confused the files

# Conflicts:
#	.github/actions/neon-project-create/action.yml

.github/actions/neon-project-create/action.yml

@@ -49,6 +49,10 @@ inputs:
     description: 'A JSON object with project settings'
     required: false
     default: '{}'
+  default_endpoint_settings:
+    description: 'A JSON object with the default endpoint settings'
+    required: false
+    default: '{}'
 
 outputs:
   dsn:
@@ -135,6 +139,21 @@ runs:
             -H "Accept: application/json" -H "Content-Type: application/json" -H "Authorization: Bearer ${ADMIN_API_KEY}" \
             -d "{\"scheduling\": \"Essential\"}"
         fi
+        # XXX
+        # This is a workaround for the default endpoint settings, which currently do not allow some settings in the public API.
+        # https://github.com/neondatabase/cloud/issues/27108
+        if [[ -n ${DEFAULT_ENDPOINT_SETTINGS} && ${DEFAULT_ENDPOINT_SETTINGS} != "{}" ]] ; then
+          PROJECT_DATA=$(curl -X GET \
+              "https://${API_HOST}/regions/${REGION_ID}/api/v1/admin/projects/${project_id}" \
+              -H "Accept: application/json" -H "Content-Type: application/json" -H "Authorization: Bearer ${ADMIN_API_KEY}" \
+              -d "{\"scheduling\": \"Essential\"}"
+          )
+          NEW_DEFAULT_ENDPOINT_SETTINGS=$(echo ${PROJECT_DATA} | jq -rc ".project.default_endpoint_settings + ${DEFAULT_ENDPOINT_SETTINGS}")
+          curl -X POST --fail \
+                "https://${API_HOST}/regions/${REGION_ID}/api/v1/admin/projects/${project_id}/default_endpoint_settings" \
+                -H "Accept: application/json" -H "Content-Type: application/json" -H "Authorization: Bearer ${ADMIN_API_KEY}" \
+                --data "${NEW_DEFAULT_ENDPOINT_SETTINGS}"
+        fi
         
 
       env:
@@ -152,3 +171,4 @@ runs:
         PSQL: ${{ inputs.psql_path }}
         LD_LIBRARY_PATH: ${{ inputs.libpq_lib_path }}
         PROJECT_SETTINGS: ${{ inputs.project_settings }}
+        DEFAULT_ENDPOINT_SETTINGS: ${{ inputs.default_endpoint_settings }}

.github/workflows/_build-and-test-locally.yml

@@ -279,14 +279,18 @@ jobs:
           # run all non-pageserver tests
           ${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E '!package(pageserver)'
 
-          # run pageserver tests
-          # (When developing new pageserver features gated by config fields, we commonly make the rust
-          # unit tests sensitive to an environment variable NEON_PAGESERVER_UNIT_TEST_FEATURENAME.
-          # Then run the nextest invocation below for all relevant combinations. Singling out the
-          # pageserver tests from non-pageserver tests cuts down the time it takes for this CI step.)
-          NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IOENGINE=tokio-epoll-uring  \
-          ${cov_prefix} \
-          cargo nextest run $CARGO_FLAGS $CARGO_FEATURES  -E 'package(pageserver)'
+          # run pageserver tests with different settings
+          for get_vectored_concurrent_io in sequential sidecar-task; do
+            for io_engine in std-fs tokio-epoll-uring ; do
+                for io_mode in buffered direct direct-rw ; do
+                  NEON_PAGESERVER_UNIT_TEST_GET_VECTORED_CONCURRENT_IO=$get_vectored_concurrent_io \
+                  NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IOENGINE=$io_engine \
+                  NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IO_MODE=$io_mode \
+                  ${cov_prefix} \
+                  cargo nextest run $CARGO_FLAGS $CARGO_FEATURES  -E 'package(pageserver)'
+              done
+            done
+          done
 
           # Run separate tests for real S3
           export ENABLE_REAL_S3_REMOTE_STORAGE=nonempty
@@ -401,6 +405,8 @@ jobs:
           CHECK_ONDISK_DATA_COMPATIBILITY: nonempty
           BUILD_TAG: ${{ inputs.build-tag }}
           PAGESERVER_VIRTUAL_FILE_IO_ENGINE: tokio-epoll-uring
+          PAGESERVER_GET_VECTORED_CONCURRENT_IO: sidecar-task
+          PAGESERVER_VIRTUAL_FILE_IO_MODE: direct-rw
           USE_LFC: ${{ matrix.lfc_state == 'with-lfc' && 'true' || 'false' }}
 
       # Temporary disable this step until we figure out why it's so flaky

.github/workflows/build_and_test.yml

@@ -323,6 +323,8 @@ jobs:
           PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
           TEST_RESULT_CONNSTR: "${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}"
           PAGESERVER_VIRTUAL_FILE_IO_ENGINE: tokio-epoll-uring
+          PAGESERVER_GET_VECTORED_CONCURRENT_IO: sidecar-task
+          PAGESERVER_VIRTUAL_FILE_IO_MODE: direct-rw
           SYNC_BETWEEN_TESTS: true
       # XXX: no coverage data handling here, since benchmarks are run on release builds,
       # while coverage is currently collected for the debug ones
@@ -963,7 +965,7 @@ jobs:
           fi
 
       - name: Verify docker-compose example and test extensions
-        timeout-minutes: 20
+        timeout-minutes: 40
         env:
           TAG: >-
             ${{

.github/workflows/cloud-extensions.yml

@@ -10,10 +10,10 @@ on:
     - cron:  '45 1 * * *' # run once a day, timezone is utc
   workflow_dispatch: # adds ability to run this manually
     inputs:
-      region_id:
+      project_id:
         description: 'Project region id. If not set, the default region will be used'
         required: false
-        default: 'aws-us-east-2'
+        default: 'raspy-voice-43157743'
 
 defaults:
   run:
@@ -33,12 +33,12 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        pg-version: [16, 17]
+        pg-version: [17]
 
     runs-on: us-east-2
     container:
       # We use the neon-test-extensions image here as it contains the source code for the extensions.
-      image: ghcr.io/neondatabase/neon-test-extensions-v${{ matrix.pg-version }}:latest
+      image: ghcr.io/neondatabase/neon-test-extensions-v${{ matrix.pg-version }}:14928114423
       credentials:
         username: ${{ github.actor }}
         password: ${{ secrets.GITHUB_TOKEN }}
@@ -61,23 +61,37 @@ jobs:
             ULID=pgx_ulid
           fi
           LIBS=timescaledb:rag_bge_small_en_v15,rag_jina_reranker_v1_tiny_en:$ULID
-          settings=$(jq -c -n --arg libs $LIBS '{preload_libraries:{use_defaults:false,enabled_libraries:($libs| split(":"))}}')
+          settings=$(jq -c -n --arg libs $LIBS '{preload_libraries:{use_defaults:false,enabled_libraries:($libs| split(":"))}, compute_flags:{target_architecture:"x64"}}')
           echo settings=$settings >> $GITHUB_OUTPUT
-          
-      - name: Create Neon Project
-        id: create-neon-project
-        uses: ./.github/actions/neon-project-create
-        with:
-          region_id: ${{ inputs.region_id || 'aws-us-east-2' }}
-          postgres_version: ${{ matrix.pg-version }}
-          project_settings: ${{ steps.project-settings.outputs.settings }}
-          api_key: ${{ secrets.NEON_STAGING_API_KEY }}
 
+      - name: Get the connection URI
+        id: connect-uri
+        run: |
+          res=$(curl -w "%{http_code}" -X GET \
+                "https://console-stage.neon.build/api/v2/projects/${PROJECT_ID}/connection_uri?database_name=neondb&role_name=neondb_owner&pooled=false" \
+                -H 'accept: application/json' \
+                -H "Authorization: Bearer ${API_KEY}" 
+          )
+          code=${res: -3}
+          echo ${code}
+          if [[ ${code} -ge 400 ]]; then
+            echo ${res::-3}
+            exit 1
+          fi
+          URI=$(echo ${res::-3} | jq -r .uri)
+          sed +x
+          password=$(echo "$URI" | sed -n 's|.*://[^:]*:\([^@]*\)@.*|\1|p')
+          echo ::add-mask::$password
+          echo uri=${URI} >> ${GITHUB_OUTPUT}
+        env:
+          PROJECT_ID: ${{ inputs.project_id }}
+          API_KEY: ${{ secrets.NEON_STAGING_API_KEY }}
+          
       - name: Run the regression tests
         run: /run-tests.sh -r /ext-src
         env:
-          BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
-          SKIP: "pg_hint_plan-src,pg_repack-src,pg_cron-src,plpgsql_check-src"
+          BENCHMARK_CONNSTR: ${{ steps.connect-uri.outputs.uri }}
+          SKIP: "hll-src,hypopg-src,ip4r-src,pg_cron-src,pg_graphql-src,pg_hint_plan-src,pg_ivm-src,pg_jsonschema-src,pg_repack-src,pg_roaringbitmap-src,pg_semver-src,pg_session_jwt-src,pg_tiktoken-src,pg_uuidv7-src,pgjwt-src,pgrag-src,pgtap-src,pgvector-src,pgx_ulid-src,plv8-src,postgresql-unit-src,prefix-src,rag_bge_small_en_v15-src,rag_jina_reranker_v1_tiny_en-src,rum-src,plpgsql_check-src"
 
       - name: Delete Neon Project
         if: ${{ always() }}

.github/workflows/neon_extra_builds.yml

@@ -63,10 +63,8 @@ jobs:
 
       - name: Filter out only v-string for build matrix
         id: postgres_changes
-        env:
-          CHANGES: ${{ steps.files_changed.outputs.changes }}
         run: |
-          v_strings_only_as_json_array=$(echo ${CHANGES} | jq '.[]|select(test("v\\d+"))' | jq --slurp -c)
+          v_strings_only_as_json_array=$(echo ${{ steps.files_changed.outputs.chnages }} | jq '.[]|select(test("v\\d+"))' | jq --slurp -c)
           echo "changes=${v_strings_only_as_json_array}" | tee -a "${GITHUB_OUTPUT}"
 
   check-macos-build:

Cargo.lock

@@ -1112,12 +1112,6 @@ version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
 
-[[package]]
-name = "cfg_aliases"
-version = "0.2.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724"
-
 [[package]]
 name = "cgroups-rs"
 version = "0.3.3"
@@ -1309,10 +1303,9 @@ dependencies = [
  "futures",
  "http 1.1.0",
  "indexmap 2.0.1",
- "itertools 0.10.5",
  "jsonwebtoken",
  "metrics",
- "nix 0.30.1",
+ "nix 0.27.1",
  "notify",
  "num_cpus",
  "once_cell",
@@ -1435,7 +1428,7 @@ dependencies = [
  "humantime-serde",
  "hyper 0.14.30",
  "jsonwebtoken",
- "nix 0.30.1",
+ "nix 0.27.1",
  "once_cell",
  "pageserver_api",
  "pageserver_client",
@@ -3518,9 +3511,9 @@ dependencies = [
 
 [[package]]
 name = "libc"
-version = "0.2.172"
+version = "0.2.169"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d750af042f7ef4f724306de029d18836c26c1765a54a6a3f094cbd23a7267ffa"
+checksum = "b5aba8db14291edd000dfcc4d620c7ebfb122c613afb886ca8803fa4e128a20a"
 
 [[package]]
 name = "libloading"
@@ -3827,13 +3820,12 @@ dependencies = [
 
 [[package]]
 name = "nix"
-version = "0.30.1"
+version = "0.27.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "74523f3a35e05aba87a1d978330aef40f67b0304ac79c1c00b294c9830543db6"
+checksum = "2eb04e9c688eff1c89d72b407f168cf79bb9e867a9d3323ed6c01519eb9cc053"
 dependencies = [
  "bitflags 2.8.0",
  "cfg-if",
- "cfg_aliases",
  "libc",
  "memoffset 0.9.0",
 ]
@@ -4287,7 +4279,7 @@ dependencies = [
  "jsonwebtoken",
  "md5",
  "metrics",
- "nix 0.30.1",
+ "nix 0.27.1",
  "num-traits",
  "num_cpus",
  "once_cell",
@@ -4338,7 +4330,6 @@ dependencies = [
  "toml_edit",
  "tracing",
  "tracing-utils",
- "twox-hash",
  "url",
  "utils",
  "uuid",
@@ -4363,7 +4354,7 @@ dependencies = [
  "humantime",
  "humantime-serde",
  "itertools 0.10.5",
- "nix 0.30.1",
+ "nix 0.27.1",
  "once_cell",
  "postgres_backend",
  "postgres_ffi",
@@ -4856,19 +4847,6 @@ dependencies = [
  "workspace_hack",
 ]
 
-[[package]]
-name = "posthog_client_lite"
-version = "0.1.0"
-dependencies = [
- "anyhow",
- "reqwest",
- "serde",
- "serde_json",
- "sha2",
- "thiserror 1.0.69",
- "workspace_hack",
-]
-
 [[package]]
 name = "powerfmt"
 version = "0.2.0"
@@ -7906,7 +7884,7 @@ dependencies = [
  "humantime",
  "jsonwebtoken",
  "metrics",
- "nix 0.30.1",
+ "nix 0.27.1",
  "once_cell",
  "pem",
  "pin-project-lite",
@@ -8460,10 +8438,8 @@ dependencies = [
  "fail",
  "form_urlencoded",
  "futures-channel",
- "futures-core",
  "futures-executor",
  "futures-io",
- "futures-task",
  "futures-util",
  "generic-array",
  "getrandom 0.2.11",
@@ -8493,7 +8469,6 @@ dependencies = [
  "once_cell",
  "p256 0.13.2",
  "parquet",
- "percent-encoding",
  "prettyplease",
  "proc-macro2",
  "prost 0.13.3",

Cargo.toml

@@ -26,7 +26,6 @@ members = [
     "libs/utils",
     "libs/consumption_metrics",
     "libs/postgres_backend",
-    "libs/posthog_client_lite",
     "libs/pq_proto",
     "libs/tenant_size_model",
     "libs/metrics",
@@ -127,7 +126,7 @@ md5 = "0.7.0"
 measured = { version = "0.0.22", features=["lasso"] }
 measured-process = { version = "0.0.22" }
 memoffset = "0.9"
-nix = { version = "0.30.1", features = ["dir", "fs", "process", "socket", "signal", "poll"] }
+nix = { version = "0.27", features = ["dir", "fs", "process", "socket", "signal", "poll"] }
 # Do not update to >= 7.0.0, at least. The update will have a significant impact
 # on compute startup metrics (start_postgres_ms), >= 25% degradation.
 notify = "6.0.0"

build-tools.Dockerfile

@@ -144,7 +144,6 @@ RUN set -e \
         openssh-client \
         parallel \
         pkg-config \
-        sudo \
         unzip \
         wget \
         xz-utils \
@@ -293,7 +292,7 @@ WORKDIR /home/nonroot
 
 # Rust
 # Please keep the version of llvm (installed above) in sync with rust llvm (`rustc --version --verbose | grep LLVM`)
-ENV RUSTC_VERSION=1.87.0
+ENV RUSTC_VERSION=1.86.0
 ENV RUSTUP_HOME="/home/nonroot/.rustup"
 ENV PATH="/home/nonroot/.cargo/bin:${PATH}"
 ARG RUSTFILT_VERSION=0.2.1

compute/compute-node.Dockerfile

@@ -297,6 +297,7 @@ 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 && \
@@ -1117,8 +1118,8 @@ RUN wget https://github.com/microsoft/onnxruntime/archive/refs/tags/v1.18.1.tar.
     mkdir onnxruntime-src && cd onnxruntime-src && tar xzf ../onnxruntime.tar.gz --strip-components=1 -C . && \
     echo "#nothing to test here" > neon-test.sh
 
-RUN wget https://github.com/neondatabase-labs/pgrag/archive/refs/tags/v0.1.2.tar.gz -O pgrag.tar.gz &&  \
-    echo "7361654ea24f08cbb9db13c2ee1c0fe008f6114076401bb871619690dafc5225 pgrag.tar.gz" | sha256sum --check && \
+RUN wget https://github.com/neondatabase-labs/pgrag/archive/refs/tags/v0.1.1.tar.gz -O pgrag.tar.gz &&  \
+    echo "087b2ecd11ba307dc968042ef2e9e43dc04d9ba60e8306e882c407bbe1350a50 pgrag.tar.gz" | sha256sum --check && \
     mkdir pgrag-src && cd pgrag-src && tar xzf ../pgrag.tar.gz --strip-components=1 -C .
 
 FROM rust-extensions-build-pgrx14 AS pgrag-build
@@ -1809,10 +1810,25 @@ 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-src /ext-src/ /ext-src/
+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=plv8-src /ext-src/ /ext-src/
 #COPY --from=h3-pg-src /ext-src/ /ext-src/
 COPY --from=postgresql-unit-src /ext-src/ /ext-src/
@@ -1971,8 +1987,7 @@ COPY --from=sql_exporter_preprocessor --chmod=0644 /home/nonroot/compute/etc/sql
 COPY --from=sql_exporter_preprocessor --chmod=0644 /home/nonroot/compute/etc/neon_collector_autoscaling.yml /etc/neon_collector_autoscaling.yml
 
 # Make the libraries we built available
-COPY --chmod=0666 compute/etc/ld.so.conf.d/00-neon.conf /etc/ld.so.conf.d/00-neon.conf
-RUN /sbin/ldconfig
+RUN echo '/usr/local/lib' >> /etc/ld.so.conf && /sbin/ldconfig
 
 # rsyslog config permissions
 # directory for rsyslogd pid file

compute/etc/ld.so.conf.d/00-neon.conf

@@ -1 +0,0 @@
-/usr/local/lib

compute_tools/Cargo.toml

@@ -28,7 +28,6 @@ flate2.workspace = true
 futures.workspace = true
 http.workspace = true
 indexmap.workspace = true
-itertools.workspace = true
 jsonwebtoken.workspace = true
 metrics.workspace = true
 nix.workspace = true

compute_tools/src/compute.rs

@@ -11,7 +11,6 @@ use compute_api::spec::{
 use futures::StreamExt;
 use futures::future::join_all;
 use futures::stream::FuturesUnordered;
-use itertools::Itertools;
 use nix::sys::signal::{Signal, kill};
 use nix::unistd::Pid;
 use once_cell::sync::Lazy;
@@ -19,7 +18,7 @@ use postgres;
 use postgres::NoTls;
 use postgres::error::SqlState;
 use remote_storage::{DownloadError, RemotePath};
-use std::collections::{HashMap, HashSet};
+use std::collections::HashMap;
 use std::net::SocketAddr;
 use std::os::unix::fs::{PermissionsExt, symlink};
 use std::path::Path;
@@ -1996,40 +1995,23 @@ LIMIT 100",
         tokio::spawn(conn);
 
         // TODO: support other types of grants apart from schemas?
-
-        // check the role grants first - to gracefully handle read-replicas.
-        let select = "SELECT privilege_type
-            FROM pg_namespace
-                JOIN LATERAL (SELECT * FROM aclexplode(nspacl) AS x) acl ON true
-                JOIN pg_user users ON acl.grantee = users.usesysid
-            WHERE users.usename = $1
-                AND nspname = $2";
-        let rows = db_client
-            .query(select, &[role_name, schema_name])
-            .await
-            .with_context(|| format!("Failed to execute query: {select}"))?;
-
-        let already_granted: HashSet<String> = rows.into_iter().map(|row| row.get(0)).collect();
-
-        let grants = privileges
-            .iter()
-            .filter(|p| !already_granted.contains(p.as_str()))
-            // should not be quoted as it's part of the command.
-            // is already sanitized so it's ok
-            .map(|p| p.as_str())
-            .join(", ");
-
-        if !grants.is_empty() {
+        let query = format!(
+            "GRANT {} ON SCHEMA {} TO {}",
+            privileges
+                .iter()
+                // should not be quoted as it's part of the command.
+                // is already sanitized so it's ok
+                .map(|p| p.as_str())
+                .collect::<Vec<&'static str>>()
+                .join(", "),
             // quote the schema and role name as identifiers to sanitize them.
-            let schema_name = schema_name.pg_quote();
-            let role_name = role_name.pg_quote();
-
-            let query = format!("GRANT {grants} ON SCHEMA {schema_name} TO {role_name}",);
-            db_client
-                .simple_query(&query)
-                .await
-                .with_context(|| format!("Failed to execute query: {}", query))?;
-        }
+            schema_name.pg_quote(),
+            role_name.pg_quote(),
+        );
+        db_client
+            .simple_query(&query)
+            .await
+            .with_context(|| format!("Failed to execute query: {}", query))?;
 
         Ok(())
     }

compute_tools/src/config.rs

@@ -224,10 +224,7 @@ pub fn write_postgres_conf(
             writeln!(file, "pgaudit.log_rotation_age=5")?;
 
             // Enable audit logs for pg_session_jwt extension
-            // TODO: Consider a good approach for shipping pg_session_jwt logs to the same sink as
-            // pgAudit - additional context in https://github.com/neondatabase/cloud/issues/28863
-            //
-            // writeln!(file, "pg_session_jwt.audit_log=on")?;
+            writeln!(file, "pg_session_jwt.audit_log=on")?;
 
             // Add audit shared_preload_libraries, if they are not present.
             //

control_plane/src/background_process.rs

@@ -14,7 +14,7 @@
 
 use std::ffi::OsStr;
 use std::io::Write;
-use std::os::fd::AsFd;
+use std::os::unix::prelude::AsRawFd;
 use std::os::unix::process::CommandExt;
 use std::path::Path;
 use std::process::Command;
@@ -356,7 +356,7 @@ where
             let file = pid_file::claim_for_current_process(&path).expect("claim pid file");
             // Remove the FD_CLOEXEC flag on the pidfile descriptor so that the pidfile
             // remains locked after exec.
-            nix::fcntl::fcntl(file.as_fd(), FcntlArg::F_SETFD(FdFlag::empty()))
+            nix::fcntl::fcntl(file.as_raw_fd(), FcntlArg::F_SETFD(FdFlag::empty()))
                 .expect("remove FD_CLOEXEC");
             // Don't run drop(file), it would close the file before we actually exec.
             std::mem::forget(file);

control_plane/src/bin/neon_local.rs

@@ -8,6 +8,7 @@
 use std::borrow::Cow;
 use std::collections::{BTreeSet, HashMap};
 use std::fs::File;
+use std::os::fd::AsRawFd;
 use std::path::PathBuf;
 use std::process::exit;
 use std::str::FromStr;
@@ -30,7 +31,7 @@ use control_plane::safekeeper::SafekeeperNode;
 use control_plane::storage_controller::{
     NeonStorageControllerStartArgs, NeonStorageControllerStopArgs, StorageController,
 };
-use nix::fcntl::{Flock, FlockArg};
+use nix::fcntl::{FlockArg, flock};
 use pageserver_api::config::{
     DEFAULT_HTTP_LISTEN_PORT as DEFAULT_PAGESERVER_HTTP_PORT,
     DEFAULT_PG_LISTEN_PORT as DEFAULT_PAGESERVER_PG_PORT,
@@ -748,16 +749,16 @@ struct TimelineTreeEl {
 
 /// A flock-based guard over the neon_local repository directory
 struct RepoLock {
-    _file: Flock<File>,
+    _file: File,
 }
 
 impl RepoLock {
     fn new() -> Result<Self> {
         let repo_dir = File::open(local_env::base_path())?;
-        match Flock::lock(repo_dir, FlockArg::LockExclusive) {
-            Ok(f) => Ok(Self { _file: f }),
-            Err((_, e)) => Err(e).context("flock error"),
-        }
+        let repo_dir_fd = repo_dir.as_raw_fd();
+        flock(repo_dir_fd, FlockArg::LockExclusive)?;
+
+        Ok(Self { _file: repo_dir })
     }
 }
 

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 && chown postgres /ext-src/pg_hint_plan-src /postgres/contrib/file_fdw
+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
 
 USER postgres

docker-compose/compute_wrapper/shell/compute.sh

@@ -14,14 +14,6 @@ PG_VERSION=${PG_VERSION:-14}
 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
-first_path="$(ldconfig --verbose 2>/dev/null \
-    | grep --invert-match ^$'\t' \
-    | cut --delimiter=: --fields=1 \
-    | head --lines=1)"
-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;

docker-compose/docker-compose.yml

@@ -186,13 +186,14 @@ services:
 
   neon-test-extensions:
     profiles: ["test-extensions"]
-    image: ${REPOSITORY:-ghcr.io/neondatabase}/neon-test-extensions-v${PG_TEST_VERSION:-16}:${TEST_EXTENSIONS_TAG:-${TAG:-latest}}
+    image: ${REPOSITORY:-ghcr.io/neondatabase}/neon-test-extensions-v${PG_TEST_VERSION:-${PG_VERSION:-16}}:${TEST_EXTENSIONS_TAG:-${TAG:-latest}}
     environment:
-      - PGPASSWORD=cloud_admin
+      - PGUSER=${PGUSER:-cloud_admin}
+      - PGPASSWORD=${PGPASSWORD:-cloud_admin}
     entrypoint:
       - "/bin/bash"
       - "-c"
     command:
-      - sleep 1800
+      - sleep 360000
     depends_on:
       - compute

docker-compose/docker_compose_test.sh

@@ -54,6 +54,15 @@ 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"
@@ -68,7 +77,7 @@ 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,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 \
+        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 \
         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/alter_db.sh

@@ -1,8 +0,0 @@
-#!/bin/bash
-# We need these settings to get the expected output results.
-# We cannot use the environment variables e.g. PGTZ due to
-# https://github.com/neondatabase/neon/issues/1287
-export DATABASE=${1:-contrib_regression}
-psql -c "ALTER DATABASE ${DATABASE} SET neon.allow_unstable_extensions='on'" \
-     -c "ALTER DATABASE ${DATABASE} SET DateStyle='Postgres,MDY'" \
-     -c "ALTER DATABASE ${DATABASE} SET TimeZone='America/Los_Angeles'" \

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

@@ -18,7 +18,6 @@ TESTS=${TESTS/row_level_security/}
 TESTS=${TESTS/sqli_connection/}
 dropdb --if-exist contrib_regression
 createdb contrib_regression
-. ../alter_db.sh
 psql -v ON_ERROR_STOP=1 -f test/fixtures.sql -d contrib_regression
 ${REGRESS} --use-existing --dbname=contrib_regression --inputdir=${TESTDIR} ${TESTS}
 

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

@@ -3,7 +3,6 @@ set -ex
 cd "$(dirname "${0}")"
 dropdb --if-exist contrib_regression
 createdb contrib_regression
-. ../alter_db.sh
 psql -d contrib_regression -c "CREATE EXTENSION vector" -c "CREATE EXTENSION rag"
 PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
 ${PG_REGRESS} --inputdir=./ --bindir='/usr/local/pgsql/bin'    --use-existing --load-extension=vector --load-extension=rag --dbname=contrib_regression basic_functions text_processing api_keys chunking_functions document_processing embedding_api_functions voyageai_functions

docker-compose/ext-src/pgx_ulid-src/Makefile

@@ -20,6 +20,5 @@ installcheck: regression-test
 regression-test:
 	dropdb --if-exists contrib_regression
 	createdb contrib_regression
-	../alter_db.sh
 	psql -d contrib_regression -c "CREATE EXTENSION $(EXTNAME)"
 	$(PG_REGRESS) --inputdir=. --outputdir=. --use-existing --dbname=contrib_regression $(REGRESS)

docker-compose/ext-src/plv8-src/regular-test.sh

@@ -3,7 +3,6 @@ set -ex
 cd "$(dirname ${0})"
 dropdb --if-exist contrib_regression
 createdb contrib_regression
-. ../alter_db.sh
 PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
 REGRESS="$(make -n installcheck | awk '{print substr($0,index($0,"init-extension"));}')"
 REGRESS="${REGRESS/startup_perms/}"

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

@@ -0,0 +1,9 @@
+#!/bin/bash
+set -ex
+cd "$(dirname "$0")"
+if [[ ${PG_VERSION} = v17 ]]; then
+  sed -i '/computed_columns/d' regress/core/tests.mk
+fi
+patch -p1 <postgis-no-upgrade-test.patch
+trap 'echo Cleaning up; patch -R -p1 <postgis-no-upgrade-test.patch' EXIT
+make installcheck-base

docker-compose/ext-src/postgis-src/postgis-no-upgrade-test.patch

@@ -0,0 +1,21 @@
+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-regular-v16.patch

@@ -0,0 +1,198 @@
+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 3abd7bc..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 \
+@@ -144,11 +140,6 @@ 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/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

@@ -0,0 +1,218 @@
+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 9e05244..a63a3e1 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 \
+@@ -143,8 +139,7 @@ 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/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

@@ -0,0 +1,19 @@
+#!/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-no-upgrade-test.patch
+patch -p1 <"postgis-regular-${PG_VERSION}.patch"
+psql -d contrib_regression -f raster_outdb_template.sql
+trap 'patch -R -p1 <postgis-no-upgrade-test.patch && patch -R -p1 <"postgis-regular-${PG_VERSION}.patch"' EXIT
+#XXX remove after fix of using system libpq problem
+export LD_LIBRARY_PATH=/usr/local/pgsql/lib
+POSTGIS_REGRESS_DB=contrib_regression RUNTESTFLAGS=--nocreate make installcheck-base

docker-compose/ext-src/rag_bge_small_en_v15-src/Makefile

@@ -11,6 +11,5 @@ PG_REGRESS := $(dir $(PGXS))../../src/test/regress/pg_regress
 installcheck:
 	dropdb --if-exists contrib_regression
 	createdb contrib_regression
-	../alter_db.sh
 	psql -d contrib_regression -c "CREATE EXTENSION vector" -c "CREATE EXTENSION rag_bge_small_en_v15"
 	$(PG_REGRESS) --use-existing --dbname=contrib_regression $(REGRESS)

docker-compose/ext-src/rag_jina_reranker_v1_tiny_en-src/Makefile

@@ -11,6 +11,5 @@ PG_REGRESS := $(dir $(PGXS))../../src/test/regress/pg_regress
 installcheck:
 	dropdb --if-exists contrib_regression
 	createdb contrib_regression
-	../alter_db.sh
 	psql -d contrib_regression -c "CREATE EXTENSION vector" -c "CREATE EXTENSION rag_jina_reranker_v1_tiny_en"
 	$(PG_REGRESS) --use-existing --dbname=contrib_regression $(REGRESS)

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

@@ -3,6 +3,5 @@ set -ex
 cd "$(dirname ${0})"
 dropdb --if-exist contrib_regression
 createdb contrib_regression
-. ../alter_db.sh
 PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
 ${PG_REGRESS} --inputdir=./ --bindir='/usr/local/pgsql/bin' --use-existing --dbname=contrib_regression rum rum_hash ruminv timestamp orderby orderby_hash altorder altorder_hash limits int2 int4 int8 float4 float8 money oid time timetz date interval macaddr inet cidr text varchar char bytea bit varbit numeric rum_weight expr array

docker-compose/pageserver_config/pageserver.toml

@@ -5,4 +5,3 @@ listen_http_addr='0.0.0.0:9898'
 remote_storage={ endpoint='http://minio:9000', bucket_name='neon', bucket_region='eu-north-1', prefix_in_bucket='/pageserver' }
 control_plane_api='http://0.0.0.0:6666' # No storage controller in docker compose, specify a junk address
 control_plane_emergency_mode=true
-virtual_file_io_mode="buffered" # the CI runners where we run the docker compose tests have slow disks

docker-compose/run-tests.sh

@@ -63,5 +63,9 @@ 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

docs/rfcs/030-vectored-timeline-get.md

@@ -7,8 +7,6 @@ Author: Christian Schwarz
 
 A brief RFC / GitHub Epic describing a vectored version of the `Timeline::get` method that is at the heart of Pageserver.
 
-**EDIT**: the implementation of this feature is described in [Vlad's (internal) tech talk](https://drive.google.com/file/d/1vfY24S869UP8lEUUDHRWKF1AJn8fpWoJ/view?usp=drive_link).
-
 # Motivation
 
 During basebackup, we issue many `Timeline::get` calls for SLRU pages that are *adjacent* in key space.

docs/rfcs/043-bottom-most-gc-compaction.md

@@ -1,194 +0,0 @@
-# Bottommost Garbage-Collection Compaction
-
-## Summary
-
-The goal of this doc is to propose a way to reliably collect garbages below the GC horizon. This process is called bottom-most garbage-collect-compaction, and is part of the broader legacy-enhanced compaction that we plan to implement in the future.
-
-## Motivation
-
-The current GC algorithm will wait until the covering via image layers before collecting the garbages of a key region. Relying on image layer generation to generate covering images is not reliable. There are prior arts to generate feedbacks from the GC algorithm to the image generation process to accelerate garbage collection, but it slows down the system and creates write amplification.
-
-# Basic Idea
-
-![](images/036-bottom-most-gc-compaction/01-basic-idea.svg)
-
-The idea of bottom-most compaction is simple: we rewrite all layers that are below or intersect with the GC horizon to produce a flat level of image layers at the GC horizon and deltas above the GC horizon. In this process,
-
-- All images and deltas ≤ GC horizon LSN will be dropped. This process collects garbages.
-- We produce images for all keys involved in the compaction process at the GC horizon.
-
-Therefore, it can precisely collect all garbages below the horizon, and reduce the space amplification, i.e., in the staircase pattern (test_gc_feedback).
-
-![The staircase pattern in test_gc_feedback in the original compaction algorithm. The goal is to collect garbage below the red horizontal line.](images/036-bottom-most-gc-compaction/12-staircase-test-gc-feedback.png)
-
-The staircase pattern in test_gc_feedback in the original compaction algorithm. The goal is to collect garbage below the red horizontal line.
-
-# Branches
-
-With branches, the bottom-most compaction should retain a snapshot of the keyspace at the `retain_lsn` so that the child branch can access data at the branch point. This requires some modifications to the basic bottom-most compaction algorithm that we sketched above. 
-
-![](images/036-bottom-most-gc-compaction/03-retain-lsn.svg)
-
-## Single Timeline w/ Snapshots: handle `retain_lsn`
-
-First let’s look into the case where we create branches over the main branch but don’t write any data to them (aka “snapshots”).
-
-The bottom-most compaction algorithm collects all deltas and images of a key and can make decisions on what data to retain. Given that we have a single key’s history as below:
-
-```
-LSN 0x10 -> A
-LSN 0x20 -> append B
-retain_lsn: 0x20
-LSN 0x30 -> append C
-LSN 0x40 -> append D
-retain_lsn: 0x40
-LSN 0x50 -> append E
-GC horizon: 0x50
-LSN 0x60 -> append F
-```
-
-The algorithm will produce:
-
-```
-LSN 0x20 -> AB
-(drop all history below the earliest retain_lsn)
-LSN 0x40 -> ABCD
-(assume the cost of replaying 2 deltas is higher than storing the full image, we generate an image here)
-LSN 0x50 -> append E
-(replay one delta is cheap)
-LSN 0x60 -> append F
-(keep everything as-is above the GC horizon)
-```
-
-![](images/036-bottom-most-gc-compaction/05-btmgc-parent.svg)
-
-What happens is that we balance the space taken by each retain_lsn and the cost of replaying deltas during the bottom-most compaction process. This is controlled by a threshold. If `count(deltas) < $threshold`, the deltas will be retained. Otherwise, an image will be generated and the deltas will be dropped.
-
-In the example above, the `$threshold` is 2.
-
-## Child Branches with data: pull + partial images
-
-In the previous section we have shown how bottom-most compaction respects `retain_lsn` so that all data that was readable at branch creation remains readable. But branches can have data on their own, and that data can fall out of the branch’s PITR window. So, this section explains how we deal with that.
-
-We will run the same bottom-most compaction for these branches, to ensure the space amplification on the child branch is reasonable. 
-
-```
-branch_lsn: 0x20
-LSN 0x30 -> append P
-LSN 0x40 -> append Q
-LSN 0x50 -> append R
-GC horizon: 0x50
-LSN 0x60 -> append S
-```
-
-Note that bottom-most compaction happens on a per-timeline basis. When it processes this key, it only reads the history from LSN 0x30 without a base image. Therefore, on child branches, the bottom-most compaction process will make image creation decisions based on the same `count(deltas) < $threshold` criteria, and if it decides to create an image, the base image will be retrieved from the ancestor branch.
-
-```
-branch_lsn: 0x20
-LSN 0x50 -> ABPQR
-(we pull the image at LSN 0x20 from the ancestor branch to get AB, and then apply append PQ to the page; we replace the record at 0x40 with an image and drop the delta)
-GC horizon: 0x50
-LSN 0x60 -> append S
-```
-
-![](images/036-bottom-most-gc-compaction/06-btmgc-child.svg)
-
-Note that for child branches, we do not create image layers for the images when bottom-most compaction runs. Instead, we drop the 0x30/0x40/0x50 delta records and directly place the image ABPQR@0x50 into the delta layer, which serves as a sparse image layer. For child branches, if we create image layers, we will need to put all keys in the range into the image layer. This causes space bloat and slow compactions. In this proposal, the compaction process will only compact and process keys modified inside the child branch.
-
-# Result
-
-Bottom-most compaction ensures all garbage under the GC horizon gets collected right away (compared with “eventually” in the current algorithm). Meanwhile, it generates images at each of the retain_lsn to ensure branch reads are fast. As we make per-key decisions on whether to generate an image or not, the theoretical lower bound of the storage space we need to retain for a branch is lower than before.
-
-Before: min(sum(logs for each key), sum(image for each key)), for each partition — we always generate image layers on a key range
-
-After: sum(min(logs for each key, image for each key))
-
-# Compaction Trigger
-
-The bottom-most compaction can be automatically triggered. The goal of the trigger is that it should ensure a constant factor for write amplification. Say that the user write 1GB of WAL into the system, we should write 1GB x C data to S3. The legacy compaction algorithm does not have such a constant factor C. The data we write to S3 is quadratic to the logical size of the database (see [A Theoretical View of Neon Storage](https://www.notion.so/A-Theoretical-View-of-Neon-Storage-8d7ad7555b0c41b2a3597fa780911194?pvs=21)).
-
-We propose the following compaction trigger that generates a constant write amplification factor. Write amplification >= total writes to S3 / total user writes. We only analyze the write amplification caused by the bottom-most GC-compaction process, ignoring the legacy create image layers amplification.
-
-Given that we have ***X*** bytes of the delta layers above the GC horizon, ***A*** bytes of the delta layers intersecting with the GC horizon, ***B*** bytes of the delta layers below the GC horizon, and ***C*** bytes of the image layers below the GC horizon.
-
-The legacy GC + compaction loop will always keep ***A*** unchanged, reduce ***B and C*** when there are image layers covering the key range. This yields 0 write amplification (only file deletions) and extra ***B*** bytes of space.
-
-![](images/036-bottom-most-gc-compaction/09-btmgc-analysis-2.svg)
-
-The bottom-most compaction proposed here will split ***A*** into deltas above the GC horizon and below the GC horizon. Everything below the GC horizon will be image layers after the compaction (not considering branches). Therefore, this yields ***A+C*** extra write traffic each iteration, plus 0 extra space.
-
-![](images/036-bottom-most-gc-compaction/07-btmgc-analysis-1.svg)
-
-Also considering read amplification (below the GC horizon). When a read request reaches the GC horizon, the read amplification will be (A+B+C)/C=1+(A+B)/C. Reducing ***A*** and ***B*** can help reduce the read amplification below the GC horizon.
-
-The metrics-based trigger will wait until a point that space amplification is not that large and write amplification is not that large before the compaction gets triggered. The trigger is defined as **(A+B)/C ≥ 1 (or some other ratio)**.
-
-To reason about this trigger, consider the two cases:
-
-**Data Ingestion**
-
-User keeps ingesting data into the database, which indicates that WAL size roughly equals to the database logical size. The compaction gets triggered only when the newly-written WAL roughly equals to the current bottom-most image size (=X). Therefore, it’s triggered when the database size gets doubled. This is a reasonable amount of work. Write amplification is 2X/X=1 for the X amount of data written.
-
-![](images/036-bottom-most-gc-compaction/10-btmgc-analysis-3.svg)
-
-**Updates/Deletion**
-
-In this case, WAL size will be larger than the database logical size ***D***. The compaction gets triggered for every ***D*** bytes of WAL written. Therefore, for every ***D*** bytes of WAL, we rewrite the bottom-most layer, which produces an extra ***D*** bytes of write amplification. This incurs exactly 2x write amplification (by the write of D), 1.5x write amplification (if we count from the start of the process) and no space amplification. 
-
-![](images/036-bottom-most-gc-compaction/11-btmgc-analysis-4.svg)
-
-Note that here I try to reason that write amplification is a constant (i.e., the data we write to S3 is proportional to the data the user write). The main problem with the current legacy compaction algorithm is that write amplification is proportional to the database size.
-
-The next step is to optimize the write amplification above the GC horizon (i.e., change the image creation criteria, top-most compaction, or introduce tiered compaction), to ensure the write amplification of the whole system is a constant factor.
-
-20GB layers → +20GB layers → delete 20GB, need 40GB temporary space
-
-# Sub-Compactions
-
-The gc-compaction algorithm may take a long time and we need to split the job into multiple sub-compaction jobs.
-
-![](images/036-bottom-most-gc-compaction/13-job-split.svg)
-
-As in the figure, the auto-trigger schedules a compaction job covering the full keyspace below a specific LSN. In such case that we cannot finish compacting it in one run in a reasonable amount of time, the algorithm will vertically split it into multiple jobs (in this case, 5).
-
-Each gc-compaction job will create one level of delta layers and one flat level of image layers for each LSN. Those layers will be automatically split based on size, which means that if the sub-compaction job produces 1GB of deltas, it will produce 4 * 256MB delta layers. For those layers that is not fully contained within the sub-compaction job rectangles, it will be rewritten to only contain the keys outside of the key range.
-
-# Implementation
-
-The main implementation of gc-compaction is in `compaction.rs`.
-
-* `compact_with_gc`: The main loop of gc-compaction. It takes a rectangle range of the layer map and compact that specific range. It selects layers intersecting with the rectangle, downloads the layers, creates the k-merge iterator to read those layers in the key-lsn order, and decide which keys to keep or insert a reconstructed page. The process is the basic unit of a gc-compaction and is not interruptable. If the process gets preempted by L0 compaction, it has to be restarted from scratch. For layers overlaps with the rectangle but not fully inside, the main loop will also rewrite them so that the new layer (or two layers if both left and right ends are outside of the rectangle) has the same LSN range as the original one but only contain the keys outside of the compaction range.
-* `gc_compaction_split_jobs`: Splits a big gc-compaction job into sub-compactions based on heuristics in the layer map. The function looks at the layer map and splits the compaction job based on the size of the layers so that each compaction job only pulls ~4GB of layer files.
-* `generate_key_retention` and `KeyHistoryRetention`: Implements the algorithm described in the "basic idea" and "branch" chapter of this RFC. It takes a vector of history of a key (key-lsn-value) and decides which LSNs of the key to retain. If there are too many deltas between two retain_lsns, it will reconstruct the page and insert an image into the compaction result. Also, we implement `KeyHistoryRetention::verify` to ensure the generated result is not corrupted -- all retain_lsns and all LSNs above the gc-horizon should be accessible.
-* `GcCompactionQueue`: the automatic trigger implementation for gc-compaction. `GcCompactionQueue::iteration` is called at the end of the tenant compaction loop. It will then call `trigger_auto_compaction` to decide whether to trigger a gc-compaction job for this tenant. If yes, the compaction-job will be added to the compaction queue, and the queue will be slowly drained once there are no other compaction jobs running. gc-compaction has the lowest priority. If a sub-compaction job is not successful or gets preempted by L0 compaction (see limitations for reasons why a compaction job would fail), it will _not_ be retried.
-* Changes to `index_part.json`: we added a `last_completed_lsn` field to the index part for the auto-trigger to decide when to trigger a compaction.
-* Changes to the read path: when gc-compaction updates the layer map, all reads need to wait. See `gc_compaction_layer_update_lock` and comments in the code path for more information.
-
-Gc-compaction can also be scheduled over the HTTP API. Example:
-
-```
-curl 'localhost:9898/v1/tenant/:tenant_id/timeline/:timeline_id/compact?enhanced_gc_bottom_most_compaction=true&dry_run=true' -X PUT -H "Content-Type: application/json" -d '{"scheduled": true, "compact_key_range": { "start": "000000067F0000A0000002A1CF0100000000", "end": "000000067F0000A0000002A1D70100000000" } }'
-```
-
-The `dry_run` mode can be specified in the query string so that the compaction will go through all layers to estimate how much space can be saved without writing the compaction result into the layer map.
-
-The auto-trigger is controlled by tenant-level flag `gc_compaction_enabled`. If this is set to false, no gc-compaction will be automatically scheduled on this tenant (but manual trigger still works).
-
-# Next Steps
-
-There are still some limitations of gc-compaction itself that needs to be resolved and tested,
-
-- gc-compaction is currently only automatically triggered on root branches. We have not tested gc-compaction on child branches in staging.
-- gc-compaction will skip aux key regions because of the possible conflict with the assumption of aux file tombstones.
-- gc-compaction does not consider keyspaces at retain_lsns and only look at keys in the layers. This also causes us giving up some sub-compaction jobs because a key might have part of its history available due to traditional GC removing part of the history.
-- We limit gc-compaction to run over shards <= 150GB to avoid gc-compaction taking too much time blocking other compaction jobs. The sub-compaction split algorithm needs to be improved to be able to split vertically and horizontally. Also, we need to move the download layer process out of the compaction loop so that we don't block other compaction jobs for too long.
-- The compaction trigger always schedules gc-compaction from the lowest LSN to the gc-horizon. Currently we do not schedule compaction jobs that only selects layers in the middle. Allowing this could potentially reduce the number of layers read/write throughout the process.
-- gc-compaction will give up if there are too many layers to rewrite or if there are not enough disk space for the compaction.
-- gc-compaction sometimes fails with "no key produced during compaction", which means that all existing keys within the compaction range can be collected; but we don't have a way to write this information back to the layer map -- we cannot generate an empty image layer.
-- We limit the maximum size of deltas for a single key to 512MB. If above this size, gc-compaction will give up. This can be resolved by changing `generate_key_retention` to be a stream instead of requiring to collect all the key history.
-
-In the future,
-
-- Top-most compaction: ensure we always have an image coverage for the latest data (or near the latest data), so that reads will be fast at the latest LSN.
-- Tiered compaction on deltas: ensure read from any LSN is fast.
-- Per-timeline compaction → tenant-wide compaction?

