proxy: refactor redis batching

.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: 60
+        timeout-minutes: 20
         env:
           TAG: >-
             ${{

.github/workflows/cloud-extensions.yml

@@ -35,7 +35,7 @@ jobs:
       matrix:
         pg-version: [16, 17]
 
-    runs-on: us-east-2
+    runs-on: [ self-hosted, small ]
     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
@@ -71,7 +71,20 @@ jobs:
           region_id: ${{ inputs.region_id || 'aws-us-east-2' }}
           postgres_version: ${{ matrix.pg-version }}
           project_settings: ${{ steps.project-settings.outputs.settings }}
+          # 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
+          default_endpoint_settings: >
+            {
+              "pg_settings": {
+                "DateStyle": "Postgres,MDY",
+                "TimeZone": "America/Los_Angeles",
+                "compute_query_id": "off",
+                "neon.allow_unstable_extensions": "on"
+              }
+            }
           api_key: ${{ secrets.NEON_STAGING_API_KEY }}
+          admin_api_key: ${{ secrets.NEON_STAGING_ADMIN_API_KEY }}
 
       - name: Run the regression tests
         run: /run-tests.sh -r /ext-src

.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"
@@ -1312,7 +1306,7 @@ dependencies = [
  "itertools 0.10.5",
  "jsonwebtoken",
  "metrics",
- "nix 0.30.1",
+ "nix 0.27.1",
  "notify",
  "num_cpus",
  "once_cell",
@@ -1435,7 +1429,7 @@ dependencies = [
  "humantime-serde",
  "hyper 0.14.30",
  "jsonwebtoken",
- "nix 0.30.1",
+ "nix 0.27.1",
  "once_cell",
  "pageserver_api",
  "pageserver_client",
@@ -3518,9 +3512,9 @@ 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"
@@ -3794,16 +3788,6 @@ version = "0.8.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e5ce46fe64a9d73be07dcbe690a38ce1b293be448fd8ce1e6c1b8062c9f72c6a"
 
-[[package]]
-name = "neon-shmem"
-version = "0.1.0"
-dependencies = [
- "nix 0.30.1",
- "tempfile",
- "thiserror 1.0.69",
- "workspace_hack",
-]
-
 [[package]]
 name = "never-say-never"
 version = "6.6.666"
@@ -3837,13 +3821,12 @@ 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",
 ]
@@ -4297,7 +4280,7 @@ dependencies = [
  "jsonwebtoken",
  "md5",
  "metrics",
- "nix 0.30.1",
+ "nix 0.27.1",
  "num-traits",
  "num_cpus",
  "once_cell",
@@ -4348,7 +4331,6 @@ dependencies = [
  "toml_edit",
  "tracing",
  "tracing-utils",
- "twox-hash",
  "url",
  "utils",
  "uuid",
@@ -4373,7 +4355,7 @@ dependencies = [
  "humantime",
  "humantime-serde",
  "itertools 0.10.5",
- "nix 0.30.1",
+ "nix 0.27.1",
  "once_cell",
  "postgres_backend",
  "postgres_ffi",
@@ -4434,16 +4416,6 @@ dependencies = [
  "workspace_hack",
 ]
 
-[[package]]
-name = "pageserver_page_api"
-version = "0.1.0"
-dependencies = [
- "prost 0.13.3",
- "tonic",
- "tonic-build",
- "workspace_hack",
-]
-
 [[package]]
 name = "papaya"
 version = "0.2.1"
@@ -4876,19 +4848,6 @@ 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"
@@ -7926,7 +7885,7 @@ dependencies = [
  "humantime",
  "jsonwebtoken",
  "metrics",
- "nix 0.30.1",
+ "nix 0.27.1",
  "once_cell",
  "pem",
  "pin-project-lite",
@@ -8480,10 +8439,8 @@ dependencies = [
  "fail",
  "form_urlencoded",
  "futures-channel",
- "futures-core",
  "futures-executor",
  "futures-io",
- "futures-task",
  "futures-util",
  "generic-array",
  "getrandom 0.2.11",
@@ -8502,7 +8459,6 @@ dependencies = [
  "log",
  "memchr",
  "nix 0.26.4",
- "nix 0.30.1",
  "nom",
  "num",
  "num-bigint",
@@ -8514,7 +8470,6 @@ dependencies = [
  "once_cell",
  "p256 0.13.2",
  "parquet",
- "percent-encoding",
  "prettyplease",
  "proc-macro2",
  "prost 0.13.3",

Cargo.toml

@@ -9,7 +9,6 @@ members = [
     "pageserver/ctl",
     "pageserver/client",
     "pageserver/pagebench",
-    "pageserver/page_api",
     "proxy",
     "safekeeper",
     "safekeeper/client",
@@ -24,11 +23,9 @@ members = [
     "libs/postgres_ffi",
     "libs/safekeeper_api",
     "libs/desim",
-    "libs/neon-shmem",
     "libs/utils",
     "libs/consumption_metrics",
     "libs/postgres_backend",
-    "libs/posthog_client_lite",
     "libs/pq_proto",
     "libs/tenant_size_model",
     "libs/metrics",
@@ -129,7 +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", "mman", "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"
@@ -253,7 +250,6 @@ pageserver = { path = "./pageserver" }
 pageserver_api = { version = "0.1", path = "./libs/pageserver_api/" }
 pageserver_client = { path = "./pageserver/client" }
 pageserver_compaction = { version = "0.1", path = "./pageserver/compaction/" }
-pageserver_page_api = { path = "./pageserver/page_api" }
 postgres_backend = { version = "0.1", path = "./libs/postgres_backend/" }
 postgres_connection = { version = "0.1", path = "./libs/postgres_connection/" }
 postgres_ffi = { version = "0.1", path = "./libs/postgres_ffi/" }

build-tools.Dockerfile

@@ -292,7 +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

@@ -1117,8 +1117,8 @@ 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

compute/patches/rum.patch

@@ -7,7 +7,7 @@ index 255e616..1c6edb7 100644
  			 RelationGetRelationName(index));
  
 +#ifdef NEON_SMGR
-+	smgr_start_unlogged_build(RelationGetSmgr(index));
++	smgr_start_unlogged_build(index->rd_smgr);
 +#endif
 +
  	initRumState(&buildstate.rumstate, index);
@@ -18,7 +18,7 @@ index 255e616..1c6edb7 100644
  	rumUpdateStats(index, &buildstate.buildStats, buildstate.rumstate.isBuild);
  
 +#ifdef NEON_SMGR
-+	smgr_finish_unlogged_build_phase_1(RelationGetSmgr(index));
++	smgr_finish_unlogged_build_phase_1(index->rd_smgr);
 +#endif
 +
  	/*
@@ -29,7 +29,7 @@ index 255e616..1c6edb7 100644
  	}
  
 +#ifdef NEON_SMGR
-+	smgr_end_unlogged_build(RelationGetSmgr(index));
++	smgr_end_unlogged_build(index->rd_smgr);
 +#endif
 +
  	/*

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/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/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

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/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>

endpoint_storage/src/app.rs

@@ -462,8 +462,6 @@ MC4CAQAwBQYDK2VwBCIEID/Drmc1AA6U/znNRWpF3zEGegOATQxfkdWxitcOMsIH
         if var(REAL_S3_ENV).is_ok() {
             assert!(body.contains("remote_storage_s3_deleted_objects_total"));
         }
-
-        #[cfg(target_os = "linux")]
         assert!(body.contains("process_threads"));
     }
 

libs/neon-shmem/Cargo.toml

@@ -1,13 +0,0 @@
-[package]
-name = "neon-shmem"
-version = "0.1.0"
-edition.workspace = true
-license.workspace = true
-
-[dependencies]
-thiserror.workspace = true
-nix.workspace=true
-workspace_hack = { version = "0.1", path = "../../workspace_hack" }
-
-[target.'cfg(target_os = "macos")'.dependencies]
-tempfile = "3.14.0"

libs/neon-shmem/src/lib.rs

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

libs/pageserver_api/src/config.rs

@@ -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,
@@ -1866,7 +1851,15 @@ pub mod virtual_file {
 
     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 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.
+            static ENV_OVERRIDE: LazyLock<Option<IoMode>> = LazyLock::new(|| {
+                utils::env::var_serde_json_string("NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IO_MODE")
+            });
+            ENV_OVERRIDE.unwrap_or(IoMode::DirectRw)
         }
     }
 

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/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/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/page_api/Cargo.toml

@@ -1,13 +0,0 @@
-[package]
-name = "pageserver_page_api"
-version = "0.1.0"
-edition.workspace = true
-license.workspace = true
-
-[dependencies]
-prost.workspace = true
-tonic.workspace = true
-workspace_hack.workspace = true
-
-[build-dependencies]
-tonic-build.workspace = true

pageserver/page_api/build.rs

@@ -1,13 +0,0 @@
-use std::env;
-use std::path::PathBuf;
-
-/// Generates Rust code from .proto Protobuf schemas, along with a binary file
-/// descriptor set for Protobuf schema reflection.
-fn main() -> Result<(), Box<dyn std::error::Error>> {
-    let out_dir = PathBuf::from(env::var("OUT_DIR")?);
-    tonic_build::configure()
-        .bytes(["."])
-        .file_descriptor_set_path(out_dir.join("page_api_descriptor.bin"))
-        .compile_protos(&["proto/page_service.proto"], &["proto"])
-        .map_err(|err| err.into())
-}

