Tests Requiring Tunable Parameter Modifications
-
-These tests attempt to modify the `postgis.gdal_enabled_drivers` parameter, which is only accessible to superusers:
-- `raster/test/regress/rt_wkb`
-- `raster/test/regress/rt_addband`
-- `raster/test/regress/rt_setbandpath`
-- `raster/test/regress/rt_fromgdalraster`
-- `raster/test/regress/rt_asgdalraster`
-- `raster/test/regress/rt_astiff`
-- `raster/test/regress/rt_asjpeg`
-- `raster/test/regress/rt_aspng`
-- `raster/test/regress/permitted_gdal_drivers`
-- Loader tests: `BasicOutDB`, `Tiled10x10`, `Tiled10x10Copy`, `Tiled8x8`, `TiledAuto`, `TiledAutoSkipNoData`, `TiledAutoCopyn`
-
-### Topology Tests (v17 only)
-- `populate_topology_layer`
-- `renametopogeometrycolumn`
-
-## Other Modifications
-
-- Binary.sql tests are modified to use explicit file paths
-- Server-side SQL COPY commands (which require superuser privileges) are converted to client-side `\copy` commands
-- Upgrade tests are disabled

docker-compose/ext-src/postgis-src/neon-test.sh

@@ -1,6 +0,0 @@
-#!/bin/sh
-set -ex
-cd "$(dirname "$0")"
-patch -p1 <"postgis-common-${PG_VERSION}.patch"
-trap 'echo Cleaning up; patch -R -p1 <postgis-common-${PG_VERSION}.patch' EXIT
-make installcheck-base

docker-compose/ext-src/postgis-src/postgis-common-v16.patch

@@ -1,37 +0,0 @@
-diff --git a/regress/core/tests.mk b/regress/core/tests.mk
-index 3abd7bc..64a9254 100644
---- a/regress/core/tests.mk
-+++ b/regress/core/tests.mk
-@@ -144,11 +144,6 @@ TESTS_SLOW = \
- 	$(top_srcdir)/regress/core/concave_hull_hard \
- 	$(top_srcdir)/regress/core/knn_recheck
- 
--ifeq ($(shell expr "$(POSTGIS_PGSQL_VERSION)" ">=" 120),1)
--	TESTS += \
--		$(top_srcdir)/regress/core/computed_columns
--endif
--
- ifeq ($(shell expr "$(POSTGIS_GEOS_VERSION)" ">=" 30700),1)
- 	# GEOS-3.7 adds:
- 	# ST_FrechetDistance
-diff --git a/regress/runtest.mk b/regress/runtest.mk
-index c051f03..010e493 100644
---- a/regress/runtest.mk
-+++ b/regress/runtest.mk
-@@ -24,16 +24,6 @@ check-regress:
- 
- 	POSTGIS_TOP_BUILD_DIR=$(abs_top_builddir) $(PERL) $(top_srcdir)/regress/run_test.pl $(RUNTESTFLAGS) $(RUNTESTFLAGS_INTERNAL) $(TESTS)
- 
--	@if echo "$(RUNTESTFLAGS)" | grep -vq -- --upgrade; then \
--		echo "Running upgrade test as RUNTESTFLAGS did not contain that"; \
--		POSTGIS_TOP_BUILD_DIR=$(abs_top_builddir) $(PERL) $(top_srcdir)/regress/run_test.pl \
--      --upgrade \
--      $(RUNTESTFLAGS) \
--      $(RUNTESTFLAGS_INTERNAL) \
--      $(TESTS); \
--	else \
--		echo "Skipping upgrade test as RUNTESTFLAGS already requested upgrades"; \
--	fi
- 
- check-long:
- 	$(PERL) $(top_srcdir)/regress/run_test.pl $(RUNTESTFLAGS) $(TESTS) $(TESTS_SLOW)

docker-compose/ext-src/postgis-src/postgis-common-v17.patch

@@ -1,35 +0,0 @@
-diff --git a/regress/core/tests.mk b/regress/core/tests.mk
-index 9e05244..90987df 100644
---- a/regress/core/tests.mk
-+++ b/regress/core/tests.mk
-@@ -143,8 +143,7 @@ TESTS += \
- 	$(top_srcdir)/regress/core/oriented_envelope \
- 	$(top_srcdir)/regress/core/point_coordinates \
- 	$(top_srcdir)/regress/core/out_geojson \
--  $(top_srcdir)/regress/core/wrapx \
--	$(top_srcdir)/regress/core/computed_columns
-+  $(top_srcdir)/regress/core/wrapx
- 
- # Slow slow tests
- TESTS_SLOW = \
-diff --git a/regress/runtest.mk b/regress/runtest.mk
-index 4b95b7e..449d5a2 100644
---- a/regress/runtest.mk
-+++ b/regress/runtest.mk
-@@ -24,16 +24,6 @@ check-regress:
- 
- 	@POSTGIS_TOP_BUILD_DIR=$(abs_top_builddir) $(PERL) $(top_srcdir)/regress/run_test.pl $(RUNTESTFLAGS) $(RUNTESTFLAGS_INTERNAL) $(TESTS)
- 
--	@if echo "$(RUNTESTFLAGS)" | grep -vq -- --upgrade; then \
--		echo "Running upgrade test as RUNTESTFLAGS did not contain that"; \
--		POSTGIS_TOP_BUILD_DIR=$(abs_top_builddir) $(PERL) $(top_srcdir)/regress/run_test.pl \
--      --upgrade \
--      $(RUNTESTFLAGS) \
--      $(RUNTESTFLAGS_INTERNAL) \
--      $(TESTS); \
--	else \
--		echo "Skipping upgrade test as RUNTESTFLAGS already requested upgrades"; \
--	fi
- 
- check-long:
- 	$(PERL) $(top_srcdir)/regress/run_test.pl $(RUNTESTFLAGS) $(TESTS) $(TESTS_SLOW)

docker-compose/ext-src/postgis-src/postgis-regular-v16.patch

@@ -1,186 +0,0 @@
-diff --git a/raster/test/regress/tests.mk b/raster/test/regress/tests.mk
-index 00918e1..7e2b6cd 100644
---- a/raster/test/regress/tests.mk
-+++ b/raster/test/regress/tests.mk
-@@ -17,9 +17,7 @@ override RUNTESTFLAGS_INTERNAL := \
-   $(RUNTESTFLAGS_INTERNAL) \
-   --after-upgrade-script $(top_srcdir)/raster/test/regress/hooks/hook-after-upgrade-raster.sql
- 
--RASTER_TEST_FIRST = \
--	$(top_srcdir)/raster/test/regress/check_gdal \
--	$(top_srcdir)/raster/test/regress/loader/load_outdb
-+RASTER_TEST_FIRST =
- 
- RASTER_TEST_LAST = \
- 	$(top_srcdir)/raster/test/regress/clean
-@@ -33,9 +31,7 @@ RASTER_TEST_IO = \
- 
- RASTER_TEST_BASIC_FUNC = \
- 	$(top_srcdir)/raster/test/regress/rt_bytea \
--	$(top_srcdir)/raster/test/regress/rt_wkb \
- 	$(top_srcdir)/raster/test/regress/box3d \
--	$(top_srcdir)/raster/test/regress/rt_addband \
- 	$(top_srcdir)/raster/test/regress/rt_band \
- 	$(top_srcdir)/raster/test/regress/rt_tile
- 
-@@ -73,16 +69,10 @@ RASTER_TEST_BANDPROPS = \
- 	$(top_srcdir)/raster/test/regress/rt_neighborhood \
- 	$(top_srcdir)/raster/test/regress/rt_nearestvalue \
- 	$(top_srcdir)/raster/test/regress/rt_pixelofvalue \
--	$(top_srcdir)/raster/test/regress/rt_polygon \
--	$(top_srcdir)/raster/test/regress/rt_setbandpath
-+	$(top_srcdir)/raster/test/regress/rt_polygon
- 
- RASTER_TEST_UTILITY = \
- 	$(top_srcdir)/raster/test/regress/rt_utility \
--	$(top_srcdir)/raster/test/regress/rt_fromgdalraster \
--	$(top_srcdir)/raster/test/regress/rt_asgdalraster \
--	$(top_srcdir)/raster/test/regress/rt_astiff \
--	$(top_srcdir)/raster/test/regress/rt_asjpeg \
--	$(top_srcdir)/raster/test/regress/rt_aspng \
- 	$(top_srcdir)/raster/test/regress/rt_reclass \
- 	$(top_srcdir)/raster/test/regress/rt_gdalwarp \
- 	$(top_srcdir)/raster/test/regress/rt_gdalcontour \
-@@ -120,21 +110,13 @@ RASTER_TEST_SREL = \
- 
- RASTER_TEST_BUGS = \
- 	$(top_srcdir)/raster/test/regress/bug_test_car5 \
--	$(top_srcdir)/raster/test/regress/permitted_gdal_drivers \
- 	$(top_srcdir)/raster/test/regress/tickets
- 
- RASTER_TEST_LOADER = \
- 	$(top_srcdir)/raster/test/regress/loader/Basic \
- 	$(top_srcdir)/raster/test/regress/loader/Projected \
- 	$(top_srcdir)/raster/test/regress/loader/BasicCopy \
--	$(top_srcdir)/raster/test/regress/loader/BasicFilename \
--	$(top_srcdir)/raster/test/regress/loader/BasicOutDB \
--	$(top_srcdir)/raster/test/regress/loader/Tiled10x10 \
--	$(top_srcdir)/raster/test/regress/loader/Tiled10x10Copy \
--	$(top_srcdir)/raster/test/regress/loader/Tiled8x8 \
--	$(top_srcdir)/raster/test/regress/loader/TiledAuto \
--	$(top_srcdir)/raster/test/regress/loader/TiledAutoSkipNoData \
--	$(top_srcdir)/raster/test/regress/loader/TiledAutoCopyn
-+	$(top_srcdir)/raster/test/regress/loader/BasicFilename
- 
- RASTER_TESTS := $(RASTER_TEST_FIRST) \
- 	$(RASTER_TEST_METADATA) $(RASTER_TEST_IO) $(RASTER_TEST_BASIC_FUNC) \
-diff --git a/regress/core/binary.sql b/regress/core/binary.sql
-index 7a36b65..ad78fc7 100644
---- a/regress/core/binary.sql
-+++ b/regress/core/binary.sql
-@@ -1,4 +1,5 @@
- SET client_min_messages TO warning;
-+
- CREATE SCHEMA tm;
- 
- CREATE TABLE tm.geoms (id serial, g geometry);
-@@ -31,24 +32,39 @@ SELECT st_force4d(g) FROM tm.geoms WHERE id < 15 ORDER BY id;
- INSERT INTO tm.geoms(g)
- SELECT st_setsrid(g,4326) FROM tm.geoms ORDER BY id;
- 
--COPY tm.geoms TO :tmpfile WITH BINARY;
-+-- define temp file path
-+\set tmpfile '/tmp/postgis_binary_test.dat'
-+
-+-- export
-+\set command '\\copy tm.geoms TO ':tmpfile' WITH (FORMAT BINARY)'
-+:command
-+
-+-- import
- CREATE TABLE tm.geoms_in AS SELECT * FROM tm.geoms LIMIT 0;
--COPY tm.geoms_in FROM :tmpfile WITH BINARY;
--SELECT 'geometry', count(*) FROM tm.geoms_in i, tm.geoms o WHERE i.id = o.id
-- AND ST_OrderingEquals(i.g, o.g);
-+\set command '\\copy tm.geoms_in FROM ':tmpfile' WITH (FORMAT BINARY)'
-+:command
-+
-+SELECT 'geometry', count(*) FROM tm.geoms_in i, tm.geoms o
-+WHERE i.id = o.id AND ST_OrderingEquals(i.g, o.g);
- 
- CREATE TABLE tm.geogs AS SELECT id,g::geography FROM tm.geoms
- WHERE geometrytype(g) NOT LIKE '%CURVE%'
-   AND geometrytype(g) NOT LIKE '%CIRCULAR%'
-   AND geometrytype(g) NOT LIKE '%SURFACE%'
-   AND geometrytype(g) NOT LIKE 'TRIANGLE%'
--  AND geometrytype(g) NOT LIKE 'TIN%'
--;
-+  AND geometrytype(g) NOT LIKE 'TIN%';
- 
--COPY tm.geogs TO :tmpfile WITH BINARY;
-+-- export
-+\set command '\\copy tm.geogs TO ':tmpfile' WITH (FORMAT BINARY)'
-+:command
-+
-+-- import
- CREATE TABLE tm.geogs_in AS SELECT * FROM tm.geogs LIMIT 0;
--COPY tm.geogs_in FROM :tmpfile WITH BINARY;
--SELECT 'geometry', count(*) FROM tm.geogs_in i, tm.geogs o WHERE i.id = o.id
-- AND ST_OrderingEquals(i.g::geometry, o.g::geometry);
-+\set command '\\copy tm.geogs_in FROM ':tmpfile' WITH (FORMAT BINARY)'
-+:command
-+
-+SELECT 'geometry', count(*) FROM tm.geogs_in i, tm.geogs o
-+WHERE i.id = o.id AND ST_OrderingEquals(i.g::geometry, o.g::geometry);
- 
- DROP SCHEMA tm CASCADE;
-+
-diff --git a/regress/core/tests.mk b/regress/core/tests.mk
-index 64a9254..94903c3 100644
---- a/regress/core/tests.mk
-+++ b/regress/core/tests.mk
-@@ -23,7 +23,6 @@ current_dir := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
- RUNTESTFLAGS_INTERNAL += \
-   --before-upgrade-script $(top_srcdir)/regress/hooks/hook-before-upgrade.sql \
-   --after-upgrade-script  $(top_srcdir)/regress/hooks/hook-after-upgrade.sql \
--  --after-create-script   $(top_srcdir)/regress/hooks/hook-after-create.sql \
-   --before-uninstall-script $(top_srcdir)/regress/hooks/hook-before-uninstall.sql
- 
- TESTS += \
-@@ -40,7 +39,6 @@ TESTS += \
- 	$(top_srcdir)/regress/core/dumppoints \
- 	$(top_srcdir)/regress/core/dumpsegments \
- 	$(top_srcdir)/regress/core/empty \
--	$(top_srcdir)/regress/core/estimatedextent \
- 	$(top_srcdir)/regress/core/forcecurve \
- 	$(top_srcdir)/regress/core/flatgeobuf \
- 	$(top_srcdir)/regress/core/geography \
-@@ -55,7 +53,6 @@ TESTS += \
- 	$(top_srcdir)/regress/core/out_marc21 \
- 	$(top_srcdir)/regress/core/in_encodedpolyline \
- 	$(top_srcdir)/regress/core/iscollection \
--	$(top_srcdir)/regress/core/legacy \
- 	$(top_srcdir)/regress/core/letters \
- 	$(top_srcdir)/regress/core/long_xact \
- 	$(top_srcdir)/regress/core/lwgeom_regress \
-@@ -112,7 +109,6 @@ TESTS += \
- 	$(top_srcdir)/regress/core/temporal_knn \
- 	$(top_srcdir)/regress/core/tickets \
- 	$(top_srcdir)/regress/core/twkb \
--	$(top_srcdir)/regress/core/typmod \
- 	$(top_srcdir)/regress/core/wkb \
- 	$(top_srcdir)/regress/core/wkt \
- 	$(top_srcdir)/regress/core/wmsservers \
-diff --git a/regress/loader/tests.mk b/regress/loader/tests.mk
-index 1fc77ac..c3cb9de 100644
---- a/regress/loader/tests.mk
-+++ b/regress/loader/tests.mk
-@@ -38,7 +38,5 @@ TESTS += \
- 	$(top_srcdir)/regress/loader/Latin1 \
- 	$(top_srcdir)/regress/loader/Latin1-implicit \
- 	$(top_srcdir)/regress/loader/mfile \
--	$(top_srcdir)/regress/loader/TestSkipANALYZE \
--	$(top_srcdir)/regress/loader/TestANALYZE \
- 	$(top_srcdir)/regress/loader/CharNoWidth
- 
-diff --git a/regress/run_test.pl b/regress/run_test.pl
-index 0ec5b2d..1c331f4 100755
---- a/regress/run_test.pl
-+++ b/regress/run_test.pl
-@@ -147,7 +147,6 @@ $ENV{"LANG"} = "C";
- # Add locale info to the psql options
- # Add pg12 precision suppression
- my $PGOPTIONS = $ENV{"PGOPTIONS"};
--$PGOPTIONS .= " -c lc_messages=C";
- $PGOPTIONS .= " -c client_min_messages=NOTICE";
- $PGOPTIONS .= " -c extra_float_digits=0";
- $ENV{"PGOPTIONS"} = $PGOPTIONS;

docker-compose/ext-src/postgis-src/postgis-regular-v17.patch

@@ -1,208 +0,0 @@
-diff --git a/raster/test/regress/tests.mk b/raster/test/regress/tests.mk
-index 00918e1..7e2b6cd 100644
---- a/raster/test/regress/tests.mk
-+++ b/raster/test/regress/tests.mk
-@@ -17,9 +17,7 @@ override RUNTESTFLAGS_INTERNAL := \
-   $(RUNTESTFLAGS_INTERNAL) \
-   --after-upgrade-script $(top_srcdir)/raster/test/regress/hooks/hook-after-upgrade-raster.sql
- 
--RASTER_TEST_FIRST = \
--	$(top_srcdir)/raster/test/regress/check_gdal \
--	$(top_srcdir)/raster/test/regress/loader/load_outdb
-+RASTER_TEST_FIRST =
- 
- RASTER_TEST_LAST = \
- 	$(top_srcdir)/raster/test/regress/clean
-@@ -33,9 +31,7 @@ RASTER_TEST_IO = \
- 
- RASTER_TEST_BASIC_FUNC = \
- 	$(top_srcdir)/raster/test/regress/rt_bytea \
--	$(top_srcdir)/raster/test/regress/rt_wkb \
- 	$(top_srcdir)/raster/test/regress/box3d \
--	$(top_srcdir)/raster/test/regress/rt_addband \
- 	$(top_srcdir)/raster/test/regress/rt_band \
- 	$(top_srcdir)/raster/test/regress/rt_tile
- 
-@@ -73,16 +69,10 @@ RASTER_TEST_BANDPROPS = \
- 	$(top_srcdir)/raster/test/regress/rt_neighborhood \
- 	$(top_srcdir)/raster/test/regress/rt_nearestvalue \
- 	$(top_srcdir)/raster/test/regress/rt_pixelofvalue \
--	$(top_srcdir)/raster/test/regress/rt_polygon \
--	$(top_srcdir)/raster/test/regress/rt_setbandpath
-+	$(top_srcdir)/raster/test/regress/rt_polygon
- 
- RASTER_TEST_UTILITY = \
- 	$(top_srcdir)/raster/test/regress/rt_utility \
--	$(top_srcdir)/raster/test/regress/rt_fromgdalraster \
--	$(top_srcdir)/raster/test/regress/rt_asgdalraster \
--	$(top_srcdir)/raster/test/regress/rt_astiff \
--	$(top_srcdir)/raster/test/regress/rt_asjpeg \
--	$(top_srcdir)/raster/test/regress/rt_aspng \
- 	$(top_srcdir)/raster/test/regress/rt_reclass \
- 	$(top_srcdir)/raster/test/regress/rt_gdalwarp \
- 	$(top_srcdir)/raster/test/regress/rt_gdalcontour \
-@@ -120,21 +110,13 @@ RASTER_TEST_SREL = \
- 
- RASTER_TEST_BUGS = \
- 	$(top_srcdir)/raster/test/regress/bug_test_car5 \
--	$(top_srcdir)/raster/test/regress/permitted_gdal_drivers \
- 	$(top_srcdir)/raster/test/regress/tickets
- 
- RASTER_TEST_LOADER = \
- 	$(top_srcdir)/raster/test/regress/loader/Basic \
- 	$(top_srcdir)/raster/test/regress/loader/Projected \
- 	$(top_srcdir)/raster/test/regress/loader/BasicCopy \
--	$(top_srcdir)/raster/test/regress/loader/BasicFilename \
--	$(top_srcdir)/raster/test/regress/loader/BasicOutDB \
--	$(top_srcdir)/raster/test/regress/loader/Tiled10x10 \
--	$(top_srcdir)/raster/test/regress/loader/Tiled10x10Copy \
--	$(top_srcdir)/raster/test/regress/loader/Tiled8x8 \
--	$(top_srcdir)/raster/test/regress/loader/TiledAuto \
--	$(top_srcdir)/raster/test/regress/loader/TiledAutoSkipNoData \
--	$(top_srcdir)/raster/test/regress/loader/TiledAutoCopyn
-+	$(top_srcdir)/raster/test/regress/loader/BasicFilename
- 
- RASTER_TESTS := $(RASTER_TEST_FIRST) \
- 	$(RASTER_TEST_METADATA) $(RASTER_TEST_IO) $(RASTER_TEST_BASIC_FUNC) \
-diff --git a/regress/core/binary.sql b/regress/core/binary.sql
-index 7a36b65..ad78fc7 100644
---- a/regress/core/binary.sql
-+++ b/regress/core/binary.sql
-@@ -1,4 +1,5 @@
- SET client_min_messages TO warning;
-+
- CREATE SCHEMA tm;
- 
- CREATE TABLE tm.geoms (id serial, g geometry);
-@@ -31,24 +32,39 @@ SELECT st_force4d(g) FROM tm.geoms WHERE id < 15 ORDER BY id;
- INSERT INTO tm.geoms(g)
- SELECT st_setsrid(g,4326) FROM tm.geoms ORDER BY id;
- 
--COPY tm.geoms TO :tmpfile WITH BINARY;
-+-- define temp file path
-+\set tmpfile '/tmp/postgis_binary_test.dat'
-+
-+-- export
-+\set command '\\copy tm.geoms TO ':tmpfile' WITH (FORMAT BINARY)'
-+:command
-+
-+-- import
- CREATE TABLE tm.geoms_in AS SELECT * FROM tm.geoms LIMIT 0;
--COPY tm.geoms_in FROM :tmpfile WITH BINARY;
--SELECT 'geometry', count(*) FROM tm.geoms_in i, tm.geoms o WHERE i.id = o.id
-- AND ST_OrderingEquals(i.g, o.g);
-+\set command '\\copy tm.geoms_in FROM ':tmpfile' WITH (FORMAT BINARY)'
-+:command
-+
-+SELECT 'geometry', count(*) FROM tm.geoms_in i, tm.geoms o
-+WHERE i.id = o.id AND ST_OrderingEquals(i.g, o.g);
- 
- CREATE TABLE tm.geogs AS SELECT id,g::geography FROM tm.geoms
- WHERE geometrytype(g) NOT LIKE '%CURVE%'
-   AND geometrytype(g) NOT LIKE '%CIRCULAR%'
-   AND geometrytype(g) NOT LIKE '%SURFACE%'
-   AND geometrytype(g) NOT LIKE 'TRIANGLE%'
--  AND geometrytype(g) NOT LIKE 'TIN%'
--;
-+  AND geometrytype(g) NOT LIKE 'TIN%';
- 
--COPY tm.geogs TO :tmpfile WITH BINARY;
-+-- export
-+\set command '\\copy tm.geogs TO ':tmpfile' WITH (FORMAT BINARY)'
-+:command
-+
-+-- import
- CREATE TABLE tm.geogs_in AS SELECT * FROM tm.geogs LIMIT 0;
--COPY tm.geogs_in FROM :tmpfile WITH BINARY;
--SELECT 'geometry', count(*) FROM tm.geogs_in i, tm.geogs o WHERE i.id = o.id
-- AND ST_OrderingEquals(i.g::geometry, o.g::geometry);
-+\set command '\\copy tm.geogs_in FROM ':tmpfile' WITH (FORMAT BINARY)'
-+:command
-+
-+SELECT 'geometry', count(*) FROM tm.geogs_in i, tm.geogs o
-+WHERE i.id = o.id AND ST_OrderingEquals(i.g::geometry, o.g::geometry);
- 
- DROP SCHEMA tm CASCADE;
-+
-diff --git a/regress/core/tests.mk b/regress/core/tests.mk
-index 90987df..74fe3f1 100644
---- a/regress/core/tests.mk
-+++ b/regress/core/tests.mk
-@@ -16,14 +16,13 @@ POSTGIS_PGSQL_VERSION=170
- POSTGIS_GEOS_VERSION=31101
- HAVE_JSON=yes
- HAVE_SPGIST=yes
--INTERRUPTTESTS=yes
-+INTERRUPTTESTS=no
- 
- current_dir := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
- 
- RUNTESTFLAGS_INTERNAL += \
-   --before-upgrade-script $(top_srcdir)/regress/hooks/hook-before-upgrade.sql \
-   --after-upgrade-script  $(top_srcdir)/regress/hooks/hook-after-upgrade.sql \
--  --after-create-script   $(top_srcdir)/regress/hooks/hook-after-create.sql \
-   --before-uninstall-script $(top_srcdir)/regress/hooks/hook-before-uninstall.sql
- 
- TESTS += \
-@@ -40,7 +39,6 @@ TESTS += \
- 	$(top_srcdir)/regress/core/dumppoints \
- 	$(top_srcdir)/regress/core/dumpsegments \
- 	$(top_srcdir)/regress/core/empty \
--	$(top_srcdir)/regress/core/estimatedextent \
- 	$(top_srcdir)/regress/core/forcecurve \
- 	$(top_srcdir)/regress/core/flatgeobuf \
- 	$(top_srcdir)/regress/core/frechet \
-@@ -60,7 +58,6 @@ TESTS += \
- 	$(top_srcdir)/regress/core/out_marc21 \
- 	$(top_srcdir)/regress/core/in_encodedpolyline \
- 	$(top_srcdir)/regress/core/iscollection \
--	$(top_srcdir)/regress/core/legacy \
- 	$(top_srcdir)/regress/core/letters \
- 	$(top_srcdir)/regress/core/lwgeom_regress \
- 	$(top_srcdir)/regress/core/measures \
-@@ -119,7 +116,6 @@ TESTS += \
- 	$(top_srcdir)/regress/core/temporal_knn \
- 	$(top_srcdir)/regress/core/tickets \
- 	$(top_srcdir)/regress/core/twkb \
--	$(top_srcdir)/regress/core/typmod \
- 	$(top_srcdir)/regress/core/wkb \
- 	$(top_srcdir)/regress/core/wkt \
- 	$(top_srcdir)/regress/core/wmsservers \
-diff --git a/regress/loader/tests.mk b/regress/loader/tests.mk
-index ac4f8ad..4bad4fc 100644
---- a/regress/loader/tests.mk
-+++ b/regress/loader/tests.mk
-@@ -38,7 +38,5 @@ TESTS += \
- 	$(top_srcdir)/regress/loader/Latin1 \
- 	$(top_srcdir)/regress/loader/Latin1-implicit \
- 	$(top_srcdir)/regress/loader/mfile \
--	$(top_srcdir)/regress/loader/TestSkipANALYZE \
--	$(top_srcdir)/regress/loader/TestANALYZE \
- 	$(top_srcdir)/regress/loader/CharNoWidth \
- 
-diff --git a/regress/run_test.pl b/regress/run_test.pl
-index cac4b2e..4c7c82b 100755
---- a/regress/run_test.pl
-+++ b/regress/run_test.pl
-@@ -238,7 +238,6 @@ $ENV{"LANG"} = "C";
- # Add locale info to the psql options
- # Add pg12 precision suppression
- my $PGOPTIONS = $ENV{"PGOPTIONS"};
--$PGOPTIONS .= " -c lc_messages=C";
- $PGOPTIONS .= " -c client_min_messages=NOTICE";
- $PGOPTIONS .= " -c extra_float_digits=0";
- $ENV{"PGOPTIONS"} = $PGOPTIONS;
-diff --git a/topology/test/tests.mk b/topology/test/tests.mk
-index cbe2633..2c7c18f 100644
---- a/topology/test/tests.mk
-+++ b/topology/test/tests.mk
-@@ -46,9 +46,7 @@ TESTS += \
- 	$(top_srcdir)/topology/test/regress/legacy_query.sql \
- 	$(top_srcdir)/topology/test/regress/legacy_validate.sql \
- 	$(top_srcdir)/topology/test/regress/polygonize.sql \
--	$(top_srcdir)/topology/test/regress/populate_topology_layer.sql \
- 	$(top_srcdir)/topology/test/regress/removeunusedprimitives.sql \
--	$(top_srcdir)/topology/test/regress/renametopogeometrycolumn.sql \
- 	$(top_srcdir)/topology/test/regress/renametopology.sql \
- 	$(top_srcdir)/topology/test/regress/share_sequences.sql \
- 	$(top_srcdir)/topology/test/regress/sqlmm.sql \

docker-compose/ext-src/postgis-src/regular-test.sh

@@ -1,17 +0,0 @@
-#!/bin/bash
-set -ex
-cd "$(dirname "${0}")"
-dropdb --if-exist contrib_regression
-createdb contrib_regression
-psql -d contrib_regression -c "ALTER DATABASE contrib_regression SET TimeZone='UTC'" \
-     -c "ALTER DATABASE contrib_regression SET DateStyle='ISO, MDY'" \
-     -c "CREATE EXTENSION postgis SCHEMA public" \
-     -c "CREATE EXTENSION postgis_topology" \
-     -c "CREATE EXTENSION postgis_tiger_geocoder CASCADE" \
-     -c "CREATE EXTENSION postgis_raster SCHEMA public" \
-     -c "CREATE EXTENSION postgis_sfcgal SCHEMA public"
-patch -p1 <"postgis-common-${PG_VERSION}.patch"
-patch -p1 <"postgis-regular-${PG_VERSION}.patch"
-psql -d contrib_regression -f raster_outdb_template.sql
-trap 'patch -R -p1 <postgis-regular-${PG_VERSION}.patch && patch -R -p1 <"postgis-common-${PG_VERSION}.patch"' EXIT
-POSTGIS_REGRESS_DB=contrib_regression RUNTESTFLAGS=--nocreate make installcheck-base

docker-compose/run-tests.sh

@@ -63,9 +63,5 @@ done
 for d in ${FAILED}; do
   cat "$(find $d -name regression.diffs)"
 done
-for postgis_diff in /tmp/pgis_reg/*_diff; do
-  echo "${postgis_diff}:"
-  cat "${postgis_diff}"
-done
 echo "${FAILED}"
 exit 1

docker-compose/test_extensions_upgrade.sh

@@ -82,8 +82,7 @@ EXTENSIONS='[
 {"extname": "pg_ivm", "extdir": "pg_ivm-src"},
 {"extname": "pgjwt", "extdir": "pgjwt-src"},
 {"extname": "pgtap", "extdir": "pgtap-src"},
-{"extname": "pg_repack", "extdir": "pg_repack-src"},
-{"extname": "h3", "extdir": "h3-pg-src"}
+{"extname": "pg_repack", "extdir": "pg_repack-src"}
 ]'
 EXTNAMES=$(echo ${EXTENSIONS} | jq -r '.[].extname' | paste -sd ' ' -)
 COMPUTE_TAG=${NEW_COMPUTE_TAG} docker compose --profile test-extensions up --quiet-pull --build -d

libs/compute_api/src/spec.rs

@@ -178,9 +178,9 @@ pub struct ComputeSpec {
     /// JWT for authorizing requests to endpoint storage service
     pub endpoint_storage_token: Option<String>,
 
-    /// Download LFC state from endpoint_storage and pass it to Postgres on startup
+    /// If true, download LFC state from endpoint_storage and pass it to Postgres on startup
     #[serde(default)]
-    pub autoprewarm: bool,
+    pub prewarm_lfc_on_startup: bool,
 }
 
 /// Feature flag to signal `compute_ctl` to enable certain experimental functionality.
@@ -192,9 +192,6 @@ pub enum ComputeFeature {
     /// track short-lived connections as user activity.
     ActivityMonitorExperimental,
 
-    /// Enable TLS functionality.
-    TlsExperimental,
-
     /// This is a special feature flag that is used to represent unknown feature flags.
     /// Basically all unknown to enum flags are represented as this one. See unit test
     /// `parse_unknown_features()` for more details.
@@ -253,44 +250,34 @@ impl RemoteExtSpec {
         }
 
         match self.extension_data.get(real_ext_name) {
-            Some(_ext_data) => Ok((
-                real_ext_name.to_string(),
-                Self::build_remote_path(build_tag, pg_major_version, real_ext_name)?,
-            )),
+            Some(_ext_data) => {
+                // We have decided to use the Go naming convention due to Kubernetes.
+
+                let arch = match std::env::consts::ARCH {
+                    "x86_64" => "amd64",
+                    "aarch64" => "arm64",
+                    arch => arch,
+                };
+
+                // Construct the path to the extension archive
+                // BUILD_TAG/PG_MAJOR_VERSION/extensions/EXTENSION_NAME.tar.zst
+                //
+                // Keep it in sync with path generation in
+                // https://github.com/neondatabase/build-custom-extensions/tree/main
+                let archive_path_str = format!(
+                    "{build_tag}/{arch}/{pg_major_version}/extensions/{real_ext_name}.tar.zst"
+                );
+                Ok((
+                    real_ext_name.to_string(),
+                    RemotePath::from_string(&archive_path_str)?,
+                ))
+            }
             None => Err(anyhow::anyhow!(
                 "real_ext_name {} is not found",
                 real_ext_name
             )),
         }
     }
-
-    /// Get the architecture-specific portion of the remote extension path. We
-    /// use the Go naming convention due to Kubernetes.
-    fn get_arch() -> &'static str {
-        match std::env::consts::ARCH {
-            "x86_64" => "amd64",
-            "aarch64" => "arm64",
-            arch => arch,
-        }
-    }
-
-    /// Build a [`RemotePath`] for an extension.
-    fn build_remote_path(
-        build_tag: &str,
-        pg_major_version: &str,
-        ext_name: &str,
-    ) -> anyhow::Result<RemotePath> {
-        let arch = Self::get_arch();
-
-        // Construct the path to the extension archive
-        // BUILD_TAG/PG_MAJOR_VERSION/extensions/EXTENSION_NAME.tar.zst
-        //
-        // Keep it in sync with path generation in
-        // https://github.com/neondatabase/build-custom-extensions/tree/main
-        RemotePath::from_string(&format!(
-            "{build_tag}/{arch}/{pg_major_version}/extensions/{ext_name}.tar.zst"
-        ))
-    }
 }
 
 #[derive(Clone, Copy, Debug, Default, Eq, PartialEq, Deserialize, Serialize)]
@@ -531,37 +518,6 @@ mod tests {
             .expect("Library should be found");
     }
 
-    #[test]
-    fn remote_extension_path() {
-        let rspec: RemoteExtSpec = serde_json::from_value(serde_json::json!({
-            "public_extensions": ["ext"],
-            "custom_extensions": [],
-            "library_index": {
-                "extlib": "ext",
-            },
-            "extension_data": {
-                "ext": {
-                    "control_data": {
-                        "ext.control": ""
-                    },
-                    "archive_path": ""
-                }
-            },
-        }))
-        .unwrap();
-
-        let (_ext_name, ext_path) = rspec
-            .get_ext("ext", false, "latest", "v17")
-            .expect("Extension should be found");
-        // Starting with a forward slash would have consequences for the
-        // Url::join() that occurs when downloading a remote extension.
-        assert!(!ext_path.to_string().starts_with("/"));
-        assert_eq!(
-            ext_path,
-            RemoteExtSpec::build_remote_path("latest", "v17", "ext").unwrap()
-        );
-    }
-
     #[test]
     fn parse_spec_file() {
         let file = File::open("tests/cluster_spec.json").unwrap();

libs/compute_api/tests/cluster_spec.json

@@ -85,7 +85,7 @@
                 "vartype": "bool"
             },
             {
-                "name": "autoprewarm",
+                "name": "prewarm_lfc_on_startup",
                 "value": "off",
                 "vartype": "bool"
             },

libs/metrics/src/hll.rs

@@ -107,7 +107,7 @@ impl<const N: usize> MetricType for HyperLogLogState<N> {
 }
 
 impl<const N: usize> HyperLogLogState<N> {
-    pub fn measure(&self, item: &(impl Hash + ?Sized)) {
+    pub fn measure(&self, item: &impl Hash) {
         // changing the hasher will break compatibility with previous measurements.
         self.record(BuildHasherDefault::<xxh3::Hash64>::default().hash_one(item));
     }

libs/metrics/src/lib.rs

@@ -27,7 +27,6 @@ pub use prometheus::{
 
 pub mod launch_timestamp;
 mod wrappers;
-pub use prometheus;
 pub use wrappers::{CountedReader, CountedWriter};
 mod hll;
 pub use hll::{HyperLogLog, HyperLogLogState, HyperLogLogVec};

libs/neon-shmem/Cargo.toml

@@ -6,12 +6,8 @@ license.workspace = true
 
 [dependencies]
 thiserror.workspace = true
-nix.workspace = true
+nix.workspace=true
 workspace_hack = { version = "0.1", path = "../../workspace_hack" }
 