docs/rfcs/2025-04-30-direct-io-for-pageserver.md

@@ -1,362 +0,0 @@
-# Direct IO For Pageserver
-
-Date: Apr 30, 2025
-
-## Summary
-
-This document is a retroactive RFC. It
-- provides some background on what direct IO is,
-- motivates why Pageserver should be using it for its IO, and
-- describes how we changed Pageserver to use it.
-
-The [initial proposal](https://github.com/neondatabase/neon/pull/8240) that kicked off the work can be found in this closed GitHub PR.
-
-People primarily involved in this project were:
-- Yuchen Liang <yuchen@neon.tech>
-- Vlad Lazar <vlad@neon.tech>
-- Christian Schwarz <christian@neon.tech>
-
-## Timeline
-
-For posterity, here is the rough timeline of the development work that got us to where we are today.
-
-- Jan 2024: [integrate `tokio-epoll-uring`](https://github.com/neondatabase/neon/pull/5824) along with owned buffers API
-- March 2024: `tokio-epoll-uring` enabled in all regions in buffered IO mode
-- Feb 2024 to June 2024: PS PageCache Bypass For Data Blocks
-  - Feb 2024: [Vectored Get Implementation](https://github.com/neondatabase/neon/pull/6576) bypasses delta & image layer blocks for page requests
-  - Apr to June 2024: [Epic: bypass PageCache for use data blocks](https://github.com/neondatabase/neon/issues/7386) addresses remaining users
-- Aug to Nov 2024: direct IO: first code; preliminaries; read path coding; BufferedWriter; benchmarks show perf regressions too high, no-go.
-- Nov 2024 to Jan 2025: address perf regressions by developing page_service pipelining (aka batching) and concurrent IO ([Epic](https://github.com/neondatabase/neon/issues/9376))
-- Feb to March 2024: rollout batching, then concurrent+direct IO => read path and InMemoryLayer is now direct IO
-- Apr 2025: develop & roll out direct IO for the write path
-
-## Background: Terminology & Glossary
-
-**kernel page cache**: the Linux kernel's page cache is a write-back cache for filesystem contents.
-The cached unit is memory-page-sized & aligned chunks of the files that are being cached (typically 4k).
-The cache lives in kernel memory and is not directly accessible through userspace.
-
-**Buffered IO**: an application's read/write system calls go through the kernel page cache.
-For example, a 10 byte sized read or write to offset 5000 in a file will load the file contents
-at offset `[4096,8192)` into a free page in the kernel page cache. If necessary, it will evict
-a page to make room (cf eviction). Then, the kernel performs a memory-to-memory copy of 10 bytes
-from/to the offset `4` (`5000 = 4096 + 4`) within the cached page. If it's a write, the kernel keeps
-track of the fact that the page is now "dirty" in some ancillary structure.
-
-**Writeback**: a buffered read/write syscall returns after the memory-to-memory copy. The modifications
-made by e.g. write system calls are not even *issued* to disk, let alone durable. Instead, the kernel
-asynchronously writes back dirtied pages based on a variety of conditions. For us, the most relevant
-ones are a) explicit request by userspace (`fsync`) and b) memory pressure.
-
-**Memory pressure**: the kernel page cache is a best effort service and a user of spare memory capacity.
-If there is no free memory, the kernel page allocator will take pages used by page cache to satisfy allocations.
-Before reusing a page like that, the page has to be written back (writeback, see above).
-The far-reaching consequence of this is that **any allocation of anonymous memory can do IO** if the only
-way to get that memory is by eviction & re-using a dirty page cache page.
-Notably, this includes a simple `malloc` in userspace, because eventually that boils down to `mmap(..., MAP_ANON, ...)`.
-I refer to this effect as the "malloc latency backscatter" caused by buffered IO.
-
-**Direct IO** allows application's read/write system calls to bypass the kernel page cache. The filesystem
-is still involved because it is ultimately in charge of mapping the concept of files & offsets within them
-to sectors on block devices. Typically, the filesystem poses size and alignment requirements for memory buffers
-and file offsets (statx `Dio_mem_align` / `Dio_offset_align`), see [this gist](https://gist.github.com/problame/1c35cac41b7cd617779f8aae50f97155).
-The IO operations will fail at runtime with EINVAL if the alignment requirements are not met.
-
-**"buffered" vs "direct"**: the central distinction between buffered and direct IO is about who allocates and
-fills the IO buffers, and who controls when exactly the IOs are issued. In buffered IO, it's the syscall handlers,
-kernel page cache, and memory management subsystems (cf "writeback"). In direct IO, all of it is done by
-the application.
-It takes more effort by the application to program with direct instead of buffered IO.
-The return is precise control over and a clear distinction between consumption/modification of memory vs disk.
-
-**Pageserver PageCache**: Pageserver has an additional `PageCache` (referred to as PS PageCache from here on, as opposed to "kernel page cache").
-Its caching unit is 8KiB blocks of the layer files written by Pageserver.
-A miss in PageCache is filled by reading from the filesystem, through the `VirtualFile` abstraction layer.
-The default size is tiny (64MiB), very much like Postgres's `shared_buffers`.
-We ran production at 128MiB for a long time but gradually moved it up to 2GiB over the past ~year.
-
-**VirtualFile** is Pageserver's abstraction for file IO, very similar to the facility in Postgres that bears the same name.
-Its historical purpose appears to be working around open file descriptor limitations, which is practically irrelevant on Linux.
-However, the facility in Pageserver is useful as an intermediary layer for metrics and abstracts over the different kinds of
-IO engines that Pageserver supports (`std-fs` vs `tokio-epoll-uring`).
-
-## Background: History Of Caching In Pageserver
-
-For multiple years, Pageserver's `PageCache` was on the path of all read _and write_ IO.
-It performed write-back to the kernel using buffered IO.
-
-We converted it into a read-only cache of immutable data in [PR 4994](https://github.com/neondatabase/neon/pull/4994).
-
-The introduction of `tokio-epoll-uring` required converting the code base to used owned IO buffers.
-The `PageCache` pages are usable as owned IO buffers.
-
-We then started bypassing PageCache for user data blocks.
-Data blocks are the 8k blocks of data in layer files that hold the multiple `Value`s, as opposed to the disk btree index blocks that tell us which values exist in a file at what offsets.
-The disk btree embedded in delta & image layers remains `PageCache`'d.
-Epics for that work were:
-- Vectored `Timeline::get` (cf RFC 30) skipped delta and image layer data block `PageCache`ing outright.
-- Epic https://github.com/neondatabase/neon/issues/7386 took care of the remaining users for data blocks:
-  - Materialized page cache (cached materialized pages; shown to be ~0% hit rate in practice)
-  - InMemoryLayer
-  - Compaction
-
-The outcome of the above:
-1. All data blocks are always read through the `VirtualFile` APIs, hitting the kernel buffered read path (=> kernel page cache).
-2. Indirect blocks (=disk btree blocks) would be cached in the PS `PageCache`.
-
-In production we size the PS `PageCache` to be 2GiB.
-Thus drives hit rate up to ~99.95% and the eviction rate / replacement rates down to less than 200/second on a 1-minute average, on the busiest machines.
-High baseline replacement rates are treated as a signal of resource exhaustion (page cache insufficient to host working set of the PS).
-The response to this is to migrate tenants away, or increase PS `PageCache` size.
-It is currently manual but could be automated, e.g., in Storage Controller.
-
-In the future, we may eliminate the `PageCache` even for indirect blocks.
-For example with an LRU cache that has as unit the entire disk btree content
-instead of individual blocks.
-
-## High-Level Design
-
-So, before work on this project started, all data block reads and the entire write path of Pageserver were using kernel-buffered IO, i.e., the kernel page cache.
-We now want to get the kernel page cache out of the picture by using direct IO for all interaction with the filesystem.
-This achieves the following system properties:
-
-**Predictable VirtualFile latencies**
-* With buffered IO, reads are sometimes fast, sometimes slow, depending on kernel page cache hit/miss.
-* With buffered IO, appends when writing out new layer files during ingest or compaction are sometimes fast, sometimes slow because of write-back backpressure.
-* With buffered IO, the "malloc backscatter" phenomenon pointed out in the Glossary section is not something we actively observe.
-  But we do have occasional spikes in Dirty memory amount and Memory PSI graphs, so it may already be affecting to some degree.
-* By switching to direct IO, above operations will have the (predictable) device latency -- always.
-  Reads and appends always go to disk.
-  And malloc will not have to write back dirty data.
-
-**Explicitness & Tangibility of resource usage**
-* In a multi-tenant system, it is generally desirable and valuable to be *explicit* about the main resources we use for each tenant.
-* By using direct IO, we become explicit about the resources *disk IOPs*  and *memory capacity* in a way that was previously being conflated through the kernel page cache, outside our immediate control.
-* We will be able to build per-tenant observability of resource usage ("what tenant is causing the actual IOs that are sent to the disk?").
-* We will be able to build accounting & QoS by implementing an IO scheduler that is tenant aware. The kernel is not tenant-aware and can't do that.
-
-**CPU Efficiency**
-* The involvement of the kernel page cache means one additional memory-to-memory copy on read and write path.
-* Direct IO will eliminate that memory-to-memory copy, if we can make the userspace buffers used for the IO calls satisfy direct IO alignment requirements.
-
-The **trade-off** is that we no longer get the theoretical benefits of the kernel page cache. These are:
-- read latency improvements for repeat reads of the same data ("locality of reference")
-  - asterisk: only if that state is still cache-resident by time of next access
-- write throughput by having kernel page cache batch small VFS writes into bigger disk writes
-  - asterisk: only if memory pressure is low enough that the kernel can afford to delay writeback
-
-We are **happy to make this trade-off**:
-- Because of the advantages listed above.
-- Because we empirically have enough DRAM on Pageservers to serve metadata (=index blocks) from PS PageCache.
-  (At just 2GiB PS PageCache size, we average a 99.95% hit rate).
-  So, the latency of going to disk is only for data block reads, not the index traversal.
-- Because **the kernel page cache is ineffective** at high tenant density anyway (#tenants/pageserver instance).
-  And because dense packing of tenants will always be desirable to drive COGS down, we should design the system for it.
-  (See the appendix for a more detailed explanation why this is).
-- So, we accept that some reads that used to be fast by circumstance will have higher but **predictable** latency than before.
-
-### Desired End State
-
-The desired end state of the project is as follows, and with some asterisks, we have achieved it.
-
-All IOs of the Pageserver data path use direct IO, thereby bypassing the kernel page cache.
-
-In particular, the "data path" includes
-- the wal ingest path
-- compaction
-- anything on the `Timeline::get` / `Timeline::get_vectored` path.
-
-The production Pageserver config is tuned such that virtually all non-data blocks are cached in the PS PageCache.
-Hit rate target is 99.95%.
-
-There are no regressions to ingest latency.
-
-The total "wait-for-disk time" contribution to random getpage request latency is `O(1 read IOP latency)`.
-We accomplish that by having a near 100% PS PageCache hit rate so that layer index traversal effectively never needs not wait for IO.
-Thereby, it can issue all the data blocks as it traverses the index, and only wait at the end of it (concurrent IO).
-
-The amortized "wait-for-disk time" contribution of this direct IO proposal to a series of sequential getpage requests is `1/32 * read IOP latency` for each getpage request.
-We accomplish this by server-side batching of up to 32 reads into a single `Timeline::get_vectored` call.
-(This is an ideal world where our batches are full - that's not the case in prod today because of lack of queue depth).
-
-## Design & Implementation
-
-### Prerequisites
-
-A lot of prerequisite work had to happen to enable use of direct IO.
-
-To meet the "wait-for-disk time" requirements from the DoD, we implement for the read path:
-- page_service level server-side batching (config field `page_service_pipelining`)
-- concurrent IO (config field `get_vectored_concurrent_io`)
-The work for both of these these was tracked [in the epic](https://github.com/neondatabase/neon/issues/9376).
-Server-side batching will likely be obsoleted by the [#proj-compute-communicator](https://github.com/neondatabase/neon/pull/10799).
-The Concurrent IO work is described in retroactive RFC `2025-04-30-pageserver-concurrent-io-on-read-path.md`.
-The implementation is relatively brittle and needs further investment, see the `Future Work` section in that RFC.
-
-For the write path, and especially WAL ingest, we need to hide write latency.
-We accomplish this by implementing a (`BufferedWriter`) type that does double-buffering: flushes of the filled
-buffer happen in a sidecar tokio task while new writes fill a new buffer.
-We refactor InMemoryLayer as well as BlobWriter (=> delta and image layer writers) to use this new `BufferedWriter`.
-The most comprehensive write-up of this work is in [the PR description](https://github.com/neondatabase/neon/pull/11558).
-
-### Ensuring Adherence to Alignment Requirements
-
-Direct IO puts requirements on
-- memory buffer alignment
-- io size (=memory buffer size)
-- file offset alignment
-
-The requirements are specific to a combination of filesystem/block-device/architecture(hardware page size!).
-
-In Neon production environments we currently use ext4 with Linux 6.1.X on AWS and Azure storage-optimized instances (locally attached NVMe).
-Instead of dynamic discovery using `statx`, we statically hard-code 512 bytes as the buffer/offset alignment and size-multiple.
-We made this decision because:
-- a) it is compatible with all the environments we need to run in
-- b) our primary workload can be small-random-read-heavy (we do merge adjacent reads if possible, but the worst case is that all `Value`s that needs to be read are far apart)
-- c) 512-byte tail latency on the production instance types is much better than 4k (p99.9: 3x lower, p99.99 5x lower).
-- d) hard-coding at compile-time allows us to use the Rust type system to enforce the use of only aligned IO buffers, eliminating a source of runtime errors typically associated with direct IO.
-
-This was [discussed here](https://neondb.slack.com/archives/C07BZ38E6SD/p1725036790965549?thread_ts=1725026845.455259&cid=C07BZ38E6SD).
-
-The new `IoBufAligned` / `IoBufAlignedMut` marker traits indicate that a given buffer meets memory alignment requirements.
-All `VirtualFile` APIs and several software layers built on top of them only accept buffers that implement those traits.
-Implementors of the marker traits are:
-- `IoBuffer` / `IoBufferMut`: used for most reads and writes
-- `PageWriteGuardBuf`: for filling PS PageCache pages (index blocks!)
-
-The alignment requirement is infectious; it permeates bottom-up throughout the code base.
-We stop the infection at roughly the same layers in the code base where we stopped permeating the
-use of owned-buffers-style API for tokio-epoll-uring. The way the stopping works is by introducing
-a memory-to-memory copy from/to some unaligned memory location on the stack/current/heap.
-The places where we currently stop permeating are sort of arbitrary. For example, it would probably
-make sense to replace more usage of `Bytes` that we know holds 8k pages with 8k-sized `IoBuffer`s.
-
-The `IoBufAligned` / `IoBufAlignedMut` types do not protect us from the following types of runtime errors:
-- non-adherence to file offset alignment requirements
-- non-adherence to io size requirements
-
-The following higher-level constructs ensure we meet the requirements:
-- read path: the `ChunkedVectoredReadBuilder` and `mod vectored_dio_read` ensure reads happen at aligned offsets and in appropriate size multiples.
-- write path: `BufferedWriter` only writes in multiples of the capacity, at offsets that are `start_offset+N*capacity`; see its doc comment.
-
-Note that these types are used always, regardless of whether direct IO is enabled or not.
-There are some cases where this adds unnecessary overhead to buffered IO (e.g. all memcpy's inflated to multiples of 512).
-But we could not identify meaningful impact in practice when we shipped these changes while we were still using buffered IO.
-
-### Configuration / Feature Flagging
-
-In the previous section we described how all users of VirtualFile were changed to always adhere to direct IO alignment and size-multiple requirements.
-To actually enable direct IO, all we need to do is set the `O_DIRECT` flag in `open` syscalls / io_uring operations.
-
-We set `O_DIRECT` based on:
-- the VirtualFile API used to create/open the VirtualFile instance
-- the `virtual_file_io_mode` configuration flag
-- the OpenOptions `read` and/or `write` flags.
-
-The VirtualFile APIs suffixed with `_v2` are the only ones that _may_ open with `O_DIRECT` depending on the other two factors in above list.
-Other APIs never use `O_DIRECT`.
-(The name is bad and should really be `_maybe_direct_io`.)
-
-The reason for having new APIs is because all code used VirtualFile but implementation and rollout happened in consecutive phases (read path, InMemoryLayer, write path).
-At the VirtualFile level, context on whether an instance of VirtualFile is on read path, InMemoryLayer, or write path is not available.
-
-The `_v2` APIs then check make the decision to set `O_DIRECT` based on the `virtual_file_io_mode` flag and the OpenOptions `read`/`write` flags.
-The result is the following runtime behavior:
-
-|what|OpenOptions|`v_f_io_mode`<br/>=`buffered`|`v_f_io_mode`<br/>=`direct`|`v_f_io_mode`<br/>=`direct-rw`|
-|-|-|-|-|-|
-|`DeltaLayerInner`|read|()|O_DIRECT|O_DIRECT|
-|`ImageLayerInner`|read|()|O_DIRECT|O_DIRECT|
-|`InMemoryLayer`|read + write|()|()*|O_DIRECT|
-|`DeltaLayerWriter`| write | () | () |  O_DIRECT |
-|`ImageLayerWriter`| write | () | () |  O_DIRECT |
-|`download_layer_file`|write |()|()|O_DIRECT|
-
-The `InMemoryLayer` is marked with `*` because there was a period when it *did* use O_DIRECT under `=direct`.
-That period was when we implemented and shipped the first version of `BufferedWriter`.
-We used it in `InMemoryLayer` and `download_layer_file` but it was only sensitive to `v_f_io_mode` in `InMemoryLayer`.
-The introduction of `=direct-rw`, and the switch of the remaining write path to `BufferedWriter`, happened later,
-in https://github.com/neondatabase/neon/pull/11558.
-
-Note that this way of feature flagging inside VirtualFile makes it less and less a general purpose POSIX file access abstraction.
-For example, with `=direct-rw` enabled, it is no longer possible to open a `VirtualFile` without `O_DIRECT`. It'll always be set.
-
-## Correctness Validation
-
-The correctness risks with this project were:
-- Memory safety issues in the `IoBuffer` / `IoBufferMut` implementation.
-  These types expose an API that is largely identical to that of the `bytes` crate and/or Vec.
-- Runtime errors (=> downtime / unavailability) because of non-adherence to alignment/size-multiple requirements, resulting in EINVAL on the read path.
-
-We sadly do not have infrastructure to run pageserver under `cargo miri`.
-So for memory safety issues, we relied on careful peer review.
-
-We do assert the production-like alignment requirements in testing builds.
-However, these asserts were added retroactively.
-The actual validation before rollout happened in staging and pre-prod.
-We eventually enabled  `=direct`/`=direct-rw` for Rust unit tests and the regression test suite.
-I cannot recall a single instance of staging/pre-prod/production errors caused by non-adherence to alignment/size-multiple requirements.
-Evidently developer testing was good enough.
-
-## Performance Validation
-
-The read path went through a lot of iterations of benchmarking in staging and pre-prod.
-The benchmarks in those environments demonstrated performance regressions early in the implementation.
-It was actually this performance testing that made us implement batching and concurrent IO to avoid unacceptable regressions.
-
-The write path was much quicker to validate because `bench_ingest` covered all of the (less numerous) access patterns.
-
-## Future Work
-
-There is minor and major follow-up work that can be considered in the future.
-Check the (soon-to-be-closed) Epic https://github.com/neondatabase/neon/issues/8130's "Follow-Ups" section for a current list.
-
-Read Path:
-- PS PageCache hit rate is crucial to unlock concurrent IO and reasonable latency for random reads generally.
-  Instead of reactively sizing PS PageCache, we should estimate the required PS PageCache size
-  and potentially also use that to drive placement decisions of shards from StorageController
-  https://github.com/neondatabase/neon/issues/9288
-- ... unless we get rid of PS PageCache entirely and cache the index block in a more specialized cache.
-  But even then, an estimation of the working set would be helpful to figure out caching strategy.
-
-Write Path:
-- BlobWriter and its users could switch back to a borrowed API  https://github.com/neondatabase/neon/issues/10129
-- ... unless we want to implement bypass mode for large writes https://github.com/neondatabase/neon/issues/10101
-- The `TempVirtualFile` introduced as part of this project could internalize more of the common usage pattern: https://github.com/neondatabase/neon/issues/11692
-- Reduce conditional compilation around `virtual_file_io_mode`: https://github.com/neondatabase/neon/issues/11676
-
-Both:
-- A performance simulation mode that pads VirtualFile op latencies to typical NVMe latencies, even if the underlying storage is faster.
-  This would avoid misleadingly good performance on developer systems and in benchmarks on systems that are less busy than production hosts.
-  However, padding latencies at microsecond scale is non-trivial.
-
-Misc:
-- We should finish trimming VirtualFile's scope to be truly limited to core data path read & write.
-  Abstractions for reading & writing pageserver config, location config, heatmaps, etc, should use
-  APIs in a different package (`VirtualFile::crashsafe_overwrite` and `VirtualFile::read_to_string`
-  are good entrypoints for cleanup.) https://github.com/neondatabase/neon/issues/11809
-
-# Appendix
-
-## Why Kernel Page Cache Is Ineffective At Tenant High Density
-
-In the Motivation section, we stated:
-
-> - **The kernel page cache ineffective** at high tenant density anyways (#tenants/pageserver instance).
-
-The reason is that the  Pageserver workload sent from Computes is whatever is a Compute cache(s) miss.
-That's either sequential scans or random reads.
-A random read workload simply causes cache thrashing because a packed Pageserver NVMe drive (`im4gn.2xlarge`) has ~100x more capacity than DRAM available.
-It is complete waste to have the kernel page cache cache data blocks in this case.
-Sequential read workloads *can* benefit iff those pages have been updated recently (=no image layer yet) and together in time/LSN space.
-In such cases, the WAL records of those updates likely sit on the same delta layer block.
-When Compute does a sequential scan, it sends a series of single-page requests for these individual pages.
-When Pageserver processes the second request in such a series, it goes to the same delta layer block and have a kernel page cache hit.
-This dependence on kernel page cache for sequential scan performance is significant, but the solution is at a higher level than generic data block caching.
-We can either add a small per-connection LRU cache for such delta layer blocks.
-Or we can merge those sequential requests into a larger vectored get request, which is designed to never read a block twice.
-This amortizes the read latency for our delta layer block across the vectored get batch size (which currently is up to 32).
-
-There are Pageserver-internal workloads that do sequential access (compaction, image layer generation), but these
-1. are not latency-critical and can do batched access outside of the `page_service` protocol constraints (image layer generation)
-2. don't actually need to reconstruct images and therefore can use totally different access methods (=> compaction can use k-way merge iterators with their own internal buffering / prefetching).

docs/rfcs/2025-04-30-pageserver-concurrent-io-on-read-path.md

@@ -1,251 +0,0 @@
-# Concurrent IO for Pageserver Read Path
-
-Date: May 6, 2025
-
-## Summary
-
-This document is a retroactive RFC on the Pageserver Concurrent IO work that happened in late 2024 / early 2025.
-
-The gist of it is that Pageserver's `Timeline::get_vectored` now _issues_ the data block read operations against layer files
-_as it traverses the layer map_ and only _wait_ once, for all of them, after traversal is complete.
-
-Assuming a good PS PageCache hits on the index blocks during traversal, this drives down the "wait-for-disk" time
-contribution down from `random_read_io_latency * O(number_of_values)` to `random_read_io_latency * O(1 + traversal)`.
-
-The motivation for why this work had to happen when it happened was the switch of Pageserver to
-- not cache user data blocks in PS PageCache and
-- switch to use direct IO.
-More context on this are given in complimentary RFC `./rfcs/2025-04-30-direct-io-for-pageserver.md`.
-
-### Refs
-
-- Epic: https://github.com/neondatabase/neon/issues/9378
-- Prototyping happened during the Lisbon 2024 Offsite hackathon: https://github.com/neondatabase/neon/pull/9002
-- Main implementation PR with good description: https://github.com/neondatabase/neon/issues/9378
-
-Design and implementation by:
-- Vlad Lazar <vlad@neon.tech>
-- Christian Schwarz <christian@neon.tech>
-
-## Background & Motivation
-
-The Pageserver read path (`Timeline::get_vectored`) consists of two high-level steps:
-- Retrieve the delta and image `Value`s required to reconstruct the requested Page@LSN (`Timeline::get_values_reconstruct_data`).
-- Pass these values to walredo to reconstruct the page images.
-
-The read path used to be single-key but has been made multi-key some time ago.
-([Internal tech talk by Vlad](https://drive.google.com/file/d/1vfY24S869UP8lEUUDHRWKF1AJn8fpWoJ/view?usp=drive_link))
-However, for simplicity, most of this doc will explain things in terms of a single key being requested.
-
-The `Value` retrieval step above can be broken down into the following functions:
-- **Traversal** of the layer map to figure out which `Value`s from which layer files are required for the page reconstruction.
-- **Read IO Planning**: planning of the read IOs that need to be issued to the layer files / filesystem / disk.
-  The main job here is to coalesce the small value reads into larger filesystem-level read operations.
-  This layer also takes care of direct IO alignment and size-multiple requirements (cf the RFC for details.)
-  Check `struct VectoredReadPlanner` and `mod vectored_dio_read` for how it's done.
-- **Perform the read IO** using `tokio-epoll-uring`.
-
-Before this project, above functions were sequentially interleaved, meaning:
-1. we would advance traversal, ...
-2. discover, that we need to read a value, ...
-3. read it from disk using `tokio-epoll-uring`, ...
-4. goto 1 unless we're done.
-
-This meant that if N `Value`s need to be read to reconstruct a page,
-the time we spend waiting for disk will be we `random_read_io_latency * O(number_of_values)`.
-
-## Design
-
-The **traversal** and **read IO Planning** jobs still happen sequentially, layer by layer, as before.
-But instead of performing the read IOs inline, we submit the IOs to a concurrent tokio task for execution.
-After the last read from the last layer is submitted, we wait for the IOs to complete.
-
-Assuming the filesystem / disk is able to actually process the submitted IOs without queuing,
-we arrive at _time spent waiting for disk_ ~ `random_read_io_latency * O(1 + traversal)`.
-
-Note this whole RFC is concerned with the steady state where all layer files required for reconstruction are resident on local NVMe.
-Traversal will stall on on-demand layer download if a layer is not yet resident.
-It cannot proceed without the layer being resident beccause its next step depends on the contents of the layer index.
-
-### Avoiding Waiting For IO During Traversal
-
-The `traversal` component in above time-spent-waiting-for-disk estimation is dominant and needs to be minimized.
-
-Before this project, traversal needed to perform IOs for the following:
-1. The time we are waiting on PS PageCache to page in the visited layers' disk btree index blocks.
-2. When visiting a delta layer, reading the data block that contains a `Value` for a requested key,
-   to determine whether the `Value::will_init` the page and therefore traversal can stop for this key.
-
-The solution for (1) is to raise the PS PageCache size such that the hit rate is practically 100%.
-(Check out the `Background: History Of Caching In Pageserver` section in the RFC on Direct IO for more details.)
-
-The solution for (2) is source `will_init` from the disk btree index keys, which fortunately
-already encode this bit of information since the introduction of the current storage/layer format.
-
-### Concurrent IOs, Submission & Completion
-
-To separate IO submission from waiting for its completion,
-we introduce the notion of an `IoConcurrency` struct through which IOs are issued.
-
-An IO is an opaque future that
-- captures the `tx` side of a `oneshot` channel
-- performs the read IO by calling `VirtualFile::read_exact_at().await`
-- sending the result into the `tx`
-
-Issuing an IO means `Box`ing the future above and handing that `Box` over to the `IoConcurrency` struct.
-
-The traversal code that submits the IO stores the the corresponding `oneshot::Receiver`
-in the `VectoredValueReconstructState`, in the the place where we previously stored
-the sequentially read `img` and `records` fields.
-
-When we're done with traversal, we wait for all submitted IOs:
-for each key, there is a future that awaits all the `oneshot::Receiver`s
-for that key, and then calls into walredo to reconstruct the page image.
-Walredo is now invoked concurrently for each value instead of sequentially.
-Walredo itself remains unchanged.
-
-The spawned IO futures are driven to completion by a sidecar tokio task that
-is separate from the task that performs all the layer visiting and spawning of IOs.
-That tasks receives the IO futures via an unbounded mpsc channel and
-drives them to completion inside a `FuturedUnordered`.
-
-### Error handling, Panics, Cancellation-Safety
-
-There are two error classes during reconstruct data retrieval:
-* traversal errors: index lookup, move to next layer, and the like
-* value read IO errors
-
-A traversal error fails the entire `get_vectored` request, as before this PR.
-A value read error only fails reconstruction of that value.
-
-Panics and dropping of the `get_vectored` future before it completes
-leaves the sidecar task running and does not cancel submitted IOs
-(see next section for details on sidecar task lifecycle).
-All of this is safe, but, today's preference in the team is to close out
-all resource usage explicitly if possible, rather than cancelling + forgetting
-about it on drop. So, there is warning if we drop a
-`VectoredValueReconstructState`/`ValuesReconstructState` that still has uncompleted IOs.
-
-### Sidecar Task Lifecycle
-
-The sidecar tokio task is spawned as part of the `IoConcurrency::spawn_from_conf` struct.
-The `IoConcurrency` object acts as a handle through which IO futures are submitted.
-
-The spawned tokio task holds the `Timeline::gate` open.
-It is _not_ sensitive to `Timeline::cancel`, but instead to the `IoConcurrency` object being dropped.
-
-Once the `IoConcurrency` struct is dropped, no new IO futures can come in
-but already submitted IO futures will be driven to completion regardless.
-We _could_ safely stop polling these futures because `tokio-epoll-uring` op futures are cancel-safe.
-But the underlying kernel and hardware resources are not magically freed up by that.
-So, again, in the interest of closing out all outstanding resource usage, we make timeline shutdown wait for sidecar tasks and their IOs to complete.
-Under normal conditions, this should be in the low hundreds of microseconds.
-
-It is advisable to make the `IoConcurrency` as long-lived as possible to minimize the amount of
-tokio task churn (=> lower pressure on tokio). Generally this means creating it "high up" in the call stack.
-The pain with this is that the `IoConcurrency` reference needs to be propagated "down" to
-the (short-lived) functions/scope where we issue the IOs.
-We would like to use `RequestContext` for this propagation in the future (issue [here](https://github.com/neondatabase/neon/issues/10460)).
-For now, we just add another argument to the relevant code paths.
-
-### Feature Gating
-
-The `IoConcurrency` is an `enum` with two variants: `Sequential` and `SidecarTask`.
-
-The behavior from before this project is available through `IoConcurrency::Sequential`,
-which awaits the IO futures in place, without "spawning" or "submitting" them anywhere.
-
-The `get_vectored_concurrent_io` pageserver config variable determines the runtime value,
-**except** for the places that use `IoConcurrency::sequential` to get an `IoConcurrency` object.
-
-### Alternatives Explored & Caveats Encountered
-
-A few words on the rationale behind having a sidecar *task* and what
-alternatives were considered but abandoned.
-
-#### Why We Need A Sidecar *Task* / Why Just `FuturesUnordered` Doesn't Work
-
-We explored to not have a sidecar task, and instead have a `FuturesUnordered` per
-`Timeline::get_vectored`. We would queue all IO futures in it and poll it for the
-first time after traversal is complete (i.e., at `collect_pending_ios`).
-
-The obvious disadvantage, but not showstopper, is that we wouldn't be submitting
-IOs until traversal is complete.
-
-The showstopper however, is that deadlocks happen if we don't drive the
-IO futures to completion independently of the traversal task.
-The reason is that both the IO futures and the traversal task may hold _some_,
-_and_ try to acquire _more_, shared limited resources.
-For example, both the travseral task and IO future may try to acquire
-* a `VirtualFile` file descriptor cache slot async mutex (observed during impl)
-* a `tokio-epoll-uring` submission slot (observed during impl)
-* a `PageCache` slot (currently this is not the case but we may move more code into the IO futures in the future)
-
-#### Why We Don't Do `tokio::task`-per-IO-future
-
-Another option is to spawn a short-lived `tokio::task` for each IO future.
-We implemented and benchmarked it during development, but found little
-throughput improvement and moderate mean & tail latency degradation.
-Concerns about pressure on the tokio scheduler led us to abandon this variant.
-
-## Future Work
-
-In addition to what is listed here, also check the "Punted" list in the epic:
-https://github.com/neondatabase/neon/issues/9378
-
-### Enable `Timeline::get`
-
-The only major code path that still uses `IoConcurrency::sequential` is `Timeline::get`.
-The impact is that roughly the following parts of pageserver do not benefit yet:
-- parts of basebackup
-- reads performed by the ingest path
-- most internal operations that read metadata keys (e.g. `collect_keyspace`!)
-
-The solution is to propagate `IoConcurrency` via `RequestContext`:https://github.com/neondatabase/neon/issues/10460
-
-The tricky part is to figure out at which level of the code the `IoConcurrency` is spawned (and added to the RequestContext).
-
-Also, propagation via `RequestContext` makes makes it harder to tell during development whether a given
-piece of code uses concurrent vs sequential mode: one has to recurisvely walk up the call tree to find the
-place that puts the `IoConcurrency` into the `RequestContext`.
-We'd have to use `::Sequential` as the conservative default value in a fresh `RequestContext`, and add some
-observability to weed out places that fail to enrich with a properly spanwed `IoConcurrency::spawn_from_conf`.
-
-### Concurrent On-Demand Downloads enabled by Detached Indices
-
-As stated earlier, traversal stalls on on-demand download because its next step depends on the contents of the layer index.
-Once we have separated indices from data blocks (=> https://github.com/neondatabase/neon/issues/11695)
-we will only need to stall if the index is not resident. The download of the data blocks can happen concurrently or in the background. For example:
-- Move the `Layer::get_or_maybe_download().await` inside the IO futures.
-  This goes in the opposite direction of the next "future work" item below, but it's easy to do.
-- Serve the IO future directly from object storage and dispatch the layer download
-  to some other actor, e.g., an actor that is responsible for both downloads & eviction.
-
-### New `tokio-epoll-uring` API That Separates Submission & Wait-For-Completion
-
-Instead of `$op().await` style API, it would be useful to have a different `tokio-epoll-uring` API
-that separates enqueuing (without necessarily `io_uring_enter`ing the kernel each time), submission,
-and then wait for completion.
-
-The `$op().await` API is too opaque, so we _have_ to stuff it into a `FuturesUnordered`.
-
-A split API as sketched above would allow traversal to ensure an IO operation is enqueued to the kernel/disk (and get back-pressure iff the io_uring squeue is full).
-While avoiding spending of CPU cycles on processing of completions while we're still traversing.
-
-The idea gets muddied by the fact that we may self-deadlock if we submit too much without completing.
-So, the submission part of the split API needs to process completions if squeue is full.
-
-In any way, this split API is precondition for the bigger issue with the design presented here,
-which we dicsuss in the next section.
-
-### Opaque Futures Are Brittle
-
-The use of opaque futures to represent submitted IOs is a clever hack to minimize changes & allow for near-perfect feature-gating.
-However, we take on **brittleness** because callers must guarantee that the submitted futures are independent.
-By our experience, it is non-trivial to identify or rule out the interdependencies.
-See the lengthy doc comment on the `IoConcurrency::spawn_io` method for more details.
-
-The better interface and proper subsystem boundary is a _descriptive_ struct of what needs to be done ("read this range from this VirtualFile into this buffer")
-and get back a means to wait for completion.
-The subsystem can thereby reason by its own how operations may be related;
-unlike today, where the submitted opaque future can do just about anything.