pageserver/page_api/proto/page_service.proto

@@ -1,233 +0,0 @@
-// Page service, presented by pageservers for computes.
-//
-// This is the compute read path. It primarily serves page versions at given
-// LSNs, but also base backups, SLRU segments, and relation metadata.
-//
-// EXPERIMENTAL: this is still under development and subject to change.
-//
-// Request metadata headers:
-// - authorization: JWT token ("Bearer <token>"), if auth is enabled
-// - neon-tenant-id: tenant ID ("7c4a1f9e3bd6470c8f3e21a65bd2e980")
-// - neon-shard-id: shard ID, as <number><count> in hex ("0b10" = shard 11 of 16, 0-based)
-// - neon-timeline-id: timeline ID ("f08c4e9a2d5f76b1e3a7c2d8910f4b3e")
-//
-// The service can be accessed via e.g. grpcurl:
-//
-//    ```
-//    grpcurl \
-//      -plaintext \
-//      -H "neon-tenant-id: 7c4a1f9e3bd6470c8f3e21a65bd2e980" \
-//      -H "neon-shard-id: 0b10" \
-//      -H "neon-timeline-id: f08c4e9a2d5f76b1e3a7c2d8910f4b3e" \
-//      -H "authorization: Bearer $JWT" \
-//      -d '{"read_lsn": {"request_lsn": 1234567890}, "rel": {"spc_oid": 1663, "db_oid": 1234, "rel_number": 5678, "fork_number": 0}}'
-//      localhost:51051 page_api.PageService/CheckRelExists
-//    ```
-//
-// TODO: consider adding neon-compute-mode ("primary", "static", "replica").
-// However, this will require reconnecting when changing modes.
-//
-// TODO: write implementation guidance on
-// - Health checks
-// - Tracing, OpenTelemetry
-// - Compression
-
-syntax = "proto3";
-package page_api;
-
-service PageService {
-  // Returns whether a relation exists.
-  rpc CheckRelExists(CheckRelExistsRequest) returns (CheckRelExistsResponse);
-
-  // Fetches a base backup.
-  rpc GetBaseBackup (GetBaseBackupRequest) returns (stream GetBaseBackupResponseChunk);
-
-  // Returns the total size of a database, as # of bytes.
-  rpc GetDbSize (GetDbSizeRequest) returns (GetDbSizeResponse);
-
-  // Fetches pages.
-  //
-  // This is implemented as a bidirectional streaming RPC for performance. Unary
-  // requests incur costs for e.g. HTTP/2 stream setup, header parsing,
-  // authentication, and so on -- with streaming, we only pay these costs during
-  // the initial stream setup. This ~doubles throughput in benchmarks. Other
-  // RPCs use regular unary requests, since they are not as frequent and
-  // performance-critical, and this simplifies implementation.
-  //
-  // NB: a status response (e.g. errors) will terminate the stream. The stream
-  // may be shared by e.g. multiple Postgres backends, so we should avoid this.
-  // Most errors are therefore sent as GetPageResponse.status instead.
-  rpc GetPages (stream GetPageRequest) returns (stream GetPageResponse);
-
-  // Returns the size of a relation, as # of blocks.
-  rpc GetRelSize (GetRelSizeRequest) returns (GetRelSizeResponse);
-
-  // Fetches an SLRU segment.
-  rpc GetSlruSegment (GetSlruSegmentRequest) returns (GetSlruSegmentResponse);
-}
-
-// The LSN a request should read at.
-message ReadLsn {
-  // The request's read LSN. Required.
-  uint64 request_lsn = 1;
-  // If given, the caller guarantees that the page has not been modified since
-  // this LSN. Must be smaller than or equal to request_lsn. This allows the
-  // Pageserver to serve an old page without waiting for the request LSN to
-  // arrive. Valid for all request types.
-  //
-  // It is undefined behaviour to make a request such that the page was, in
-  // fact, modified between request_lsn and not_modified_since_lsn. The
-  // Pageserver might detect it and return an error, or it might return the old
-  // page version or the new page version. Setting not_modified_since_lsn equal
-  // to request_lsn is always safe, but can lead to unnecessary waiting.
-  uint64 not_modified_since_lsn = 2;
-}
-
-// A relation identifier.
-message RelTag {
-    uint32 spc_oid = 1;
-    uint32 db_oid = 2;
-    uint32 rel_number = 3;
-    uint32 fork_number = 4;
-}
-
-// Checks whether a relation exists, at the given LSN. Only valid on shard 0,
-// other shards will error.
-message CheckRelExistsRequest {
-  ReadLsn read_lsn = 1;
-  RelTag rel = 2;
-}
-
-message CheckRelExistsResponse {
-  bool exists = 1;
-}
-
-// Requests a base backup at a given LSN.
-message GetBaseBackupRequest {
-  // The LSN to fetch a base backup at.
-  ReadLsn read_lsn = 1;
-  // If true, logical replication slots will not be created.
-  bool replica = 2;
-}
-
-// Base backup response chunk, returned as an ordered stream.
-message GetBaseBackupResponseChunk {
-  // A basebackup data chunk. The size is undefined, but bounded by the 4 MB
-  // gRPC message size limit.
-  bytes chunk = 1;
-}
-
-// Requests the size of a database, as # of bytes. Only valid on shard 0, other
-// shards will error.
-message GetDbSizeRequest {
-  ReadLsn read_lsn = 1;
-  uint32 db_oid = 2;
-}
-
-message GetDbSizeResponse {
-  uint64 num_bytes = 1;
-}
-
-// Requests one or more pages.
-message GetPageRequest {
-  // A request ID. Will be included in the response. Should be unique for
-  // in-flight requests on the stream.
-  uint64 request_id = 1;
-  // The request class.
-  GetPageClass request_class = 2;
-  // The LSN to read at.
-  ReadLsn read_lsn = 3;
-  // The relation to read from.
-  RelTag rel = 4;
-  // Page numbers to read. Must belong to the remote shard.
-  //
-  // Multiple pages will be executed as a single batch by the Pageserver,
-  // amortizing layer access costs and parallelizing them. This may increase the
-  // latency of any individual request, but improves the overall latency and
-  // throughput of the batch as a whole.
-  //
-  // TODO: this causes an allocation in the common single-block case. The sender
-  // can use a SmallVec to stack-allocate it, but Prost will always deserialize
-  // into a heap-allocated Vec. Consider optimizing this.
-  //
-  // TODO: we might be able to avoid a sort or something if we mandate that these
-  // are always in order. But we can't currenly rely on this on the server, because
-  // of compatibility with the libpq protocol handler.
-  repeated uint32 block_number = 5;
-}
-
-// A GetPageRequest class. Primarily intended for observability, but may also be
-// used for prioritization in the future.
-enum GetPageClass {
-  // Unknown class. For forwards compatibility: used when the client sends a
-  // class that the server doesn't know about.
-  GET_PAGE_CLASS_UNKNOWN = 0;
-  // A normal request. This is the default.
-  GET_PAGE_CLASS_NORMAL = 1;
-  // A prefetch request. NB: can only be classified on pg < 18.
-  GET_PAGE_CLASS_PREFETCH = 2;
-  // A background request (e.g. vacuum).
-  GET_PAGE_CLASS_BACKGROUND = 3;
-}
-
-// A GetPage response.
-//
-// A batch response will contain all of the requested pages. We could eagerly
-// emit individual pages as soon as they are ready, but on a readv() Postgres
-// holds buffer pool locks on all pages in the batch and we'll only return once
-// the entire batch is ready, so no one can make use of the individual pages.
-message GetPageResponse {
-  // The original request's ID.
-  uint64 request_id = 1;
-  // The response status code.
-  GetPageStatus status = 2;
-  // A string describing the status, if any.
-  string reason = 3;
-  // The 8KB page images, in the same order as the request. Empty if status != OK.
-  repeated bytes page_image = 4;
-}
-
-// A GetPageResponse status code. Since we use a bidirectional stream, we don't
-// want to send errors as gRPC statuses, since this would terminate the stream.
-enum GetPageStatus {
-  // Unknown status. For forwards compatibility: used when the server sends a
-  // status code that the client doesn't know about.
-  GET_PAGE_STATUS_UNKNOWN = 0;
-  // The request was successful.
-  GET_PAGE_STATUS_OK = 1;
-  // The page did not exist. The tenant/timeline/shard has already been
-  // validated during stream setup.
-  GET_PAGE_STATUS_NOT_FOUND = 2;
-  // The request was invalid.
-  GET_PAGE_STATUS_INVALID = 3;
-  // The tenant is rate limited. Slow down and retry later.
-  GET_PAGE_STATUS_SLOW_DOWN = 4;
-  // TODO: consider adding a GET_PAGE_STATUS_LAYER_DOWNLOAD in the case of a
-  // layer download. This could free up the server task to process other
-  // requests while the layer download is in progress.
-}
-
-// Fetches the size of a relation at a given LSN, as # of blocks. Only valid on
-// shard 0, other shards will error.
-message GetRelSizeRequest {
-  ReadLsn read_lsn = 1;
-  RelTag rel = 2;
-}
-
-message GetRelSizeResponse {
-  uint32 num_blocks = 1;
-}
-
-// Requests an SLRU segment. Only valid on shard 0, other shards will error.
-message GetSlruSegmentRequest {
-  ReadLsn read_lsn = 1;
-  uint32 kind = 2;
-  uint32 segno = 3;
-}
-
-// Returns an SLRU segment.
-//
-// These are up 32 pages (256 KB), so we can send them as a single response.
-message GetSlruSegmentResponse {
-  bytes segment = 1;
-}

pageserver/page_api/src/lib.rs

@@ -1,19 +0,0 @@
-//! This crate provides the Pageserver's page API. It contains:
-//!
-//! * proto/page_service.proto: the Protobuf schema for the page API.
-//! * proto: auto-generated Protobuf types for gRPC.
-//!
-//! This crate is used by both the client and the server. Try to keep it slim.
-
-// Code generated by protobuf.
-pub mod proto {
-    tonic::include_proto!("page_api");
-
-    /// File descriptor set for Protobuf schema reflection. This allows using
-    /// e.g. grpcurl with the API.
-    pub const FILE_DESCRIPTOR_SET: &[u8] =
-        tonic::include_file_descriptor_set!("page_api_descriptor");
-
-    pub use page_service_client::PageServiceClient;
-    pub use page_service_server::{PageService, PageServiceServer};
-}

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/page_service.rs

@@ -1278,7 +1278,7 @@ impl PageServerHandler {
     }
 
     #[instrument(level = tracing::Level::DEBUG, skip_all)]
-    async fn pagestream_handle_batched_message<IO>(
+    async fn pagesteam_handle_batched_message<IO>(
         &mut self,
         pgb_writer: &mut PostgresBackend<IO>,
         batch: BatchedFeMessage,
@@ -1733,7 +1733,7 @@ impl PageServerHandler {
             };
 
             let result = self
-                .pagestream_handle_batched_message(
+                .pagesteam_handle_batched_message(
                     pgb_writer,
                     msg,
                     io_concurrency.clone(),
@@ -1909,7 +1909,7 @@ impl PageServerHandler {
                             return Err(e);
                         }
                     };
-                    self.pagestream_handle_batched_message(
+                    self.pagesteam_handle_batched_message(
                         pgb_writer,
                         batch,
                         io_concurrency.clone(),

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

@@ -3435,7 +3435,6 @@ 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
@@ -3612,16 +3611,12 @@ 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 {
+                if accumulated_values.len() >= 65536 {
+                    // Assume all of them are images, that would be 512MB of data in memory for a single key.
                     return Err(CompactionError::Other(anyhow!(
-                        "too many values for a single key: {} for key {}, {} items",
-                        accumulated_values_estimated_size,
-                        key,
-                        accumulated_values.len()
+                        "too many values for a single key, giving up gc-compaction"
                     )));
                 }
             } else {
@@ -3656,7 +3651,6 @@ 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

@@ -408,7 +408,7 @@ 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.