-[dev-dependencies]
-rand = "0.9.1"
-rand_distr = "0.5.1"
-
 [target.'cfg(target_os = "macos")'.dependencies]
 tempfile = "3.14.0"

libs/neon-shmem/src/hash.rs

@@ -1,304 +0,0 @@
-//! Hash table implementation on top of 'shmem'
-//!
-//! Features required in the long run by the communicator project:
-//!
-//! [X] Accessible from both Postgres processes and rust threads in the communicator process
-//! [X] Low latency
-//! [ ] Scalable to lots of concurrent accesses (currently relies on caller for locking)
-//! [ ] Resizable
-
-use std::fmt::Debug;
-use std::hash::{DefaultHasher, Hash, Hasher};
-use std::mem::MaybeUninit;
-
-use crate::shmem::ShmemHandle;
-
-mod core;
-pub mod entry;
-
-#[cfg(test)]
-mod tests;
-
-use core::CoreHashMap;
-use entry::{Entry, OccupiedEntry};
-
-#[derive(Debug)]
-pub struct OutOfMemoryError();
-
-pub struct HashMapInit<'a, K, V> {
-    // Hash table can be allocated in a fixed memory area, or in a resizeable ShmemHandle.
-    shmem_handle: Option<ShmemHandle>,
-    shared_ptr: *mut HashMapShared<'a, K, V>,
-}
-
-pub struct HashMapAccess<'a, K, V> {
-    shmem_handle: Option<ShmemHandle>,
-    shared_ptr: *mut HashMapShared<'a, K, V>,
-}
-
-unsafe impl<'a, K: Sync, V: Sync> Sync for HashMapAccess<'a, K, V> {}
-unsafe impl<'a, K: Send, V: Send> Send for HashMapAccess<'a, K, V> {}
-
-impl<'a, K, V> HashMapInit<'a, K, V> {
-    pub fn attach_writer(self) -> HashMapAccess<'a, K, V> {
-        HashMapAccess {
-            shmem_handle: self.shmem_handle,
-            shared_ptr: self.shared_ptr,
-        }
-    }
-
-    pub fn attach_reader(self) -> HashMapAccess<'a, K, V> {
-        // no difference to attach_writer currently
-        self.attach_writer()
-    }
-}
-
-/// This is stored in the shared memory area
-///
-/// NOTE: We carve out the parts from a contiguous chunk. Growing and shrinking the hash table
-/// relies on the memory layout! The data structures are laid out in the contiguous shared memory
-/// area as follows:
-///
-/// HashMapShared
-/// [buckets]
-/// [dictionary]
-///
-/// In between the above parts, there can be padding bytes to align the parts correctly.
-struct HashMapShared<'a, K, V> {
-    inner: CoreHashMap<'a, K, V>,
-}
-
-impl<'a, K, V> HashMapInit<'a, K, V>
-where
-    K: Clone + Hash + Eq,
-{
-    pub fn estimate_size(num_buckets: u32) -> usize {
-        // add some margin to cover alignment etc.
-        CoreHashMap::<K, V>::estimate_size(num_buckets) + size_of::<HashMapShared<K, V>>() + 1000
-    }
-
-    pub fn init_in_fixed_area(
-        num_buckets: u32,
-        area: &'a mut [MaybeUninit<u8>],
-    ) -> HashMapInit<'a, K, V> {
-        Self::init_common(num_buckets, None, area.as_mut_ptr().cast(), area.len())
-    }
-
-    /// Initialize a new hash map in the given shared memory area
-    pub fn init_in_shmem(num_buckets: u32, mut shmem: ShmemHandle) -> HashMapInit<'a, K, V> {
-        let size = Self::estimate_size(num_buckets);
-        shmem
-            .set_size(size)
-            .expect("could not resize shared memory area");
-
-        let ptr = unsafe { shmem.data_ptr.as_mut() };
-        Self::init_common(num_buckets, Some(shmem), ptr, size)
-    }
-
-    fn init_common(
-        num_buckets: u32,
-        shmem_handle: Option<ShmemHandle>,
-        area_ptr: *mut u8,
-        area_len: usize,
-    ) -> HashMapInit<'a, K, V> {
-        // carve out the HashMapShared struct from the area.
-        let mut ptr: *mut u8 = area_ptr;
-        let end_ptr: *mut u8 = unsafe { area_ptr.add(area_len) };
-        ptr = unsafe { ptr.add(ptr.align_offset(align_of::<HashMapShared<K, V>>())) };
-        let shared_ptr: *mut HashMapShared<K, V> = ptr.cast();
-        ptr = unsafe { ptr.add(size_of::<HashMapShared<K, V>>()) };
-
-        // carve out the buckets
-        ptr = unsafe { ptr.byte_add(ptr.align_offset(align_of::<core::Bucket<K, V>>())) };
-        let buckets_ptr = ptr;
-        ptr = unsafe { ptr.add(size_of::<core::Bucket<K, V>>() * num_buckets as usize) };
-
-        // use remaining space for the dictionary
-        ptr = unsafe { ptr.byte_add(ptr.align_offset(align_of::<u32>())) };
-        assert!(ptr.addr() < end_ptr.addr());
-        let dictionary_ptr = ptr;
-        let dictionary_size = unsafe { end_ptr.byte_offset_from(ptr) / size_of::<u32>() as isize };
-        assert!(dictionary_size > 0);
-
-        let buckets =
-            unsafe { std::slice::from_raw_parts_mut(buckets_ptr.cast(), num_buckets as usize) };
-        let dictionary = unsafe {
-            std::slice::from_raw_parts_mut(dictionary_ptr.cast(), dictionary_size as usize)
-        };
-        let hashmap = CoreHashMap::new(buckets, dictionary);
-        unsafe {
-            std::ptr::write(shared_ptr, HashMapShared { inner: hashmap });
-        }
-
-        HashMapInit {
-            shmem_handle: shmem_handle,
-            shared_ptr,
-        }
-    }
-}
-
-impl<'a, K, V> HashMapAccess<'a, K, V>
-where
-    K: Clone + Hash + Eq,
-{
-    pub fn get_hash_value(&self, key: &K) -> u64 {
-        let mut hasher = DefaultHasher::new();
-        key.hash(&mut hasher);
-        hasher.finish()
-    }
-
-    pub fn get_with_hash<'e>(&'e self, key: &K, hash: u64) -> Option<&'e V> {
-        let map = unsafe { self.shared_ptr.as_ref() }.unwrap();
-
-        map.inner.get_with_hash(key, hash)
-    }
-
-    pub fn entry_with_hash(&mut self, key: K, hash: u64) -> Entry<'a, '_, K, V> {
-        let map = unsafe { self.shared_ptr.as_mut() }.unwrap();
-
-        map.inner.entry_with_hash(key, hash)
-    }
-
-    pub fn remove_with_hash(&mut self, key: &K, hash: u64) {
-        let map = unsafe { self.shared_ptr.as_mut() }.unwrap();
-
-        match map.inner.entry_with_hash(key.clone(), hash) {
-            Entry::Occupied(e) => {
-                e.remove();
-            }
-            Entry::Vacant(_) => {}
-        };
-    }
-
-    pub fn entry_at_bucket(&mut self, pos: usize) -> Option<OccupiedEntry<'a, '_, K, V>> {
-        let map = unsafe { self.shared_ptr.as_mut() }.unwrap();
-        map.inner.entry_at_bucket(pos)
-    }
-
-    pub fn get_num_buckets(&self) -> usize {
-        let map = unsafe { self.shared_ptr.as_ref() }.unwrap();
-        map.inner.get_num_buckets()
-    }
-
-    /// Return the key and value stored in bucket with given index. This can be used to
-    /// iterate through the hash map. (An Iterator might be nicer. The communicator's
-    /// clock algorithm needs to _slowly_ iterate through all buckets with its clock hand,
-    /// without holding a lock. If we switch to an Iterator, it must not hold the lock.)
-    pub fn get_at_bucket(&self, pos: usize) -> Option<&(K, V)> {
-        let map = unsafe { self.shared_ptr.as_ref() }.unwrap();
-
-        if pos >= map.inner.buckets.len() {
-            return None;
-        }
-        let bucket = &map.inner.buckets[pos];
-        bucket.inner.as_ref()
-    }
-
-    pub fn get_bucket_for_value(&self, val_ptr: *const V) -> usize {
-        let map = unsafe { self.shared_ptr.as_ref() }.unwrap();
-
-        let origin = map.inner.buckets.as_ptr();
-        let idx = (val_ptr as usize - origin as usize) / (size_of::<V>() as usize);
-        assert!(idx < map.inner.buckets.len());
-
-        idx
-    }
-
-    // for metrics
-    pub fn get_num_buckets_in_use(&self) -> usize {
-        let map = unsafe { self.shared_ptr.as_ref() }.unwrap();
-        map.inner.buckets_in_use as usize
-    }
-
-    /// Grow
-    ///
-    /// 1. grow the underlying shared memory area
-    /// 2. Initialize new buckets. This overwrites the current dictionary
-    /// 3. Recalculate the dictionary
-    pub fn grow(&mut self, num_buckets: u32) -> Result<(), crate::shmem::Error> {
-        let map = unsafe { self.shared_ptr.as_mut() }.unwrap();
-        let inner = &mut map.inner;
-        let old_num_buckets = inner.buckets.len() as u32;
-
-        if num_buckets < old_num_buckets {
-            panic!("grow called with a smaller number of buckets");
-        }
-        if num_buckets == old_num_buckets {
-            return Ok(());
-        }
-        let shmem_handle = self
-            .shmem_handle
-            .as_ref()
-            .expect("grow called on a fixed-size hash table");
-
-        let size_bytes = HashMapInit::<K, V>::estimate_size(num_buckets);
-        shmem_handle.set_size(size_bytes)?;
-        let end_ptr: *mut u8 = unsafe { shmem_handle.data_ptr.as_ptr().add(size_bytes) };
-
-        // Initialize new buckets. The new buckets are linked to the free list. NB: This overwrites
-        // the dictionary!
-        let buckets_ptr = inner.buckets.as_mut_ptr();
-        unsafe {
-            for i in old_num_buckets..num_buckets {
-                let bucket_ptr = buckets_ptr.add(i as usize);
-                bucket_ptr.write(core::Bucket {
-                    next: if i < num_buckets {
-                        i as u32 + 1
-                    } else {
-                        inner.free_head
-                    },
-                    inner: None,
-                });
-            }
-        }
-
-        // Recalculate the dictionary
-        let buckets;
-        let dictionary;
-        unsafe {
-            let buckets_end_ptr = buckets_ptr.add(num_buckets as usize);
-            let dictionary_ptr: *mut u32 = buckets_end_ptr
-                .byte_add(buckets_end_ptr.align_offset(align_of::<u32>()))
-                .cast();
-            let dictionary_size: usize =
-                end_ptr.byte_offset_from(buckets_end_ptr) as usize / size_of::<u32>();
-
-            buckets = std::slice::from_raw_parts_mut(buckets_ptr, num_buckets as usize);
-            dictionary = std::slice::from_raw_parts_mut(dictionary_ptr, dictionary_size);
-        }
-        for i in 0..dictionary.len() {
-            dictionary[i] = core::INVALID_POS;
-        }
-
-        for i in 0..old_num_buckets as usize {
-            if buckets[i].inner.is_none() {
-                continue;
-            }
-
-            let mut hasher = DefaultHasher::new();
-            buckets[i].inner.as_ref().unwrap().0.hash(&mut hasher);
-            let hash = hasher.finish();
-
-            let pos: usize = (hash % dictionary.len() as u64) as usize;
-            buckets[i].next = dictionary[pos];
-            dictionary[pos] = i as u32;
-        }
-
-        // Finally, update the CoreHashMap struct
-        inner.dictionary = dictionary;
-        inner.buckets = buckets;
-        inner.free_head = old_num_buckets;
-
-        Ok(())
-    }
-
-    // TODO: Shrinking is a multi-step process that requires co-operation from the caller
-    //
-    // 1. The caller must first call begin_shrink(). That forbids allocation of higher-numbered
-    // buckets.
-    //
-    // 2. Next, the caller must evict all entries in higher-numbered buckets.
-    //
-    // 3. Finally, call finish_shrink(). This recomputes the dictionary and shrinks the underlying
-    //    shmem area
-}

libs/neon-shmem/src/hash/core.rs

@@ -1,174 +0,0 @@
-//! Simple hash table with chaining
-//!
-//! # Resizing
-//!
-
-use std::hash::Hash;
-use std::mem::MaybeUninit;
-
-use crate::hash::entry::{Entry, OccupiedEntry, PrevPos, VacantEntry};
-
-pub(crate) const INVALID_POS: u32 = u32::MAX;
-
-// Bucket
-pub(crate) struct Bucket<K, V> {
-    pub(crate) next: u32,
-    pub(crate) inner: Option<(K, V)>,
-}
-
-pub(crate) struct CoreHashMap<'a, K, V> {
-    pub(crate) dictionary: &'a mut [u32],
-    pub(crate) buckets: &'a mut [Bucket<K, V>],
-    pub(crate) free_head: u32,
-
-    pub(crate) _user_list_head: u32,
-
-    // metrics
-    pub(crate) buckets_in_use: u32,
-}
-
-#[derive(Debug)]
-pub struct FullError();
-
-impl<'a, K: Hash + Eq, V> CoreHashMap<'a, K, V>
-where
-    K: Clone + Hash + Eq,
-{
-    const FILL_FACTOR: f32 = 0.60;
-
-    pub fn estimate_size(num_buckets: u32) -> usize {
-        let mut size = 0;
-
-        // buckets
-        size += size_of::<Bucket<K, V>>() * num_buckets as usize;
-
-        // dictionary
-        size += (f32::ceil((size_of::<u32>() * num_buckets as usize) as f32 / Self::FILL_FACTOR))
-            as usize;
-
-        size
-    }
-
-    pub fn new(
-        buckets: &'a mut [MaybeUninit<Bucket<K, V>>],
-        dictionary: &'a mut [MaybeUninit<u32>],
-    ) -> CoreHashMap<'a, K, V> {
-        // Initialize the buckets
-        for i in 0..buckets.len() {
-            buckets[i].write(Bucket {
-                next: if i < buckets.len() - 1 {
-                    i as u32 + 1
-                } else {
-                    INVALID_POS
-                },
-                inner: None,
-            });
-        }
-
-        // Initialize the dictionary
-        for i in 0..dictionary.len() {
-            dictionary[i].write(INVALID_POS);
-        }
-
-        // TODO: use std::slice::assume_init_mut() once it stabilizes
-        let buckets =
-            unsafe { std::slice::from_raw_parts_mut(buckets.as_mut_ptr().cast(), buckets.len()) };
-        let dictionary = unsafe {
-            std::slice::from_raw_parts_mut(dictionary.as_mut_ptr().cast(), dictionary.len())
-        };
-
-        CoreHashMap {
-            dictionary,
-            buckets,
-            free_head: 0,
-            buckets_in_use: 0,
-            _user_list_head: INVALID_POS,
-        }
-    }
-
-    pub fn get_with_hash(&self, key: &K, hash: u64) -> Option<&V> {
-        let mut next = self.dictionary[hash as usize % self.dictionary.len()];
-        loop {
-            if next == INVALID_POS {
-                return None;
-            }
-
-            let bucket = &self.buckets[next as usize];
-            let (bucket_key, bucket_value) = bucket.inner.as_ref().expect("entry is in use");
-            if bucket_key == key {
-                return Some(&bucket_value);
-            }
-            next = bucket.next;
-        }
-    }
-
-    // all updates are done through Entry
-    pub fn entry_with_hash(&mut self, key: K, hash: u64) -> Entry<'a, '_, K, V> {
-        let dict_pos = hash as usize % self.dictionary.len();
-        let first = self.dictionary[dict_pos];
-        if first == INVALID_POS {
-            // no existing entry
-            return Entry::Vacant(VacantEntry {
-                map: self,
-                key,
-                dict_pos: dict_pos as u32,
-            });
-        }
-
-        let mut prev_pos = PrevPos::First(dict_pos as u32);
-        let mut next = first;
-        loop {
-            let bucket = &mut self.buckets[next as usize];
-            let (bucket_key, _bucket_value) = bucket.inner.as_mut().expect("entry is in use");
-            if *bucket_key == key {
-                // found existing entry
-                return Entry::Occupied(OccupiedEntry {
-                    map: self,
-                    _key: key,
-                    prev_pos,
-                    bucket_pos: next,
-                });
-            }
-
-            if bucket.next == INVALID_POS {
-                // No existing entry
-                return Entry::Vacant(VacantEntry {
-                    map: self,
-                    key,
-                    dict_pos: dict_pos as u32,
-                });
-            }
-            prev_pos = PrevPos::Chained(next);
-            next = bucket.next;
-        }
-    }
-
-    pub fn get_num_buckets(&self) -> usize {
-        self.buckets.len()
-    }
-
-    pub fn entry_at_bucket(&mut self, pos: usize) -> Option<OccupiedEntry<K, V>> {
-        if pos >= self.buckets.len() {
-            return None;
-        }
-
-        todo!()
-        //self.buckets[pos].inner.as_ref()
-    }
-
-    pub(crate) fn alloc_bucket(&mut self, key: K, value: V) -> Result<u32, FullError> {
-        let pos = self.free_head;
-        if pos == INVALID_POS {
-            return Err(FullError());
-        }
-
-        let bucket = &mut self.buckets[pos as usize];
-        self.free_head = bucket.next;
-        self.buckets_in_use += 1;
-
-        bucket.next = INVALID_POS;
-        bucket.inner = Some((key, value));
-
-        return Ok(pos);
-    }
-}

libs/neon-shmem/src/hash/entry.rs

@@ -1,91 +0,0 @@
-//! Like std::collections::hash_map::Entry;
-
-use crate::hash::core::{CoreHashMap, FullError, INVALID_POS};
-
-use std::hash::Hash;
-use std::mem;
-
-pub enum Entry<'a, 'b, K, V> {
-    Occupied(OccupiedEntry<'a, 'b, K, V>),
-    Vacant(VacantEntry<'a, 'b, K, V>),
-}
-
-pub(crate) enum PrevPos {
-    First(u32),
-    Chained(u32),
-}
-
-pub struct OccupiedEntry<'a, 'b, K, V> {
-    pub(crate) map: &'b mut CoreHashMap<'a, K, V>,
-    pub(crate) _key: K, // The key of the occupied entry
-    pub(crate) prev_pos: PrevPos,
-    pub(crate) bucket_pos: u32, // The position of the bucket in the CoreHashMap's buckets array
-}
-
-impl<'a, 'b, K, V> OccupiedEntry<'a, 'b, K, V> {
-    pub fn get(&self) -> &V {
-        &self.map.buckets[self.bucket_pos as usize]
-            .inner
-            .as_ref()
-            .unwrap()
-            .1
-    }
-
-    pub fn get_mut(&mut self) -> &mut V {
-        &mut self.map.buckets[self.bucket_pos as usize]
-            .inner
-            .as_mut()
-            .unwrap()
-            .1
-    }
-
-    pub fn insert(&mut self, value: V) -> V {
-        let bucket = &mut self.map.buckets[self.bucket_pos as usize];
-        // This assumes inner is Some, which it must be for an OccupiedEntry
-        let old_value = mem::replace(&mut bucket.inner.as_mut().unwrap().1, value);
-        old_value
-    }
-
-    pub fn remove(self) -> V {
-        // CoreHashMap::remove returns Option<(K, V)>. We know it's Some for an OccupiedEntry.
-        let bucket = &mut self.map.buckets[self.bucket_pos as usize];
-
-        // unlink it from the chain
-        match self.prev_pos {
-            PrevPos::First(dict_pos) => self.map.dictionary[dict_pos as usize] = bucket.next,
-            PrevPos::Chained(bucket_pos) => {
-                self.map.buckets[bucket_pos as usize].next = bucket.next
-            }
-        }
-
-        // and add it to the freelist
-        let bucket = &mut self.map.buckets[self.bucket_pos as usize];
-        let old_value = bucket.inner.take();
-        bucket.next = self.map.free_head;
-        self.map.free_head = self.bucket_pos;
-        self.map.buckets_in_use -= 1;
-
-        return old_value.unwrap().1;
-    }
-}
-
-pub struct VacantEntry<'a, 'b, K, V> {
-    pub(crate) map: &'b mut CoreHashMap<'a, K, V>,
-    pub(crate) key: K, // The key to insert
-    pub(crate) dict_pos: u32,
-}
-
-impl<'a, 'b, K: Clone + Hash + Eq, V> VacantEntry<'a, 'b, K, V> {
-    pub fn insert(self, value: V) -> Result<&'b mut V, FullError> {
-        let pos = self.map.alloc_bucket(self.key, value)?;
-        if pos == INVALID_POS {
-            return Err(FullError());
-        }
-        let bucket = &mut self.map.buckets[pos as usize];
-        bucket.next = self.map.dictionary[self.dict_pos as usize];
-        self.map.dictionary[self.dict_pos as usize] = pos;
-
-        let result = &mut self.map.buckets[pos as usize].inner.as_mut().unwrap().1;
-        return Ok(result);
-    }
-}

libs/neon-shmem/src/hash/tests.rs

@@ -1,220 +0,0 @@
-use std::collections::BTreeMap;
-use std::collections::HashSet;
-use std::fmt::{Debug, Formatter};
-use std::sync::atomic::{AtomicUsize, Ordering};
-
-use crate::hash::HashMapAccess;
-use crate::hash::HashMapInit;
-use crate::hash::UpdateAction;
-use crate::shmem::ShmemHandle;
-
-use rand::seq::SliceRandom;
-use rand::{Rng, RngCore};
-use rand_distr::Zipf;
-
-const TEST_KEY_LEN: usize = 16;
-
-#[derive(Clone, Copy, Debug, Hash, PartialEq, Eq, PartialOrd, Ord)]
-struct TestKey([u8; TEST_KEY_LEN]);
-
-impl From<&TestKey> for u128 {
-    fn from(val: &TestKey) -> u128 {
-        u128::from_be_bytes(val.0)
-    }
-}
-
-impl From<u128> for TestKey {
-    fn from(val: u128) -> TestKey {
-        TestKey(val.to_be_bytes())
-    }
-}
-
-impl<'a> From<&'a [u8]> for TestKey {
-    fn from(bytes: &'a [u8]) -> TestKey {
-        TestKey(bytes.try_into().unwrap())
-    }
-}
-
-fn test_inserts<K: Into<TestKey> + Copy>(keys: &[K]) {
-    const MAX_MEM_SIZE: usize = 10000000;
-    let shmem = ShmemHandle::new("test_inserts", 0, MAX_MEM_SIZE).unwrap();
-
-    let init_struct = HashMapInit::<TestKey, usize>::init_in_shmem(100000, shmem);
-    let w = init_struct.attach_writer();
-
-    for (idx, k) in keys.iter().enumerate() {
-        let res = w.insert(&(*k).into(), idx);
-        assert!(res.is_ok());
-    }
-
-    for (idx, k) in keys.iter().enumerate() {
-        let x = w.get(&(*k).into());
-        let value = x.as_deref().copied();
-        assert_eq!(value, Some(idx));
-    }
-
-    //eprintln!("stats: {:?}", tree_writer.get_statistics());
-}
-
-#[test]
-fn dense() {
-    // This exercises splitting a node with prefix
-    let keys: &[u128] = &[0, 1, 2, 3, 256];
-    test_inserts(keys);
-
-    // Dense keys
-    let mut keys: Vec<u128> = (0..10000).collect();
-    test_inserts(&keys);
-
-    // Do the same in random orders
-    for _ in 1..10 {
-        keys.shuffle(&mut rand::rng());
-        test_inserts(&keys);
-    }
-}
-
-#[test]
-fn sparse() {
-    // sparse keys
-    let mut keys: Vec<TestKey> = Vec::new();
-    let mut used_keys = HashSet::new();
-    for _ in 0..10000 {
-        loop {
-            let key = rand::random::<u128>();
-            if used_keys.get(&key).is_some() {
-                continue;
-            }
-            used_keys.insert(key);
-            keys.push(key.into());
-            break;
-        }
-    }
-    test_inserts(&keys);
-}
-
-struct TestValue(AtomicUsize);
-
-impl TestValue {
-    fn new(val: usize) -> TestValue {
-        TestValue(AtomicUsize::new(val))
-    }
-
-    fn load(&self) -> usize {
-        self.0.load(Ordering::Relaxed)
-    }
-}
-
-impl Clone for TestValue {
-    fn clone(&self) -> TestValue {
-        TestValue::new(self.load())
-    }
-}
-
-impl Debug for TestValue {
-    fn fmt(&self, fmt: &mut Formatter<'_>) -> Result<(), std::fmt::Error> {
-        write!(fmt, "{:?}", self.load())
-    }
-}
-
-#[derive(Clone, Debug)]
-struct TestOp(TestKey, Option<usize>);
-
-fn apply_op(
-    op: &TestOp,
-    sut: &HashMapAccess<TestKey, TestValue>,
-    shadow: &mut BTreeMap<TestKey, usize>,
-) {
-    eprintln!("applying op: {op:?}");
-
-    // apply the change to the shadow tree first
-    let shadow_existing = if let Some(v) = op.1 {
-        shadow.insert(op.0, v)
-    } else {
-        shadow.remove(&op.0)
-    };
-
-    // apply to Art tree
-    sut.update_with_fn(&op.0, |existing| {
-        assert_eq!(existing.map(TestValue::load), shadow_existing);
-
-        match (existing, op.1) {
-            (None, None) => UpdateAction::Nothing,
-            (None, Some(new_val)) => UpdateAction::Insert(TestValue::new(new_val)),
-            (Some(_old_val), None) => UpdateAction::Remove,
-            (Some(old_val), Some(new_val)) => {
-                old_val.0.store(new_val, Ordering::Relaxed);
-                UpdateAction::Nothing
-            }
-        }
-    })
-    .expect("out of memory");
-}
-
-#[test]
-fn random_ops() {
-    const MAX_MEM_SIZE: usize = 10000000;
-    let shmem = ShmemHandle::new("test_inserts", 0, MAX_MEM_SIZE).unwrap();
-
-    let init_struct = HashMapInit::<TestKey, TestValue>::init_in_shmem(100000, shmem);
-    let writer = init_struct.attach_writer();
-
-    let mut shadow: std::collections::BTreeMap<TestKey, usize> = BTreeMap::new();
-
-    let distribution = Zipf::new(u128::MAX as f64, 1.1).unwrap();
-    let mut rng = rand::rng();
-    for i in 0..100000 {
-        let key: TestKey = (rng.sample(distribution) as u128).into();
-
-        let op = TestOp(key, if rng.random_bool(0.75) { Some(i) } else { None });
-
-        apply_op(&op, &writer, &mut shadow);
-
-        if i % 1000 == 0 {
-            eprintln!("{i} ops processed");
-            //eprintln!("stats: {:?}", tree_writer.get_statistics());
-            //test_iter(&tree_writer, &shadow);
-        }
-    }
-}
-
-#[test]
-fn test_grow() {
-    const MEM_SIZE: usize = 10000000;
-    let shmem = ShmemHandle::new("test_grow", 0, MEM_SIZE).unwrap();
-
-    let init_struct = HashMapInit::<TestKey, TestValue>::init_in_shmem(1000, shmem);
-    let writer = init_struct.attach_writer();
-
-    let mut shadow: std::collections::BTreeMap<TestKey, usize> = BTreeMap::new();
-
-    let mut rng = rand::rng();
-    for i in 0..10000 {
-        let key: TestKey = ((rng.next_u32() % 1000) as u128).into();
-
-        let op = TestOp(key, if rng.random_bool(0.75) { Some(i) } else { None });
-
-        apply_op(&op, &writer, &mut shadow);
-
-        if i % 1000 == 0 {
-            eprintln!("{i} ops processed");
-            //eprintln!("stats: {:?}", tree_writer.get_statistics());
-            //test_iter(&tree_writer, &shadow);
-        }
-    }
-
-    writer.grow(1500).unwrap();
-
-    for i in 0..10000 {
-        let key: TestKey = ((rng.next_u32() % 1500) as u128).into();
-
-        let op = TestOp(key, if rng.random_bool(0.75) { Some(i) } else { None });
-
-        apply_op(&op, &writer, &mut shadow);
-
-        if i % 1000 == 0 {
-            eprintln!("{i} ops processed");
-            //eprintln!("stats: {:?}", tree_writer.get_statistics());
-            //test_iter(&tree_writer, &shadow);
-        }
-    }
-}

libs/neon-shmem/src/lib.rs

@@ -1,4 +1,418 @@
 //! Shared memory utilities for neon communicator
 
-pub mod hash;
-pub mod shmem;
+use std::num::NonZeroUsize;
+use std::os::fd::{AsFd, BorrowedFd, OwnedFd};
+use std::ptr::NonNull;
+use std::sync::atomic::{AtomicUsize, Ordering};
+
+use nix::errno::Errno;
+use nix::sys::mman::MapFlags;
+use nix::sys::mman::ProtFlags;
+use nix::sys::mman::mmap as nix_mmap;
+use nix::sys::mman::munmap as nix_munmap;
+use nix::unistd::ftruncate as nix_ftruncate;
+
+/// ShmemHandle represents a shared memory area that can be shared by processes over fork().
+/// Unlike shared memory allocated by Postgres, this area is resizable, up to 'max_size' that's
+/// specified at creation.
+///
+/// The area is backed by an anonymous file created with memfd_create(). The full address space for
+/// 'max_size' is reserved up-front with mmap(), but whenever you call [`ShmemHandle::set_size`],
+/// the underlying file is resized. Do not access the area beyond the current size. Currently, that
+/// will cause the file to be expanded, but we might use mprotect() etc. to enforce that in the
+/// future.
+pub struct ShmemHandle {
+    /// memfd file descriptor
+    fd: OwnedFd,
+
+    max_size: usize,
+
+    // Pointer to the beginning of the shared memory area. The header is stored there.
+    shared_ptr: NonNull<SharedStruct>,
+
+    // Pointer to the beginning of the user data
+    pub data_ptr: NonNull<u8>,
+}
+
+/// This is stored at the beginning in the shared memory area.
+struct SharedStruct {
+    max_size: usize,
+
+    /// Current size of the backing file. The high-order bit is used for the RESIZE_IN_PROGRESS flag
+    current_size: AtomicUsize,
+}
+
+const RESIZE_IN_PROGRESS: usize = 1 << 63;
+
+const HEADER_SIZE: usize = std::mem::size_of::<SharedStruct>();
+
+/// Error type returned by the ShmemHandle functions.
+#[derive(thiserror::Error, Debug)]
+#[error("{msg}: {errno}")]
+pub struct Error {
+    pub msg: String,
+    pub errno: Errno,
+}
+
+impl Error {
+    fn new(msg: &str, errno: Errno) -> Error {
+        Error {
+            msg: msg.to_string(),
+            errno,
+        }
+    }
+}
+
+impl ShmemHandle {
+    /// Create a new shared memory area. To communicate between processes, the processes need to be
+    /// fork()'d after calling this, so that the ShmemHandle is inherited by all processes.
+    ///
+    /// If the ShmemHandle is dropped, the memory is unmapped from the current process. Other
+    /// processes can continue using it, however.
+    pub fn new(name: &str, initial_size: usize, max_size: usize) -> Result<ShmemHandle, Error> {
+        // create the backing anonymous file.
+        let fd = create_backing_file(name)?;
+
+        Self::new_with_fd(fd, initial_size, max_size)
+    }
+
+    fn new_with_fd(
+        fd: OwnedFd,
+        initial_size: usize,
+        max_size: usize,
+    ) -> Result<ShmemHandle, Error> {
+        // We reserve the high-order bit for the RESIZE_IN_PROGRESS flag, and the actual size
+        // is a little larger than this because of the SharedStruct header. Make the upper limit
+        // somewhat smaller than that, because with anything close to that, you'll run out of
+        // memory anyway.
+        if max_size >= 1 << 48 {
+            panic!("max size {} too large", max_size);
+        }
+        if initial_size > max_size {
+            panic!("initial size {initial_size} larger than max size {max_size}");
+        }
+
+        // The actual initial / max size is the one given by the caller, plus the size of
+        // 'SharedStruct'.
+        let initial_size = HEADER_SIZE + initial_size;
+        let max_size = NonZeroUsize::new(HEADER_SIZE + max_size).unwrap();
+
+        // Reserve address space for it with mmap
+        //
+        // TODO: Use MAP_HUGETLB if possible
+        let start_ptr = unsafe {
+            nix_mmap(
+                None,
+                max_size,
+                ProtFlags::PROT_READ | ProtFlags::PROT_WRITE,
+                MapFlags::MAP_SHARED,
+                &fd,
+                0,
+            )
+        }
+        .map_err(|e| Error::new("mmap failed: {e}", e))?;
+
+        // Reserve space for the initial size
+        enlarge_file(fd.as_fd(), initial_size as u64)?;
+
+        // Initialize the header
+        let shared: NonNull<SharedStruct> = start_ptr.cast();
+        unsafe {
+            shared.write(SharedStruct {
+                max_size: max_size.into(),
+                current_size: AtomicUsize::new(initial_size),
+            })
+        };
+
+        // The user data begins after the header
+        let data_ptr = unsafe { start_ptr.cast().add(HEADER_SIZE) };
+
+        Ok(ShmemHandle {
+            fd,
+            max_size: max_size.into(),
+            shared_ptr: shared,
+            data_ptr,
+        })
+    }
+
+    // return reference to the header
+    fn shared(&self) -> &SharedStruct {
+        unsafe { self.shared_ptr.as_ref() }
+    }
+
+    /// Resize the shared memory area. 'new_size' must not be larger than the 'max_size' specified
+    /// when creating the area.
+    ///
+    /// This may only be called from one process/thread concurrently. We detect that case
+    /// and return an Error.
+    pub fn set_size(&self, new_size: usize) -> Result<(), Error> {
+        let new_size = new_size + HEADER_SIZE;
+        let shared = self.shared();
+
+        if new_size > self.max_size {
+            panic!(
+                "new size ({} is greater than max size ({})",
+                new_size, self.max_size
+            );
+        }
+        assert_eq!(self.max_size, shared.max_size);
+
+        // Lock the area by setting the bit in 'current_size'
+        //
+        // Ordering::Relaxed would probably be sufficient here, as we don't access any other memory
+        // and the posix_fallocate/ftruncate call is surely a synchronization point anyway. But
+        // since this is not performance-critical, better safe than sorry .
+        let mut old_size = shared.current_size.load(Ordering::Acquire);
+        loop {
+            if (old_size & RESIZE_IN_PROGRESS) != 0 {
+                return Err(Error::new(
+                    "concurrent resize detected",
+                    Errno::UnknownErrno,
+                ));
+            }
+            match shared.current_size.compare_exchange(
+                old_size,
+                new_size,
+                Ordering::Acquire,
+                Ordering::Relaxed,
+            ) {
+                Ok(_) => break,
+                Err(x) => old_size = x,
+            }
+        }
+
+        // Ok, we got the lock.
+        //
+        // NB: If anything goes wrong, we *must* clear the bit!
+        let result = {
+            use std::cmp::Ordering::{Equal, Greater, Less};
+            match new_size.cmp(&old_size) {
+                Less => nix_ftruncate(&self.fd, new_size as i64).map_err(|e| {
+                    Error::new("could not shrink shmem segment, ftruncate failed: {e}", e)
+                }),
+                Equal => Ok(()),
+                Greater => enlarge_file(self.fd.as_fd(), new_size as u64),
+            }
+        };
+
+        // Unlock
+        shared.current_size.store(
+            if result.is_ok() { new_size } else { old_size },
+            Ordering::Release,
+        );
+
+        result
+    }
+
+    /// Returns the current user-visible size of the shared memory segment.
+    ///
+    /// NOTE: a concurrent set_size() call can change the size at any time. It is the caller's
+    /// responsibility not to access the area beyond the current size.
+    pub fn current_size(&self) -> usize {
+        let total_current_size =
+            self.shared().current_size.load(Ordering::Relaxed) & !RESIZE_IN_PROGRESS;
+        total_current_size - HEADER_SIZE
+    }
+}
+
+impl Drop for ShmemHandle {
+    fn drop(&mut self) {
+        // SAFETY: The pointer was obtained from mmap() with the given size.
+        // We unmap the entire region.
+        let _ = unsafe { nix_munmap(self.shared_ptr.cast(), self.max_size) };
+        // The fd is dropped automatically by OwnedFd.
+    }
+}
+
+/// Create a "backing file" for the shared memory area. On Linux, use memfd_create(), to create an
+/// anonymous in-memory file. One macos, fall back to a regular file. That's good enough for
+/// development and testing, but in production we want the file to stay in memory.
+///
+/// disable 'unused_variables' warnings, because in the macos path, 'name' is unused.
+#[allow(unused_variables)]
+fn create_backing_file(name: &str) -> Result<OwnedFd, Error> {
+    #[cfg(not(target_os = "macos"))]
+    {
+        nix::sys::memfd::memfd_create(name, nix::sys::memfd::MFdFlags::empty())
+            .map_err(|e| Error::new("memfd_create failed: {e}", e))
+    }
+    #[cfg(target_os = "macos")]
+    {
+        let file = tempfile::tempfile().map_err(|e| {
+            Error::new(
+                "could not create temporary file to back shmem area: {e}",
+                nix::errno::Errno::from_raw(e.raw_os_error().unwrap_or(0)),
+            )
+        })?;
+        Ok(OwnedFd::from(file))
+    }
+}
+
+fn enlarge_file(fd: BorrowedFd, size: u64) -> Result<(), Error> {
+    // Use posix_fallocate() to enlarge the file. It reserves the space correctly, so that
+    // we don't get a segfault later when trying to actually use it.
+    #[cfg(not(target_os = "macos"))]
+    {
+        nix::fcntl::posix_fallocate(fd, 0, size as i64).map_err(|e| {
+            Error::new(
+                "could not grow shmem segment, posix_fallocate failed: {e}",
+                e,
+            )
+        })
+    }
+    // As a fallback on macos, which doesn't have posix_fallocate, use plain 'fallocate'
+    #[cfg(target_os = "macos")]
+    {
+        nix::unistd::ftruncate(fd, size as i64)
+            .map_err(|e| Error::new("could not grow shmem segment, ftruncate failed: {e}", e))
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    use nix::unistd::ForkResult;
+    use std::ops::Range;
+
+    /// check that all bytes in given range have the expected value.
+    fn assert_range(ptr: *const u8, expected: u8, range: Range<usize>) {
+        for i in range {
+            let b = unsafe { *(ptr.add(i)) };
+            assert_eq!(expected, b, "unexpected byte at offset {}", i);
+        }
+    }
+
+    /// Write 'b' to all bytes in the given range
+    fn write_range(ptr: *mut u8, b: u8, range: Range<usize>) {
+        unsafe { std::ptr::write_bytes(ptr.add(range.start), b, range.end - range.start) };
+    }
+
+    // simple single-process test of growing and shrinking
+    #[test]
+    fn test_shmem_resize() -> Result<(), Error> {
+        let max_size = 1024 * 1024;
+        let init_struct = ShmemHandle::new("test_shmem_resize", 0, max_size)?;
+
+        assert_eq!(init_struct.current_size(), 0);
+
+        // Initial grow
+        let size1 = 10000;
+        init_struct.set_size(size1).unwrap();
+        assert_eq!(init_struct.current_size(), size1);
+
+        // Write some data
+        let data_ptr = init_struct.data_ptr.as_ptr();
+        write_range(data_ptr, 0xAA, 0..size1);
+        assert_range(data_ptr, 0xAA, 0..size1);
+
+        // Shrink
+        let size2 = 5000;
+        init_struct.set_size(size2).unwrap();
+        assert_eq!(init_struct.current_size(), size2);
+
+        // Grow again
+        let size3 = 20000;
+        init_struct.set_size(size3).unwrap();
+        assert_eq!(init_struct.current_size(), size3);
+
+        // Try to read it. The area that was shrunk and grown again should read as all zeros now
+        assert_range(data_ptr, 0xAA, 0..5000);
+        assert_range(data_ptr, 0, 5000..size1);
+
+        // Try to grow beyond max_size
+        //let size4 = max_size + 1;
+        //assert!(init_struct.set_size(size4).is_err());
+
+        // Dropping init_struct should unmap the memory
+        drop(init_struct);
+
+        Ok(())
+    }
+
+    /// This is used in tests to coordinate between test processes. It's like std::sync::Barrier,
+    /// but is stored in the shared memory area and works across processes. It's implemented by
+    /// polling, because e.g. standard rust mutexes are not guaranteed to work across processes.
+    struct SimpleBarrier {
+        num_procs: usize,
+        count: AtomicUsize,
+    }
+
+    impl SimpleBarrier {
+        unsafe fn init(ptr: *mut SimpleBarrier, num_procs: usize) {
+            unsafe {
+                *ptr = SimpleBarrier {
+                    num_procs,
+                    count: AtomicUsize::new(0),
+                }
+            }
+        }
+
+        pub fn wait(&self) {
+            let old = self.count.fetch_add(1, Ordering::Relaxed);
+
+            let generation = old / self.num_procs;
+
+            let mut current = old + 1;
+            while current < (generation + 1) * self.num_procs {
+                std::thread::sleep(std::time::Duration::from_millis(10));
+                current = self.count.load(Ordering::Relaxed);
+            }
+        }
+    }
+
+    #[test]
+    fn test_multi_process() {
+        // Initialize
+        let max_size = 1_000_000_000_000;
+        let init_struct = ShmemHandle::new("test_multi_process", 0, max_size).unwrap();
+        let ptr = init_struct.data_ptr.as_ptr();
+
+        // Store the SimpleBarrier in the first 1k of the area.
+        init_struct.set_size(10000).unwrap();
+        let barrier_ptr: *mut SimpleBarrier = unsafe {
+            ptr.add(ptr.align_offset(std::mem::align_of::<SimpleBarrier>()))
+                .cast()
+        };
+        unsafe { SimpleBarrier::init(barrier_ptr, 2) };
+        let barrier = unsafe { barrier_ptr.as_ref().unwrap() };
+
+        // Fork another test process. The code after this runs in both processes concurrently.
+        let fork_result = unsafe { nix::unistd::fork().unwrap() };
+
+        // In the parent, fill bytes between 1000..2000. In the child, between 2000..3000
+        if fork_result.is_parent() {
+            write_range(ptr, 0xAA, 1000..2000);
+        } else {
+            write_range(ptr, 0xBB, 2000..3000);
+        }
+        barrier.wait();
+        // Verify the contents. (in both processes)
+        assert_range(ptr, 0xAA, 1000..2000);
+        assert_range(ptr, 0xBB, 2000..3000);
+
+        // Grow, from the child this time
+        let size = 10_000_000;
+        if !fork_result.is_parent() {
+            init_struct.set_size(size).unwrap();
+        }
+        barrier.wait();
+
+        // make some writes at the end
+        if fork_result.is_parent() {
+            write_range(ptr, 0xAA, (size - 10)..size);
+        } else {
+            write_range(ptr, 0xBB, (size - 20)..(size - 10));
+        }
+        barrier.wait();
+
+        // Verify the contents. (This runs in both processes)
+        assert_range(ptr, 0, (size - 1000)..(size - 20));
+        assert_range(ptr, 0xBB, (size - 20)..(size - 10));
+        assert_range(ptr, 0xAA, (size - 10)..size);
+
+        if let ForkResult::Parent { child } = fork_result {
+            nix::sys::wait::waitpid(child, None).unwrap();
+        }
+    }
+}