docs/rfcs/images/036-bottom-most-gc-compaction/01-basic-idea.svg

@@ -1,135 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
-<svg xmlns="http://www.w3.org/2000/svg" xmlns:xl="http://www.w3.org/1999/xlink" xmlns:dc="http://purl.org/dc/elements/1.1/" version="1.1" viewBox="82 284 863 375" width="863" height="375">
-  <defs/>
-  <g id="01-basic-idea" stroke-opacity="1" stroke-dasharray="none" stroke="none" fill="none" fill-opacity="1">
-    <title>01-basic-idea</title>
-    <rect fill="white" x="82" y="284" width="863" height="375"/>
-    <g id="01-basic-idea_Layer_1">
-      <title>Layer 1</title>
-      <g id="Graphic_2">
-        <rect x="234" y="379.5" width="203.5" height="17.5" fill="white"/>
-        <rect x="234" y="379.5" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_3">
-        <rect x="453.5" y="379.5" width="203.5" height="17.5" fill="white"/>
-        <rect x="453.5" y="379.5" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_4">
-        <rect x="672.5" y="379.5" width="203.5" height="17.5" fill="white"/>
-        <rect x="672.5" y="379.5" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_5">
-        <rect x="234" y="288.5" width="127" height="77.5" fill="white"/>
-        <rect x="234" y="288.5" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_6">
-        <rect x="375" y="288.5" width="127" height="77.5" fill="white"/>
-        <rect x="375" y="288.5" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_7">
-        <rect x="516" y="288.5" width="127" height="77.5" fill="white"/>
-        <rect x="516" y="288.5" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_8">
-        <rect x="657" y="288.5" width="127" height="77.5" fill="white"/>
-        <rect x="657" y="288.5" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_9">
-        <rect x="798" y="288.5" width="78" height="77.5" fill="white"/>
-        <rect x="798" y="288.5" width="78" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_11">
-        <line x1="185.5" y1="326.75" x2="943.7734" y2="326.75" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_12">
-        <text transform="translate(87 318.026)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_13">
-        <text transform="translate(106.41 372.886)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="8.39" y="15" xml:space="preserve">Images </tspan>
-          <tspan font-family="Helvetica Neue" font-size="10" fill="black" x="29132252e-19" y="28.447998" xml:space="preserve">at earlier LSN</tspan>
-        </text>
-      </g>
-      <g id="Graphic_14">
-        <text transform="translate(121.92 289.578)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="8739676e-19" y="15" xml:space="preserve">Deltas</tspan>
-        </text>
-      </g>
-      <g id="Graphic_15">
-        <path d="M 517.125 423.5 L 553.375 423.5 L 553.375 482 L 571.5 482 L 535.25 512 L 499 482 L 517.125 482 Z" fill="white"/>
-        <path d="M 517.125 423.5 L 553.375 423.5 L 553.375 482 L 571.5 482 L 535.25 512 L 499 482 L 517.125 482 Z" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_26">
-        <rect x="234" y="599.474" width="203.5" height="17.5" fill="white"/>
-        <rect x="234" y="599.474" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_25">
-        <rect x="453.5" y="599.474" width="203.5" height="17.5" fill="white"/>
-        <rect x="453.5" y="599.474" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_24">
-        <rect x="672.5" y="599.474" width="203.5" height="17.5" fill="white"/>
-        <rect x="672.5" y="599.474" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_23">
-        <rect x="234" y="533" width="127" height="52.974" fill="white"/>
-        <rect x="234" y="533" width="127" height="52.974" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_22">
-        <rect x="375" y="533" width="310.5" height="52.974" fill="white"/>
-        <rect x="375" y="533" width="310.5" height="52.974" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_21">
-        <rect x="702.5" y="533" width="173.5" height="52.974" fill="white"/>
-        <rect x="702.5" y="533" width="173.5" height="52.974" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_18">
-        <line x1="185.5" y1="607.724" x2="943.7734" y2="607.724" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_16">
-        <text transform="translate(121.92 538)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="8739676e-19" y="15" xml:space="preserve">Deltas</tspan>
-        </text>
-      </g>
-      <g id="Graphic_27">
-        <text transform="translate(114.8 592.86)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="3488765e-18" y="15" xml:space="preserve">Images </tspan>
-          <tspan font-family="Helvetica Neue" font-size="10" fill="black" x="4.01" y="28.447998" xml:space="preserve">at GC LSN</tspan>
-        </text>
-      </g>
-      <g id="Graphic_28">
-        <rect x="243.06836" y="300" width="624.3633" height="17.5" fill="#c0ffc0"/>
-        <text transform="translate(248.06836 301.068)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="13" fill="black" x="233.52364" y="12" xml:space="preserve">Deltas above GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_30">
-        <rect x="243.06836" y="335.5" width="624.3633" height="17.5" fill="#c0ffff"/>
-        <text transform="translate(248.06836 336.568)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="13" fill="black" x="233.89414" y="12" xml:space="preserve">Deltas below GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_32">
-        <rect x="243.06836" y="550.737" width="624.3633" height="17.5" fill="#c0ffc0"/>
-        <text transform="translate(248.06836 551.805)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="13" fill="black" x="233.52364" y="12" xml:space="preserve">Deltas above GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_33">
-        <rect x="304" y="630.474" width="485.5" height="28.447998" fill="#c0ffff"/>
-        <text transform="translate(309 637.016)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="13" fill="black" x="63.095" y="12" xml:space="preserve">Deltas and image below GC Horizon gets garbage-collected</tspan>
-        </text>
-      </g>
-      <g id="Graphic_34">
-        <text transform="translate(576.5 444.0325)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" x="0" y="11" xml:space="preserve">WAL replay of deltas+image below GC Horizon</tspan>
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" x="0" y="25.336" xml:space="preserve">Reshuffle deltas</tspan>
-        </text>
-      </g>
-    </g>
-  </g>
-</svg>

docs/rfcs/images/036-bottom-most-gc-compaction/03-retain-lsn.svg

@@ -1,141 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
-<svg xmlns="http://www.w3.org/2000/svg" xmlns:xl="http://www.w3.org/1999/xlink" xmlns:dc="http://purl.org/dc/elements/1.1/" version="1.1" viewBox="-104 215 863 335" width="863" height="335">
-  <defs>
-    <marker orient="auto" overflow="visible" markerUnits="strokeWidth" id="FilledArrow_Marker" stroke-linejoin="miter" stroke-miterlimit="10" viewBox="-1 -4 10 8" markerWidth="10" markerHeight="8" color="#7f8080">
-      <g>
-        <path d="M 8 0 L 0 -3 L 0 3 Z" fill="currentColor" stroke="currentColor" stroke-width="1"/>
-      </g>
-    </marker>
-  </defs>
-  <g id="03-retain-lsn" stroke-opacity="1" stroke-dasharray="none" stroke="none" fill="none" fill-opacity="1">
-    <title>03-retain-lsn</title>
-    <rect fill="white" x="-104" y="215" width="863" height="335"/>
-    <g id="03-retain-lsn_Layer_1">
-      <title>Layer 1</title>
-      <g id="Graphic_28">
-        <rect x="48" y="477" width="203.5" height="9.990005" fill="white"/>
-        <rect x="48" y="477" width="203.5" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_27">
-        <rect x="267.5" y="477" width="203.5" height="9.990005" fill="white"/>
-        <rect x="267.5" y="477" width="203.5" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_26">
-        <rect x="486.5" y="477" width="203.5" height="9.990005" fill="white"/>
-        <rect x="486.5" y="477" width="203.5" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_20">
-        <line x1="-.5" y1="387.172" x2="757.7734" y2="387.172" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_19">
-        <text transform="translate(-99 378.448)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_31">
-        <rect x="48.25" y="410" width="203.5" height="9.990005" fill="white"/>
-        <rect x="48.25" y="410" width="203.5" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_30">
-        <rect x="267.75" y="410" width="203.5" height="9.990005" fill="white"/>
-        <rect x="267.75" y="410" width="203.5" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_29">
-        <rect x="486.75" y="410" width="203.5" height="9.990005" fill="white"/>
-        <rect x="486.75" y="410" width="203.5" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_34">
-        <rect x="48.25" y="431.495" width="113.75" height="34" fill="white"/>
-        <rect x="48.25" y="431.495" width="113.75" height="34" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_33">
-        <rect x="172.5" y="431.495" width="203.5" height="34" fill="white"/>
-        <rect x="172.5" y="431.495" width="203.5" height="34" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_32">
-        <rect x="386.5" y="431.495" width="303.5" height="34" fill="white"/>
-        <rect x="386.5" y="431.495" width="303.5" height="34" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_37">
-        <rect x="48" y="498.495" width="203.5" height="9.990005" fill="white"/>
-        <rect x="48" y="498.495" width="203.5" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_36">
-        <rect x="267.5" y="498.495" width="203.5" height="9.990005" fill="white"/>
-        <rect x="267.5" y="498.495" width="203.5" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_35">
-        <rect x="486.5" y="498.495" width="203.5" height="9.990005" fill="white"/>
-        <rect x="486.5" y="498.495" width="203.5" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_38">
-        <line x1="-10.48" y1="535.5395" x2="39.318294" y2="508.24794" marker-end="url(#FilledArrow_Marker)" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_39">
-        <text transform="translate(-96.984 526.3155)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="40500936e-20" y="15" xml:space="preserve">retain_lsn 1</tspan>
-        </text>
-      </g>
-      <g id="Line_41">
-        <line x1="-10.48" y1="507.0915" x2="38.90236" y2="485.8992" marker-end="url(#FilledArrow_Marker)" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_40">
-        <text transform="translate(-96.984 497.8675)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="40500936e-20" y="15" xml:space="preserve">retain_lsn 2</tspan>
-        </text>
-      </g>
-      <g id="Line_43">
-        <line x1="-10.48" y1="478.6435" x2="39.44267" y2="453.01616" marker-end="url(#FilledArrow_Marker)" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_42">
-        <text transform="translate(-96.984 469.4195)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="40500936e-20" y="15" xml:space="preserve">retain_lsn 3</tspan>
-        </text>
-      </g>
-      <g id="Line_45">
-        <line x1="-10.48" y1="448.495" x2="39.65061" y2="419.90015" marker-end="url(#FilledArrow_Marker)" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_44">
-        <text transform="translate(-96.984 439.271)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="40500936e-20" y="15" xml:space="preserve">retain_lsn 4</tspan>
-        </text>
-      </g>
-      <g id="Graphic_46">
-        <rect x="335.46477" y="215.5" width="353.4299" height="125.495" fill="white"/>
-        <rect x="335.46477" y="215.5" width="353.4299" height="125.495" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_48">
-        <text transform="translate(549.3766 317.547)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="6536993e-19" y="15" xml:space="preserve">Dependent Branch</tspan>
-        </text>
-      </g>
-      <g id="Graphic_50">
-        <text transform="translate(340.43824 317.547)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="40500936e-20" y="15" xml:space="preserve">retain_lsn 3</tspan>
-        </text>
-      </g>
-      <g id="Line_57">
-        <line x1="323.90685" y1="248.8045" x2="714.9232" y2="248.8045" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_56">
-        <text transform="translate(165.91346 240.0805)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="35811354e-19" y="15" xml:space="preserve">Branch GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_58">
-        <rect x="493.9232" y="301.6405" width="107.45294" height="9.990005" fill="white"/>
-        <rect x="493.9232" y="301.6405" width="107.45294" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_59">
-        <text transform="translate(358.9232 277.276)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">Partial Image Coverage</tspan>
-        </text>
-      </g>
-      <g id="Graphic_60">
-        <rect x="354.1732" y="301.6405" width="107.45294" height="9.990005" fill="white"/>
-        <rect x="354.1732" y="301.6405" width="107.45294" height="9.990005" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-    </g>
-  </g>
-</svg>

docs/rfcs/images/036-bottom-most-gc-compaction/05-btmgc-parent.svg

@@ -1,187 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
-<svg xmlns="http://www.w3.org/2000/svg" xmlns:xl="http://www.w3.org/1999/xlink" xmlns:dc="http://purl.org/dc/elements/1.1/" version="1.1" viewBox="-235 426 864 366" width="864" height="366">
-  <defs/>
-  <g id="05-btmgc-parent" stroke-opacity="1" stroke-dasharray="none" stroke="none" fill="none" fill-opacity="1">
-    <title>05-btmgc-parent</title>
-    <rect fill="white" x="-235" y="426" width="864" height="366"/>
-    <g id="05-btmgc-parent_Layer_1">
-      <title>Layer 1</title>
-      <g id="Graphic_23">
-        <rect x="-83" y="510.15" width="203.5" height="26.391998" fill="white"/>
-        <rect x="-83" y="510.15" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-78 516.178)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" x="51.714" y="11" xml:space="preserve">Append C@0x30</tspan>
-        </text>
-      </g>
-      <g id="Graphic_22">
-        <rect x="136.5" y="510.15" width="203.5" height="26.391998" fill="white"/>
-        <rect x="136.5" y="510.15" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_21">
-        <rect x="355.5" y="510.15" width="203.5" height="26.391998" fill="white"/>
-        <rect x="355.5" y="510.15" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_20">
-        <line x1="-100.448" y1="459.224" x2="626.77344" y2="459.224" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_19">
-        <text transform="translate(-230 450.5)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_18">
-        <rect x="-82.75" y="426.748" width="203.5" height="26.391998" fill="white"/>
-        <rect x="-82.75" y="426.748" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-77.75 432.776)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" x="52.602" y="11" xml:space="preserve">Append F@0x60</tspan>
-        </text>
-      </g>
-      <g id="Graphic_17">
-        <rect x="136.75" y="426.748" width="203.5" height="26.391998" fill="white"/>
-        <rect x="136.75" y="426.748" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_16">
-        <rect x="355.75" y="426.748" width="203.5" height="26.391998" fill="white"/>
-        <rect x="355.75" y="426.748" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_15">
-        <rect x="-82.75" y="464.645" width="113.75" height="34" fill="white"/>
-        <rect x="-82.75" y="464.645" width="113.75" height="34" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-77.75 467.309)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" x="7.505" y="11" xml:space="preserve">Append E@0x50</tspan>
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" x="6.947" y="25.336" xml:space="preserve">Append D@0x40</tspan>
-        </text>
-      </g>
-      <g id="Graphic_14">
-        <rect x="41.5" y="464.645" width="203.5" height="34" fill="white"/>
-        <rect x="41.5" y="464.645" width="203.5" height="34" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_13">
-        <rect x="255.5" y="464.645" width="303.5" height="34" fill="white"/>
-        <rect x="255.5" y="464.645" width="303.5" height="34" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_12">
-        <rect x="-83" y="548.047" width="203.5" height="26.391998" fill="white"/>
-        <rect x="-83" y="548.047" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-78 554.075)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" x="26.796" y="11" xml:space="preserve">A@0x10, Append B@0x20</tspan>
-        </text>
-      </g>
-      <g id="Graphic_11">
-        <rect x="136.5" y="548.047" width="203.5" height="26.391998" fill="white"/>
-        <rect x="136.5" y="548.047" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_10">
-        <rect x="355.5" y="548.047" width="203.5" height="26.391998" fill="white"/>
-        <rect x="355.5" y="548.047" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_24">
-        <line x1="-104" y1="542" x2="610.5" y2="542" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-dasharray="4.0,4.0" stroke-width="1"/>
-      </g>
-      <g id="Graphic_25">
-        <text transform="translate(-139.604 534.5)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="14" fill="black" x="0" y="13" xml:space="preserve">0x20</tspan>
-        </text>
-      </g>
-      <g id="Graphic_28">
-        <text transform="translate(-139.604 452.556)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="14" fill="black" x="0" y="13" xml:space="preserve">0x50</tspan>
-        </text>
-      </g>
-      <g id="Line_30">
-        <line x1="-100.448" y1="481.145" x2="614.052" y2="481.145" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-dasharray="4.0,4.0" stroke-width="1"/>
-      </g>
-      <g id="Graphic_29">
-        <text transform="translate(-139.604 473.449)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="14" fill="black" x="0" y="13" xml:space="preserve">0x40</tspan>
-        </text>
-      </g>
-      <g id="Line_48">
-        <line x1="-99.448" y1="701.513" x2="627.77344" y2="701.513" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_47">
-        <text transform="translate(-229 692.789)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_46">
-        <rect x="-81.75" y="670.496" width="113.75" height="26.391998" fill="white"/>
-        <rect x="-81.75" y="670.496" width="113.75" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-76.75 676.524)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" x="7.727" y="11" xml:space="preserve">Append F@0x60</tspan>
-        </text>
-      </g>
-      <g id="Graphic_43">
-        <rect x="-81.75" y="708.393" width="113.75" height="34" fill="white"/>
-        <rect x="-81.75" y="708.393" width="113.75" height="34" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-76.75 718.225)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" x="7.505" y="11" xml:space="preserve">Append E@0x50</tspan>
-        </text>
-      </g>
-      <g id="Line_37">
-        <line x1="-101" y1="777.2665" x2="613.5" y2="777.2665" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-dasharray="4.0,4.0" stroke-width="1"/>
-      </g>
-      <g id="Graphic_36">
-        <text transform="translate(-138.604 769.7665)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="14" fill="black" x="0" y="13" xml:space="preserve">0x20</tspan>
-        </text>
-      </g>
-      <g id="Graphic_33">
-        <text transform="translate(-138.604 694.845)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="14" fill="black" x="0" y="13" xml:space="preserve">0x50</tspan>
-        </text>
-      </g>
-      <g id="Line_32">
-        <line x1="-99.448" y1="755.089" x2="615.052" y2="755.089" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-dasharray="4.0,4.0" stroke-width="1"/>
-      </g>
-      <g id="Graphic_31">
-        <text transform="translate(-138.604 747.393)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="14" fill="black" x="0" y="13" xml:space="preserve">0x40</tspan>
-        </text>
-      </g>
-      <g id="Graphic_40">
-        <rect x="-82" y="770.909" width="203.5" height="14.107002" fill="white"/>
-        <rect x="-82" y="770.909" width="203.5" height="14.107002" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-77 770.7945)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" x="70.836" y="11" xml:space="preserve">AB@0x20</tspan>
-        </text>
-      </g>
-      <g id="Graphic_39">
-        <rect x="137.5" y="770.909" width="203.5" height="14.107002" fill="white"/>
-        <rect x="137.5" y="770.909" width="203.5" height="14.107002" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_38">
-        <rect x="356.5" y="770.909" width="203.5" height="14.107002" fill="white"/>
-        <rect x="356.5" y="770.909" width="203.5" height="14.107002" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_54">
-        <rect x="-81.75" y="748.5355" width="203.5" height="14.107002" fill="white"/>
-        <rect x="-81.75" y="748.5355" width="203.5" height="14.107002" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-76.75 748.421)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" x="62.28" y="11" xml:space="preserve">ABCD@0x40</tspan>
-        </text>
-      </g>
-      <g id="Graphic_53">
-        <rect x="137.75" y="748.5355" width="203.5" height="14.107002" fill="white"/>
-        <rect x="137.75" y="748.5355" width="203.5" height="14.107002" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_52">
-        <rect x="356.75" y="748.5355" width="203.5" height="14.107002" fill="white"/>
-        <rect x="356.75" y="748.5355" width="203.5" height="14.107002" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_57">
-        <path d="M 211.32422 585 L 265.17578 585 L 265.17578 611.332 L 287.84375 611.332 L 238.25 633.117 L 188.65625 611.332 L 211.32422 611.332 Z" fill="white"/>
-        <path d="M 211.32422 585 L 265.17578 585 L 265.17578 611.332 L 287.84375 611.332 L 238.25 633.117 L 188.65625 611.332 L 211.32422 611.332 Z" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_60">
-        <rect x="359" y="692.858" width="203.5" height="14.107002" fill="white"/>
-        <rect x="359" y="692.858" width="203.5" height="14.107002" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_59">
-        <rect x="41.5" y="693.858" width="303" height="14.107002" fill="white"/>
-        <rect x="41.5" y="693.858" width="303" height="14.107002" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-    </g>
-  </g>
-</svg>

docs/rfcs/images/036-bottom-most-gc-compaction/06-btmgc-child.svg

@@ -1,184 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
-<svg xmlns="http://www.w3.org/2000/svg" xmlns:xl="http://www.w3.org/1999/xlink" xmlns:dc="http://purl.org/dc/elements/1.1/" version="1.1" viewBox="-413 471 931 354" width="931" height="354">
-  <defs/>
-  <g id="06-btmgc-child" stroke-opacity="1" stroke-dasharray="none" stroke="none" fill="none" fill-opacity="1">
-    <title>06-btmgc-child</title>
-    <rect fill="white" x="-413" y="471" width="931" height="354"/>
-    <g id="06-btmgc-child_Layer_1">
-      <title>Layer 1</title>
-      <g id="Graphic_47">
-        <rect x="-412" y="594.402" width="928" height="28.447998" fill="white"/>
-        <rect x="-412" y="594.402" width="928" height="28.447998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_46">
-        <rect x="-205" y="555.552" width="203.5" height="26.391998" fill="white"/>
-        <rect x="-205" y="555.552" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-200 561.58)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" x="52.158" y="11" xml:space="preserve">Append P@0x30</tspan>
-        </text>
-      </g>
-      <g id="Graphic_45">
-        <rect x="14.5" y="555.552" width="203.5" height="26.391998" fill="white"/>
-        <rect x="14.5" y="555.552" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_44">
-        <rect x="233.5" y="555.552" width="203.5" height="26.391998" fill="white"/>
-        <rect x="233.5" y="555.552" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_43">
-        <line x1="-222.448" y1="504.724" x2="504.77344" y2="504.724" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_42">
-        <text transform="translate(-352 496)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_41">
-        <rect x="-204.75" y="472.15" width="203.5" height="26.391998" fill="white"/>
-        <rect x="-204.75" y="472.15" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-199.75 478.178)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" x="52.158" y="11" xml:space="preserve">Append S@0x60</tspan>
-        </text>
-      </g>
-      <g id="Graphic_40">
-        <rect x="14.75" y="472.15" width="203.5" height="26.391998" fill="white"/>
-        <rect x="14.75" y="472.15" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_39">
-        <rect x="233.75" y="472.15" width="203.5" height="26.391998" fill="white"/>
-        <rect x="233.75" y="472.15" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_38">
-        <rect x="-204.75" y="510.047" width="113.75" height="34" fill="white"/>
-        <rect x="-204.75" y="510.047" width="113.75" height="34" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-199.75 512.711)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" x="7.061" y="11" xml:space="preserve">Append R@0x50</tspan>
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" x="6.611" y="25.336" xml:space="preserve">Append Q@0x40</tspan>
-        </text>
-      </g>
-      <g id="Graphic_37">
-        <rect x="-80.5" y="510.047" width="203.5" height="34" fill="white"/>
-        <rect x="-80.5" y="510.047" width="203.5" height="34" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_36">
-        <rect x="133.5" y="510.047" width="303.5" height="34" fill="white"/>
-        <rect x="133.5" y="510.047" width="303.5" height="34" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_33">
-        <text transform="translate(-261.604 498.056)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="14" fill="black" x="0" y="13" xml:space="preserve">0x50</tspan>
-        </text>
-      </g>
-      <g id="Line_30">
-        <line x1="-224" y1="607.9115" x2="490.5" y2="607.9115" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-dasharray="4.0,4.0" stroke-width="1"/>
-      </g>
-      <g id="Graphic_29">
-        <text transform="translate(-261.604 600.4115)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="14" fill="black" x="0" y="13" xml:space="preserve">0x20</tspan>
-        </text>
-      </g>
-      <g id="Graphic_28">
-        <rect x="-205" y="601.554" width="203.5" height="14.107002" fill="white"/>
-        <rect x="-205" y="601.554" width="203.5" height="14.107002" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-200 601.4395)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" x="70.836" y="11" xml:space="preserve">AB@0x20</tspan>
-        </text>
-      </g>
-      <g id="Graphic_27">
-        <rect x="14.5" y="601.554" width="203.5" height="14.107002" fill="white"/>
-        <rect x="14.5" y="601.554" width="203.5" height="14.107002" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_26">
-        <rect x="233.5" y="601.554" width="203.5" height="14.107002" fill="white"/>
-        <rect x="233.5" y="601.554" width="203.5" height="14.107002" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_25">
-        <text transform="translate(-407 599.1875)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">Ancestor Branch</tspan>
-        </text>
-      </g>
-      <g id="Graphic_24">
-        <rect x="-411" y="795.46" width="928" height="28.447998" fill="white"/>
-        <rect x="-411" y="795.46" width="928" height="28.447998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_20">
-        <line x1="-221.448" y1="755.528" x2="505.77344" y2="755.528" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_19">
-        <text transform="translate(-351 746.804)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_18">
-        <rect x="-203.75" y="723.579" width="203.25" height="26.391998" fill="white"/>
-        <rect x="-203.75" y="723.579" width="203.25" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-198.75 729.607)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" x="52.033" y="11" xml:space="preserve">Append S@0x60</tspan>
-        </text>
-      </g>
-      <g id="Graphic_10">
-        <text transform="translate(-260.604 748.86)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="14" fill="black" x="0" y="13" xml:space="preserve">0x50</tspan>
-        </text>
-      </g>
-      <g id="Line_7">
-        <line x1="-223" y1="808.9695" x2="491.5" y2="808.9695" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-dasharray="4.0,4.0" stroke-width="1"/>
-      </g>
-      <g id="Graphic_6">
-        <text transform="translate(-260.604 801.4695)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="14" fill="black" x="0" y="13" xml:space="preserve">0x20</tspan>
-        </text>
-      </g>
-      <g id="Graphic_5">
-        <rect x="-204" y="802.612" width="203.5" height="14.107002" fill="white"/>
-        <rect x="-204" y="802.612" width="203.5" height="14.107002" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-199 802.4975)" fill="#b1001c">
-          <tspan font-family="Helvetica Neue" font-size="12" fill="#b1001c" x="70.836" y="11" xml:space="preserve">AB</tspan>
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" y="11" xml:space="preserve">@0x20</tspan>
-        </text>
-      </g>
-      <g id="Graphic_4">
-        <rect x="15.5" y="802.612" width="203.5" height="14.107002" fill="white"/>
-        <rect x="15.5" y="802.612" width="203.5" height="14.107002" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_3">
-        <rect x="234.5" y="802.612" width="203.5" height="14.107002" fill="white"/>
-        <rect x="234.5" y="802.612" width="203.5" height="14.107002" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_2">
-        <text transform="translate(-406 800.2455)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">Ancestor Branch</tspan>
-        </text>
-      </g>
-      <g id="Graphic_48">
-        <path d="M 89.32422 639.081 L 143.17578 639.081 L 143.17578 665.413 L 165.84375 665.413 L 116.25 687.198 L 66.65625 665.413 L 89.32422 665.413 Z" fill="white"/>
-        <path d="M 89.32422 639.081 L 143.17578 639.081 L 143.17578 665.413 L 165.84375 665.413 L 116.25 687.198 L 66.65625 665.413 L 89.32422 665.413 Z" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_49">
-        <rect x="-204" y="762.428" width="203.5" height="26.391998" fill="white"/>
-        <rect x="-204" y="762.428" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-199 768.456)" fill="#b1001c">
-          <tspan font-family="Helvetica Neue" font-size="12" fill="#b1001c" x="58.278" y="11" xml:space="preserve">AB</tspan>
-          <tspan font-family="Helvetica Neue" font-size="12" fill="black" y="11" xml:space="preserve">PQR@0x50</tspan>
-        </text>
-      </g>
-      <g id="Graphic_59">
-        <rect x="14.5" y="723.579" width="203.5" height="26.391998" fill="white"/>
-        <rect x="14.5" y="723.579" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_58">
-        <rect x="233.5" y="723.579" width="203.5" height="26.391998" fill="white"/>
-        <rect x="233.5" y="723.579" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_63">
-        <rect x="9" y="762.085" width="203.5" height="26.391998" fill="white"/>
-        <rect x="9" y="762.085" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_62">
-        <rect x="225" y="762.085" width="213" height="26.391998" fill="white"/>
-        <rect x="225" y="762.085" width="213" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-    </g>
-  </g>
-</svg>

docs/rfcs/images/036-bottom-most-gc-compaction/07-btmgc-analysis-1.svg

@@ -1,180 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
-<svg xmlns="http://www.w3.org/2000/svg" xmlns:xl="http://www.w3.org/1999/xlink" xmlns:dc="http://purl.org/dc/elements/1.1/" version="1.1" viewBox="-556 476 923 411" width="923" height="411">
-  <defs/>
-  <g id="07-btmgc-analysis-1" stroke-opacity="1" stroke-dasharray="none" stroke="none" fill="none" fill-opacity="1">
-    <title>07-btmgc-analysis-1</title>
-    <rect fill="white" x="-556" y="476" width="923" height="411"/>
-    <g id="07-btmgc-analysis-1_Layer_1">
-      <title>Layer 1</title>
-      <g id="Graphic_85">
-        <rect x="-404" y="609.062" width="203.5" height="17.5" fill="white"/>
-        <rect x="-404" y="609.062" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_84">
-        <rect x="-184.5" y="609.062" width="203.5" height="17.5" fill="white"/>
-        <rect x="-184.5" y="609.062" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_83">
-        <rect x="34.5" y="609.062" width="203.5" height="17.5" fill="white"/>
-        <rect x="34.5" y="609.062" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_82">
-        <rect x="-404" y="479.922" width="127" height="77.5" fill="white"/>
-        <rect x="-404" y="479.922" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_81">
-        <rect x="-263" y="479.922" width="127" height="77.5" fill="white"/>
-        <rect x="-263" y="479.922" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_80">
-        <rect x="-122" y="479.922" width="127" height="77.5" fill="white"/>
-        <rect x="-122" y="479.922" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_79">
-        <rect x="19" y="479.922" width="127" height="77.5" fill="white"/>
-        <rect x="19" y="479.922" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_78">
-        <rect x="160" y="479.922" width="78" height="77.5" fill="white"/>
-        <rect x="160" y="479.922" width="78" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_77">
-        <line x1="-452.5" y1="518.172" x2="251" y2="518.172" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_76">
-        <text transform="translate(-551 509.448)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_75">
-        <text transform="translate(-531.59 602.448)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="8.39" y="15" xml:space="preserve">Images </tspan>
-          <tspan font-family="Helvetica Neue" font-size="10" fill="black" x="29132252e-19" y="28.447998" xml:space="preserve">at earlier LSN</tspan>
-        </text>
-      </g>
-      <g id="Graphic_74">
-        <text transform="translate(-516.08 481)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="8739676e-19" y="15" xml:space="preserve">Deltas</tspan>
-        </text>
-      </g>
-      <g id="Graphic_73">
-        <path d="M -120.675 651.5 L -84.425 651.5 L -84.425 710 L -66.3 710 L -102.55 740 L -138.8 710 L -120.675 710 Z" fill="white"/>
-        <path d="M -120.675 651.5 L -84.425 651.5 L -84.425 710 L -66.3 710 L -102.55 740 L -138.8 710 L -120.675 710 Z" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_72">
-        <rect x="-403.8" y="827.474" width="203.5" height="17.5" fill="white"/>
-        <rect x="-403.8" y="827.474" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_71">
-        <rect x="-184.3" y="827.474" width="203.5" height="17.5" fill="white"/>
-        <rect x="-184.3" y="827.474" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_70">
-        <rect x="34.7" y="827.474" width="203.5" height="17.5" fill="white"/>
-        <rect x="34.7" y="827.474" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_69">
-        <rect x="-403.8" y="761" width="127" height="52.974" fill="white"/>
-        <rect x="-403.8" y="761" width="127" height="52.974" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_68">
-        <rect x="-262.8" y="761" width="310.5" height="52.974" fill="white"/>
-        <rect x="-262.8" y="761" width="310.5" height="52.974" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_67">
-        <rect x="64.7" y="761" width="173.5" height="52.974" fill="white"/>
-        <rect x="64.7" y="761" width="173.5" height="52.974" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_66">
-        <line x1="-452.3" y1="835.724" x2="251.2" y2="835.724" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_65">
-        <text transform="translate(-515.88 766)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="8739676e-19" y="15" xml:space="preserve">Deltas</tspan>
-        </text>
-      </g>
-      <g id="Graphic_64">
-        <text transform="translate(-523 820.86)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="3488765e-18" y="15" xml:space="preserve">Images </tspan>
-          <tspan font-family="Helvetica Neue" font-size="10" fill="black" x="4.01" y="28.447998" xml:space="preserve">at GC LSN</tspan>
-        </text>
-      </g>
-      <g id="Graphic_63">
-        <rect x="-394.93164" y="491.422" width="624.3633" height="17.5" fill="#c0ffc0"/>
-        <text transform="translate(-389.93164 492.49)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="13" fill="black" x="233.52364" y="12" xml:space="preserve">Deltas above GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_62">
-        <rect x="-394.93164" y="526.922" width="624.3633" height="17.5" fill="#c0ffff"/>
-        <text transform="translate(-389.93164 527.99)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="13" fill="black" x="233.89414" y="12" xml:space="preserve">Deltas below GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_61">
-        <rect x="-394.73164" y="778.737" width="624.3633" height="17.5" fill="#c0ffc0"/>
-        <text transform="translate(-389.73164 779.805)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="13" fill="black" x="233.52364" y="12" xml:space="preserve">Deltas above GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_60">
-        <rect x="-333.8" y="858.474" width="485.5" height="28.447998" fill="#c0ffff"/>
-        <text transform="translate(-328.8 865.016)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="13" fill="black" x="63.095" y="12" xml:space="preserve">Deltas and image below GC Horizon gets garbage-collected</tspan>
-        </text>
-      </g>
-      <g id="Graphic_86">
-        <text transform="translate(263 499.724)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="32" fill="black" x="0" y="30" xml:space="preserve">size=A</tspan>
-        </text>
-      </g>
-      <g id="Line_87">
-        <line x1="260.87012" y1="479.068" x2="360.71387" y2="479.068" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_88">
-        <line x1="260.87012" y1="561" x2="360.71387" y2="561" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_89">
-        <rect x="-403.8" y="569" width="161.8" height="28.447998" fill="white"/>
-        <rect x="-403.8" y="569" width="161.8" height="28.447998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_90">
-        <rect x="-229.5" y="569.018" width="277.2" height="28.447998" fill="white"/>
-        <rect x="-229.5" y="569.018" width="277.2" height="28.447998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_91">
-        <rect x="64.7" y="569.018" width="173.5" height="28.447998" fill="white"/>
-        <rect x="64.7" y="569.018" width="173.5" height="28.447998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_92">
-        <line x1="262" y1="602" x2="361.84375" y2="602" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_93">
-        <line x1="263" y1="625.562" x2="362.84375" y2="625.562" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_94">
-        <text transform="translate(264.53787 562.276)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="32" fill="black" x="14210855e-21" y="30" xml:space="preserve">size=B</tspan>
-        </text>
-      </g>
-      <g id="Graphic_95">
-        <text transform="translate(285.12 599.5)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="24" fill="black" x="0" y="23" xml:space="preserve">size=C</tspan>
-        </text>
-      </g>
-      <g id="Graphic_98">
-        <text transform="translate(264.53787 773.772)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="26" fill="black" x="8881784e-19" y="25" xml:space="preserve">A</tspan>
-          <tspan font-family="Lucida Grande" font-size="26" fill="black" y="25" xml:space="preserve">↓</tspan>
-        </text>
-      </g>
-      <g id="Graphic_97">
-        <text transform="translate(265.87013 815.5)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="26" fill="black" x="6536993e-19" y="25" xml:space="preserve">B</tspan>
-          <tspan font-family="Lucida Grande" font-size="26" fill="black" y="25" xml:space="preserve">↓</tspan>
-        </text>
-      </g>
-    </g>
-  </g>
-</svg>