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)
+        }
     }
 }
 

pgxn/neon/file_cache.c

@@ -936,44 +936,6 @@ lfc_prewarm_main(Datum main_arg)
 	lfc_ctl->prewarm_workers[worker_id].completed = GetCurrentTimestamp();
 }
 
-void
-lfc_invalidate(NRelFileInfo rinfo, ForkNumber forkNum, BlockNumber nblocks)
-{
-	BufferTag	tag;
-	FileCacheEntry *entry;
-	uint32		hash;
-
-	if (lfc_maybe_disabled())	/* fast exit if file cache is disabled */
-		return;
-
-	CopyNRelFileInfoToBufTag(tag, rinfo);
-	tag.forkNum = forkNum;
-
-	CriticalAssert(BufTagGetRelNumber(&tag) != InvalidRelFileNumber);
-
-	LWLockAcquire(lfc_lock, LW_EXCLUSIVE);
-	if (LFC_ENABLED())
-	{
-		for (BlockNumber blkno = 0; blkno < nblocks; blkno += lfc_blocks_per_chunk)
-		{
-			tag.blockNum = blkno;
-			hash = get_hash_value(lfc_hash, &tag);
-			entry = hash_search_with_hash_value(lfc_hash, &tag, hash, HASH_FIND, NULL);
-			if (entry != NULL)
-			{
-				for (int i = 0; i < lfc_blocks_per_chunk; i++)
-				{
-					if (GET_STATE(entry, i) == AVAILABLE)
-					{
-						lfc_ctl->used_pages -= 1;
-						SET_STATE(entry, i, UNAVAILABLE);
-					}
-				}
-			}
-		}
-	}
-	LWLockRelease(lfc_lock);
-}
 
 /*
  * Check if page is present in the cache.

pgxn/neon/file_cache.h

@@ -28,7 +28,6 @@ typedef struct FileCacheState
 extern bool lfc_store_prefetch_result;
 
 /* functions for local file cache */
-extern void lfc_invalidate(NRelFileInfo rinfo, ForkNumber forkNum, BlockNumber nblocks);
 extern void lfc_writev(NRelFileInfo rinfo, ForkNumber forkNum,
 					   BlockNumber blkno, const void *const *buffers,
 					   BlockNumber nblocks);

pgxn/neon/neon_pgversioncompat.h

@@ -86,7 +86,7 @@ InitBufferTag(BufferTag *tag, const RelFileNode *rnode,
 
 #define InvalidRelFileNumber InvalidOid
 
-#define SMgrRelGetRelInfo(reln)				\
+#define SMgrRelGetRelInfo(reln) \
 	(reln->smgr_rnode.node)
 
 #define DropRelationAllLocalBuffers DropRelFileNodeAllLocalBuffers
@@ -148,12 +148,6 @@ InitBufferTag(BufferTag *tag, const RelFileNode *rnode,
 #define DropRelationAllLocalBuffers DropRelationAllLocalBuffers
 #endif
 
-#define NRelFileInfoInvalidate(rinfo) do { \
-		NInfoGetSpcOid(rinfo) = InvalidOid; \
-		NInfoGetDbOid(rinfo) = InvalidOid; \
-		NInfoGetRelNumber(rinfo) = InvalidRelFileNumber; \
-	} while (0)
-
 #if PG_MAJORVERSION_NUM < 17
 #define ProcNumber BackendId
 #define INVALID_PROC_NUMBER InvalidBackendId

pgxn/neon/pagestore_smgr.c

@@ -108,7 +108,7 @@ typedef enum
 	UNLOGGED_BUILD_NOT_PERMANENT
 } UnloggedBuildPhase;
 
-static NRelFileInfo unlogged_build_rel_info;
+static SMgrRelation unlogged_build_rel = NULL;
 static UnloggedBuildPhase unlogged_build_phase = UNLOGGED_BUILD_NOT_IN_PROGRESS;
 
 static bool neon_redo_read_buffer_filter(XLogReaderState *record, uint8 block_id);
@@ -912,19 +912,16 @@ neon_extend(SMgrRelation reln, ForkNumber forkNum, BlockNumber blkno,
 	{
 		case 0:
 			neon_log(ERROR, "cannot call smgrextend() on rel with unknown persistence");
-			break;
 
 		case RELPERSISTENCE_PERMANENT:
-			if (RelFileInfoEquals(unlogged_build_rel_info, InfoFromSMgrRel(reln)))
-			{
-				mdextend(reln, forkNum, blkno, buffer, skipFsync);
-				return;
-			}
 			break;
 
 		case RELPERSISTENCE_TEMP:
 		case RELPERSISTENCE_UNLOGGED:
 			mdextend(reln, forkNum, blkno, buffer, skipFsync);
+			/* Update LFC in case of unlogged index build */
+			if (reln == unlogged_build_rel && unlogged_build_phase == UNLOGGED_BUILD_PHASE_2)
+				lfc_write(InfoFromSMgrRel(reln), forkNum, blkno, buffer);
 			return;
 
 		default:
@@ -1006,19 +1003,21 @@ neon_zeroextend(SMgrRelation reln, ForkNumber forkNum, BlockNumber blocknum,
 	{
 		case 0:
 			neon_log(ERROR, "cannot call smgrextend() on rel with unknown persistence");
-			break;
 
 		case RELPERSISTENCE_PERMANENT:
-			if (RelFileInfoEquals(unlogged_build_rel_info, InfoFromSMgrRel(reln)))
-			{
-				mdzeroextend(reln, forkNum, blocknum, nblocks, skipFsync);
-				return;
-			}
 			break;
 
 		case RELPERSISTENCE_TEMP:
 		case RELPERSISTENCE_UNLOGGED:
 			mdzeroextend(reln, forkNum, blocknum, nblocks, skipFsync);
+			/* Update LFC in case of unlogged index build */
+			if (reln == unlogged_build_rel && unlogged_build_phase == UNLOGGED_BUILD_PHASE_2)
+			{
+				for (int i = 0; i < nblocks; i++)
+				{
+					lfc_write(InfoFromSMgrRel(reln), forkNum, blocknum + i, buffer.data);
+				}
+			}
 			return;
 
 		default:
@@ -1282,24 +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();
+
+	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();
+
+#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);
@@ -1363,111 +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");
-			break;
-
-		case RELPERSISTENCE_PERMANENT:
-			if (RelFileInfoEquals(unlogged_build_rel_info, InfoFromSMgrRel(reln)))
-			{
-				mdread(reln, forkNum, blkno, buffer);
-				return;
-			}
-			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)
@@ -1481,14 +1431,8 @@ neon_readv(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 	{
 		case 0:
 			neon_log(ERROR, "cannot call smgrread() on rel with unknown persistence");
-			break;
 
 		case RELPERSISTENCE_PERMANENT:
-			if (RelFileInfoEquals(unlogged_build_rel_info, InfoFromSMgrRel(reln)))
-			{
-				mdreadv(reln, forknum, blocknum, buffers, nblocks);
-				return;
-			}
 			break;
 
 		case RELPERSISTENCE_TEMP:
@@ -1516,13 +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,
@@ -1531,14 +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);
@@ -1549,8 +1483,91 @@ neon_readv(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 	communicator_prefetch_pump_state();
 
 #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
@@ -1621,15 +1638,6 @@ neon_write(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, const vo
 			break;
 
 		case RELPERSISTENCE_PERMANENT:
-			if (RelFileInfoEquals(unlogged_build_rel_info, InfoFromSMgrRel(reln)))
-			{
-#if PG_MAJORVERSION_NUM >= 17
-				mdwritev(reln, forknum, blocknum, &buffer, 1, skipFsync);
-#else
-				mdwrite(reln, forknum, blocknum, buffer, skipFsync);
-#endif
-				return;
-			}
 			break;
 
 		case RELPERSISTENCE_TEMP:
@@ -1639,6 +1647,9 @@ neon_write(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum, const vo
 			#else
 			mdwrite(reln, forknum, blocknum, buffer, skipFsync);
 			#endif
+			/* Update LFC in case of unlogged index build */
+			if (reln == unlogged_build_rel && unlogged_build_phase == UNLOGGED_BUILD_PHASE_2)
+				lfc_write(InfoFromSMgrRel(reln), forknum, blocknum, buffer);
 			return;
 		default:
 			neon_log(ERROR, "unknown relpersistence '%c'", reln->smgr_relpersistence);
@@ -1699,16 +1710,14 @@ neon_writev(SMgrRelation reln, ForkNumber forknum, BlockNumber blkno,
 			break;
 
 		case RELPERSISTENCE_PERMANENT:
-			if (RelFileInfoEquals(unlogged_build_rel_info, InfoFromSMgrRel(reln)))
-			{
-				mdwritev(reln, forknum, blkno, buffers, nblocks, skipFsync);
-				return;
-			}
 			break;
 
 		case RELPERSISTENCE_TEMP:
 		case RELPERSISTENCE_UNLOGGED:
 			mdwritev(reln, forknum, blkno, buffers, nblocks, skipFsync);
+			/* Update LFC in case of unlogged index build */
+			if (reln == unlogged_build_rel && unlogged_build_phase == UNLOGGED_BUILD_PHASE_2)
+				lfc_writev(InfoFromSMgrRel(reln), forknum, blkno, buffers, nblocks);
 			return;
 		default:
 			neon_log(ERROR, "unknown relpersistence '%c'", reln->smgr_relpersistence);
@@ -1744,10 +1753,6 @@ neon_nblocks(SMgrRelation reln, ForkNumber forknum)
 			break;
 
 		case RELPERSISTENCE_PERMANENT:
-			if (RelFileInfoEquals(unlogged_build_rel_info, InfoFromSMgrRel(reln)))
-			{
-				return mdnblocks(reln, forknum);
-			}
 			break;
 
 		case RELPERSISTENCE_TEMP:
@@ -1817,11 +1822,6 @@ neon_truncate(SMgrRelation reln, ForkNumber forknum, BlockNumber old_blocks, Blo
 			break;
 
 		case RELPERSISTENCE_PERMANENT:
-			if (RelFileInfoEquals(unlogged_build_rel_info, InfoFromSMgrRel(reln)))
-			{
-				mdtruncate(reln, forknum, old_blocks, nblocks);
-				return;
-			}
 			break;
 
 		case RELPERSISTENCE_TEMP:
@@ -1960,6 +1960,7 @@ neon_start_unlogged_build(SMgrRelation reln)
 	 */
 	if (unlogged_build_phase != UNLOGGED_BUILD_NOT_IN_PROGRESS)
 		neon_log(ERROR, "unlogged relation build is already in progress");
+	Assert(unlogged_build_rel == NULL);
 
 	ereport(SmgrTrace,
 			(errmsg(NEON_TAG "starting unlogged build of relation %u/%u/%u",
@@ -1976,7 +1977,7 @@ neon_start_unlogged_build(SMgrRelation reln)
 
 		case RELPERSISTENCE_TEMP:
 		case RELPERSISTENCE_UNLOGGED:
-			unlogged_build_rel_info = InfoFromSMgrRel(reln);
+			unlogged_build_rel = reln;
 			unlogged_build_phase = UNLOGGED_BUILD_NOT_PERMANENT;
 #ifdef DEBUG_COMPARE_LOCAL
 			if (!IsParallelWorker())
@@ -1997,9 +1998,12 @@ neon_start_unlogged_build(SMgrRelation reln)
 		neon_log(ERROR, "cannot perform unlogged index build, index is not empty ");
 #endif
 
-	unlogged_build_rel_info = InfoFromSMgrRel(reln);
+	unlogged_build_rel = reln;
 	unlogged_build_phase = UNLOGGED_BUILD_PHASE_1;
 