libs/neon-shmem/src/shmem.rs

@@ -1,418 +0,0 @@
-//! Dynamically resizable contiguous chunk of shared memory
-
-use std::num::NonZeroUsize;
-use std::os::fd::{AsFd, BorrowedFd, OwnedFd};
-use std::ptr::NonNull;
-use std::sync::atomic::{AtomicUsize, Ordering};
-
-use nix::errno::Errno;
-use nix::sys::mman::MapFlags;
-use nix::sys::mman::ProtFlags;
-use nix::sys::mman::mmap as nix_mmap;
-use nix::sys::mman::munmap as nix_munmap;
-use nix::unistd::ftruncate as nix_ftruncate;
-
-/// ShmemHandle represents a shared memory area that can be shared by processes over fork().
-/// Unlike shared memory allocated by Postgres, this area is resizable, up to 'max_size' that's
-/// specified at creation.
-///
-/// The area is backed by an anonymous file created with memfd_create(). The full address space for
-/// 'max_size' is reserved up-front with mmap(), but whenever you call [`ShmemHandle::set_size`],
-/// the underlying file is resized. Do not access the area beyond the current size. Currently, that
-/// will cause the file to be expanded, but we might use mprotect() etc. to enforce that in the
-/// future.
-pub struct ShmemHandle {
-    /// memfd file descriptor
-    fd: OwnedFd,
-
-    max_size: usize,
-
-    // Pointer to the beginning of the shared memory area. The header is stored there.
-    shared_ptr: NonNull<SharedStruct>,
-
-    // Pointer to the beginning of the user data
-    pub data_ptr: NonNull<u8>,
-}
-
-/// This is stored at the beginning in the shared memory area.
-struct SharedStruct {
-    max_size: usize,
-
-    /// Current size of the backing file. The high-order bit is used for the RESIZE_IN_PROGRESS flag
-    current_size: AtomicUsize,
-}
-
-const RESIZE_IN_PROGRESS: usize = 1 << 63;
-
-const HEADER_SIZE: usize = std::mem::size_of::<SharedStruct>();
-
-/// Error type returned by the ShmemHandle functions.
-#[derive(thiserror::Error, Debug)]
-#[error("{msg}: {errno}")]
-pub struct Error {
-    pub msg: String,
-    pub errno: Errno,
-}
-
-impl Error {
-    fn new(msg: &str, errno: Errno) -> Error {
-        Error {
-            msg: msg.to_string(),
-            errno,
-        }
-    }
-}
-
-impl ShmemHandle {
-    /// Create a new shared memory area. To communicate between processes, the processes need to be
-    /// fork()'d after calling this, so that the ShmemHandle is inherited by all processes.
-    ///
-    /// If the ShmemHandle is dropped, the memory is unmapped from the current process. Other
-    /// processes can continue using it, however.
-    pub fn new(name: &str, initial_size: usize, max_size: usize) -> Result<ShmemHandle, Error> {
-        // create the backing anonymous file.
-        let fd = create_backing_file(name)?;
-
-        Self::new_with_fd(fd, initial_size, max_size)
-    }
-
-    fn new_with_fd(
-        fd: OwnedFd,
-        initial_size: usize,
-        max_size: usize,
-    ) -> Result<ShmemHandle, Error> {
-        // We reserve the high-order bit for the RESIZE_IN_PROGRESS flag, and the actual size
-        // is a little larger than this because of the SharedStruct header. Make the upper limit
-        // somewhat smaller than that, because with anything close to that, you'll run out of
-        // memory anyway.
-        if max_size >= 1 << 48 {
-            panic!("max size {} too large", max_size);
-        }
-        if initial_size > max_size {
-            panic!("initial size {initial_size} larger than max size {max_size}");
-        }
-
-        // The actual initial / max size is the one given by the caller, plus the size of
-        // 'SharedStruct'.
-        let initial_size = HEADER_SIZE + initial_size;
-        let max_size = NonZeroUsize::new(HEADER_SIZE + max_size).unwrap();
-
-        // Reserve address space for it with mmap
-        //
-        // TODO: Use MAP_HUGETLB if possible
-        let start_ptr = unsafe {
-            nix_mmap(
-                None,
-                max_size,
-                ProtFlags::PROT_READ | ProtFlags::PROT_WRITE,
-                MapFlags::MAP_SHARED,
-                &fd,
-                0,
-            )
-        }
-        .map_err(|e| Error::new("mmap failed: {e}", e))?;
-
-        // Reserve space for the initial size
-        enlarge_file(fd.as_fd(), initial_size as u64)?;
-
-        // Initialize the header
-        let shared: NonNull<SharedStruct> = start_ptr.cast();
-        unsafe {
-            shared.write(SharedStruct {
-                max_size: max_size.into(),
-                current_size: AtomicUsize::new(initial_size),
-            })
-        };
-
-        // The user data begins after the header
-        let data_ptr = unsafe { start_ptr.cast().add(HEADER_SIZE) };
-
-        Ok(ShmemHandle {
-            fd,
-            max_size: max_size.into(),
-            shared_ptr: shared,
-            data_ptr,
-        })
-    }
-
-    // return reference to the header
-    fn shared(&self) -> &SharedStruct {
-        unsafe { self.shared_ptr.as_ref() }
-    }
-
-    /// Resize the shared memory area. 'new_size' must not be larger than the 'max_size' specified
-    /// when creating the area.
-    ///
-    /// This may only be called from one process/thread concurrently. We detect that case
-    /// and return an Error.
-    pub fn set_size(&self, new_size: usize) -> Result<(), Error> {
-        let new_size = new_size + HEADER_SIZE;
-        let shared = self.shared();
-
-        if new_size > self.max_size {
-            panic!(
-                "new size ({} is greater than max size ({})",
-                new_size, self.max_size
-            );
-        }
-        assert_eq!(self.max_size, shared.max_size);
-
-        // Lock the area by setting the bit in 'current_size'
-        //
-        // Ordering::Relaxed would probably be sufficient here, as we don't access any other memory
-        // and the posix_fallocate/ftruncate call is surely a synchronization point anyway. But
-        // since this is not performance-critical, better safe than sorry .
-        let mut old_size = shared.current_size.load(Ordering::Acquire);
-        loop {
-            if (old_size & RESIZE_IN_PROGRESS) != 0 {
-                return Err(Error::new(
-                    "concurrent resize detected",
-                    Errno::UnknownErrno,
-                ));
-            }
-            match shared.current_size.compare_exchange(
-                old_size,
-                new_size,
-                Ordering::Acquire,
-                Ordering::Relaxed,
-            ) {
-                Ok(_) => break,
-                Err(x) => old_size = x,
-            }
-        }
-
-        // Ok, we got the lock.
-        //
-        // NB: If anything goes wrong, we *must* clear the bit!
-        let result = {
-            use std::cmp::Ordering::{Equal, Greater, Less};
-            match new_size.cmp(&old_size) {
-                Less => nix_ftruncate(&self.fd, new_size as i64).map_err(|e| {
-                    Error::new("could not shrink shmem segment, ftruncate failed: {e}", e)
-                }),
-                Equal => Ok(()),
-                Greater => enlarge_file(self.fd.as_fd(), new_size as u64),
-            }
-        };
-
-        // Unlock
-        shared.current_size.store(
-            if result.is_ok() { new_size } else { old_size },
-            Ordering::Release,
-        );
-
-        result
-    }
-
-    /// Returns the current user-visible size of the shared memory segment.
-    ///
-    /// NOTE: a concurrent set_size() call can change the size at any time. It is the caller's
-    /// responsibility not to access the area beyond the current size.
-    pub fn current_size(&self) -> usize {
-        let total_current_size =
-            self.shared().current_size.load(Ordering::Relaxed) & !RESIZE_IN_PROGRESS;
-        total_current_size - HEADER_SIZE
-    }
-}
-
-impl Drop for ShmemHandle {
-    fn drop(&mut self) {
-        // SAFETY: The pointer was obtained from mmap() with the given size.
-        // We unmap the entire region.
-        let _ = unsafe { nix_munmap(self.shared_ptr.cast(), self.max_size) };
-        // The fd is dropped automatically by OwnedFd.
-    }
-}
-
-/// Create a "backing file" for the shared memory area. On Linux, use memfd_create(), to create an
-/// anonymous in-memory file. One macos, fall back to a regular file. That's good enough for
-/// development and testing, but in production we want the file to stay in memory.
-///
-/// disable 'unused_variables' warnings, because in the macos path, 'name' is unused.
-#[allow(unused_variables)]
-fn create_backing_file(name: &str) -> Result<OwnedFd, Error> {
-    #[cfg(not(target_os = "macos"))]
-    {
-        nix::sys::memfd::memfd_create(name, nix::sys::memfd::MFdFlags::empty())
-            .map_err(|e| Error::new("memfd_create failed: {e}", e))
-    }
-    #[cfg(target_os = "macos")]
-    {
-        let file = tempfile::tempfile().map_err(|e| {
-            Error::new(
-                "could not create temporary file to back shmem area: {e}",
-                nix::errno::Errno::from_raw(e.raw_os_error().unwrap_or(0)),
-            )
-        })?;
-        Ok(OwnedFd::from(file))
-    }
-}
-
-fn enlarge_file(fd: BorrowedFd, size: u64) -> Result<(), Error> {
-    // Use posix_fallocate() to enlarge the file. It reserves the space correctly, so that
-    // we don't get a segfault later when trying to actually use it.
-    #[cfg(not(target_os = "macos"))]
-    {
-        nix::fcntl::posix_fallocate(fd, 0, size as i64).map_err(|e| {
-            Error::new(
-                "could not grow shmem segment, posix_fallocate failed: {e}",
-                e,
-            )
-        })
-    }
-    // As a fallback on macos, which doesn't have posix_fallocate, use plain 'fallocate'
-    #[cfg(target_os = "macos")]
-    {
-        nix::unistd::ftruncate(fd, size as i64)
-            .map_err(|e| Error::new("could not grow shmem segment, ftruncate failed: {e}", e))
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    use nix::unistd::ForkResult;
-    use std::ops::Range;
-
-    /// check that all bytes in given range have the expected value.
-    fn assert_range(ptr: *const u8, expected: u8, range: Range<usize>) {
-        for i in range {
-            let b = unsafe { *(ptr.add(i)) };
-            assert_eq!(expected, b, "unexpected byte at offset {}", i);
-        }
-    }
-
-    /// Write 'b' to all bytes in the given range
-    fn write_range(ptr: *mut u8, b: u8, range: Range<usize>) {
-        unsafe { std::ptr::write_bytes(ptr.add(range.start), b, range.end - range.start) };
-    }
-
-    // simple single-process test of growing and shrinking
-    #[test]
-    fn test_shmem_resize() -> Result<(), Error> {
-        let max_size = 1024 * 1024;
-        let init_struct = ShmemHandle::new("test_shmem_resize", 0, max_size)?;
-
-        assert_eq!(init_struct.current_size(), 0);
-
-        // Initial grow
-        let size1 = 10000;
-        init_struct.set_size(size1).unwrap();
-        assert_eq!(init_struct.current_size(), size1);
-
-        // Write some data
-        let data_ptr = init_struct.data_ptr.as_ptr();
-        write_range(data_ptr, 0xAA, 0..size1);
-        assert_range(data_ptr, 0xAA, 0..size1);
-
-        // Shrink
-        let size2 = 5000;
-        init_struct.set_size(size2).unwrap();
-        assert_eq!(init_struct.current_size(), size2);
-
-        // Grow again
-        let size3 = 20000;
-        init_struct.set_size(size3).unwrap();
-        assert_eq!(init_struct.current_size(), size3);
-
-        // Try to read it. The area that was shrunk and grown again should read as all zeros now
-        assert_range(data_ptr, 0xAA, 0..5000);
-        assert_range(data_ptr, 0, 5000..size1);
-
-        // Try to grow beyond max_size
-        //let size4 = max_size + 1;
-        //assert!(init_struct.set_size(size4).is_err());
-
-        // Dropping init_struct should unmap the memory
-        drop(init_struct);
-
-        Ok(())
-    }
-
-    /// This is used in tests to coordinate between test processes. It's like std::sync::Barrier,
-    /// but is stored in the shared memory area and works across processes. It's implemented by
-    /// polling, because e.g. standard rust mutexes are not guaranteed to work across processes.
-    struct SimpleBarrier {
-        num_procs: usize,
-        count: AtomicUsize,
-    }
-
-    impl SimpleBarrier {
-        unsafe fn init(ptr: *mut SimpleBarrier, num_procs: usize) {
-            unsafe {
-                *ptr = SimpleBarrier {
-                    num_procs,
-                    count: AtomicUsize::new(0),
-                }
-            }
-        }
-
-        pub fn wait(&self) {
-            let old = self.count.fetch_add(1, Ordering::Relaxed);
-
-            let generation = old / self.num_procs;
-
-            let mut current = old + 1;
-            while current < (generation + 1) * self.num_procs {
-                std::thread::sleep(std::time::Duration::from_millis(10));
-                current = self.count.load(Ordering::Relaxed);
-            }
-        }
-    }
-
-    #[test]
-    fn test_multi_process() {
-        // Initialize
-        let max_size = 1_000_000_000_000;
-        let init_struct = ShmemHandle::new("test_multi_process", 0, max_size).unwrap();
-        let ptr = init_struct.data_ptr.as_ptr();
-
-        // Store the SimpleBarrier in the first 1k of the area.
-        init_struct.set_size(10000).unwrap();
-        let barrier_ptr: *mut SimpleBarrier = unsafe {
-            ptr.add(ptr.align_offset(std::mem::align_of::<SimpleBarrier>()))
-                .cast()
-        };
-        unsafe { SimpleBarrier::init(barrier_ptr, 2) };
-        let barrier = unsafe { barrier_ptr.as_ref().unwrap() };
-
-        // Fork another test process. The code after this runs in both processes concurrently.
-        let fork_result = unsafe { nix::unistd::fork().unwrap() };
-
-        // In the parent, fill bytes between 1000..2000. In the child, between 2000..3000
-        if fork_result.is_parent() {
-            write_range(ptr, 0xAA, 1000..2000);
-        } else {
-            write_range(ptr, 0xBB, 2000..3000);
-        }
-        barrier.wait();
-        // Verify the contents. (in both processes)
-        assert_range(ptr, 0xAA, 1000..2000);
-        assert_range(ptr, 0xBB, 2000..3000);
-
-        // Grow, from the child this time
-        let size = 10_000_000;
-        if !fork_result.is_parent() {
-            init_struct.set_size(size).unwrap();
-        }
-        barrier.wait();
-
-        // make some writes at the end
-        if fork_result.is_parent() {
-            write_range(ptr, 0xAA, (size - 10)..size);
-        } else {
-            write_range(ptr, 0xBB, (size - 20)..(size - 10));
-        }
-        barrier.wait();
-
-        // Verify the contents. (This runs in both processes)
-        assert_range(ptr, 0, (size - 1000)..(size - 20));
-        assert_range(ptr, 0xBB, (size - 20)..(size - 10));
-        assert_range(ptr, 0xAA, (size - 10)..size);
-
-        if let ForkResult::Parent { child } = fork_result {
-            nix::sys::wait::waitpid(child, None).unwrap();
-        }
-    }
-}

libs/pageserver_api/src/config.rs

@@ -8,8 +8,6 @@ pub const DEFAULT_PG_LISTEN_PORT: u16 = 64000;
 pub const DEFAULT_PG_LISTEN_ADDR: &str = formatcp!("127.0.0.1:{DEFAULT_PG_LISTEN_PORT}");
 pub const DEFAULT_HTTP_LISTEN_PORT: u16 = 9898;
 pub const DEFAULT_HTTP_LISTEN_ADDR: &str = formatcp!("127.0.0.1:{DEFAULT_HTTP_LISTEN_PORT}");
-// TODO: gRPC is disabled by default for now, but the port is used in neon_local.
-pub const DEFAULT_GRPC_LISTEN_PORT: u16 = 51051; // storage-broker already uses 50051
 
 use std::collections::HashMap;
 use std::num::{NonZeroU64, NonZeroUsize};
@@ -20,6 +18,7 @@ use postgres_backend::AuthType;
 use remote_storage::RemoteStorageConfig;
 use serde_with::serde_as;
 use utils::logging::LogFormat;
+use utils::postgres_client::PostgresClientProtocol;
 
 use crate::models::{ImageCompressionAlgorithm, LsnLease};
 
@@ -44,21 +43,6 @@ pub struct NodeMetadata {
     pub other: HashMap<String, serde_json::Value>,
 }
 
-/// PostHog integration config.
-#[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
-pub struct PostHogConfig {
-    /// PostHog project ID
-    pub project_id: String,
-    /// Server-side (private) API key
-    pub server_api_key: String,
-    /// Client-side (public) API key
-    pub client_api_key: String,
-    /// Private API URL
-    pub private_api_url: String,
-    /// Public API URL
-    pub public_api_url: String,
-}
-
 /// `pageserver.toml`
 ///
 /// We use serde derive with `#[serde(default)]` to generate a deserializer
@@ -120,7 +104,6 @@ pub struct ConfigToml {
     pub listen_pg_addr: String,
     pub listen_http_addr: String,
     pub listen_https_addr: Option<String>,
-    pub listen_grpc_addr: Option<String>,
     pub ssl_key_file: Utf8PathBuf,
     pub ssl_cert_file: Utf8PathBuf,
     #[serde(with = "humantime_serde")]
@@ -140,7 +123,6 @@ pub struct ConfigToml {
     pub http_auth_type: AuthType,
     #[serde_as(as = "serde_with::DisplayFromStr")]
     pub pg_auth_type: AuthType,
-    pub grpc_auth_type: AuthType,
     pub auth_validation_public_key_path: Option<Utf8PathBuf>,
     pub remote_storage: Option<RemoteStorageConfig>,
     pub tenant_config: TenantConfigToml,
@@ -180,7 +162,6 @@ pub struct ConfigToml {
     pub virtual_file_io_engine: Option<crate::models::virtual_file::IoEngineKind>,
     pub ingest_batch_size: u64,
     pub max_vectored_read_bytes: MaxVectoredReadBytes,
-    pub max_get_vectored_keys: MaxGetVectoredKeys,
     pub image_compression: ImageCompressionAlgorithm,
     pub timeline_offloading: bool,
     pub ephemeral_bytes_per_memory_kb: usize,
@@ -188,6 +169,7 @@ pub struct ConfigToml {
     pub virtual_file_io_mode: Option<crate::models::virtual_file::IoMode>,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub no_sync: Option<bool>,
+    pub wal_receiver_protocol: PostgresClientProtocol,
     pub page_service_pipelining: PageServicePipeliningConfig,
     pub get_vectored_concurrent_io: GetVectoredConcurrentIo,
     pub enable_read_path_debugging: Option<bool>,
@@ -200,8 +182,6 @@ pub struct ConfigToml {
     pub tracing: Option<Tracing>,
     pub enable_tls_page_service_api: bool,
     pub dev_mode: bool,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub posthog_config: Option<PostHogConfig>,
     pub timeline_import_config: TimelineImportConfig,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub basebackup_cache_config: Option<BasebackupCacheConfig>,
@@ -228,7 +208,7 @@ pub enum PageServicePipeliningConfig {
 }
 #[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
 pub struct PageServicePipeliningConfigPipelined {
-    /// Failed config parsing and validation if larger than `max_get_vectored_keys`.
+    /// Causes runtime errors if larger than max get_vectored batch size.
     pub max_batch_size: NonZeroUsize,
     pub execution: PageServiceProtocolPipelinedExecutionStrategy,
     // The default below is such that new versions of the software can start
@@ -328,8 +308,6 @@ pub struct TimelineImportConfig {
     pub import_job_concurrency: NonZeroUsize,
     pub import_job_soft_size_limit: NonZeroUsize,
     pub import_job_checkpoint_threshold: NonZeroUsize,
-    /// Max size of the remote storage partial read done by any job
-    pub import_job_max_byte_range_size: NonZeroUsize,
 }
 
 #[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
@@ -404,16 +382,6 @@ impl Default for EvictionOrder {
 #[serde(transparent)]
 pub struct MaxVectoredReadBytes(pub NonZeroUsize);
 
-#[derive(Copy, Clone, Debug, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
-#[serde(transparent)]
-pub struct MaxGetVectoredKeys(NonZeroUsize);
-
-impl MaxGetVectoredKeys {
-    pub fn get(&self) -> usize {
-        self.0.get()
-    }
-}
-
 /// Tenant-level configuration values, used for various purposes.
 #[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
 #[serde(default)]
@@ -525,6 +493,8 @@ pub struct TenantConfigToml {
     /// (either this flag or the pageserver-global one need to be set)
     pub timeline_offloading: bool,
 
+    pub wal_receiver_protocol_override: Option<PostgresClientProtocol>,
+
     /// Enable rel_size_v2 for this tenant. Once enabled, the tenant will persist this information into
     /// `index_part.json`, and it cannot be reversed.
     pub rel_size_v2_enabled: bool,
@@ -596,8 +566,6 @@ pub mod defaults {
     /// That is, slightly above 128 kB.
     pub const DEFAULT_MAX_VECTORED_READ_BYTES: usize = 130 * 1024; // 130 KiB
 
-    pub const DEFAULT_MAX_GET_VECTORED_KEYS: usize = 32;
-
     pub const DEFAULT_IMAGE_COMPRESSION: ImageCompressionAlgorithm =
         ImageCompressionAlgorithm::Zstd { level: Some(1) };
 
@@ -605,6 +573,9 @@ pub mod defaults {
 
     pub const DEFAULT_IO_BUFFER_ALIGNMENT: usize = 512;
 
+    pub const DEFAULT_WAL_RECEIVER_PROTOCOL: utils::postgres_client::PostgresClientProtocol =
+        utils::postgres_client::PostgresClientProtocol::Vanilla;
+
     pub const DEFAULT_SSL_KEY_FILE: &str = "server.key";
     pub const DEFAULT_SSL_CERT_FILE: &str = "server.crt";
 }
@@ -617,7 +588,6 @@ impl Default for ConfigToml {
             listen_pg_addr: (DEFAULT_PG_LISTEN_ADDR.to_string()),
             listen_http_addr: (DEFAULT_HTTP_LISTEN_ADDR.to_string()),
             listen_https_addr: (None),
-            listen_grpc_addr: None, // TODO: default to 127.0.0.1:51051
             ssl_key_file: Utf8PathBuf::from(DEFAULT_SSL_KEY_FILE),
             ssl_cert_file: Utf8PathBuf::from(DEFAULT_SSL_CERT_FILE),
             ssl_cert_reload_period: Duration::from_secs(60),
@@ -634,7 +604,6 @@ impl Default for ConfigToml {
             pg_distrib_dir: None, // Utf8PathBuf::from("./pg_install"), // TODO: formely, this was std::env::current_dir()
             http_auth_type: (AuthType::Trust),
             pg_auth_type: (AuthType::Trust),
-            grpc_auth_type: (AuthType::Trust),
             auth_validation_public_key_path: (None),
             remote_storage: None,
             broker_endpoint: (storage_broker::DEFAULT_ENDPOINT
@@ -693,9 +662,6 @@ impl Default for ConfigToml {
             max_vectored_read_bytes: (MaxVectoredReadBytes(
                 NonZeroUsize::new(DEFAULT_MAX_VECTORED_READ_BYTES).unwrap(),
             )),
-            max_get_vectored_keys: (MaxGetVectoredKeys(
-                NonZeroUsize::new(DEFAULT_MAX_GET_VECTORED_KEYS).unwrap(),
-            )),
             image_compression: (DEFAULT_IMAGE_COMPRESSION),
             timeline_offloading: true,
             ephemeral_bytes_per_memory_kb: (DEFAULT_EPHEMERAL_BYTES_PER_MEMORY_KB),
@@ -703,6 +669,7 @@ impl Default for ConfigToml {
             virtual_file_io_mode: None,
             tenant_config: TenantConfigToml::default(),
             no_sync: None,
+            wal_receiver_protocol: DEFAULT_WAL_RECEIVER_PROTOCOL,
             page_service_pipelining: PageServicePipeliningConfig::Pipelined(
                 PageServicePipeliningConfigPipelined {
                     max_batch_size: NonZeroUsize::new(32).unwrap(),
@@ -723,13 +690,11 @@ impl Default for ConfigToml {
             enable_tls_page_service_api: false,
             dev_mode: false,
             timeline_import_config: TimelineImportConfig {
-                import_job_concurrency: NonZeroUsize::new(32).unwrap(),
-                import_job_soft_size_limit: NonZeroUsize::new(256 * 1024 * 1024).unwrap(),
-                import_job_checkpoint_threshold: NonZeroUsize::new(32).unwrap(),
-                import_job_max_byte_range_size: NonZeroUsize::new(4 * 1024 * 1024).unwrap(),
+                import_job_concurrency: NonZeroUsize::new(128).unwrap(),
+                import_job_soft_size_limit: NonZeroUsize::new(1024 * 1024 * 1024).unwrap(),
+                import_job_checkpoint_threshold: NonZeroUsize::new(128).unwrap(),
             },
             basebackup_cache_config: None,
-            posthog_config: None,
         }
     }
 }
@@ -847,6 +812,7 @@ impl Default for TenantConfigToml {
             lsn_lease_length: LsnLease::DEFAULT_LENGTH,
             lsn_lease_length_for_ts: LsnLease::DEFAULT_LENGTH_FOR_TS,
             timeline_offloading: true,
+            wal_receiver_protocol_override: None,
             rel_size_v2_enabled: false,
             gc_compaction_enabled: DEFAULT_GC_COMPACTION_ENABLED,
             gc_compaction_verification: DEFAULT_GC_COMPACTION_VERIFICATION,

libs/pageserver_api/src/models.rs

@@ -20,6 +20,7 @@ use serde_with::serde_as;
 pub use utilization::PageserverUtilization;
 use utils::id::{NodeId, TenantId, TimelineId};
 use utils::lsn::Lsn;
+use utils::postgres_client::PostgresClientProtocol;
 use utils::{completion, serde_system_time};
 
 use crate::config::Ratio;
@@ -353,9 +354,6 @@ pub struct ShardImportProgressV1 {
     pub completed: usize,
     /// Hash of the plan
     pub import_plan_hash: u64,
-    /// Soft limit for the job size
-    /// This needs to remain constant throughout the import
-    pub job_soft_size_limit: usize,
 }
 
 impl ShardImportStatus {
@@ -404,8 +402,6 @@ pub enum TimelineCreateRequestMode {
         // using a flattened enum, so, it was an accepted field, and
         // we continue to accept it by having it here.
         pg_version: Option<u32>,
-        #[serde(default, skip_serializing_if = "std::ops::Not::not")]
-        read_only: bool,
     },
     ImportPgdata {
         import_pgdata: TimelineCreateRequestModeImportPgdata,
@@ -621,6 +617,8 @@ pub struct TenantConfigPatch {
     #[serde(skip_serializing_if = "FieldPatch::is_noop")]
     pub timeline_offloading: FieldPatch<bool>,
     #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub wal_receiver_protocol_override: FieldPatch<PostgresClientProtocol>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
     pub rel_size_v2_enabled: FieldPatch<bool>,
     #[serde(skip_serializing_if = "FieldPatch::is_noop")]
     pub gc_compaction_enabled: FieldPatch<bool>,
@@ -745,6 +743,9 @@ pub struct TenantConfig {
     #[serde(skip_serializing_if = "Option::is_none")]
     pub timeline_offloading: Option<bool>,
 
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub wal_receiver_protocol_override: Option<PostgresClientProtocol>,
+
     #[serde(skip_serializing_if = "Option::is_none")]
     pub rel_size_v2_enabled: Option<bool>,
 
@@ -806,6 +807,7 @@ impl TenantConfig {
             mut lsn_lease_length,
             mut lsn_lease_length_for_ts,
             mut timeline_offloading,
+            mut wal_receiver_protocol_override,
             mut rel_size_v2_enabled,
             mut gc_compaction_enabled,
             mut gc_compaction_verification,
@@ -898,6 +900,9 @@ impl TenantConfig {
             .map(|v| humantime::parse_duration(&v))?
             .apply(&mut lsn_lease_length_for_ts);
         patch.timeline_offloading.apply(&mut timeline_offloading);
+        patch
+            .wal_receiver_protocol_override
+            .apply(&mut wal_receiver_protocol_override);
         patch.rel_size_v2_enabled.apply(&mut rel_size_v2_enabled);
         patch
             .gc_compaction_enabled
@@ -950,6 +955,7 @@ impl TenantConfig {
             lsn_lease_length,
             lsn_lease_length_for_ts,
             timeline_offloading,
+            wal_receiver_protocol_override,
             rel_size_v2_enabled,
             gc_compaction_enabled,
             gc_compaction_verification,
@@ -1047,6 +1053,9 @@ impl TenantConfig {
             timeline_offloading: self
                 .timeline_offloading
                 .unwrap_or(global_conf.timeline_offloading),
+            wal_receiver_protocol_override: self
+                .wal_receiver_protocol_override
+                .or(global_conf.wal_receiver_protocol_override),
             rel_size_v2_enabled: self
                 .rel_size_v2_enabled
                 .unwrap_or(global_conf.rel_size_v2_enabled),
@@ -1920,7 +1929,7 @@ pub enum PagestreamFeMessage {
 }
 
 // Wrapped in libpq CopyData
-#[derive(Debug, strum_macros::EnumProperty)]
+#[derive(strum_macros::EnumProperty)]
 pub enum PagestreamBeMessage {
     Exists(PagestreamExistsResponse),
     Nblocks(PagestreamNblocksResponse),
@@ -2031,7 +2040,7 @@ pub enum PagestreamProtocolVersion {
 
 pub type RequestId = u64;
 
-#[derive(Debug, Default, PartialEq, Eq, Clone, Copy)]
+#[derive(Debug, PartialEq, Eq, Clone, Copy)]
 pub struct PagestreamRequest {
     pub reqid: RequestId,
     pub request_lsn: Lsn,
@@ -2050,7 +2059,7 @@ pub struct PagestreamNblocksRequest {
     pub rel: RelTag,
 }
 
-#[derive(Debug, Default, PartialEq, Eq, Clone, Copy)]
+#[derive(Debug, PartialEq, Eq, Clone, Copy)]
 pub struct PagestreamGetPageRequest {
     pub hdr: PagestreamRequest,
     pub rel: RelTag,

libs/pageserver_api/src/reltag.rs

@@ -24,7 +24,7 @@ use serde::{Deserialize, Serialize};
 // FIXME: should move 'forknum' as last field to keep this consistent with Postgres.
 // Then we could replace the custom Ord and PartialOrd implementations below with
 // deriving them. This will require changes in walredoproc.c.
-#[derive(Debug, Default, PartialEq, Eq, Hash, Clone, Copy, Serialize, Deserialize)]
+#[derive(Debug, PartialEq, Eq, Hash, Clone, Copy, Serialize, Deserialize)]
 pub struct RelTag {
     pub forknum: u8,
     pub spcnode: Oid,
@@ -184,12 +184,12 @@ pub enum SlruKind {
     MultiXactOffsets,
 }
 
-impl fmt::Display for SlruKind {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+impl SlruKind {
+    pub fn to_str(&self) -> &'static str {
         match self {
-            Self::Clog => write!(f, "pg_xact"),
-            Self::MultiXactMembers => write!(f, "pg_multixact/members"),
-            Self::MultiXactOffsets => write!(f, "pg_multixact/offsets"),
+            Self::Clog => "pg_xact",
+            Self::MultiXactMembers => "pg_multixact/members",
+            Self::MultiXactOffsets => "pg_multixact/offsets",
         }
     }
 }

libs/posthog_client_lite/Cargo.toml

@@ -6,14 +6,9 @@ license.workspace = true
 
 [dependencies]
 anyhow.workspace = true
-arc-swap.workspace = true
 reqwest.workspace = true
-serde_json.workspace = true
 serde.workspace = true
+serde_json.workspace = true
 sha2.workspace = true
-thiserror.workspace = true
-tokio = { workspace = true, features = ["process", "sync", "fs", "rt", "io-util", "time"] }
-tokio-util.workspace = true
-tracing-utils.workspace = true
-tracing.workspace = true
 workspace_hack.workspace = true
+thiserror.workspace = true

libs/posthog_client_lite/src/background_loop.rs

@@ -1,87 +0,0 @@
-//! A background loop that fetches feature flags from PostHog and updates the feature store.
-
-use std::{sync::Arc, time::Duration};
-
-use arc_swap::ArcSwap;
-use tokio_util::sync::CancellationToken;
-use tracing::{Instrument, info_span};
-
-use crate::{CaptureEvent, FeatureStore, PostHogClient, PostHogClientConfig};
-
-/// A background loop that fetches feature flags from PostHog and updates the feature store.
-pub struct FeatureResolverBackgroundLoop {
-    posthog_client: PostHogClient,
-    feature_store: ArcSwap<FeatureStore>,
-    cancel: CancellationToken,
-}
-
-impl FeatureResolverBackgroundLoop {
-    pub fn new(config: PostHogClientConfig, shutdown_pageserver: CancellationToken) -> Self {
-        Self {
-            posthog_client: PostHogClient::new(config),
-            feature_store: ArcSwap::new(Arc::new(FeatureStore::new())),
-            cancel: shutdown_pageserver,
-        }
-    }
-
-    pub fn spawn(
-        self: Arc<Self>,
-        handle: &tokio::runtime::Handle,
-        refresh_period: Duration,
-        fake_tenants: Vec<CaptureEvent>,
-    ) {
-        let this = self.clone();
-        let cancel = self.cancel.clone();
-
-        // Main loop of updating the feature flags.
-        handle.spawn(
-            async move {
-                tracing::info!("Starting PostHog feature resolver");
-                let mut ticker = tokio::time::interval(refresh_period);
-                ticker.set_missed_tick_behavior(tokio::time::MissedTickBehavior::Skip);
-                loop {
-                    tokio::select! {
-                        _ = ticker.tick() => {}
-                        _ = cancel.cancelled() => break
-                    }
-                    let resp = match this
-                        .posthog_client
-                        .get_feature_flags_local_evaluation()
-                        .await
-                    {
-                        Ok(resp) => resp,
-                        Err(e) => {
-                            tracing::warn!("Cannot get feature flags: {}", e);
-                            continue;
-                        }
-                    };
-                    let feature_store = FeatureStore::new_with_flags(resp.flags);
-                    this.feature_store.store(Arc::new(feature_store));
-                    tracing::info!("Feature flag updated");
-                }
-                tracing::info!("PostHog feature resolver stopped");
-            }
-            .instrument(info_span!("posthog_feature_resolver")),
-        );
-
-        // Report fake tenants to PostHog so that we have the combination of all the properties in the UI.
-        // Do one report per pageserver restart.
-        let this = self.clone();
-        handle.spawn(
-            async move {
-                tracing::info!("Starting PostHog feature reporter");
-                for tenant in &fake_tenants {
-                    tracing::info!("Reporting fake tenant: {:?}", tenant);
-                }
-                if let Err(e) = this.posthog_client.capture_event_batch(&fake_tenants).await {
-                    tracing::warn!("Cannot report fake tenants: {}", e);
-                }
-            }
-            .instrument(info_span!("posthog_feature_reporter")),
-        );
-    }
-
-    pub fn feature_store(&self) -> Arc<FeatureStore> {
-        self.feature_store.load_full()
-    }
-}

libs/posthog_client_lite/src/lib.rs

@@ -1,9 +1,5 @@
 //! A lite version of the PostHog client that only supports local evaluation of feature flags.
 
-mod background_loop;
-
-pub use background_loop::FeatureResolverBackgroundLoop;
-
 use std::collections::HashMap;
 
 use serde::{Deserialize, Serialize};
@@ -22,19 +18,10 @@ pub enum PostHogEvaluationError {
     Internal(String),
 }
 
-impl PostHogEvaluationError {
-    pub fn as_variant_str(&self) -> &'static str {
-        match self {
-            PostHogEvaluationError::NotAvailable(_) => "not_available",
-            PostHogEvaluationError::NoConditionGroupMatched => "no_condition_group_matched",
-            PostHogEvaluationError::Internal(_) => "internal",
-        }
-    }
-}
-
 #[derive(Deserialize)]
 pub struct LocalEvaluationResponse {
-    pub flags: Vec<LocalEvaluationFlag>,
+    #[allow(dead_code)]
+    flags: Vec<LocalEvaluationFlag>,
 }
 
 #[derive(Deserialize)]
@@ -47,7 +34,7 @@ pub struct LocalEvaluationFlag {
 #[derive(Deserialize)]
 pub struct LocalEvaluationFlagFilters {
     groups: Vec<LocalEvaluationFlagFilterGroup>,
-    multivariate: Option<LocalEvaluationFlagMultivariate>,
+    multivariate: LocalEvaluationFlagMultivariate,
 }
 
 #[derive(Deserialize)]
@@ -64,7 +51,7 @@ pub struct LocalEvaluationFlagFilterProperty {
     operator: String,
 }
 
-#[derive(Debug, Serialize, Deserialize, Clone)]
+#[derive(Debug, Serialize, Deserialize)]
 #[serde(untagged)]
 pub enum PostHogFlagFilterPropertyValue {
     String(String),
@@ -107,12 +94,6 @@ impl FeatureStore {
         }
     }
 
-    pub fn new_with_flags(flags: Vec<LocalEvaluationFlag>) -> Self {
-        let mut store = Self::new();
-        store.set_flags(flags);
-        store
-    }
-
     pub fn set_flags(&mut self, flags: Vec<LocalEvaluationFlag>) {
         self.flags.clear();
         for flag in flags {
@@ -264,7 +245,7 @@ impl FeatureStore {
         }
     }
 
-    /// Evaluate a multivariate feature flag. Returns an error if the flag is not available or if there are errors
+    /// Evaluate a multivariate feature flag. Returns `None` if the flag is not available or if there are errors
     /// during the evaluation.
     ///
     /// The parsing logic is as follows:
@@ -282,15 +263,10 @@ impl FeatureStore {
     /// Example: we have a multivariate flag with 3 groups of the configured global rollout percentage: A (10%), B (20%), C (70%).
     /// There is a single group with a condition that has a rollout percentage of 10% and it does not have a variant override.
     /// Then, we will have 1% of the users evaluated to A, 2% to B, and 7% to C.
-    ///
-    /// Error handling: the caller should inspect the error and decide the behavior when a feature flag
-    /// cannot be evaluated (i.e., default to false if it cannot be resolved). The error should *not* be
-    /// propagated beyond where the feature flag gets resolved.
     pub fn evaluate_multivariate(
         &self,
         flag_key: &str,
         user_id: &str,
-        properties: &HashMap<String, PostHogFlagFilterPropertyValue>,
     ) -> Result<String, PostHogEvaluationError> {
         let hash_on_global_rollout_percentage =
             Self::consistent_hash(user_id, flag_key, "multivariate");
@@ -300,39 +276,10 @@ impl FeatureStore {
             flag_key,
             hash_on_global_rollout_percentage,
             hash_on_group_rollout_percentage,
-            properties,
+            &HashMap::new(),
         )
     }
 
-    /// Evaluate a boolean feature flag. Returns  an error if the flag is not available or if there are errors
-    /// during the evaluation.
-    ///
-    /// The parsing logic is as follows:
-    ///
-    /// * Generate a consistent hash for the tenant-feature.
-    /// * Match each filter group.
-    ///   - If a group is matched, it will first determine whether the user is in the range of the rollout
-    ///     percentage.
-    ///   - If the hash falls within the group's rollout percentage, return true.
-    /// * Otherwise, continue with the next group until all groups are evaluated and no group is within the
-    ///   rollout percentage.
-    /// * If there are no matching groups, return an error.
-    ///
-    /// Returns `Ok(())` if the feature flag evaluates to true. In the future, it will return a payload.
-    ///
-    /// Error handling: the caller should inspect the error and decide the behavior when a feature flag
-    /// cannot be evaluated (i.e., default to false if it cannot be resolved). The error should *not* be
-    /// propagated beyond where the feature flag gets resolved.
-    pub fn evaluate_boolean(
-        &self,
-        flag_key: &str,
-        user_id: &str,
-        properties: &HashMap<String, PostHogFlagFilterPropertyValue>,
-    ) -> Result<(), PostHogEvaluationError> {
-        let hash_on_global_rollout_percentage = Self::consistent_hash(user_id, flag_key, "boolean");
-        self.evaluate_boolean_inner(flag_key, hash_on_global_rollout_percentage, properties)
-    }
-
     /// Evaluate a multivariate feature flag. Note that we directly take the mapped user ID
     /// (a consistent hash ranging from 0 to 1) so that it is easier to use it in the tests
     /// and avoid duplicate computations.
@@ -359,11 +306,6 @@ impl FeatureStore {
                     flag_key
                 )));
             }
-            let Some(ref multivariate) = flag_config.filters.multivariate else {
-                return Err(PostHogEvaluationError::Internal(format!(
-                    "No multivariate available, should use evaluate_boolean?: {flag_key}"
-                )));
-            };
             // TODO: sort the groups so that variant overrides always get evaluated first and it follows the PostHog
             // Python SDK behavior; for now we do not configure conditions without variant overrides in Neon so it
             // does not matter.
@@ -372,7 +314,7 @@ impl FeatureStore {
                     GroupEvaluationResult::MatchedAndOverride(variant) => return Ok(variant),
                     GroupEvaluationResult::MatchedAndEvaluate => {
                         let mut percentage = 0;
-                        for variant in &multivariate.variants {
+                        for variant in &flag_config.filters.multivariate.variants {
                             percentage += variant.rollout_percentage;
                             if self
                                 .evaluate_percentage(hash_on_global_rollout_percentage, percentage)
@@ -400,89 +342,6 @@ impl FeatureStore {
             )))
         }
     }
-
-    /// Evaluate a multivariate feature flag. Note that we directly take the mapped user ID
-    /// (a consistent hash ranging from 0 to 1) so that it is easier to use it in the tests
-    /// and avoid duplicate computations.
-    ///
-    /// Use a different consistent hash for evaluating the group rollout percentage.
-    /// The behavior: if the condition is set to rolling out to 10% of the users, and
-    /// we set the variant A to 20% in the global config, then 2% of the total users will
-    /// be evaluated to variant A.
-    ///
-    /// Note that the hash to determine group rollout percentage is shared across all groups. So if we have two
-    /// exactly-the-same conditions with 10% and 20% rollout percentage respectively, a total of 20% of the users
-    /// will be evaluated (versus 30% if group evaluation is done independently).
-    pub(crate) fn evaluate_boolean_inner(
-        &self,
-        flag_key: &str,
-        hash_on_global_rollout_percentage: f64,
-        properties: &HashMap<String, PostHogFlagFilterPropertyValue>,
-    ) -> Result<(), PostHogEvaluationError> {
-        if let Some(flag_config) = self.flags.get(flag_key) {
-            if !flag_config.active {
-                return Err(PostHogEvaluationError::NotAvailable(format!(
-                    "The feature flag is not active: {}",
-                    flag_key
-                )));
-            }
-            if flag_config.filters.multivariate.is_some() {
-                return Err(PostHogEvaluationError::Internal(format!(
-                    "This looks like a multivariate flag, should use evaluate_multivariate?: {flag_key}"
-                )));
-            };
-            // TODO: sort the groups so that variant overrides always get evaluated first and it follows the PostHog
-            // Python SDK behavior; for now we do not configure conditions without variant overrides in Neon so it
-            // does not matter.
-            for group in &flag_config.filters.groups {
-                match self.evaluate_group(group, hash_on_global_rollout_percentage, properties)? {
-                    GroupEvaluationResult::MatchedAndOverride(_) => {
-                        return Err(PostHogEvaluationError::Internal(format!(
-                            "Boolean flag cannot have overrides: {}",
-                            flag_key
-                        )));
-                    }
-                    GroupEvaluationResult::MatchedAndEvaluate => {
-                        return Ok(());
-                    }
-                    GroupEvaluationResult::Unmatched => continue,
-                }
-            }
-            // If no group is matched, the feature is not available, and up to the caller to decide what to do.
-            Err(PostHogEvaluationError::NoConditionGroupMatched)
-        } else {
-            // The feature flag is not available yet
-            Err(PostHogEvaluationError::NotAvailable(format!(
-                "Not found in the local evaluation spec: {}",
-                flag_key
-            )))
-        }
-    }
-
-    /// Infer whether a feature flag is a boolean flag by checking if it has a multivariate filter.
-    pub fn is_feature_flag_boolean(&self, flag_key: &str) -> Result<bool, PostHogEvaluationError> {
-        if let Some(flag_config) = self.flags.get(flag_key) {
-            Ok(flag_config.filters.multivariate.is_none())
-        } else {
-            Err(PostHogEvaluationError::NotAvailable(format!(
-                "Not found in the local evaluation spec: {}",
-                flag_key
-            )))
-        }
-    }
-}
-
-pub struct PostHogClientConfig {
-    /// The server API key.
-    pub server_api_key: String,
-    /// The client API key.
-    pub client_api_key: String,
-    /// The project ID.
-    pub project_id: String,
-    /// The private API URL.
-    pub private_api_url: String,
-    /// The public API URL.
-    pub public_api_url: String,
 }
 