docs/rfcs/images/036-bottom-most-gc-compaction/08-optimization.svg

@@ -1,158 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
-<svg xmlns="http://www.w3.org/2000/svg" xmlns:xl="http://www.w3.org/1999/xlink" xmlns:dc="http://purl.org/dc/elements/1.1/" version="1.1" viewBox="-235 406 586 424" width="586" height="424">
-  <defs/>
-  <g id="08-optimization" stroke-opacity="1" stroke-dasharray="none" stroke="none" fill="none" fill-opacity="1">
-    <title>08-optimization</title>
-    <rect fill="white" x="-235" y="406" width="586" height="424"/>
-    <g id="08-optimization_Layer_1">
-      <title>Layer 1</title>
-      <g id="Graphic_22">
-        <rect x="-100.448" y="509.902" width="203.5" height="26.391998" fill="white"/>
-        <rect x="-100.448" y="509.902" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_21">
-        <rect x="118.552" y="509.902" width="203.5" height="26.391998" fill="white"/>
-        <rect x="118.552" y="509.902" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_20">
-        <line x1="-101.79572" y1="420.322" x2="349.5" y2="420.322" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_19">
-        <text transform="translate(-230 411.598)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_17">
-        <rect x="-100.198" y="426.5" width="203.5" height="26.391998" fill="white"/>
-        <rect x="-100.198" y="426.5" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_16">
-        <rect x="118.802" y="426.5" width="203.5" height="26.391998" fill="white"/>
-        <rect x="118.802" y="426.5" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_14">
-        <rect x="-100.198" y="464.397" width="108.25" height="34" fill="white"/>
-        <rect x="-100.198" y="464.397" width="108.25" height="34" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_13">
-        <rect x="18.552" y="464.397" width="303.5" height="34" fill="white"/>
-        <rect x="18.552" y="464.397" width="303.5" height="34" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_11">
-        <rect x="-100.448" y="547.799" width="203.5" height="26.391998" fill="white"/>
-        <rect x="-100.448" y="547.799" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_10">
-        <rect x="118.552" y="547.799" width="203.5" height="26.391998" fill="white"/>
-        <rect x="118.552" y="547.799" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_24">
-        <line x1="-104" y1="542" x2="339.4011" y2="542" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-dasharray="4.0,4.0" stroke-width="1"/>
-      </g>
-      <g id="Graphic_25">
-        <text transform="translate(-139.604 534.5)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="14" fill="black" x="0" y="13" xml:space="preserve">0x20</tspan>
-        </text>
-      </g>
-      <g id="Line_27">
-        <line x1="-101.79572" y1="459.098" x2="341.6054" y2="459.098" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-dasharray="4.0,4.0" stroke-width="1"/>
-      </g>
-      <g id="Graphic_26">
-        <text transform="translate(-139.604 451.402)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="14" fill="black" x="0" y="13" xml:space="preserve">0x50</tspan>
-        </text>
-      </g>
-      <g id="Graphic_28">
-        <text transform="translate(-139.604 413.654)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="14" fill="black" x="0" y="13" xml:space="preserve">0x60</tspan>
-        </text>
-      </g>
-      <g id="Line_30">
-        <line x1="-101.79572" y1="481.145" x2="341.6054" y2="481.145" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-dasharray="4.0,4.0" stroke-width="1"/>
-      </g>
-      <g id="Graphic_29">
-        <text transform="translate(-139.604 473.449)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="14" fill="black" x="0" y="13" xml:space="preserve">0x40</tspan>
-        </text>
-      </g>
-      <g id="Graphic_77">
-        <rect x="-100.448" y="765.19595" width="203.5" height="26.391998" fill="white"/>
-        <rect x="-100.448" y="765.19595" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_76">
-        <rect x="118.552" y="765.19595" width="203.5" height="26.391998" fill="white"/>
-        <rect x="118.552" y="765.19595" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_75">
-        <line x1="-101.79572" y1="637.317" x2="349.5" y2="637.317" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_74">
-        <text transform="translate(-230 628.593)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_73">
-        <rect x="-100.198" y="681.794" width="203.5" height="26.391998" fill="white"/>
-        <rect x="-100.198" y="681.794" width="203.5" height="26.391998" stroke="#b1001c" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_72">
-        <rect x="118.802" y="681.794" width="203.5" height="26.391998" fill="white"/>
-        <rect x="118.802" y="681.794" width="203.5" height="26.391998" stroke="#b1001c" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_71">
-        <rect x="-100.198" y="719.69096" width="108.25" height="34" fill="white"/>
-        <rect x="-100.198" y="719.69096" width="108.25" height="34" stroke="#b1001c" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_70">
-        <rect x="18.552" y="719.69096" width="303.5" height="34" fill="white"/>
-        <rect x="18.552" y="719.69096" width="303.5" height="34" stroke="#b1001c" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_69">
-        <rect x="-100.448" y="803.09295" width="203.5" height="26.391998" fill="white"/>
-        <rect x="-100.448" y="803.09295" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_68">
-        <rect x="118.552" y="803.09295" width="203.5" height="26.391998" fill="white"/>
-        <rect x="118.552" y="803.09295" width="203.5" height="26.391998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_67">
-        <line x1="-104" y1="797.294" x2="339.4011" y2="797.294" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-dasharray="4.0,4.0" stroke-width="1"/>
-      </g>
-      <g id="Graphic_66">
-        <text transform="translate(-139.604 789.794)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="14" fill="black" x="0" y="13" xml:space="preserve">0x20</tspan>
-        </text>
-      </g>
-      <g id="Graphic_63">
-        <text transform="translate(-139.604 630.649)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="14" fill="black" x="0" y="13" xml:space="preserve">0x70</tspan>
-        </text>
-      </g>
-      <g id="Line_62">
-        <line x1="-101.79572" y1="736.439" x2="341.6054" y2="736.439" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-dasharray="4.0,4.0" stroke-width="1"/>
-      </g>
-      <g id="Graphic_61">
-        <text transform="translate(-139.604 728.743)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="14" fill="black" x="0" y="13" xml:space="preserve">0x40</tspan>
-        </text>
-      </g>
-      <g id="Graphic_79">
-        <rect x="-100.198" y="644.393" width="168.198" height="26.391998" fill="white"/>
-        <rect x="-100.198" y="644.393" width="168.198" height="26.391998" stroke="#b1001c" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_78">
-        <rect x="80" y="644.393" width="242.302" height="26.391998" fill="white"/>
-        <rect x="80" y="644.393" width="242.302" height="26.391998" stroke="#b1001c" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_81">
-        <line x1="-101.79572" y1="714.139" x2="341.6054" y2="714.139" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-dasharray="1.0,4.0" stroke-width="1"/>
-      </g>
-      <g id="Graphic_80">
-        <text transform="translate(-139.604 706.443)" fill="#a5a5a5">
-          <tspan font-family="Helvetica Neue" font-size="14" fill="#a5a5a5" x="0" y="13" xml:space="preserve">0x50</tspan>
-        </text>
-      </g>
-    </g>
-  </g>
-</svg>

docs/rfcs/images/036-bottom-most-gc-compaction/09-btmgc-analysis-2.svg

@@ -1,184 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
-<svg xmlns="http://www.w3.org/2000/svg" xmlns:xl="http://www.w3.org/1999/xlink" xmlns:dc="http://purl.org/dc/elements/1.1/" version="1.1" viewBox="-562 479 876 429" width="876" height="429">
-  <defs/>
-  <g id="09-btmgc-analysis-2" stroke-opacity="1" stroke-dasharray="none" stroke="none" fill="none" fill-opacity="1">
-    <title>09-btmgc-analysis-2</title>
-    <rect fill="white" x="-562" y="479" width="876" height="429"/>
-    <g id="09-btmgc-analysis-2_Layer_1">
-      <title>Layer 1</title>
-      <g id="Graphic_85">
-        <rect x="-404" y="622.386" width="203.5" height="17.5" fill="white"/>
-        <rect x="-404" y="622.386" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-399 621.912)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="90.974" y="15" xml:space="preserve">C</tspan>
-        </text>
-      </g>
-      <g id="Graphic_84">
-        <rect x="-184.5" y="622.386" width="203.5" height="17.5" fill="white"/>
-        <rect x="-184.5" y="622.386" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-179.5 621.912)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="90.974" y="15" xml:space="preserve">C</tspan>
-        </text>
-      </g>
-      <g id="Graphic_83">
-        <rect x="34.5" y="622.386" width="203.5" height="17.5" fill="white"/>
-        <rect x="34.5" y="622.386" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(39.5 621.912)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="90.974" y="15" xml:space="preserve">C</tspan>
-        </text>
-      </g>
-      <g id="Graphic_82">
-        <rect x="-404" y="479.922" width="127" height="77.5" fill="white"/>
-        <rect x="-404" y="479.922" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-399 509.448)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="53.316" y="15" xml:space="preserve">A</tspan>
-        </text>
-      </g>
-      <g id="Graphic_81">
-        <rect x="-263" y="479.922" width="127" height="77.5" fill="white"/>
-        <rect x="-263" y="479.922" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-258 509.448)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="53.316" y="15" xml:space="preserve">A</tspan>
-        </text>
-      </g>
-      <g id="Graphic_80">
-        <rect x="-122" y="479.922" width="127" height="77.5" fill="white"/>
-        <rect x="-122" y="479.922" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-117 509.448)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="53.316" y="15" xml:space="preserve">A</tspan>
-        </text>
-      </g>
-      <g id="Graphic_79">
-        <rect x="19" y="479.922" width="127" height="77.5" fill="white"/>
-        <rect x="19" y="479.922" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(24 509.448)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="53.316" y="15" xml:space="preserve">A</tspan>
-        </text>
-      </g>
-      <g id="Graphic_78">
-        <rect x="160" y="479.922" width="78" height="77.5" fill="white"/>
-        <rect x="160" y="479.922" width="78" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(165 509.448)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="28.816" y="15" xml:space="preserve">A</tspan>
-        </text>
-      </g>
-      <g id="Line_77">
-        <line x1="-452.5" y1="518.172" x2="251" y2="518.172" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_76">
-        <text transform="translate(-551 509.448)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_73">
-        <path d="M -120.675 651.5 L -84.425 651.5 L -84.425 710 L -66.3 710 L -102.55 740 L -138.8 710 L -120.675 710 Z" fill="white"/>
-        <path d="M -120.675 651.5 L -84.425 651.5 L -84.425 710 L -66.3 710 L -102.55 740 L -138.8 710 L -120.675 710 Z" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_89">
-        <rect x="-403.8" y="582.324" width="161.8" height="28.447998" fill="white"/>
-        <rect x="-403.8" y="582.324" width="161.8" height="28.447998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-398.8 587.324)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="70.42" y="15" xml:space="preserve">B</tspan>
-        </text>
-      </g>
-      <g id="Graphic_90">
-        <rect x="-229.5" y="582.342" width="277.2" height="28.447998" fill="white"/>
-        <rect x="-229.5" y="582.342" width="277.2" height="28.447998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-224.5 587.342)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="128.12" y="15" xml:space="preserve">B</tspan>
-        </text>
-      </g>
-      <g id="Graphic_91">
-        <rect x="64.7" y="582.342" width="173.5" height="28.447998" fill="white"/>
-        <rect x="64.7" y="582.342" width="173.5" height="28.447998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(69.7 587.342)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="76.27" y="15" xml:space="preserve">B</tspan>
-        </text>
-      </g>
-      <g id="Graphic_97">
-        <rect x="-403.8" y="564.842" width="490.8" height="12.157997" fill="white"/>
-        <rect x="-403.8" y="564.842" width="490.8" height="12.157997" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-398.8 561.697)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="234.624" y="15" xml:space="preserve">C</tspan>
-        </text>
-      </g>
-      <g id="Graphic_109">
-        <rect x="28.6" y="889.964" width="203.5" height="17.5" fill="white"/>
-        <rect x="28.6" y="889.964" width="203.5" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(33.6 889.49)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="90.974" y="15" xml:space="preserve">C</tspan>
-        </text>
-      </g>
-      <g id="Graphic_108">
-        <rect x="-409.9" y="747.5" width="127" height="77.5" fill="white"/>
-        <rect x="-409.9" y="747.5" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-404.9 777.026)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="53.316" y="15" xml:space="preserve">A</tspan>
-        </text>
-      </g>
-      <g id="Graphic_107">
-        <rect x="-268.9" y="747.5" width="127" height="77.5" fill="white"/>
-        <rect x="-268.9" y="747.5" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-263.9 777.026)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="53.316" y="15" xml:space="preserve">A</tspan>
-        </text>
-      </g>
-      <g id="Graphic_106">
-        <rect x="-127.9" y="747.5" width="127" height="77.5" fill="white"/>
-        <rect x="-127.9" y="747.5" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-122.9 777.026)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="53.316" y="15" xml:space="preserve">A</tspan>
-        </text>
-      </g>
-      <g id="Graphic_105">
-        <rect x="13.1" y="747.5" width="127" height="77.5" fill="white"/>
-        <rect x="13.1" y="747.5" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(18.1 777.026)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="53.316" y="15" xml:space="preserve">A</tspan>
-        </text>
-      </g>
-      <g id="Graphic_104">
-        <rect x="154.1" y="747.5" width="78" height="77.5" fill="white"/>
-        <rect x="154.1" y="747.5" width="78" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(159.1 777.026)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="28.816" y="15" xml:space="preserve">A</tspan>
-        </text>
-      </g>
-      <g id="Line_103">
-        <line x1="-458.4" y1="785.75" x2="245.1" y2="785.75" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_102">
-        <text transform="translate(-556.9 777.026)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_99">
-        <rect x="58.8" y="849.92" width="173.5" height="28.447998" fill="white"/>
-        <rect x="58.8" y="849.92" width="173.5" height="28.447998" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(63.8 854.92)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="76.27" y="15" xml:space="preserve">B</tspan>
-        </text>
-      </g>
-      <g id="Graphic_98">
-        <rect x="-409.7" y="832.42" width="490.8" height="12.157997" fill="white"/>
-        <rect x="-409.7" y="832.42" width="490.8" height="12.157997" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(-404.7 829.275)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="234.624" y="15" xml:space="preserve">C</tspan>
-        </text>
-      </g>
-      <g id="Graphic_112">
-        <text transform="translate(273 797.5)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="26" fill="black" x="6536993e-19" y="25" xml:space="preserve">B</tspan>
-          <tspan font-family="Lucida Grande" font-size="26" fill="black" y="25" xml:space="preserve">↓</tspan>
-        </text>
-      </g>
-      <g id="Graphic_113">
-        <text transform="translate(273 833.974)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="26" fill="black" x="42277293e-20" y="25" xml:space="preserve">C</tspan>
-          <tspan font-family="Lucida Grande" font-size="26" fill="black" y="25" xml:space="preserve">↓</tspan>
-        </text>
-      </g>
-    </g>
-  </g>
-</svg>

docs/rfcs/images/036-bottom-most-gc-compaction/10-btmgc-analysis-3.svg

@@ -1,81 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
-<svg xmlns="http://www.w3.org/2000/svg" xmlns:xl="http://www.w3.org/1999/xlink" xmlns:dc="http://purl.org/dc/elements/1.1/" version="1.1" viewBox="-12 920 809 269" width="809" height="269">
-  <defs/>
-  <g id="10-btmgc-analysis-3" stroke-opacity="1" stroke-dasharray="none" stroke="none" fill="none" fill-opacity="1">
-    <title>10-btmgc-analysis-3</title>
-    <rect fill="white" x="-12" y="920" width="809" height="269"/>
-    <g id="10-btmgc-analysis-3_Layer_1">
-      <title>Layer 1</title>
-      <g id="Graphic_13">
-        <rect x="433.7" y="949" width="63.559346" height="77.5" fill="white"/>
-        <rect x="433.7" y="949" width="63.559346" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(438.7 978.526)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="8.107673" y="15" xml:space="preserve">1/5 X</tspan>
-        </text>
-      </g>
-      <g id="Graphic_12">
-        <rect x="503.7654" y="949" width="63.559346" height="77.5" fill="white"/>
-        <rect x="503.7654" y="949" width="63.559346" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(508.7654 978.526)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="8.107673" y="15" xml:space="preserve">1/5 X</tspan>
-        </text>
-      </g>
-      <g id="Graphic_11">
-        <rect x="574.8318" y="949" width="63.559346" height="77.5" fill="white"/>
-        <rect x="574.8318" y="949" width="63.559346" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(579.8318 978.526)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="8.107673" y="15" xml:space="preserve">1/5 X</tspan>
-        </text>
-      </g>
-      <g id="Graphic_10">
-        <rect x="645.3977" y="949" width="63.559346" height="77.5" fill="white"/>
-        <rect x="645.3977" y="949" width="63.559346" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(650.3977 978.526)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="8.107673" y="15" xml:space="preserve">1/5 X</tspan>
-        </text>
-      </g>
-      <g id="Line_8">
-        <line x1="92" y1="934.276" x2="795.5" y2="934.276" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_7">
-        <text transform="translate(-6.500003 925.552)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_2">
-        <rect x="113.2" y="1033.92" width="321.3" height="12.157997" fill="white"/>
-        <rect x="113.2" y="1033.92" width="321.3" height="12.157997" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(118.2 1030.775)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="150.762" y="15" xml:space="preserve">X</tspan>
-        </text>
-      </g>
-      <g id="Graphic_17">
-        <path d="M 420.125 1062 L 456.375 1062 L 456.375 1120.5 L 474.5 1120.5 L 438.25 1150.5 L 402 1120.5 L 420.125 1120.5 Z" fill="white"/>
-        <path d="M 420.125 1062 L 456.375 1062 L 456.375 1120.5 L 474.5 1120.5 L 438.25 1150.5 L 402 1120.5 L 420.125 1120.5 Z" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_27">
-        <line x1="93" y1="1164.224" x2="796.5" y2="1164.224" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_26">
-        <text transform="translate(-5.5000034 1155.5)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_25">
-        <rect x="114" y="1173.5" width="641.8" height="12.157997" fill="white"/>
-        <rect x="114" y="1173.5" width="641.8" height="12.157997" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(119 1170.355)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="306.564" y="15" xml:space="preserve">2X</tspan>
-        </text>
-      </g>
-      <g id="Graphic_33">
-        <rect x="715.96355" y="949" width="63.559346" height="77.5" fill="white"/>
-        <rect x="715.96355" y="949" width="63.559346" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(720.96355 978.526)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="8.107673" y="15" xml:space="preserve">1/5 X</tspan>
-        </text>
-      </g>
-    </g>
-  </g>
-</svg>

docs/rfcs/images/036-bottom-most-gc-compaction/11-btmgc-analysis-4.svg

@@ -1,81 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
-<svg xmlns="http://www.w3.org/2000/svg" xmlns:xl="http://www.w3.org/1999/xlink" xmlns:dc="http://purl.org/dc/elements/1.1/" version="1.1" viewBox="-12 920 809 269" width="809" height="269">
-  <defs/>
-  <g id="11-btmgc-analysis-4" stroke-opacity="1" stroke-dasharray="none" stroke="none" fill="none" fill-opacity="1">
-    <title>11-btmgc-analysis-4</title>
-    <rect fill="white" x="-12" y="920" width="809" height="269"/>
-    <g id="11-btmgc-analysis-4_Layer_1">
-      <title>Layer 1</title>
-      <g id="Graphic_13">
-        <rect x="113" y="949" width="127" height="77.5" fill="white"/>
-        <rect x="113" y="949" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(118 978.526)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="39.084" y="15" xml:space="preserve">1/5 D</tspan>
-        </text>
-      </g>
-      <g id="Graphic_12">
-        <rect x="253" y="949" width="127" height="77.5" fill="white"/>
-        <rect x="253" y="949" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(258 978.526)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="39.084" y="15" xml:space="preserve">1/5 D</tspan>
-        </text>
-      </g>
-      <g id="Graphic_11">
-        <rect x="395" y="949" width="127" height="77.5" fill="white"/>
-        <rect x="395" y="949" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(400 978.526)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="39.084" y="15" xml:space="preserve">1/5 D</tspan>
-        </text>
-      </g>
-      <g id="Graphic_10">
-        <rect x="536" y="949" width="127" height="77.5" fill="white"/>
-        <rect x="536" y="949" width="127" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(541 978.526)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="39.084" y="15" xml:space="preserve">1/5 D</tspan>
-        </text>
-      </g>
-      <g id="Graphic_9">
-        <rect x="677" y="949" width="78" height="77.5" fill="white"/>
-        <rect x="677" y="949" width="78" height="77.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(682 978.526)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="14.584" y="15" xml:space="preserve">1/5 D</tspan>
-        </text>
-      </g>
-      <g id="Line_8">
-        <line x1="92" y1="934.276" x2="795.5" y2="934.276" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_7">
-        <text transform="translate(-6.500003 925.552)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_2">
-        <rect x="113.2" y="1033.92" width="641.8" height="12.157997" fill="white"/>
-        <rect x="113.2" y="1033.92" width="641.8" height="12.157997" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(118.2 1030.775)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="310.268" y="15" xml:space="preserve">D</tspan>
-        </text>
-      </g>
-      <g id="Graphic_17">
-        <path d="M 420.125 1062 L 456.375 1062 L 456.375 1120.5 L 474.5 1120.5 L 438.25 1150.5 L 402 1120.5 L 420.125 1120.5 Z" fill="white"/>
-        <path d="M 420.125 1062 L 456.375 1062 L 456.375 1120.5 L 474.5 1120.5 L 438.25 1150.5 L 402 1120.5 L 420.125 1120.5 Z" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_27">
-        <line x1="93" y1="1164.224" x2="796.5" y2="1164.224" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_26">
-        <text transform="translate(-5.5000034 1155.5)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">GC Horizon</tspan>
-        </text>
-      </g>
-      <g id="Graphic_25">
-        <rect x="114" y="1173.5" width="641.8" height="12.157997" fill="white"/>
-        <rect x="114" y="1173.5" width="641.8" height="12.157997" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(119 1170.355)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="310.268" y="15" xml:space="preserve">D</tspan>
-        </text>
-      </g>
-    </g>
-  </g>
-</svg>

docs/rfcs/images/036-bottom-most-gc-compaction/13-job-split.svg

@@ -1,176 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
-<svg version="1.1" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns="http://www.w3.org/2000/svg" xmlns:xl="http://www.w3.org/1999/xlink" viewBox="210 271 870 514" width="870" height="514">
-  <defs/>
-  <g id="gc-compaction-split" stroke-dasharray="none" fill-opacity="1" stroke="none" fill="none" stroke-opacity="1">
-    <title>gc-compaction-split</title>
-    <rect fill="white" x="210" y="271" width="870" height="514"/>
-    <g id="gc-compaction-split_Layer_1">
-      <title>Layer 1</title>
-      <g id="Graphic_12">
-        <rect x="241" y="272" width="213" height="50.5" fill="white"/>
-        <rect x="241" y="272" width="213" height="50.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_11">
-        <rect x="468.72266" y="272" width="213" height="50.5" fill="white"/>
-        <rect x="468.72266" y="272" width="213" height="50.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_10">
-        <rect x="695.72266" y="272" width="213" height="50.5" fill="white"/>
-        <rect x="695.72266" y="272" width="213" height="50.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_9">
-        <rect x="241" y="337.3711" width="303.5" height="50.5" fill="white"/>
-        <rect x="241" y="337.3711" width="303.5" height="50.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_8">
-        <rect x="556.2617" y="337.3711" width="352.46094" height="50.5" fill="white"/>
-        <rect x="556.2617" y="337.3711" width="352.46094" height="50.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_7">
-        <rect x="241" y="402.7422" width="667.72266" height="50.5" fill="white"/>
-        <rect x="241" y="402.7422" width="667.72266" height="50.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_6">
-        <line x1="211" y1="355.5" x2="947.4961" y2="355.5" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_5">
-        <text transform="translate(952.4961 346.776)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">branch point</tspan>
-        </text>
-      </g>
-      <g id="Line_4">
-        <line x1="212" y1="438.5182" x2="948.4961" y2="438.5182" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_3">
-        <text transform="translate(953.4961 429.7942)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">last branch point</tspan>
-        </text>
-      </g>
-      <g id="Graphic_13">
-        <rect x="241" y="272" width="127.99101" height="181.24219" fill="#3a8eed" fill-opacity=".5"/>
-        <text transform="translate(246 353.3971)" fill="white">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="white" x="38.835502" y="15" xml:space="preserve">Job 1</tspan>
-        </text>
-      </g>
-      <g id="Graphic_57">
-        <rect x="359" y="647.96484" width="551.72266" height="50.5" fill="white"/>
-        <rect x="359" y="647.96484" width="551.72266" height="50.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_54">
-        <rect x="359" y="517.22266" width="96" height="50.5" fill="white"/>
-        <rect x="359" y="517.22266" width="96" height="50.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_53">
-        <rect x="469.72266" y="517.22266" width="213" height="50.5" fill="white"/>
-        <rect x="469.72266" y="517.22266" width="213" height="50.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_52">
-        <rect x="696.72266" y="517.22266" width="213" height="50.5" fill="white"/>
-        <rect x="696.72266" y="517.22266" width="213" height="50.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_51">
-        <rect x="359" y="582.59375" width="186.5" height="50.5" fill="white"/>
-        <rect x="359" y="582.59375" width="186.5" height="50.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_50">
-        <rect x="557.2617" y="582.59375" width="352.46094" height="50.5" fill="white"/>
-        <rect x="557.2617" y="582.59375" width="352.46094" height="50.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Line_49">
-        <line x1="212" y1="600.72266" x2="948.4961" y2="600.72266" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_48">
-        <text transform="translate(953.4961 591.99866)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">branch point</tspan>
-        </text>
-      </g>
-      <g id="Line_47">
-        <line x1="213" y1="683.74084" x2="949.4961" y2="683.74084" stroke="#7f8080" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_46">
-        <text transform="translate(954.4961 675.01685)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="0" y="15" xml:space="preserve">last branch point</tspan>
-        </text>
-      </g>
-      <g id="Graphic_63">
-        <rect x="376.72525" y="272" width="127.99101" height="181.24219" fill="#3a8eed" fill-opacity=".5"/>
-        <text transform="translate(381.72525 353.3971)" fill="white">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="white" x="38.835502" y="15" xml:space="preserve">Job 2</tspan>
-        </text>
-      </g>
-      <g id="Graphic_64">
-        <rect x="511.39405" y="272" width="127.99101" height="181.24219" fill="#3a8eed" fill-opacity=".5"/>
-        <text transform="translate(516.39405 353.3971)" fill="white">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="white" x="38.835502" y="15" xml:space="preserve">Job 3</tspan>
-        </text>
-      </g>
-      <g id="Graphic_65">
-        <rect x="646.06285" y="272" width="127.99101" height="181.24219" fill="#3a8eed" fill-opacity=".5"/>
-        <text transform="translate(651.06285 353.3971)" fill="white">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="white" x="38.835502" y="15" xml:space="preserve">Job 4</tspan>
-        </text>
-      </g>
-      <g id="Graphic_66">
-        <rect x="780.73165" y="272" width="127.99101" height="181.24219" fill="#3a8eed" fill-opacity=".5"/>
-        <text transform="translate(785.73165 353.3971)" fill="white">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="white" x="38.835502" y="15" xml:space="preserve">Job 5</tspan>
-        </text>
-      </g>
-      <g id="Graphic_56">
-        <rect x="243.5" y="517.22266" width="125.49101" height="181.24219" fill="#ccc"/>
-        <rect x="243.5" y="517.22266" width="125.49101" height="181.24219" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_55">
-        <rect x="243.5" y="673.46484" width="125.49101" height="17.5" fill="#6b7ca5"/>
-        <rect x="243.5" y="673.46484" width="125.49101" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_68">
-        <rect x="379.22525" y="517.22266" width="125.49101" height="181.24219" fill="#ccc"/>
-        <rect x="379.22525" y="517.22266" width="125.49101" height="181.24219" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_67">
-        <rect x="379.22525" y="673.46484" width="125.49101" height="17.5" fill="#6b7ca5"/>
-        <rect x="379.22525" y="673.46484" width="125.49101" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_70">
-        <rect x="514.22525" y="517.22266" width="125.49101" height="181.24219" fill="#ccc"/>
-        <rect x="514.22525" y="517.22266" width="125.49101" height="181.24219" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_69">
-        <rect x="514.22525" y="673.46484" width="125.49101" height="17.5" fill="#6b7ca5"/>
-        <rect x="514.22525" y="673.46484" width="125.49101" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_72">
-        <rect x="649.22525" y="517.22266" width="125.49101" height="181.24219" fill="#ccc"/>
-        <rect x="649.22525" y="517.22266" width="125.49101" height="181.24219" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_71">
-        <rect x="649.22525" y="673.46484" width="125.49101" height="17.5" fill="#6b7ca5"/>
-        <rect x="649.22525" y="673.46484" width="125.49101" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_74">
-        <rect x="785.23165" y="517.22266" width="125.49101" height="181.24219" fill="#ccc"/>
-        <rect x="785.23165" y="517.22266" width="125.49101" height="181.24219" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_73">
-        <rect x="785.23165" y="673.46484" width="125.49101" height="17.5" fill="#6b7ca5"/>
-        <rect x="785.23165" y="673.46484" width="125.49101" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-      </g>
-      <g id="Graphic_78">
-        <rect x="241" y="731.3359" width="125.49101" height="27.26953" fill="#ccc"/>
-        <rect x="241" y="731.3359" width="125.49101" height="27.26953" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(246 735.7467)" fill="black">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="black" x="17.297502" y="15" xml:space="preserve">Delta Layer</tspan>
-        </text>
-      </g>
-      <g id="Graphic_79">
-        <rect x="241" y="766.759" width="125.49101" height="17.5" fill="#6b7ca5"/>
-        <rect x="241" y="766.759" width="125.49101" height="17.5" stroke="black" stroke-linecap="round" stroke-linejoin="round" stroke-width="1"/>
-        <text transform="translate(246 766.285)" fill="white">
-          <tspan font-family="Helvetica Neue" font-size="16" fill="white" x="13.737502" y="15" xml:space="preserve">Image Layer</tspan>
-        </text>
-      </g>
-    </g>
-  </g>
-</svg>

libs/pageserver_api/src/config.rs

@@ -305,7 +305,6 @@ impl From<OtelExporterProtocol> for tracing_utils::Protocol {
 pub struct TimelineImportConfig {
     pub import_job_concurrency: NonZeroUsize,
     pub import_job_soft_size_limit: NonZeroUsize,
-    pub import_job_checkpoint_threshold: NonZeroUsize,
 }
 
 pub mod statvfs {
@@ -640,15 +639,23 @@ impl Default for ConfigToml {
             tenant_config: TenantConfigToml::default(),
             no_sync: None,
             wal_receiver_protocol: DEFAULT_WAL_RECEIVER_PROTOCOL,
-            page_service_pipelining: PageServicePipeliningConfig::Pipelined(
-                PageServicePipeliningConfigPipelined {
+            page_service_pipelining: if !cfg!(test) {
+                PageServicePipeliningConfig::Serial
+            } else {
+                // Do not turn this into the default until scattered reads have been
+                // validated and rolled-out fully.
+                PageServicePipeliningConfig::Pipelined(PageServicePipeliningConfigPipelined {
                     max_batch_size: NonZeroUsize::new(32).unwrap(),
                     execution: PageServiceProtocolPipelinedExecutionStrategy::ConcurrentFutures,
                     batching: PageServiceProtocolPipelinedBatchingStrategy::ScatteredLsn,
-                },
-            ),
-            get_vectored_concurrent_io: GetVectoredConcurrentIo::SidecarTask,
-            enable_read_path_debugging: if cfg!(feature = "testing") {
+                })
+            },
+            get_vectored_concurrent_io: if !cfg!(test) {
+                GetVectoredConcurrentIo::Sequential
+            } else {
+                GetVectoredConcurrentIo::SidecarTask
+            },
+            enable_read_path_debugging: if cfg!(test) || cfg!(feature = "testing") {
                 Some(true)
             } else {
                 None
@@ -662,7 +669,6 @@ impl Default for ConfigToml {
             timeline_import_config: TimelineImportConfig {
                 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(),
             },
         }
     }

libs/pageserver_api/src/key.rs

@@ -910,11 +910,6 @@ impl Key {
         self.field1 == 0x00 && self.field4 != 0 && self.field6 != 0xffffffff
     }
 
-    #[inline(always)]
-    pub fn is_rel_block_of_rel(&self, rel: Oid) -> bool {
-        self.is_rel_block_key() && self.field4 == rel
-    }
-
     #[inline(always)]
     pub fn is_rel_dir_key(&self) -> bool {
         self.field1 == 0x00

libs/pageserver_api/src/models.rs

@@ -336,30 +336,14 @@ impl TimelineCreateRequest {
 
 #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq)]
 pub enum ShardImportStatus {
-    InProgress(Option<ShardImportProgress>),
+    InProgress,
     Done,
     Error(String),
 }
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq)]
-pub enum ShardImportProgress {
-    V1(ShardImportProgressV1),
-}
-
-#[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq)]
-pub struct ShardImportProgressV1 {
-    /// Total number of jobs in the import plan
-    pub jobs: usize,
-    /// Number of jobs completed
-    pub completed: usize,
-    /// Hash of the plan
-    pub import_plan_hash: u64,
-}
-
 impl ShardImportStatus {
     pub fn is_terminal(&self) -> bool {
         match self {
-            ShardImportStatus::InProgress(_) => false,
+            ShardImportStatus::InProgress => false,
             ShardImportStatus::Done | ShardImportStatus::Error(_) => true,
         }
     }
@@ -1819,6 +1803,7 @@ pub struct TopTenantShardsResponse {
 }
 
 pub mod virtual_file {
+    use std::sync::LazyLock;
 
     #[derive(
         Copy,
@@ -1847,7 +1832,6 @@ pub mod virtual_file {
         Eq,
         Hash,
         strum_macros::EnumString,
-        strum_macros::EnumIter,
         strum_macros::Display,
         serde_with::DeserializeFromStr,
         serde_with::SerializeDisplay,
@@ -1859,14 +1843,37 @@ pub mod virtual_file {
         /// Uses buffered IO.
         Buffered,
         /// Uses direct IO for reads only.
+        #[cfg(target_os = "linux")]
         Direct,
         /// Use direct IO for reads and writes.
+        #[cfg(target_os = "linux")]
         DirectRw,
     }
 
     impl IoMode {
         pub fn preferred() -> Self {
-            IoMode::DirectRw
+            // The default behavior when running Rust unit tests without any further
+            // flags is to use the newest behavior (DirectRw).
+            // The CI uses the following environment variable to unit tests for all
+            // different modes.
+            // NB: the Python regression & perf tests have their own defaults management
+            // that writes pageserver.toml; they do not use this variable.
+            if cfg!(test) {
+                static CACHED: LazyLock<IoMode> = LazyLock::new(|| {
+                    utils::env::var_serde_json_string(
+                        "NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IO_MODE",
+                    )
+                    .unwrap_or(
+                        #[cfg(target_os = "linux")]
+                        IoMode::DirectRw,
+                        #[cfg(not(target_os = "linux"))]
+                        IoMode::Buffered,
+                    )
+                });
+                *CACHED
+            } else {
+                IoMode::Buffered
+            }
         }
     }
 
@@ -1876,7 +1883,9 @@ pub mod virtual_file {
         fn try_from(value: u8) -> Result<Self, Self::Error> {
             Ok(match value {
                 v if v == (IoMode::Buffered as u8) => IoMode::Buffered,
+                #[cfg(target_os = "linux")]
                 v if v == (IoMode::Direct as u8) => IoMode::Direct,
+                #[cfg(target_os = "linux")]
                 v if v == (IoMode::DirectRw as u8) => IoMode::DirectRw,
                 x => return Err(x),
             })

libs/pageserver_api/src/upcall_api.rs

@@ -4,7 +4,6 @@
 //! See docs/rfcs/025-generation-numbers.md
 
 use serde::{Deserialize, Serialize};
-use utils::generation::Generation;
 use utils::id::{NodeId, TimelineId};
 
 use crate::controller_api::NodeRegisterRequest;
@@ -64,17 +63,9 @@ pub struct ValidateResponseTenant {
     pub valid: bool,
 }
 
-#[derive(Serialize, Deserialize)]
-pub struct TimelineImportStatusRequest {
-    pub tenant_shard_id: TenantShardId,
-    pub timeline_id: TimelineId,
-    pub generation: Generation,
-}
-
 #[derive(Serialize, Deserialize)]
 pub struct PutTimelineImportStatusRequest {
     pub tenant_shard_id: TenantShardId,
     pub timeline_id: TimelineId,
     pub status: ShardImportStatus,
-    pub generation: Generation,
 }

libs/pageserver_api/src/value.rs

@@ -36,24 +36,6 @@ impl Value {
             Value::WalRecord(rec) => rec.will_init(),
         }
     }
-
-    #[inline(always)]
-    pub fn estimated_size(&self) -> usize {
-        match self {
-            Value::Image(image) => image.len(),
-            Value::WalRecord(NeonWalRecord::AuxFile {
-                content: Some(content),
-                ..
-            }) => content.len(),
-            Value::WalRecord(NeonWalRecord::Postgres { rec, .. }) => rec.len(),
-            Value::WalRecord(NeonWalRecord::ClogSetAborted { xids }) => xids.len() * 4,
-            Value::WalRecord(NeonWalRecord::ClogSetCommitted { xids, .. }) => xids.len() * 4,
-            Value::WalRecord(NeonWalRecord::MultixactMembersCreate { members, .. }) => {
-                members.len() * 8
-            }
-            _ => 8192, /* use image size as the estimation */
-        }
-    }
 }
 