+	/* Make the relation look like it's unlogged */
+	reln->smgr_relpersistence = RELPERSISTENCE_UNLOGGED;
+
 	/*
 	 * Create the local file. In a parallel build, the leader is expected to
 	 * call this first and do it.
@@ -2026,16 +2030,17 @@ neon_start_unlogged_build(SMgrRelation reln)
 static void
 neon_finish_unlogged_build_phase_1(SMgrRelation reln)
 {
-	Assert(RelFileInfoEquals(unlogged_build_rel_info, InfoFromSMgrRel(reln)));
+	Assert(unlogged_build_rel == reln);
 
 	ereport(SmgrTrace,
 			(errmsg(NEON_TAG "finishing phase 1 of unlogged build of relation %u/%u/%u",
-					RelFileInfoFmt((unlogged_build_rel_info)))));
+					RelFileInfoFmt(InfoFromSMgrRel(reln)))));
 
 	if (unlogged_build_phase == UNLOGGED_BUILD_NOT_PERMANENT)
 		return;
 
 	Assert(unlogged_build_phase == UNLOGGED_BUILD_PHASE_1);
+	Assert(reln->smgr_relpersistence == RELPERSISTENCE_UNLOGGED);
 
 	/*
 	 * In a parallel build, (only) the leader process performs the 2nd
@@ -2043,7 +2048,7 @@ neon_finish_unlogged_build_phase_1(SMgrRelation reln)
 	 */
 	if (IsParallelWorker())
 	{
-		NRelFileInfoInvalidate(unlogged_build_rel_info);
+		unlogged_build_rel = NULL;
 		unlogged_build_phase = UNLOGGED_BUILD_NOT_IN_PROGRESS;
 	}
 	else
@@ -2064,11 +2069,11 @@ neon_end_unlogged_build(SMgrRelation reln)
 {
 	NRelFileInfoBackend rinfob = InfoBFromSMgrRel(reln);
 
-	Assert(RelFileInfoEquals(unlogged_build_rel_info, InfoFromSMgrRel(reln)));
+	Assert(unlogged_build_rel == reln);
 
 	ereport(SmgrTrace,
 			(errmsg(NEON_TAG "ending unlogged build of relation %u/%u/%u",
-					RelFileInfoFmt(unlogged_build_rel_info))));
+					RelFileInfoFmt(InfoFromNInfoB(rinfob)))));
 
 	if (unlogged_build_phase != UNLOGGED_BUILD_NOT_PERMANENT)
 	{
@@ -2076,6 +2081,7 @@ neon_end_unlogged_build(SMgrRelation reln)
 		BlockNumber nblocks;
 
 		Assert(unlogged_build_phase == UNLOGGED_BUILD_PHASE_2);
+		Assert(reln->smgr_relpersistence == RELPERSISTENCE_UNLOGGED);
 
 		/*
 		 * Update the last-written LSN cache.
@@ -2096,6 +2102,9 @@ neon_end_unlogged_build(SMgrRelation reln)
 								InfoFromNInfoB(rinfob),
 								MAIN_FORKNUM);
 
+		/* Make the relation look permanent again */
+		reln->smgr_relpersistence = RELPERSISTENCE_PERMANENT;
+
 		/* Remove local copy */
 		for (int forknum = 0; forknum <= MAX_FORKNUM; forknum++)
 		{
@@ -2104,8 +2113,6 @@ neon_end_unlogged_build(SMgrRelation reln)
 				 forknum);
 
 			forget_cached_relsize(InfoFromNInfoB(rinfob), forknum);
-			lfc_invalidate(InfoFromNInfoB(rinfob), forknum, nblocks);
-
 			mdclose(reln, forknum);
 #ifndef DEBUG_COMPARE_LOCAL
 			/* use isRedo == true, so that we drop it immediately */
@@ -2116,7 +2123,7 @@ neon_end_unlogged_build(SMgrRelation reln)
 		mdunlink(rinfob, INIT_FORKNUM, true);
 #endif
 	}
-	NRelFileInfoInvalidate(unlogged_build_rel_info);
+	unlogged_build_rel = NULL;
 	unlogged_build_phase = UNLOGGED_BUILD_NOT_IN_PROGRESS;
 }
 
@@ -2189,7 +2196,7 @@ AtEOXact_neon(XactEvent event, void *arg)
 			 * Forget about any build we might have had in progress. The local
 			 * file will be unlinked by smgrDoPendingDeletes()
 			 */
-			NRelFileInfoInvalidate(unlogged_build_rel_info);
+			unlogged_build_rel = NULL;
 			unlogged_build_phase = UNLOGGED_BUILD_NOT_IN_PROGRESS;
 			break;
 
@@ -2201,7 +2208,7 @@ AtEOXact_neon(XactEvent event, void *arg)
 		case XACT_EVENT_PRE_PREPARE:
 			if (unlogged_build_phase != UNLOGGED_BUILD_NOT_IN_PROGRESS)
 			{
-				NRelFileInfoInvalidate(unlogged_build_rel_info);
+				unlogged_build_rel = NULL;
 				unlogged_build_phase = UNLOGGED_BUILD_NOT_IN_PROGRESS;
 				ereport(ERROR,
 						(errcode(ERRCODE_INTERNAL_ERROR),

poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 2.1.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.1.2 and should not be changed by hand.
 
 [[package]]
 name = "aiohappyeyeballs"
@@ -1145,19 +1145,18 @@ dotenv = ["python-dotenv"]
 
 [[package]]
 name = "flask-cors"
-version = "6.0.0"
-description = "A Flask extension simplifying CORS support"
+version = "5.0.0"
+description = "A Flask extension adding a decorator for CORS support"
 optional = false
-python-versions = "<4.0,>=3.9"
+python-versions = "*"
 groups = ["main"]
 files = [
-    {file = "flask_cors-6.0.0-py3-none-any.whl", hash = "sha256:6332073356452343a8ccddbfec7befdc3fdd040141fe776ec9b94c262f058657"},
-    {file = "flask_cors-6.0.0.tar.gz", hash = "sha256:4592c1570246bf7beee96b74bc0adbbfcb1b0318f6ba05c412e8909eceec3393"},
+    {file = "Flask_Cors-5.0.0-py2.py3-none-any.whl", hash = "sha256:b9e307d082a9261c100d8fb0ba909eec6a228ed1b60a8315fd85f783d61910bc"},
+    {file = "flask_cors-5.0.0.tar.gz", hash = "sha256:5aadb4b950c4e93745034594d9f3ea6591f734bb3662e16e255ffbf5e89c88ef"},
 ]
 
 [package.dependencies]
-flask = ">=0.9"
-Werkzeug = ">=0.7"
+Flask = ">=0.9"
 
 [[package]]
 name = "frozenlist"

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/pg_sni_router.rs

@@ -383,25 +383,17 @@ async fn handle_client(
     info!("performing the proxy pass...");
 
     let res = match client {
-        Connection::Raw(mut c) => {
-            copy_bidirectional_client_compute(&mut tls_stream, &mut c, |_, _| {}).await
-        }
-        Connection::Tls(mut c) => {
-            copy_bidirectional_client_compute(&mut tls_stream, &mut c, |_, _| {}).await
-        }
+        Connection::Raw(mut c) => copy_bidirectional_client_compute(&mut tls_stream, &mut c).await,
+        Connection::Tls(mut c) => copy_bidirectional_client_compute(&mut tls_stream, &mut c).await,
     };
 
     match res {
-        Ok(()) => Ok(()),
-        Err(ErrorSource::Timeout(_)) => Err(anyhow!(
-            "timed out while gracefully shutting down the connection"
-        )),
+        Ok(_) => Ok(()),
         Err(ErrorSource::Client(err)) => Err(err).context("client"),
         Err(ErrorSource::Compute(err)) => Err(err).context("compute"),
     }
 }
 
-#[allow(clippy::large_enum_variant)]
 enum Connection {
     Raw(tokio::net::TcpStream),
     Tls(tokio_rustls::client::TlsStream<tokio::net::TcpStream>),

proxy/src/binary/proxy.rs

@@ -43,12 +43,11 @@ 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"))]
@@ -161,11 +160,8 @@ struct ProxyCliArgs {
     #[clap(long, default_values_t = RateBucketInfo::DEFAULT_REDIS_SET)]
     redis_rps_limit: Vec<RateBucketInfo>,
     /// Cancellation channel size (max queue size for redis kv client)
-    #[clap(long, default_value_t = 1024)]
+    #[clap(long, default_value = "1024")]
     cancellation_ch_size: usize,
-    /// Cancellation ops batch size for redis
-    #[clap(long, default_value_t = 8)]
-    cancellation_batch_size: usize,
     /// cache for `allowed_ips` (use `size=0` to disable)
     #[clap(long, default_value = config::CacheOptions::CACHE_DEFAULT_OPTIONS)]
     allowed_ips_cache: String,
@@ -545,12 +541,7 @@ pub async fn run() -> anyhow::Result<()> {
             if let Some(mut redis_kv_client) = redis_kv_client {
                 maintenance_tasks.spawn(async move {
                     redis_kv_client.try_connect().await?;
-                    handle_cancel_messages(
-                        &mut redis_kv_client,
-                        rx_cancel,
-                        args.cancellation_batch_size,
-                    )
-                    .await?;
+                    handle_cancel_messages(&mut redis_kv_client, rx_cancel).await?;
 
                     drop(redis_kv_client);
 
@@ -716,7 +707,7 @@ 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()?;
@@ -871,7 +862,7 @@ async fn configure_redis(
         ("irsa", _) => match (&args.redis_host, args.redis_port) {
             (Some(host), Some(port)) => Some(
                 ConnectionWithCredentialsProvider::new_with_credentials_provider(
-                    host.clone(),
+                    host.to_string(),
                     port,
                     elasticache::CredentialsProvider::new(
                         args.aws_region.clone(),

proxy/src/cancellation.rs

@@ -30,6 +30,8 @@ use crate::tls::postgres_rustls::MakeRustlsConnect;
 type IpSubnetKey = IpNet;
 
 const CANCEL_KEY_TTL: i64 = 1_209_600; // 2 weeks cancellation key expire time
+const REDIS_SEND_TIMEOUT: std::time::Duration = std::time::Duration::from_millis(10);
+const BATCH_SIZE: usize = 8;
 
 // Message types for sending through mpsc channel
 pub enum CancelKeyOp {
@@ -54,9 +56,11 @@ pub enum CancelKeyOp {
     },
 }
 