 /// A lite PostHog client.
@@ -501,23 +360,37 @@ pub struct PostHogClientConfig {
 /// want to report the feature flag usage back to PostHog. The current plan is to use PostHog only as an UI to
 /// configure feature flags so it is very likely that the client API will not be used.
 pub struct PostHogClient {
-    /// The config.
-    config: PostHogClientConfig,
+    /// The server API key.
+    server_api_key: String,
+    /// The client API key.
+    client_api_key: String,
+    /// The project ID.
+    project_id: String,
+    /// The private API URL.
+    private_api_url: String,
+    /// The public API URL.
+    public_api_url: String,
     /// The HTTP client.
     client: reqwest::Client,
 }
 
-#[derive(Serialize, Debug)]
-pub struct CaptureEvent {
-    pub event: String,
-    pub distinct_id: String,
-    pub properties: serde_json::Value,
-}
-
 impl PostHogClient {
-    pub fn new(config: PostHogClientConfig) -> Self {
+    pub fn new(
+        server_api_key: String,
+        client_api_key: String,
+        project_id: String,
+        private_api_url: String,
+        public_api_url: String,
+    ) -> Self {
         let client = reqwest::Client::new();
-        Self { config, client }
+        Self {
+            server_api_key,
+            client_api_key,
+            project_id,
+            private_api_url,
+            public_api_url,
+            client,
+        }
     }
 
     pub fn new_with_us_region(
@@ -525,13 +398,13 @@ impl PostHogClient {
         client_api_key: String,
         project_id: String,
     ) -> Self {
-        Self::new(PostHogClientConfig {
+        Self::new(
             server_api_key,
             client_api_key,
             project_id,
-            private_api_url: "https://us.posthog.com".to_string(),
-            public_api_url: "https://us.i.posthog.com".to_string(),
-        })
+            "https://us.posthog.com".to_string(),
+            "https://us.i.posthog.com".to_string(),
+        )
     }
 
     /// Fetch the feature flag specs from the server.
@@ -549,23 +422,15 @@ impl PostHogClient {
         // with bearer token of self.server_api_key
         let url = format!(
             "{}/api/projects/{}/feature_flags/local_evaluation",
-            self.config.private_api_url, self.config.project_id
+            self.private_api_url, self.project_id
         );
         let response = self
             .client
             .get(url)
-            .bearer_auth(&self.config.server_api_key)
+            .bearer_auth(&self.server_api_key)
             .send()
             .await?;
-        let status = response.status();
         let body = response.text().await?;
-        if !status.is_success() {
-            return Err(anyhow::anyhow!(
-                "Failed to get feature flags: {}, {}",
-                status,
-                body
-            ));
-        }
         Ok(serde_json::from_str(&body)?)
     }
 
@@ -577,54 +442,21 @@ impl PostHogClient {
         &self,
         event: &str,
         distinct_id: &str,
-        properties: &serde_json::Value,
+        properties: &HashMap<String, PostHogFlagFilterPropertyValue>,
     ) -> anyhow::Result<()> {
         // PUBLIC_URL/capture/
-        let url = format!("{}/capture/", self.config.public_api_url);
-        let response = self
-            .client
+        // with bearer token of self.client_api_key
+        let url = format!("{}/capture/", self.public_api_url);
+        self.client
             .post(url)
             .body(serde_json::to_string(&json!({
-                "api_key": self.config.client_api_key,
+                "api_key": self.client_api_key,
                 "distinct_id": distinct_id,
                 "event": event,
                 "properties": properties,
             }))?)
             .send()
             .await?;
-        let status = response.status();
-        let body = response.text().await?;
-        if !status.is_success() {
-            return Err(anyhow::anyhow!(
-                "Failed to capture events: {}, {}",
-                status,
-                body
-            ));
-        }
-        Ok(())
-    }
-
-    pub async fn capture_event_batch(&self, events: &[CaptureEvent]) -> anyhow::Result<()> {
-        // PUBLIC_URL/batch/
-        let url = format!("{}/batch/", self.config.public_api_url);
-        let response = self
-            .client
-            .post(url)
-            .body(serde_json::to_string(&json!({
-                "api_key": self.config.client_api_key,
-                "batch": events,
-            }))?)
-            .send()
-            .await?;
-        let status = response.status();
-        let body = response.text().await?;
-        if !status.is_success() {
-            return Err(anyhow::anyhow!(
-                "Failed to capture events: {}, {}",
-                status,
-                body
-            ));
-        }
         Ok(())
     }
 }
@@ -635,162 +467,95 @@ mod tests {
 
     fn data() -> &'static str {
         r#"{
-  "flags": [
-    {
-      "id": 141807,
-      "team_id": 152860,
-      "name": "",
-      "key": "image-compaction-boundary",
-      "filters": {
-        "groups": [
-          {
-            "variant": null,
-            "properties": [
-              {
-                "key": "plan_type",
-                "type": "person",
-                "value": [
-                  "free"
-                ],
-                "operator": "exact"
-              }
+            "flags": [
+                {
+                    "id": 132794,
+                    "team_id": 152860,
+                    "name": "",
+                    "key": "gc-compaction",
+                    "filters": {
+                        "groups": [
+                            {
+                                "variant": "enabled-stage-2",
+                                "properties": [
+                                    {
+                                        "key": "plan_type",
+                                        "type": "person",
+                                        "value": [
+                                            "free"
+                                        ],
+                                        "operator": "exact"
+                                    },
+                                    {
+                                        "key": "pageserver_remote_size",
+                                        "type": "person",
+                                        "value": "10000000",
+                                        "operator": "lt"
+                                    }
+                                ],
+                                "rollout_percentage": 50
+                            },
+                            {
+                                "properties": [
+                                    {
+                                        "key": "plan_type",
+                                        "type": "person",
+                                        "value": [
+                                            "free"
+                                        ],
+                                        "operator": "exact"
+                                    },
+                                    {
+                                        "key": "pageserver_remote_size",
+                                        "type": "person",
+                                        "value": "10000000",
+                                        "operator": "lt"
+                                    }
+                                ],
+                                "rollout_percentage": 80
+                            }
+                        ],
+                        "payloads": {},
+                        "multivariate": {
+                            "variants": [
+                                {
+                                    "key": "disabled",
+                                    "name": "",
+                                    "rollout_percentage": 90
+                                },
+                                {
+                                    "key": "enabled-stage-1",
+                                    "name": "",
+                                    "rollout_percentage": 10
+                                },
+                                {
+                                    "key": "enabled-stage-2",
+                                    "name": "",
+                                    "rollout_percentage": 0
+                                },
+                                {
+                                    "key": "enabled-stage-3",
+                                    "name": "",
+                                    "rollout_percentage": 0
+                                },
+                                {
+                                    "key": "enabled",
+                                    "name": "",
+                                    "rollout_percentage": 0
+                                }
+                            ]
+                        }
+                    },
+                    "deleted": false,
+                    "active": true,
+                    "ensure_experience_continuity": false,
+                    "has_encrypted_payloads": false,
+                    "version": 6
+                }
             ],
-            "rollout_percentage": 40
-          },
-          {
-            "variant": null,
-            "properties": [],
-            "rollout_percentage": 10
-          }
-        ],
-        "payloads": {},
-        "multivariate": null
-      },
-      "deleted": false,
-      "active": true,
-      "ensure_experience_continuity": false,
-      "has_encrypted_payloads": false,
-      "version": 1
-    },
-    {
-      "id": 135586,
-      "team_id": 152860,
-      "name": "",
-      "key": "boolean-flag",
-      "filters": {
-        "groups": [
-          {
-            "variant": null,
-            "properties": [
-              {
-                "key": "plan_type",
-                "type": "person",
-                "value": [
-                  "free"
-                ],
-                "operator": "exact"
-              }
-            ],
-            "rollout_percentage": 47
-          }
-        ],
-        "payloads": {},
-        "multivariate": null
-      },
-      "deleted": false,
-      "active": true,
-      "ensure_experience_continuity": false,
-      "has_encrypted_payloads": false,
-      "version": 1
-    },
-    {
-      "id": 132794,
-      "team_id": 152860,
-      "name": "",
-      "key": "gc-compaction",
-      "filters": {
-        "groups": [
-          {
-            "variant": "enabled-stage-2",
-            "properties": [
-              {
-                "key": "plan_type",
-                "type": "person",
-                "value": [
-                  "free"
-                ],
-                "operator": "exact"
-              },
-              {
-                "key": "pageserver_remote_size",
-                "type": "person",
-                "value": "10000000",
-                "operator": "lt"
-              }
-            ],
-             "rollout_percentage": 50
-          },
-          {
-            "properties": [
-              {
-                "key": "plan_type",
-                "type": "person",
-                "value": [
-                  "free"
-                ],
-                "operator": "exact"
-              },
-              {
-                "key": "pageserver_remote_size",
-                "type": "person",
-                "value": "10000000",
-                "operator": "lt"
-              }
-            ],
-            "rollout_percentage": 80
-          }
-        ],
-        "payloads": {},
-        "multivariate": {
-          "variants": [
-            {
-              "key": "disabled",
-              "name": "",
-              "rollout_percentage": 90
-            },
-            {
-              "key": "enabled-stage-1",
-              "name": "",
-              "rollout_percentage": 10
-            },
-            {
-              "key": "enabled-stage-2",
-              "name": "",
-              "rollout_percentage": 0
-            },
-            {
-              "key": "enabled-stage-3",
-              "name": "",
-              "rollout_percentage": 0
-            },
-            {
-              "key": "enabled",
-              "name": "",
-              "rollout_percentage": 0
-            }
-          ]
-        }
-      },
-      "deleted": false,
-      "active": true,
-      "ensure_experience_continuity": false,
-      "has_encrypted_payloads": false,
-      "version": 7
-    }
-  ],
-  "group_type_mapping": {},
-  "cohorts": {}
-}"#
+            "group_type_mapping": {},
+            "cohorts": {}
+        }"#
     }
 
     #[test]
@@ -866,125 +631,4 @@ mod tests {
             Err(PostHogEvaluationError::NoConditionGroupMatched)
         ),);
     }
-
-    #[test]
-    fn evaluate_boolean_1() {
-        // The `boolean-flag` feature flag only has one group that matches on the free user.
-
-        let mut store = FeatureStore::new();
-        let response: LocalEvaluationResponse = serde_json::from_str(data()).unwrap();
-        store.set_flags(response.flags);
-
-        // This lacks the required properties and cannot be evaluated.
-        let variant = store.evaluate_boolean_inner("boolean-flag", 1.00, &HashMap::new());
-        assert!(matches!(
-            variant,
-            Err(PostHogEvaluationError::NotAvailable(_))
-        ),);
-
-        let properties_unmatched = HashMap::from([
-            (
-                "plan_type".to_string(),
-                PostHogFlagFilterPropertyValue::String("paid".to_string()),
-            ),
-            (
-                "pageserver_remote_size".to_string(),
-                PostHogFlagFilterPropertyValue::Number(1000.0),
-            ),
-        ]);
-
-        // This does not match any group so there will be an error.
-        let variant = store.evaluate_boolean_inner("boolean-flag", 1.00, &properties_unmatched);
-        assert!(matches!(
-            variant,
-            Err(PostHogEvaluationError::NoConditionGroupMatched)
-        ),);
-
-        let properties = HashMap::from([
-            (
-                "plan_type".to_string(),
-                PostHogFlagFilterPropertyValue::String("free".to_string()),
-            ),
-            (
-                "pageserver_remote_size".to_string(),
-                PostHogFlagFilterPropertyValue::Number(1000.0),
-            ),
-        ]);
-
-        // It matches the first group as 0.10 <= 0.50 and the properties are matched. Then it gets evaluated to the variant override.
-        let variant = store.evaluate_boolean_inner("boolean-flag", 0.10, &properties);
-        assert!(variant.is_ok());
-
-        // It matches the group conditions but not the group rollout percentage.
-        let variant = store.evaluate_boolean_inner("boolean-flag", 1.00, &properties);
-        assert!(matches!(
-            variant,
-            Err(PostHogEvaluationError::NoConditionGroupMatched)
-        ),);
-    }
-
-    #[test]
-    fn evaluate_boolean_2() {
-        // The `image-compaction-boundary` feature flag has one group that matches on the free user and a group that matches on all users.
-
-        let mut store = FeatureStore::new();
-        let response: LocalEvaluationResponse = serde_json::from_str(data()).unwrap();
-        store.set_flags(response.flags);
-
-        // This lacks the required properties and cannot be evaluated.
-        let variant =
-            store.evaluate_boolean_inner("image-compaction-boundary", 1.00, &HashMap::new());
-        assert!(matches!(
-            variant,
-            Err(PostHogEvaluationError::NotAvailable(_))
-        ),);
-
-        let properties_unmatched = HashMap::from([
-            (
-                "plan_type".to_string(),
-                PostHogFlagFilterPropertyValue::String("paid".to_string()),
-            ),
-            (
-                "pageserver_remote_size".to_string(),
-                PostHogFlagFilterPropertyValue::Number(1000.0),
-            ),
-        ]);
-
-        // This does not match the filtered group but the all user group.
-        let variant =
-            store.evaluate_boolean_inner("image-compaction-boundary", 1.00, &properties_unmatched);
-        assert!(matches!(
-            variant,
-            Err(PostHogEvaluationError::NoConditionGroupMatched)
-        ),);
-        let variant =
-            store.evaluate_boolean_inner("image-compaction-boundary", 0.05, &properties_unmatched);
-        assert!(variant.is_ok());
-
-        let properties = HashMap::from([
-            (
-                "plan_type".to_string(),
-                PostHogFlagFilterPropertyValue::String("free".to_string()),
-            ),
-            (
-                "pageserver_remote_size".to_string(),
-                PostHogFlagFilterPropertyValue::Number(1000.0),
-            ),
-        ]);
-
-        // It matches the first group as 0.30 <= 0.40 and the properties are matched. Then it gets evaluated to the variant override.
-        let variant = store.evaluate_boolean_inner("image-compaction-boundary", 0.30, &properties);
-        assert!(variant.is_ok());
-
-        // It matches the group conditions but not the group rollout percentage.
-        let variant = store.evaluate_boolean_inner("image-compaction-boundary", 1.00, &properties);
-        assert!(matches!(
-            variant,
-            Err(PostHogEvaluationError::NoConditionGroupMatched)
-        ),);
-
-        // It matches the second "all" group conditions.
-        let variant = store.evaluate_boolean_inner("image-compaction-boundary", 0.09, &properties);
-        assert!(variant.is_ok());
-    }
 }

libs/utils/src/leaky_bucket.rs

@@ -28,7 +28,6 @@ use std::time::Duration;
 use tokio::sync::Notify;
 use tokio::time::Instant;
 
-#[derive(Clone, Copy)]
 pub struct LeakyBucketConfig {
     /// This is the "time cost" of a single request unit.
     /// Should loosely represent how long it takes to handle a request unit in active resource time.

libs/utils/src/lib.rs

@@ -73,7 +73,6 @@ pub mod error;
 /// async timeout helper
 pub mod timeout;
 
-pub mod span;
 pub mod sync;
 
 pub mod failpoint_support;

libs/utils/src/span.rs

@@ -1,19 +0,0 @@
-//! Tracing span helpers.
-
-/// Records the given fields in the current span, as a single call. The fields must already have
-/// been declared for the span (typically with empty values).
-#[macro_export]
-macro_rules! span_record {
-    ($($tokens:tt)*) => {$crate::span_record_in!(::tracing::Span::current(), $($tokens)*)};
-}
-
-/// Records the given fields in the given span, as a single call. The fields must already have been
-/// declared for the span (typically with empty values).
-#[macro_export]
-macro_rules! span_record_in {
-    ($span:expr, $($tokens:tt)*) => {
-        if let Some(meta) = $span.metadata() {
-            $span.record_all(&tracing::valueset!(meta.fields(), $($tokens)*));
-        }
-    };
-}

libs/walproposer/src/api_bindings.rs

@@ -439,7 +439,6 @@ pub fn empty_shmem() -> crate::bindings::WalproposerShmemState {
         currentClusterSize: crate::bindings::pg_atomic_uint64 { value: 0 },
         shard_ps_feedback: [empty_feedback; 128],
         num_shards: 0,
-        replica_promote: false,
         min_ps_feedback: empty_feedback,
     }
 }

libs/walproposer/src/walproposer.rs

@@ -1,7 +1,6 @@
 #![allow(clippy::todo)]
 
 use std::ffi::CString;
-use std::str::FromStr;
 
 use postgres_ffi::WAL_SEGMENT_SIZE;
 use utils::id::TenantTimelineId;
@@ -174,8 +173,6 @@ pub struct Config {
     pub ttid: TenantTimelineId,
     /// List of safekeepers in format `host:port`
     pub safekeepers_list: Vec<String>,
-    /// libpq connection info options
-    pub safekeeper_conninfo_options: String,
     /// Safekeeper reconnect timeout in milliseconds
     pub safekeeper_reconnect_timeout: i32,
     /// Safekeeper connection timeout in milliseconds
@@ -205,9 +202,6 @@ impl Wrapper {
             .into_bytes_with_nul();
         assert!(safekeepers_list_vec.len() == safekeepers_list_vec.capacity());
         let safekeepers_list = safekeepers_list_vec.as_mut_ptr() as *mut std::ffi::c_char;
-        let safekeeper_conninfo_options = CString::from_str(&config.safekeeper_conninfo_options)
-            .unwrap()
-            .into_raw();
 
         let callback_data = Box::into_raw(Box::new(api)) as *mut ::std::os::raw::c_void;
 
@@ -215,11 +209,11 @@ impl Wrapper {
             neon_tenant,
             neon_timeline,
             safekeepers_list,
-            safekeeper_conninfo_options,
             safekeeper_reconnect_timeout: config.safekeeper_reconnect_timeout,
             safekeeper_connection_timeout: config.safekeeper_connection_timeout,
             wal_segment_size: WAL_SEGMENT_SIZE as i32, // default 16MB
             syncSafekeepers: config.sync_safekeepers,
+            replicaPromote: false,
             systemId: 0,
             pgTimeline: 1,
             proto_version: 3,
@@ -583,7 +577,6 @@ mod tests {
         let config = crate::walproposer::Config {
             ttid,
             safekeepers_list: vec!["localhost:5000".to_string()],
-            safekeeper_conninfo_options: String::new(),
             safekeeper_reconnect_timeout: 1000,
             safekeeper_connection_timeout: 10000,
             sync_safekeepers: true,

pageserver/Cargo.toml

@@ -17,70 +17,50 @@ anyhow.workspace = true
 arc-swap.workspace = true
 async-compression.workspace = true
 async-stream.workspace = true
-bincode.workspace = true
 bit_field.workspace = true
+bincode.workspace = true
 byteorder.workspace = true
 bytes.workspace = true
-camino-tempfile.workspace = true
 camino.workspace = true
+camino-tempfile.workspace = true
 chrono = { workspace = true, features = ["serde"] }
 clap = { workspace = true, features = ["string"] }
 consumption_metrics.workspace = true
 crc32c.workspace = true
 either.workspace = true
-enum-map.workspace = true
-enumset = { workspace = true, features = ["serde"]}
 fail.workspace = true
 futures.workspace = true
 hashlink.workspace = true
 hex.workspace = true
-http.workspace = true
-http-utils.workspace = true
-humantime-serde.workspace = true
 humantime.workspace = true
+humantime-serde.workspace = true
 hyper0.workspace = true
 itertools.workspace = true
 jsonwebtoken.workspace = true
 md5.workspace = true
-metrics.workspace = true
 nix.workspace = true
-num_cpus.workspace = true # hack to get the number of worker threads tokio uses
+# hack to get the number of worker threads tokio uses
+num_cpus.workspace = true
 num-traits.workspace = true
 once_cell.workspace = true
-pageserver_api.workspace = true
-pageserver_client.workspace = true # for ResponseErrorMessageExt TOOD refactor that
-pageserver_compaction.workspace = true
-pageserver_page_api.workspace = true
-pem.workspace = true
 pin-project-lite.workspace = true
 postgres_backend.workspace = true
-postgres_connection.workspace = true
-postgres_ffi.workspace = true
-postgres_initdb.workspace = true
 postgres-protocol.workspace = true
 postgres-types.workspace = true
-posthog_client_lite.workspace = true
+postgres_initdb.workspace = true
 pprof.workspace = true
-pq_proto.workspace = true
 rand.workspace = true
 range-set-blaze = { version = "0.1.16", features = ["alloc"] }
 regex.workspace = true
-remote_storage.workspace = true
-reqwest.workspace = true
-rpds.workspace = true
 rustls.workspace = true
 scopeguard.workspace = true
 send-future.workspace = true
+serde.workspace = true
 serde_json = { workspace = true, features = ["raw_value"] }
 serde_path_to_error.workspace = true
 serde_with.workspace = true
-serde.workspace = true
-smallvec.workspace = true
-storage_broker.workspace = true
-strum_macros.workspace = true
-strum.workspace = true
 sysinfo.workspace = true
-tenant_size_model.workspace = true
+tokio-tar.workspace = true
 thiserror.workspace = true
 tikv-jemallocator.workspace = true
 tokio = { workspace = true, features = ["process", "sync", "fs", "rt", "io-util", "time"] }
@@ -89,19 +69,34 @@ tokio-io-timeout.workspace = true
 tokio-postgres.workspace = true
 tokio-rustls.workspace = true
 tokio-stream.workspace = true
-tokio-tar.workspace = true
 tokio-util.workspace = true
 toml_edit = { workspace = true, features = [ "serde" ] }
-tonic.workspace = true
-tonic-reflection.workspace = true
-tower.workspace = true
 tracing.workspace = true
 tracing-utils.workspace = true
 url.workspace = true
-utils.workspace = true
-wal_decoder.workspace = true
 walkdir.workspace = true
+metrics.workspace = true
+pageserver_api.workspace = true
+pageserver_client.workspace = true # for ResponseErrorMessageExt TOOD refactor that
+pageserver_compaction.workspace = true
+pem.workspace = true
+postgres_connection.workspace = true
+postgres_ffi.workspace = true
+pq_proto.workspace = true
+remote_storage.workspace = true
+storage_broker.workspace = true
+tenant_size_model.workspace = true
+http-utils.workspace = true
+utils.workspace = true
 workspace_hack.workspace = true
+reqwest.workspace = true
+rpds.workspace = true
+enum-map.workspace = true
+enumset = { workspace = true, features = ["serde"]}
+strum.workspace = true
+strum_macros.workspace = true
+wal_decoder.workspace = true
+smallvec.workspace = true
 twox-hash.workspace = true
 
 [target.'cfg(target_os = "linux")'.dependencies]

pageserver/benches/bench_metrics.rs

@@ -264,56 +264,10 @@ mod propagation_of_cached_label_value {
     }
 }
 
-criterion_group!(histograms, histograms::bench_bucket_scalability);
-mod histograms {
-    use std::time::Instant;
-
-    use criterion::{BenchmarkId, Criterion};
-    use metrics::core::Collector;
-
-    pub fn bench_bucket_scalability(c: &mut Criterion) {
-        let mut g = c.benchmark_group("bucket_scalability");
-
-        for n in [1, 4, 8, 16, 32, 64, 128, 256] {
-            g.bench_with_input(BenchmarkId::new("nbuckets", n), &n, |b, n| {
-                b.iter_custom(|iters| {
-                    let buckets: Vec<f64> = (0..*n).map(|i| i as f64 * 100.0).collect();
-                    let histo = metrics::Histogram::with_opts(
-                        metrics::prometheus::HistogramOpts::new("name", "help")
-                            .buckets(buckets.clone()),
-                    )
-                    .unwrap();
-                    let start = Instant::now();
-                    for i in 0..usize::try_from(iters).unwrap() {
-                        histo.observe(buckets[i % buckets.len()]);
-                    }
-                    let elapsed = start.elapsed();
-                    // self-test
-                    let mfs = histo.collect();
-                    assert_eq!(mfs.len(), 1);
-                    let metrics = mfs[0].get_metric();
-                    assert_eq!(metrics.len(), 1);
-                    let histo = metrics[0].get_histogram();
-                    let buckets = histo.get_bucket();
-                    assert!(
-                        buckets
-                            .iter()
-                            .enumerate()
-                            .all(|(i, b)| b.get_cumulative_count()
-                                >= i as u64 * (iters / buckets.len() as u64))
-                    );
-                    elapsed
-                })
-            });
-        }
-    }
-}
-
 criterion_main!(
     label_values,
     single_metric_multicore_scalability,
-    propagation_of_cached_label_value,
-    histograms,
+    propagation_of_cached_label_value
 );
 
 /*
@@ -336,14 +290,6 @@ propagation_of_cached_label_value__naive/nthreads/8 time:   [211.50 ns 214.44 ns
 propagation_of_cached_label_value__long_lived_reference_per_thread/nthreads/1 time:   [14.135 ns 14.147 ns 14.160 ns]
 propagation_of_cached_label_value__long_lived_reference_per_thread/nthreads/4 time:   [14.243 ns 14.255 ns 14.268 ns]
 propagation_of_cached_label_value__long_lived_reference_per_thread/nthreads/8 time:   [14.470 ns 14.682 ns 14.895 ns]
-bucket_scalability/nbuckets/1     time:   [30.352 ns 30.353 ns 30.354 ns]
-bucket_scalability/nbuckets/4     time:   [30.464 ns 30.465 ns 30.467 ns]
-bucket_scalability/nbuckets/8     time:   [30.569 ns 30.575 ns 30.584 ns]
-bucket_scalability/nbuckets/16      time:   [30.961 ns 30.965 ns 30.969 ns]
-bucket_scalability/nbuckets/32      time:   [35.691 ns 35.707 ns 35.722 ns]
-bucket_scalability/nbuckets/64      time:   [47.829 ns 47.898 ns 47.974 ns]
-bucket_scalability/nbuckets/128     time:   [73.479 ns 73.512 ns 73.545 ns]
-bucket_scalability/nbuckets/256     time:   [127.92 ns 127.94 ns 127.96 ns]
 
 Results on an i3en.3xlarge instance
 
@@ -398,14 +344,6 @@ propagation_of_cached_label_value__naive/nthreads/8     time:   [434.87 ns 456.4
 propagation_of_cached_label_value__long_lived_reference_per_thread/nthreads/1     time:   [3.3767 ns 3.3974 ns 3.4220 ns]
 propagation_of_cached_label_value__long_lived_reference_per_thread/nthreads/4     time:   [3.6105 ns 4.2355 ns 5.1463 ns]
 propagation_of_cached_label_value__long_lived_reference_per_thread/nthreads/8     time:   [4.0889 ns 4.9714 ns 6.0779 ns]
-bucket_scalability/nbuckets/1     time:   [4.8455 ns 4.8542 ns 4.8646 ns]
-bucket_scalability/nbuckets/4     time:   [4.5663 ns 4.5722 ns 4.5787 ns]
-bucket_scalability/nbuckets/8     time:   [4.5531 ns 4.5670 ns 4.5842 ns]
-bucket_scalability/nbuckets/16      time:   [4.6392 ns 4.6524 ns 4.6685 ns]
-bucket_scalability/nbuckets/32      time:   [6.0302 ns 6.0439 ns 6.0589 ns]
-bucket_scalability/nbuckets/64      time:   [10.608 ns 10.644 ns 10.691 ns]
-bucket_scalability/nbuckets/128     time:   [22.178 ns 22.316 ns 22.483 ns]
-bucket_scalability/nbuckets/256     time:   [42.190 ns 42.328 ns 42.492 ns]
 
 Results on a Hetzner AX102 AMD Ryzen 9 7950X3D 16-Core Processor
 
@@ -424,13 +362,5 @@ propagation_of_cached_label_value__naive/nthreads/8     time:   [164.24 ns 170.1
 propagation_of_cached_label_value__long_lived_reference_per_thread/nthreads/1     time:   [2.2915 ns 2.2960 ns 2.3012 ns]
 propagation_of_cached_label_value__long_lived_reference_per_thread/nthreads/4     time:   [2.5726 ns 2.6158 ns 2.6624 ns]
 propagation_of_cached_label_value__long_lived_reference_per_thread/nthreads/8     time:   [2.7068 ns 2.8243 ns 2.9824 ns]
-bucket_scalability/nbuckets/1     time:   [6.3998 ns 6.4288 ns 6.4684 ns]
-bucket_scalability/nbuckets/4     time:   [6.3603 ns 6.3620 ns 6.3637 ns]
-bucket_scalability/nbuckets/8     time:   [6.1646 ns 6.1654 ns 6.1667 ns]
-bucket_scalability/nbuckets/16      time:   [6.1341 ns 6.1391 ns 6.1454 ns]
-bucket_scalability/nbuckets/32      time:   [8.2206 ns 8.2254 ns 8.2301 ns]
-bucket_scalability/nbuckets/64      time:   [13.988 ns 13.994 ns 14.000 ns]
-bucket_scalability/nbuckets/128     time:   [28.180 ns 28.216 ns 28.251 ns]
-bucket_scalability/nbuckets/256     time:   [54.914 ns 54.931 ns 54.951 ns]
 
 */

pageserver/page_api/Cargo.toml

@@ -5,13 +5,8 @@ edition.workspace = true
 license.workspace = true
 
 [dependencies]
-bytes.workspace = true
-pageserver_api.workspace = true
-postgres_ffi.workspace = true
 prost.workspace = true
-thiserror.workspace = true
 tonic.workspace = true
-utils.workspace = true
 workspace_hack.workspace = true
 
 [build-dependencies]

pageserver/page_api/proto/page_service.proto

@@ -54,9 +54,9 @@ service PageService {
   // RPCs use regular unary requests, since they are not as frequent and
   // performance-critical, and this simplifies implementation.
   //
-  // NB: a gRPC status response (e.g. errors) will terminate the stream. The
-  // stream may be shared by multiple Postgres backends, so we avoid this by
-  // sending them as GetPageResponse.status_code instead.
+  // NB: a status response (e.g. errors) will terminate the stream. The stream
+  // may be shared by e.g. multiple Postgres backends, so we should avoid this.
+  // Most errors are therefore sent as GetPageResponse.status instead.
   rpc GetPages (stream GetPageRequest) returns (stream GetPageResponse);
 
   // Returns the size of a relation, as # of blocks.
@@ -159,8 +159,8 @@ message GetPageRequest {
 // A GetPageRequest class. Primarily intended for observability, but may also be
 // used for prioritization in the future.
 enum GetPageClass {
-  // Unknown class. For backwards compatibility: used when an older client version sends a class
-  // that a newer server version has removed.
+  // Unknown class. For forwards compatibility: used when the client sends a
+  // class that the server doesn't know about.
   GET_PAGE_CLASS_UNKNOWN = 0;
   // A normal request. This is the default.
   GET_PAGE_CLASS_NORMAL = 1;
@@ -180,37 +180,31 @@ message GetPageResponse {
   // The original request's ID.
   uint64 request_id = 1;
   // The response status code.
-  GetPageStatusCode status_code = 2;
+  GetPageStatus status = 2;
   // A string describing the status, if any.
   string reason = 3;
-  // The 8KB page images, in the same order as the request. Empty if status_code != OK.
+  // The 8KB page images, in the same order as the request. Empty if status != OK.
   repeated bytes page_image = 4;
 }
 
-// A GetPageResponse status code.
-//
-// These are effectively equivalent to gRPC statuses. However, we use a bidirectional stream
-// (potentially shared by many backends), and a gRPC status response would terminate the stream so
-// we send GetPageResponse messages with these codes instead.
-enum GetPageStatusCode {
-  // Unknown status. For forwards compatibility: used when an older client version receives a new
-  // status code from a newer server version.
-  GET_PAGE_STATUS_CODE_UNKNOWN = 0;
+// A GetPageResponse status code. Since we use a bidirectional stream, we don't
+// want to send errors as gRPC statuses, since this would terminate the stream.
+enum GetPageStatus {
+  // Unknown status. For forwards compatibility: used when the server sends a
+  // status code that the client doesn't know about.
+  GET_PAGE_STATUS_UNKNOWN = 0;
   // The request was successful.
-  GET_PAGE_STATUS_CODE_OK = 1;
+  GET_PAGE_STATUS_OK = 1;
   // The page did not exist. The tenant/timeline/shard has already been
   // validated during stream setup.
-  GET_PAGE_STATUS_CODE_NOT_FOUND = 2;
+  GET_PAGE_STATUS_NOT_FOUND = 2;
   // The request was invalid.
-  GET_PAGE_STATUS_CODE_INVALID_REQUEST = 3;
-  // The request failed due to an internal server error.
-  GET_PAGE_STATUS_CODE_INTERNAL_ERROR = 4;
+  GET_PAGE_STATUS_INVALID = 3;
   // The tenant is rate limited. Slow down and retry later.
-  GET_PAGE_STATUS_CODE_SLOW_DOWN = 5;
-  // NB: shutdown errors are emitted as a gRPC Unavailable status.
-  //
-  // TODO: consider adding a GET_PAGE_STATUS_CODE_LAYER_DOWNLOAD in the case of a layer download.
-  // This could free up the server task to process other requests while the download is in progress.
+  GET_PAGE_STATUS_SLOW_DOWN = 4;
+  // TODO: consider adding a GET_PAGE_STATUS_LAYER_DOWNLOAD in the case of a
+  // layer download. This could free up the server task to process other
+  // requests while the layer download is in progress.
 }
 
 // Fetches the size of a relation at a given LSN, as # of blocks. Only valid on

pageserver/page_api/src/lib.rs

@@ -17,7 +17,3 @@ pub mod proto {
     pub use page_service_client::PageServiceClient;
     pub use page_service_server::{PageService, PageServiceServer};
 }
-
-mod model;
-
-pub use model::*;