 #[derive(Debug, PartialEq)]

libs/posthog_client_lite/Cargo.toml

@@ -1,14 +0,0 @@
-[package]
-name = "posthog_client_lite"
-version = "0.1.0"
-edition = "2024"
-license.workspace = true
-
-[dependencies]
-anyhow.workspace = true
-reqwest.workspace = true
-serde.workspace = true
-serde_json.workspace = true
-sha2.workspace = true
-workspace_hack.workspace = true
-thiserror.workspace = true

libs/posthog_client_lite/src/lib.rs

@@ -1,634 +0,0 @@
-//! A lite version of the PostHog client that only supports local evaluation of feature flags.
-
-use std::collections::HashMap;
-
-use serde::{Deserialize, Serialize};
-use serde_json::json;
-use sha2::Digest;
-
-#[derive(Debug, thiserror::Error)]
-pub enum PostHogEvaluationError {
-    /// The feature flag is not available, for example, because the local evaluation data is not populated yet.
-    #[error("Feature flag not available: {0}")]
-    NotAvailable(String),
-    #[error("No condition group is matched")]
-    NoConditionGroupMatched,
-    /// Real errors, e.g., the rollout percentage does not add up to 100.
-    #[error("Failed to evaluate feature flag: {0}")]
-    Internal(String),
-}
-
-#[derive(Deserialize)]
-pub struct LocalEvaluationResponse {
-    #[allow(dead_code)]
-    flags: Vec<LocalEvaluationFlag>,
-}
-
-#[derive(Deserialize)]
-pub struct LocalEvaluationFlag {
-    key: String,
-    filters: LocalEvaluationFlagFilters,
-    active: bool,
-}
-
-#[derive(Deserialize)]
-pub struct LocalEvaluationFlagFilters {
-    groups: Vec<LocalEvaluationFlagFilterGroup>,
-    multivariate: LocalEvaluationFlagMultivariate,
-}
-
-#[derive(Deserialize)]
-pub struct LocalEvaluationFlagFilterGroup {
-    variant: Option<String>,
-    properties: Option<Vec<LocalEvaluationFlagFilterProperty>>,
-    rollout_percentage: i64,
-}
-
-#[derive(Deserialize)]
-pub struct LocalEvaluationFlagFilterProperty {
-    key: String,
-    value: PostHogFlagFilterPropertyValue,
-    operator: String,
-}
-
-#[derive(Debug, Serialize, Deserialize)]
-#[serde(untagged)]
-pub enum PostHogFlagFilterPropertyValue {
-    String(String),
-    Number(f64),
-    Boolean(bool),
-    List(Vec<String>),
-}
-
-#[derive(Deserialize)]
-pub struct LocalEvaluationFlagMultivariate {
-    variants: Vec<LocalEvaluationFlagMultivariateVariant>,
-}
-
-#[derive(Deserialize)]
-pub struct LocalEvaluationFlagMultivariateVariant {
-    key: String,
-    rollout_percentage: i64,
-}
-
-pub struct FeatureStore {
-    flags: HashMap<String, LocalEvaluationFlag>,
-}
-
-impl Default for FeatureStore {
-    fn default() -> Self {
-        Self::new()
-    }
-}
-
-enum GroupEvaluationResult {
-    MatchedAndOverride(String),
-    MatchedAndEvaluate,
-    Unmatched,
-}
-
-impl FeatureStore {
-    pub fn new() -> Self {
-        Self {
-            flags: HashMap::new(),
-        }
-    }
-
-    pub fn set_flags(&mut self, flags: Vec<LocalEvaluationFlag>) {
-        self.flags.clear();
-        for flag in flags {
-            self.flags.insert(flag.key.clone(), flag);
-        }
-    }
-
-    /// Generate a consistent hash for a user ID (e.g., tenant ID).
-    ///
-    /// The implementation is different from PostHog SDK. In PostHog SDK, it is sha1 of `user_id.distinct_id.salt`.
-    /// However, as we do not upload all of our tenant IDs to PostHog, we do not have the PostHog distinct_id for a
-    /// tenant. Therefore, the way we compute it is sha256 of `user_id.feature_id.salt`.
-    fn consistent_hash(user_id: &str, flag_key: &str, salt: &str) -> f64 {
-        let mut hasher = sha2::Sha256::new();
-        hasher.update(user_id);
-        hasher.update(".");
-        hasher.update(flag_key);
-        hasher.update(".");
-        hasher.update(salt);
-        let hash = hasher.finalize();
-        let hash_int = u64::from_le_bytes(hash[..8].try_into().unwrap());
-        hash_int as f64 / u64::MAX as f64
-    }
-
-    /// Evaluate a condition. Returns an error if the condition cannot be evaluated due to parsing error or missing
-    /// property.
-    fn evaluate_condition(
-        &self,
-        operator: &str,
-        provided: &PostHogFlagFilterPropertyValue,
-        requested: &PostHogFlagFilterPropertyValue,
-    ) -> Result<bool, PostHogEvaluationError> {
-        match operator {
-            "exact" => {
-                let PostHogFlagFilterPropertyValue::String(provided) = provided else {
-                    // Left should be a string
-                    return Err(PostHogEvaluationError::Internal(format!(
-                        "The left side of the condition is not a string: {:?}",
-                        provided
-                    )));
-                };
-                let PostHogFlagFilterPropertyValue::List(requested) = requested else {
-                    // Right should be a list of string
-                    return Err(PostHogEvaluationError::Internal(format!(
-                        "The right side of the condition is not a list: {:?}",
-                        requested
-                    )));
-                };
-                Ok(requested.contains(provided))
-            }
-            "lt" | "gt" => {
-                let PostHogFlagFilterPropertyValue::String(requested) = requested else {
-                    // Right should be a string
-                    return Err(PostHogEvaluationError::Internal(format!(
-                        "The right side of the condition is not a string: {:?}",
-                        requested
-                    )));
-                };
-                let Ok(requested) = requested.parse::<f64>() else {
-                    return Err(PostHogEvaluationError::Internal(format!(
-                        "Can not parse the right side of the condition as a number: {:?}",
-                        requested
-                    )));
-                };
-                // Left can either be a number or a string
-                let provided = match provided {
-                    PostHogFlagFilterPropertyValue::Number(provided) => *provided,
-                    PostHogFlagFilterPropertyValue::String(provided) => {
-                        let Ok(provided) = provided.parse::<f64>() else {
-                            return Err(PostHogEvaluationError::Internal(format!(
-                                "Can not parse the left side of the condition as a number: {:?}",
-                                provided
-                            )));
-                        };
-                        provided
-                    }
-                    _ => {
-                        return Err(PostHogEvaluationError::Internal(format!(
-                            "The left side of the condition is not a number or a string: {:?}",
-                            provided
-                        )));
-                    }
-                };
-                match operator {
-                    "lt" => Ok(provided < requested),
-                    "gt" => Ok(provided > requested),
-                    op => Err(PostHogEvaluationError::Internal(format!(
-                        "Unsupported operator: {}",
-                        op
-                    ))),
-                }
-            }
-            _ => Err(PostHogEvaluationError::Internal(format!(
-                "Unsupported operator: {}",
-                operator
-            ))),
-        }
-    }
-
-    /// Evaluate a percentage.
-    fn evaluate_percentage(&self, mapped_user_id: f64, percentage: i64) -> bool {
-        mapped_user_id <= percentage as f64 / 100.0
-    }
-
-    /// Evaluate a filter group for a feature flag. Returns an error if there are errors during the evaluation.
-    ///
-    /// Return values:
-    /// Ok(GroupEvaluationResult::MatchedAndOverride(variant)): matched and evaluated to this value
-    /// Ok(GroupEvaluationResult::MatchedAndEvaluate): condition matched but no variant override, use the global rollout percentage
-    /// Ok(GroupEvaluationResult::Unmatched): condition unmatched
-    fn evaluate_group(
-        &self,
-        group: &LocalEvaluationFlagFilterGroup,
-        hash_on_group_rollout_percentage: f64,
-        provided_properties: &HashMap<String, PostHogFlagFilterPropertyValue>,
-    ) -> Result<GroupEvaluationResult, PostHogEvaluationError> {
-        if let Some(ref properties) = group.properties {
-            for property in properties {
-                if let Some(value) = provided_properties.get(&property.key) {
-                    // The user provided the property value
-                    if !self.evaluate_condition(
-                        property.operator.as_ref(),
-                        value,
-                        &property.value,
-                    )? {
-                        return Ok(GroupEvaluationResult::Unmatched);
-                    }
-                } else {
-                    // We cannot evaluate, the property is not available
-                    return Err(PostHogEvaluationError::NotAvailable(format!(
-                        "The required property in the condition is not available: {}",
-                        property.key
-                    )));
-                }
-            }
-        }
-
-        // The group has no condition matchers or we matched the properties
-        if self.evaluate_percentage(hash_on_group_rollout_percentage, group.rollout_percentage) {
-            if let Some(ref variant_override) = group.variant {
-                Ok(GroupEvaluationResult::MatchedAndOverride(
-                    variant_override.clone(),
-                ))
-            } else {
-                Ok(GroupEvaluationResult::MatchedAndEvaluate)
-            }
-        } else {
-            Ok(GroupEvaluationResult::Unmatched)
-        }
-    }
-
-    /// 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:
-    ///
-    /// * Match each filter group.
-    ///   - If a group is matched, it will first determine whether the user is in the range of the group's rollout
-    ///     percentage. We will generate a consistent hash for the user ID on the group rollout percentage. This hash
-    ///     is shared across all groups.
-    ///   - If the hash falls within the group's rollout percentage, return the variant if it's overridden, or
-    ///   - Evaluate the variant using the global config and the global rollout percentage.
-    /// * 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.
-    ///
-    /// 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.
-    pub fn evaluate_multivariate(
-        &self,
-        flag_key: &str,
-        user_id: &str,
-    ) -> Result<String, PostHogEvaluationError> {
-        let hash_on_global_rollout_percentage =
-            Self::consistent_hash(user_id, flag_key, "multivariate");
-        let hash_on_group_rollout_percentage =
-            Self::consistent_hash(user_id, flag_key, "within_group");
-        self.evaluate_multivariate_inner(
-            flag_key,
-            hash_on_global_rollout_percentage,
-            hash_on_group_rollout_percentage,
-            &HashMap::new(),
-        )
-    }
-
-    /// 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_multivariate_inner(
-        &self,
-        flag_key: &str,
-        hash_on_global_rollout_percentage: f64,
-        hash_on_group_rollout_percentage: f64,
-        properties: &HashMap<String, PostHogFlagFilterPropertyValue>,
-    ) -> Result<String, 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
-                )));
-            }
-            // 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_group_rollout_percentage, properties)? {
-                    GroupEvaluationResult::MatchedAndOverride(variant) => return Ok(variant),
-                    GroupEvaluationResult::MatchedAndEvaluate => {
-                        let mut percentage = 0;
-                        for variant in &flag_config.filters.multivariate.variants {
-                            percentage += variant.rollout_percentage;
-                            if self
-                                .evaluate_percentage(hash_on_global_rollout_percentage, percentage)
-                            {
-                                return Ok(variant.key.clone());
-                            }
-                        }
-                        // This should not happen because the rollout percentage always adds up to 100, but just in case that PostHog
-                        // returned invalid spec, we return an error.
-                        return Err(PostHogEvaluationError::Internal(format!(
-                            "Rollout percentage does not add up to 100: {}",
-                            flag_key
-                        )));
-                    }
-                    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
-            )))
-        }
-    }
-}
-
-/// A lite PostHog client.
-///
-/// At the point of writing this code, PostHog does not have a functional Rust client with feature flag support.
-/// This is a lite version that only supports local evaluation of feature flags and only supports those JSON specs
-/// that will be used within Neon.
-///
-/// PostHog is designed as a browser-server system: the browser (client) side uses the client key and is exposed
-/// to the end users; the server side uses a server key and is not exposed to the end users. The client and the
-/// server has different API keys and provide a different set of APIs. In Neon, we only have the server (that is
-/// pageserver), and it will use both the client API and the server API. So we need to store two API keys within
-/// our PostHog client.
-///
-/// The server API is used to fetch the feature flag specs. The client API is used to capture events in case we
-/// 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 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,
-}
-
-impl PostHogClient {
-    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 {
-            server_api_key,
-            client_api_key,
-            project_id,
-            private_api_url,
-            public_api_url,
-            client,
-        }
-    }
-
-    pub fn new_with_us_region(
-        server_api_key: String,
-        client_api_key: String,
-        project_id: String,
-    ) -> Self {
-        Self::new(
-            server_api_key,
-            client_api_key,
-            project_id,
-            "https://us.posthog.com".to_string(),
-            "https://us.i.posthog.com".to_string(),
-        )
-    }
-
-    /// Fetch the feature flag specs from the server.
-    ///
-    /// This is unfortunately an undocumented API at:
-    /// - <https://posthog.com/docs/api/feature-flags#get-api-projects-project_id-feature_flags-local_evaluation>
-    /// - <https://posthog.com/docs/feature-flags/local-evaluation>
-    ///
-    /// The handling logic in [`FeatureStore`] mostly follows the Python API implementation.
-    /// See `_compute_flag_locally` in <https://github.com/PostHog/posthog-python/blob/master/posthog/client.py>
-    pub async fn get_feature_flags_local_evaluation(
-        &self,
-    ) -> anyhow::Result<LocalEvaluationResponse> {
-        // BASE_URL/api/projects/:project_id/feature_flags/local_evaluation
-        // with bearer token of self.server_api_key
-        let url = format!(
-            "{}/api/projects/{}/feature_flags/local_evaluation",
-            self.private_api_url, self.project_id
-        );
-        let response = self
-            .client
-            .get(url)
-            .bearer_auth(&self.server_api_key)
-            .send()
-            .await?;
-        let body = response.text().await?;
-        Ok(serde_json::from_str(&body)?)
-    }
-
-    /// Capture an event. This will only be used to report the feature flag usage back to PostHog, though
-    /// it also support a lot of other functionalities.
-    ///
-    /// <https://posthog.com/docs/api/capture>
-    pub async fn capture_event(
-        &self,
-        event: &str,
-        distinct_id: &str,
-        properties: &HashMap<String, PostHogFlagFilterPropertyValue>,
-    ) -> anyhow::Result<()> {
-        // PUBLIC_URL/capture/
-        // 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.client_api_key,
-                "distinct_id": distinct_id,
-                "event": event,
-                "properties": properties,
-            }))?)
-            .send()
-            .await?;
-        Ok(())
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    fn data() -> &'static str {
-        r#"{
-            "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
-                }
-            ],
-            "group_type_mapping": {},
-            "cohorts": {}
-        }"#
-    }
-
-    #[test]
-    fn parse_local_evaluation() {
-        let data = data();
-        let _: LocalEvaluationResponse = serde_json::from_str(data).unwrap();
-    }
-
-    #[test]
-    fn evaluate_multivariate() {
-        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_multivariate_inner("gc-compaction", 1.00, 0.40, &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_multivariate_inner("gc-compaction", 1.00, 0.40, &properties_unmatched);
-        assert!(matches!(
-            variant,
-            Err(PostHogEvaluationError::NoConditionGroupMatched)
-        ),);
-        let variant =
-            store.evaluate_multivariate_inner("gc-compaction", 0.80, 0.80, &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_multivariate_inner("gc-compaction", 0.10, 0.10, &properties);
-        assert_eq!(variant.unwrap(), "enabled-stage-2".to_string());
-
-        // It matches the second group as 0.50 <= 0.60 <= 0.80 and the properties are matched. Then it gets evaluated using the global percentage.
-        let variant = store.evaluate_multivariate_inner("gc-compaction", 0.99, 0.60, &properties);
-        assert_eq!(variant.unwrap(), "enabled-stage-1".to_string());
-        let variant = store.evaluate_multivariate_inner("gc-compaction", 0.80, 0.60, &properties);
-        assert_eq!(variant.unwrap(), "disabled".to_string());
-
-        // It matches the group conditions but not the group rollout percentage.
-        let variant = store.evaluate_multivariate_inner("gc-compaction", 1.00, 0.90, &properties);
-        assert!(matches!(
-            variant,
-            Err(PostHogEvaluationError::NoConditionGroupMatched)
-        ),);
-    }
-}

libs/remote_storage/src/azure_blob.rs

@@ -330,18 +330,11 @@ impl AzureBlobStorage {
                 if let Err(DownloadError::Timeout) = &next_item {
                     timeout_try_cnt += 1;
                     if timeout_try_cnt <= 5 {
-                        continue 'outer;
+                        continue;
                     }
                 }
 
-                let next_item = match next_item {
-                    Ok(next_item) => next_item,
-                    Err(e) => {
-                        // The error is potentially retryable, so we must rewind the loop after yielding.
-                        yield Err(e);
-                        continue 'outer;
-                    },
-                };
+                let next_item = next_item?;
 
                 // Log a warning if we saw two timeouts in a row before a successful request
                 if timeout_try_cnt > 2 {

libs/remote_storage/src/s3_bucket.rs

@@ -657,14 +657,7 @@ impl RemoteStorage for S3Bucket {
                     res = request => Ok(res),
                     _ = tokio::time::sleep(self.timeout) => Err(DownloadError::Timeout),
                     _ = cancel.cancelled() => Err(DownloadError::Cancelled),
-                };
-
-                if let Err(DownloadError::Timeout) = &response {
-                    yield Err(DownloadError::Timeout);
-                    continue 'outer;
-                }
-
-                let response = response?; // always yield cancellation errors and stop the stream
+                }?;
 
                 let response = response
                     .context("Failed to list S3 prefixes")

libs/safekeeper_api/src/models.rs

@@ -299,7 +299,6 @@ pub struct PullTimelineRequest {
     pub tenant_id: TenantId,
     pub timeline_id: TimelineId,
     pub http_hosts: Vec<String>,
-    pub ignore_tombstone: Option<bool>,
 }
 
 #[derive(Debug, Serialize, Deserialize)]

libs/utils/src/crashsafe.rs

@@ -1,7 +1,7 @@
 use std::borrow::Cow;
 use std::fs::{self, File};
 use std::io::{self, Write};
-use std::os::fd::AsFd;
+use std::os::fd::AsRawFd;
 
 use camino::{Utf8Path, Utf8PathBuf};
 
@@ -210,13 +210,13 @@ pub fn overwrite(
 
 /// Syncs the filesystem for the given file descriptor.
 #[cfg_attr(target_os = "macos", allow(unused_variables))]
-pub fn syncfs(fd: impl AsFd) -> anyhow::Result<()> {
+pub fn syncfs(fd: impl AsRawFd) -> anyhow::Result<()> {
     // Linux guarantees durability for syncfs.
     // POSIX doesn't have syncfs, and further does not actually guarantee durability of sync().
     #[cfg(target_os = "linux")]
     {
         use anyhow::Context;
-        nix::unistd::syncfs(fd).context("syncfs")?;
+        nix::unistd::syncfs(fd.as_raw_fd()).context("syncfs")?;
     }
     #[cfg(target_os = "macos")]
     {

libs/utils/src/fs_ext/rename_noreplace.rs

@@ -11,9 +11,9 @@ pub fn rename_noreplace<P1: ?Sized + NixPath, P2: ?Sized + NixPath>(
         #[cfg(all(target_os = "linux", target_env = "gnu"))]
         {
             nix::fcntl::renameat2(
-                nix::fcntl::AT_FDCWD,
+                None,
                 src,
-                nix::fcntl::AT_FDCWD,
+                None,
                 dst,
                 nix::fcntl::RenameFlags::RENAME_NOREPLACE,
             )

libs/utils/src/lock_file.rs

@@ -1,6 +1,6 @@
 //! A module to create and read lock files.
 //!
-//! File locking is done using [`nix::fcntl::Flock`] exclusive locks.
+//! File locking is done using [`fcntl::flock`] exclusive locks.
 //! The only consumer of this module is currently
 //! [`pid_file`](crate::pid_file). See the module-level comment
 //! there for potential pitfalls with lock files that are used
@@ -9,25 +9,26 @@
 use std::fs;
 use std::io::{Read, Write};
 use std::ops::Deref;
+use std::os::unix::prelude::AsRawFd;
 
 use anyhow::Context;
 use camino::{Utf8Path, Utf8PathBuf};
 use nix::errno::Errno::EAGAIN;
-use nix::fcntl::{Flock, FlockArg};
+use nix::fcntl;
 
 use crate::crashsafe;
 
-/// A handle to an open and flocked, but not-yet-written lock file.
+/// A handle to an open and unlocked, but not-yet-written lock file.
 /// Returned by [`create_exclusive`].
 #[must_use]
 pub struct UnwrittenLockFile {
     path: Utf8PathBuf,
-    file: Flock<fs::File>,
+    file: fs::File,
 }
 
 /// Returned by [`UnwrittenLockFile::write_content`].
 #[must_use]
-pub struct LockFileGuard(Flock<fs::File>);
+pub struct LockFileGuard(fs::File);
 
 impl Deref for LockFileGuard {
     type Target = fs::File;
@@ -66,14 +67,17 @@ pub fn create_exclusive(lock_file_path: &Utf8Path) -> anyhow::Result<UnwrittenLo
         .open(lock_file_path)
         .context("open lock file")?;
 
-    let res = Flock::lock(lock_file, FlockArg::LockExclusiveNonblock);
+    let res = fcntl::flock(
+        lock_file.as_raw_fd(),
+        fcntl::FlockArg::LockExclusiveNonblock,
+    );
     match res {
-        Ok(lock_file) => Ok(UnwrittenLockFile {
+        Ok(()) => Ok(UnwrittenLockFile {
             path: lock_file_path.to_owned(),
             file: lock_file,
         }),
-        Err((_, EAGAIN)) => anyhow::bail!("file is already locked"),
-        Err((_, e)) => Err(e).context("flock error"),
+        Err(EAGAIN) => anyhow::bail!("file is already locked"),
+        Err(e) => Err(e).context("flock error"),
     }
 }
 
@@ -101,37 +105,32 @@ pub enum LockFileRead {
 /// Check the [`LockFileRead`] variants for details.
 pub fn read_and_hold_lock_file(path: &Utf8Path) -> anyhow::Result<LockFileRead> {
     let res = fs::OpenOptions::new().read(true).open(path);
-    let lock_file = match res {
+    let mut lock_file = match res {
         Ok(f) => f,
         Err(e) => match e.kind() {
             std::io::ErrorKind::NotFound => return Ok(LockFileRead::NotExist),
             _ => return Err(e).context("open lock file"),
         },
     };
-    let res = Flock::lock(lock_file, FlockArg::LockExclusiveNonblock);
+    let res = fcntl::flock(
+        lock_file.as_raw_fd(),
+        fcntl::FlockArg::LockExclusiveNonblock,
+    );
     // We need the content regardless of lock success / failure.
     // But, read it after flock so that, if it succeeded, the content is consistent.
+    let mut content = String::new();
+    lock_file
+        .read_to_string(&mut content)
+        .context("read lock file")?;
     match res {
-        Ok(mut locked_file) => {
-            let mut content = String::new();
-            locked_file
-                .read_to_string(&mut content)
-                .context("read lock file")?;
-            Ok(LockFileRead::NotHeldByAnyProcess(
-                LockFileGuard(locked_file),
-                content,
-            ))
-        }
-        Err((mut not_locked_file, EAGAIN)) => {
-            let mut content = String::new();
-            not_locked_file
-                .read_to_string(&mut content)
-                .context("read lock file")?;
-            Ok(LockFileRead::LockedByOtherProcess {
-                not_locked_file,
-                content,
-            })
-        }
-        Err((_, e)) => Err(e).context("flock error"),
+        Ok(()) => Ok(LockFileRead::NotHeldByAnyProcess(
+            LockFileGuard(lock_file),
+            content,
+        )),
+        Err(EAGAIN) => Ok(LockFileRead::LockedByOtherProcess {
+            not_locked_file: lock_file,
+            content,
+        }),
+        Err(e) => Err(e).context("flock error"),
     }
 }

libs/utils/src/tracing_span_assert.rs

@@ -127,12 +127,12 @@ macro_rules! __check_fields_present {
 
             match check_fields_present0($extractors) {
                 Ok(FoundEverything) => Ok(()),
-                Ok(Unconfigured) if cfg!(feature = "testing") => {
+                Ok(Unconfigured) if cfg!(test) => {
                     // allow unconfigured in tests
                     Ok(())
                 },
                 Ok(Unconfigured) => {
-                    panic!(r#"utils::tracing_span_assert: outside of #[cfg(feature = "testing")] expected tracing to be configured with tracing_error::ErrorLayer"#)
+                    panic!("utils::tracing_span_assert: outside of #[cfg(test)] expected tracing to be configured with tracing_error::ErrorLayer")
                 },
                 Err(missing) => Err(missing)
             }

pageserver/Cargo.toml

@@ -96,7 +96,6 @@ strum.workspace = true
 strum_macros.workspace = true
 wal_decoder.workspace = true
 smallvec.workspace = true
-twox-hash.workspace = true
 
 [target.'cfg(target_os = "linux")'.dependencies]
 procfs.workspace = true

pageserver/benches/bench_ingest.rs

@@ -14,7 +14,6 @@ use pageserver_api::key::Key;
 use pageserver_api::models::virtual_file::IoMode;
 use pageserver_api::shard::TenantShardId;
 use pageserver_api::value::Value;
-use strum::IntoEnumIterator;
 use tokio_util::sync::CancellationToken;
 use utils::bin_ser::BeSer;
 use utils::id::{TenantId, TimelineId};
@@ -245,7 +244,13 @@ fn criterion_benchmark(c: &mut Criterion) {
     ];
     let exploded_parameters = {
         let mut out = Vec::new();
-        for io_mode in IoMode::iter() {
+        for io_mode in [
+            IoMode::Buffered,
+            #[cfg(target_os = "linux")]
+            IoMode::Direct,
+            #[cfg(target_os = "linux")]
+            IoMode::DirectRw,
+        ] {
             for param in expect.clone() {
                 let HandPickedParameters {
                     volume_mib,

pageserver/client/src/mgmt_api.rs

@@ -1,6 +1,5 @@
 use std::collections::HashMap;
 use std::error::Error as _;
-use std::time::Duration;
 
 use bytes::Bytes;
 use detach_ancestor::AncestorDetached;
@@ -820,25 +819,4 @@ impl Client {
             .await
             .map(|resp| resp.status())
     }
-
-    pub async fn activate_post_import(
-        &self,
-        tenant_shard_id: TenantShardId,
-        timeline_id: TimelineId,
-        activate_timeline_timeout: Duration,
-    ) -> Result<TimelineInfo> {
-        let uri = format!(
-            "{}/v1/tenant/{}/timeline/{}/activate_post_import?timeline_activate_timeout_ms={}",
-            self.mgmt_api_endpoint,
-            tenant_shard_id,
-            timeline_id,
-            activate_timeline_timeout.as_millis()
-        );
-
-        self.request(Method::PUT, uri, ())
-            .await?
-            .json()
-            .await
-            .map_err(Error::ReceiveBody)
-    }
 }

pageserver/pagebench/src/cmd/getpage_latest_lsn.rs

@@ -65,9 +65,6 @@ pub(crate) struct Args {
     #[clap(long, default_value = "1")]
     queue_depth: NonZeroUsize,
 
-    #[clap(long)]
-    only_relnode: Option<u32>,
-
     targets: Option<Vec<TenantTimelineId>>,
 }
 
@@ -209,12 +206,7 @@ async fn main_impl(
                     for r in partitioning.keys.ranges.iter() {
                         let mut i = r.start;
                         while i != r.end {
-                            let mut include = true;
-                            include &= i.is_rel_block_key();
-                            if let Some(only_relnode) = args.only_relnode {
-                                include &= i.is_rel_block_of_rel(only_relnode);
-                            }
-                            if include {
+                            if i.is_rel_block_key() {
                                 filtered.add_key(i);
                             }
                             i = i.next();

pageserver/src/controller_upcall_client.rs

@@ -7,7 +7,7 @@ use pageserver_api::models::ShardImportStatus;
 use pageserver_api::shard::TenantShardId;
 use pageserver_api::upcall_api::{
     PutTimelineImportStatusRequest, ReAttachRequest, ReAttachResponse, ReAttachResponseTenant,
-    TimelineImportStatusRequest, ValidateRequest, ValidateRequestTenant, ValidateResponse,
+    ValidateRequest, ValidateRequestTenant, ValidateResponse,
 };
 use reqwest::Certificate;
 use serde::Serialize;
@@ -51,15 +51,8 @@ pub trait StorageControllerUpcallApi {
         &self,
         tenant_shard_id: TenantShardId,
         timeline_id: TimelineId,
-        generation: Generation,
         status: ShardImportStatus,
     ) -> impl Future<Output = Result<(), RetryForeverError>> + Send;
-    fn get_timeline_import_status(
-        &self,
-        tenant_shard_id: TenantShardId,
-        timeline_id: TimelineId,
-        generation: Generation,
-    ) -> impl Future<Output = Result<ShardImportStatus, RetryForeverError>> + Send;
 }
 
 impl StorageControllerUpcallClient {
@@ -104,7 +97,6 @@ impl StorageControllerUpcallClient {
         &self,
         url: &url::Url,
         request: R,
-        method: reqwest::Method,
     ) -> Result<T, RetryForeverError>
     where
         R: Serialize,
@@ -114,7 +106,7 @@ impl StorageControllerUpcallClient {
             || async {
                 let response = self
                     .http_client
-                    .request(method.clone(), url.clone())
+                    .post(url.clone())
                     .json(&request)
                     .send()
                     .await?;
@@ -223,9 +215,7 @@ impl StorageControllerUpcallApi for StorageControllerUpcallClient {
             register: register.clone(),
         };
 
-        let response: ReAttachResponse = self
-            .retry_http_forever(&url, request, reqwest::Method::POST)
-            .await?;
+        let response: ReAttachResponse = self.retry_http_forever(&url, request).await?;
         tracing::info!(
             "Received re-attach response with {} tenants (node {}, register: {:?})",
             response.tenants.len(),
@@ -278,9 +268,7 @@ impl StorageControllerUpcallApi for StorageControllerUpcallClient {
                 return Err(RetryForeverError::ShuttingDown);
             }
 
-            let response: ValidateResponse = self
-                .retry_http_forever(&url, request, reqwest::Method::POST)
-                .await?;
+            let response: ValidateResponse = self.retry_http_forever(&url, request).await?;
             for rt in response.tenants {
                 result.insert(rt.id, rt.valid);
             }
@@ -299,7 +287,6 @@ impl StorageControllerUpcallApi for StorageControllerUpcallClient {
         &self,
         tenant_shard_id: TenantShardId,
         timeline_id: TimelineId,
-        generation: Generation,
         status: ShardImportStatus,
     ) -> Result<(), RetryForeverError> {
         let url = self
@@ -310,35 +297,9 @@ impl StorageControllerUpcallApi for StorageControllerUpcallClient {
         let request = PutTimelineImportStatusRequest {
             tenant_shard_id,
             timeline_id,
-            generation,
             status,
         };
 
-        self.retry_http_forever(&url, request, reqwest::Method::POST)
-            .await
-    }
-
-    #[tracing::instrument(skip_all)] // so that warning logs from retry_http_forever have context
-    async fn get_timeline_import_status(
-        &self,
-        tenant_shard_id: TenantShardId,
-        timeline_id: TimelineId,
-        generation: Generation,
-    ) -> Result<ShardImportStatus, RetryForeverError> {
-        let url = self
-            .base_url
-            .join("timeline_import_status")
-            .expect("Failed to build path");
-
-        let request = TimelineImportStatusRequest {
-            tenant_shard_id,
-            timeline_id,
-            generation,
-        };
-
-        let response: ShardImportStatus = self
-            .retry_http_forever(&url, request, reqwest::Method::GET)
-            .await?;
-        Ok(response)
+        self.retry_http_forever(&url, request).await
     }
 }

pageserver/src/deletion_queue.rs

@@ -663,7 +663,6 @@ mod test {
     use camino::Utf8Path;
     use hex_literal::hex;
     use pageserver_api::key::Key;
-    use pageserver_api::models::ShardImportStatus;
     use pageserver_api::shard::ShardIndex;
     use pageserver_api::upcall_api::ReAttachResponseTenant;
     use remote_storage::{RemoteStorageConfig, RemoteStorageKind};
@@ -793,20 +792,10 @@ mod test {
             &self,
             _tenant_shard_id: TenantShardId,
             _timeline_id: TimelineId,
-            _generation: Generation,
             _status: pageserver_api::models::ShardImportStatus,
         ) -> Result<(), RetryForeverError> {
             unimplemented!()
         }
-
-        async fn get_timeline_import_status(
-            &self,
-            _tenant_shard_id: TenantShardId,
-            _timeline_id: TimelineId,
-            _generation: Generation,
-        ) -> Result<ShardImportStatus, RetryForeverError> {
-            unimplemented!()
-        }
     }
 
     async fn setup(test_name: &str) -> anyhow::Result<TestSetup> {

pageserver/src/http/routes.rs

@@ -3500,107 +3500,6 @@ async fn put_tenant_timeline_import_wal(
     }.instrument(span).await
 }
 
-/// Activate a timeline after its import has completed
-///
-/// The endpoint is idempotent and callers are expected to retry all
-/// errors until a successful response.
-async fn activate_post_import_handler(
-    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 timeline_id: TimelineId = parse_request_param(&request, "timeline_id")?;
-    const DEFAULT_ACTIVATE_TIMEOUT: Duration = Duration::from_secs(1);
-    let activate_timeout = parse_query_param(&request, "timeline_activate_timeout_ms")?
-        .map(Duration::from_millis)
-        .unwrap_or(DEFAULT_ACTIVATE_TIMEOUT);
-
-    let span = info_span!(
-        "activate_post_import_handler",
-        tenant_id=%tenant_shard_id.tenant_id,
-        timeline_id=%timeline_id,
-        shard_id=%tenant_shard_id.shard_slug()
-    );
-
-    async move {
-        let state = get_state(&request);
-        let tenant = state
-            .tenant_manager
-            .get_attached_tenant_shard(tenant_shard_id)?;
-
-        tenant.wait_to_become_active(ACTIVE_TENANT_TIMEOUT).await?;
-
-        tenant
-            .finalize_importing_timeline(timeline_id)
-            .await
-            .map_err(ApiError::InternalServerError)?;
-
-        match tenant.get_timeline(timeline_id, false) {
-            Ok(_timeline) => {
-                // Timeline is already visible. Reset not required: fall through.
-            }
-            Err(GetTimelineError::NotFound { .. }) => {
-                // This is crude: we reset the whole tenant such that the new timeline is detected
-                // and activated. We can come up with something more granular in the future.
-                //
-                // Note that we only reset the tenant if required: when the timeline is
-                // not present in [`Tenant::timelines`].
-                let ctx = RequestContext::new(TaskKind::MgmtRequest, DownloadBehavior::Warn);
-                state
-                    .tenant_manager
-                    .reset_tenant(tenant_shard_id, false, &ctx)
-                    .await
-                    .map_err(ApiError::InternalServerError)?;
-            }
-            Err(GetTimelineError::ShuttingDown) => {
-                return Err(ApiError::ShuttingDown);
-            }
-            Err(GetTimelineError::NotActive { .. }) => {
-                unreachable!("Called get_timeline with active_only=false");
-            }
-        }
-
-        let timeline = tenant.get_timeline(timeline_id, false)?;
-
-        let ctx = RequestContext::new(TaskKind::MgmtRequest, DownloadBehavior::Warn)
-            .with_scope_timeline(&timeline);
-
-        let result =
-            tokio::time::timeout(activate_timeout, timeline.wait_to_become_active(&ctx)).await;
-        match result {
-            Ok(Ok(())) => {
-                // fallthrough
-            }
-            // Timeline reached some other state that's not active
-            // TODO(vlad): if the tenant is broken, return a permananet error
-            Ok(Err(_timeline_state)) => {
-                return Err(ApiError::InternalServerError(anyhow::anyhow!(
-                    "Timeline activation failed"
-                )));
-            }
-            // Activation timed out
-            Err(_) => {
-                return Err(ApiError::Timeout("Timeline activation timed out".into()));
-            }
-        }
-
-        let timeline_info = build_timeline_info(
-            &timeline, false, // include_non_incremental_logical_size,
-            false, // force_await_initial_logical_size
-            &ctx,
-        )
-        .await
-        .context("get local timeline info")
-        .map_err(ApiError::InternalServerError)?;
-
-        json_response(StatusCode::OK, timeline_info)
-    }
-    .instrument(span)
-    .await
-}
-
 /// Read the end of a tar archive.
 ///
 /// A tar archive normally ends with two consecutive blocks of zeros, 512 bytes each.
@@ -4025,9 +3924,5 @@ pub fn make_router(
             "/v1/tenant/:tenant_id/timeline/:timeline_id/import_wal",
             |r| api_handler(r, put_tenant_timeline_import_wal),
         )
-        .put(
-            "/v1/tenant/:tenant_shard_id/timeline/:timeline_id/activate_post_import",
-            |r| api_handler(r, activate_post_import_handler),
-        )
         .any(handler_404))
 }

pageserver/src/tenant.rs

@@ -50,7 +50,6 @@ use remote_timeline_client::{
 use secondary::heatmap::{HeatMapTenant, HeatMapTimeline};
 use storage_broker::BrokerClientChannel;
 use timeline::compaction::{CompactionOutcome, GcCompactionQueue};
-use timeline::import_pgdata::ImportingTimeline;
 use timeline::offload::{OffloadError, offload_timeline};
 use timeline::{
     CompactFlags, CompactOptions, CompactionError, PreviousHeatmap, ShutdownMode, import_pgdata,
@@ -285,19 +284,6 @@ pub struct TenantShard {
     /// **Lock order**: if acquiring all (or a subset), acquire them in order `timelines`, `timelines_offloaded`, `timelines_creating`
     timelines_offloaded: Mutex<HashMap<TimelineId, Arc<OffloadedTimeline>>>,
 
-    /// Tracks the timelines that are currently importing into this tenant shard.
-    ///
-    /// Note that importing timelines are also present in [`Self::timelines_creating`].
-    /// Keep this in mind when ordering lock acquisition.
-    ///
-    /// Lifetime:
-    /// * An imported timeline is created while scanning the bucket on tenant attach
-    ///   if the index part contains an `import_pgdata` entry and said field marks the import
-    ///   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, 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.
     ///
@@ -937,10 +923,19 @@ enum StartCreatingTimelineResult {
 
 #[allow(clippy::large_enum_variant, reason = "TODO")]
 enum TimelineInitAndSyncResult {
-    ReadyToActivate,
+    ReadyToActivate(Arc<Timeline>),
     NeedsSpawnImportPgdata(TimelineInitAndSyncNeedsSpawnImportPgdata),
 }
 
+impl TimelineInitAndSyncResult {
+    fn ready_to_activate(self) -> Option<Arc<Timeline>> {
+        match self {
+            Self::ReadyToActivate(timeline) => Some(timeline),
+            _ => None,
+        }
+    }
+}
+
 #[must_use]
 struct TimelineInitAndSyncNeedsSpawnImportPgdata {
     timeline: Arc<Timeline>,
@@ -1017,6 +1012,10 @@ enum CreateTimelineCause {
 enum LoadTimelineCause {
     Attach,
     Unoffload,
+    ImportPgdata {
+        create_guard: TimelineCreateGuard,
+        activate: ActivateTimelineArgs,
+    },
 }
 
 #[derive(thiserror::Error, Debug)]
@@ -1098,7 +1097,7 @@ impl TenantShard {
         self: &Arc<Self>,
         timeline_id: TimelineId,
         resources: TimelineResources,
-        index_part: IndexPart,
+        mut index_part: IndexPart,
         metadata: TimelineMetadata,
         previous_heatmap: Option<PreviousHeatmap>,
         ancestor: Option<Arc<Timeline>>,
@@ -1107,7 +1106,7 @@ impl TenantShard {
     ) -> anyhow::Result<TimelineInitAndSyncResult> {
         let tenant_id = self.tenant_shard_id;
 
-        let import_pgdata = index_part.import_pgdata.clone();
+        let import_pgdata = index_part.import_pgdata.take();
         let idempotency = match &import_pgdata {
             Some(import_pgdata) => {
                 CreateTimelineIdempotency::ImportPgdata(CreatingTimelineIdempotencyImportPgdata {
@@ -1128,7 +1127,7 @@ impl TenantShard {
             }
         };
 
-        let (timeline, _timeline_ctx) = self.create_timeline_struct(
+        let (timeline, timeline_ctx) = self.create_timeline_struct(
             timeline_id,
             &metadata,
             previous_heatmap,
@@ -1198,6 +1197,14 @@ impl TenantShard {
 
         match import_pgdata {
             Some(import_pgdata) if !import_pgdata.is_done() => {
+                match cause {
+                    LoadTimelineCause::Attach | LoadTimelineCause::Unoffload => (),
+                    LoadTimelineCause::ImportPgdata { .. } => {
+                        unreachable!(
+                            "ImportPgdata should not be reloading timeline import is done and persisted as such in s3"
+                        )
+                    }
+                }
                 let mut guard = self.timelines_creating.lock().unwrap();
                 if !guard.insert(timeline_id) {
                     // We should never try and load the same timeline twice during startup
@@ -1253,7 +1260,26 @@ impl TenantShard {
                     "Timeline has no ancestor and no layer files"
                 );
 