+type Callback = Box<dyn FnOnce(anyhow::Result<&[redis::Value]>) + Send>;
 pub struct Pipeline {
     inner: redis::Pipeline,
-    replies: Vec<CancelReplyOp>,
+    // vec![(number of commands, fn(values))]
+    replies: Vec<(usize, Callback)>,
 }
 
 impl Pipeline {
@@ -68,29 +72,36 @@ impl Pipeline {
     }
 
     async fn execute(&mut self, client: &mut RedisKVClient) {
-        let responses = self.replies.len();
-        let batch_size = self.inner.len();
+        let commands = self.inner.len();
+        let batch_size = self.replies.len();
 
         match client.query(&self.inner).await {
-            // for each reply, we expect that many values.
-            Ok(Value::Array(values)) if values.len() == responses => {
+            Ok(Value::Array(values)) if values.len() == commands => {
                 debug!(
-                    batch_size,
-                    responses, "successfully completed cancellation jobs",
+                    commands,
+                    batch_size, "successfully completed cancellation jobs",
                 );
-                for (value, reply) in std::iter::zip(values, self.replies.drain(..)) {
-                    reply.send_value(value);
+                let mut values = &*values;
+                for (n, resp) in self.replies.drain(..) {
+                    let (v, rest) = values.split_at(n);
+                    values = rest;
+                    resp(Ok(v));
                 }
             }
             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"));
+                error!(
+                    commands,
+                    batch_size,
+                    ?value,
+                    "unexpected redis return value"
+                );
+                for (_n, resp) in self.replies.drain(..) {
+                    resp(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}"));
+                for (_n, resp) in self.replies.drain(..) {
+                    resp(Err(anyhow!("could not send cmd to redis: {err}")));
                 }
             }
         }
@@ -99,20 +110,27 @@ impl Pipeline {
         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),
+    /// Add a batch of commands to the pipeline, and run the resp fn when they are all done.
+    ///
+    /// If multiple commands are provided, the response should be able to decode
+    /// all of the values. You can provide a tuple in that case.
+    fn add_commands<F, T, const N: usize>(&mut self, cmds: [Cmd; N], resp: F)
+    where
+        F: FnOnce(anyhow::Result<T>) + Send + 'static,
+        T: FromRedisValue,
+    {
+        for cmd in cmds {
+            self.inner.add_command(cmd);
         }
+        let reply = Box::new(move |res: anyhow::Result<&[redis::Value]>| {
+            let res = match res {
+                Ok(v) => T::from_redis_value(&redis::Value::Array(v.to_owned()))
+                    .context("could not parse value"),
+                Err(e) => Err(e),
+            };
+            resp(res);
+        });
+        self.replies.push((N, reply as Box<_>));
     }
 }
 
@@ -128,18 +146,30 @@ 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.add_commands(
+                    [Cmd::hset(&key, field, value), Cmd::expire(key, expire)],
+                    // ignore all results
+                    move |res: anyhow::Result<()>| {
+                        let _guard = _guard;
+                        if let Some(resp_tx) = resp_tx {
+                            if resp_tx.send(res).is_err() {
+                                tracing::debug!("could not send reply");
+                            }
+                        }
+                    },
+                );
             }
             CancelKeyOp::GetCancelData {
                 key,
                 resp_tx,
                 _guard,
             } => {
-                let reply = CancelReplyOp::GetCancelData { resp_tx, _guard };
-                pipe.add_command_with_reply(Cmd::hgetall(key), reply);
+                pipe.add_commands([Cmd::hgetall(key)], move |res| {
+                    let _guard = _guard;
+                    if resp_tx.send(res).is_err() {
+                        tracing::debug!("could not send reply");
+                    }
+                });
             }
             CancelKeyOp::RemoveCancelKey {
                 key,
@@ -147,79 +177,14 @@ 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);
-            }
-        }
-    }
-}
-
-// Message types for sending through mpsc channel
-pub enum CancelReplyOp {
-    StoreCancelKey {
-        resp_tx: oneshot::Sender<anyhow::Result<()>>,
-        _guard: CancelChannelSizeGuard<'static>,
-    },
-    GetCancelData {
-        resp_tx: oneshot::Sender<anyhow::Result<Vec<(String, String)>>>,
-        _guard: CancelChannelSizeGuard<'static>,
-    },
-    RemoveCancelKey {
-        resp_tx: oneshot::Sender<anyhow::Result<()>>,
-        _guard: CancelChannelSizeGuard<'static>,
-    },
-}
-
-impl CancelReplyOp {
-    fn send_err(self, e: anyhow::Error) {
-        match self {
-            CancelReplyOp::StoreCancelKey { resp_tx, _guard } => {
-                resp_tx
-                    .send(Err(e))
-                    .inspect_err(|_| tracing::debug!("could not send reply"))
-                    .ok();
-            }
-            CancelReplyOp::GetCancelData { resp_tx, _guard } => {
-                resp_tx
-                    .send(Err(e))
-                    .inspect_err(|_| tracing::debug!("could not send reply"))
-                    .ok();
-            }
-            CancelReplyOp::RemoveCancelKey { resp_tx, _guard } => {
-                resp_tx
-                    .send(Err(e))
-                    .inspect_err(|_| tracing::debug!("could not send reply"))
-                    .ok();
-            }
-        }
-    }
-
-    fn send_value(self, v: redis::Value) {
-        match self {
-            CancelReplyOp::StoreCancelKey { resp_tx, _guard } => {
-                let send =
-                    FromRedisValue::from_owned_redis_value(v).context("could not parse value");
-                resp_tx
-                    .send(send)
-                    .inspect_err(|_| tracing::debug!("could not send reply"))
-                    .ok();
-            }
-            CancelReplyOp::GetCancelData { resp_tx, _guard } => {
-                let send =
-                    FromRedisValue::from_owned_redis_value(v).context("could not parse value");
-                resp_tx
-                    .send(send)
-                    .inspect_err(|_| tracing::debug!("could not send reply"))
-                    .ok();
-            }
-            CancelReplyOp::RemoveCancelKey { resp_tx, _guard } => {
-                let send =
-                    FromRedisValue::from_owned_redis_value(v).context("could not parse value");
-                resp_tx
-                    .send(send)
-                    .inspect_err(|_| tracing::debug!("could not send reply"))
-                    .ok();
+                pipe.add_commands([Cmd::hdel(key, field)], move |res| {
+                    let _guard = _guard;
+                    if let Some(resp_tx) = resp_tx {
+                        if resp_tx.send(res).is_err() {
+                            tracing::debug!("could not send reply");
+                        }
+                    }
+                });
             }
         }
     }
@@ -229,13 +194,12 @@ impl CancelReplyOp {
 pub async fn handle_cancel_messages(
     client: &mut RedisKVClient,
     mut rx: mpsc::Receiver<CancelKeyOp>,
-    batch_size: usize,
 ) -> anyhow::Result<()> {
-    let mut batch = Vec::with_capacity(batch_size);
-    let mut pipeline = Pipeline::with_capacity(batch_size);
+    let mut batch = Vec::with_capacity(BATCH_SIZE);
+    let mut pipeline = Pipeline::with_capacity(BATCH_SIZE);
 
     loop {
-        if rx.recv_many(&mut batch, batch_size).await == 0 {
+        if rx.recv_many(&mut batch, BATCH_SIZE).await == 0 {
             warn!("shutting down cancellation queue");
             break Ok(());
         }
@@ -366,7 +330,8 @@ impl CancellationHandler {
             return Err(CancelError::InternalError);
         };
 
-        tx.try_send(op)
+        tx.send_timeout(op, REDIS_SEND_TIMEOUT)
+            .await
             .map_err(|e| {
                 tracing::warn!("failed to send GetCancelData for {key}: {e}");
             })
@@ -568,7 +533,7 @@ impl Session {
     }
 
     // Send the store key op to the cancellation handler and set TTL for the key
-    pub(crate) fn write_cancel_key(
+    pub(crate) async fn write_cancel_key(
         &self,
         cancel_closure: CancelClosure,
     ) -> Result<(), CancelError> {
@@ -594,14 +559,14 @@ impl Session {
             expire: CANCEL_KEY_TTL,
         };
 
-        let _ = tx.try_send(op).map_err(|e| {
+        let _ = tx.send_timeout(op, REDIS_SEND_TIMEOUT).await.map_err(|e| {
             let key = self.key;
             tracing::warn!("failed to send StoreCancelKey for {key}: {e}");
         });
         Ok(())
     }
 
-    pub(crate) fn remove_cancel_key(&self) -> Result<(), CancelError> {
+    pub(crate) async fn remove_cancel_key(&self) -> Result<(), CancelError> {
         let Some(tx) = &self.cancellation_handler.tx else {
             tracing::warn!("cancellation handler is not available");
             return Err(CancelError::InternalError);
@@ -617,7 +582,7 @@ impl Session {
                 .guard(RedisMsgKind::HDel),
         };
 
-        let _ = tx.try_send(op).map_err(|e| {
+        let _ = tx.send_timeout(op, REDIS_SEND_TIMEOUT).await.map_err(|e| {
             let key = self.key;
             tracing::warn!("failed to send RemoveCancelKey for {key}: {e}");
         });

proxy/src/console_redirect_proxy.rs

@@ -129,12 +129,6 @@ pub async fn task_main(
                     let _disconnect = ctx.log_connect();
                     match p.proxy_pass(&config.connect_to_compute).await {
                         Ok(()) => {}
-                        Err(ErrorSource::Timeout(_)) => {
-                            info!(
-                                ?session_id,
-                                "per-client task timed out while gracefully shutting down the connection"
-                            );
-                        }
                         Err(ErrorSource::Client(e)) => {
                             error!(
                                 ?session_id,
@@ -250,7 +244,9 @@ pub(crate) async fn handle_client<S: AsyncRead + AsyncWrite + Unpin>(
     let cancellation_handler_clone = Arc::clone(&cancellation_handler);
     let session = cancellation_handler_clone.get_key();
 
-    session.write_cancel_key(node.cancel_closure.clone())?;
+    session
+        .write_cancel_key(node.cancel_closure.clone())
+        .await?;
 
     prepare_client_connection(&node, *session.key(), &mut stream).await?;
 

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/metrics.rs

@@ -200,10 +200,8 @@ pub enum HttpDirection {
 #[derive(FixedCardinalityLabel, Copy, Clone)]
 #[label(singleton = "direction")]
 pub enum Direction {
-    #[label(rename = "tx")]
-    ComputeToClient,
-    #[label(rename = "rx")]
-    ClientToCompute,
+    Tx,
+    Rx,
 }
 
 #[derive(FixedCardinalityLabel, Clone, Copy, Debug)]

proxy/src/proxy/copy_bidirectional.rs

@@ -1,394 +1,313 @@
 use std::future::poll_fn;
 use std::io;
-use std::ops::Range;
 use std::pin::Pin;
 use std::task::{Context, Poll, ready};
-use std::time::Duration;
 
 use tokio::io::{AsyncRead, AsyncWrite, ReadBuf};
 use tracing::info;
 
-use crate::metrics::Direction;
+#[derive(Debug)]
+enum TransferState {
+    Running(CopyBuffer),
+    ShuttingDown(u64),
+    Done(u64),
+}
 
-const DISCONNECT_TIMEOUT: Duration = Duration::from_secs(10);
+#[derive(Debug)]
+pub(crate) enum ErrorDirection {
+    Read(io::Error),
+    Write(io::Error),
+}
 