pageserver/page_api/src/model.rs

@@ -1,587 +0,0 @@
-//! Structs representing the canonical page service API.
-//!
-//! These mirror the autogenerated Protobuf types. The differences are:
-//!
-//! - Types that are in fact required by the API are not Options. The protobuf "required"
-//!   attribute is deprecated and 'prost' marks a lot of members as optional because of that.
-//!   (See <https://github.com/tokio-rs/prost/issues/800> for a gripe on this)
-//!
-//! - Use more precise datatypes, e.g. Lsn and uints shorter than 32 bits.
-//!
-//! - Validate protocol invariants, via try_from() and try_into().
-//!
-//! Validation only happens on the receiver side, i.e. when converting from Protobuf to domain
-//! types. This is where it matters -- the Protobuf types are less strict than the domain types, and
-//! receivers should expect all sorts of junk from senders. This also allows the sender to use e.g.
-//! stream combinators without dealing with errors, and avoids validating the same message twice.
-
-use std::fmt::Display;
-
-use bytes::Bytes;
-use postgres_ffi::Oid;
-// TODO: split out Lsn, RelTag, SlruKind, Oid and other basic types to a separate crate, to avoid
-// pulling in all of their other crate dependencies when building the client.
-use utils::lsn::Lsn;
-
-use crate::proto;
-
-/// A protocol error. Typically returned via try_from() or try_into().
-#[derive(thiserror::Error, Debug)]
-pub enum ProtocolError {
-    #[error("field '{0}' has invalid value '{1}'")]
-    Invalid(&'static str, String),
-    #[error("required field '{0}' is missing")]
-    Missing(&'static str),
-}
-
-impl ProtocolError {
-    /// Helper to generate a new ProtocolError::Invalid for the given field and value.
-    pub fn invalid(field: &'static str, value: impl std::fmt::Debug) -> Self {
-        Self::Invalid(field, format!("{value:?}"))
-    }
-}
-
-impl From<ProtocolError> for tonic::Status {
-    fn from(err: ProtocolError) -> Self {
-        tonic::Status::invalid_argument(format!("{err}"))
-    }
-}
-
-/// The LSN a request should read at.
-#[derive(Clone, Copy, Debug)]
-pub struct ReadLsn {
-    /// The request's read LSN.
-    pub request_lsn: Lsn,
-    /// If given, the caller guarantees that the page has not been modified since this LSN. Must be
-    /// smaller than or equal to request_lsn. This allows the Pageserver to serve an old page
-    /// without waiting for the request LSN to arrive. If not given, the request will read at the
-    /// request_lsn and wait for it to arrive if necessary. Valid for all request types.
-    ///
-    /// It is undefined behaviour to make a request such that the page was, in fact, modified
-    /// between request_lsn and not_modified_since_lsn. The Pageserver might detect it and return an
-    /// error, or it might return the old page version or the new page version. Setting
-    /// not_modified_since_lsn equal to request_lsn is always safe, but can lead to unnecessary
-    /// waiting.
-    pub not_modified_since_lsn: Option<Lsn>,
-}
-
-impl Display for ReadLsn {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-        let req_lsn = self.request_lsn;
-        if let Some(mod_lsn) = self.not_modified_since_lsn {
-            write!(f, "{req_lsn}>={mod_lsn}")
-        } else {
-            req_lsn.fmt(f)
-        }
-    }
-}
-
-impl TryFrom<proto::ReadLsn> for ReadLsn {
-    type Error = ProtocolError;
-
-    fn try_from(pb: proto::ReadLsn) -> Result<Self, Self::Error> {
-        if pb.request_lsn == 0 {
-            return Err(ProtocolError::invalid("request_lsn", pb.request_lsn));
-        }
-        if pb.not_modified_since_lsn > pb.request_lsn {
-            return Err(ProtocolError::invalid(
-                "not_modified_since_lsn",
-                pb.not_modified_since_lsn,
-            ));
-        }
-        Ok(Self {
-            request_lsn: Lsn(pb.request_lsn),
-            not_modified_since_lsn: match pb.not_modified_since_lsn {
-                0 => None,
-                lsn => Some(Lsn(lsn)),
-            },
-        })
-    }
-}
-
-impl From<ReadLsn> for proto::ReadLsn {
-    fn from(read_lsn: ReadLsn) -> Self {
-        Self {
-            request_lsn: read_lsn.request_lsn.0,
-            not_modified_since_lsn: read_lsn.not_modified_since_lsn.unwrap_or_default().0,
-        }
-    }
-}
-
-// RelTag is defined in pageserver_api::reltag.
-pub type RelTag = pageserver_api::reltag::RelTag;
-
-impl TryFrom<proto::RelTag> for RelTag {
-    type Error = ProtocolError;
-
-    fn try_from(pb: proto::RelTag) -> Result<Self, Self::Error> {
-        Ok(Self {
-            spcnode: pb.spc_oid,
-            dbnode: pb.db_oid,
-            relnode: pb.rel_number,
-            forknum: pb
-                .fork_number
-                .try_into()
-                .map_err(|_| ProtocolError::invalid("fork_number", pb.fork_number))?,
-        })
-    }
-}
-
-impl From<RelTag> for proto::RelTag {
-    fn from(rel_tag: RelTag) -> Self {
-        Self {
-            spc_oid: rel_tag.spcnode,
-            db_oid: rel_tag.dbnode,
-            rel_number: rel_tag.relnode,
-            fork_number: rel_tag.forknum as u32,
-        }
-    }
-}
-
-/// Checks whether a relation exists, at the given LSN. Only valid on shard 0, other shards error.
-#[derive(Clone, Copy, Debug)]
-pub struct CheckRelExistsRequest {
-    pub read_lsn: ReadLsn,
-    pub rel: RelTag,
-}
-
-impl TryFrom<proto::CheckRelExistsRequest> for CheckRelExistsRequest {
-    type Error = ProtocolError;
-
-    fn try_from(pb: proto::CheckRelExistsRequest) -> Result<Self, Self::Error> {
-        Ok(Self {
-            read_lsn: pb
-                .read_lsn
-                .ok_or(ProtocolError::Missing("read_lsn"))?
-                .try_into()?,
-            rel: pb.rel.ok_or(ProtocolError::Missing("rel"))?.try_into()?,
-        })
-    }
-}
-
-impl From<CheckRelExistsRequest> for proto::CheckRelExistsRequest {
-    fn from(request: CheckRelExistsRequest) -> Self {
-        Self {
-            read_lsn: Some(request.read_lsn.into()),
-            rel: Some(request.rel.into()),
-        }
-    }
-}
-
-pub type CheckRelExistsResponse = bool;
-
-impl From<proto::CheckRelExistsResponse> for CheckRelExistsResponse {
-    fn from(pb: proto::CheckRelExistsResponse) -> Self {
-        pb.exists
-    }
-}
-
-impl From<CheckRelExistsResponse> for proto::CheckRelExistsResponse {
-    fn from(exists: CheckRelExistsResponse) -> Self {
-        Self { exists }
-    }
-}
-
-/// Requests a base backup at a given LSN.
-#[derive(Clone, Copy, Debug)]
-pub struct GetBaseBackupRequest {
-    /// The LSN to fetch a base backup at.
-    pub read_lsn: ReadLsn,
-    /// If true, logical replication slots will not be created.
-    pub replica: bool,
-}
-
-impl TryFrom<proto::GetBaseBackupRequest> for GetBaseBackupRequest {
-    type Error = ProtocolError;
-
-    fn try_from(pb: proto::GetBaseBackupRequest) -> Result<Self, Self::Error> {
-        Ok(Self {
-            read_lsn: pb
-                .read_lsn
-                .ok_or(ProtocolError::Missing("read_lsn"))?
-                .try_into()?,
-            replica: pb.replica,
-        })
-    }
-}
-
-impl From<GetBaseBackupRequest> for proto::GetBaseBackupRequest {
-    fn from(request: GetBaseBackupRequest) -> Self {
-        Self {
-            read_lsn: Some(request.read_lsn.into()),
-            replica: request.replica,
-        }
-    }
-}
-
-pub type GetBaseBackupResponseChunk = Bytes;
-
-impl TryFrom<proto::GetBaseBackupResponseChunk> for GetBaseBackupResponseChunk {
-    type Error = ProtocolError;
-
-    fn try_from(pb: proto::GetBaseBackupResponseChunk) -> Result<Self, Self::Error> {
-        if pb.chunk.is_empty() {
-            return Err(ProtocolError::Missing("chunk"));
-        }
-        Ok(pb.chunk)
-    }
-}
-
-impl From<GetBaseBackupResponseChunk> for proto::GetBaseBackupResponseChunk {
-    fn from(chunk: GetBaseBackupResponseChunk) -> Self {
-        Self { chunk }
-    }
-}
-
-/// Requests the size of a database, as # of bytes. Only valid on shard 0, other shards will error.
-#[derive(Clone, Copy, Debug)]
-pub struct GetDbSizeRequest {
-    pub read_lsn: ReadLsn,
-    pub db_oid: Oid,
-}
-
-impl TryFrom<proto::GetDbSizeRequest> for GetDbSizeRequest {
-    type Error = ProtocolError;
-
-    fn try_from(pb: proto::GetDbSizeRequest) -> Result<Self, Self::Error> {
-        Ok(Self {
-            read_lsn: pb
-                .read_lsn
-                .ok_or(ProtocolError::Missing("read_lsn"))?
-                .try_into()?,
-            db_oid: pb.db_oid,
-        })
-    }
-}
-
-impl From<GetDbSizeRequest> for proto::GetDbSizeRequest {
-    fn from(request: GetDbSizeRequest) -> Self {
-        Self {
-            read_lsn: Some(request.read_lsn.into()),
-            db_oid: request.db_oid,
-        }
-    }
-}
-
-pub type GetDbSizeResponse = u64;
-
-impl From<proto::GetDbSizeResponse> for GetDbSizeResponse {
-    fn from(pb: proto::GetDbSizeResponse) -> Self {
-        pb.num_bytes
-    }
-}
-
-impl From<GetDbSizeResponse> for proto::GetDbSizeResponse {
-    fn from(num_bytes: GetDbSizeResponse) -> Self {
-        Self { num_bytes }
-    }
-}
-
-/// Requests one or more pages.
-#[derive(Clone, Debug)]
-pub struct GetPageRequest {
-    /// A request ID. Will be included in the response. Should be unique for in-flight requests on
-    /// the stream.
-    pub request_id: RequestID,
-    /// The request class.
-    pub request_class: GetPageClass,
-    /// The LSN to read at.
-    pub read_lsn: ReadLsn,
-    /// The relation to read from.
-    pub rel: RelTag,
-    /// Page numbers to read. Must belong to the remote shard.
-    ///
-    /// Multiple pages will be executed as a single batch by the Pageserver, amortizing layer access
-    /// costs and parallelizing them. This may increase the latency of any individual request, but
-    /// improves the overall latency and throughput of the batch as a whole.
-    pub block_numbers: Vec<u32>,
-}
-
-impl TryFrom<proto::GetPageRequest> for GetPageRequest {
-    type Error = ProtocolError;
-
-    fn try_from(pb: proto::GetPageRequest) -> Result<Self, Self::Error> {
-        if pb.block_number.is_empty() {
-            return Err(ProtocolError::Missing("block_number"));
-        }
-        Ok(Self {
-            request_id: pb.request_id,
-            request_class: pb.request_class.into(),
-            read_lsn: pb
-                .read_lsn
-                .ok_or(ProtocolError::Missing("read_lsn"))?
-                .try_into()?,
-            rel: pb.rel.ok_or(ProtocolError::Missing("rel"))?.try_into()?,
-            block_numbers: pb.block_number,
-        })
-    }
-}
-
-impl From<GetPageRequest> for proto::GetPageRequest {
-    fn from(request: GetPageRequest) -> Self {
-        Self {
-            request_id: request.request_id,
-            request_class: request.request_class.into(),
-            read_lsn: Some(request.read_lsn.into()),
-            rel: Some(request.rel.into()),
-            block_number: request.block_numbers,
-        }
-    }
-}
-
-/// A GetPage request ID.
-pub type RequestID = u64;
-
-/// A GetPage request class.
-#[derive(Clone, Copy, Debug)]
-pub enum GetPageClass {
-    /// Unknown class. For backwards compatibility: used when an older client version sends a class
-    /// that a newer server version has removed.
-    Unknown,
-    /// A normal request. This is the default.
-    Normal,
-    /// A prefetch request. NB: can only be classified on pg < 18.
-    Prefetch,
-    /// A background request (e.g. vacuum).
-    Background,
-}
-
-impl From<proto::GetPageClass> for GetPageClass {
-    fn from(pb: proto::GetPageClass) -> Self {
-        match pb {
-            proto::GetPageClass::Unknown => Self::Unknown,
-            proto::GetPageClass::Normal => Self::Normal,
-            proto::GetPageClass::Prefetch => Self::Prefetch,
-            proto::GetPageClass::Background => Self::Background,
-        }
-    }
-}
-
-impl From<i32> for GetPageClass {
-    fn from(class: i32) -> Self {
-        proto::GetPageClass::try_from(class)
-            .unwrap_or(proto::GetPageClass::Unknown)
-            .into()
-    }
-}
-
-impl From<GetPageClass> for proto::GetPageClass {
-    fn from(class: GetPageClass) -> Self {
-        match class {
-            GetPageClass::Unknown => Self::Unknown,
-            GetPageClass::Normal => Self::Normal,
-            GetPageClass::Prefetch => Self::Prefetch,
-            GetPageClass::Background => Self::Background,
-        }
-    }
-}
-
-impl From<GetPageClass> for i32 {
-    fn from(class: GetPageClass) -> Self {
-        proto::GetPageClass::from(class).into()
-    }
-}
-
-/// A GetPage response.
-///
-/// A batch response will contain all of the requested pages. We could eagerly emit individual pages
-/// as soon as they are ready, but on a readv() Postgres holds buffer pool locks on all pages in the
-/// batch and we'll only return once the entire batch is ready, so no one can make use of the
-/// individual pages.
-#[derive(Clone, Debug)]
-pub struct GetPageResponse {
-    /// The original request's ID.
-    pub request_id: RequestID,
-    /// The response status code.
-    pub status_code: GetPageStatusCode,
-    /// A string describing the status, if any.
-    pub reason: Option<String>,
-    /// The 8KB page images, in the same order as the request. Empty if status != OK.
-    pub page_images: Vec<Bytes>,
-}
-
-impl From<proto::GetPageResponse> for GetPageResponse {
-    fn from(pb: proto::GetPageResponse) -> Self {
-        Self {
-            request_id: pb.request_id,
-            status_code: pb.status_code.into(),
-            reason: Some(pb.reason).filter(|r| !r.is_empty()),
-            page_images: pb.page_image,
-        }
-    }
-}
-
-impl From<GetPageResponse> for proto::GetPageResponse {
-    fn from(response: GetPageResponse) -> Self {
-        Self {
-            request_id: response.request_id,
-            status_code: response.status_code.into(),
-            reason: response.reason.unwrap_or_default(),
-            page_image: response.page_images,
-        }
-    }
-}
-
-/// A GetPage response status code.
-///
-/// These are effectively equivalent to gRPC statuses. However, we use a bidirectional stream
-/// (potentially shared by many backends), and a gRPC status response would terminate the stream so
-/// we send GetPageResponse messages with these codes instead.
-#[derive(Clone, Copy, Debug)]
-pub enum GetPageStatusCode {
-    /// Unknown status. For forwards compatibility: used when an older client version receives a new
-    /// status code from a newer server version.
-    Unknown,
-    /// The request was successful.
-    Ok,
-    /// The page did not exist. The tenant/timeline/shard has already been validated during stream
-    /// setup.
-    NotFound,
-    /// The request was invalid.
-    InvalidRequest,
-    /// The request failed due to an internal server error.
-    InternalError,
-    /// The tenant is rate limited. Slow down and retry later.
-    SlowDown,
-}
-
-impl From<proto::GetPageStatusCode> for GetPageStatusCode {
-    fn from(pb: proto::GetPageStatusCode) -> Self {
-        match pb {
-            proto::GetPageStatusCode::Unknown => Self::Unknown,
-            proto::GetPageStatusCode::Ok => Self::Ok,
-            proto::GetPageStatusCode::NotFound => Self::NotFound,
-            proto::GetPageStatusCode::InvalidRequest => Self::InvalidRequest,
-            proto::GetPageStatusCode::InternalError => Self::InternalError,
-            proto::GetPageStatusCode::SlowDown => Self::SlowDown,
-        }
-    }
-}
-
-impl From<i32> for GetPageStatusCode {
-    fn from(status_code: i32) -> Self {
-        proto::GetPageStatusCode::try_from(status_code)
-            .unwrap_or(proto::GetPageStatusCode::Unknown)
-            .into()
-    }
-}
-
-impl From<GetPageStatusCode> for proto::GetPageStatusCode {
-    fn from(status_code: GetPageStatusCode) -> Self {
-        match status_code {
-            GetPageStatusCode::Unknown => Self::Unknown,
-            GetPageStatusCode::Ok => Self::Ok,
-            GetPageStatusCode::NotFound => Self::NotFound,
-            GetPageStatusCode::InvalidRequest => Self::InvalidRequest,
-            GetPageStatusCode::InternalError => Self::InternalError,
-            GetPageStatusCode::SlowDown => Self::SlowDown,
-        }
-    }
-}
-
-impl From<GetPageStatusCode> for i32 {
-    fn from(status_code: GetPageStatusCode) -> Self {
-        proto::GetPageStatusCode::from(status_code).into()
-    }
-}
-
-// Fetches the size of a relation at a given LSN, as # of blocks. Only valid on shard 0, other
-// shards will error.
-pub struct GetRelSizeRequest {
-    pub read_lsn: ReadLsn,
-    pub rel: RelTag,
-}
-
-impl TryFrom<proto::GetRelSizeRequest> for GetRelSizeRequest {
-    type Error = ProtocolError;
-
-    fn try_from(proto: proto::GetRelSizeRequest) -> Result<Self, Self::Error> {
-        Ok(Self {
-            read_lsn: proto
-                .read_lsn
-                .ok_or(ProtocolError::Missing("read_lsn"))?
-                .try_into()?,
-            rel: proto.rel.ok_or(ProtocolError::Missing("rel"))?.try_into()?,
-        })
-    }
-}
-
-impl From<GetRelSizeRequest> for proto::GetRelSizeRequest {
-    fn from(request: GetRelSizeRequest) -> Self {
-        Self {
-            read_lsn: Some(request.read_lsn.into()),
-            rel: Some(request.rel.into()),
-        }
-    }
-}
-
-pub type GetRelSizeResponse = u32;
-
-impl From<proto::GetRelSizeResponse> for GetRelSizeResponse {
-    fn from(proto: proto::GetRelSizeResponse) -> Self {
-        proto.num_blocks
-    }
-}
-
-impl From<GetRelSizeResponse> for proto::GetRelSizeResponse {
-    fn from(num_blocks: GetRelSizeResponse) -> Self {
-        Self { num_blocks }
-    }
-}
-
-/// Requests an SLRU segment. Only valid on shard 0, other shards will error.
-pub struct GetSlruSegmentRequest {
-    pub read_lsn: ReadLsn,
-    pub kind: SlruKind,
-    pub segno: u32,
-}
-
-impl TryFrom<proto::GetSlruSegmentRequest> for GetSlruSegmentRequest {
-    type Error = ProtocolError;
-
-    fn try_from(pb: proto::GetSlruSegmentRequest) -> Result<Self, Self::Error> {
-        Ok(Self {
-            read_lsn: pb
-                .read_lsn
-                .ok_or(ProtocolError::Missing("read_lsn"))?
-                .try_into()?,
-            kind: u8::try_from(pb.kind)
-                .ok()
-                .and_then(SlruKind::from_repr)
-                .ok_or_else(|| ProtocolError::invalid("slru_kind", pb.kind))?,
-            segno: pb.segno,
-        })
-    }
-}
-
-impl From<GetSlruSegmentRequest> for proto::GetSlruSegmentRequest {
-    fn from(request: GetSlruSegmentRequest) -> Self {
-        Self {
-            read_lsn: Some(request.read_lsn.into()),
-            kind: request.kind as u32,
-            segno: request.segno,
-        }
-    }
-}
-
-pub type GetSlruSegmentResponse = Bytes;
-
-impl TryFrom<proto::GetSlruSegmentResponse> for GetSlruSegmentResponse {
-    type Error = ProtocolError;
-
-    fn try_from(pb: proto::GetSlruSegmentResponse) -> Result<Self, Self::Error> {
-        if pb.segment.is_empty() {
-            return Err(ProtocolError::Missing("segment"));
-        }
-        Ok(pb.segment)
-    }
-}
-
-impl From<GetSlruSegmentResponse> for proto::GetSlruSegmentResponse {
-    fn from(segment: GetSlruSegmentResponse) -> Self {
-        Self { segment }
-    }
-}
-
-// SlruKind is defined in pageserver_api::reltag.
-pub type SlruKind = pageserver_api::reltag::SlruKind;

pageserver/pagebench/Cargo.toml

@@ -8,8 +8,6 @@ license.workspace = true
 
 [dependencies]
 anyhow.workspace = true
-async-trait.workspace = true
-bytes.workspace = true
 camino.workspace = true
 clap.workspace = true
 futures.workspace = true
@@ -17,17 +15,14 @@ hdrhistogram.workspace = true
 humantime.workspace = true
 humantime-serde.workspace = true
 rand.workspace = true
-reqwest.workspace = true
+reqwest.workspace=true
 serde.workspace = true
 serde_json.workspace = true
 tracing.workspace = true
 tokio.workspace = true
-tokio-stream.workspace = true
 tokio-util.workspace = true
-tonic.workspace = true
 
 pageserver_client.workspace = true
 pageserver_api.workspace = true
-pageserver_page_api.workspace = true
 utils = { path = "../../libs/utils/" }
 workspace_hack = { version = "0.1", path = "../../workspace_hack" }

pageserver/pagebench/src/cmd/getpage_latest_lsn.rs

@@ -1,4 +1,4 @@
-use std::collections::{HashMap, HashSet, VecDeque};
+use std::collections::{HashSet, VecDeque};
 use std::future::Future;
 use std::num::NonZeroUsize;
 use std::pin::Pin;
@@ -7,15 +7,11 @@ use std::sync::{Arc, Mutex};
 use std::time::{Duration, Instant};
 
 use anyhow::Context;
-use async_trait::async_trait;
-use bytes::Bytes;
 use camino::Utf8PathBuf;
 use pageserver_api::key::Key;
 use pageserver_api::keyspace::KeySpaceAccum;
 use pageserver_api::models::{PagestreamGetPageRequest, PagestreamRequest};
-use pageserver_api::reltag::RelTag;
 use pageserver_api::shard::TenantShardId;
-use pageserver_page_api::proto;
 use rand::prelude::*;
 use tokio::task::JoinSet;
 use tokio_util::sync::CancellationToken;
@@ -26,12 +22,6 @@ use utils::lsn::Lsn;
 use crate::util::tokio_thread_local_stats::AllThreadLocalStats;
 use crate::util::{request_stats, tokio_thread_local_stats};
 
-#[derive(clap::ValueEnum, Clone, Debug)]
-enum Protocol {
-    Libpq,
-    Grpc,
-}
-
 /// GetPage@LatestLSN, uniformly distributed across the compute-accessible keyspace.
 #[derive(clap::Parser)]
 pub(crate) struct Args {
@@ -45,8 +35,6 @@ pub(crate) struct Args {
     num_clients: NonZeroUsize,
     #[clap(long)]
     runtime: Option<humantime::Duration>,
-    #[clap(long, value_enum, default_value = "libpq")]
-    protocol: Protocol,
     /// Each client sends requests at the given rate.
     ///
     /// If a request takes too long and we should be issuing a new request already,
@@ -77,16 +65,6 @@ pub(crate) struct Args {
     #[clap(long, default_value = "1")]
     queue_depth: NonZeroUsize,
 
-    /// Batch size of contiguous pages generated by each client. This is equivalent to how Postgres
-    /// will request page batches (e.g. prefetches or vectored reads). A batch counts as 1 RPS and
-    /// 1 queue depth.
-    ///
-    /// The libpq protocol does not support client-side batching, and will submit batches as many
-    /// individual requests, in the hope that the server will batch them. Each batch still counts as
-    /// 1 RPS and 1 queue depth.
-    #[clap(long, default_value = "1")]
-    batch_size: NonZeroUsize,
-
     #[clap(long)]
     only_relnode: Option<u32>,
 
@@ -325,20 +303,7 @@ async fn main_impl(
                 .unwrap();
 
         Box::pin(async move {
-            let client: Box<dyn Client> = match args.protocol {
-                Protocol::Libpq => Box::new(
-                    LibpqClient::new(args.page_service_connstring.clone(), worker_id.timeline)
-                        .await
-                        .unwrap(),
-                ),
-
-                Protocol::Grpc => Box::new(
-                    GrpcClient::new(args.page_service_connstring.clone(), worker_id.timeline)
-                        .await
-                        .unwrap(),
-                ),
-            };
-            run_worker(args, client, ss, cancel, rps_period, ranges, weights).await
+            client_libpq(args, worker_id, ss, cancel, rps_period, ranges, weights).await
         })
     };
 
@@ -390,28 +355,27 @@ async fn main_impl(
     anyhow::Ok(())
 }
 
-async fn run_worker(
+async fn client_libpq(
     args: &Args,
-    mut client: Box<dyn Client>,
+    worker_id: WorkerId,
     shared_state: Arc<SharedState>,
     cancel: CancellationToken,
     rps_period: Option<Duration>,
     ranges: Vec<KeyRange>,
     weights: rand::distributions::weighted::WeightedIndex<i128>,
 ) {
+    let client = pageserver_client::page_service::Client::new(args.page_service_connstring.clone())
+        .await
+        .unwrap();
+    let mut client = client
+        .pagestream(worker_id.timeline.tenant_id, worker_id.timeline.timeline_id)
+        .await
+        .unwrap();
+
     shared_state.start_work_barrier.wait().await;
     let client_start = Instant::now();
     let mut ticks_processed = 0;
-    let mut req_id = 0;
-    let batch_size: usize = args.batch_size.into();
-
-    // Track inflight requests by request ID and start time. This times the request duration, and
-    // ensures responses match requests. We don't expect responses back in any particular order.
-    //
-    // NB: this does not check that all requests received a response, because we don't wait for the
-    // inflight requests to complete when the duration elapses.
-    let mut inflight: HashMap<u64, Instant> = HashMap::new();
-
+    let mut inflight = VecDeque::new();
     while !cancel.is_cancelled() {
         // Detect if a request took longer than the RPS rate
         if let Some(period) = &rps_period {
@@ -427,72 +391,36 @@ async fn run_worker(
         }
 
         while inflight.len() < args.queue_depth.get() {
-            req_id += 1;
             let start = Instant::now();
-            let (req_lsn, mod_lsn, rel, blks) = {
-                /// Converts a compact i128 key to a relation tag and block number.
-                fn key_to_block(key: i128) -> (RelTag, u32) {
-                    let key = Key::from_i128(key);
-                    assert!(key.is_rel_block_key());
-                    key.to_rel_block()
-                        .expect("we filter non-rel-block keys out above")
-                }
-
-                // Pick a random page from a random relation.
+            let req = {
                 let mut rng = rand::thread_rng();
                 let r = &ranges[weights.sample(&mut rng)];
                 let key: i128 = rng.gen_range(r.start..r.end);
-                let (rel_tag, block_no) = key_to_block(key);
-
-                let mut blks = VecDeque::with_capacity(batch_size);
-                blks.push_back(block_no);
-
-                // If requested, populate a batch of sequential pages. This is how Postgres will
-                // request page batches (e.g. prefetches). If we hit the end of the relation, we
-                // grow the batch towards the start too.
-                for i in 1..batch_size {
-                    let (r, b) = key_to_block(key + i as i128);
-                    if r != rel_tag {
-                        break; // went outside relation
-                    }
-                    blks.push_back(b)
+                let key = Key::from_i128(key);
+                assert!(key.is_rel_block_key());
+                let (rel_tag, block_no) = key
+                    .to_rel_block()
+                    .expect("we filter non-rel-block keys out above");
+                PagestreamGetPageRequest {
+                    hdr: PagestreamRequest {
+                        reqid: 0,
+                        request_lsn: if rng.gen_bool(args.req_latest_probability) {
+                            Lsn::MAX
+                        } else {
+                            r.timeline_lsn
+                        },
+                        not_modified_since: r.timeline_lsn,
+                    },
+                    rel: rel_tag,
+                    blkno: block_no,
                 }
-
-                if blks.len() < batch_size {
-                    // Grow batch backwards if needed.
-                    for i in 1..batch_size {
-                        let (r, b) = key_to_block(key - i as i128);
-                        if r != rel_tag {
-                            break; // went outside relation
-                        }
-                        blks.push_front(b)
-                    }
-                }
-
-                // We assume that the entire batch can fit within the relation.
-                assert_eq!(blks.len(), batch_size, "incomplete batch");
-
-                let req_lsn = if rng.gen_bool(args.req_latest_probability) {
-                    Lsn::MAX
-                } else {
-                    r.timeline_lsn
-                };
-                (req_lsn, r.timeline_lsn, rel_tag, blks.into())
             };
-            client
-                .send_get_page(req_id, req_lsn, mod_lsn, rel, blks)
-                .await
-                .unwrap();
-            let old = inflight.insert(req_id, start);
-            assert!(old.is_none(), "duplicate request ID {req_id}");
+            client.getpage_send(req).await.unwrap();
+            inflight.push_back(start);
         }
 
-        let (req_id, pages) = client.recv_get_page().await.unwrap();
-        assert_eq!(pages.len(), batch_size, "unexpected page count");
-        assert!(pages.iter().all(|p| !p.is_empty()), "empty page");
-        let start = inflight
-            .remove(&req_id)
-            .expect("response for unknown request ID");
+        let start = inflight.pop_front().unwrap();
+        client.getpage_recv().await.unwrap();
         let end = Instant::now();
         shared_state.live_stats.request_done();
         ticks_processed += 1;
@@ -514,154 +442,3 @@ async fn run_worker(
         }
     }
 }
-
-/// A benchmark client, to allow switching out the transport protocol.
-///
-/// For simplicity, this just uses separate asynchronous send/recv methods. The send method could
-/// return a future that resolves when the response is received, but we don't really need it.
-#[async_trait]
-trait Client: Send {
-    /// Sends an asynchronous GetPage request to the pageserver.
-    async fn send_get_page(
-        &mut self,
-        req_id: u64,
-        req_lsn: Lsn,
-        mod_lsn: Lsn,
-        rel: RelTag,
-        blks: Vec<u32>,
-    ) -> anyhow::Result<()>;
-
-    /// Receives the next GetPage response from the pageserver.
-    async fn recv_get_page(&mut self) -> anyhow::Result<(u64, Vec<Bytes>)>;
-}
-
-/// A libpq-based Pageserver client.
-struct LibpqClient {
-    inner: pageserver_client::page_service::PagestreamClient,
-    // Track sent batches, so we know how many responses to expect.
-    batch_sizes: VecDeque<usize>,
-}
-
-impl LibpqClient {
-    async fn new(connstring: String, ttid: TenantTimelineId) -> anyhow::Result<Self> {
-        let inner = pageserver_client::page_service::Client::new(connstring)
-            .await?
-            .pagestream(ttid.tenant_id, ttid.timeline_id)
-            .await?;
-        Ok(Self {
-            inner,
-            batch_sizes: VecDeque::new(),
-        })
-    }
-}
-
-#[async_trait]
-impl Client for LibpqClient {
-    async fn send_get_page(
-        &mut self,
-        req_id: u64,
-        req_lsn: Lsn,
-        mod_lsn: Lsn,
-        rel: RelTag,
-        blks: Vec<u32>,
-    ) -> anyhow::Result<()> {
-        // libpq doesn't support client-side batches, so we send a bunch of individual requests
-        // instead in the hope that the server will batch them for us. We use the same request ID
-        // for all, because we'll return a single batch response.
-        self.batch_sizes.push_back(blks.len());
-        for blkno in blks {
-            let req = PagestreamGetPageRequest {
-                hdr: PagestreamRequest {
-                    reqid: req_id,
-                    request_lsn: req_lsn,
-                    not_modified_since: mod_lsn,
-                },
-                rel,
-                blkno,
-            };
-            self.inner.getpage_send(req).await?;
-        }
-        Ok(())
-    }
-
-    async fn recv_get_page(&mut self) -> anyhow::Result<(u64, Vec<Bytes>)> {
-        let batch_size = self.batch_sizes.pop_front().unwrap();
-        let mut batch = Vec::with_capacity(batch_size);
-        let mut req_id = None;
-        for _ in 0..batch_size {
-            let resp = self.inner.getpage_recv().await?;
-            if req_id.is_none() {
-                req_id = Some(resp.req.hdr.reqid);
-            }
-            assert_eq!(req_id, Some(resp.req.hdr.reqid), "request ID mismatch");
-            batch.push(resp.page);
-        }
-        Ok((req_id.unwrap(), batch))
-    }
-}
-
-/// A gRPC client using the raw, no-frills gRPC client.
-struct GrpcClient {
-    req_tx: tokio::sync::mpsc::Sender<proto::GetPageRequest>,
-    resp_rx: tonic::Streaming<proto::GetPageResponse>,
-}
-
-impl GrpcClient {
-    async fn new(connstring: String, ttid: TenantTimelineId) -> anyhow::Result<Self> {
-        let mut client = pageserver_page_api::proto::PageServiceClient::connect(connstring).await?;
-
-        // The channel has a buffer size of 1, since 0 is not allowed. It does not matter, since the
-        // benchmark will control the queue depth (i.e. in-flight requests) anyway, and requests are
-        // buffered by Tonic and the OS too.
-        let (req_tx, req_rx) = tokio::sync::mpsc::channel(1);
-        let req_stream = tokio_stream::wrappers::ReceiverStream::new(req_rx);
-        let mut req = tonic::Request::new(req_stream);
-        let metadata = req.metadata_mut();
-        metadata.insert("neon-tenant-id", ttid.tenant_id.to_string().try_into()?);
-        metadata.insert("neon-timeline-id", ttid.timeline_id.to_string().try_into()?);
-        metadata.insert("neon-shard-id", "0000".try_into()?);
-
-        let resp = client.get_pages(req).await?;
-        let resp_stream = resp.into_inner();
-
-        Ok(Self {
-            req_tx,
-            resp_rx: resp_stream,
-        })
-    }
-}
-
-#[async_trait]
-impl Client for GrpcClient {
-    async fn send_get_page(
-        &mut self,
-        req_id: u64,
-        req_lsn: Lsn,
-        mod_lsn: Lsn,
-        rel: RelTag,
-        blks: Vec<u32>,
-    ) -> anyhow::Result<()> {
-        let req = proto::GetPageRequest {
-            request_id: req_id,
-            request_class: proto::GetPageClass::Normal as i32,
-            read_lsn: Some(proto::ReadLsn {
-                request_lsn: req_lsn.0,
-                not_modified_since_lsn: mod_lsn.0,
-            }),
-            rel: Some(rel.into()),
-            block_number: blks,
-        };
-        self.req_tx.send(req).await?;
-        Ok(())
-    }
-
-    async fn recv_get_page(&mut self) -> anyhow::Result<(u64, Vec<Bytes>)> {
-        let resp = self.resp_rx.message().await?.unwrap();
-        anyhow::ensure!(
-            resp.status_code == proto::GetPageStatusCode::Ok as i32,
-            "unexpected status code: {}",
-            resp.status_code
-        );
-        Ok((resp.request_id, resp.page_image))
-    }
-}

pageserver/src/basebackup.rs

@@ -65,30 +65,6 @@ impl From<GetVectoredError> for BasebackupError {
     }
 }
 
-impl From<BasebackupError> for postgres_backend::QueryError {
-    fn from(err: BasebackupError) -> Self {
-        use postgres_backend::QueryError;
-        use pq_proto::framed::ConnectionError;
-        match err {
-            BasebackupError::Client(err, _) => QueryError::Disconnected(ConnectionError::Io(err)),
-            BasebackupError::Server(err) => QueryError::Other(err),
-            BasebackupError::Shutdown => QueryError::Shutdown,
-        }
-    }
-}
-
-impl From<BasebackupError> for tonic::Status {
-    fn from(err: BasebackupError) -> Self {
-        use tonic::Code;
-        let code = match &err {
-            BasebackupError::Client(_, _) => Code::Cancelled,
-            BasebackupError::Server(_) => Code::Internal,
-            BasebackupError::Shutdown => Code::Unavailable,
-        };
-        tonic::Status::new(code, err.to_string())
-    }
-}
-
 /// Create basebackup with non-rel data in it.
 /// Only include relational data if 'full_backup' is true.
 ///
@@ -272,7 +248,7 @@ where
     async fn flush(&mut self) -> Result<(), BasebackupError> {
         let nblocks = self.buf.len() / BLCKSZ as usize;
         let (kind, segno) = self.current_segment.take().unwrap();
-        let segname = format!("{kind}/{segno:>04X}");
+        let segname = format!("{}/{:>04X}", kind.to_str(), segno);
         let header = new_tar_header(&segname, self.buf.len() as u64)?;
         self.ar
             .append(&header, self.buf.as_slice())
@@ -371,7 +347,7 @@ where
                 .await?
                 .partition(
                     self.timeline.get_shard_identity(),
-                    self.timeline.conf.max_get_vectored_keys.get() as u64 * BLCKSZ as u64,
+                    Timeline::MAX_GET_VECTORED_KEYS * BLCKSZ as u64,
                 );
 
             let mut slru_builder = SlruSegmentsBuilder::new(&mut self.ar);

pageserver/src/bin/pageserver.rs

@@ -21,7 +21,6 @@ use pageserver::config::{PageServerConf, PageserverIdentity, ignored_fields};
 use pageserver::controller_upcall_client::StorageControllerUpcallClient;
 use pageserver::deletion_queue::DeletionQueue;
 use pageserver::disk_usage_eviction_task::{self, launch_disk_usage_global_eviction_task};
-use pageserver::feature_resolver::FeatureResolver;
 use pageserver::metrics::{STARTUP_DURATION, STARTUP_IS_LOADING};
 use pageserver::task_mgr::{
     BACKGROUND_RUNTIME, COMPUTE_REQUEST_RUNTIME, MGMT_REQUEST_RUNTIME, WALRECEIVER_RUNTIME,
@@ -158,6 +157,7 @@ fn main() -> anyhow::Result<()> {
     // (maybe we should automate this with a visitor?).
     info!(?conf.virtual_file_io_engine, "starting with virtual_file IO engine");
     info!(?conf.virtual_file_io_mode, "starting with virtual_file IO mode");
+    info!(?conf.wal_receiver_protocol, "starting with WAL receiver protocol");
     info!(?conf.validate_wal_contiguity, "starting with WAL contiguity validation");
     info!(?conf.page_service_pipelining, "starting with page service pipelining config");
     info!(?conf.get_vectored_concurrent_io, "starting with get_vectored IO concurrency config");
@@ -388,30 +388,23 @@ fn start_pageserver(
     // We need to release the lock file only when the process exits.
     std::mem::forget(lock_file);
 
-    // Bind the HTTP, libpq, and gRPC ports early, to error out if they are
-    // already in use.
-    info!(
-        "Starting pageserver http handler on {} with auth {:#?}",
-        conf.listen_http_addr, conf.http_auth_type
-    );
-    let http_listener = tcp_listener::bind(&conf.listen_http_addr)?;
+    // Bind the HTTP and libpq ports early, so that if they are in use by some other
+    // process, we error out early.
+    let http_addr = &conf.listen_http_addr;
+    info!("Starting pageserver http handler on {http_addr}");
+    let http_listener = tcp_listener::bind(http_addr)?;
 
     let https_listener = match conf.listen_https_addr.as_ref() {
         Some(https_addr) => {
-            info!(
-                "Starting pageserver https handler on {https_addr} with auth {:#?}",
-                conf.http_auth_type
-            );
+            info!("Starting pageserver https handler on {https_addr}");
             Some(tcp_listener::bind(https_addr)?)
         }
         None => None,
     };
 
-    info!(
-        "Starting pageserver pg protocol handler on {} with auth {:#?}",
-        conf.listen_pg_addr, conf.pg_auth_type,
-    );
-    let pageserver_listener = tcp_listener::bind(&conf.listen_pg_addr)?;
+    let pg_addr = &conf.listen_pg_addr;
+    info!("Starting pageserver pg protocol handler on {pg_addr}");
+    let pageserver_listener = tcp_listener::bind(pg_addr)?;
 
     // Enable SO_KEEPALIVE on the socket, to detect dead connections faster.
     // These are configured via net.ipv4.tcp_keepalive_* sysctls.
@@ -420,15 +413,6 @@ fn start_pageserver(
     // support enabling keepalives while using the default OS sysctls.
     setsockopt(&pageserver_listener, sockopt::KeepAlive, &true)?;
 
-    let mut grpc_listener = None;
-    if let Some(grpc_addr) = &conf.listen_grpc_addr {
-        info!(
-            "Starting pageserver gRPC handler on {grpc_addr} with auth {:#?}",
-            conf.grpc_auth_type
-        );
-        grpc_listener = Some(tcp_listener::bind(grpc_addr).map_err(|e| anyhow!("{e}"))?);
-    }
-
     // Launch broker client
     // The storage_broker::connect call needs to happen inside a tokio runtime thread.
     let broker_client = WALRECEIVER_RUNTIME
@@ -456,8 +440,7 @@ fn start_pageserver(
     // Initialize authentication for incoming connections
     let http_auth;
     let pg_auth;
-    let grpc_auth;
-    if [conf.http_auth_type, conf.pg_auth_type, conf.grpc_auth_type].contains(&AuthType::NeonJWT) {
+    if conf.http_auth_type == AuthType::NeonJWT || conf.pg_auth_type == AuthType::NeonJWT {
         // unwrap is ok because check is performed when creating config, so path is set and exists
         let key_path = conf.auth_validation_public_key_path.as_ref().unwrap();
         info!("Loading public key(s) for verifying JWT tokens from {key_path:?}");
@@ -465,23 +448,20 @@ fn start_pageserver(
         let jwt_auth = JwtAuth::from_key_path(key_path)?;
         let auth: Arc<SwappableJwtAuth> = Arc::new(SwappableJwtAuth::new(jwt_auth));
 
-        http_auth = match conf.http_auth_type {
+        http_auth = match &conf.http_auth_type {
             AuthType::Trust => None,
             AuthType::NeonJWT => Some(auth.clone()),
         };
-        pg_auth = match conf.pg_auth_type {
-            AuthType::Trust => None,
-            AuthType::NeonJWT => Some(auth.clone()),
-        };
-        grpc_auth = match conf.grpc_auth_type {
+        pg_auth = match &conf.pg_auth_type {
             AuthType::Trust => None,
             AuthType::NeonJWT => Some(auth),
         };
     } else {
         http_auth = None;
         pg_auth = None;
-        grpc_auth = None;
     }
+    info!("Using auth for http API: {:#?}", conf.http_auth_type);
+    info!("Using auth for pg connections: {:#?}", conf.pg_auth_type);
 
     let tls_server_config = if conf.listen_https_addr.is_some() || conf.enable_tls_page_service_api
     {
@@ -522,12 +502,6 @@ fn start_pageserver(
     // Set up remote storage client
     let remote_storage = BACKGROUND_RUNTIME.block_on(create_remote_storage_client(conf))?;
 
-    let feature_resolver = create_feature_resolver(
-        conf,
-        shutdown_pageserver.clone(),
-        BACKGROUND_RUNTIME.handle(),
-    )?;
-
     // Set up deletion queue
     let (deletion_queue, deletion_workers) = DeletionQueue::new(
         remote_storage.clone(),
@@ -581,7 +555,6 @@ fn start_pageserver(
             deletion_queue_client,
             l0_flush_global_state,
             basebackup_prepare_sender,
-            feature_resolver,
         },
         order,
         shutdown_pageserver.clone(),
@@ -806,23 +779,6 @@ fn start_pageserver(
         basebackup_cache,
     );
 
-    // Spawn a Pageserver gRPC server task. It will spawn separate tasks for
-    // each stream/request.
-    //
-    // TODO: this uses a separate Tokio runtime for the page service. If we want
-    // other gRPC services, they will need their own port and runtime. Is this
-    // necessary?
-    let mut page_service_grpc = None;
-    if let Some(grpc_listener) = grpc_listener {
-        page_service_grpc = Some(page_service::spawn_grpc(
-            tenant_manager.clone(),
-            grpc_auth,
-            otel_guard.as_ref().map(|g| g.dispatch.clone()),
-            conf.get_vectored_concurrent_io,
-            grpc_listener,
-        )?);
-    }
-
     // All started up! Now just sit and wait for shutdown signal.
     BACKGROUND_RUNTIME.block_on(async move {
         let signal_token = CancellationToken::new();
@@ -841,7 +797,6 @@ fn start_pageserver(
             http_endpoint_listener,
             https_endpoint_listener,
             page_service,
-            page_service_grpc,
             consumption_metrics_tasks,
             disk_usage_eviction_task,
             &tenant_manager,
@@ -855,14 +810,6 @@ fn start_pageserver(
     })
 }
 
-fn create_feature_resolver(
-    conf: &'static PageServerConf,
-    shutdown_pageserver: CancellationToken,
-    handle: &tokio::runtime::Handle,
-) -> anyhow::Result<FeatureResolver> {
-    FeatureResolver::spawn(conf, shutdown_pageserver, handle)
-}
-
 async fn create_remote_storage_client(
     conf: &'static PageServerConf,
 ) -> anyhow::Result<GenericRemoteStorage> {

pageserver/src/config.rs

@@ -14,10 +14,7 @@ use std::time::Duration;
 use anyhow::{Context, bail, ensure};
 use camino::{Utf8Path, Utf8PathBuf};
 use once_cell::sync::OnceCell;
-use pageserver_api::config::{
-    DiskUsageEvictionTaskConfig, MaxGetVectoredKeys, MaxVectoredReadBytes,
-    PageServicePipeliningConfig, PageServicePipeliningConfigPipelined, PostHogConfig,
-};
+use pageserver_api::config::{DiskUsageEvictionTaskConfig, MaxVectoredReadBytes};
 use pageserver_api::models::ImageCompressionAlgorithm;
 use pageserver_api::shard::TenantShardId;
 use pem::Pem;
@@ -27,6 +24,7 @@ use reqwest::Url;
 use storage_broker::Uri;
 use utils::id::{NodeId, TimelineId};
 use utils::logging::{LogFormat, SecretString};
+use utils::postgres_client::PostgresClientProtocol;
 
 use crate::tenant::storage_layer::inmemory_layer::IndexEntry;
 use crate::tenant::{TENANTS_SEGMENT_NAME, TIMELINES_SEGMENT_NAME};
@@ -60,16 +58,11 @@ pub struct PageServerConf {
     pub listen_http_addr: String,
     /// Example: 127.0.0.1:9899
     pub listen_https_addr: Option<String>,
-    /// If set, expose a gRPC API on this address.
-    /// Example: 127.0.0.1:51051
-    ///
-    /// EXPERIMENTAL: this protocol is unstable and under active development.
-    pub listen_grpc_addr: Option<String>,
 