-                Ok(TimelineInitAndSyncResult::ReadyToActivate)
+                match cause {
+                    LoadTimelineCause::Attach | LoadTimelineCause::Unoffload => (),
+                    LoadTimelineCause::ImportPgdata {
+                        create_guard,
+                        activate,
+                    } => {
+                        // TODO: see the comment in the task code above how I'm not so certain
+                        // it is safe to activate here because of concurrent shutdowns.
+                        match activate {
+                            ActivateTimelineArgs::Yes { broker_client } => {
+                                info!("activating timeline after reload from pgdata import task");
+                                timeline.activate(self.clone(), broker_client, None, &timeline_ctx);
+                            }
+                            ActivateTimelineArgs::No => (),
+                        }
+                        drop(create_guard);
+                    }
+                }
+
+                Ok(TimelineInitAndSyncResult::ReadyToActivate(timeline))
             }
         }
     }
@@ -1742,7 +1768,7 @@ impl TenantShard {
                 })?;
 
             match effect {
-                TimelineInitAndSyncResult::ReadyToActivate => {
+                TimelineInitAndSyncResult::ReadyToActivate(_) => {
                     // activation happens later, on Tenant::activate
                 }
                 TimelineInitAndSyncResult::NeedsSpawnImportPgdata(
@@ -1752,24 +1778,13 @@ impl TenantShard {
                         guard,
                     },
                 ) => {
-                    let timeline_id = timeline.timeline_id;
-                    let import_task_handle =
-                        tokio::task::spawn(self.clone().create_timeline_import_pgdata_task(
-                            timeline.clone(),
-                            import_pgdata,
-                            guard,
-                            ctx.detached_child(TaskKind::ImportPgdata, DownloadBehavior::Warn),
-                        ));
-
-                    let prev = self.timelines_importing.lock().unwrap().insert(
-                        timeline_id,
-                        ImportingTimeline {
-                            timeline: timeline.clone(),
-                            import_task_handle,
-                        },
-                    );
-
-                    assert!(prev.is_none());
+                    tokio::task::spawn(self.clone().create_timeline_import_pgdata_task(
+                        timeline,
+                        import_pgdata,
+                        ActivateTimelineArgs::No,
+                        guard,
+                        ctx.detached_child(TaskKind::ImportPgdata, DownloadBehavior::Warn),
+                    ));
                 }
             }
         }
@@ -2663,7 +2678,14 @@ impl TenantShard {
                     .await?
             }
             CreateTimelineParams::ImportPgdata(params) => {
-                self.create_timeline_import_pgdata(params, ctx).await?
+                self.create_timeline_import_pgdata(
+                    params,
+                    ActivateTimelineArgs::Yes {
+                        broker_client: broker_client.clone(),
+                    },
+                    ctx,
+                )
+                .await?
             }
         };
 
@@ -2737,6 +2759,7 @@ impl TenantShard {
     async fn create_timeline_import_pgdata(
         self: &Arc<Self>,
         params: CreateTimelineParamsImportPgdata,
+        activate: ActivateTimelineArgs,
         ctx: &RequestContext,
     ) -> Result<CreateTimelineResult, CreateTimelineError> {
         let CreateTimelineParamsImportPgdata {
@@ -2817,71 +2840,24 @@ impl TenantShard {
 
         let (timeline, timeline_create_guard) = uninit_timeline.finish_creation_myself();
 
-        let import_task_handle = tokio::spawn(self.clone().create_timeline_import_pgdata_task(
+        tokio::spawn(self.clone().create_timeline_import_pgdata_task(
             timeline.clone(),
             index_part,
+            activate,
             timeline_create_guard,
             timeline_ctx.detached_child(TaskKind::ImportPgdata, DownloadBehavior::Warn),
         ));
 
-        let prev = self.timelines_importing.lock().unwrap().insert(
-            timeline.timeline_id,
-            ImportingTimeline {
-                timeline: timeline.clone(),
-                import_task_handle,
-            },
-        );
-
-        // Idempotency is enforced higher up the stack
-        assert!(prev.is_none());
-
         // NB: the timeline doesn't exist in self.timelines at this point
         Ok(CreateTimelineResult::ImportSpawned(timeline))
     }
 
-    /// Finalize the import of a timeline on this shard by marking it complete in
-    /// the index part. If the import task hasn't finished yet, returns an error.
-    ///
-    /// This method is idempotent. If the import was finalized once, the next call
-    /// will be a no-op.
-    pub(crate) async fn finalize_importing_timeline(
-        &self,
-        timeline_id: TimelineId,
-    ) -> 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(anyhow::anyhow!("Import task not done yet"));
-                    }
-
-                    importing_timeline.timeline.clone()
-                }
-                None => {
-                    return Ok(());
-                }
-            }
-        };
-
-        timeline
-            .remote_client
-            .schedule_index_upload_for_import_pgdata_finalize()?;
-        timeline.remote_client.wait_completion().await?;
-
-        self.timelines_importing
-            .lock()
-            .unwrap()
-            .remove(&timeline_id);
-
-        Ok(())
-    }
-
     #[instrument(skip_all, fields(tenant_id=%self.tenant_shard_id.tenant_id, shard_id=%self.tenant_shard_id.shard_slug(), timeline_id=%timeline.timeline_id))]
     async fn create_timeline_import_pgdata_task(
         self: Arc<TenantShard>,
         timeline: Arc<Timeline>,
         index_part: import_pgdata::index_part_format::Root,
+        activate: ActivateTimelineArgs,
         timeline_create_guard: TimelineCreateGuard,
         ctx: RequestContext,
     ) {
@@ -2893,6 +2869,7 @@ impl TenantShard {
             .create_timeline_import_pgdata_task_impl(
                 timeline,
                 index_part,
+                activate,
                 timeline_create_guard,
                 ctx,
             )
@@ -2908,15 +2885,60 @@ impl TenantShard {
         self: Arc<TenantShard>,
         timeline: Arc<Timeline>,
         index_part: import_pgdata::index_part_format::Root,
-        _timeline_create_guard: TimelineCreateGuard,
+        activate: ActivateTimelineArgs,
+        timeline_create_guard: TimelineCreateGuard,
         ctx: RequestContext,
     ) -> Result<(), anyhow::Error> {
         info!("importing pgdata");
-        let ctx = ctx.with_scope_timeline(&timeline);
         import_pgdata::doit(&timeline, index_part, &ctx, self.cancel.clone())
             .await
             .context("import")?;
-        info!("import done - waiting for activation");
+        info!("import done");
+
+        //
+        // Reload timeline from remote.
+        // This proves that the remote state is attachable, and it reuses the code.
+        //
+        // TODO: think about whether this is safe to do with concurrent TenantShard::shutdown.
+        // timeline_create_guard hols the tenant gate open, so, shutdown cannot _complete_ until we exit.
+        // But our activate() call might launch new background tasks after TenantShard::shutdown
+        // already went past shutting down the TenantShard::timelines, which this timeline here is no part of.
+        // I think the same problem exists with the bootstrap & branch mgmt API tasks (tenant shutting
+        // down while bootstrapping/branching + activating), but, the race condition is much more likely
+        // to manifest because of the long runtime of this import task.
+
+        //        in theory this shouldn't even .await anything except for coop yield
+        info!("shutting down timeline");
+        timeline.shutdown(ShutdownMode::Hard).await;
+        info!("timeline shut down, reloading from remote");
+        // TODO: we can't do the following check because create_timeline_import_pgdata must return an Arc<Timeline>
+        // let Some(timeline) = Arc::into_inner(timeline) else {
+        //     anyhow::bail!("implementation error: timeline that we shut down was still referenced from somewhere");
+        // };
+        let timeline_id = timeline.timeline_id;
+
+        // load from object storage like TenantShard::attach does
+        let resources = self.build_timeline_resources(timeline_id);
+        let index_part = resources
+            .remote_client
+            .download_index_file(&self.cancel)
+            .await?;
+        let index_part = match index_part {
+            MaybeDeletedIndexPart::Deleted(_) => {
+                // likely concurrent delete call, cplane should prevent this
+                anyhow::bail!(
+                    "index part says deleted but we are not done creating yet, this should not happen but"
+                )
+            }
+            MaybeDeletedIndexPart::IndexPart(p) => p,
+        };
+        let metadata = index_part.metadata.clone();
+        self
+            .load_remote_timeline(timeline_id, index_part, metadata, None, resources, LoadTimelineCause::ImportPgdata{
+                create_guard: timeline_create_guard, activate, }, &ctx)
+            .await?
+            .ready_to_activate()
+            .context("implementation error: reloaded timeline still needs import after import reported success")?;
 
         anyhow::Ok(())
     }
@@ -3453,14 +3475,6 @@ impl TenantShard {
                 timeline.defuse_for_tenant_drop();
             });
         }
-        {
-            let mut timelines_importing = self.timelines_importing.lock().unwrap();
-            timelines_importing
-                .drain()
-                .for_each(|(_timeline_id, importing_timeline)| {
-                    importing_timeline.shutdown();
-                });
-        }
         // test_long_timeline_create_then_tenant_delete is leaning on this message
         tracing::info!("Waiting for timelines...");
         while let Some(res) = js.join_next().await {
@@ -3935,6 +3949,13 @@ where
     Ok(result)
 }
 
+enum ActivateTimelineArgs {
+    Yes {
+        broker_client: storage_broker::BrokerClientChannel,
+    },
+    No,
+}
+
 impl TenantShard {
     pub fn tenant_specific_overrides(&self) -> pageserver_api::models::TenantConfig {
         self.tenant_conf.load().tenant_conf.clone()
@@ -4301,7 +4322,6 @@ impl TenantShard {
             timelines: Mutex::new(HashMap::new()),
             timelines_creating: Mutex::new(HashSet::new()),
             timelines_offloaded: Mutex::new(HashMap::new()),
-            timelines_importing: Mutex::new(HashMap::new()),
             remote_tenant_manifest: Default::default(),
             gc_cs: tokio::sync::Mutex::new(()),
             walredo_mgr,

pageserver/src/tenant/remote_timeline_client.rs

@@ -949,35 +949,6 @@ impl RemoteTimelineClient {
         Ok(())
     }
 
-    /// If the `import_pgdata` field marks the timeline as having an import in progress,
-    /// launch an index-file upload operation that transitions it to done in the background
-    pub(crate) fn schedule_index_upload_for_import_pgdata_finalize(
-        self: &Arc<Self>,
-    ) -> anyhow::Result<()> {
-        use import_pgdata::index_part_format;
-
-        let mut guard = self.upload_queue.lock().unwrap();
-        let upload_queue = guard.initialized_mut()?;
-        let to_update = match &upload_queue.dirty.import_pgdata {
-            Some(import) if !import.is_done() => Some(import),
-            Some(_) | None => None,
-        };
-
-        if let Some(old) = to_update {
-            let new =
-                index_part_format::Root::V1(index_part_format::V1::Done(index_part_format::Done {
-                    idempotency_key: old.idempotency_key().clone(),
-                    started_at: *old.started_at(),
-                    finished_at: chrono::Utc::now().naive_utc(),
-                }));
-
-            upload_queue.dirty.import_pgdata = Some(new);
-            self.schedule_index_upload(upload_queue);
-        }
-
-        Ok(())
-    }
-
     /// Launch an index-file upload operation in the background, setting `gc_compaction_state` field.
     pub(crate) fn schedule_index_upload_for_gc_compaction_state_update(
         self: &Arc<Self>,

pageserver/src/tenant/secondary/downloader.rs

@@ -668,9 +668,7 @@ impl From<DownloadError> for UpdateError {
 
 impl From<std::io::Error> for UpdateError {
     fn from(value: std::io::Error) -> Self {
-        if let Some(nix::errno::Errno::ENOSPC) =
-            value.raw_os_error().map(nix::errno::Errno::from_raw)
-        {
+        if let Some(nix::errno::Errno::ENOSPC) = value.raw_os_error().map(nix::errno::from_i32) {
             UpdateError::NoSpace
         } else if value
             .get_ref()

pageserver/src/tenant/timeline/compaction.rs

@@ -1277,8 +1277,6 @@ impl Timeline {
             return Ok(CompactionOutcome::YieldForL0);
         }
 
-        let gc_cutoff = *self.applied_gc_cutoff_lsn.read();
-
         // 2. Repartition and create image layers if necessary
         match self
             .repartition(
@@ -1289,7 +1287,7 @@ impl Timeline {
             )
             .await
         {
-            Ok(((dense_partitioning, sparse_partitioning), lsn)) if lsn >= gc_cutoff => {
+            Ok(((dense_partitioning, sparse_partitioning), lsn)) => {
                 // Disables access_stats updates, so that the files we read remain candidates for eviction after we're done with them
                 let image_ctx = RequestContextBuilder::from(ctx)
                     .access_stats_behavior(AccessStatsBehavior::Skip)
@@ -1343,10 +1341,6 @@ impl Timeline {
                 }
             }
 
-            Ok(_) => {
-                info!("skipping repartitioning due to image compaction LSN being below GC cutoff");
-            }
-
             // Suppress errors when cancelled.
             Err(_) if self.cancel.is_cancelled() => {}
             Err(err) if err.is_cancel() => {}
@@ -3435,7 +3429,6 @@ impl Timeline {
 
         // Step 2: Produce images+deltas.
         let mut accumulated_values = Vec::new();
-        let mut accumulated_values_estimated_size = 0;
         let mut last_key: Option<Key> = None;
 
         // Only create image layers when there is no ancestor branches. TODO: create covering image layer
@@ -3612,18 +3605,7 @@ impl Timeline {
                 if last_key.is_none() {
                     last_key = Some(key);
                 }
-                accumulated_values_estimated_size += val.estimated_size();
                 accumulated_values.push((key, lsn, val));
-
-                // Accumulated values should never exceed 512MB.
-                if accumulated_values_estimated_size >= 1024 * 1024 * 512 {
-                    return Err(CompactionError::Other(anyhow!(
-                        "too many values for a single key: {} for key {}, {} items",
-                        accumulated_values_estimated_size,
-                        key,
-                        accumulated_values.len()
-                    )));
-                }
             } else {
                 let last_key: &mut Key = last_key.as_mut().unwrap();
                 stat.on_unique_key_visited(); // TODO: adjust statistics for partial compaction
@@ -3656,7 +3638,6 @@ impl Timeline {
                     .map_err(CompactionError::Other)?;
                 accumulated_values.clear();
                 *last_key = key;
-                accumulated_values_estimated_size = val.estimated_size();
                 accumulated_values.push((key, lsn, val));
             }
         }

pageserver/src/tenant/timeline/import_pgdata.rs

@@ -1,10 +1,8 @@
 use std::sync::Arc;
 
 use anyhow::{Context, bail};
-use importbucket_client::{ControlFile, RemoteStorageWrapper};
 use pageserver_api::models::ShardImportStatus;
 use remote_storage::RemotePath;
-use tokio::task::JoinHandle;
 use tokio_util::sync::CancellationToken;
 use tracing::info;
 use utils::lsn::Lsn;
@@ -19,17 +17,6 @@ mod importbucket_client;
 mod importbucket_format;
 pub(crate) mod index_part_format;
 
-pub(crate) struct ImportingTimeline {
-    pub import_task_handle: JoinHandle<()>,
-    pub timeline: Arc<Timeline>,
-}
-
-impl ImportingTimeline {
-    pub(crate) fn shutdown(self) {
-        self.import_task_handle.abort();
-    }
-}
-
 pub async fn doit(
     timeline: &Arc<Timeline>,
     index_part: index_part_format::Root,
@@ -39,225 +26,173 @@ pub async fn doit(
     let index_part_format::Root::V1(v1) = index_part;
     let index_part_format::InProgress {
         location,
-        idempotency_key: _,
-        started_at: _,
+        idempotency_key,
+        started_at,
     } = match v1 {
         index_part_format::V1::Done(_) => return Ok(()),
         index_part_format::V1::InProgress(in_progress) => in_progress,
     };
 
-    let storcon_client = StorageControllerUpcallClient::new(timeline.conf, &cancel);
+    let storage = importbucket_client::new(timeline.conf, &location, cancel.clone()).await?;
 
-    let shard_status = storcon_client
-        .get_timeline_import_status(
-            timeline.tenant_shard_id,
-            timeline.timeline_id,
-            timeline.generation,
-        )
-        .await
-        .map_err(|_err| anyhow::anyhow!("Shut down while getting timeline import status"))?;
-
-    info!(?shard_status, "peeking shard status");
-    match shard_status {
-        ShardImportStatus::InProgress(maybe_progress) => {
-            let storage =
-                importbucket_client::new(timeline.conf, &location, cancel.clone()).await?;
-
-            let control_file_res = if maybe_progress.is_none() {
-                // Only prepare the import once when there's no progress.
-                prepare_import(timeline, storage.clone(), &cancel).await
-            } else {
-                storage.get_control_file().await
-            };
-
-            let control_file = match control_file_res {
-                Ok(cf) => cf,
-                Err(err) => {
-                    return Err(
-                        terminate_flow_with_error(timeline, err, &storcon_client, &cancel).await,
-                    );
-                }
-            };
-
-            let res = flow::run(
-                timeline.clone(),
-                control_file,
-                storage.clone(),
-                maybe_progress,
-                ctx,
-            )
-            .await;
-            if let Err(err) = res {
-                return Err(
-                    terminate_flow_with_error(timeline, err, &storcon_client, &cancel).await,
-                );
-            }
-
-            // 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.
-            //
-            // Note that we do not mark the import complete in the index part now.
-            // This happens in [`Tenant::finalize_importing_timeline`] in response
-            // to the storage controller calling
-            // `/v1/tenant/:tenant_id/timeline/:timeline_id/activate_post_import`.
-            storcon_client
-                .put_timeline_import_status(
-                    timeline.tenant_shard_id,
-                    timeline.timeline_id,
-                    timeline.generation,
-                    ShardImportStatus::Done,
-                )
-                .await
-                .map_err(|_err| {
-                    anyhow::anyhow!("Shut down while putting timeline import status")
-                })?;
-        }
-        ShardImportStatus::Error(err) => {
-            info!(
-                "shard status indicates that the shard is done (error), skipping import {}",
-                err
-            );
-        }
-        ShardImportStatus::Done => {
-            info!("shard status indicates that the shard is done (success), skipping import");
-        }
-    }
-
-    Ok(())
-}
-
-async fn prepare_import(
-    timeline: &Arc<Timeline>,
-    storage: RemoteStorageWrapper,
-    cancel: &CancellationToken,
-) -> anyhow::Result<ControlFile> {
-    // Wipe the slate clean before starting the import as a precaution.
-    // This method is only called when there's no recorded checkpoint for the import
-    // in the storage controller.
-    //
-    // Note that this is split-brain safe (two imports for same timeline shards running in
-    // different generations) because we go through the usual deletion path, including deletion queue.
-    info!("wipe the slate clean");
-    {
-        // TODO: do we need to hold GC lock for this?
-        let mut guard = timeline.layers.write().await;
-        assert!(
-            guard.layer_map()?.open_layer.is_none(),
-            "while importing, there should be no in-memory layer" // this just seems like a good place to assert it
-        );
-        let all_layers_keys = guard.all_persistent_layers();
-        let all_layers: Vec<_> = all_layers_keys
-            .iter()
-            .map(|key| guard.get_from_key(key))
-            .collect();
-        let open = guard.open_mut().context("open_mut")?;
-
-        timeline.remote_client.schedule_gc_update(&all_layers)?;
-        open.finish_gc_timeline(&all_layers);
-    }
-
-    //
-    // Wait for pgdata to finish uploading
-    //
-    info!("wait for pgdata to reach status 'done'");
     let status_prefix = RemotePath::from_string("status").unwrap();
-    let pgdata_status_key = status_prefix.join("pgdata");
-    loop {
-        let res = async {
-            let pgdata_status: Option<importbucket_format::PgdataStatus> = storage
-                .get_json(&pgdata_status_key)
-                .await
-                .context("get pgdata status")?;
-            info!(?pgdata_status, "peeking pgdata status");
-            if pgdata_status.map(|st| st.done).unwrap_or(false) {
-                Ok(())
-            } else {
-                Err(anyhow::anyhow!("pgdata not done yet"))
-            }
+
+    //
+    // See if shard is done.
+    // TODO: incorporate generations into status key for split brain safety. Figure out together with checkpointing.
+    //
+    let shard_status_key =
+        status_prefix.join(format!("shard-{}", timeline.tenant_shard_id.shard_slug()));
+    let shard_status: Option<importbucket_format::ShardStatus> =
+        storage.get_json(&shard_status_key).await?;
+    info!(?shard_status, "peeking shard status");
+    if shard_status.map(|st| st.done).unwrap_or(false) {
+        info!("shard status indicates that the shard is done, skipping import");
+    } else {
+        // TODO: checkpoint the progress into the IndexPart instead of restarting
+        // from the beginning.
+
+        //
+        // Wipe the slate clean - the flow does not allow resuming.
+        // We can implement resuming in the future by checkpointing the progress into the IndexPart.
+        //
+        info!("wipe the slate clean");
+        {
+            // TODO: do we need to hold GC lock for this?
+            let mut guard = timeline.layers.write().await;
+            assert!(
+                guard.layer_map()?.open_layer.is_none(),
+                "while importing, there should be no in-memory layer" // this just seems like a good place to assert it
+            );
+            let all_layers_keys = guard.all_persistent_layers();
+            let all_layers: Vec<_> = all_layers_keys
+                .iter()
+                .map(|key| guard.get_from_key(key))
+                .collect();
+            let open = guard.open_mut().context("open_mut")?;
+
+            timeline.remote_client.schedule_gc_update(&all_layers)?;
+            open.finish_gc_timeline(&all_layers);
         }
-        .await;
-        match res {
-            Ok(_) => break,
-            Err(err) => {
-                info!(?err, "indefinitely waiting for pgdata to finish");
-                if tokio::time::timeout(std::time::Duration::from_secs(10), cancel.cancelled())
+
+        //
+        // Wait for pgdata to finish uploading
+        //
+        info!("wait for pgdata to reach status 'done'");
+        let pgdata_status_key = status_prefix.join("pgdata");
+        loop {
+            let res = async {
+                let pgdata_status: Option<importbucket_format::PgdataStatus> = storage
+                    .get_json(&pgdata_status_key)
                     .await
-                    .is_ok()
-                {
-                    bail!("cancelled while waiting for pgdata");
+                    .context("get pgdata status")?;
+                info!(?pgdata_status, "peeking pgdata status");
+                if pgdata_status.map(|st| st.done).unwrap_or(false) {
+                    Ok(())
+                } else {
+                    Err(anyhow::anyhow!("pgdata not done yet"))
+                }
+            }
+            .await;
+            match res {
+                Ok(_) => break,
+                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()
+                    {
+                        bail!("cancelled while waiting for pgdata");
+                    }
                 }
             }
         }
-    }
 
-    let control_file = storage.get_control_file().await?;
-    let base_lsn = control_file.base_lsn();
+        //
+        // Do the import
+        //
+        info!("do the import");
+        let control_file = storage.get_control_file().await?;
+        let base_lsn = control_file.base_lsn();
 
-    info!("update TimelineMetadata based on LSNs from control file");
-    {
-        let pg_version = control_file.pg_version();
-        async move {
-            // FIXME: The 'disk_consistent_lsn' should be the LSN at the *end* of the
-            // checkpoint record, and prev_record_lsn should point to its beginning.
-            // We should read the real end of the record from the WAL, but here we
-            // just fake it.
-            let disk_consistent_lsn = Lsn(base_lsn.0 + 8);
-            let prev_record_lsn = base_lsn;
-            let metadata = TimelineMetadata::new(
-                disk_consistent_lsn,
-                Some(prev_record_lsn),
-                None,     // no ancestor
-                Lsn(0),   // no ancestor lsn
-                base_lsn, // latest_gc_cutoff_lsn
-                base_lsn, // initdb_lsn
-                pg_version,
-            );
+        info!("update TimelineMetadata based on LSNs from control file");
+        {
+            let pg_version = control_file.pg_version();
+            let _ctx: &RequestContext = ctx;
+            async move {
+                // FIXME: The 'disk_consistent_lsn' should be the LSN at the *end* of the
+                // checkpoint record, and prev_record_lsn should point to its beginning.
+                // We should read the real end of the record from the WAL, but here we
+                // just fake it.
+                let disk_consistent_lsn = Lsn(base_lsn.0 + 8);
+                let prev_record_lsn = base_lsn;
+                let metadata = TimelineMetadata::new(
+                    disk_consistent_lsn,
+                    Some(prev_record_lsn),
+                    None,     // no ancestor
+                    Lsn(0),   // no ancestor lsn
+                    base_lsn, // latest_gc_cutoff_lsn
+                    base_lsn, // initdb_lsn
+                    pg_version,
+                );
 
-            let _start_lsn = disk_consistent_lsn + 1;
+                let _start_lsn = disk_consistent_lsn + 1;
 
-            timeline
-                .remote_client
-                .schedule_index_upload_for_full_metadata_update(&metadata)?;
+                timeline
+                    .remote_client
+                    .schedule_index_upload_for_full_metadata_update(&metadata)?;
 
-            timeline.remote_client.wait_completion().await?;
+                timeline.remote_client.wait_completion().await?;
 
-            anyhow::Ok(())
+                anyhow::Ok(())
+            }
         }
-    }
-    .await?;
+        .await?;
 
-    Ok(control_file)
-}
+        flow::run(timeline.clone(), control_file, storage.clone(), ctx).await?;
 
-async fn terminate_flow_with_error(
-    timeline: &Arc<Timeline>,
-    error: anyhow::Error,
-    storcon_client: &StorageControllerUpcallClient,
-    cancel: &CancellationToken,
-) -> anyhow::Error {
-    // The import task is a aborted on tenant shutdown, so in principle, it should
-    // never be cancelled. To be on the safe side, check the cancellation tokens
-    // before marking the import as failed.
-    if !(cancel.is_cancelled() || timeline.cancel.is_cancelled()) {
-        let notify_res = storcon_client
+        //
+        // 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.
+        //
+        let storcon_client = StorageControllerUpcallClient::new(timeline.conf, &cancel);
+        storcon_client
             .put_timeline_import_status(
                 timeline.tenant_shard_id,
                 timeline.timeline_id,
-                timeline.generation,
-                ShardImportStatus::Error(format!("{error:#}")),
+                // TODO(vlad): What about import errors?
+                ShardImportStatus::Done,
             )
-            .await;
+            .await
+            .map_err(|_err| anyhow::anyhow!("Shut down while putting timeline import status"))?;
 
-        if let Err(_notify_error) = notify_res {
-            // The [`StorageControllerUpcallClient::put_timeline_import_status`] retries
-            // forever internally, so errors returned by it can only be due to cancellation.
-            info!("failed to notify storcon about permanent import error");
-        }
-
-        // Will be logged by [`Tenant::create_timeline_import_pgdata_task`]
-        error
-    } else {
-        anyhow::anyhow!("Import task cancelled")
+        storage
+            .put_json(
+                &shard_status_key,
+                &importbucket_format::ShardStatus { done: true },
+            )
+            .await
+            .context("put shard status")?;
     }
+
+    //
+    // Mark as done in index_part.
+    // This makes subsequent timeline loads enter the normal load code path
+    // instead of spawning the import task and calling this here function.
+    //
+    info!("mark import as complete in index part");
+    timeline
+        .remote_client
+        .schedule_index_upload_for_import_pgdata_state_update(Some(index_part_format::Root::V1(
+            index_part_format::V1::Done(index_part_format::Done {
+                idempotency_key,
+                started_at,
+                finished_at: chrono::Utc::now().naive_utc(),
+            }),
+        )))?;
+
+    timeline.remote_client.wait_completion().await?;
+
+    Ok(())
 }

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

@@ -29,11 +29,10 @@
 //! - version-specific CheckPointData (=> pgv abstraction, already exists for regular walingest)
 
 use std::collections::HashSet;
-use std::hash::{Hash, Hasher};
 use std::ops::Range;
 use std::sync::Arc;
 
-use anyhow::ensure;
+use anyhow::{bail, ensure};
 use bytes::Bytes;
 use futures::stream::FuturesOrdered;
 use itertools::Itertools;
@@ -44,7 +43,6 @@ use pageserver_api::key::{
     slru_segment_size_to_key,
 };
 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;
 use postgres_ffi::relfile_utils::parse_relfilename;
@@ -55,42 +53,21 @@ use tokio_stream::StreamExt;
 use tracing::{debug, instrument};
 use utils::bin_ser::BeSer;
 use utils::lsn::Lsn;
-use utils::pausable_failpoint;
 
 use super::Timeline;
 use super::importbucket_client::{ControlFile, RemoteStorageWrapper};
 use crate::assert_u64_eq_usize::UsizeIsU64;
 use crate::context::{DownloadBehavior, RequestContext};
-use crate::controller_upcall_client::{StorageControllerUpcallApi, StorageControllerUpcallClient};
 use crate::pgdatadir_mapping::{
     DbDirectory, RelDirectory, SlruSegmentDirectory, TwoPhaseDirectory,
 };
 use crate::task_mgr::TaskKind;
-use crate::tenant::storage_layer::{AsLayerDesc, ImageLayerWriter, Layer};
+use crate::tenant::storage_layer::{ImageLayerWriter, Layer};
 
 pub async fn run(
     timeline: Arc<Timeline>,
     control_file: ControlFile,
     storage: RemoteStorageWrapper,
-    import_progress: Option<ShardImportProgress>,
-    ctx: &RequestContext,
-) -> anyhow::Result<()> {
-    // Match how we run the import based on the progress version.
-    // If there's no import progress, it means that this is a new import
-    // and we can use whichever version we want.
-    match import_progress {
-        Some(ShardImportProgress::V1(progress)) => {
-            run_v1(timeline, control_file, storage, Some(progress), ctx).await
-        }
-        None => run_v1(timeline, control_file, storage, None, ctx).await,
-    }
-}
-
-async fn run_v1(
-    timeline: Arc<Timeline>,
-    control_file: ControlFile,
-    storage: RemoteStorageWrapper,
-    import_progress: Option<ShardImportProgressV1>,
     ctx: &RequestContext,
 ) -> anyhow::Result<()> {
     let planner = Planner {
@@ -102,32 +79,7 @@ async fn run_v1(
 
     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.
-    //
-    // This is not intended to be a cryptographically secure hash.
-    const SEED: u64 = 42;
-    let mut hasher = twox_hash::XxHash64::with_seed(SEED);
-    plan.hash(&mut hasher);
-    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")
-        }
-    }
-
-    pausable_failpoint!("import-timeline-pre-execute-pausable");
-
-    let start_from_job_idx = import_progress.map(|progress| progress.completed);
-    plan.execute(timeline, start_from_job_idx, plan_hash, import_config, ctx)
-        .await
+    plan.execute(timeline, import_config, ctx).await
 }
 
 struct Planner {
@@ -137,11 +89,8 @@ struct Planner {
     tasks: Vec<AnyImportTask>,
 }
 
-#[derive(Hash)]
 struct Plan {
     jobs: Vec<ChunkProcessingJob>,
-    // Included here such that it ends up in the hash for the plan
-    shard: ShardIdentity,
 }
 
 impl Planner {
@@ -245,10 +194,7 @@ impl Planner {
             pgdata_lsn,
         ));
 
-        Ok(Plan {
-            jobs,
-            shard: self.shard,
-        })
+        Ok(Plan { jobs })
     }
 
     #[instrument(level = tracing::Level::DEBUG, skip_all, fields(dboid=%db.dboid, tablespace=%db.spcnode, path=%db.path))]
@@ -377,45 +323,25 @@ impl Plan {
     async fn execute(
         self,
         timeline: Arc<Timeline>,
-        start_after_job_idx: Option<usize>,
-        import_plan_hash: u64,
         import_config: &TimelineImportConfig,
         ctx: &RequestContext,
     ) -> anyhow::Result<()> {
-        let storcon_client = StorageControllerUpcallClient::new(timeline.conf, &timeline.cancel);
-
         let mut work = FuturesOrdered::new();
         let semaphore = Arc::new(Semaphore::new(import_config.import_job_concurrency.into()));
 
         let jobs_in_plan = self.jobs.len();
 
-        let mut jobs = self
-            .jobs
-            .into_iter()
-            .enumerate()
-            .map(|(idx, job)| (idx + 1, job))
-            .filter(|(idx, _job)| {
-                // Filter out any jobs that have been done already
-                if let Some(start_after) = start_after_job_idx {
-                    *idx > start_after
-                } else {
-                    true
-                }
-            })
-            .peekable();
-
-        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 mut jobs = self.jobs.into_iter().enumerate().peekable();
+        let mut results = Vec::new();
 
         // 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
         // building block for resuming imports across pageserver restarts or tenant migrations.
-        while last_completed_job_idx < jobs_in_plan {
+        while results.len() < jobs_in_plan {
             tokio::select! {
                 permit = semaphore.clone().acquire_owned(), if jobs.peek().is_some() => {
                     let permit = permit.expect("never closed");
                     let (job_idx, job) = jobs.next().expect("we peeked");
-
                     let job_timeline = timeline.clone();
                     let ctx = ctx.detached_child(TaskKind::ImportPgdata, DownloadBehavior::Error);
 
@@ -427,35 +353,13 @@ impl Plan {
                 },
                 maybe_complete_job_idx = work.next() => {
                     match maybe_complete_job_idx {
-                        Some(Ok((job_idx, res))) => {
-                            assert!(last_completed_job_idx.checked_add(1).unwrap() == job_idx);
-
-                            res?;
-                            last_completed_job_idx = job_idx;
-
-                            if last_completed_job_idx % checkpoint_every == 0 {
-                                let progress = ShardImportProgressV1 {
-                                    jobs: jobs_in_plan,
-                                    completed: last_completed_job_idx,
-                                    import_plan_hash,
-                                };
-
-                                storcon_client.put_timeline_import_status(
-                                    timeline.tenant_shard_id,
-                                    timeline.timeline_id,
-                                    timeline.generation,
-                                    ShardImportStatus::InProgress(Some(ShardImportProgress::V1(progress)))
-                                )
-                                .await
-                                .map_err(|_err| {
-                                    anyhow::anyhow!("Shut down while putting timeline import status")
-                                })?;
-                            }
+                        Some(Ok((_job_idx, res))) => {
+                            results.push(res);
                         },
                         Some(Err(_)) => {
-                            anyhow::bail!(
-                                "import job panicked or cancelled"
-                            );
+                            results.push(Err(anyhow::anyhow!(
+                                "parallel job panicked or cancelled, check pageserver logs"
+                            )));
                         }
                         None => {}
                     }
@@ -463,7 +367,17 @@ impl Plan {
             }
         }
 
-        Ok(())
+        if results.iter().all(|r| r.is_ok()) {
+            Ok(())
+        } else {
+            let mut msg = String::new();
+            for result in results {
+                if let Err(err) = result {
+                    msg.push_str(&format!("{err:?}\n\n"));
+                }
+            }
+            bail!("Some parallel jobs failed:\n\n{msg}");
+        }
     }
 }
 
@@ -635,15 +549,6 @@ struct ImportSingleKeyTask {
     buf: Bytes,
 }
 
-impl Hash for ImportSingleKeyTask {
-    fn hash<H: Hasher>(&self, state: &mut H) {
-        let ImportSingleKeyTask { key, buf } = self;
-
-        key.hash(state);
-        buf.hash(state);
-    }
-}
-
 impl ImportSingleKeyTask {
     fn new(key: Key, buf: Bytes) -> Self {
         ImportSingleKeyTask { key, buf }
@@ -672,20 +577,6 @@ struct ImportRelBlocksTask {
     storage: RemoteStorageWrapper,
 }
 
-impl Hash for ImportRelBlocksTask {
-    fn hash<H: Hasher>(&self, state: &mut H) {
-        let ImportRelBlocksTask {
-            shard_identity: _,
-            key_range,
-            path,
-            storage: _,
-        } = self;
-
-        key_range.hash(state);
-        path.hash(state);
-    }
-}
-
 impl ImportRelBlocksTask {
     fn new(
         shard_identity: ShardIdentity,
@@ -770,19 +661,6 @@ struct ImportSlruBlocksTask {
     storage: RemoteStorageWrapper,
 }
 
-impl Hash for ImportSlruBlocksTask {
-    fn hash<H: Hasher>(&self, state: &mut H) {
-        let ImportSlruBlocksTask {
-            key_range,
-            path,
-            storage: _,
-        } = self;
-
-        key_range.hash(state);
-        path.hash(state);
-    }
-}
-
 impl ImportSlruBlocksTask {
     fn new(key_range: Range<Key>, path: &RemotePath, storage: RemoteStorageWrapper) -> Self {
         ImportSlruBlocksTask {
@@ -825,7 +703,6 @@ impl ImportTask for ImportSlruBlocksTask {
     }
 }
 
-#[derive(Hash)]
 enum AnyImportTask {
     SingleKey(ImportSingleKeyTask),
     RelBlocks(ImportRelBlocksTask),
@@ -872,7 +749,6 @@ impl From<ImportSlruBlocksTask> for AnyImportTask {
     }
 }
 
-#[derive(Hash)]
 struct ChunkProcessingJob {
     range: Range<Key>,
     tasks: Vec<AnyImportTask>,
@@ -910,51 +786,17 @@ impl ChunkProcessingJob {
 
         let resident_layer = if nimages > 0 {
             let (desc, path) = writer.finish(ctx).await?;
-
-            {
-                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 {
-                        return Err(anyhow::anyhow!(
-                            "Import attempted to rewrite layer file in the same generation: {}",
-                            layer.local_path()
-                        ));
-                    }
-                }
-            }
-
             Layer::finish_creating(timeline.conf, &timeline, desc, &path)?
         } else {
             // dropping the writer cleans up
             return Ok(());
         };
 
-        // The same import job might run multiple times since not each job is checkpointed.
-        // Hence, we must support the cases where the layer already exists. We cannot be
-        // certain that the existing layer is identical to the new one, so in that case
-        // we replace the old layer with the one we just generated.
-
+        // this is sharing the same code as create_image_layers
         let mut guard = timeline.layers.write().await;
-
-        let existing_layer = guard
-            .try_get_from_key(&resident_layer.layer_desc().key())
-            .cloned();
-        match existing_layer {
-            Some(existing) => {
-                guard.open_mut()?.rewrite_layers(
-                    &[(existing.clone(), resident_layer.clone())],
-                    &[],
-                    &timeline.metrics,
-                );
-            }
-            None => {
-                guard
-                    .open_mut()?
-                    .track_new_image_layers(&[resident_layer.clone()], &timeline.metrics);
-            }
-        }
-
+        guard
+            .open_mut()?
+            .track_new_image_layers(&[resident_layer.clone()], &timeline.metrics);
         crate::tenant::timeline::drop_wlock(guard);
 
         timeline

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

@@ -190,6 +190,31 @@ impl RemoteStorageWrapper {
         Ok(Some(res))
     }
 
+    #[instrument(level = tracing::Level::DEBUG, skip_all, fields(%path))]
+    pub async fn put_json<T>(&self, path: &RemotePath, value: &T) -> anyhow::Result<()>
+    where
+        T: serde::Serialize,
+    {
+        let buf = serde_json::to_vec(value)?;
+        let bytes = Bytes::from(buf);
+        utils::backoff::retry(
+            || async {
+                let size = bytes.len();
+                let bytes = futures::stream::once(futures::future::ready(Ok(bytes.clone())));
+                self.storage
+                    .upload_storage_object(bytes, size, path, &self.cancel)
+                    .await
+            },
+            remote_storage::TimeoutOrCancel::caused_by_cancel,
+            1,
+            u32::MAX,
+            &format!("put json {path}"),
+            &self.cancel,
+        )
+        .await
+        .expect("practically infinite retries")
+    }
+
     #[instrument(level = tracing::Level::DEBUG, skip_all, fields(%path))]
     pub async fn get_range(
         &self,

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

@@ -5,3 +5,9 @@ pub struct PgdataStatus {
     pub done: bool,
     // TODO: remaining fields
 }
+
+#[derive(Deserialize, Serialize, Debug, Clone, PartialEq, Eq)]
+pub struct ShardStatus {
+    pub done: bool,
+    // TODO: remaining fields
+}

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

@@ -64,12 +64,4 @@ impl Root {
             },
         }
     }
-    pub fn started_at(&self) -> &chrono::NaiveDateTime {
-        match self {
-            Root::V1(v1) => match v1 {
-                V1::InProgress(in_progress) => &in_progress.started_at,
-                V1::Done(done) => &done.started_at,
-            },
-        }
-    }
 }

pageserver/src/virtual_file.rs

@@ -74,8 +74,6 @@ pub struct VirtualFile {
 
 impl VirtualFile {
     /// Open a file in read-only mode. Like File::open.
-    ///
-    /// Insensitive to `virtual_file_io_mode` setting.
     pub async fn open<P: AsRef<Utf8Path>>(
         path: P,
         ctx: &RequestContext,
@@ -97,20 +95,31 @@ impl VirtualFile {
         Self::open_with_options_v2(path.as_ref(), OpenOptions::new().read(true), ctx).await
     }
 