-/// Mark a value as being unlikely.
-#[cold]
-#[inline(always)]
-fn cold<I>(i: I) -> I {
-    i
+impl ErrorSource {
+    fn from_client(err: ErrorDirection) -> ErrorSource {
+        match err {
+            ErrorDirection::Read(client) => Self::Client(client),
+            ErrorDirection::Write(compute) => Self::Compute(compute),
+        }
+    }
+    fn from_compute(err: ErrorDirection) -> ErrorSource {
+        match err {
+            ErrorDirection::Write(client) => Self::Client(client),
+            ErrorDirection::Read(compute) => Self::Compute(compute),
+        }
+    }
 }
 
 #[derive(Debug)]
 pub enum ErrorSource {
     Client(io::Error),
     Compute(io::Error),
-    Timeout(tokio::time::error::Elapsed),
 }
 
-impl ErrorSource {
-    fn read(dir: Direction, err: io::Error) -> Self {
-        match dir {
-            Direction::ComputeToClient => ErrorSource::Compute(err),
-            Direction::ClientToCompute => ErrorSource::Client(err),
-        }
-    }
-
-    fn write(dir: Direction, err: io::Error) -> Self {
-        match dir {
-            Direction::ComputeToClient => ErrorSource::Client(err),
-            Direction::ClientToCompute => ErrorSource::Compute(err),
+fn transfer_one_direction<A, B>(
+    cx: &mut Context<'_>,
+    state: &mut TransferState,
+    r: &mut A,
+    w: &mut B,
+) -> Poll<Result<u64, ErrorDirection>>
+where
+    A: AsyncRead + AsyncWrite + Unpin + ?Sized,
+    B: AsyncRead + AsyncWrite + Unpin + ?Sized,
+{
+    let mut r = Pin::new(r);
+    let mut w = Pin::new(w);
+    loop {
+        match state {
+            TransferState::Running(buf) => {
+                let count = ready!(buf.poll_copy(cx, r.as_mut(), w.as_mut()))?;
+                *state = TransferState::ShuttingDown(count);
+            }
+            TransferState::ShuttingDown(count) => {
+                ready!(w.as_mut().poll_shutdown(cx)).map_err(ErrorDirection::Write)?;
+                *state = TransferState::Done(*count);
+            }
+            TransferState::Done(count) => return Poll::Ready(Ok(*count)),
         }
     }
 }
 
+#[tracing::instrument(skip_all)]
 pub async fn copy_bidirectional_client_compute<Client, Compute>(
     client: &mut Client,
     compute: &mut Compute,
-    mut f: impl for<'a> FnMut(Direction, &'a [u8]),
-) -> Result<(), ErrorSource>
+) -> Result<(u64, u64), ErrorSource>
 where
     Client: AsyncRead + AsyncWrite + Unpin + ?Sized,
     Compute: AsyncRead + AsyncWrite + Unpin + ?Sized,
 {
-    let f = &mut f;
-    let mut client_to_compute = CopyBuffer::new(Direction::ClientToCompute);
-    let mut compute_to_client = CopyBuffer::new(Direction::ComputeToClient);
+    let mut client_to_compute = TransferState::Running(CopyBuffer::new());
+    let mut compute_to_client = TransferState::Running(CopyBuffer::new());
 
-    let mut client = Pin::new(client);
-    let mut compute = Pin::new(compute);
+    poll_fn(|cx| {
+        let mut client_to_compute_result =
+            transfer_one_direction(cx, &mut client_to_compute, client, compute)
+                .map_err(ErrorSource::from_client)?;
+        let mut compute_to_client_result =
+            transfer_one_direction(cx, &mut compute_to_client, compute, client)
+                .map_err(ErrorSource::from_compute)?;
 
-    // Initial copy hot path
-    let close_dir = poll_fn(|cx| -> Poll<Result<_, ErrorSource>> {
-        let copy1 = client_to_compute.poll_copy(cx, f, client.as_mut(), compute.as_mut())?;
-        let copy2 = compute_to_client.poll_copy(cx, f, compute.as_mut(), client.as_mut())?;
+        // TODO: 1 info log, with a enum label for close direction.
 
-        match (copy1, copy2) {
-            (Poll::Pending, Poll::Pending) => Poll::Pending,
-            (Poll::Ready(()), _) => Poll::Ready(Ok(client_to_compute.dir)),
-            (_, Poll::Ready(())) => Poll::Ready(Ok(compute_to_client.dir)),
+        // Early termination checks from compute to client.
+        if let TransferState::Done(_) = compute_to_client {
+            if let TransferState::Running(buf) = &client_to_compute {
+                info!("Compute is done, terminate client");
+                // Initiate shutdown
+                client_to_compute = TransferState::ShuttingDown(buf.amt);
+                client_to_compute_result =
+                    transfer_one_direction(cx, &mut client_to_compute, client, compute)
+                        .map_err(ErrorSource::from_client)?;
+            }
         }
+
+        // Early termination checks from client to compute.
+        if let TransferState::Done(_) = client_to_compute {
+            if let TransferState::Running(buf) = &compute_to_client {
+                info!("Client is done, terminate compute");
+                // Initiate shutdown
+                compute_to_client = TransferState::ShuttingDown(buf.amt);
+                compute_to_client_result =
+                    transfer_one_direction(cx, &mut compute_to_client, compute, client)
+                        .map_err(ErrorSource::from_compute)?;
+            }
+        }
+
+        // It is not a problem if ready! returns early ... (comment remains the same)
+        let client_to_compute = ready!(client_to_compute_result);
+        let compute_to_client = ready!(compute_to_client_result);
+
+        Poll::Ready(Ok((client_to_compute, compute_to_client)))
     })
-    .await?;
-
-    // initiate shutdown.
-    match close_dir {
-        Direction::ClientToCompute => {
-            info!("Client is done, terminate compute");
-
-            // we will never write anymore data to the client.
-            compute_to_client.filled = 0..0;
-
-            // make sure to shutdown the client conn.
-            compute_to_client.need_flush = true;
-        }
-        Direction::ComputeToClient => {
-            info!("Compute is done, terminate client");
-
-            // we will never write anymore data to the compute.
-            client_to_compute.filled = 0..0;
-
-            // make sure to shutdown the compute conn.
-            client_to_compute.need_flush = true;
-        }
-    }
-
-    // Finish sending the rest of the data to client/compute before shutting it down.
-    //
-    // Edge case:
-    // * peer has filled the TCP buffers and is blocking on a `write()`,
-    // * proxy has filled the TCP buffers and is waiting on a `write()`.
-    // Since no side is reading from the buffers, no progress will be made.
-    let shutdown = poll_fn(|cx| {
-        let res1 = client_to_compute.poll_empty(cx, compute.as_mut())?;
-        let res2 = compute_to_client.poll_empty(cx, client.as_mut())?;
-
-        if res1.is_ready() && res2.is_ready() {
-            Poll::Ready(Ok(()))
-        } else {
-            Poll::Pending
-        }
-    });
-
-    // We assume most peers will have enough buffer space so this issue doesn't arise, but we apply
-    // a timeout just in case.
-    //
-    // We could also update `poll_empty` to try and read the data, but I think this is not an edge case
-    // worth overcomplicating.
-    let res = tokio::time::timeout(DISCONNECT_TIMEOUT, shutdown).await;
-
-    match res {
-        Ok(res) => res,
-        Err(timeout) => Err(ErrorSource::Timeout(timeout)),
-    }
+    .await
 }
 
-const DEFAULT_BUF_SIZE: usize = 1024;
+#[derive(Debug)]
 pub(super) struct CopyBuffer {
-    dir: Direction,
+    read_done: bool,
     need_flush: bool,
-    filled: Range<usize>,
-    buf: [u8; DEFAULT_BUF_SIZE],
+    pos: usize,
+    cap: usize,
+    amt: u64,
+    buf: Box<[u8]>,
 }
+const DEFAULT_BUF_SIZE: usize = 1024;
 
 impl CopyBuffer {
-    pub(super) const fn new(dir: Direction) -> Self {
+    pub(super) fn new() -> Self {
         Self {
-            dir,
+            read_done: false,
             need_flush: false,
-            filled: 0..0,
-            buf: [0; DEFAULT_BUF_SIZE],
+            pos: 0,
+            cap: 0,
+            amt: 0,
+            buf: vec![0; DEFAULT_BUF_SIZE].into_boxed_slice(),
         }
     }
 
-    /// Returns Ready(Ok(())) when no more writes could progress, and the buffer has space to read.
-    #[inline(always)]
-    fn poll_write_loop<W>(
+    fn poll_fill_buf<R>(
         &mut self,
         cx: &mut Context<'_>,
-        mut writer: Pin<&mut W>,
-    ) -> Poll<Result<(), ErrorSource>>
-    where
-        W: AsyncWrite + ?Sized,
-    {
-        debug_assert!(!self.filled.is_empty());
-
-        loop {
-            let filled_buf = &self.buf[self.filled.clone()];
-            match writer.as_mut().poll_write(cx, filled_buf) {
-                Poll::Ready(Err(err)) => {
-                    return Poll::Ready(Err(ErrorSource::write(self.dir, cold(err))));
-                }
-                Poll::Ready(Ok(0)) => {
-                    let err =
-                        io::Error::new(io::ErrorKind::WriteZero, "write zero byte into writer");
-                    return Poll::Ready(Err(ErrorSource::write(self.dir, cold(err))));
-                }
-                Poll::Ready(Ok(i)) => {
-                    // update the write head.
-                    self.filled.start += i;
-                    self.need_flush = true;
-
-                    // we wrote some data, but the filled buffer might not be fully empty yet.
-                    if !self.filled.is_empty() {
-                        continue;
-                    }
-
-                    // the buffer is definitely empty. reset positions.
-                    self.filled = 0..0;
-                    break;
-                }
-                // While we couldn't write, we might be able to read.
-                Poll::Pending if self.filled.end < self.buf.len() => break,
-                // We couldn't write, and have no space to read. Just exit.
-                Poll::Pending => return Poll::Pending,
-            }
-        }
-
-        Poll::Ready(Ok(()))
-    }
-
-    /// Returns Ready(Ok((true))) when read returns EOF.
-    /// Returns Ready(Ok((false))) when read returns data.
-    #[inline(always)]
-    fn poll_read_once<R>(
-        &mut self,
-        cx: &mut Context<'_>,
-        f: &mut impl for<'a> FnMut(Direction, &'a [u8]),
         reader: Pin<&mut R>,
-    ) -> Poll<Result<bool, ErrorSource>>
+    ) -> Poll<io::Result<()>>
     where
         R: AsyncRead + ?Sized,
     {
-        debug_assert!(self.filled.end < self.buf.len());
-        let mut buf = ReadBuf::new(&mut self.buf[self.filled.end..]);
+        let me = &mut *self;
+        let mut buf = ReadBuf::new(&mut me.buf);
+        buf.set_filled(me.cap);
 