-    /// Path to a file with certificate's private key for https and gRPC API.
+    /// Path to a file with certificate's private key for https API.
     /// Default: server.key
     pub ssl_key_file: Utf8PathBuf,
-    /// Path to a file with a X509 certificate for https and gRPC API.
+    /// Path to a file with a X509 certificate for https API.
     /// Default: server.crt
     pub ssl_cert_file: Utf8PathBuf,
     /// Period to reload certificate and private key from files.
@@ -107,8 +100,6 @@ pub struct PageServerConf {
     pub http_auth_type: AuthType,
     /// authentication method for libpq connections from compute
     pub pg_auth_type: AuthType,
-    /// authentication method for gRPC connections from compute
-    pub grpc_auth_type: AuthType,
     /// Path to a file or directory containing public key(s) for verifying JWT tokens.
     /// Used for both mgmt and compute auth, if enabled.
     pub auth_validation_public_key_path: Option<Utf8PathBuf>,
@@ -187,9 +178,6 @@ pub struct PageServerConf {
 
     pub max_vectored_read_bytes: MaxVectoredReadBytes,
 
-    /// Maximum number of keys to be read in a single get_vectored call.
-    pub max_get_vectored_keys: MaxGetVectoredKeys,
-
     pub image_compression: ImageCompressionAlgorithm,
 
     /// Whether to offload archived timelines automatically
@@ -210,6 +198,8 @@ pub struct PageServerConf {
     /// Optionally disable disk syncs (unsafe!)
     pub no_sync: bool,
 
+    pub wal_receiver_protocol: PostgresClientProtocol,
+
     pub page_service_pipelining: pageserver_api::config::PageServicePipeliningConfig,
 
     pub get_vectored_concurrent_io: pageserver_api::config::GetVectoredConcurrentIo,
@@ -241,9 +231,6 @@ pub struct PageServerConf {
     /// This is insecure and should only be used in development environments.
     pub dev_mode: bool,
 
-    /// PostHog integration config.
-    pub posthog_config: Option<PostHogConfig>,
-
     pub timeline_import_config: pageserver_api::config::TimelineImportConfig,
 
     pub basebackup_cache_config: Option<pageserver_api::config::BasebackupCacheConfig>,
@@ -368,7 +355,6 @@ impl PageServerConf {
             listen_pg_addr,
             listen_http_addr,
             listen_https_addr,
-            listen_grpc_addr,
             ssl_key_file,
             ssl_cert_file,
             ssl_cert_reload_period,
@@ -383,7 +369,6 @@ impl PageServerConf {
             pg_distrib_dir,
             http_auth_type,
             pg_auth_type,
-            grpc_auth_type,
             auth_validation_public_key_path,
             remote_storage,
             broker_endpoint,
@@ -407,7 +392,6 @@ impl PageServerConf {
             secondary_download_concurrency,
             ingest_batch_size,
             max_vectored_read_bytes,
-            max_get_vectored_keys,
             image_compression,
             timeline_offloading,
             ephemeral_bytes_per_memory_kb,
@@ -418,6 +402,7 @@ impl PageServerConf {
             virtual_file_io_engine,
             tenant_config,
             no_sync,
+            wal_receiver_protocol,
             page_service_pipelining,
             get_vectored_concurrent_io,
             enable_read_path_debugging,
@@ -427,7 +412,6 @@ impl PageServerConf {
             tracing,
             enable_tls_page_service_api,
             dev_mode,
-            posthog_config,
             timeline_import_config,
             basebackup_cache_config,
         } = config_toml;
@@ -439,7 +423,6 @@ impl PageServerConf {
             listen_pg_addr,
             listen_http_addr,
             listen_https_addr,
-            listen_grpc_addr,
             ssl_key_file,
             ssl_cert_file,
             ssl_cert_reload_period,
@@ -452,7 +435,6 @@ impl PageServerConf {
             max_file_descriptors,
             http_auth_type,
             pg_auth_type,
-            grpc_auth_type,
             auth_validation_public_key_path,
             remote_storage_config: remote_storage,
             broker_endpoint,
@@ -473,13 +455,13 @@ impl PageServerConf {
             secondary_download_concurrency,
             ingest_batch_size,
             max_vectored_read_bytes,
-            max_get_vectored_keys,
             image_compression,
             timeline_offloading,
             ephemeral_bytes_per_memory_kb,
             import_pgdata_upcall_api,
             import_pgdata_upcall_api_token: import_pgdata_upcall_api_token.map(SecretString::from),
             import_pgdata_aws_endpoint_url,
+            wal_receiver_protocol,
             page_service_pipelining,
             get_vectored_concurrent_io,
             tracing,
@@ -543,16 +525,13 @@ impl PageServerConf {
                 }
                 None => Vec::new(),
             },
-            posthog_config,
         };
 
         // ------------------------------------------------------------
         // custom validation code that covers more than one field in isolation
         // ------------------------------------------------------------
 
-        if [conf.http_auth_type, conf.pg_auth_type, conf.grpc_auth_type]
-            .contains(&AuthType::NeonJWT)
-        {
+        if conf.http_auth_type == AuthType::NeonJWT || conf.pg_auth_type == AuthType::NeonJWT {
             let auth_validation_public_key_path = conf
                 .auth_validation_public_key_path
                 .get_or_insert_with(|| workdir.join("auth_public_key.pem"));
@@ -601,19 +580,6 @@ impl PageServerConf {
                 )
             })?;
 
-        if let PageServicePipeliningConfig::Pipelined(PageServicePipeliningConfigPipelined {
-            max_batch_size,
-            ..
-        }) = conf.page_service_pipelining
-        {
-            if max_batch_size.get() > conf.max_get_vectored_keys.get() {
-                return Err(anyhow::anyhow!(
-                    "`max_batch_size` ({max_batch_size}) must be less than or equal to `max_get_vectored_keys` ({})",
-                    conf.max_get_vectored_keys.get()
-                ));
-            }
-        };
-
         Ok(conf)
     }
 
@@ -701,7 +667,6 @@ impl ConfigurableSemaphore {
 mod tests {
 
     use camino::Utf8PathBuf;
-    use rstest::rstest;
     use utils::id::NodeId;
 
     use super::PageServerConf;
@@ -741,28 +706,4 @@ mod tests {
         PageServerConf::parse_and_validate(NodeId(0), config_toml, &workdir)
             .expect_err("parse_and_validate should fail for endpoint without scheme");
     }
-
-    #[rstest]
-    #[case(32, 32, true)]
-    #[case(64, 32, false)]
-    #[case(64, 64, true)]
-    #[case(128, 128, true)]
-    fn test_config_max_batch_size_is_valid(
-        #[case] max_batch_size: usize,
-        #[case] max_get_vectored_keys: usize,
-        #[case] is_valid: bool,
-    ) {
-        let input = format!(
-            r#"
-            control_plane_api = "http://localhost:6666"
-            max_get_vectored_keys = {max_get_vectored_keys}
-            page_service_pipelining = {{ mode="pipelined", execution="concurrent-futures", max_batch_size={max_batch_size}, batching="uniform-lsn" }}
-        "#,
-        );
-        let config_toml = toml_edit::de::from_str::<pageserver_api::config::ConfigToml>(&input)
-            .expect("config has valid fields");
-        let workdir = Utf8PathBuf::from("/nonexistent");
-        let result = PageServerConf::parse_and_validate(NodeId(0), config_toml, &workdir);
-        assert_eq!(result.is_ok(), is_valid);
-    }
 }

pageserver/src/disk_usage_eviction_task.rs

@@ -837,30 +837,7 @@ async fn collect_eviction_candidates(
                 continue;
             }
             let info = tl.get_local_layers_for_disk_usage_eviction().await;
-            debug!(
-                tenant_id=%tl.tenant_shard_id.tenant_id,
-                shard_id=%tl.tenant_shard_id.shard_slug(),
-                timeline_id=%tl.timeline_id,
-                "timeline resident layers count: {}", info.resident_layers.len()
-            );
-
-            tenant_candidates.extend(info.resident_layers.into_iter());
-            max_layer_size = max_layer_size.max(info.max_layer_size.unwrap_or(0));
-
-            if cancel.is_cancelled() {
-                return Ok(EvictionCandidates::Cancelled);
-            }
-        }
-
-        // Also consider layers of timelines being imported for eviction
-        for tl in tenant.list_importing_timelines() {
-            let info = tl.timeline.get_local_layers_for_disk_usage_eviction().await;
-            debug!(
-                tenant_id=%tl.timeline.tenant_shard_id.tenant_id,
-                shard_id=%tl.timeline.tenant_shard_id.shard_slug(),
-                timeline_id=%tl.timeline.timeline_id,
-                "timeline resident layers count: {}", info.resident_layers.len()
-            );
+            debug!(tenant_id=%tl.tenant_shard_id.tenant_id, shard_id=%tl.tenant_shard_id.shard_slug(), timeline_id=%tl.timeline_id, "timeline resident layers count: {}", info.resident_layers.len());
 
             tenant_candidates.extend(info.resident_layers.into_iter());
             max_layer_size = max_layer_size.max(info.max_layer_size.unwrap_or(0));

pageserver/src/feature_resolver.rs

@@ -1,237 +0,0 @@
-use std::{collections::HashMap, sync::Arc, time::Duration};
-
-use posthog_client_lite::{
-    CaptureEvent, FeatureResolverBackgroundLoop, PostHogClientConfig, PostHogEvaluationError,
-    PostHogFlagFilterPropertyValue,
-};
-use remote_storage::RemoteStorageKind;
-use serde_json::json;
-use tokio_util::sync::CancellationToken;
-use utils::id::TenantId;
-
-use crate::{config::PageServerConf, metrics::FEATURE_FLAG_EVALUATION};
-
-#[derive(Clone)]
-pub struct FeatureResolver {
-    inner: Option<Arc<FeatureResolverBackgroundLoop>>,
-    internal_properties: Option<Arc<HashMap<String, PostHogFlagFilterPropertyValue>>>,
-}
-
-impl FeatureResolver {
-    pub fn new_disabled() -> Self {
-        Self {
-            inner: None,
-            internal_properties: None,
-        }
-    }
-
-    pub fn spawn(
-        conf: &PageServerConf,
-        shutdown_pageserver: CancellationToken,
-        handle: &tokio::runtime::Handle,
-    ) -> anyhow::Result<Self> {
-        // DO NOT block in this function: make it return as fast as possible to avoid startup delays.
-        if let Some(posthog_config) = &conf.posthog_config {
-            let inner = FeatureResolverBackgroundLoop::new(
-                PostHogClientConfig {
-                    server_api_key: posthog_config.server_api_key.clone(),
-                    client_api_key: posthog_config.client_api_key.clone(),
-                    project_id: posthog_config.project_id.clone(),
-                    private_api_url: posthog_config.private_api_url.clone(),
-                    public_api_url: posthog_config.public_api_url.clone(),
-                },
-                shutdown_pageserver,
-            );
-            let inner = Arc::new(inner);
-
-            // The properties shared by all tenants on this pageserver.
-            let internal_properties = {
-                let mut properties = HashMap::new();
-                properties.insert(
-                    "pageserver_id".to_string(),
-                    PostHogFlagFilterPropertyValue::String(conf.id.to_string()),
-                );
-                if let Some(availability_zone) = &conf.availability_zone {
-                    properties.insert(
-                        "availability_zone".to_string(),
-                        PostHogFlagFilterPropertyValue::String(availability_zone.clone()),
-                    );
-                }
-                // Infer region based on the remote storage config.
-                if let Some(remote_storage) = &conf.remote_storage_config {
-                    match &remote_storage.storage {
-                        RemoteStorageKind::AwsS3(config) => {
-                            properties.insert(
-                                "region".to_string(),
-                                PostHogFlagFilterPropertyValue::String(format!(
-                                    "aws-{}",
-                                    config.bucket_region
-                                )),
-                            );
-                        }
-                        RemoteStorageKind::AzureContainer(config) => {
-                            properties.insert(
-                                "region".to_string(),
-                                PostHogFlagFilterPropertyValue::String(format!(
-                                    "azure-{}",
-                                    config.container_region
-                                )),
-                            );
-                        }
-                        RemoteStorageKind::LocalFs { .. } => {
-                            properties.insert(
-                                "region".to_string(),
-                                PostHogFlagFilterPropertyValue::String("local".to_string()),
-                            );
-                        }
-                    }
-                }
-                // TODO: add pageserver URL.
-                Arc::new(properties)
-            };
-            let fake_tenants = {
-                let mut tenants = Vec::new();
-                for i in 0..10 {
-                    let distinct_id = format!(
-                        "fake_tenant_{}_{}_{}",
-                        conf.availability_zone.as_deref().unwrap_or_default(),
-                        conf.id,
-                        i
-                    );
-                    let properties = Self::collect_properties_inner(
-                        distinct_id.clone(),
-                        Some(&internal_properties),
-                    );
-                    tenants.push(CaptureEvent {
-                        event: "initial_tenant_report".to_string(),
-                        distinct_id,
-                        properties: json!({ "$set": properties }), // use `$set` to set the person properties instead of the event properties
-                    });
-                }
-                tenants
-            };
-            // TODO: make refresh period configurable
-            inner
-                .clone()
-                .spawn(handle, Duration::from_secs(60), fake_tenants);
-            Ok(FeatureResolver {
-                inner: Some(inner),
-                internal_properties: Some(internal_properties),
-            })
-        } else {
-            Ok(FeatureResolver {
-                inner: None,
-                internal_properties: None,
-            })
-        }
-    }
-
-    fn collect_properties_inner(
-        tenant_id: String,
-        internal_properties: Option<&HashMap<String, PostHogFlagFilterPropertyValue>>,
-    ) -> HashMap<String, PostHogFlagFilterPropertyValue> {
-        let mut properties = HashMap::new();
-        if let Some(internal_properties) = internal_properties {
-            for (key, value) in internal_properties.iter() {
-                properties.insert(key.clone(), value.clone());
-            }
-        }
-        properties.insert(
-            "tenant_id".to_string(),
-            PostHogFlagFilterPropertyValue::String(tenant_id),
-        );
-        properties
-    }
-
-    /// Collect all properties availble for the feature flag evaluation.
-    pub(crate) fn collect_properties(
-        &self,
-        tenant_id: TenantId,
-    ) -> HashMap<String, PostHogFlagFilterPropertyValue> {
-        Self::collect_properties_inner(tenant_id.to_string(), self.internal_properties.as_deref())
-    }
-
-    /// Evaluate a multivariate feature flag. Currently, we do not support any properties.
-    ///
-    /// Error handling: the caller should inspect the error and decide the behavior when a feature flag
-    /// cannot be evaluated (i.e., default to false if it cannot be resolved). The error should *not* be
-    /// propagated beyond where the feature flag gets resolved.
-    pub fn evaluate_multivariate(
-        &self,
-        flag_key: &str,
-        tenant_id: TenantId,
-    ) -> Result<String, PostHogEvaluationError> {
-        if let Some(inner) = &self.inner {
-            let res = inner.feature_store().evaluate_multivariate(
-                flag_key,
-                &tenant_id.to_string(),
-                &self.collect_properties(tenant_id),
-            );
-            match &res {
-                Ok(value) => {
-                    FEATURE_FLAG_EVALUATION
-                        .with_label_values(&[flag_key, "ok", value])
-                        .inc();
-                }
-                Err(e) => {
-                    FEATURE_FLAG_EVALUATION
-                        .with_label_values(&[flag_key, "error", e.as_variant_str()])
-                        .inc();
-                }
-            }
-            res
-        } else {
-            Err(PostHogEvaluationError::NotAvailable(
-                "PostHog integration is not enabled".to_string(),
-            ))
-        }
-    }
-
-    /// Evaluate a boolean feature flag. Currently, we do not support any properties.
-    ///
-    /// Returns `Ok(())` if the flag is evaluated to true, otherwise returns an error.
-    ///
-    /// Error handling: the caller should inspect the error and decide the behavior when a feature flag
-    /// cannot be evaluated (i.e., default to false if it cannot be resolved). The error should *not* be
-    /// propagated beyond where the feature flag gets resolved.
-    pub fn evaluate_boolean(
-        &self,
-        flag_key: &str,
-        tenant_id: TenantId,
-    ) -> Result<(), PostHogEvaluationError> {
-        if let Some(inner) = &self.inner {
-            let res = inner.feature_store().evaluate_boolean(
-                flag_key,
-                &tenant_id.to_string(),
-                &self.collect_properties(tenant_id),
-            );
-            match &res {
-                Ok(()) => {
-                    FEATURE_FLAG_EVALUATION
-                        .with_label_values(&[flag_key, "ok", "true"])
-                        .inc();
-                }
-                Err(e) => {
-                    FEATURE_FLAG_EVALUATION
-                        .with_label_values(&[flag_key, "error", e.as_variant_str()])
-                        .inc();
-                }
-            }
-            res
-        } else {
-            Err(PostHogEvaluationError::NotAvailable(
-                "PostHog integration is not enabled".to_string(),
-            ))
-        }
-    }
-
-    pub fn is_feature_flag_boolean(&self, flag_key: &str) -> Result<bool, PostHogEvaluationError> {
-        if let Some(inner) = &self.inner {
-            inner.feature_store().is_feature_flag_boolean(flag_key)
-        } else {
-            Err(PostHogEvaluationError::NotAvailable(
-                "PostHog integration is not enabled".to_string(),
-            ))
-        }
-    }
-}

pageserver/src/http/openapi_spec.yml

@@ -353,33 +353,6 @@ paths:
         "200":
           description: OK
 
-  /v1/tenant/{tenant_shard_id}/timeline/{timeline_id}/mark_invisible:
-    parameters:
-      - name: tenant_shard_id
-        in: path
-        required: true
-        schema:
-          type: string
-      - name: timeline_id
-        in: path
-        required: true
-        schema:
-          type: string
-          format: hex
-    put:
-      requestBody:
-        content:
-          application/json:
-            schema:
-              type: object
-              properties:
-                is_visible:
-                  type: boolean
-                  default: false
-      responses:
-        "200":
-          description: OK
-
   /v1/tenant/{tenant_shard_id}/location_config:
     parameters:
       - name: tenant_shard_id
@@ -653,8 +626,6 @@ paths:
                   format: hex
                 pg_version:
                   type: integer
-                read_only:
-                  type: boolean
                 existing_initdb_timeline_id:
                   type: string
                   format: hex

pageserver/src/http/routes.rs

@@ -43,7 +43,6 @@ use pageserver_api::models::{
 use pageserver_api::shard::{ShardCount, TenantShardId};
 use remote_storage::{DownloadError, GenericRemoteStorage, TimeTravelError};
 use scopeguard::defer;
-use serde_json::json;
 use tenant_size_model::svg::SvgBranchKind;
 use tenant_size_model::{SizeResult, StorageModel};
 use tokio::time::Instant;
@@ -371,18 +370,6 @@ impl From<crate::tenant::secondary::SecondaryTenantError> for ApiError {
     }
 }
 
-impl From<crate::tenant::FinalizeTimelineImportError> for ApiError {
-    fn from(err: crate::tenant::FinalizeTimelineImportError) -> ApiError {
-        use crate::tenant::FinalizeTimelineImportError::*;
-        match err {
-            ImportTaskStillRunning => {
-                ApiError::ResourceUnavailable("Import task still running".into())
-            }
-            ShuttingDown => ApiError::ShuttingDown,
-        }
-    }
-}
-
 // Helper function to construct a TimelineInfo struct for a timeline
 async fn build_timeline_info(
     timeline: &Arc<Timeline>,
@@ -585,7 +572,6 @@ async fn timeline_create_handler(
         TimelineCreateRequestMode::Branch {
             ancestor_timeline_id,
             ancestor_start_lsn,
-            read_only: _,
             pg_version: _,
         } => tenant::CreateTimelineParams::Branch(tenant::CreateTimelineParamsBranch {
             new_timeline_id,
@@ -3546,7 +3532,10 @@ async fn activate_post_import_handler(
 
         tenant.wait_to_become_active(ACTIVE_TENANT_TIMEOUT).await?;
 
-        tenant.finalize_importing_timeline(timeline_id).await?;
+        tenant
+            .finalize_importing_timeline(timeline_id)
+            .await
+            .map_err(ApiError::InternalServerError)?;
 
         match tenant.get_timeline(timeline_id, false) {
             Ok(_timeline) => {
@@ -3664,47 +3653,6 @@ async fn read_tar_eof(mut reader: (impl tokio::io::AsyncRead + Unpin)) -> anyhow
     Ok(())
 }
 
-async fn tenant_evaluate_feature_flag(
-    request: Request<Body>,
-    _cancel: CancellationToken,
-) -> Result<Response<Body>, ApiError> {
-    let tenant_shard_id: TenantShardId = parse_request_param(&request, "tenant_shard_id")?;
-    check_permission(&request, Some(tenant_shard_id.tenant_id))?;
-
-    let flag: String = must_parse_query_param(&request, "flag")?;
-    let as_type: String = must_parse_query_param(&request, "as")?;
-
-    let state = get_state(&request);
-
-    async {
-        let tenant = state
-            .tenant_manager
-            .get_attached_tenant_shard(tenant_shard_id)?;
-        let properties = tenant.feature_resolver.collect_properties(tenant_shard_id.tenant_id);
-        if as_type == "boolean" {
-            let result = tenant.feature_resolver.evaluate_boolean(&flag, tenant_shard_id.tenant_id);
-            let result = result.map(|_| true).map_err(|e| e.to_string());
-            json_response(StatusCode::OK, json!({ "result": result, "properties": properties }))
-        } else if as_type == "multivariate" {
-            let result = tenant.feature_resolver.evaluate_multivariate(&flag, tenant_shard_id.tenant_id).map_err(|e| e.to_string());
-            json_response(StatusCode::OK, json!({ "result": result, "properties": properties }))
-        } else {
-            // Auto infer the type of the feature flag.
-            let is_boolean = tenant.feature_resolver.is_feature_flag_boolean(&flag).map_err(|e| ApiError::InternalServerError(anyhow::anyhow!("{e}")))?;
-            if is_boolean {
-                let result = tenant.feature_resolver.evaluate_boolean(&flag, tenant_shard_id.tenant_id);
-                let result = result.map(|_| true).map_err(|e| e.to_string());
-                json_response(StatusCode::OK, json!({ "result": result, "properties": properties }))
-            } else {
-                let result = tenant.feature_resolver.evaluate_multivariate(&flag, tenant_shard_id.tenant_id).map_err(|e| e.to_string());
-                json_response(StatusCode::OK, json!({ "result": result, "properties": properties }))
-            }
-        }
-    }
-    .instrument(info_span!("tenant_evaluate_feature_flag", tenant_id = %tenant_shard_id.tenant_id, shard_id = %tenant_shard_id.shard_slug()))
-    .await
-}
-
 /// Common functionality of all the HTTP API handlers.
 ///
 /// - Adds a tracing span to each request (by `request_span`)
@@ -4081,8 +4029,5 @@ pub fn make_router(
             "/v1/tenant/:tenant_shard_id/timeline/:timeline_id/activate_post_import",
             |r| api_handler(r, activate_post_import_handler),
         )
-        .get("/v1/tenant/:tenant_shard_id/feature_flag", |r| {
-            api_handler(r, tenant_evaluate_feature_flag)
-        })
         .any(handler_404))
 }

pageserver/src/lib.rs

@@ -10,7 +10,6 @@ pub mod context;
 pub mod controller_upcall_client;
 pub mod deletion_queue;
 pub mod disk_usage_eviction_task;
-pub mod feature_resolver;
 pub mod http;
 pub mod import_datadir;
 pub mod l0_flush;
@@ -85,7 +84,6 @@ pub async fn shutdown_pageserver(
     http_listener: HttpEndpointListener,
     https_listener: Option<HttpsEndpointListener>,
     page_service: page_service::Listener,
-    grpc_task: Option<CancellableTask>,
     consumption_metrics_worker: ConsumptionMetricsTasks,
     disk_usage_eviction_task: Option<DiskUsageEvictionTask>,
     tenant_manager: &TenantManager,
@@ -179,16 +177,6 @@ pub async fn shutdown_pageserver(
     )
     .await;
 
-    // Shut down the gRPC server task, including request handlers.
-    if let Some(grpc_task) = grpc_task {
-        timed(
-            grpc_task.shutdown(),
-            "shutdown gRPC PageRequestHandler",
-            Duration::from_secs(3),
-        )
-        .await;
-    }
-
     // Shut down all the tenants. This flushes everything to disk and kills
     // the checkpoint and GC tasks.
     timed(

pageserver/src/metrics.rs

@@ -15,7 +15,6 @@ use metrics::{
     register_int_gauge, register_int_gauge_vec, register_uint_gauge, register_uint_gauge_vec,
 };
 use once_cell::sync::Lazy;
-use pageserver_api::config::defaults::DEFAULT_MAX_GET_VECTORED_KEYS;
 use pageserver_api::config::{
     PageServicePipeliningConfig, PageServicePipeliningConfigPipelined,
     PageServiceProtocolPipelinedBatchingStrategy, PageServiceProtocolPipelinedExecutionStrategy,
@@ -33,6 +32,7 @@ use crate::config::PageServerConf;
 use crate::context::{PageContentKind, RequestContext};
 use crate::pgdatadir_mapping::DatadirModificationStats;
 use crate::task_mgr::TaskKind;
+use crate::tenant::Timeline;
 use crate::tenant::layer_map::LayerMap;
 use crate::tenant::mgr::TenantSlot;
 use crate::tenant::storage_layer::{InMemoryLayer, PersistentLayerDesc};
@@ -446,15 +446,6 @@ static PAGE_CACHE_ERRORS: Lazy<IntCounterVec> = Lazy::new(|| {
     .expect("failed to define a metric")
 });
 
-pub(crate) static FEATURE_FLAG_EVALUATION: Lazy<CounterVec> = Lazy::new(|| {
-    register_counter_vec!(
-        "pageserver_feature_flag_evaluation",
-        "Number of times a feature flag is evaluated",
-        &["flag_key", "status", "value"],
-    )
-    .unwrap()
-});
-
 #[derive(IntoStaticStr)]
 #[strum(serialize_all = "kebab_case")]
 pub(crate) enum PageCacheErrorKind {
@@ -1321,44 +1312,11 @@ impl EvictionsWithLowResidenceDuration {
 //
 // Roughly logarithmic scale.
 const STORAGE_IO_TIME_BUCKETS: &[f64] = &[
-    0.00005,  // 50us
-    0.00006,  // 60us
-    0.00007,  // 70us
-    0.00008,  // 80us
-    0.00009,  // 90us
-    0.0001,   // 100us
-    0.000110, // 110us
-    0.000120, // 120us
-    0.000130, // 130us
-    0.000140, // 140us
-    0.000150, // 150us
-    0.000160, // 160us
-    0.000170, // 170us
-    0.000180, // 180us
-    0.000190, // 190us
-    0.000200, // 200us
-    0.000210, // 210us
-    0.000220, // 220us
-    0.000230, // 230us
-    0.000240, // 240us
-    0.000250, // 250us
-    0.000300, // 300us
-    0.000350, // 350us
-    0.000400, // 400us
-    0.000450, // 450us
-    0.000500, // 500us
-    0.000600, // 600us
-    0.000700, // 700us
-    0.000800, // 800us
-    0.000900, // 900us
-    0.001000, // 1ms
-    0.002000, // 2ms
-    0.003000, // 3ms
-    0.004000, // 4ms
-    0.005000, // 5ms
-    0.01000,  // 10ms
-    0.02000,  // 20ms
-    0.05000,  // 50ms
+    0.000030, // 30 usec
+    0.001000, // 1000 usec
+    0.030,    // 30 ms
+    1.000,    // 1000 ms
+    30.000,   // 30000 ms
 ];
 
 /// VirtualFile fs operation variants.
@@ -1948,7 +1906,7 @@ static SMGR_QUERY_TIME_GLOBAL: Lazy<HistogramVec> = Lazy::new(|| {
 });
 
 static PAGE_SERVICE_BATCH_SIZE_BUCKETS_GLOBAL: Lazy<Vec<f64>> = Lazy::new(|| {
-    (1..=u32::try_from(DEFAULT_MAX_GET_VECTORED_KEYS).unwrap())
+    (1..=u32::try_from(Timeline::MAX_GET_VECTORED_KEYS).unwrap())
         .map(|v| v.into())
         .collect()
 });
@@ -1966,7 +1924,7 @@ static PAGE_SERVICE_BATCH_SIZE_BUCKETS_PER_TIMELINE: Lazy<Vec<f64>> = Lazy::new(
     let mut buckets = Vec::new();
     for i in 0.. {
         let bucket = 1 << i;
-        if bucket > u32::try_from(DEFAULT_MAX_GET_VECTORED_KEYS).unwrap() {
+        if bucket > u32::try_from(Timeline::MAX_GET_VECTORED_KEYS).unwrap() {
             break;
         }
         buckets.push(bucket.into());
@@ -2276,10 +2234,8 @@ impl BasebackupQueryTimeOngoingRecording<'_> {
         // If you want to change categorize of a specific error, also change it in `log_query_error`.
         let metric = match res {
             Ok(_) => &self.parent.ok,
-            Err(QueryError::Shutdown) | Err(QueryError::Reconnect) => {
-                // Do not observe ok/err for shutdown/reconnect.
-                // Reconnect error might be raised when the operation is waiting for LSN and the tenant shutdown interrupts
-                // the operation. A reconnect error will be issued and the client will retry.
+            Err(QueryError::Shutdown) => {
+                // Do not observe ok/err for shutdown
                 return;
             }
             Err(QueryError::Disconnected(ConnectionError::Io(io_error)))
@@ -2855,6 +2811,7 @@ pub(crate) struct WalIngestMetrics {
     pub(crate) records_received: IntCounter,
     pub(crate) records_observed: IntCounter,
     pub(crate) records_committed: IntCounter,
+    pub(crate) records_filtered: IntCounter,
     pub(crate) values_committed_metadata_images: IntCounter,
     pub(crate) values_committed_metadata_deltas: IntCounter,
     pub(crate) values_committed_data_images: IntCounter,
@@ -2910,6 +2867,11 @@ pub(crate) static WAL_INGEST: Lazy<WalIngestMetrics> = Lazy::new(|| {
         "Number of WAL records which resulted in writes to pageserver storage"
     )
     .expect("failed to define a metric"),
+    records_filtered: register_int_counter!(
+        "pageserver_wal_ingest_records_filtered",
+        "Number of WAL records filtered out due to sharding"
+    )
+    .expect("failed to define a metric"),
     values_committed_metadata_images: values_committed.with_label_values(&["metadata", "image"]),
     values_committed_metadata_deltas: values_committed.with_label_values(&["metadata", "delta"]),
     values_committed_data_images: values_committed.with_label_values(&["data", "image"]),

pageserver/src/pgdatadir_mapping.rs

@@ -431,10 +431,10 @@ impl Timeline {
                         GetVectoredError::InvalidLsn(e) => {
                             Err(anyhow::anyhow!("invalid LSN: {e:?}").into())
                         }
-                        // NB: this should never happen in practice because we limit batch size to be smaller than max_get_vectored_keys
+                        // NB: this should never happen in practice because we limit MAX_GET_VECTORED_KEYS
                         // TODO: we can prevent this error class by moving this check into the type system
-                        GetVectoredError::Oversized(err, max) => {
-                            Err(anyhow::anyhow!("batching oversized: {err} > {max}").into())
+                        GetVectoredError::Oversized(err) => {
+                            Err(anyhow::anyhow!("batching oversized: {err:?}").into())
                         }
                     };
 
@@ -471,19 +471,8 @@ impl Timeline {
 
         let rels = self.list_rels(spcnode, dbnode, version, ctx).await?;
 
-        if rels.is_empty() {
-            return Ok(0);
-        }
-
-        // Pre-deserialize the rel directory to avoid duplicated work in `get_relsize_cached`.
-        let reldir_key = rel_dir_to_key(spcnode, dbnode);
-        let buf = version.get(self, reldir_key, ctx).await?;
-        let reldir = RelDirectory::des(&buf)?;
-
         for rel in rels {
-            let n_blocks = self
-                .get_rel_size_in_reldir(rel, version, Some((reldir_key, &reldir)), ctx)
-                .await?;
+            let n_blocks = self.get_rel_size(rel, version, ctx).await?;
             total_blocks += n_blocks as usize;
         }
         Ok(total_blocks)
@@ -498,19 +487,6 @@ impl Timeline {
         tag: RelTag,
         version: Version<'_>,
         ctx: &RequestContext,
-    ) -> Result<BlockNumber, PageReconstructError> {
-        self.get_rel_size_in_reldir(tag, version, None, ctx).await
-    }
-
-    /// Get size of a relation file. The relation must exist, otherwise an error is returned.
-    ///
-    /// See [`Self::get_rel_exists_in_reldir`] on why we need `deserialized_reldir_v1`.
-    pub(crate) async fn get_rel_size_in_reldir(
-        &self,
-        tag: RelTag,
-        version: Version<'_>,
-        deserialized_reldir_v1: Option<(Key, &RelDirectory)>,
-        ctx: &RequestContext,
     ) -> Result<BlockNumber, PageReconstructError> {
         if tag.relnode == 0 {
             return Err(PageReconstructError::Other(
@@ -523,9 +499,7 @@ impl Timeline {
         }
 
         if (tag.forknum == FSM_FORKNUM || tag.forknum == VISIBILITYMAP_FORKNUM)
-            && !self
-                .get_rel_exists_in_reldir(tag, version, deserialized_reldir_v1, ctx)
-                .await?
+            && !self.get_rel_exists(tag, version, ctx).await?
         {
             // FIXME: Postgres sometimes calls smgrcreate() to create
             // FSM, and smgrnblocks() on it immediately afterwards,
@@ -547,28 +521,11 @@ impl Timeline {
     ///
     /// Only shard 0 has a full view of the relations. Other shards only know about relations that
     /// the shard stores pages for.
-    ///
     pub(crate) async fn get_rel_exists(
         &self,
         tag: RelTag,
         version: Version<'_>,
         ctx: &RequestContext,
-    ) -> Result<bool, PageReconstructError> {
-        self.get_rel_exists_in_reldir(tag, version, None, ctx).await
-    }
-
-    /// Does the relation exist? With a cached deserialized `RelDirectory`.
-    ///
-    /// There are some cases where the caller loops across all relations. In that specific case,
-    /// the caller should obtain the deserialized `RelDirectory` first and then call this function
-    /// to avoid duplicated work of deserliazation. This is a hack and should be removed by introducing
-    /// a new API (e.g., `get_rel_exists_batched`).
-    pub(crate) async fn get_rel_exists_in_reldir(
-        &self,
-        tag: RelTag,
-        version: Version<'_>,
-        deserialized_reldir_v1: Option<(Key, &RelDirectory)>,
-        ctx: &RequestContext,
     ) -> Result<bool, PageReconstructError> {
         if tag.relnode == 0 {
             return Err(PageReconstructError::Other(
@@ -611,17 +568,6 @@ impl Timeline {
         // fetch directory listing (old)
 
         let key = rel_dir_to_key(tag.spcnode, tag.dbnode);
-
-        if let Some((cached_key, dir)) = deserialized_reldir_v1 {
-            if cached_key == key {
-                return Ok(dir.rels.contains(&(tag.relnode, tag.forknum)));
-            } else if cfg!(test) || cfg!(feature = "testing") {
-                panic!("cached reldir key mismatch: {cached_key} != {key}");
-            } else {
-                warn!("cached reldir key mismatch: {cached_key} != {key}");
-            }
-            // Fallback to reading the directory from the datadir.
-        }
         let buf = version.get(self, key, ctx).await?;
 
         let dir = RelDirectory::des(&buf)?;
@@ -719,7 +665,7 @@ impl Timeline {
 
         let batches = keyspace.partition(
             self.get_shard_identity(),
-            self.conf.max_get_vectored_keys.get() as u64 * BLCKSZ as u64,
+            Timeline::MAX_GET_VECTORED_KEYS * BLCKSZ as u64,
         );
 
         let io_concurrency = IoConcurrency::spawn_from_conf(
@@ -959,7 +905,7 @@ impl Timeline {
 
             let batches = keyspace.partition(
                 self.get_shard_identity(),
-                self.conf.max_get_vectored_keys.get() as u64 * BLCKSZ as u64,
+                Timeline::MAX_GET_VECTORED_KEYS * BLCKSZ as u64,
             );
 
             let io_concurrency = IoConcurrency::spawn_from_conf(

pageserver/src/task_mgr.rs

@@ -276,10 +276,9 @@ pub enum TaskKind {
     // HTTP endpoint listener.
     HttpEndpointListener,
 
-    /// Task that handles a single page service connection. A PageRequestHandler
-    /// task starts detached from any particular tenant or timeline, but it can
-    /// be associated with one later, after receiving a command from the client.
-    /// Also used for the gRPC page service API, including the main server task.
+    // Task that handles a single connection. A PageRequestHandler task
+    // starts detached from any particular tenant or timeline, but it can be
+    // associated with one later, after receiving a command from the client.
     PageRequestHandler,
 
     /// Manages the WAL receiver connection for one timeline.

pageserver/src/tenant.rs

@@ -84,7 +84,6 @@ use crate::context;
 use crate::context::RequestContextBuilder;
 use crate::context::{DownloadBehavior, RequestContext};
 use crate::deletion_queue::{DeletionQueueClient, DeletionQueueError};
-use crate::feature_resolver::FeatureResolver;
 use crate::l0_flush::L0FlushGlobalState;
 use crate::metrics::{
     BROKEN_TENANTS_SET, CIRCUIT_BREAKERS_BROKEN, CIRCUIT_BREAKERS_UNBROKEN, CONCURRENT_INITDBS,
@@ -160,7 +159,6 @@ pub struct TenantSharedResources {
     pub deletion_queue_client: DeletionQueueClient,
     pub l0_flush_global_state: L0FlushGlobalState,
     pub basebackup_prepare_sender: BasebackupPrepareSender,
-    pub feature_resolver: FeatureResolver,
 }
 
 /// A [`TenantShard`] is really an _attached_ tenant.  The configuration
@@ -300,7 +298,7 @@ pub struct TenantShard {
     ///   as in progress.
     /// * Imported timelines are removed when the storage controller calls the post timeline
     ///   import activation endpoint.
-    timelines_importing: std::sync::Mutex<HashMap<TimelineId, Arc<ImportingTimeline>>>,
+    timelines_importing: std::sync::Mutex<HashMap<TimelineId, ImportingTimeline>>,
 
     /// The last tenant manifest known to be in remote storage. None if the manifest has not yet
     /// been either downloaded or uploaded. Always Some after tenant attach.
@@ -382,8 +380,6 @@ pub struct TenantShard {
     pub(crate) gc_block: gc_block::GcBlock,
 
     l0_flush_global_state: L0FlushGlobalState,
-
-    pub(crate) feature_resolver: FeatureResolver,
 }
 impl std::fmt::Debug for TenantShard {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
@@ -672,7 +668,6 @@ pub enum MaybeOffloaded {
 pub enum TimelineOrOffloaded {
     Timeline(Arc<Timeline>),
     Offloaded(Arc<OffloadedTimeline>),
-    Importing(Arc<ImportingTimeline>),
 }
 
 impl TimelineOrOffloaded {
@@ -684,9 +679,6 @@ impl TimelineOrOffloaded {
             TimelineOrOffloaded::Offloaded(offloaded) => {
                 TimelineOrOffloadedArcRef::Offloaded(offloaded)
             }
-            TimelineOrOffloaded::Importing(importing) => {
-                TimelineOrOffloadedArcRef::Importing(importing)
-            }
         }
     }
     pub fn tenant_shard_id(&self) -> TenantShardId {
@@ -699,16 +691,12 @@ impl TimelineOrOffloaded {
         match self {
             TimelineOrOffloaded::Timeline(timeline) => &timeline.delete_progress,
             TimelineOrOffloaded::Offloaded(offloaded) => &offloaded.delete_progress,
-            TimelineOrOffloaded::Importing(importing) => &importing.delete_progress,
         }
     }
     fn maybe_remote_client(&self) -> Option<Arc<RemoteTimelineClient>> {
         match self {
             TimelineOrOffloaded::Timeline(timeline) => Some(timeline.remote_client.clone()),
             TimelineOrOffloaded::Offloaded(_offloaded) => None,
-            TimelineOrOffloaded::Importing(importing) => {
-                Some(importing.timeline.remote_client.clone())
-            }
         }
     }
 }
@@ -716,7 +704,6 @@ impl TimelineOrOffloaded {
 pub enum TimelineOrOffloadedArcRef<'a> {
     Timeline(&'a Arc<Timeline>),
     Offloaded(&'a Arc<OffloadedTimeline>),
-    Importing(&'a Arc<ImportingTimeline>),
 }
 
 impl TimelineOrOffloadedArcRef<'_> {
@@ -724,14 +711,12 @@ impl TimelineOrOffloadedArcRef<'_> {
         match self {
             TimelineOrOffloadedArcRef::Timeline(timeline) => timeline.tenant_shard_id,
             TimelineOrOffloadedArcRef::Offloaded(offloaded) => offloaded.tenant_shard_id,
-            TimelineOrOffloadedArcRef::Importing(importing) => importing.timeline.tenant_shard_id,
         }
     }
     pub fn timeline_id(&self) -> TimelineId {
         match self {
             TimelineOrOffloadedArcRef::Timeline(timeline) => timeline.timeline_id,
             TimelineOrOffloadedArcRef::Offloaded(offloaded) => offloaded.timeline_id,
-            TimelineOrOffloadedArcRef::Importing(importing) => importing.timeline.timeline_id,
         }
     }
 }
@@ -748,12 +733,6 @@ impl<'a> From<&'a Arc<OffloadedTimeline>> for TimelineOrOffloadedArcRef<'a> {
     }
 }
 