-    /// `O_DIRECT` will be enabled base on `virtual_file_io_mode`.
     pub async fn open_with_options_v2<P: AsRef<Utf8Path>>(
         path: P,
-        mut open_options: OpenOptions,
+        #[cfg_attr(not(target_os = "linux"), allow(unused_mut))] mut open_options: OpenOptions,
         ctx: &RequestContext,
     ) -> Result<Self, std::io::Error> {
         let mode = get_io_mode();
-        let direct = match (mode, open_options.is_write()) {
+        let set_o_direct = match (mode, open_options.is_write()) {
             (IoMode::Buffered, _) => false,
+            #[cfg(target_os = "linux")]
             (IoMode::Direct, false) => true,
+            #[cfg(target_os = "linux")]
             (IoMode::Direct, true) => false,
+            #[cfg(target_os = "linux")]
             (IoMode::DirectRw, _) => true,
         };
-        open_options = open_options.direct(direct);
+        if set_o_direct {
+            #[cfg(target_os = "linux")]
+            {
+                open_options = open_options.custom_flags(nix::libc::O_DIRECT);
+            }
+            #[cfg(not(target_os = "linux"))]
+            unreachable!(
+                "O_DIRECT is not supported on this platform, IoMode's that result in set_o_direct=true shouldn't even be defined"
+            );
+        }
         let inner = VirtualFileInner::open_with_options(path, open_options, ctx).await?;
         Ok(VirtualFile { inner, _mode: mode })
     }
@@ -408,7 +417,7 @@ impl OpenFiles {
 /// error types may be elegible for retry.
 pub(crate) fn is_fatal_io_error(e: &std::io::Error) -> bool {
     use nix::errno::Errno::*;
-    match e.raw_os_error().map(nix::errno::Errno::from_raw) {
+    match e.raw_os_error().map(nix::errno::from_i32) {
         Some(EIO) => {
             // Terminate on EIO because we no longer trust the device to store
             // data safely, or to uphold persistence guarantees on fsync.
@@ -782,12 +791,6 @@ impl VirtualFileInner {
     where
         Buf: tokio_epoll_uring::IoBufMut + Send,
     {
-        self.validate_direct_io(
-            Slice::stable_ptr(&buf).addr(),
-            Slice::bytes_total(&buf),
-            offset,
-        );
-
         let file_guard = match self
             .lock_file()
             .await
@@ -813,8 +816,6 @@ impl VirtualFileInner {
         offset: u64,
         ctx: &RequestContext,
     ) -> (FullSlice<B>, Result<usize, Error>) {
-        self.validate_direct_io(buf.as_ptr().addr(), buf.len(), offset);
-
         let file_guard = match self.lock_file().await {
             Ok(file_guard) => file_guard,
             Err(e) => return (buf, Err(e)),
@@ -829,64 +830,6 @@ impl VirtualFileInner {
             (buf, result)
         })
     }
-
-    /// Validate all reads and writes to adhere to the O_DIRECT requirements of our production systems.
-    ///
-    /// Validating it iin userspace sets a consistent bar, independent of what actual OS/filesystem/block device is in use.
-    fn validate_direct_io(&self, addr: usize, size: usize, offset: u64) {
-        // TODO: eventually enable validation in the builds we use in real environments like staging, preprod, and prod.
-        if !(cfg!(feature = "testing") || cfg!(test)) {
-            return;
-        }
-        if !self.open_options.is_direct() {
-            return;
-        }
-
-        // Validate buffer memory alignment.
-        //
-        // What practically matters as of Linux 6.1 is bdev_dma_alignment()
-        // which is practically between 512 and 4096.
-        // On our production systems, the value is 512.
-        // The IoBuffer/IoBufferMut hard-code that value.
-        //
-        // Because the alloctor might return _more_ aligned addresses than requested,
-        // there is a chance that testing would not catch violations of a runtime requirement stricter than 512.
-        {
-            let requirement = 512;
-            let remainder = addr % requirement;
-            assert!(
-                remainder == 0,
-                "Direct I/O buffer must be aligned: buffer_addr=0x{addr:x} % 0x{requirement:x} = 0x{remainder:x}"
-            );
-        }
-
-        // Validate offset alignment.
-        //
-        // We hard-code 512 throughout the code base.
-        // So enforce just that and not anything more restrictive.
-        // Even the shallowest testing will expose more restrictive requirements if those ever arise.
-        {
-            let requirement = 512;
-            let remainder = offset % requirement;
-            assert!(
-                remainder == 0,
-                "Direct I/O offset must be aligned: offset=0x{offset:x} % 0x{requirement:x} = 0x{remainder:x}"
-            );
-        }
-
-        // Validate buffer size multiple requirement.
-        //
-        // The requirement in Linux 6.1 is bdev_logical_block_size().
-        // On our production systems, that is 512.
-        {
-            let requirement = 512;
-            let remainder = size % requirement;
-            assert!(
-                remainder == 0,
-                "Direct I/O buffer size must be a multiple of {requirement}: size=0x{size:x} % 0x{requirement:x} = 0x{remainder:x}"
-            );
-        }
-    }
 }
 
 // Adapted from https://doc.rust-lang.org/1.72.0/src/std/os/unix/fs.rs.html#117-135
@@ -1275,6 +1218,7 @@ mod tests {
     use std::sync::Arc;
 
     use owned_buffers_io::io_buf_ext::IoBufExt;
+    use owned_buffers_io::slice::SliceMutExt;
     use rand::seq::SliceRandom;
     use rand::{Rng, thread_rng};
 
@@ -1282,38 +1226,162 @@ mod tests {
     use crate::context::DownloadBehavior;
     use crate::task_mgr::TaskKind;
 
+    enum MaybeVirtualFile {
+        VirtualFile(VirtualFile),
+        File(File),
+    }
+
+    impl From<VirtualFile> for MaybeVirtualFile {
+        fn from(vf: VirtualFile) -> Self {
+            MaybeVirtualFile::VirtualFile(vf)
+        }
+    }
+
+    impl MaybeVirtualFile {
+        async fn read_exact_at(
+            &self,
+            mut slice: tokio_epoll_uring::Slice<IoBufferMut>,
+            offset: u64,
+            ctx: &RequestContext,
+        ) -> Result<tokio_epoll_uring::Slice<IoBufferMut>, Error> {
+            match self {
+                MaybeVirtualFile::VirtualFile(file) => file.read_exact_at(slice, offset, ctx).await,
+                MaybeVirtualFile::File(file) => {
+                    let rust_slice: &mut [u8] = slice.as_mut_rust_slice_full_zeroed();
+                    file.read_exact_at(rust_slice, offset).map(|()| slice)
+                }
+            }
+        }
+        async fn write_all_at<Buf: IoBufAligned + Send>(
+            &self,
+            buf: FullSlice<Buf>,
+            offset: u64,
+            ctx: &RequestContext,
+        ) -> Result<(), Error> {
+            match self {
+                MaybeVirtualFile::VirtualFile(file) => {
+                    let (_buf, res) = file.write_all_at(buf, offset, ctx).await;
+                    res
+                }
+                MaybeVirtualFile::File(file) => file.write_all_at(&buf[..], offset),
+            }
+        }
+
+        // Helper function to slurp a portion of a file into a string
+        async fn read_string_at(
+            &mut self,
+            pos: u64,
+            len: usize,
+            ctx: &RequestContext,
+        ) -> Result<String, Error> {
+            let slice = IoBufferMut::with_capacity(len).slice_full();
+            assert_eq!(slice.bytes_total(), len);
+            let slice = self.read_exact_at(slice, pos, ctx).await?;
+            let buf = slice.into_inner();
+            assert_eq!(buf.len(), len);
+
+            Ok(String::from_utf8(buf.to_vec()).unwrap())
+        }
+    }
+
     #[tokio::test]
     async fn test_virtual_files() -> anyhow::Result<()> {
+        // The real work is done in the test_files() helper function. This
+        // allows us to run the same set of tests against a native File, and
+        // VirtualFile. We trust the native Files and wouldn't need to test them,
+        // but this allows us to verify that the operations return the same
+        // results with VirtualFiles as with native Files. (Except that with
+        // native files, you will run out of file descriptors if the ulimit
+        // is low enough.)
+        struct A;
+
+        impl Adapter for A {
+            async fn open(
+                path: Utf8PathBuf,
+                opts: OpenOptions,
+                ctx: &RequestContext,
+            ) -> Result<MaybeVirtualFile, anyhow::Error> {
+                let vf = VirtualFile::open_with_options_v2(&path, opts, ctx).await?;
+                Ok(MaybeVirtualFile::VirtualFile(vf))
+            }
+        }
+        test_files::<A>("virtual_files").await
+    }
+
+    #[tokio::test]
+    async fn test_physical_files() -> anyhow::Result<()> {
+        struct B;
+
+        impl Adapter for B {
+            async fn open(
+                path: Utf8PathBuf,
+                opts: OpenOptions,
+                _ctx: &RequestContext,
+            ) -> Result<MaybeVirtualFile, anyhow::Error> {
+                Ok(MaybeVirtualFile::File({
+                    let owned_fd = opts.open(path.as_std_path()).await?;
+                    File::from(owned_fd)
+                }))
+            }
+        }
+
+        test_files::<B>("physical_files").await
+    }
+
+    /// This is essentially a closure which returns a MaybeVirtualFile, but because rust edition
+    /// 2024 is not yet out with new lifetime capture or outlives rules, this is a async function
+    /// in trait which benefits from the new lifetime capture rules already.
+    trait Adapter {
+        async fn open(
+            path: Utf8PathBuf,
+            opts: OpenOptions,
+            ctx: &RequestContext,
+        ) -> Result<MaybeVirtualFile, anyhow::Error>;
+    }
+
+    async fn test_files<A>(testname: &str) -> anyhow::Result<()>
+    where
+        A: Adapter,
+    {
         let ctx =
             RequestContext::new(TaskKind::UnitTest, DownloadBehavior::Error).with_scope_unit_test();
-        let testdir = crate::config::PageServerConf::test_repo_dir("test_virtual_files");
+        let testdir = crate::config::PageServerConf::test_repo_dir(testname);
         std::fs::create_dir_all(&testdir)?;
 
-        let zeropad512 = |content: &[u8]| {
-            let mut buf = IoBufferMut::with_capacity_zeroed(512);
-            buf[..content.len()].copy_from_slice(content);
-            buf.freeze().slice_len()
-        };
-
         let path_a = testdir.join("file_a");
-        let file_a = VirtualFile::open_with_options_v2(
+        let mut file_a = A::open(
             path_a.clone(),
             OpenOptions::new()
-                .read(true)
                 .write(true)
-                // set create & truncate flags to ensure when we trigger a reopen later in this test,
-                // the reopen_options must have masked out those flags; if they don't, then
-                // the after reopen we will fail to read the `content_a` that we write here.
                 .create(true)
-                .truncate(true),
+                .truncate(true)
+                .to_owned(),
             &ctx,
         )
         .await?;
-        let (_, res) = file_a.write_all_at(zeropad512(b"content_a"), 0, &ctx).await;
-        res?;
 
+        file_a
+            .write_all_at(IoBuffer::from(b"foobar").slice_len(), 0, &ctx)
+            .await?;
+
+        // cannot read from a file opened in write-only mode
+        let _ = file_a.read_string_at(0, 1, &ctx).await.unwrap_err();
+
+        // Close the file and re-open for reading
+        let mut file_a = A::open(path_a, OpenOptions::new().read(true), &ctx).await?;
+
+        // cannot write to a file opened in read-only mode
+        let _ = file_a
+            .write_all_at(IoBuffer::from(b"bar").slice_len(), 0, &ctx)
+            .await
+            .unwrap_err();
+
+        // Try simple read
+        assert_eq!("foobar", file_a.read_string_at(0, 6, &ctx).await?);
+
+        // Create another test file, and try FileExt functions on it.
         let path_b = testdir.join("file_b");
-        let file_b = VirtualFile::open_with_options_v2(
+        let mut file_b = A::open(
             path_b.clone(),
             OpenOptions::new()
                 .read(true)
@@ -1323,44 +1391,37 @@ mod tests {
             &ctx,
         )
         .await?;
-        let (_, res) = file_b.write_all_at(zeropad512(b"content_b"), 0, &ctx).await;
-        res?;
-
-        let assert_first_512_eq = async |vfile: &VirtualFile, expect: &[u8]| {
-            let buf = vfile
-                .read_exact_at(IoBufferMut::with_capacity_zeroed(512).slice_full(), 0, &ctx)
-                .await
-                .unwrap();
-            assert_eq!(&buf[..], &zeropad512(expect)[..]);
-        };
-
-        // Open a lot of file descriptors / VirtualFile instances.
-        // Enough to cause some evictions in the fd cache.
-
-        let mut file_b_dupes = Vec::new();
-        for _ in 0..100 {
-            let vfile = VirtualFile::open_with_options_v2(
-                path_b.clone(),
-                OpenOptions::new().read(true),
-                &ctx,
-            )
+        file_b
+            .write_all_at(IoBuffer::from(b"BAR").slice_len(), 3, &ctx)
             .await?;
-            assert_first_512_eq(&vfile, b"content_b").await;
-            file_b_dupes.push(vfile);
+        file_b
+            .write_all_at(IoBuffer::from(b"FOO").slice_len(), 0, &ctx)
+            .await?;
+
+        assert_eq!(file_b.read_string_at(2, 3, &ctx).await?, "OBA");
+
+        // Open a lot of files, enough to cause some evictions. (Or to be precise,
+        // open the same file many times. The effect is the same.)
+
+        let mut vfiles = Vec::new();
+        for _ in 0..100 {
+            let mut vfile = A::open(path_b.clone(), OpenOptions::new().read(true), &ctx).await?;
+            assert_eq!("FOOBAR", vfile.read_string_at(0, 6, &ctx).await?);
+            vfiles.push(vfile);
         }
 
         // make sure we opened enough files to definitely cause evictions.
-        assert!(file_b_dupes.len() > TEST_MAX_FILE_DESCRIPTORS * 2);
+        assert!(vfiles.len() > TEST_MAX_FILE_DESCRIPTORS * 2);
 
         // The underlying file descriptor for 'file_a' should be closed now. Try to read
-        // from it again. The VirtualFile reopens the file internally.
-        assert_first_512_eq(&file_a, b"content_a").await;
+        // from it again.
+        assert_eq!("foobar", file_a.read_string_at(0, 6, &ctx).await?);
 
         // Check that all the other FDs still work too. Use them in random order for
         // good measure.
-        file_b_dupes.as_mut_slice().shuffle(&mut thread_rng());
-        for vfile in file_b_dupes.iter_mut() {
-            assert_first_512_eq(vfile, b"content_b").await;
+        vfiles.as_mut_slice().shuffle(&mut thread_rng());
+        for vfile in vfiles.iter_mut() {
+            assert_eq!("OOBAR", vfile.read_string_at(1, 5, &ctx).await?);
         }
 
         Ok(())
@@ -1391,7 +1452,7 @@ mod tests {
         // Open the file many times.
         let mut files = Vec::new();
         for _ in 0..VIRTUAL_FILES {
-            let f = VirtualFile::open_with_options_v2(
+            let f = VirtualFileInner::open_with_options(
                 &test_file_path,
                 OpenOptions::new().read(true),
                 &ctx,
@@ -1436,6 +1497,8 @@ mod tests {
 
     #[tokio::test]
     async fn test_atomic_overwrite_basic() {
+        let ctx =
+            RequestContext::new(TaskKind::UnitTest, DownloadBehavior::Error).with_scope_unit_test();
         let testdir = crate::config::PageServerConf::test_repo_dir("test_atomic_overwrite_basic");
         std::fs::create_dir_all(&testdir).unwrap();
 
@@ -1445,22 +1508,26 @@ mod tests {
         VirtualFileInner::crashsafe_overwrite(path.clone(), tmp_path.clone(), b"foo".to_vec())
             .await
             .unwrap();
-
-        let post = std::fs::read_to_string(&path).unwrap();
+        let mut file = MaybeVirtualFile::from(VirtualFile::open(&path, &ctx).await.unwrap());
+        let post = file.read_string_at(0, 3, &ctx).await.unwrap();
         assert_eq!(post, "foo");
         assert!(!tmp_path.exists());
+        drop(file);
 
         VirtualFileInner::crashsafe_overwrite(path.clone(), tmp_path.clone(), b"bar".to_vec())
             .await
             .unwrap();
-
-        let post = std::fs::read_to_string(&path).unwrap();
+        let mut file = MaybeVirtualFile::from(VirtualFile::open(&path, &ctx).await.unwrap());
+        let post = file.read_string_at(0, 3, &ctx).await.unwrap();
         assert_eq!(post, "bar");
         assert!(!tmp_path.exists());
+        drop(file);
     }
 
     #[tokio::test]
     async fn test_atomic_overwrite_preexisting_tmp() {
+        let ctx =
+            RequestContext::new(TaskKind::UnitTest, DownloadBehavior::Error).with_scope_unit_test();
         let testdir =
             crate::config::PageServerConf::test_repo_dir("test_atomic_overwrite_preexisting_tmp");
         std::fs::create_dir_all(&testdir).unwrap();
@@ -1475,8 +1542,10 @@ mod tests {
             .await
             .unwrap();
 
-        let post = std::fs::read_to_string(&path).unwrap();
+        let mut file = MaybeVirtualFile::from(VirtualFile::open(&path, &ctx).await.unwrap());
+        let post = file.read_string_at(0, 3, &ctx).await.unwrap();
         assert_eq!(post, "foo");
         assert!(!tmp_path.exists());
+        drop(file);
     }
 }

pageserver/src/virtual_file/io_engine.rs

@@ -124,7 +124,9 @@ pub(super) fn epoll_uring_error_to_std(
 ) -> std::io::Error {
     match e {
         tokio_epoll_uring::Error::Op(e) => e,
-        tokio_epoll_uring::Error::System(system) => std::io::Error::other(system),
+        tokio_epoll_uring::Error::System(system) => {
+            std::io::Error::new(std::io::ErrorKind::Other, system)
+        }
     }
 }
 

pageserver/src/virtual_file/open_options.rs

@@ -8,13 +8,7 @@ use super::io_engine::IoEngine;
 
 #[derive(Debug, Clone)]
 pub struct OpenOptions {
-    /// We keep a copy of the write() flag we pass to the `inner`` `OptionOptions`
-    /// to support [`Self::is_write`].
     write: bool,
-    /// We don't expose + pass through a raw `custom_flags()` style API.
-    /// The only custom flag we support is `O_DIRECT`, which we track here
-    /// and map to `custom_flags()` in the [`Self::open`] method.
-    direct: bool,
     inner: Inner,
 }
 #[derive(Debug, Clone)]
@@ -36,7 +30,6 @@ impl Default for OpenOptions {
         };
         Self {
             write: false,
-            direct: false,
             inner,
         }
     }
@@ -51,10 +44,6 @@ impl OpenOptions {
         self.write
     }
 
-    pub(super) fn is_direct(&self) -> bool {
-        self.direct
-    }
-
     pub fn read(mut self, read: bool) -> Self {
         match &mut self.inner {
             Inner::StdFs(x) => {
@@ -127,38 +116,13 @@ impl OpenOptions {
     }
 
     pub(in crate::virtual_file) async fn open(&self, path: &Path) -> std::io::Result<OwnedFd> {
-        #[cfg_attr(not(target_os = "linux"), allow(unused_mut))]
-        let mut custom_flags = 0;
-        if self.direct {
+        match &self.inner {
+            Inner::StdFs(x) => x.open(path).map(|file| file.into()),
             #[cfg(target_os = "linux")]
-            {
-                custom_flags |= nix::libc::O_DIRECT;
-            }
-            #[cfg(not(target_os = "linux"))]
-            {
-                // Other platforms may be used for development but don't necessarily have a 1:1 equivalent to Linux's O_DIRECT (macOS!).
-                // Just don't set the flag; to catch alignment bugs typical for O_DIRECT,
-                // we have a runtime validation layer inside `VirtualFile::write_at` and `VirtualFile::read_at`.
-                static WARNING: std::sync::Once = std::sync::Once::new();
-                WARNING.call_once(|| {
-                    let span = tracing::info_span!(parent: None, "open_options");
-                    let _enter = span.enter();
-                    tracing::warn!("your platform is not a supported production platform, ignoing request for O_DIRECT; this could hide alignment bugs; this warning is logged once per process");
-                });
-            }
-        }
-
-        match self.inner.clone() {
-            Inner::StdFs(mut x) => x
-                .custom_flags(custom_flags)
-                .open(path)
-                .map(|file| file.into()),
-            #[cfg(target_os = "linux")]
-            Inner::TokioEpollUring(mut x) => {
-                x.custom_flags(custom_flags);
+            Inner::TokioEpollUring(x) => {
                 let system = super::io_engine::tokio_epoll_uring_ext::thread_local_system().await;
                 let (_, res) = super::io_engine::retry_ecanceled_once((), |()| async {
-                    let res = system.open(path, &x).await;
+                    let res = system.open(path, x).await;
                     ((), res)
                 })
                 .await;
@@ -180,8 +144,19 @@ impl OpenOptions {
         self
     }
 
-    pub fn direct(mut self, direct: bool) -> Self {
-        self.direct = direct;
+    pub fn custom_flags(mut self, flags: i32) -> Self {
+        if flags & nix::libc::O_APPEND != 0 {
+            super::io_engine::panic_operation_must_be_idempotent();
+        }
+        match &mut self.inner {
+            Inner::StdFs(x) => {
+                let _ = x.custom_flags(flags);
+            }
+            #[cfg(target_os = "linux")]
+            Inner::TokioEpollUring(x) => {
+                let _ = x.custom_flags(flags);
+            }
+        }
         self
     }
 }

pgxn/neon/communicator.c

@@ -425,12 +425,15 @@ compact_prefetch_buffers(void)
  * point inside and outside PostgreSQL.
  *
  * This still does throw errors when it receives malformed responses from PS.
+ *
+ * When we're not called from CHECK_FOR_INTERRUPTS (indicated by
+ * IsHandlingInterrupts) we also report we've ended prefetch receive work,
+ * just in case state tracking was lost due to an error in the sync getPage
+ * response code.
  */
 void
-communicator_prefetch_pump_state(void)
+communicator_prefetch_pump_state(bool IsHandlingInterrupts)
 {
-	START_PREFETCH_RECEIVE_WORK();
-
 	while (MyPState->ring_receive != MyPState->ring_flush)
 	{
 		NeonResponse   *response;
@@ -479,7 +482,9 @@ communicator_prefetch_pump_state(void)
 		}
 	}
 
-	END_PREFETCH_RECEIVE_WORK();
+	/* We never pump the prefetch state while handling other pages */
+	if (!IsHandlingInterrupts)
+		END_PREFETCH_RECEIVE_WORK();
 
 	communicator_reconfigure_timeout_if_needed();
 }
@@ -667,10 +672,9 @@ prefetch_wait_for(uint64 ring_index)
 
 	Assert(MyPState->ring_unused > ring_index);
 
-	START_PREFETCH_RECEIVE_WORK();
-
 	while (MyPState->ring_receive <= ring_index)
 	{
+		START_PREFETCH_RECEIVE_WORK();
 		entry = GetPrfSlot(MyPState->ring_receive);
 
 		Assert(entry->status == PRFS_REQUESTED);
@@ -679,18 +683,17 @@ prefetch_wait_for(uint64 ring_index)
 			result = false;
 			break;
 		}
+
+		END_PREFETCH_RECEIVE_WORK();
 		CHECK_FOR_INTERRUPTS();
 	}
-
 	if (result)
 	{
 		/* Check that slot is actually received (srver can be disconnected in prefetch_pump_state called from CHECK_FOR_INTERRUPTS */
 		PrefetchRequest *slot = GetPrfSlot(ring_index);
-		result = slot->status == PRFS_RECEIVED;
+		return slot->status == PRFS_RECEIVED;
 	}
-	END_PREFETCH_RECEIVE_WORK();
-
-	return result;
+	return false;
 ;
 }
 
@@ -717,7 +720,6 @@ prefetch_read(PrefetchRequest *slot)
 	Assert(slot->status == PRFS_REQUESTED);
 	Assert(slot->response == NULL);
 	Assert(slot->my_ring_index == MyPState->ring_receive);
-	Assert(readpage_reentrant_guard);
 
 	if (slot->status != PRFS_REQUESTED ||
 		slot->response != NULL ||
@@ -800,7 +802,6 @@ communicator_prefetch_receive(BufferTag tag)
 	PrfHashEntry *entry;
 	PrefetchRequest hashkey;
 
-	Assert(readpage_reentrant_guard);
 	hashkey.buftag = tag;
 	entry = prfh_lookup(MyPState->prf_hash, &hashkey);
 	if (entry != NULL && prefetch_wait_for(entry->slot->my_ring_index))
@@ -820,12 +821,8 @@ communicator_prefetch_receive(BufferTag tag)
 void
 prefetch_on_ps_disconnect(void)
 {
-	bool save_readpage_reentrant_guard = readpage_reentrant_guard;
 	MyPState->ring_flush = MyPState->ring_unused;
 
-	/* Prohibit callig of prefetch_pump_state */
-	START_PREFETCH_RECEIVE_WORK();
-
 	while (MyPState->ring_receive < MyPState->ring_unused)
 	{
 		PrefetchRequest *slot;
@@ -854,9 +851,6 @@ prefetch_on_ps_disconnect(void)
 		MyNeonCounters->getpage_prefetch_discards_total += 1;
 	}
 
-	/* Restore guard */
-	readpage_reentrant_guard = save_readpage_reentrant_guard;
-
 	/*
 	 * We can have gone into retry due to network error, so update stats with
 	 * the latest available
@@ -2515,7 +2509,7 @@ communicator_processinterrupts(void)
 	if (timeout_signaled)
 	{
 		if (!readpage_reentrant_guard && readahead_getpage_pull_timeout_ms > 0)
-			communicator_prefetch_pump_state();
+			communicator_prefetch_pump_state(true);
 
 		timeout_signaled = false;
 		communicator_reconfigure_timeout_if_needed();

pgxn/neon/communicator.h

@@ -44,7 +44,7 @@ extern int communicator_read_slru_segment(SlruKind kind, int64 segno,
 										  void *buffer);
 
 extern void communicator_reconfigure_timeout_if_needed(void);
-extern void communicator_prefetch_pump_state(void);
+extern void communicator_prefetch_pump_state(bool IsHandlingInterrupts);
 
 
 #endif

pgxn/neon/libpagestore.c

@@ -433,6 +433,7 @@ pageserver_connect(shardno_t shard_no, int elevel)
 
 		now = GetCurrentTimestamp();
 		us_since_last_attempt = (int64) (now - shard->last_reconnect_time);
+		shard->last_reconnect_time = now;
 
 		/*
 		 * Make sure we don't do exponential backoff with a constant multiplier
@@ -446,23 +447,14 @@ pageserver_connect(shardno_t shard_no, int elevel)
 		/*
 		 * If we did other tasks between reconnect attempts, then we won't
 		 * need to wait as long as a full delay.
-		 *
-		 * This is a loop to protect against interrupted sleeps.
 		 */
-		while (us_since_last_attempt < shard->delay_us)
+		if (us_since_last_attempt < shard->delay_us)
 		{
 			pg_usleep(shard->delay_us - us_since_last_attempt);
-
-			/* At least we should handle cancellations here */
-			CHECK_FOR_INTERRUPTS();
-
-			now = GetCurrentTimestamp();
-			us_since_last_attempt = (int64) (now - shard->last_reconnect_time);
 		}
 
 		/* update the delay metric */
 		shard->delay_us = Min(shard->delay_us * 2, MAX_RECONNECT_INTERVAL_USEC);
-		shard->last_reconnect_time = now;
 
 		/*
 		 * Connect using the connection string we got from the

pgxn/neon/pagestore_smgr.c

@@ -1179,7 +1179,7 @@ neon_prefetch(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 		blocknum += iterblocks;
 	}
 
-	communicator_prefetch_pump_state();
+	communicator_prefetch_pump_state(false);
 
 	return false;
 }
@@ -1218,7 +1218,7 @@ neon_prefetch(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum)
 
 	communicator_prefetch_register_bufferv(tag, NULL, 1, NULL);
 
-	communicator_prefetch_pump_state();
+	communicator_prefetch_pump_state(false);
 
 	return false;
 }
@@ -1262,7 +1262,7 @@ neon_writeback(SMgrRelation reln, ForkNumber forknum,
 	 */
 	neon_log(SmgrTrace, "writeback noop");
 
-	communicator_prefetch_pump_state();
+	communicator_prefetch_pump_state(false);
 
 #ifdef DEBUG_COMPARE_LOCAL
 	if (IS_LOCAL_REL(reln))
@@ -1281,24 +1281,75 @@ neon_read_at_lsn(NRelFileInfo rinfo, ForkNumber forkNum, BlockNumber blkno,
 	communicator_read_at_lsnv(rinfo, forkNum, blkno, &request_lsns, &buffer, 1, NULL);
 }
 
-#ifdef DEBUG_COMPARE_LOCAL
+#if PG_MAJORVERSION_NUM < 17
+/*
+ *	neon_read() -- Read the specified block from a relation.
+ */
+#if PG_MAJORVERSION_NUM < 16
 static void
-compare_with_local(SMgrRelation reln, ForkNumber forkNum, BlockNumber blkno, void* buffer, XLogRecPtr request_lsn)
+neon_read(SMgrRelation reln, ForkNumber forkNum, BlockNumber blkno, char *buffer)
+#else
+static void
+neon_read(SMgrRelation reln, ForkNumber forkNum, BlockNumber blkno, void *buffer)
+#endif
 {
+	neon_request_lsns request_lsns;
+	bits8		present;
+	void	   *bufferp;
+
+	switch (reln->smgr_relpersistence)
+	{
+		case 0:
+			neon_log(ERROR, "cannot call smgrread() on rel with unknown persistence");
+
+		case RELPERSISTENCE_PERMANENT:
+			break;
+
+		case RELPERSISTENCE_TEMP:
+		case RELPERSISTENCE_UNLOGGED:
+			mdread(reln, forkNum, blkno, buffer);
+			return;
+
+		default:
+			neon_log(ERROR, "unknown relpersistence '%c'", reln->smgr_relpersistence);
+	}
+
+	/* Try to read PS results if they are available */
+	communicator_prefetch_pump_state(false);
+
+	neon_get_request_lsns(InfoFromSMgrRel(reln), forkNum, blkno, &request_lsns, 1);
+
+	present = 0;
+	bufferp = buffer;
+	if (communicator_prefetch_lookupv(InfoFromSMgrRel(reln), forkNum, blkno, &request_lsns, 1, &bufferp, &present))
+	{
+		/* Prefetch hit */
+		return;
+	}
+
+	/* Try to read from local file cache */
+	if (lfc_read(InfoFromSMgrRel(reln), forkNum, blkno, buffer))
+	{
+		MyNeonCounters->file_cache_hits_total++;
+		return;
+	}
+
+	neon_read_at_lsn(InfoFromSMgrRel(reln), forkNum, blkno, request_lsns, buffer);
+
+	/*
+	 * Try to receive prefetch results once again just to make sure we don't leave the smgr code while the OS might still have buffered bytes.
+	 */
+	communicator_prefetch_pump_state(false);
+
+#ifdef DEBUG_COMPARE_LOCAL
 	if (forkNum == MAIN_FORKNUM && IS_LOCAL_REL(reln))
 	{
 		char		pageserver_masked[BLCKSZ];
 		PGIOAlignedBlock mdbuf;
 		PGIOAlignedBlock mdbuf_masked;
+		XLogRecPtr  request_lsn = request_lsns.request_lsn;
 
-#if PG_MAJORVERSION_NUM >= 17
-		{
-			void* mdbuffers[1] = { mdbuf.data };
-			mdreadv(reln, forkNum, blkno, mdbuffers, 1);
-		}
-#else
 		mdread(reln, forkNum, blkno, mdbuf.data);
-#endif
 
 		memcpy(pageserver_masked, buffer, BLCKSZ);
 		memcpy(mdbuf_masked.data, mdbuf.data, BLCKSZ);
@@ -1362,105 +1413,11 @@ compare_with_local(SMgrRelation reln, ForkNumber forkNum, BlockNumber blkno, voi
 			}
 		}
 	}
-}
-#endif
-
-
-#if PG_MAJORVERSION_NUM < 17
-
-/*
- *	neon_read() -- Read the specified block from a relation.
- */
-#if PG_MAJORVERSION_NUM < 16
-static void
-neon_read(SMgrRelation reln, ForkNumber forkNum, BlockNumber blkno, char *buffer)
-#else
-static void
-neon_read(SMgrRelation reln, ForkNumber forkNum, BlockNumber blkno, void *buffer)
-#endif
-{
-	neon_request_lsns request_lsns;
-	bits8		present;
-	void	   *bufferp;
-
-	switch (reln->smgr_relpersistence)
-	{
-		case 0:
-			neon_log(ERROR, "cannot call smgrread() on rel with unknown persistence");
-
-		case RELPERSISTENCE_PERMANENT:
-			break;
-
-		case RELPERSISTENCE_TEMP:
-		case RELPERSISTENCE_UNLOGGED:
-			mdread(reln, forkNum, blkno, buffer);
-			return;
-
-		default:
-			neon_log(ERROR, "unknown relpersistence '%c'", reln->smgr_relpersistence);
-	}
-
-	/* Try to read PS results if they are available */
-	communicator_prefetch_pump_state();
-
-	neon_get_request_lsns(InfoFromSMgrRel(reln), forkNum, blkno, &request_lsns, 1);
-
-	present = 0;
-	bufferp = buffer;
-	if (communicator_prefetch_lookupv(InfoFromSMgrRel(reln), forkNum, blkno, &request_lsns, 1, &bufferp, &present))
-	{
-		/* Prefetch hit */
-#ifdef DEBUG_COMPARE_LOCAL
-		compare_with_local(reln, forkNum, blkno, buffer, request_lsns.request_lsn);
-#else
-		return;
-#endif
-	}
-
-	/* Try to read from local file cache */
-	if (lfc_read(InfoFromSMgrRel(reln), forkNum, blkno, buffer))
-	{
-		MyNeonCounters->file_cache_hits_total++;
-#ifdef DEBUG_COMPARE_LOCAL
-		compare_with_local(reln, forkNum, blkno, buffer, request_lsns.request_lsn);
-#else
-		return;
-#endif
-	}
-
-	neon_read_at_lsn(InfoFromSMgrRel(reln), forkNum, blkno, request_lsns, buffer);
-
-	/*
-	 * Try to receive prefetch results once again just to make sure we don't leave the smgr code while the OS might still have buffered bytes.
-	 */
-	communicator_prefetch_pump_state();
-
-#ifdef DEBUG_COMPARE_LOCAL
-	compare_with_local(reln, forkNum, blkno, buffer, request_lsns.request_lsn);
 #endif
 }
 #endif /* PG_MAJORVERSION_NUM <= 16 */
 
 #if PG_MAJORVERSION_NUM >= 17
-
-#ifdef DEBUG_COMPARE_LOCAL
-static void
-compare_with_localv(SMgrRelation reln, ForkNumber forkNum, BlockNumber blkno, void** buffers, BlockNumber nblocks, neon_request_lsns* request_lsns, bits8* read_pages)
-{
-	if (forkNum == MAIN_FORKNUM && IS_LOCAL_REL(reln))
-	{
-		for (BlockNumber i = 0; i < nblocks; i++)
-		{
-			if (BITMAP_ISSET(read_pages, i))
-			{
-				compare_with_local(reln, forkNum, blkno + i, buffers[i], request_lsns[i].request_lsn);
-			}
-		}
-	}
-}
-#endif
-
-
 static void
 neon_readv(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 		   void **buffers, BlockNumber nblocks)
@@ -1492,7 +1449,7 @@ neon_readv(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 				 nblocks, PG_IOV_MAX);
 
 	/* Try to read PS results if they are available */
-	communicator_prefetch_pump_state();
+	communicator_prefetch_pump_state(false);
 
 	neon_get_request_lsns(InfoFromSMgrRel(reln), forknum, blocknum,
 						  request_lsns, nblocks);
@@ -1503,13 +1460,8 @@ neon_readv(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 													blocknum, request_lsns, nblocks,
 													buffers, read_pages);
 
-#ifdef DEBUG_COMPARE_LOCAL
-	compare_with_localv(reln, forknum, blocknum, buffers, nblocks, request_lsns, read_pages);
-	memset(read_pages, 0, sizeof(read_pages));
-#else
 	if (prefetch_result == nblocks)
 		return;
-#endif
 
 	/* Try to read from local file cache */
 	lfc_result = lfc_readv_select(InfoFromSMgrRel(reln), forknum, blocknum, buffers,
@@ -1518,14 +1470,9 @@ neon_readv(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 	if (lfc_result > 0)
 		MyNeonCounters->file_cache_hits_total += lfc_result;
 
-#ifdef DEBUG_COMPARE_LOCAL
-	compare_with_localv(reln, forknum, blocknum, buffers, nblocks, request_lsns, read_pages);
-	memset(read_pages, 0, sizeof(read_pages));
-#else
 	/* Read all blocks from LFC, so we're done */
 	if (prefetch_result + lfc_result == nblocks)
 		return;
-#endif
 
 	communicator_read_at_lsnv(InfoFromSMgrRel(reln), forknum, blocknum, request_lsns,
 							  buffers, nblocks, read_pages);
@@ -1533,11 +1480,94 @@ neon_readv(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 	/*
 	 * Try to receive prefetch results once again just to make sure we don't leave the smgr code while the OS might still have buffered bytes.
 	 */
-	communicator_prefetch_pump_state();
+	communicator_prefetch_pump_state(false);
 