-        match reader.poll_read(cx, &mut buf) {
-            Poll::Ready(Ok(())) => {
-                let filled = buf.filled();
-                // no more data to read, switch to shutdown mode.
-                if filled.is_empty() {
-                    self.need_flush = true;
-                    return Poll::Ready(Ok(true));
-                }
-
-                // run our inspection callback.
-                f(self.dir, filled);
-
-                // update the read head.
-                self.filled.end += filled.len();
-
-                // read more data
-                Poll::Ready(Ok(false))
-            }
-            // cannot continue on error.
-            Poll::Ready(Err(e)) => Poll::Ready(Err(ErrorSource::read(self.dir, cold(e)))),
-            // No more data to read, and no more data to write.
-            Poll::Pending => Poll::Pending,
+        let res = reader.poll_read(cx, &mut buf);
+        if let Poll::Ready(Ok(())) = res {
+            let filled_len = buf.filled().len();
+            me.read_done = me.cap == filled_len;
+            me.cap = filled_len;
         }
+        res
     }
 
-    /// Returns Ready(Ok(())) when read returns EOF.
-    fn poll_copy<R, W>(
+    fn poll_write_buf<R, W>(
         &mut self,
         cx: &mut Context<'_>,
-        f: &mut impl for<'a> FnMut(Direction, &'a [u8]),
         mut reader: Pin<&mut R>,
         mut writer: Pin<&mut W>,
-    ) -> Poll<Result<(), ErrorSource>>
+    ) -> Poll<Result<usize, ErrorDirection>>
     where
         R: AsyncRead + ?Sized,
         W: AsyncWrite + ?Sized,
     {
-        // this register eliminates a branch in the hot loop.
-        let mut empty = self.filled.is_empty();
-
-        // write then read hot loop
-        loop {
-            if !empty {
-                ready!(self.poll_write_loop(cx, writer.as_mut())?);
-            }
-
-            // If empty is true, there is guaranteed space to read.
-            // If empty is false, and the write loop returned ready, then we know there's space for more reads.
-            match self.poll_read_once(cx, f, reader.as_mut())? {
-                // EOF
-                Poll::Ready(true) => return Poll::Ready(Ok(())),
-                // Needs write.
-                Poll::Ready(false) => empty = false,
-                // Cannot read. The peer might not send us anything until
-                // they receive data from us, so let's switch to flushing.
-                Poll::Pending => break,
+        let me = &mut *self;
+        match writer.as_mut().poll_write(cx, &me.buf[me.pos..me.cap]) {
+            Poll::Pending => {
+                // Top up the buffer towards full if we can read a bit more
+                // data - this should improve the chances of a large write
+                if !me.read_done && me.cap < me.buf.len() {
+                    ready!(me.poll_fill_buf(cx, reader.as_mut())).map_err(ErrorDirection::Read)?;
+                }
+                Poll::Pending
             }
+            res @ Poll::Ready(_) => res.map_err(ErrorDirection::Write),
         }
-
-        if self.need_flush {
-            let flush = writer.as_mut().poll_flush(cx);
-            ready!(flush.map_err(|e| ErrorSource::write(self.dir, e))?);
-            self.need_flush = false;
-        }
-
-        // there might be more data still to read.
-        Poll::Pending
     }
 
-    /// Returns Ready(Ok(())) when the conn is fully shutdown.
-    pub(super) fn poll_empty<W>(
+    pub(super) fn poll_copy<R, W>(
         &mut self,
         cx: &mut Context<'_>,
+        mut reader: Pin<&mut R>,
         mut writer: Pin<&mut W>,
-    ) -> Poll<Result<(), ErrorSource>>
+    ) -> Poll<Result<u64, ErrorDirection>>
     where
+        R: AsyncRead + ?Sized,
         W: AsyncWrite + ?Sized,
     {
-        if !self.filled.is_empty() {
-            ready!(self.poll_write_loop(cx, writer.as_mut())?);
+        loop {
+            // If there is some space left in our buffer, then we try to read some
+            // data to continue, thus maximizing the chances of a large write.
+            if self.cap < self.buf.len() && !self.read_done {
+                match self.poll_fill_buf(cx, reader.as_mut()) {
+                    Poll::Ready(Ok(())) => (),
+                    Poll::Ready(Err(err)) => return Poll::Ready(Err(ErrorDirection::Read(err))),
+                    Poll::Pending => {
+                        // Ignore pending reads when our buffer is not empty, because
+                        // we can try to write data immediately.
+                        if self.pos == self.cap {
+                            // Try flushing when the reader has no progress to avoid deadlock
+                            // when the reader depends on buffered writer.
+                            if self.need_flush {
+                                ready!(writer.as_mut().poll_flush(cx))
+                                    .map_err(ErrorDirection::Write)?;
+                                self.need_flush = false;
+                            }
 
-            if !self.filled.is_empty() {
-                // still some data to write
-                return Poll::Pending;
+                            return Poll::Pending;
+                        }
+                    }
+                }
+            }
+
+            // If our buffer has some data, let's write it out!
+            while self.pos < self.cap {
+                let i = ready!(self.poll_write_buf(cx, reader.as_mut(), writer.as_mut()))?;
+                if i == 0 {
+                    return Poll::Ready(Err(ErrorDirection::Write(io::Error::new(
+                        io::ErrorKind::WriteZero,
+                        "write zero byte into writer",
+                    ))));
+                }
+                self.pos += i;
+                self.amt += i as u64;
+                self.need_flush = true;
+            }
+
+            // If pos larger than cap, this loop will never stop.
+            // In particular, user's wrong poll_write implementation returning
+            // incorrect written length may lead to thread blocking.
+            debug_assert!(
+                self.pos <= self.cap,
+                "writer returned length larger than input slice"
+            );
+
+            // All data has been written, the buffer can be considered empty again
+            self.pos = 0;
+            self.cap = 0;
+
+            // If we've written all the data and we've seen EOF, flush out the
+            // data and finish the transfer.
+            if self.read_done {
+                ready!(writer.as_mut().poll_flush(cx)).map_err(ErrorDirection::Write)?;
+                return Poll::Ready(Ok(self.amt));
             }
         }
-
-        if self.need_flush {
-            let res = writer.poll_shutdown(cx);
-            ready!(res.map_err(|e| ErrorSource::write(self.dir, e))?);
-            self.need_flush = false;
-        }
-
-        // no data to read, no data to write.
-        Poll::Ready(Ok(()))
     }
 }
 
 #[cfg(test)]
 mod tests {
-    use tokio::io::{AsyncReadExt, AsyncWriteExt};
+    use tokio::io::AsyncWriteExt;
 
     use super::*;
 
     #[tokio::test]
     async fn test_client_to_compute() {
-        let (mut client, mut client_proxy) = tokio::io::duplex(32); // Create a mock duplex stream
-        let (mut proxy_compute, mut compute) = tokio::io::duplex(16); // Create a mock duplex stream
+        let (mut client_client, mut client_proxy) = tokio::io::duplex(8); // Create a mock duplex stream
+        let (mut compute_proxy, mut compute_client) = tokio::io::duplex(32); // Create a mock duplex stream
 
-        client.write_all(b"Neon Serverless Postgres").await.unwrap();
-        compute.write_all(b"is amazing").await.unwrap();
+        // Simulate 'a' finishing while there's still data for 'b'
+        client_client.write_all(b"hello").await.unwrap();
+        client_client.shutdown().await.unwrap();
+        compute_client.write_all(b"Neon").await.unwrap();
+        compute_client.shutdown().await.unwrap();
 
-        client.shutdown().await.unwrap();
-
-        let copy = tokio::spawn(async move {
-            copy_bidirectional_client_compute(&mut client_proxy, &mut proxy_compute, |_, _| {})
-                .await
-                .unwrap();
-        });
+        let result = copy_bidirectional_client_compute(&mut client_proxy, &mut compute_proxy)
+            .await
+            .unwrap();
 
         // Assert correct transferred amounts
-        let mut client_recv = String::new();
-        let mut compute_recv = String::new();
-
-        client.read_to_string(&mut client_recv).await.unwrap();
-        compute.read_to_string(&mut compute_recv).await.unwrap();
-
-        assert_eq!(compute_recv, "Neon Serverless Postgres");
-        assert_eq!(client_recv, "is amazing");
-
-        copy.await.unwrap();
+        let (client_to_compute_count, compute_to_client_count) = result;
+        assert_eq!(client_to_compute_count, 5); // 'hello' was transferred
+        assert_eq!(compute_to_client_count, 4); // response only partially transferred or not at all
     }
 
     #[tokio::test]
     async fn test_compute_to_client() {
-        let (mut client, mut client_proxy) = tokio::io::duplex(32); // Create a mock duplex stream
-        let (mut proxy_compute, mut compute) = tokio::io::duplex(16); // Create a mock duplex stream
+        let (mut client_client, mut client_proxy) = tokio::io::duplex(32); // Create a mock duplex stream
+        let (mut compute_proxy, mut compute_client) = tokio::io::duplex(8); // Create a mock duplex stream
 
-        client.write_all(b"Neon Serverless Postgres").await.unwrap();
-        compute.write_all(b"is amazing").await.unwrap();
+        // Simulate 'a' finishing while there's still data for 'b'
+        compute_client.write_all(b"hello").await.unwrap();
+        compute_client.shutdown().await.unwrap();
+        client_client
+            .write_all(b"Neon Serverless Postgres")
+            .await
+            .unwrap();
 
-        compute.shutdown().await.unwrap();
-
-        let copy = tokio::spawn(async move {
-            copy_bidirectional_client_compute(&mut client_proxy, &mut proxy_compute, |_, _| {})
-                .await
-                .unwrap();
-        });
+        let result = copy_bidirectional_client_compute(&mut client_proxy, &mut compute_proxy)
+            .await
+            .unwrap();
 
         // Assert correct transferred amounts
-        let mut client_recv = String::new();
-        let mut compute_recv = String::new();
-
-        client.read_to_string(&mut client_recv).await.unwrap();
-        compute.read_to_string(&mut compute_recv).await.unwrap();
-
-        assert_eq!(compute_recv, "Neon Serverless ");
-        assert_eq!(client_recv, "is amazing");
-
-        copy.await.unwrap();
-    }
-
-    #[tokio::test(start_paused = true)]
-    async fn test_timeout() {
-        let (mut client, mut client_proxy) = tokio::io::duplex(32); // Create a mock duplex stream
-        let (mut proxy_compute, mut compute) = tokio::io::duplex(16); // Create a mock duplex stream
-
-        // Try to send 24 bytes to compute, but compute only has space for 16 bytes.
-        // Writes will not succeed.
-        client.write_all(b"Neon Serverless Postgres").await.unwrap();
-        client.shutdown().await.unwrap();
-
-        let copy = tokio::spawn(async move {
-            copy_bidirectional_client_compute(&mut client_proxy, &mut proxy_compute, |_, _| {})
-                .await
-                .unwrap_err()
-        });
-
-        tokio::time::advance(DISCONNECT_TIMEOUT).await;
-
-        let res = copy.await.unwrap();
-        assert!(matches!(res, ErrorSource::Timeout(_)));
-
-        // Assert correct transferred amounts
-        let mut compute_recv = String::new();
-        compute.read_to_string(&mut compute_recv).await.unwrap();
-        assert_eq!(compute_recv, "Neon Serverless ");
+        let (client_to_compute_count, compute_to_client_count) = result;
+        assert_eq!(compute_to_client_count, 5); // 'hello' was transferred
+        assert!(client_to_compute_count <= 8); // response only partially transferred or not at all
     }
 }

proxy/src/proxy/mod.rs

@@ -167,12 +167,6 @@ pub async fn task_main(
                     let _disconnect = ctx.log_connect();
                     match p.proxy_pass(&config.connect_to_compute).await {
                         Ok(()) => {}
-                        Err(ErrorSource::Timeout(_)) => {
-                            info!(
-                                ?session_id,
-                                "per-client task timed out while gracefully shutting down the connection"
-                            );
-                        }
                         Err(ErrorSource::Client(e)) => {
                             warn!(
                                 ?session_id,
@@ -389,7 +383,9 @@ pub(crate) async fn handle_client<S: AsyncRead + AsyncWrite + Unpin>(
     let cancellation_handler_clone = Arc::clone(&cancellation_handler);
     let session = cancellation_handler_clone.get_key();
 