-impl<'a> From<&'a Arc<ImportingTimeline>> for TimelineOrOffloadedArcRef<'a> {
-    fn from(timeline: &'a Arc<ImportingTimeline>) -> Self {
-        Self::Importing(timeline)
-    }
-}
-
 #[derive(Debug, thiserror::Error, PartialEq, Eq)]
 pub enum GetTimelineError {
     #[error("Timeline is shutting down")]
@@ -881,14 +860,6 @@ impl Debug for SetStoppingError {
     }
 }
 
-#[derive(thiserror::Error, Debug)]
-pub(crate) enum FinalizeTimelineImportError {
-    #[error("Import task not done yet")]
-    ImportTaskStillRunning,
-    #[error("Shutting down")]
-    ShuttingDown,
-}
-
 /// Arguments to [`TenantShard::create_timeline`].
 ///
 /// Not usable as an idempotency key for timeline creation because if [`CreateTimelineParamsBranch::ancestor_start_lsn`]
@@ -1175,20 +1146,10 @@ impl TenantShard {
             ctx,
         )?;
         let disk_consistent_lsn = timeline.get_disk_consistent_lsn();
-
-        if !disk_consistent_lsn.is_valid() {
-            // As opposed to normal timelines which get initialised with a disk consitent LSN
-            // via initdb, imported timelines start from 0. If the import task stops before
-            // it advances disk consitent LSN, allow it to resume.
-            let in_progress_import = import_pgdata
-                .as_ref()
-                .map(|import| !import.is_done())
-                .unwrap_or(false);
-            if !in_progress_import {
-                anyhow::bail!("Timeline {tenant_id}/{timeline_id} has invalid disk_consistent_lsn");
-            }
-        }
-
+        anyhow::ensure!(
+            disk_consistent_lsn.is_valid(),
+            "Timeline {tenant_id}/{timeline_id} has invalid disk_consistent_lsn"
+        );
         assert_eq!(
             disk_consistent_lsn,
             metadata.disk_consistent_lsn(),
@@ -1282,25 +1243,20 @@ impl TenantShard {
                     }
                 }
 
-                if disk_consistent_lsn.is_valid() {
-                    // Sanity check: a timeline should have some content.
-                    // Exception: importing timelines might not yet have any
-                    anyhow::ensure!(
-                        ancestor.is_some()
-                            || timeline
-                                .layers
-                                .read()
-                                .await
-                                .layer_map()
-                                .expect(
-                                    "currently loading, layer manager cannot be shutdown already"
-                                )
-                                .iter_historic_layers()
-                                .next()
-                                .is_some(),
-                        "Timeline has no ancestor and no layer files"
-                    );
-                }
+                // Sanity check: a timeline should have some content.
+                anyhow::ensure!(
+                    ancestor.is_some()
+                        || timeline
+                            .layers
+                            .read()
+                            .await
+                            .layer_map()
+                            .expect("currently loading, layer manager cannot be shutdown already")
+                            .iter_historic_layers()
+                            .next()
+                            .is_some(),
+                    "Timeline has no ancestor and no layer files"
+                );
 
                 Ok(TimelineInitAndSyncResult::ReadyToActivate)
             }
@@ -1336,7 +1292,6 @@ impl TenantShard {
             deletion_queue_client,
             l0_flush_global_state,
             basebackup_prepare_sender,
-            feature_resolver,
         } = resources;
 
         let attach_mode = attached_conf.location.attach_mode;
@@ -1353,7 +1308,6 @@ impl TenantShard {
             deletion_queue_client,
             l0_flush_global_state,
             basebackup_prepare_sender,
-            feature_resolver,
         ));
 
         // The attach task will carry a GateGuard, so that shutdown() reliably waits for it to drop out if
@@ -1806,25 +1760,20 @@ impl TenantShard {
                     },
                 ) => {
                     let timeline_id = timeline.timeline_id;
-                    let import_task_gate = Gate::default();
-                    let import_task_guard = import_task_gate.enter().unwrap();
                     let import_task_handle =
                         tokio::task::spawn(self.clone().create_timeline_import_pgdata_task(
                             timeline.clone(),
                             import_pgdata,
                             guard,
-                            import_task_guard,
                             ctx.detached_child(TaskKind::ImportPgdata, DownloadBehavior::Warn),
                         ));
 
                     let prev = self.timelines_importing.lock().unwrap().insert(
                         timeline_id,
-                        Arc::new(ImportingTimeline {
+                        ImportingTimeline {
                             timeline: timeline.clone(),
                             import_task_handle,
-                            import_task_gate,
-                            delete_progress: TimelineDeleteProgress::default(),
-                        }),
+                        },
                     );
 
                     assert!(prev.is_none());
@@ -2442,17 +2391,6 @@ impl TenantShard {
             .collect()
     }
 
-    /// Lists timelines the tenant contains.
-    /// It's up to callers to omit certain timelines that are not considered ready for use.
-    pub fn list_importing_timelines(&self) -> Vec<Arc<ImportingTimeline>> {
-        self.timelines_importing
-            .lock()
-            .unwrap()
-            .values()
-            .map(Arc::clone)
-            .collect()
-    }
-
     /// Lists timelines the tenant manages, including offloaded ones.
     ///
     /// It's up to callers to omit certain timelines that are not considered ready for use.
@@ -2886,25 +2824,19 @@ impl TenantShard {
 
         let (timeline, timeline_create_guard) = uninit_timeline.finish_creation_myself();
 
-        let import_task_gate = Gate::default();
-        let import_task_guard = import_task_gate.enter().unwrap();
-
         let import_task_handle = tokio::spawn(self.clone().create_timeline_import_pgdata_task(
             timeline.clone(),
             index_part,
             timeline_create_guard,
-            import_task_guard,
             timeline_ctx.detached_child(TaskKind::ImportPgdata, DownloadBehavior::Warn),
         ));
 
         let prev = self.timelines_importing.lock().unwrap().insert(
             timeline.timeline_id,
-            Arc::new(ImportingTimeline {
+            ImportingTimeline {
                 timeline: timeline.clone(),
                 import_task_handle,
-                import_task_gate,
-                delete_progress: TimelineDeleteProgress::default(),
-            }),
+            },
         );
 
         // Idempotency is enforced higher up the stack
@@ -2922,13 +2854,13 @@ impl TenantShard {
     pub(crate) async fn finalize_importing_timeline(
         &self,
         timeline_id: TimelineId,
-    ) -> Result<(), FinalizeTimelineImportError> {
+    ) -> anyhow::Result<()> {
         let timeline = {
             let locked = self.timelines_importing.lock().unwrap();
             match locked.get(&timeline_id) {
                 Some(importing_timeline) => {
                     if !importing_timeline.import_task_handle.is_finished() {
-                        return Err(FinalizeTimelineImportError::ImportTaskStillRunning);
+                        return Err(anyhow::anyhow!("Import task not done yet"));
                     }
 
                     importing_timeline.timeline.clone()
@@ -2941,13 +2873,8 @@ impl TenantShard {
 
         timeline
             .remote_client
-            .schedule_index_upload_for_import_pgdata_finalize()
-            .map_err(|_err| FinalizeTimelineImportError::ShuttingDown)?;
-        timeline
-            .remote_client
-            .wait_completion()
-            .await
-            .map_err(|_err| FinalizeTimelineImportError::ShuttingDown)?;
+            .schedule_index_upload_for_import_pgdata_finalize()?;
+        timeline.remote_client.wait_completion().await?;
 
         self.timelines_importing
             .lock()
@@ -2963,7 +2890,6 @@ impl TenantShard {
         timeline: Arc<Timeline>,
         index_part: import_pgdata::index_part_format::Root,
         timeline_create_guard: TimelineCreateGuard,
-        _import_task_guard: GateGuard,
         ctx: RequestContext,
     ) {
         debug_assert_current_span_has_tenant_and_timeline_id();
@@ -3209,18 +3135,11 @@ impl TenantShard {
                         .or_insert_with(|| Arc::new(GcCompactionQueue::new()))
                         .clone()
                 };
-                let gc_compaction_strategy = self
-                    .feature_resolver
-                    .evaluate_multivariate("gc-comapction-strategy", self.tenant_shard_id.tenant_id)
-                    .ok();
-                let span = if let Some(gc_compaction_strategy) = gc_compaction_strategy {
-                    info_span!("gc_compact_timeline", timeline_id = %timeline.timeline_id, strategy = %gc_compaction_strategy)
-                } else {
-                    info_span!("gc_compact_timeline", timeline_id = %timeline.timeline_id)
-                };
                 outcome = queue
                     .iteration(cancel, ctx, &self.gc_block, &timeline)
-                    .instrument(span)
+                    .instrument(
+                        info_span!("gc_compact_timeline", timeline_id = %timeline.timeline_id),
+                    )
                     .await?;
             }
 
@@ -3552,9 +3471,8 @@ impl TenantShard {
             let mut timelines_importing = self.timelines_importing.lock().unwrap();
             timelines_importing
                 .drain()
-                .for_each(|(timeline_id, importing_timeline)| {
-                    let span = tracing::info_span!("importing_timeline_shutdown", %timeline_id);
-                    js.spawn(async move { importing_timeline.shutdown().instrument(span).await });
+                .for_each(|(_timeline_id, importing_timeline)| {
+                    importing_timeline.shutdown();
                 });
         }
         // test_long_timeline_create_then_tenant_delete is leaning on this message
@@ -3875,9 +3793,6 @@ impl TenantShard {
                         .build_timeline_client(offloaded.timeline_id, self.remote_storage.clone());
                     Arc::new(remote_client)
                 }
-                TimelineOrOffloadedArcRef::Importing(_) => {
-                    unreachable!("Importing timelines are not included in the iterator")
-                }
             };
 
             // Shut down the timeline's remote client: this means that the indices we write
@@ -4332,7 +4247,6 @@ impl TenantShard {
         deletion_queue_client: DeletionQueueClient,
         l0_flush_global_state: L0FlushGlobalState,
         basebackup_prepare_sender: BasebackupPrepareSender,
-        feature_resolver: FeatureResolver,
     ) -> TenantShard {
         assert!(!attached_conf.location.generation.is_none());
 
@@ -4437,7 +4351,6 @@ impl TenantShard {
             gc_block: Default::default(),
             l0_flush_global_state,
             basebackup_prepare_sender,
-            feature_resolver,
         }
     }
 
@@ -5087,14 +5000,6 @@ impl TenantShard {
                 info!("timeline already exists but is offloaded");
                 Err(CreateTimelineError::Conflict)
             }
-            Err(TimelineExclusionError::AlreadyExists {
-                existing: TimelineOrOffloaded::Importing(_existing),
-                ..
-            }) => {
-                // If there's a timeline already importing, then we would hit
-                // the [`TimelineExclusionError::AlreadyCreating`] branch above.
-                unreachable!("Importing timelines hold the creation guard")
-            }
             Err(TimelineExclusionError::AlreadyExists {
                 existing: TimelineOrOffloaded::Timeline(existing),
                 arg,
@@ -5366,7 +5271,6 @@ impl TenantShard {
             l0_compaction_trigger: self.l0_compaction_trigger.clone(),
             l0_flush_global_state: self.l0_flush_global_state.clone(),
             basebackup_prepare_sender: self.basebackup_prepare_sender.clone(),
-            feature_resolver: self.feature_resolver.clone(),
         }
     }
 
@@ -5832,7 +5736,6 @@ pub(crate) mod harness {
         pub conf: &'static PageServerConf,
         pub tenant_conf: pageserver_api::models::TenantConfig,
         pub tenant_shard_id: TenantShardId,
-        pub shard_identity: ShardIdentity,
         pub generation: Generation,
         pub shard: ShardIndex,
         pub remote_storage: GenericRemoteStorage,
@@ -5900,7 +5803,6 @@ pub(crate) mod harness {
                 conf,
                 tenant_conf,
                 tenant_shard_id,
-                shard_identity,
                 generation,
                 shard,
                 remote_storage,
@@ -5962,7 +5864,8 @@ pub(crate) mod harness {
                     &ShardParameters::default(),
                 ))
                 .unwrap(),
-                self.shard_identity,
+                // This is a legacy/test code path: sharding isn't supported here.
+                ShardIdentity::unsharded(),
                 Some(walredo_mgr),
                 self.tenant_shard_id,
                 self.remote_storage.clone(),
@@ -5970,7 +5873,6 @@ pub(crate) mod harness {
                 // TODO: ideally we should run all unit tests with both configs
                 L0FlushGlobalState::new(L0FlushConfig::default()),
                 basebackup_requst_sender,
-                FeatureResolver::new_disabled(),
             ));
 
             let preload = tenant
@@ -6084,7 +5986,6 @@ mod tests {
     use timeline::compaction::{KeyHistoryRetention, KeyLogAtLsn};
     use timeline::{CompactOptions, DeltaLayerTestDesc, VersionedKeySpaceQuery};
     use utils::id::TenantId;
-    use utils::shard::{ShardCount, ShardNumber};
 
     use super::*;
     use crate::DEFAULT_PG_VERSION;
@@ -7197,7 +7098,7 @@ mod tests {
             let end = desc
                 .key_range
                 .start
-                .add(tenant.conf.max_get_vectored_keys.get() as u32);
+                .add(Timeline::MAX_GET_VECTORED_KEYS.try_into().unwrap());
             reads.push(KeySpace {
                 ranges: vec![start..end],
             });
@@ -8413,24 +8314,10 @@ mod tests {
             }
 
             tline.freeze_and_flush().await?;
-            // Force layers to L1
-            tline
-                .compact(
-                    &cancel,
-                    {
-                        let mut flags = EnumSet::new();
-                        flags.insert(CompactFlags::ForceL0Compaction);
-                        flags
-                    },
-                    &ctx,
-                )
-                .await?;
 
             if iter % 5 == 0 {
-                let scan_lsn = Lsn(lsn.0 + 1);
-                info!("scanning at {}", scan_lsn);
                 let (_, before_delta_file_accessed) =
-                    scan_with_statistics(&tline, &keyspace, scan_lsn, &ctx, io_concurrency.clone())
+                    scan_with_statistics(&tline, &keyspace, lsn, &ctx, io_concurrency.clone())
                         .await?;
                 tline
                     .compact(
@@ -8439,14 +8326,13 @@ mod tests {
                             let mut flags = EnumSet::new();
                             flags.insert(CompactFlags::ForceImageLayerCreation);
                             flags.insert(CompactFlags::ForceRepartition);
-                            flags.insert(CompactFlags::ForceL0Compaction);
                             flags
                         },
                         &ctx,
                     )
                     .await?;
                 let (_, after_delta_file_accessed) =
-                    scan_with_statistics(&tline, &keyspace, scan_lsn, &ctx, io_concurrency.clone())
+                    scan_with_statistics(&tline, &keyspace, lsn, &ctx, io_concurrency.clone())
                         .await?;
                 assert!(
                     after_delta_file_accessed < before_delta_file_accessed,
@@ -8887,8 +8773,6 @@ mod tests {
 
         let cancel = CancellationToken::new();
 
-        // Image layer creation happens on the disk_consistent_lsn so we need to force set it now.
-        tline.force_set_disk_consistent_lsn(Lsn(0x40));
         tline
             .compact(
                 &cancel,
@@ -8902,7 +8786,8 @@ mod tests {
             )
             .await
             .unwrap();
-        // Image layers are created at repartition LSN
+
+        // Image layers are created at last_record_lsn
         let images = tline
             .inspect_image_layers(Lsn(0x40), &ctx, io_concurrency.clone())
             .await
@@ -9420,77 +9305,6 @@ mod tests {
         Ok(())
     }
 
-    #[tokio::test]
-    async fn test_failed_flush_should_not_update_disk_consistent_lsn() -> anyhow::Result<()> {
-        //
-        // Setup
-        //
-        let harness = TenantHarness::create_custom(
-            "test_failed_flush_should_not_upload_disk_consistent_lsn",
-            pageserver_api::models::TenantConfig::default(),
-            TenantId::generate(),
-            ShardIdentity::new(ShardNumber(0), ShardCount(4), ShardStripeSize(128)).unwrap(),
-            Generation::new(1),
-        )
-        .await?;
-        let (tenant, ctx) = harness.load().await;
-
-        let timeline = tenant
-            .create_test_timeline(TIMELINE_ID, Lsn(0x10), DEFAULT_PG_VERSION, &ctx)
-            .await?;
-        assert_eq!(timeline.get_shard_identity().count, ShardCount(4));
-        let mut writer = timeline.writer().await;
-        writer
-            .put(
-                *TEST_KEY,
-                Lsn(0x20),
-                &Value::Image(test_img("foo at 0x20")),
-                &ctx,
-            )
-            .await?;
-        writer.finish_write(Lsn(0x20));
-        drop(writer);
-        timeline.freeze_and_flush().await.unwrap();
-
-        timeline.remote_client.wait_completion().await.unwrap();
-        let disk_consistent_lsn = timeline.get_disk_consistent_lsn();
-        let remote_consistent_lsn = timeline.get_remote_consistent_lsn_projected();
-        assert_eq!(Some(disk_consistent_lsn), remote_consistent_lsn);
-
-        //
-        // Test
-        //
-
-        let mut writer = timeline.writer().await;
-        writer
-            .put(
-                *TEST_KEY,
-                Lsn(0x30),
-                &Value::Image(test_img("foo at 0x30")),
-                &ctx,
-            )
-            .await?;
-        writer.finish_write(Lsn(0x30));
-        drop(writer);
-
-        fail::cfg(
-            "flush-layer-before-update-remote-consistent-lsn",
-            "return()",
-        )
-        .unwrap();
-
-        let flush_res = timeline.freeze_and_flush().await;
-        // if flush failed, the disk/remote consistent LSN should not be updated
-        assert!(flush_res.is_err());
-        assert_eq!(disk_consistent_lsn, timeline.get_disk_consistent_lsn());
-        assert_eq!(
-            remote_consistent_lsn,
-            timeline.get_remote_consistent_lsn_projected()
-        );
-
-        Ok(())
-    }
-
     #[cfg(feature = "testing")]
     #[tokio::test]
     async fn test_simple_bottom_most_compaction_deltas_1() -> anyhow::Result<()> {
@@ -11260,11 +11074,11 @@ mod tests {
                 let mut keyspaces_at_lsn: HashMap<Lsn, KeySpaceRandomAccum> = HashMap::default();
                 let mut used_keys: HashSet<Key> = HashSet::default();
 
-                while used_keys.len() < tenant.conf.max_get_vectored_keys.get() {
+                while used_keys.len() < Timeline::MAX_GET_VECTORED_KEYS as usize {
                     let selected_lsn = interesting_lsns.choose(&mut random).expect("not empty");
                     let mut selected_key = start_key.add(random.gen_range(0..KEY_DIMENSION_SIZE));
 
-                    while used_keys.len() < tenant.conf.max_get_vectored_keys.get() {
+                    while used_keys.len() < Timeline::MAX_GET_VECTORED_KEYS as usize {
                         if used_keys.contains(&selected_key)
                             || selected_key >= start_key.add(KEY_DIMENSION_SIZE)
                         {

pageserver/src/tenant/remote_timeline_client.rs

@@ -1348,21 +1348,6 @@ impl RemoteTimelineClient {
         Ok(())
     }
 
-    pub(crate) fn schedule_unlinking_of_layers_from_index_part<I>(
-        self: &Arc<Self>,
-        names: I,
-    ) -> Result<(), NotInitialized>
-    where
-        I: IntoIterator<Item = LayerName>,
-    {
-        let mut guard = self.upload_queue.lock().unwrap();
-        let upload_queue = guard.initialized_mut()?;
-
-        self.schedule_unlinking_of_layers_from_index_part0(upload_queue, names);
-
-        Ok(())
-    }
-
     /// Update the remote index file, removing the to-be-deleted files from the index,
     /// allowing scheduling of actual deletions later.
     fn schedule_unlinking_of_layers_from_index_part0<I>(

pageserver/src/tenant/timeline.rs

@@ -103,7 +103,6 @@ use crate::context::{
     DownloadBehavior, PerfInstrumentFutureExt, RequestContext, RequestContextBuilder,
 };
 use crate::disk_usage_eviction_task::{DiskUsageEvictionInfo, EvictionCandidate, finite_f32};
-use crate::feature_resolver::FeatureResolver;
 use crate::keyspace::{KeyPartitioning, KeySpace};
 use crate::l0_flush::{self, L0FlushGlobalState};
 use crate::metrics::{
@@ -199,7 +198,6 @@ pub struct TimelineResources {
     pub l0_compaction_trigger: Arc<Notify>,
     pub l0_flush_global_state: l0_flush::L0FlushGlobalState,
     pub basebackup_prepare_sender: BasebackupPrepareSender,
-    pub feature_resolver: FeatureResolver,
 }
 
 pub struct Timeline {
@@ -446,8 +444,6 @@ pub struct Timeline {
 
     /// A channel to send async requests to prepare a basebackup for the basebackup cache.
     basebackup_prepare_sender: BasebackupPrepareSender,
-
-    feature_resolver: FeatureResolver,
 }
 
 pub(crate) enum PreviousHeatmap {
@@ -817,8 +813,8 @@ pub(crate) enum GetVectoredError {
     #[error("timeline shutting down")]
     Cancelled,
 
-    #[error("requested too many keys: {0} > {1}")]
-    Oversized(u64, u64),
+    #[error("requested too many keys: {0} > {}", Timeline::MAX_GET_VECTORED_KEYS)]
+    Oversized(u64),
 
     #[error("requested at invalid LSN: {0}")]
     InvalidLsn(Lsn),
@@ -950,18 +946,6 @@ pub(crate) enum WaitLsnError {
     Timeout(String),
 }
 
-impl From<WaitLsnError> for tonic::Status {
-    fn from(err: WaitLsnError) -> Self {
-        use tonic::Code;
-        let code = match &err {
-            WaitLsnError::Timeout(_) => Code::Internal,
-            WaitLsnError::BadState(_) => Code::Internal,
-            WaitLsnError::Shutdown => Code::Unavailable,
-        };
-        tonic::Status::new(code, err.to_string())
-    }
-}
-
 // The impls below achieve cancellation mapping for errors.
 // Perhaps there's a way of achieving this with less cruft.
 
@@ -1019,7 +1003,7 @@ impl From<GetVectoredError> for PageReconstructError {
         match e {
             GetVectoredError::Cancelled => PageReconstructError::Cancelled,
             GetVectoredError::InvalidLsn(_) => PageReconstructError::Other(anyhow!("Invalid LSN")),
-            err @ GetVectoredError::Oversized(_, _) => PageReconstructError::Other(err.into()),
+            err @ GetVectoredError::Oversized(_) => PageReconstructError::Other(err.into()),
             GetVectoredError::MissingKey(err) => PageReconstructError::MissingKey(err),
             GetVectoredError::GetReadyAncestorError(err) => PageReconstructError::from(err),
             GetVectoredError::Other(err) => PageReconstructError::Other(err),
@@ -1199,6 +1183,7 @@ impl Timeline {
         }
     }
 
+    pub(crate) const MAX_GET_VECTORED_KEYS: u64 = 32;
     pub(crate) const LAYERS_VISITED_WARN_THRESHOLD: u32 = 100;
 
     /// Look up multiple page versions at a given LSN
@@ -1213,12 +1198,9 @@ impl Timeline {
     ) -> Result<BTreeMap<Key, Result<Bytes, PageReconstructError>>, GetVectoredError> {
         let total_keyspace = query.total_keyspace();
 
-        let key_count = total_keyspace.total_raw_size();
-        if key_count > self.conf.max_get_vectored_keys.get() {
-            return Err(GetVectoredError::Oversized(
-                key_count as u64,
-                self.conf.max_get_vectored_keys.get() as u64,
-            ));
+        let key_count = total_keyspace.total_raw_size().try_into().unwrap();
+        if key_count > Timeline::MAX_GET_VECTORED_KEYS {
+            return Err(GetVectoredError::Oversized(key_count));
         }
 
         for range in &total_keyspace.ranges {
@@ -2506,13 +2488,6 @@ impl Timeline {
             // Preparing basebackup doesn't make sense for shards other than shard zero.
             return;
         }
-        if !self.is_active() {
-            // May happen during initial timeline creation.
-            // Such timeline is not in the global timeline map yet,
-            // so basebackup cache will not be able to find it.
-            // TODO(diko): We can prepare such timelines in finish_creation().
-            return;
-        }
 
         let res = self
             .basebackup_prepare_sender
@@ -2852,6 +2827,21 @@ impl Timeline {
             )
     }
 
+    /// Resolve the effective WAL receiver protocol to use for this tenant.
+    ///
+    /// Priority order is:
+    /// 1. Tenant config override
+    /// 2. Default value for tenant config override
+    /// 3. Pageserver config override
+    /// 4. Pageserver config default
+    pub fn resolve_wal_receiver_protocol(&self) -> PostgresClientProtocol {
+        let tenant_conf = self.tenant_conf.load().tenant_conf.clone();
+        tenant_conf
+            .wal_receiver_protocol_override
+            .or(self.conf.default_tenant_conf.wal_receiver_protocol_override)
+            .unwrap_or(self.conf.wal_receiver_protocol)
+    }
+
     pub(super) fn tenant_conf_updated(&self, new_conf: &AttachedTenantConf) {
         // NB: Most tenant conf options are read by background loops, so,
         // changes will automatically be picked up.
@@ -3082,8 +3072,6 @@ impl Timeline {
                 wait_lsn_log_slow: tokio::sync::Semaphore::new(1),
 
                 basebackup_prepare_sender: resources.basebackup_prepare_sender,
-
-                feature_resolver: resources.feature_resolver,
             };
 
             result.repartition_threshold =
@@ -3207,16 +3195,10 @@ impl Timeline {
             guard.is_none(),
             "multiple launches / re-launches of WAL receiver are not supported"
         );
-
-        let protocol = PostgresClientProtocol::Interpreted {
-            format: utils::postgres_client::InterpretedFormat::Protobuf,
-            compression: Some(utils::postgres_client::Compression::Zstd { level: 1 }),
-        };
-
         *guard = Some(WalReceiver::start(
             Arc::clone(self),
             WalReceiverConf {
-                protocol,
+                protocol: self.resolve_wal_receiver_protocol(),
                 wal_connect_timeout,
                 lagging_wal_timeout,
                 max_lsn_wal_lag,
@@ -4779,10 +4761,7 @@ impl Timeline {
                     || !flushed_to_lsn.is_valid()
             );
 
-            if flushed_to_lsn < frozen_to_lsn
-                && self.shard_identity.count.count() > 1
-                && result.is_ok()
-            {
+            if flushed_to_lsn < frozen_to_lsn && self.shard_identity.count.count() > 1 {
                 // If our layer flushes didn't carry disk_consistent_lsn up to the `to_lsn` advertised
                 // to us via layer_flush_start_rx, then advance it here.
                 //
@@ -4927,7 +4906,6 @@ impl Timeline {
                     LastImageLayerCreationStatus::Initial,
                     false, // don't yield for L0, we're flushing L0
                 )
-                .instrument(info_span!("create_image_layers", mode = %ImageLayerCreationMode::Initial, partition_mode = "initial", lsn = %self.initdb_lsn))
                 .await?;
             debug_assert!(
                 matches!(is_complete, LastImageLayerCreationStatus::Complete),
@@ -4961,10 +4939,6 @@ impl Timeline {
             return Err(FlushLayerError::Cancelled);
         }
 
-        fail_point!("flush-layer-before-update-remote-consistent-lsn", |_| {
-            Err(FlushLayerError::Other(anyhow!("failpoint").into()))
-        });
-
         let disk_consistent_lsn = Lsn(lsn_range.end.0 - 1);
 
         // The new on-disk layers are now in the layer map. We can remove the
@@ -5270,7 +5244,7 @@ impl Timeline {
                 key = key.next();
 
                 // Maybe flush `key_rest_accum`
-                if key_request_accum.raw_size() >= self.conf.max_get_vectored_keys.get() as u64
+                if key_request_accum.raw_size() >= Timeline::MAX_GET_VECTORED_KEYS
                     || (last_key_in_range && key_request_accum.raw_size() > 0)
                 {
                     let query =
@@ -5488,8 +5462,7 @@ impl Timeline {
 
     /// Returns the image layers generated and an enum indicating whether the process is fully completed.
     /// true = we have generate all image layers, false = we preempt the process for L0 compaction.
-    ///
-    /// `partition_mode` is only for logging purpose and is not used anywhere in this function.
+    #[tracing::instrument(skip_all, fields(%lsn, %mode))]
     async fn create_image_layers(
         self: &Arc<Timeline>,
         partitioning: &KeyPartitioning,

pageserver/src/tenant/timeline/compaction.rs

@@ -206,8 +206,8 @@ pub struct GcCompactionQueue {
 }
 
 static CONCURRENT_GC_COMPACTION_TASKS: Lazy<Arc<Semaphore>> = Lazy::new(|| {
-    // Only allow one timeline on one pageserver to run gc compaction at a time.
-    Arc::new(Semaphore::new(1))
+    // Only allow two timelines on one pageserver to run gc compaction at a time.
+    Arc::new(Semaphore::new(2))
 });
 
 impl GcCompactionQueue {
@@ -1278,55 +1278,11 @@ impl Timeline {
         }
 
         let gc_cutoff = *self.applied_gc_cutoff_lsn.read();
-        let l0_l1_boundary_lsn = {
-            // We do the repartition on the L0-L1 boundary. All data below the boundary
-            // are compacted by L0 with low read amplification, thus making the `repartition`
-            // function run fast.
-            let guard = self.layers.read().await;
-            guard
-                .all_persistent_layers()
-                .iter()
-                .map(|x| {
-                    // Use the end LSN of delta layers OR the start LSN of image layers.
-                    if x.is_delta {
-                        x.lsn_range.end
-                    } else {
-                        x.lsn_range.start
-                    }
-                })
-                .max()
-        };
-
-        let (partition_mode, partition_lsn) = if cfg!(test)
-            || cfg!(feature = "testing")
-            || self
-                .feature_resolver
-                .evaluate_boolean("image-compaction-boundary", self.tenant_shard_id.tenant_id)
-                .is_ok()
-        {
-            let last_repartition_lsn = self.partitioning.read().1;
-            let lsn = match l0_l1_boundary_lsn {
-                Some(boundary) => gc_cutoff
-                    .max(boundary)
-                    .max(last_repartition_lsn)
-                    .max(self.initdb_lsn)
-                    .max(self.ancestor_lsn),
-                None => self.get_last_record_lsn(),
-            };
-            if lsn <= self.initdb_lsn || lsn <= self.ancestor_lsn {
-                // Do not attempt to create image layers below the initdb or ancestor LSN -- no data below it
-                ("l0_l1_boundary", self.get_last_record_lsn())
-            } else {
-                ("l0_l1_boundary", lsn)
-            }
-        } else {
-            ("latest_record", self.get_last_record_lsn())
-        };
 
         // 2. Repartition and create image layers if necessary
         match self
             .repartition(
-                partition_lsn,
+                self.get_last_record_lsn(),
                 self.get_compaction_target_size(),
                 options.flags,
                 ctx,
@@ -1345,19 +1301,18 @@ impl Timeline {
                     .extend(sparse_partitioning.into_dense().parts);
 
                 // 3. Create new image layers for partitions that have been modified "enough".
-                let mode = if options
-                    .flags
-                    .contains(CompactFlags::ForceImageLayerCreation)
-                {
-                    ImageLayerCreationMode::Force
-                } else {
-                    ImageLayerCreationMode::Try
-                };
                 let (image_layers, outcome) = self
                     .create_image_layers(
                         &partitioning,
                         lsn,
-                        mode,
+                        if options
+                            .flags
+                            .contains(CompactFlags::ForceImageLayerCreation)
+                        {
+                            ImageLayerCreationMode::Force
+                        } else {
+                            ImageLayerCreationMode::Try
+                        },
                         &image_ctx,
                         self.last_image_layer_creation_status
                             .load()
@@ -1365,7 +1320,6 @@ impl Timeline {
                             .clone(),
                         options.flags.contains(CompactFlags::YieldForL0),
                     )
-                    .instrument(info_span!("create_image_layers", mode = %mode, partition_mode = %partition_mode, lsn = %lsn))
                     .await
                     .inspect_err(|err| {
                         if let CreateImageLayersError::GetVectoredError(
@@ -1390,8 +1344,7 @@ impl Timeline {
             }
 
             Ok(_) => {
-                // This happens very frequently so we don't want to log it.
-                debug!("skipping repartitioning due to image compaction LSN being below GC cutoff");
+                info!("skipping repartitioning due to image compaction LSN being below GC cutoff");
             }
 
             // Suppress errors when cancelled.

pageserver/src/tenant/timeline/delete.rs

@@ -121,7 +121,6 @@ async fn remove_maybe_offloaded_timeline_from_tenant(
     // This observes the locking order between timelines and timelines_offloaded
     let mut timelines = tenant.timelines.lock().unwrap();
     let mut timelines_offloaded = tenant.timelines_offloaded.lock().unwrap();
-    let mut timelines_importing = tenant.timelines_importing.lock().unwrap();
     let offloaded_children_exist = timelines_offloaded
         .iter()
         .any(|(_, entry)| entry.ancestor_timeline_id == Some(timeline.timeline_id()));
@@ -151,12 +150,8 @@ async fn remove_maybe_offloaded_timeline_from_tenant(
                 .expect("timeline that we were deleting was concurrently removed from 'timelines_offloaded' map");
             offloaded_timeline.delete_from_ancestor_with_timelines(&timelines);
         }
-        TimelineOrOffloaded::Importing(importing) => {
-            timelines_importing.remove(&importing.timeline.timeline_id);
-        }
     }
 
-    drop(timelines_importing);
     drop(timelines_offloaded);
     drop(timelines);
 
@@ -208,17 +203,8 @@ impl DeleteTimelineFlow {
         guard.mark_in_progress()?;
 
         // Now that the Timeline is in Stopping state, request all the related tasks to shut down.
-        // TODO(vlad): shut down imported timeline here
-        match &timeline {
-            TimelineOrOffloaded::Timeline(timeline) => {
-                timeline.shutdown(super::ShutdownMode::Hard).await;
-            }
-            TimelineOrOffloaded::Importing(importing) => {
-                importing.shutdown().await;
-            }
-            TimelineOrOffloaded::Offloaded(_offloaded) => {
-                // Nothing to shut down in this case
-            }
+        if let TimelineOrOffloaded::Timeline(timeline) = &timeline {
+            timeline.shutdown(super::ShutdownMode::Hard).await;
         }
 
         tenant.gc_block.before_delete(&timeline.timeline_id());
@@ -403,18 +389,10 @@ impl DeleteTimelineFlow {
             Err(anyhow::anyhow!("failpoint: timeline-delete-before-rm"))?
         });
 
-        match timeline {
-            TimelineOrOffloaded::Timeline(timeline) => {
-                delete_local_timeline_directory(conf, tenant.tenant_shard_id, timeline).await;
-            }
-            TimelineOrOffloaded::Importing(importing) => {
-                delete_local_timeline_directory(conf, tenant.tenant_shard_id, &importing.timeline)
-                    .await;
-            }
-            TimelineOrOffloaded::Offloaded(_offloaded) => {
-                // Offloaded timelines have no local state
-                // TODO: once we persist offloaded information, delete the timeline from there, too
-            }
+        // Offloaded timelines have no local state
+        // TODO: once we persist offloaded information, delete the timeline from there, too
+        if let TimelineOrOffloaded::Timeline(timeline) = timeline {
+            delete_local_timeline_directory(conf, tenant.tenant_shard_id, timeline).await;
         }
 
         fail::fail_point!("timeline-delete-after-rm", |_| {
@@ -473,16 +451,12 @@ pub(super) fn make_timeline_delete_guard(
     // For more context see this discussion: `https://github.com/neondatabase/neon/pull/4552#discussion_r1253437346`
     let timelines = tenant.timelines.lock().unwrap();
     let timelines_offloaded = tenant.timelines_offloaded.lock().unwrap();
-    let timelines_importing = tenant.timelines_importing.lock().unwrap();
 
     let timeline = match timelines.get(&timeline_id) {
         Some(t) => TimelineOrOffloaded::Timeline(Arc::clone(t)),
         None => match timelines_offloaded.get(&timeline_id) {
             Some(t) => TimelineOrOffloaded::Offloaded(Arc::clone(t)),
-            None => match timelines_importing.get(&timeline_id) {
-                Some(t) => TimelineOrOffloaded::Importing(Arc::clone(t)),
-                None => return Err(DeleteTimelineError::NotFound),
-            },
+            None => return Err(DeleteTimelineError::NotFound),
         },
     };
 

pageserver/src/tenant/timeline/import_pgdata.rs

@@ -8,10 +8,8 @@ use tokio::task::JoinHandle;
 use tokio_util::sync::CancellationToken;
 use tracing::info;
 use utils::lsn::Lsn;
-use utils::pausable_failpoint;
-use utils::sync::gate::Gate;
 
-use super::{Timeline, TimelineDeleteProgress};
+use super::Timeline;
 use crate::context::RequestContext;
 use crate::controller_upcall_client::{StorageControllerUpcallApi, StorageControllerUpcallClient};
 use crate::tenant::metadata::TimelineMetadata;
@@ -21,25 +19,14 @@ mod importbucket_client;
 mod importbucket_format;
 pub(crate) mod index_part_format;
 
-pub struct ImportingTimeline {
+pub(crate) struct ImportingTimeline {
     pub import_task_handle: JoinHandle<()>,
-    pub import_task_gate: Gate,
     pub timeline: Arc<Timeline>,
-    pub delete_progress: TimelineDeleteProgress,
-}
-
-impl std::fmt::Debug for ImportingTimeline {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-        write!(f, "ImportingTimeline<{}>", self.timeline.timeline_id)
-    }
 }
 
 impl ImportingTimeline {
-    pub async fn shutdown(&self) {
+    pub(crate) fn shutdown(self) {
         self.import_task_handle.abort();
-        self.import_task_gate.close().await;
-
-        self.timeline.remote_client.shutdown().await;
     }
 }
 
@@ -106,15 +93,6 @@ pub async fn doit(
                 );
             }
 
-            tracing::info!("Import plan executed. Flushing remote changes and notifying storcon");
-
-            timeline
-                .remote_client
-                .schedule_index_upload_for_file_changes()?;
-            timeline.remote_client.wait_completion().await?;
-
-            pausable_failpoint!("import-timeline-pre-success-notify-pausable");
-
             // Communicate that shard is done.
             // Ensure at-least-once delivery of the upcall to storage controller
             // before we mark the task as done and never come here again.
@@ -201,8 +179,8 @@ async fn prepare_import(
         .await;
         match res {
             Ok(_) => break,
-            Err(_err) => {
-                info!("indefinitely waiting for pgdata to finish");
+            Err(err) => {
+                info!(?err, "indefinitely waiting for pgdata to finish");
                 if tokio::time::timeout(std::time::Duration::from_secs(10), cancel.cancelled())
                     .await
                     .is_ok()

pageserver/src/tenant/timeline/import_pgdata/flow.rs

@@ -11,14 +11,25 @@
 //! - => S3 as the source for the PGDATA instead of local filesystem
 //!
 //! TODOs before productionization:
+//! - ChunkProcessingJob size / ImportJob::total_size does not account for sharding.
+//!   => produced image layers likely too small.
 //! - ChunkProcessingJob should cut up an ImportJob to hit exactly target image layer size.
+//! - asserts / unwraps need to be replaced with errors
+//! - don't trust remote objects will be small (=prevent OOMs in those cases)
+//!     - limit all in-memory buffers in size, or download to disk and read from there
+//! - limit task concurrency
+//! - generally play nice with other tenants in the system
+//!   - importbucket is different bucket than main pageserver storage, so, should be fine wrt S3 rate limits
+//!   - but concerns like network bandwidth, local disk write bandwidth, local disk capacity, etc
+//! - integrate with layer eviction system
+//! - audit for Tenant::cancel nor Timeline::cancel responsivity
+//! - audit for Tenant/Timeline gate holding (we spawn tokio tasks during this flow!)
 //!
 //! An incomplete set of TODOs from the Hackathon:
 //! - version-specific CheckPointData (=> pgv abstraction, already exists for regular walingest)
 
 use std::collections::HashSet;
 use std::hash::{Hash, Hasher};
-use std::num::NonZeroUsize;
 use std::ops::Range;
 use std::sync::Arc;
 
@@ -32,7 +43,7 @@ use pageserver_api::key::{
     rel_dir_to_key, rel_size_to_key, relmap_file_key, slru_block_to_key, slru_dir_to_key,
     slru_segment_size_to_key,
 };
-use pageserver_api::keyspace::{ShardedRange, singleton_range};
+use pageserver_api::keyspace::{contiguous_range_len, is_contiguous_range, singleton_range};
 use pageserver_api::models::{ShardImportProgress, ShardImportProgressV1, ShardImportStatus};
 use pageserver_api::reltag::{RelTag, SlruKind};
 use pageserver_api::shard::ShardIdentity;
@@ -89,25 +100,8 @@ async fn run_v1(
         tasks: Vec::default(),
     };
 