 #ifdef DEBUG_COMPARE_LOCAL
-	memset(read_pages, 0xFF, sizeof(read_pages));
-	compare_with_localv(reln, forknum, blocknum, buffers, nblocks, request_lsns, read_pages);
+	if (forknum == MAIN_FORKNUM && IS_LOCAL_REL(reln))
+	{
+		char		pageserver_masked[BLCKSZ];
+		PGIOAlignedBlock mdbuf;
+		PGIOAlignedBlock mdbuf_masked;
+		XLogRecPtr  request_lsn = request_lsns->request_lsn;
+
+		for (int i = 0; i < nblocks; i++)
+		{
+			BlockNumber blkno = blocknum + i;
+			if (!BITMAP_ISSET(read_pages, i))
+				continue;
+
+#if PG_MAJORVERSION_NUM >= 17
+			{
+				void* mdbuffers[1] = { mdbuf.data };
+				mdreadv(reln, forknum, blkno, mdbuffers, 1);
+			}
+#else
+			mdread(reln, forknum, blkno, mdbuf.data);
+#endif
+
+			memcpy(pageserver_masked, buffers[i], BLCKSZ);
+			memcpy(mdbuf_masked.data, mdbuf.data, BLCKSZ);
+
+			if (PageIsNew((Page) mdbuf.data))
+			{
+				if (!PageIsNew((Page) pageserver_masked))
+				{
+					neon_log(PANIC, "page is new in MD but not in Page Server at blk %u in rel %u/%u/%u fork %u (request LSN %X/%08X):\n%s\n",
+						 blkno,
+						 RelFileInfoFmt(InfoFromSMgrRel(reln)),
+						 forknum,
+						 (uint32) (request_lsn >> 32), (uint32) request_lsn,
+						 hexdump_page(buffers[i]));
+				}
+			}
+			else if (PageIsNew((Page) buffers[i]))
+			{
+				neon_log(PANIC, "page is new in Page Server but not in MD at blk %u in rel %u/%u/%u fork %u (request LSN %X/%08X):\n%s\n",
+					 blkno,
+					 RelFileInfoFmt(InfoFromSMgrRel(reln)),
+					 forknum,
+					 (uint32) (request_lsn >> 32), (uint32) request_lsn,
+					 hexdump_page(mdbuf.data));
+			}
+			else if (PageGetSpecialSize(mdbuf.data) == 0)
+			{
+				/* assume heap */
+				RmgrTable[RM_HEAP_ID].rm_mask(mdbuf_masked.data, blkno);
+				RmgrTable[RM_HEAP_ID].rm_mask(pageserver_masked, blkno);
+
+				if (memcmp(mdbuf_masked.data, pageserver_masked, BLCKSZ) != 0)
+				{
+					neon_log(PANIC, "heap buffers differ at blk %u in rel %u/%u/%u fork %u (request LSN %X/%08X):\n------ MD ------\n%s\n------ Page Server ------\n%s\n",
+						 blkno,
+						 RelFileInfoFmt(InfoFromSMgrRel(reln)),
+						 forknum,
+						 (uint32) (request_lsn >> 32), (uint32) request_lsn,
+						 hexdump_page(mdbuf_masked.data),
+						 hexdump_page(pageserver_masked));
+				}
+			}
+			else if (PageGetSpecialSize(mdbuf.data) == MAXALIGN(sizeof(BTPageOpaqueData)))
+			{
+				if (((BTPageOpaqueData *) PageGetSpecialPointer(mdbuf.data))->btpo_cycleid < MAX_BT_CYCLE_ID)
+				{
+					/* assume btree */
+					RmgrTable[RM_BTREE_ID].rm_mask(mdbuf_masked.data, blkno);
+					RmgrTable[RM_BTREE_ID].rm_mask(pageserver_masked, blkno);
+	
+					if (memcmp(mdbuf_masked.data, pageserver_masked, BLCKSZ) != 0)
+					{
+						neon_log(PANIC, "btree buffers differ at blk %u in rel %u/%u/%u fork %u (request LSN %X/%08X):\n------ MD ------\n%s\n------ Page Server ------\n%s\n",
+							 blkno,
+							 RelFileInfoFmt(InfoFromSMgrRel(reln)),
+							 forknum,
+							 (uint32) (request_lsn >> 32), (uint32) request_lsn,
+							 hexdump_page(mdbuf_masked.data),
+							 hexdump_page(pageserver_masked));
+					}
+				}
+			}
+		}
+	}
 #endif
 }
 #endif
@@ -1635,7 +1665,7 @@ neon_write(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, const vo
 
 	lfc_write(InfoFromSMgrRel(reln), forknum, blocknum, buffer);
 
-	communicator_prefetch_pump_state();
+	communicator_prefetch_pump_state(false);
 
 #ifdef DEBUG_COMPARE_LOCAL
 	if (IS_LOCAL_REL(reln))
@@ -1697,7 +1727,7 @@ neon_writev(SMgrRelation reln, ForkNumber forknum, BlockNumber blkno,
 
 	lfc_writev(InfoFromSMgrRel(reln), forknum, blkno, buffers, nblocks);
 
-	communicator_prefetch_pump_state();
+	communicator_prefetch_pump_state(false);
 
 #ifdef DEBUG_COMPARE_LOCAL
 	if (IS_LOCAL_REL(reln))
@@ -1872,7 +1902,7 @@ neon_immedsync(SMgrRelation reln, ForkNumber forknum)
 
 	neon_log(SmgrTrace, "[NEON_SMGR] immedsync noop");
 
-	communicator_prefetch_pump_state();
+	communicator_prefetch_pump_state(false);
 
 #ifdef DEBUG_COMPARE_LOCAL
 	if (IS_LOCAL_REL(reln))

proxy/src/bin/proxy.rs

@@ -1,10 +1,6 @@
 #[global_allocator]
 static GLOBAL: tikv_jemallocator::Jemalloc = tikv_jemallocator::Jemalloc;
 
-#[allow(non_upper_case_globals)]
-#[unsafe(export_name = "malloc_conf")]
-pub static malloc_conf: &[u8] = b"prof:true,prof_active:true,lg_prof_sample:21\0";
-
 #[tokio::main]
 async fn main() -> anyhow::Result<()> {
     proxy::binary::proxy::run().await

proxy/src/binary/local_proxy.rs

@@ -423,8 +423,8 @@ async fn refresh_config_inner(
     if let Some(tls_config) = data.tls {
         let tls_config = tokio::task::spawn_blocking(move || {
             crate::tls::server_config::configure_tls(
-                tls_config.key_path.as_ref(),
-                tls_config.cert_path.as_ref(),
+                &tls_config.key_path,
+                &tls_config.cert_path,
                 None,
                 false,
             )

proxy/src/binary/pg_sni_router.rs

@@ -1,10 +1,8 @@
-//! A stand-alone program that routes connections, e.g. from
-//! `aaa--bbb--1234.external.domain` to `aaa.bbb.internal.domain:1234`.
-//!
-//! This allows connecting to pods/services running in the same Kubernetes cluster from
-//! the outside. Similar to an ingress controller for HTTPS.
-
-use std::path::Path;
+/// A stand-alone program that routes connections, e.g. from
+/// `aaa--bbb--1234.external.domain` to `aaa.bbb.internal.domain:1234`.
+///
+/// This allows connecting to pods/services running in the same Kubernetes cluster from
+/// the outside. Similar to an ingress controller for HTTPS.
 use std::{net::SocketAddr, sync::Arc};
 
 use anyhow::{Context, anyhow, bail, ensure};
@@ -88,7 +86,46 @@ pub async fn run() -> anyhow::Result<()> {
         args.get_one::<String>("tls-key"),
         args.get_one::<String>("tls-cert"),
     ) {
-        (Some(key_path), Some(cert_path)) => parse_tls(key_path.as_ref(), cert_path.as_ref())?,
+        (Some(key_path), Some(cert_path)) => {
+            let key = {
+                let key_bytes = std::fs::read(key_path).context("TLS key file")?;
+
+                let mut keys =
+                    rustls_pemfile::pkcs8_private_keys(&mut &key_bytes[..]).collect_vec();
+
+                ensure!(keys.len() == 1, "keys.len() = {} (should be 1)", keys.len());
+                PrivateKeyDer::Pkcs8(
+                    keys.pop()
+                        .expect("keys should not be empty")
+                        .context(format!("Failed to read TLS keys at '{key_path}'"))?,
+                )
+            };
+
+            let cert_chain_bytes = std::fs::read(cert_path)
+                .context(format!("Failed to read TLS cert file at '{cert_path}.'"))?;
+
+            let cert_chain: Vec<_> = {
+                rustls_pemfile::certs(&mut &cert_chain_bytes[..])
+                .try_collect()
+                .with_context(|| {
+                    format!("Failed to read TLS certificate chain from bytes from file at '{cert_path}'.")
+                })?
+            };
+
+            // needed for channel bindings
+            let first_cert = cert_chain.first().context("missing certificate")?;
+            let tls_server_end_point = TlsServerEndPoint::new(first_cert)?;
+
+            let tls_config =
+                rustls::ServerConfig::builder_with_provider(Arc::new(ring::default_provider()))
+                    .with_protocol_versions(&[&rustls::version::TLS13, &rustls::version::TLS12])
+                    .context("ring should support TLS1.2 and TLS1.3")?
+                    .with_no_client_auth()
+                    .with_single_cert(cert_chain, key)?
+                    .into();
+
+            (tls_config, tls_server_end_point)
+        }
         _ => bail!("tls-key and tls-cert must be specified"),
     };
 
@@ -151,58 +188,7 @@ pub async fn run() -> anyhow::Result<()> {
     match signal {}
 }
 
-pub(super) fn parse_tls(
-    key_path: &Path,
-    cert_path: &Path,
-) -> anyhow::Result<(Arc<rustls::ServerConfig>, TlsServerEndPoint)> {
-    let key = {
-        let key_bytes = std::fs::read(key_path).context("TLS key file")?;
-
-        let mut keys = rustls_pemfile::pkcs8_private_keys(&mut &key_bytes[..]).collect_vec();
-
-        ensure!(keys.len() == 1, "keys.len() = {} (should be 1)", keys.len());
-        PrivateKeyDer::Pkcs8(
-            keys.pop()
-                .expect("keys should not be empty")
-                .context(format!(
-                    "Failed to read TLS keys at '{}'",
-                    key_path.display()
-                ))?,
-        )
-    };
-
-    let cert_chain_bytes = std::fs::read(cert_path).context(format!(
-        "Failed to read TLS cert file at '{}.'",
-        cert_path.display()
-    ))?;
-
-    let cert_chain: Vec<_> = {
-        rustls_pemfile::certs(&mut &cert_chain_bytes[..])
-            .try_collect()
-            .with_context(|| {
-                format!(
-                    "Failed to read TLS certificate chain from bytes from file at '{}'.",
-                    cert_path.display()
-                )
-            })?
-    };
-
-    // needed for channel bindings
-    let first_cert = cert_chain.first().context("missing certificate")?;
-    let tls_server_end_point = TlsServerEndPoint::new(first_cert)?;
-
-    let tls_config =
-        rustls::ServerConfig::builder_with_provider(Arc::new(ring::default_provider()))
-            .with_protocol_versions(&[&rustls::version::TLS13, &rustls::version::TLS12])
-            .context("ring should support TLS1.2 and TLS1.3")?
-            .with_no_client_auth()
-            .with_single_cert(cert_chain, key)?
-            .into();
-
-    Ok((tls_config, tls_server_end_point))
-}
-
-pub(super) async fn task_main(
+async fn task_main(
     dest_suffix: Arc<String>,
     tls_config: Arc<rustls::ServerConfig>,
     compute_tls_config: Option<Arc<rustls::ClientConfig>>,
@@ -394,7 +380,6 @@ async fn handle_client(
     }
 }
 
-#[allow(clippy::large_enum_variant)]
 enum Connection {
     Raw(tokio::net::TcpStream),
     Tls(tokio_rustls::client::TlsStream<tokio::net::TcpStream>),

proxy/src/binary/proxy.rs

@@ -1,10 +1,9 @@
 use std::net::SocketAddr;
-use std::path::PathBuf;
 use std::pin::pin;
 use std::sync::Arc;
 use std::time::Duration;
 
-use anyhow::{bail, ensure};
+use anyhow::bail;
 use arc_swap::ArcSwapOption;
 use futures::future::Either;
 use remote_storage::RemoteStorageConfig;
@@ -43,12 +42,11 @@ project_build_tag!(BUILD_TAG);
 use clap::{Parser, ValueEnum};
 
 #[derive(Clone, Debug, ValueEnum)]
-#[clap(rename_all = "kebab-case")]
 enum AuthBackendType {
-    #[clap(alias("cplane-v1"))]
-    ControlPlane,
+    #[value(name("cplane-v1"), alias("control-plane"))]
+    ControlPlaneV1,
 
-    #[clap(alias("link"))]
+    #[value(name("link"), alias("control-redirect"))]
     ConsoleRedirect,
 
     #[cfg(any(test, feature = "testing"))]
@@ -64,18 +62,18 @@ struct ProxyCliArgs {
     region: String,
     /// listen for incoming client connections on ip:port
     #[clap(short, long, default_value = "127.0.0.1:4432")]
-    proxy: SocketAddr,
+    proxy: String,
     #[clap(value_enum, long, default_value_t = AuthBackendType::ConsoleRedirect)]
     auth_backend: AuthBackendType,
     /// listen for management callback connection on ip:port
     #[clap(short, long, default_value = "127.0.0.1:7000")]
-    mgmt: SocketAddr,
+    mgmt: String,
     /// listen for incoming http connections (metrics, etc) on ip:port
     #[clap(long, default_value = "127.0.0.1:7001")]
-    http: SocketAddr,
+    http: String,
     /// listen for incoming wss connections on ip:port
     #[clap(long)]
-    wss: Option<SocketAddr>,
+    wss: Option<String>,
     /// redirect unauthenticated users to the given uri in case of console redirect auth
     #[clap(short, long, default_value = "http://localhost:3000/psql_session/")]
     uri: String,
@@ -101,18 +99,18 @@ struct ProxyCliArgs {
     ///
     /// tls-key and tls-cert are for backwards compatibility, we can put all certs in one dir
     #[clap(short = 'k', long, alias = "ssl-key")]
-    tls_key: Option<PathBuf>,
+    tls_key: Option<String>,
     /// path to TLS cert for client postgres connections
     ///
     /// tls-key and tls-cert are for backwards compatibility, we can put all certs in one dir
     #[clap(short = 'c', long, alias = "ssl-cert")]
-    tls_cert: Option<PathBuf>,
+    tls_cert: Option<String>,
     /// Allow writing TLS session keys to the given file pointed to by the environment variable `SSLKEYLOGFILE`.
     #[clap(long, alias = "allow-ssl-keylogfile")]
     allow_tls_keylogfile: bool,
     /// path to directory with TLS certificates for client postgres connections
     #[clap(long)]
-    certs_dir: Option<PathBuf>,
+    certs_dir: Option<String>,
     /// timeout for the TLS handshake
     #[clap(long, default_value = "15s", value_parser = humantime::parse_duration)]
     handshake_timeout: tokio::time::Duration,
@@ -231,9 +229,6 @@ struct ProxyCliArgs {
     // TODO: rename to `console_redirect_confirmation_timeout`.
     #[clap(long, default_value = "2m", value_parser = humantime::parse_duration)]
     webauth_confirmation_timeout: std::time::Duration,
-
-    #[clap(flatten)]
-    pg_sni_router: PgSniRouterArgs,
 }
 
 #[derive(clap::Args, Clone, Copy, Debug)]
@@ -282,25 +277,6 @@ struct SqlOverHttpArgs {
     sql_over_http_max_response_size_bytes: usize,
 }
 
-#[derive(clap::Args, Clone, Debug)]
-struct PgSniRouterArgs {
-    /// listen for incoming client connections on ip:port
-    #[clap(id = "sni-router-listen", long, default_value = "127.0.0.1:4432")]
-    listen: SocketAddr,
-    /// listen for incoming client connections on ip:port, requiring TLS to compute
-    #[clap(id = "sni-router-listen-tls", long, default_value = "127.0.0.1:4433")]
-    listen_tls: SocketAddr,
-    /// path to TLS key for client postgres connections
-    #[clap(id = "sni-router-tls-key", long)]
-    tls_key: Option<PathBuf>,
-    /// path to TLS cert for client postgres connections
-    #[clap(id = "sni-router-tls-cert", long)]
-    tls_cert: Option<PathBuf>,
-    /// append this domain zone to the SNI hostname to get the destination address
-    #[clap(id = "sni-router-destination", long)]
-    dest: Option<String>,
-}
-
 pub async fn run() -> anyhow::Result<()> {
     let _logging_guard = crate::logging::init().await?;
     let _panic_hook_guard = utils::logging::replace_panic_hook_with_tracing_panic_hook();
@@ -331,51 +307,73 @@ pub async fn run() -> anyhow::Result<()> {
         Either::Right(auth_backend) => info!("Authentication backend: {auth_backend:?}"),
     }
     info!("Using region: {}", args.aws_region);
-    let (regional_redis_client, redis_notifications_client) = configure_redis(&args).await?;
+
+    // TODO: untangle the config args
+    let regional_redis_client = match (args.redis_auth_type.as_str(), &args.redis_notifications) {
+        ("plain", redis_url) => match redis_url {
+            None => {
+                bail!("plain auth requires redis_notifications to be set");
+            }
+            Some(url) => {
+                Some(ConnectionWithCredentialsProvider::new_with_static_credentials(url.clone()))
+            }
+        },
+        ("irsa", _) => match (&args.redis_host, args.redis_port) {
+            (Some(host), Some(port)) => Some(
+                ConnectionWithCredentialsProvider::new_with_credentials_provider(
+                    host.to_string(),
+                    port,
+                    elasticache::CredentialsProvider::new(
+                        args.aws_region,
+                        args.redis_cluster_name,
+                        args.redis_user_id,
+                    )
+                    .await,
+                ),
+            ),
+            (None, None) => {
+                warn!(
+                    "irsa auth requires redis-host and redis-port to be set, continuing without regional_redis_client"
+                );
+                None
+            }
+            _ => {
+                bail!("redis-host and redis-port must be specified together");
+            }
+        },
+        _ => {
+            bail!("unknown auth type given");
+        }
+    };
+
+    let redis_notifications_client = if let Some(url) = args.redis_notifications {
+        Some(ConnectionWithCredentialsProvider::new_with_static_credentials(url))
+    } else {
+        regional_redis_client.clone()
+    };
 
     // Check that we can bind to address before further initialization
-    info!("Starting http on {}", args.http);
-    let http_listener = TcpListener::bind(args.http).await?.into_std()?;
+    let http_address: SocketAddr = args.http.parse()?;
+    info!("Starting http on {http_address}");
+    let http_listener = TcpListener::bind(http_address).await?.into_std()?;
 
-    info!("Starting mgmt on {}", args.mgmt);
-    let mgmt_listener = TcpListener::bind(args.mgmt).await?;
+    let mgmt_address: SocketAddr = args.mgmt.parse()?;
+    info!("Starting mgmt on {mgmt_address}");
+    let mgmt_listener = TcpListener::bind(mgmt_address).await?;
 
     let proxy_listener = if args.is_auth_broker {
         None
     } else {
-        info!("Starting proxy on {}", args.proxy);
-        Some(TcpListener::bind(args.proxy).await?)
-    };
+        let proxy_address: SocketAddr = args.proxy.parse()?;
+        info!("Starting proxy on {proxy_address}");
 
-    let sni_router_listeners = {
-        let args = &args.pg_sni_router;
-        if args.dest.is_some() {
-            ensure!(
-                args.tls_key.is_some(),
-                "sni-router-tls-key must be provided"
-            );
-            ensure!(
-                args.tls_cert.is_some(),
-                "sni-router-tls-cert must be provided"
-            );
-
-            info!(
-                "Starting pg-sni-router on {} and {}",
-                args.listen, args.listen_tls
-            );
-
-            Some((
-                TcpListener::bind(args.listen).await?,
-                TcpListener::bind(args.listen_tls).await?,
-            ))
-        } else {
-            None
-        }
+        Some(TcpListener::bind(proxy_address).await?)
     };
 
     // TODO: rename the argument to something like serverless.
     // It now covers more than just websockets, it also covers SQL over HTTP.
     let serverless_listener = if let Some(serverless_address) = args.wss {
+        let serverless_address: SocketAddr = serverless_address.parse()?;
         info!("Starting wss on {serverless_address}");
         Some(TcpListener::bind(serverless_address).await?)
     } else if args.is_auth_broker {
@@ -460,37 +458,6 @@ pub async fn run() -> anyhow::Result<()> {
         }
     }
 
-    // spawn pg-sni-router mode.
-    if let Some((listen, listen_tls)) = sni_router_listeners {
-        let args = args.pg_sni_router;
-        let dest = args.dest.expect("already asserted it is set");
-        let key_path = args.tls_key.expect("already asserted it is set");
-        let cert_path = args.tls_cert.expect("already asserted it is set");
-
-        let (tls_config, tls_server_end_point) =
-            super::pg_sni_router::parse_tls(&key_path, &cert_path)?;
-
-        let dest = Arc::new(dest);
-
-        client_tasks.spawn(super::pg_sni_router::task_main(
-            dest.clone(),
-            tls_config.clone(),
-            None,
-            tls_server_end_point,
-            listen,
-            cancellation_token.clone(),
-        ));
-
-        client_tasks.spawn(super::pg_sni_router::task_main(
-            dest,
-            tls_config,
-            Some(config.connect_to_compute.tls.clone()),
-            tls_server_end_point,
-            listen_tls,
-            cancellation_token.clone(),
-        ));
-    }
-
     client_tasks.spawn(crate::context::parquet::worker(
         cancellation_token.clone(),
         args.parquet_upload,
@@ -598,7 +565,7 @@ fn build_config(args: &ProxyCliArgs) -> anyhow::Result<&'static ProxyConfig> {
         (Some(key_path), Some(cert_path)) => Some(config::configure_tls(
             key_path,
             cert_path,
-            args.certs_dir.as_deref(),
+            args.certs_dir.as_ref(),
             args.allow_tls_keylogfile,
         )?),
         (None, None) => None,
@@ -708,7 +675,7 @@ fn build_auth_backend(
     args: &ProxyCliArgs,
 ) -> anyhow::Result<Either<&'static auth::Backend<'static, ()>, &'static ConsoleRedirectBackend>> {
     match &args.auth_backend {
-        AuthBackendType::ControlPlane => {
+        AuthBackendType::ControlPlaneV1 => {
             let wake_compute_cache_config: CacheOptions = args.wake_compute_cache.parse()?;
             let project_info_cache_config: ProjectInfoCacheOptions =
                 args.project_info_cache.parse()?;
@@ -844,60 +811,6 @@ fn build_auth_backend(
     }
 }
 
-async fn configure_redis(
-    args: &ProxyCliArgs,
-) -> anyhow::Result<(
-    Option<ConnectionWithCredentialsProvider>,
-    Option<ConnectionWithCredentialsProvider>,
-)> {
-    // TODO: untangle the config args
-    let regional_redis_client = match (args.redis_auth_type.as_str(), &args.redis_notifications) {
-        ("plain", redis_url) => match redis_url {
-            None => {
-                bail!("plain auth requires redis_notifications to be set");
-            }
-            Some(url) => {
-                Some(ConnectionWithCredentialsProvider::new_with_static_credentials(url.clone()))
-            }
-        },
-        ("irsa", _) => match (&args.redis_host, args.redis_port) {
-            (Some(host), Some(port)) => Some(
-                ConnectionWithCredentialsProvider::new_with_credentials_provider(
-                    host.clone(),
-                    port,
-                    elasticache::CredentialsProvider::new(
-                        args.aws_region.clone(),
-                        args.redis_cluster_name.clone(),
-                        args.redis_user_id.clone(),
-                    )
-                    .await,
-                ),
-            ),
-            (None, None) => {
-                // todo: upgrade to error?
-                warn!(
-                    "irsa auth requires redis-host and redis-port to be set, continuing without regional_redis_client"
-                );
-                None
-            }
-            _ => {
-                bail!("redis-host and redis-port must be specified together");
-            }
-        },
-        _ => {
-            bail!("unknown auth type given");
-        }
-    };
-
-    let redis_notifications_client = if let Some(url) = &args.redis_notifications {
-        Some(ConnectionWithCredentialsProvider::new_with_static_credentials(&**url))
-    } else {
-        regional_redis_client.clone()
-    };
-
-    Ok((regional_redis_client, redis_notifications_client))
-}
-
 #[cfg(test)]
 mod tests {
     use std::time::Duration;

proxy/src/cancellation.rs

@@ -6,12 +6,12 @@ use ipnet::{IpNet, Ipv4Net, Ipv6Net};
 use postgres_client::CancelToken;
 use postgres_client::tls::MakeTlsConnect;
 use pq_proto::CancelKeyData;
-use redis::{Cmd, FromRedisValue, Value};
+use redis::{FromRedisValue, Pipeline, Value, pipe};
 use serde::{Deserialize, Serialize};
 use thiserror::Error;
 use tokio::net::TcpStream;
 use tokio::sync::{mpsc, oneshot};
-use tracing::{debug, error, info, warn};
+use tracing::{debug, info, warn};
 
 use crate::auth::backend::ComputeUserInfo;
 use crate::auth::{AuthError, check_peer_addr_is_in_list};
@@ -56,70 +56,8 @@ pub enum CancelKeyOp {
     },
 }
 
-pub struct Pipeline {
-    inner: redis::Pipeline,
-    replies: Vec<CancelReplyOp>,
-}
-
-impl Pipeline {
-    fn with_capacity(n: usize) -> Self {
-        Self {
-            inner: redis::Pipeline::with_capacity(n),
-            replies: Vec::with_capacity(n),
-        }
-    }
-
-    async fn execute(&mut self, client: &mut RedisKVClient) {
-        let responses = self.replies.len();
-        let batch_size = self.inner.len();
-
-        match client.query(&self.inner).await {
-            // for each reply, we expect that many values.
-            Ok(Value::Array(values)) if values.len() == responses => {
-                debug!(
-                    batch_size,
-                    responses, "successfully completed cancellation jobs",
-                );
-                for (value, reply) in std::iter::zip(values, self.replies.drain(..)) {
-                    reply.send_value(value);
-                }
-            }
-            Ok(value) => {
-                error!(batch_size, ?value, "unexpected redis return value");
-                for reply in self.replies.drain(..) {
-                    reply.send_err(anyhow!("incorrect response type from redis"));
-                }
-            }
-            Err(err) => {
-                for reply in self.replies.drain(..) {
-                    reply.send_err(anyhow!("could not send cmd to redis: {err}"));
-                }
-            }
-        }
-
-        self.inner.clear();
-        self.replies.clear();
-    }
-
-    fn add_command_with_reply(&mut self, cmd: Cmd, reply: CancelReplyOp) {
-        self.inner.add_command(cmd);
-        self.replies.push(reply);
-    }
-
-    fn add_command_no_reply(&mut self, cmd: Cmd) {
-        self.inner.add_command(cmd).ignore();
-    }
-
-    fn add_command(&mut self, cmd: Cmd, reply: Option<CancelReplyOp>) {
-        match reply {
-            Some(reply) => self.add_command_with_reply(cmd, reply),
-            None => self.add_command_no_reply(cmd),
-        }
-    }
-}
-
 impl CancelKeyOp {
-    fn register(self, pipe: &mut Pipeline) {
+    fn register(self, pipe: &mut Pipeline) -> Option<CancelReplyOp> {
         #[allow(clippy::used_underscore_binding)]
         match self {
             CancelKeyOp::StoreCancelKey {
@@ -130,18 +68,18 @@ impl CancelKeyOp {
                 _guard,
                 expire,
             } => {
-                let reply =
-                    resp_tx.map(|resp_tx| CancelReplyOp::StoreCancelKey { resp_tx, _guard });
-                pipe.add_command(Cmd::hset(&key, field, value), reply);
-                pipe.add_command_no_reply(Cmd::expire(key, expire));
+                pipe.hset(&key, field, value);
+                pipe.expire(key, expire);
+                let resp_tx = resp_tx?;
+                Some(CancelReplyOp::StoreCancelKey { resp_tx, _guard })
             }
             CancelKeyOp::GetCancelData {
                 key,
                 resp_tx,
                 _guard,
             } => {
-                let reply = CancelReplyOp::GetCancelData { resp_tx, _guard };
-                pipe.add_command_with_reply(Cmd::hgetall(key), reply);
+                pipe.hgetall(key);
+                Some(CancelReplyOp::GetCancelData { resp_tx, _guard })
             }
             CancelKeyOp::RemoveCancelKey {
                 key,
@@ -149,9 +87,9 @@ impl CancelKeyOp {
                 resp_tx,
                 _guard,
             } => {
-                let reply =
-                    resp_tx.map(|resp_tx| CancelReplyOp::RemoveCancelKey { resp_tx, _guard });
-                pipe.add_command(Cmd::hdel(key, field), reply);
+                pipe.hdel(key, field);
+                let resp_tx = resp_tx?;
+                Some(CancelReplyOp::RemoveCancelKey { resp_tx, _guard })
             }
         }
     }
@@ -232,8 +170,8 @@ pub async fn handle_cancel_messages(
     client: &mut RedisKVClient,
     mut rx: mpsc::Receiver<CancelKeyOp>,
 ) -> anyhow::Result<()> {
-    let mut batch = Vec::with_capacity(BATCH_SIZE);
-    let mut pipeline = Pipeline::with_capacity(BATCH_SIZE);
+    let mut batch = Vec::new();
+    let mut replies = vec![];
 
     loop {
         if rx.recv_many(&mut batch, BATCH_SIZE).await == 0 {
@@ -244,11 +182,42 @@ pub async fn handle_cancel_messages(
         let batch_size = batch.len();
         debug!(batch_size, "running cancellation jobs");
 
+        let mut pipe = pipe();
         for msg in batch.drain(..) {
-            msg.register(&mut pipeline);
+            if let Some(reply) = msg.register(&mut pipe) {
+                replies.push(reply);
+            } else {
+                pipe.ignore();
+            }
         }
 
-        pipeline.execute(client).await;
+        let responses = replies.len();
+
+        match client.query(pipe).await {
+            // for each reply, we expect that many values.
+            Ok(Value::Array(values)) if values.len() == responses => {
+                debug!(
+                    batch_size,
+                    responses, "successfully completed cancellation jobs",
+                );
+                for (value, reply) in std::iter::zip(values, replies.drain(..)) {
+                    reply.send_value(value);
+                }
+            }
+            Ok(value) => {
+                debug!(?value, "unexpected redis return value");
+                for reply in replies.drain(..) {
+                    reply.send_err(anyhow!("incorrect response type from redis"));
+                }
+            }
+            Err(err) => {
+                for reply in replies.drain(..) {
+                    reply.send_err(anyhow!("could not send cmd to redis: {err}"));
+                }
+            }
+        }
+
+        replies.clear();
     }
 }
 

proxy/src/context/mod.rs

@@ -78,7 +78,7 @@ struct RequestContextInner {
 
 #[derive(Clone, Debug)]
 pub(crate) enum AuthMethod {
-    // aka link
+    // aka passwordless, fka link
     ConsoleRedirect,
     ScramSha256,
     ScramSha256Plus,

proxy/src/http/health_server.rs

@@ -3,7 +3,7 @@ use std::net::TcpListener;
 use std::sync::{Arc, Mutex};
 
 use anyhow::{anyhow, bail};
-use http_utils::endpoint::{self, profile_cpu_handler, profile_heap_handler, request_span};
+use http_utils::endpoint::{self, request_span};
 use http_utils::error::ApiError;
 use http_utils::json::json_response;
 use http_utils::{RouterBuilder, RouterService};
@@ -33,12 +33,6 @@ fn make_router(metrics: AppMetrics) -> RouterBuilder<hyper0::Body, ApiError> {
             request_span(r, move |b| prometheus_metrics_handler(b, state))
         })
         .get("/v1/status", status_handler)
-        .get("/profile/cpu", move |r| {
-            request_span(r, profile_cpu_handler)
-        })
-        .get("/profile/heap", move |r| {
-            request_span(r, profile_heap_handler)
-        })
 }
 
 pub async fn task_main(

proxy/src/redis/kv_ops.rs

@@ -47,7 +47,7 @@ impl RedisKVClient {
 
     pub(crate) async fn query<T: FromRedisValue>(
         &mut self,
-        q: &impl Queryable,
+        q: impl Queryable,
     ) -> anyhow::Result<T> {
         if !self.limiter.check() {
             tracing::info!("Rate limit exceeded. Skipping query");

proxy/src/tls/server_config.rs

@@ -1,5 +1,4 @@
 use std::collections::{HashMap, HashSet};
-use std::path::Path;
 use std::sync::Arc;
 
 use anyhow::{Context, bail};
@@ -22,9 +21,9 @@ pub struct TlsConfig {
 
 /// Configure TLS for the main endpoint.
 pub fn configure_tls(
-    key_path: &Path,
-    cert_path: &Path,
-    certs_dir: Option<&Path>,
+    key_path: &str,
+    cert_path: &str,
+    certs_dir: Option<&String>,
     allow_tls_keylogfile: bool,
 ) -> anyhow::Result<TlsConfig> {
     // add default certificate
@@ -40,7 +39,8 @@ pub fn configure_tls(
                 let key_path = path.join("tls.key");
                 let cert_path = path.join("tls.crt");
                 if key_path.exists() && cert_path.exists() {
-                    cert_resolver.add_cert_path(&key_path, &cert_path)?;
+                    cert_resolver
+                        .add_cert_path(&key_path.to_string_lossy(), &cert_path.to_string_lossy())?;
                 }
             }
         }
@@ -86,7 +86,7 @@ pub struct CertResolver {
 }
 
 impl CertResolver {
-    fn parse_new(key_path: &Path, cert_path: &Path) -> anyhow::Result<Self> {
+    fn parse_new(key_path: &str, cert_path: &str) -> anyhow::Result<Self> {
         let (priv_key, cert_chain) = parse_key_cert(key_path, cert_path)?;
         Self::new(priv_key, cert_chain)
     }
@@ -103,7 +103,7 @@ impl CertResolver {
         Ok(Self { certs, default })
     }
 
-    fn add_cert_path(&mut self, key_path: &Path, cert_path: &Path) -> anyhow::Result<()> {
+    fn add_cert_path(&mut self, key_path: &str, cert_path: &str) -> anyhow::Result<()> {
         let (priv_key, cert_chain) = parse_key_cert(key_path, cert_path)?;
         self.add_cert(priv_key, cert_chain)
     }
@@ -124,29 +124,26 @@ impl CertResolver {
 }
 
 fn parse_key_cert(
-    key_path: &Path,
-    cert_path: &Path,
+    key_path: &str,
+    cert_path: &str,
 ) -> anyhow::Result<(PrivateKeyDer<'static>, Vec<CertificateDer<'static>>)> {
     let priv_key = {
         let key_bytes = std::fs::read(key_path)
-            .with_context(|| format!("Failed to read TLS keys at '{}'", key_path.display()))?;
+            .with_context(|| format!("Failed to read TLS keys at '{key_path}'"))?;
         rustls_pemfile::private_key(&mut &key_bytes[..])
-            .with_context(|| format!("Failed to parse TLS keys at '{}'", key_path.display()))?
-            .with_context(|| format!("Failed to parse TLS keys at '{}'", key_path.display()))?
+            .with_context(|| format!("Failed to parse TLS keys at '{key_path}'"))?
+            .with_context(|| format!("Failed to parse TLS keys at '{key_path}'"))?
     };
 
-    let cert_chain_bytes = std::fs::read(cert_path).context(format!(
-        "Failed to read TLS cert file at '{}.'",
-        cert_path.display()
-    ))?;
+    let cert_chain_bytes = std::fs::read(cert_path)
+        .context(format!("Failed to read TLS cert file at '{cert_path}.'"))?;
 
     let cert_chain = {
         rustls_pemfile::certs(&mut &cert_chain_bytes[..])
             .try_collect()
             .with_context(|| {
                 format!(
-                    "Failed to read TLS certificate chain from bytes from file at '{}'.",
-                    cert_path.display()
+                    "Failed to read TLS certificate chain from bytes from file at '{cert_path}'."
                 )
             })?
     };

rust-toolchain.toml

@@ -1,5 +1,5 @@
 [toolchain]
-channel = "1.87.0"
+channel = "1.86.0"
 profile = "default"
 # The default profile includes rustc, rust-std, cargo, rust-docs, rustfmt and clippy.
 # https://rust-lang.github.io/rustup/concepts/profiles.html

safekeeper/src/bin/safekeeper.rs

@@ -22,10 +22,9 @@ use safekeeper::defaults::{
     DEFAULT_PARTIAL_BACKUP_TIMEOUT, DEFAULT_PG_LISTEN_ADDR, DEFAULT_SSL_CERT_FILE,
     DEFAULT_SSL_CERT_RELOAD_PERIOD, DEFAULT_SSL_KEY_FILE,
 };
-use safekeeper::wal_backup::WalBackup;
 use safekeeper::{
     BACKGROUND_RUNTIME, BROKER_RUNTIME, GlobalTimelines, HTTP_RUNTIME, SafeKeeperConf,
-    WAL_SERVICE_RUNTIME, broker, control_file, http, wal_service,
+    WAL_SERVICE_RUNTIME, broker, control_file, http, wal_backup, wal_service,
 };
 use sd_notify::NotifyState;
 use storage_broker::{DEFAULT_ENDPOINT, Uri};
@@ -485,15 +484,15 @@ async fn start_safekeeper(conf: Arc<SafeKeeperConf>) -> Result<()> {
         None => None,
     };
 
-    let wal_backup = Arc::new(WalBackup::new(&conf).await?);
-
-    let global_timelines = Arc::new(GlobalTimelines::new(conf.clone(), wal_backup.clone()));
+    let global_timelines = Arc::new(GlobalTimelines::new(conf.clone()));
 
     // Register metrics collector for active timelines. It's important to do this
     // after daemonizing, otherwise process collector will be upset.
     let timeline_collector = safekeeper::metrics::TimelineCollector::new(global_timelines.clone());
     metrics::register_internal(Box::new(timeline_collector))?;
 
+    wal_backup::init_remote_storage(&conf).await;
+
     // Keep handles to main tasks to die if any of them disappears.
     let mut tasks_handles: FuturesUnordered<BoxFuture<(String, JoinTaskRes)>> =
         FuturesUnordered::new();

safekeeper/src/copy_timeline.rs

@@ -3,7 +3,6 @@ use std::sync::Arc;
 use anyhow::{Result, bail};
 use camino::Utf8PathBuf;
 use postgres_ffi::{MAX_SEND_SIZE, WAL_SEGMENT_SIZE};
-use remote_storage::GenericRemoteStorage;
 use safekeeper_api::membership::Configuration;
 use tokio::fs::OpenOptions;
 use tokio::io::{AsyncSeekExt, AsyncWriteExt};
@@ -31,7 +30,6 @@ pub struct Request {
 pub async fn handle_request(
     request: Request,
     global_timelines: Arc<GlobalTimelines>,
-    storage: Arc<GenericRemoteStorage>,
 ) -> Result<()> {
     // TODO: request.until_lsn MUST be a valid LSN, and we cannot check it :(
     //   if LSN will point to the middle of a WAL record, timeline will be in "broken" state
@@ -129,7 +127,6 @@ pub async fn handle_request(
     assert!(first_ondisk_segment >= first_segment);
 
     copy_s3_segments(
-        &storage,
         wal_seg_size,
         &request.source_ttid,
         &request.destination_ttid,

safekeeper/src/http/routes.rs

@@ -258,7 +258,6 @@ async fn timeline_snapshot_handler(request: Request<Body>) -> Result<Response<Bo
 
     let global_timelines = get_global_timelines(&request);
     let tli = global_timelines.get(ttid).map_err(ApiError::from)?;
-    let storage = global_timelines.get_wal_backup().get_storage();
 
     // To stream the body use wrap_stream which wants Stream of Result<Bytes>,
     // so create the chan and write to it in another task.
@@ -270,7 +269,6 @@ async fn timeline_snapshot_handler(request: Request<Body>) -> Result<Response<Bo
         conf.my_id,
         destination,
         tx,
-        storage,
     ));
 
     let rx_stream = ReceiverStream::new(rx);
@@ -392,18 +390,12 @@ async fn timeline_copy_handler(mut request: Request<Body>) -> Result<Response<Bo
     );
 
     let global_timelines = get_global_timelines(&request);
-    let wal_backup = global_timelines.get_wal_backup();
-    let storage = wal_backup
-        .get_storage()
-        .ok_or(ApiError::BadRequest(anyhow::anyhow!(
-            "Remote Storage is not configured"
-        )))?;
 
     copy_timeline::handle_request(copy_timeline::Request{
         source_ttid,
         until_lsn: request_data.until_lsn,
         destination_ttid: TenantTimelineId::new(source_ttid.tenant_id, request_data.target_timeline_id),
-    }, global_timelines, storage)
+    }, global_timelines)
         .instrument(info_span!("copy_timeline", from=%source_ttid, to=%request_data.target_timeline_id, until_lsn=%request_data.until_lsn))
         .await
         .map_err(ApiError::InternalServerError)?;