-    // Use the job size limit encoded in the progress if we are resuming an import.
-    // This ensures that imports have stable plans even if the pageserver config changes.
-    let import_config = {
-        match &import_progress {
-            Some(progress) => {
-                let base = &timeline.conf.timeline_import_config;
-                TimelineImportConfig {
-                    import_job_soft_size_limit: NonZeroUsize::new(progress.job_soft_size_limit)
-                        .unwrap(),
-                    import_job_concurrency: base.import_job_concurrency,
-                    import_job_checkpoint_threshold: base.import_job_checkpoint_threshold,
-                    import_job_max_byte_range_size: base.import_job_max_byte_range_size,
-                }
-            }
-            None => timeline.conf.timeline_import_config.clone(),
-        }
-    };
-
-    let plan = planner.plan(&import_config).await?;
+    let import_config = &timeline.conf.timeline_import_config;
+    let plan = planner.plan(import_config).await?;
 
     // Hash the plan and compare with the hash of the plan we got back from the storage controller.
     // If the two match, it means that the planning stage had the same output.
@@ -119,28 +113,20 @@ async fn run_v1(
     let plan_hash = hasher.finish();
 
     if let Some(progress) = &import_progress {
+        if plan_hash != progress.import_plan_hash {
+            anyhow::bail!("Import plan does not match storcon metadata");
+        }
+
         // Handle collisions on jobs of unequal length
         if progress.jobs != plan.jobs.len() {
             anyhow::bail!("Import plan job length does not match storcon metadata")
         }
-
-        if plan_hash != progress.import_plan_hash {
-            anyhow::bail!("Import plan does not match storcon metadata");
-        }
     }
 
     pausable_failpoint!("import-timeline-pre-execute-pausable");
 
-    let jobs_count = import_progress.as_ref().map(|p| p.jobs);
     let start_from_job_idx = import_progress.map(|progress| progress.completed);
-
-    tracing::info!(
-        start_from_job_idx=?start_from_job_idx,
-        jobs=?jobs_count,
-        "Executing import plan"
-    );
-
-    plan.execute(timeline, start_from_job_idx, plan_hash, &import_config, ctx)
+    plan.execute(timeline, start_from_job_idx, plan_hash, import_config, ctx)
         .await
 }
 
@@ -164,7 +150,6 @@ impl Planner {
     /// This function is and must remain pure: given the same input, it will generate the same import plan.
     async fn plan(mut self, import_config: &TimelineImportConfig) -> anyhow::Result<Plan> {
         let pgdata_lsn = Lsn(self.control_file.control_file_data().checkPoint).align();
-        anyhow::ensure!(pgdata_lsn.is_valid());
 
         let datadir = PgDataDir::new(&self.storage).await?;
 
@@ -233,36 +218,15 @@ impl Planner {
                 checkpoint_buf,
             )));
 
-        // Sort the tasks by the key ranges they handle.
-        // The plan being generated here needs to be stable across invocations
-        // of this method.
-        self.tasks.sort_by_key(|task| match task {
-            AnyImportTask::SingleKey(key) => (key.key, key.key.next()),
-            AnyImportTask::RelBlocks(rel_blocks) => {
-                (rel_blocks.key_range.start, rel_blocks.key_range.end)
-            }
-            AnyImportTask::SlruBlocks(slru_blocks) => {
-                (slru_blocks.key_range.start, slru_blocks.key_range.end)
-            }
-        });
-
         // Assigns parts of key space to later parallel jobs
-        // Note: The image layers produced here may have gaps, meaning,
-        //       there is not an image for each key in the layer's key range.
-        //       The read path stops traversal at the first image layer, regardless
-        //       of whether a base image has been found for a key or not.
-        //       (Concept of sparse image layers doesn't exist.)
-        //       This behavior is exactly right for the base image layers we're producing here.
-        //       But, since no other place in the code currently produces image layers with gaps,
-        //       it seems noteworthy.
         let mut last_end_key = Key::MIN;
         let mut current_chunk = Vec::new();
         let mut current_chunk_size: usize = 0;
         let mut jobs = Vec::new();
         for task in std::mem::take(&mut self.tasks).into_iter() {
-            let task_size = task.total_size(&self.shard);
-            let projected_chunk_size = current_chunk_size.saturating_add(task_size);
-            if projected_chunk_size > import_config.import_job_soft_size_limit.into() {
+            if current_chunk_size + task.total_size()
+                > import_config.import_job_soft_size_limit.into()
+            {
                 let key_range = last_end_key..task.key_range().start;
                 jobs.push(ChunkProcessingJob::new(
                     key_range.clone(),
@@ -272,7 +236,7 @@ impl Planner {
                 last_end_key = key_range.end;
                 current_chunk_size = 0;
             }
-            current_chunk_size = current_chunk_size.saturating_add(task_size);
+            current_chunk_size += task.total_size();
             current_chunk.push(task);
         }
         jobs.push(ChunkProcessingJob::new(
@@ -442,7 +406,6 @@ impl Plan {
 
         let mut last_completed_job_idx = start_after_job_idx.unwrap_or(0);
         let checkpoint_every: usize = import_config.import_job_checkpoint_threshold.into();
-        let max_byte_range_size: usize = import_config.import_job_max_byte_range_size.into();
 
         // Run import jobs concurrently up to the limit specified by the pageserver configuration.
         // Note that we process completed futures in the oreder of insertion. This will be the
@@ -458,13 +421,11 @@ impl Plan {
 
                     work.push_back(tokio::task::spawn(async move {
                         let _permit = permit;
-                        let res = job.run(job_timeline, max_byte_range_size, &ctx).await;
+                        let res = job.run(job_timeline, &ctx).await;
                         (job_idx, res)
                     }));
                 },
                 maybe_complete_job_idx = work.next() => {
-                    pausable_failpoint!("import-task-complete-pausable");
-
                     match maybe_complete_job_idx {
                         Some(Ok((job_idx, res))) => {
                             assert!(last_completed_job_idx.checked_add(1).unwrap() == job_idx);
@@ -473,18 +434,12 @@ impl Plan {
                             last_completed_job_idx = job_idx;
 
                             if last_completed_job_idx % checkpoint_every == 0 {
-                                tracing::info!(last_completed_job_idx, jobs=%jobs_in_plan, "Checkpointing import status");
-
                                 let progress = ShardImportProgressV1 {
                                     jobs: jobs_in_plan,
                                     completed: last_completed_job_idx,
                                     import_plan_hash,
-                                    job_soft_size_limit: import_config.import_job_soft_size_limit.into(),
                                 };
 
-                                timeline.remote_client.schedule_index_upload_for_file_changes()?;
-                                timeline.remote_client.wait_completion().await?;
-
                                 storcon_client.put_timeline_import_status(
                                     timeline.tenant_shard_id,
                                     timeline.timeline_id,
@@ -613,18 +568,18 @@ impl PgDataDirDb {
                 };
 
                 let path = datadir_path.join(rel_tag.to_segfile_name(segno));
-                anyhow::ensure!(filesize % BLCKSZ as usize == 0);
+                assert!(filesize % BLCKSZ as usize == 0); // TODO: this should result in an error
                 let nblocks = filesize / BLCKSZ as usize;
 
-                Ok(PgDataDirDbFile {
+                PgDataDirDbFile {
                     path,
                     filesize,
                     rel_tag,
                     segno,
                     nblocks: Some(nblocks), // first non-cummulative sizes
-                })
+                }
             })
-            .collect::<anyhow::Result<_, _>>()?;
+            .collect();
 
         // Set cummulative sizes. Do all of that math here, so that later we could easier
         // parallelize over segments and know with which segments we need to write relsize
@@ -659,29 +614,18 @@ impl PgDataDirDb {
 trait ImportTask {
     fn key_range(&self) -> Range<Key>;
 
-    fn total_size(&self, shard_identity: &ShardIdentity) -> usize {
-        let range = ShardedRange::new(self.key_range(), shard_identity);
-        let page_count = range.page_count();
-        if page_count == u32::MAX {
-            tracing::warn!(
-                "Import task has non contiguous key range: {}..{}",
-                self.key_range().start,
-                self.key_range().end
-            );
-
-            // Tasks should operate on contiguous ranges. It is unexpected for
-            // ranges to violate this assumption. Calling code handles this by mapping
-            // any task on a non contiguous range to its own image layer.
-            usize::MAX
+    fn total_size(&self) -> usize {
+        // TODO: revisit this
+        if is_contiguous_range(&self.key_range()) {
+            contiguous_range_len(&self.key_range()) as usize * 8192
         } else {
-            page_count as usize * 8192
+            u32::MAX as usize
         }
     }
 
     async fn doit(
         self,
         layer_writer: &mut ImageLayerWriter,
-        max_byte_range_size: usize,
         ctx: &RequestContext,
     ) -> anyhow::Result<usize>;
 }
@@ -696,11 +640,7 @@ impl Hash for ImportSingleKeyTask {
         let ImportSingleKeyTask { key, buf } = self;
 
         key.hash(state);
-        // The key value might not have a stable binary representation.
-        // For instance, the db directory uses an unstable hash-map.
-        // To work around this we are a bit lax here and only hash the
-        // size of the buffer which must be consistent.
-        buf.len().hash(state);
+        buf.hash(state);
     }
 }
 
@@ -718,7 +658,6 @@ impl ImportTask for ImportSingleKeyTask {
     async fn doit(
         self,
         layer_writer: &mut ImageLayerWriter,
-        _max_byte_range_size: usize,
         ctx: &RequestContext,
     ) -> anyhow::Result<usize> {
         layer_writer.put_image(self.key, self.buf, ctx).await?;
@@ -772,7 +711,6 @@ impl ImportTask for ImportRelBlocksTask {
     async fn doit(
         self,
         layer_writer: &mut ImageLayerWriter,
-        max_byte_range_size: usize,
         ctx: &RequestContext,
     ) -> anyhow::Result<usize> {
         debug!("Importing relation file");
@@ -799,7 +737,7 @@ impl ImportTask for ImportRelBlocksTask {
                 assert_eq!(key.len(), 1);
                 assert!(!acc.is_empty());
                 assert!(acc_end > acc_start);
-                if acc_end == start && end - acc_start <= max_byte_range_size {
+                if acc_end == start /* TODO additional max range check here, to limit memory consumption per task to X */ {
                     acc.push(key.pop().unwrap());
                     Ok((acc, acc_start, end))
                 } else {
@@ -814,8 +752,8 @@ impl ImportTask for ImportRelBlocksTask {
                 .get_range(&self.path, range_start.into_u64(), range_end.into_u64())
                 .await?;
             let mut buf = Bytes::from(range_buf);
+            // TODO: batched writes
             for key in keys {
-                // The writer buffers writes internally
                 let image = buf.split_to(8192);
                 layer_writer.put_image(key, image, ctx).await?;
                 nimages += 1;
@@ -863,15 +801,11 @@ impl ImportTask for ImportSlruBlocksTask {
     async fn doit(
         self,
         layer_writer: &mut ImageLayerWriter,
-        _max_byte_range_size: usize,
         ctx: &RequestContext,
     ) -> anyhow::Result<usize> {
         debug!("Importing SLRU segment file {}", self.path);
         let buf = self.storage.get(&self.path).await?;
 
-        // TODO(vlad): Does timestamp to LSN work for imported timelines?
-        // Probably not since we don't append the `xact_time` to it as in
-        // [`WalIngest::ingest_xact_record`].
         let (kind, segno, start_blk) = self.key_range.start.to_slru_block()?;
         let (_kind, _segno, end_blk) = self.key_range.end.to_slru_block()?;
         let mut blknum = start_blk;
@@ -910,13 +844,12 @@ impl ImportTask for AnyImportTask {
     async fn doit(
         self,
         layer_writer: &mut ImageLayerWriter,
-        max_byte_range_size: usize,
         ctx: &RequestContext,
     ) -> anyhow::Result<usize> {
         match self {
-            Self::SingleKey(t) => t.doit(layer_writer, max_byte_range_size, ctx).await,
-            Self::RelBlocks(t) => t.doit(layer_writer, max_byte_range_size, ctx).await,
-            Self::SlruBlocks(t) => t.doit(layer_writer, max_byte_range_size, ctx).await,
+            Self::SingleKey(t) => t.doit(layer_writer, ctx).await,
+            Self::RelBlocks(t) => t.doit(layer_writer, ctx).await,
+            Self::SlruBlocks(t) => t.doit(layer_writer, ctx).await,
         }
     }
 }
@@ -957,12 +890,7 @@ impl ChunkProcessingJob {
         }
     }
 
-    async fn run(
-        self,
-        timeline: Arc<Timeline>,
-        max_byte_range_size: usize,
-        ctx: &RequestContext,
-    ) -> anyhow::Result<()> {
+    async fn run(self, timeline: Arc<Timeline>, ctx: &RequestContext) -> anyhow::Result<()> {
         let mut writer = ImageLayerWriter::new(
             timeline.conf,
             timeline.timeline_id,
@@ -977,7 +905,7 @@ impl ChunkProcessingJob {
 
         let mut nimages = 0;
         for task in self.tasks {
-            nimages += task.doit(&mut writer, max_byte_range_size, ctx).await?;
+            nimages += task.doit(&mut writer, ctx).await?;
         }
 
         let resident_layer = if nimages > 0 {
@@ -987,7 +915,7 @@ impl ChunkProcessingJob {
                 let guard = timeline.layers.read().await;
                 let existing_layer = guard.try_get_from_key(&desc.key());
                 if let Some(layer) = existing_layer {
-                    if layer.metadata().generation == timeline.generation {
+                    if layer.metadata().generation != timeline.generation {
                         return Err(anyhow::anyhow!(
                             "Import attempted to rewrite layer file in the same generation: {}",
                             layer.local_path()
@@ -1014,15 +942,6 @@ impl ChunkProcessingJob {
             .cloned();
         match existing_layer {
             Some(existing) => {
-                // Unlink the remote layer from the index without scheduling its deletion.
-                // When `existing_layer` drops [`LayerInner::drop`] will schedule its deletion from
-                // remote storage, but that assumes that the layer was unlinked from the index first.
-                timeline
-                    .remote_client
-                    .schedule_unlinking_of_layers_from_index_part(std::iter::once(
-                        existing.layer_desc().layer_name(),
-                    ))?;
-
                 guard.open_mut()?.rewrite_layers(
                     &[(existing.clone(), resident_layer.clone())],
                     &[],

pageserver/src/tenant/timeline/import_pgdata/importbucket_client.rs

@@ -6,7 +6,7 @@ use bytes::Bytes;
 use postgres_ffi::ControlFileData;
 use remote_storage::{
     Download, DownloadError, DownloadKind, DownloadOpts, GenericRemoteStorage, Listing,
-    ListingObject, RemotePath, RemoteStorageConfig,
+    ListingObject, RemotePath,
 };
 use serde::de::DeserializeOwned;
 use tokio_util::sync::CancellationToken;
@@ -22,9 +22,11 @@ pub async fn new(
     location: &index_part_format::Location,
     cancel: CancellationToken,
 ) -> Result<RemoteStorageWrapper, anyhow::Error> {
-    // Downloads should be reasonably sized. We do ranged reads for relblock raw data
-    // and full reads for SLRU segments which are bounded by Postgres.
-    let timeout = RemoteStorageConfig::DEFAULT_TIMEOUT;
+    // FIXME: we probably want some timeout, and we might be able to assume the max file
+    // size on S3 is 1GiB (postgres segment size). But the problem is that the individual
+    // downloaders don't know enough about concurrent downloads to make a guess on the
+    // expected bandwidth and resulting best timeout.
+    let timeout = std::time::Duration::from_secs(24 * 60 * 60);
     let location_storage = match location {
         #[cfg(feature = "testing")]
         index_part_format::Location::LocalFs { path } => {
@@ -48,12 +50,9 @@ pub async fn new(
                             .import_pgdata_aws_endpoint_url
                             .clone()
                             .map(|url| url.to_string()), //  by specifying None here, remote_storage/aws-sdk-rust will infer from env
-                        // This matches the default import job concurrency. This is managed
-                        // separately from the usual S3 client, but the concern here is bandwidth
-                        // usage.
-                        concurrency_limit: 128.try_into().unwrap(),
-                        max_keys_per_list_response: Some(1000),
-                        upload_storage_class: None, // irrelevant
+                        concurrency_limit: 100.try_into().unwrap(), // TODO: think about this
+                        max_keys_per_list_response: Some(1000),     // TODO: think about this
+                        upload_storage_class: None,                 // irrelevant
                     },
                     timeout,
                 )

pageserver/src/tenant/timeline/walreceiver.rs

@@ -113,7 +113,7 @@ impl WalReceiver {
                 }
                 connection_manager_state.shutdown().await;
                 *loop_status.write().unwrap() = None;
-                info!("task exits");
+                debug!("task exits");
             }
             .instrument(info_span!(parent: None, "wal_connection_manager", tenant_id = %tenant_shard_id.tenant_id, shard_id = %tenant_shard_id.shard_slug(), timeline_id = %timeline_id))
         });

pageserver/src/tenant/timeline/walreceiver/connection_manager.rs

@@ -32,7 +32,9 @@ use utils::backoff::{
 };
 use utils::id::{NodeId, TenantTimelineId};
 use utils::lsn::Lsn;
-use utils::postgres_client::{ConnectionConfigArgs, wal_stream_connection_config};
+use utils::postgres_client::{
+    ConnectionConfigArgs, PostgresClientProtocol, wal_stream_connection_config,
+};
 
 use super::walreceiver_connection::{WalConnectionStatus, WalReceiverError};
 use super::{TaskEvent, TaskHandle, TaskStateUpdate, WalReceiverConf};
@@ -989,12 +991,19 @@ impl ConnectionManagerState {
                     return None; // no connection string, ignore sk
                 }
 
-                let shard_identity = self.timeline.get_shard_identity();
-                let (shard_number, shard_count, shard_stripe_size) = (
-                    Some(shard_identity.number.0),
-                    Some(shard_identity.count.0),
-                    Some(shard_identity.stripe_size.0),
-                );
+                let (shard_number, shard_count, shard_stripe_size) = match self.conf.protocol {
+                    PostgresClientProtocol::Vanilla => {
+                        (None, None, None)
+                    },
+                    PostgresClientProtocol::Interpreted { .. } => {
+                        let shard_identity = self.timeline.get_shard_identity();
+                        (
+                            Some(shard_identity.number.0),
+                            Some(shard_identity.count.0),
+                            Some(shard_identity.stripe_size.0),
+                        )
+                    }
+                };
 
                 let connection_conf_args = ConnectionConfigArgs {
                     protocol: self.conf.protocol,
@@ -1111,8 +1120,8 @@ impl ReconnectReason {
 
 #[cfg(test)]
 mod tests {
+    use pageserver_api::config::defaults::DEFAULT_WAL_RECEIVER_PROTOCOL;
     use url::Host;
-    use utils::postgres_client::PostgresClientProtocol;
 
     use super::*;
     use crate::tenant::harness::{TIMELINE_ID, TenantHarness};
@@ -1543,11 +1552,6 @@ mod tests {
             .await
             .expect("Failed to create an empty timeline for dummy wal connection manager");
 
-        let protocol = PostgresClientProtocol::Interpreted {
-            format: utils::postgres_client::InterpretedFormat::Protobuf,
-            compression: Some(utils::postgres_client::Compression::Zstd { level: 1 }),
-        };
-
         ConnectionManagerState {
             id: TenantTimelineId {
                 tenant_id: harness.tenant_shard_id.tenant_id,
@@ -1556,7 +1560,7 @@ mod tests {
             timeline,
             cancel: CancellationToken::new(),
             conf: WalReceiverConf {
-                protocol,
+                protocol: DEFAULT_WAL_RECEIVER_PROTOCOL,
                 wal_connect_timeout: Duration::from_secs(1),
                 lagging_wal_timeout: Duration::from_secs(1),
                 max_lsn_wal_lag: NonZeroU64::new(1024 * 1024).unwrap(),

pageserver/src/tenant/timeline/walreceiver/walreceiver_connection.rs

@@ -15,7 +15,7 @@ use postgres_backend::is_expected_io_error;
 use postgres_connection::PgConnectionConfig;
 use postgres_ffi::WAL_SEGMENT_SIZE;
 use postgres_ffi::v14::xlog_utils::normalize_lsn;
-use postgres_ffi::waldecoder::WalDecodeError;
+use postgres_ffi::waldecoder::{WalDecodeError, WalStreamDecoder};
 use postgres_protocol::message::backend::ReplicationMessage;
 use postgres_types::PgLsn;
 use tokio::sync::watch;
@@ -31,7 +31,7 @@ use utils::lsn::Lsn;
 use utils::pageserver_feedback::PageserverFeedback;
 use utils::postgres_client::PostgresClientProtocol;
 use utils::sync::gate::GateError;
-use wal_decoder::models::{FlushUncommittedRecords, InterpretedWalRecords};
+use wal_decoder::models::{FlushUncommittedRecords, InterpretedWalRecord, InterpretedWalRecords};
 use wal_decoder::wire_format::FromWireFormat;
 
 use super::TaskStateUpdate;
@@ -275,6 +275,8 @@ pub(super) async fn handle_walreceiver_connection(
     let copy_stream = replication_client.copy_both_simple(&query).await?;
     let mut physical_stream = pin!(ReplicationStream::new(copy_stream));
 
+    let mut waldecoder = WalStreamDecoder::new(startpoint, timeline.pg_version);
+
     let mut walingest = WalIngest::new(timeline.as_ref(), startpoint, &ctx)
         .await
         .map_err(|e| match e.kind {
@@ -282,22 +284,19 @@ pub(super) async fn handle_walreceiver_connection(
             _ => WalReceiverError::Other(e.into()),
         })?;
 
-    let (format, compression) = match protocol {
+    let shard = vec![*timeline.get_shard_identity()];
+
+    let interpreted_proto_config = match protocol {
+        PostgresClientProtocol::Vanilla => None,
         PostgresClientProtocol::Interpreted {
             format,
             compression,
-        } => (format, compression),
-        PostgresClientProtocol::Vanilla => {
-            return Err(WalReceiverError::Other(anyhow!(
-                "Vanilla WAL receiver protocol is no longer supported for ingest"
-            )));
-        }
+        } => Some((format, compression)),
     };
 
     let mut expected_wal_start = startpoint;
     while let Some(replication_message) = {
         select! {
-            biased;
             _ = cancellation.cancelled() => {
                 debug!("walreceiver interrupted");
                 None
@@ -313,6 +312,16 @@ pub(super) async fn handle_walreceiver_connection(
         // Update the connection status before processing the message. If the message processing
         // fails (e.g. in walingest), we still want to know latests LSNs from the safekeeper.
         match &replication_message {
+            ReplicationMessage::XLogData(xlog_data) => {
+                connection_status.latest_connection_update = now;
+                connection_status.commit_lsn = Some(Lsn::from(xlog_data.wal_end()));
+                connection_status.streaming_lsn = Some(Lsn::from(
+                    xlog_data.wal_start() + xlog_data.data().len() as u64,
+                ));
+                if !xlog_data.data().is_empty() {
+                    connection_status.latest_wal_update = now;
+                }
+            }
             ReplicationMessage::PrimaryKeepAlive(keepalive) => {
                 connection_status.latest_connection_update = now;
                 connection_status.commit_lsn = Some(Lsn::from(keepalive.wal_end()));
@@ -343,6 +352,7 @@ pub(super) async fn handle_walreceiver_connection(
                 // were interpreted.
                 let streaming_lsn = Lsn::from(raw.streaming_lsn());
 
+                let (format, compression) = interpreted_proto_config.unwrap();
                 let batch = InterpretedWalRecords::from_wire(raw.data(), format, compression)
                     .await
                     .with_context(|| {
@@ -498,6 +508,138 @@ pub(super) async fn handle_walreceiver_connection(
                 Some(streaming_lsn)
             }
 
+            ReplicationMessage::XLogData(xlog_data) => {
+                async fn commit(
+                    modification: &mut DatadirModification<'_>,
+                    uncommitted: &mut u64,
+                    filtered: &mut u64,
+                    ctx: &RequestContext,
+                ) -> anyhow::Result<()> {
+                    let stats = modification.stats();
+                    modification.commit(ctx).await?;
+                    WAL_INGEST
+                        .records_committed
+                        .inc_by(*uncommitted - *filtered);
+                    WAL_INGEST.inc_values_committed(&stats);
+                    *uncommitted = 0;
+                    *filtered = 0;
+                    Ok(())
+                }
+
+                // Pass the WAL data to the decoder, and see if we can decode
+                // more records as a result.
+                let data = xlog_data.data();
+                let startlsn = Lsn::from(xlog_data.wal_start());
+                let endlsn = startlsn + data.len() as u64;
+
+                trace!("received XLogData between {startlsn} and {endlsn}");
+
+                WAL_INGEST.bytes_received.inc_by(data.len() as u64);
+                waldecoder.feed_bytes(data);
+
+                {
+                    let mut modification = timeline.begin_modification(startlsn);
+                    let mut uncommitted_records = 0;
+                    let mut filtered_records = 0;
+
+                    while let Some((next_record_lsn, recdata)) = waldecoder.poll_decode()? {
+                        // It is important to deal with the aligned records as lsn in getPage@LSN is
+                        // aligned and can be several bytes bigger. Without this alignment we are
+                        // at risk of hitting a deadlock.
+                        if !next_record_lsn.is_aligned() {
+                            return Err(WalReceiverError::Other(anyhow!("LSN not aligned")));
+                        }
+
+                        // Deserialize and interpret WAL record
+                        let interpreted = InterpretedWalRecord::from_bytes_filtered(
+                            recdata,
+                            &shard,
+                            next_record_lsn,
+                            modification.tline.pg_version,
+                        )?
+                        .remove(timeline.get_shard_identity())
+                        .unwrap();
+
+                        if matches!(interpreted.flush_uncommitted, FlushUncommittedRecords::Yes)
+                            && uncommitted_records > 0
+                        {
+                            // Special case: legacy PG database creations operate by reading pages from a 'template' database:
+                            // these are the only kinds of WAL record that require reading data blocks while ingesting.  Ensure
+                            // all earlier writes of data blocks are visible by committing any modification in flight.
+                            commit(
+                                &mut modification,
+                                &mut uncommitted_records,
+                                &mut filtered_records,
+                                &ctx,
+                            )
+                            .await?;
+                        }
+
+                        // Ingest the records without immediately committing them.
+                        timeline.metrics.wal_records_received.inc();
+                        let ingested = walingest
+                            .ingest_record(interpreted, &mut modification, &ctx)
+                            .await
+                            .with_context(|| {
+                                format!("could not ingest record at {next_record_lsn}")
+                            })
+                            .inspect_err(|err| {
+                                // TODO: we can't differentiate cancellation errors with
+                                // anyhow::Error, so just ignore it if we're cancelled.
+                                if !cancellation.is_cancelled() && !timeline.is_stopping() {
+                                    critical!("{err:?}")
+                                }
+                            })?;
+                        if !ingested {
+                            tracing::debug!("ingest: filtered out record @ LSN {next_record_lsn}");
+                            WAL_INGEST.records_filtered.inc();
+                            filtered_records += 1;
+                        }
+
+                        // FIXME: this cannot be made pausable_failpoint without fixing the
+                        // failpoint library; in tests, the added amount of debugging will cause us
+                        // to timeout the tests.
+                        fail_point!("walreceiver-after-ingest");
+
+                        last_rec_lsn = next_record_lsn;
+
+                        // Commit every ingest_batch_size records. Even if we filtered out
+                        // all records, we still need to call commit to advance the LSN.
+                        uncommitted_records += 1;
+                        if uncommitted_records >= ingest_batch_size
+                            || modification.approx_pending_bytes()
+                                > DatadirModification::MAX_PENDING_BYTES
+                        {
+                            commit(
+                                &mut modification,
+                                &mut uncommitted_records,
+                                &mut filtered_records,
+                                &ctx,
+                            )
+                            .await?;
+                        }
+                    }
+
+                    // Commit the remaining records.
+                    if uncommitted_records > 0 {
+                        commit(
+                            &mut modification,
+                            &mut uncommitted_records,
+                            &mut filtered_records,
+                            &ctx,
+                        )
+                        .await?;
+                    }
+                }
+
+                if !caught_up && endlsn >= end_of_wal {
+                    info!("caught up at LSN {endlsn}");
+                    caught_up = true;
+                }
+
+                Some(endlsn)
+            }
+
             ReplicationMessage::PrimaryKeepAlive(keepalive) => {
                 let wal_end = keepalive.wal_end();
                 let timestamp = keepalive.timestamp();

pgxn/neon/Makefile

@@ -1,5 +1,6 @@
 # pgxs/neon/Makefile
 
+
 MODULE_big = neon
 OBJS = \
 	$(WIN32RES) \
@@ -21,8 +22,7 @@ OBJS = \
 	walproposer.o \
 	walproposer_pg.o \
 	control_plane_connector.o \
-	walsender_hooks.o \
-	$(LIBCOMMUNICATOR_PATH)/libcommunicator.a
+	walsender_hooks.o
 
 PG_CPPFLAGS = -I$(libpq_srcdir)
 SHLIB_LINK_INTERNAL = $(libpq)

pgxn/neon/communicator/Cargo.toml

@@ -1,13 +0,0 @@
-[package]
-name = "communicator"
-version = "0.1.0"
-edition = "2024"
-
-[lib]
-crate-type = ["staticlib"]
-
-[dependencies]
-neon-shmem.workspace = true
-
-[build-dependencies]
-cbindgen.workspace = true

pgxn/neon/communicator/README.md

@@ -1,8 +0,0 @@
-This package will evolve into a "compute-pageserver communicator"
-process and machinery. For now, it just provides wrappers on the
-neon-shmem Rust crate, to allow using it in the C implementation of
-the LFC.
-
-At compilation time, pgxn/neon/communicator/ produces a static
-library, libcommunicator.a. It is linked to the neon.so extension
-library. 

pgxn/neon/communicator/build.rs

@@ -1,22 +0,0 @@
-use std::env;
-
-fn main() -> Result<(), Box<dyn std::error::Error>> {
-    let crate_dir = env::var("CARGO_MANIFEST_DIR").unwrap();
-
-    cbindgen::generate(crate_dir).map_or_else(
-        |error| match error {
-            cbindgen::Error::ParseSyntaxError { .. } => {
-                // This means there was a syntax error in the Rust sources. Don't panic, because
-                // we want the build to continue and the Rust compiler to hit the error. The
-                // Rust compiler produces a better error message than cbindgen.
-                eprintln!("Generating C bindings failed because of a Rust syntax error");
-            }
-            e => panic!("Unable to generate C bindings: {:?}", e),
-        },
-        |bindings| {
-            bindings.write_to_file("communicator_bindings.h");
-        },
-    );
-
-    Ok(())
-}

pgxn/neon/communicator/cbindgen.toml

@@ -1,4 +0,0 @@
-language = "C"
-
-[enum]
-prefix_with_name = true

pgxn/neon/communicator/src/file_cache_hashmap.rs

@@ -1,240 +0,0 @@
-//! Glue code to allow using the Rust shmem hash map implementation from C code
-//!
-//! For convience of adapting existing code, the interface provided somewhat resembles the dynahash
-//! interface.
-//!
-//! NOTE: The caller is responsible for locking! The caller is expected to hold the PostgreSQL
-//! LWLock, 'lfc_lock', while accessing the hash table, in shared or exclusive mode as appropriate.
-
-use std::ffi::c_void;
-use std::marker::PhantomData;
-
-use neon_shmem::hash::entry::Entry;
-use neon_shmem::hash::{HashMapAccess, HashMapInit};
-use neon_shmem::shmem::ShmemHandle;
-
-/// NB: This must match the definition of BufferTag in Postgres C headers. We could use bindgen to
-/// generate this from the C headers, but prefer to not introduce dependency on bindgen for now.
-///
-/// Note that there are no padding bytes. If the corresponding C struct has padding bytes, the C C
-/// code must clear them.
-#[derive(Clone, Debug, Hash, Eq, PartialEq)]
-#[repr(C)]
-pub struct FileCacheKey {
-    pub _spc_id: u32,
-    pub _db_id: u32,
-    pub _rel_number: u32,
-    pub _fork_num: u32,
-    pub _block_num: u32,
-}
-
-/// Like with FileCacheKey, this must match the definition of FileCacheEntry in file_cache.c.  We
-/// don't look at the contents here though, it's sufficent that the size and alignment matches.
-#[derive(Clone, Debug, Default)]
-#[repr(C)]
-pub struct FileCacheEntry {
-    pub _offset: u32,
-    pub _access_count: u32,
-    pub _prev: *mut FileCacheEntry,
-    pub _next: *mut FileCacheEntry,
-    pub _state: [u32; 8],
-}
-
-/// XXX: This could be just:
-///
-/// ```ignore
-/// type FileCacheHashMapHandle = HashMapInit<'a, FileCacheKey, FileCacheEntry>
-/// ```
-///
-/// but with that, cbindgen generates a broken typedef in the C header file which doesn't
-/// compile. It apparently gets confused by the generics.
-#[repr(transparent)]
-pub struct FileCacheHashMapHandle<'a>(
-    pub *mut c_void,
-    PhantomData<HashMapInit<'a, FileCacheKey, FileCacheEntry>>,
-);
-impl<'a> From<Box<HashMapInit<'a, FileCacheKey, FileCacheEntry>>> for FileCacheHashMapHandle<'a> {
-    fn from(x: Box<HashMapInit<'a, FileCacheKey, FileCacheEntry>>) -> Self {
-        FileCacheHashMapHandle(Box::into_raw(x) as *mut c_void, PhantomData::default())
-    }
-}
-impl<'a> From<FileCacheHashMapHandle<'a>> for Box<HashMapInit<'a, FileCacheKey, FileCacheEntry>> {
-    fn from(x: FileCacheHashMapHandle) -> Self {
-        unsafe { Box::from_raw(x.0.cast()) }
-    }
-}
-
-/// XXX: same for this
-#[repr(transparent)]
-pub struct FileCacheHashMapAccess<'a>(
-    pub *mut c_void,
-    PhantomData<HashMapAccess<'a, FileCacheKey, FileCacheEntry>>,
-);
-impl<'a> From<Box<HashMapAccess<'a, FileCacheKey, FileCacheEntry>>> for FileCacheHashMapAccess<'a> {
-    fn from(x: Box<HashMapAccess<'a, FileCacheKey, FileCacheEntry>>) -> Self {
-        // Convert the Box into a raw mutable pointer to the HashMapAccess itself.
-        // This transfers ownership of the HashMapAccess (and its contained ShmemHandle)
-        // to the raw pointer. The C caller is now responsible for managing this memory.
-        FileCacheHashMapAccess(Box::into_raw(x) as *mut c_void, PhantomData::default())
-    }
-}
-impl<'a> FileCacheHashMapAccess<'a> {
-    fn as_ref(self) -> &'a HashMapAccess<'a, FileCacheKey, FileCacheEntry> {
-        let ptr: *mut HashMapAccess<'_, FileCacheKey, FileCacheEntry> = self.0.cast();
-        unsafe { ptr.as_ref().unwrap() }
-    }
-    fn as_mut(self) -> &'a mut HashMapAccess<'a, FileCacheKey, FileCacheEntry> {
-        let ptr: *mut HashMapAccess<'_, FileCacheKey, FileCacheEntry> = self.0.cast();
-        unsafe { ptr.as_mut().unwrap() }
-    }
-}
-
-/// Initialize the shared memory area at postmaster startup. The returned handle is inherited
-/// by all the backend processes across fork()
-#[unsafe(no_mangle)]
-pub extern "C" fn bcomm_file_cache_shmem_init<'a>(
-    initial_num_buckets: u32,
-    max_num_buckets: u32,
-) -> FileCacheHashMapHandle<'a> {
-    let max_bytes = HashMapInit::<FileCacheKey, FileCacheEntry>::estimate_size(max_num_buckets);
-    let shmem_handle =
-        ShmemHandle::new("lfc mapping", 0, max_bytes).expect("shmem initialization failed");
-
-    let handle = HashMapInit::<FileCacheKey, FileCacheEntry>::init_in_shmem(
-        initial_num_buckets,
-        shmem_handle,
-    );
-
-    Box::new(handle).into()
-}
-
-/// Initialize the access to the shared memory area in a backend process.
-///
-/// XXX: I'm not sure if this actually gets called in each process, or if the returned struct
-/// is also inherited across fork(). It currently works either way but if this did more
-/// initialization that needed to be done after fork(), then it would matter.
-#[unsafe(no_mangle)]
-pub extern "C" fn bcomm_file_cache_shmem_access<'a>(
-    handle: FileCacheHashMapHandle<'a>,
-) -> FileCacheHashMapAccess<'a> {
-    let handle: Box<HashMapInit<'_, FileCacheKey, FileCacheEntry>> = handle.into();
-    Box::new(handle.attach_writer()).into()
-}
-
-/// Return the current number of buckets in the hash table
-#[unsafe(no_mangle)]
-pub extern "C" fn bcomm_file_cache_get_num_buckets<'a>(
-    map: FileCacheHashMapAccess<'static>,
-) -> u32 {
-    let map = map.as_ref();
-    map.get_num_buckets().try_into().unwrap()
-}
-
-/// Look up the entry with given key and hash.
-///
-/// This is similar to dynahash's hash_search(... , HASH_FIND)
-#[unsafe(no_mangle)]
-pub extern "C" fn bcomm_file_cache_hash_find<'a>(
-    map: FileCacheHashMapAccess<'static>,
-    key: &FileCacheKey,
-    hash: u64,
-) -> Option<&'static FileCacheEntry> {
-    let map = map.as_ref();
-    map.get_with_hash(key, hash)
-}
-
-/// Look up the entry at given bucket position
-///
-/// This has no direct equivalent in the dynahash interface, but can be used to
-/// iterate through all entries in the hash table.
-#[unsafe(no_mangle)]
-pub extern "C" fn bcomm_file_cache_hash_get_at_pos<'a>(
-    map: FileCacheHashMapAccess<'static>,
-    pos: u32,
-) -> Option<&'static FileCacheEntry> {
-    let map = map.as_ref();
-    map.get_at_bucket(pos as usize).map(|(_k, v)| v)
-}
-
-/// Remove entry, given a pointer to the value.
-///
-/// This is equivalent to dynahash hash_search(entry->key, HASH_REMOVE), where 'entry'
-/// is an entry you have previously looked up
-#[unsafe(no_mangle)]
-pub extern "C" fn bcomm_file_cache_hash_remove_entry<'a, 'b>(
-    map: FileCacheHashMapAccess,
-    entry: *mut FileCacheEntry,
-) {
-    let map = map.as_mut();
-    let pos = map.get_bucket_for_value(entry);
-    match map.entry_at_bucket(pos) {
-        Some(e) => {
-            e.remove();
-        }
-        None => {
-            // todo: shouldn't happen, panic?
-        }
-    }
-}
-
-/// Compute the hash for given key
-///
-/// This is equivalent to dynahash get_hash_value() function. We use Rust's default hasher
-/// for calculating the hash though.
-#[unsafe(no_mangle)]
-pub extern "C" fn bcomm_file_cache_get_hash_value<'a, 'b>(
-    map: FileCacheHashMapAccess<'static>,
-    key: &FileCacheKey,
-) -> u64 {
-    map.as_ref().get_hash_value(key)
-}
-
-/// Insert a new entry to the hash table
-///
-/// This is equivalent to dynahash hash_search(..., HASH_ENTER).
-#[unsafe(no_mangle)]
-pub extern "C" fn bcomm_file_cache_hash_enter<'a, 'b>(
-    map: FileCacheHashMapAccess,
-    key: &FileCacheKey,
-    hash: u64,
-    found: &mut bool,
-) -> *mut FileCacheEntry {
-    match map.as_mut().entry_with_hash(key.clone(), hash) {
-        Entry::Occupied(mut e) => {
-            *found = true;
-            e.get_mut()
-        }
-        Entry::Vacant(e) => {
-            *found = false;
-            let initial_value = FileCacheEntry::default();
-            e.insert(initial_value).expect("TODO: hash table full")
-        }
-    }
-}
-
-/// Get the key for a given entry, which must be present in the hash table.
-///
-/// Dynahash requires the key to be part of the "value" struct, so you can always
-/// access the key with something like `entry->key`. The Rust implementation however
-/// stores the key separately. This function extracts the separately stored key.
-#[unsafe(no_mangle)]
-pub extern "C" fn bcomm_file_cache_hash_get_key_for_entry<'a, 'b>(
-    map: FileCacheHashMapAccess,
-    entry: *const FileCacheEntry,
-) -> Option<&FileCacheKey> {
-    let map = map.as_ref();
-    let pos = map.get_bucket_for_value(entry);
-    map.get_at_bucket(pos as usize).map(|(k, _v)| k)
-}
-
-/// Remove all entries from the hash table
-#[unsafe(no_mangle)]
-pub extern "C" fn bcomm_file_cache_hash_reset<'a, 'b>(map: FileCacheHashMapAccess) {
-    let map = map.as_mut();
-    let num_buckets = map.get_num_buckets();
-    for i in 0..num_buckets {
-        if let Some(e) = map.entry_at_bucket(i) {
-            e.remove();
-        }
-    }
-}

pgxn/neon/communicator/src/lib.rs

@@ -1 +0,0 @@
-pub mod file_cache_hashmap;