-    session.write_cancel_key(node.cancel_closure.clone())?;
+    session
+        .write_cancel_key(node.cancel_closure.clone())
+        .await?;
 
     prepare_client_connection(&node, *session.key(), &mut stream).await?;
 

proxy/src/proxy/passthrough.rs

@@ -1,6 +1,7 @@
 use smol_str::SmolStr;
 use tokio::io::{AsyncRead, AsyncWrite};
 use tracing::debug;
+use utils::measured_stream::MeasuredStream;
 
 use super::copy_bidirectional::ErrorSource;
 use crate::cancellation;
@@ -8,15 +9,14 @@ use crate::compute::PostgresConnection;
 use crate::config::ComputeConfig;
 use crate::control_plane::messages::MetricsAuxInfo;
 use crate::metrics::{Direction, Metrics, NumClientConnectionsGuard, NumConnectionRequestsGuard};
-use crate::proxy::copy_bidirectional_client_compute;
 use crate::stream::Stream;
 use crate::usage_metrics::{Ids, MetricCounterRecorder, USAGE_METRICS};
 
 /// Forward bytes in both directions (client <-> compute).
-#[tracing::instrument(level = "debug", skip_all)]
+#[tracing::instrument(skip_all)]
 pub(crate) async fn proxy_pass(
-    mut client: Stream<impl AsyncRead + AsyncWrite + Unpin>,
-    mut compute: impl AsyncRead + AsyncWrite + Unpin,
+    client: impl AsyncRead + AsyncWrite + Unpin,
+    compute: impl AsyncRead + AsyncWrite + Unpin,
     aux: MetricsAuxInfo,
     private_link_id: Option<SmolStr>,
 ) -> Result<(), ErrorSource> {
@@ -28,30 +28,37 @@ pub(crate) async fn proxy_pass(
     });
 
     let metrics = &Metrics::get().proxy.io_bytes;
-    let m_sent = metrics.with_labels(Direction::ComputeToClient);
-    let m_recv = metrics.with_labels(Direction::ClientToCompute);
+    let m_sent = metrics.with_labels(Direction::Tx);
+    let mut client = MeasuredStream::new(
+        client,
+        |_| {},
+        |cnt| {
+            // Number of bytes we sent to the client (outbound).
+            metrics.get_metric(m_sent).inc_by(cnt as u64);
+            usage_tx.record_egress(cnt as u64);
+        },
+    );
 
-    let inspect = |direction, bytes: &[u8]| match direction {
-        Direction::ComputeToClient => {
-            metrics.get_metric(m_sent).inc_by(bytes.len() as u64);
-            usage_tx.record_egress(bytes.len() as u64);
-        }
-        Direction::ClientToCompute => {
-            metrics.get_metric(m_recv).inc_by(bytes.len() as u64);
-            usage_tx.record_ingress(bytes.len() as u64);
-        }
-    };
+    let m_recv = metrics.with_labels(Direction::Rx);
+    let mut compute = MeasuredStream::new(
+        compute,
+        |_| {},
+        |cnt| {
+            // Number of bytes the client sent to the compute node (inbound).
+            metrics.get_metric(m_recv).inc_by(cnt as u64);
+            usage_tx.record_ingress(cnt as u64);
+        },
+    );
 
     // Starting from here we only proxy the client's traffic.
     debug!("performing the proxy pass...");
+    let _ = crate::proxy::copy_bidirectional::copy_bidirectional_client_compute(
+        &mut client,
+        &mut compute,
+    )
+    .await?;
 
-    // reduce branching internal to the hot path.
-    match &mut client {
-        Stream::Raw { raw } => copy_bidirectional_client_compute(raw, &mut compute, inspect).await,
-        Stream::Tls { tls, .. } => {
-            copy_bidirectional_client_compute(&mut *tls, &mut compute, inspect).await
-        }
-    }
+    Ok(())
 }
 
 pub(crate) struct ProxyPassthrough<S> {
@@ -87,7 +94,7 @@ impl<S: AsyncRead + AsyncWrite + Unpin> ProxyPassthrough<S> {
             tracing::warn!(session_id = ?self.session_id, ?err, "could not cancel the query in the database");
         }
 
-        drop(self.cancel.remove_cancel_key()); // we don't need a result. If the queue is full, we just log the error
+        drop(self.cancel.remove_cancel_key().await); // we don't need a result. If the queue is full, we just log the error
 
         res
     }

proxy/src/serverless/websocket.rs

@@ -2,7 +2,7 @@ use std::pin::Pin;
 use std::sync::Arc;
 use std::task::{Context, Poll, ready};
 
-use anyhow::{Context as _, anyhow};
+use anyhow::Context as _;
 use bytes::{Buf, BufMut, Bytes, BytesMut};
 use framed_websockets::{Frame, OpCode, WebSocketServer};
 use futures::{Sink, Stream};
@@ -169,9 +169,6 @@ pub(crate) async fn serve_websocket(
             ctx.log_connect();
             match p.proxy_pass(&config.connect_to_compute).await {
                 Ok(()) => Ok(()),
-                Err(ErrorSource::Timeout(_)) => Err(anyhow!(
-                    "timed out while gracefully shutting down the connection"
-                )),
                 Err(ErrorSource::Client(err)) => Err(err).context("client"),
                 Err(ErrorSource::Compute(err)) => Err(err).context("compute"),
             }

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)?;

safekeeper/src/lib.rs

@@ -125,6 +125,12 @@ pub struct SafeKeeperConf {
     pub enable_tls_wal_service_api: bool,
 }
 
+impl SafeKeeperConf {
+    pub fn is_wal_backup_enabled(&self) -> bool {
+        self.remote_storage.is_some() && self.wal_backup_enabled
+    }
+}
+
 impl SafeKeeperConf {
     pub fn dummy() -> Self {
         SafeKeeperConf {

safekeeper/src/pull_timeline.rs

@@ -9,7 +9,6 @@ use chrono::{DateTime, Utc};
 use futures::{SinkExt, StreamExt, TryStreamExt};
 use http_utils::error::ApiError;
 use postgres_ffi::{PG_TLI, XLogFileName, XLogSegNo};
-use remote_storage::GenericRemoteStorage;
 use reqwest::Certificate;
 use safekeeper_api::Term;
 use safekeeper_api::models::{PullTimelineRequest, PullTimelineResponse, TimelineStatus};
@@ -44,7 +43,6 @@ pub async fn stream_snapshot(
     source: NodeId,
     destination: NodeId,
     tx: mpsc::Sender<Result<Bytes>>,
-    storage: Option<Arc<GenericRemoteStorage>>,
 ) {
     match tli.try_wal_residence_guard().await {
         Err(e) => {
@@ -55,32 +53,10 @@ pub async fn stream_snapshot(
         Ok(maybe_resident_tli) => {
             if let Err(e) = match maybe_resident_tli {
                 Some(resident_tli) => {
-                    stream_snapshot_resident_guts(
-                        resident_tli,
-                        source,
-                        destination,
-                        tx.clone(),
-                        storage,
-                    )
-                    .await
-                }
-                None => {
-                    if let Some(storage) = storage {
-                        stream_snapshot_offloaded_guts(
-                            tli,
-                            source,
-                            destination,
-                            tx.clone(),
-                            &storage,
-                        )
+                    stream_snapshot_resident_guts(resident_tli, source, destination, tx.clone())
                         .await
-                    } else {
-                        tx.send(Err(anyhow!("remote storage not configured")))
-                            .await
-                            .ok();
-                        return;
-                    }
                 }
+                None => stream_snapshot_offloaded_guts(tli, source, destination, tx.clone()).await,
             } {
                 // Error type/contents don't matter as they won't can't reach the client
                 // (hyper likely doesn't do anything with it), but http stream will be
@@ -147,12 +123,10 @@ pub(crate) async fn stream_snapshot_offloaded_guts(
     source: NodeId,
     destination: NodeId,
     tx: mpsc::Sender<Result<Bytes>>,
-    storage: &GenericRemoteStorage,
 ) -> Result<()> {
     let mut ar = prepare_tar_stream(tx);
 
-    tli.snapshot_offloaded(&mut ar, source, destination, storage)
-        .await?;
+    tli.snapshot_offloaded(&mut ar, source, destination).await?;
 
     ar.finish().await?;
 
@@ -165,13 +139,10 @@ pub async fn stream_snapshot_resident_guts(
     source: NodeId,
     destination: NodeId,
     tx: mpsc::Sender<Result<Bytes>>,
-    storage: Option<Arc<GenericRemoteStorage>>,
 ) -> Result<()> {
     let mut ar = prepare_tar_stream(tx);
 
-    let bctx = tli
-        .start_snapshot(&mut ar, source, destination, storage)
-        .await?;
+    let bctx = tli.start_snapshot(&mut ar, source, destination).await?;
     pausable_failpoint!("sk-snapshot-after-list-pausable");
 
     let tli_dir = tli.get_timeline_dir();
@@ -211,7 +182,6 @@ impl Timeline {
         ar: &mut tokio_tar::Builder<W>,
         source: NodeId,
         destination: NodeId,
-        storage: &GenericRemoteStorage,
     ) -> Result<()> {
         // Take initial copy of control file, then release state lock
         let mut control_file = {
@@ -246,7 +216,6 @@ impl Timeline {
         // can fail if the timeline was un-evicted and modified in the background.
         let remote_timeline_path = &self.remote_path;
         wal_backup::copy_partial_segment(
-            storage,
             &replace.previous.remote_path(remote_timeline_path),
             &replace.current.remote_path(remote_timeline_path),
         )
@@ -293,7 +262,6 @@ impl WalResidentTimeline {
         ar: &mut tokio_tar::Builder<W>,
         source: NodeId,
         destination: NodeId,
-        storage: Option<Arc<GenericRemoteStorage>>,
     ) -> Result<SnapshotContext> {
         let mut shared_state = self.write_shared_state().await;
         let wal_seg_size = shared_state.get_wal_seg_size();
@@ -315,7 +283,6 @@ impl WalResidentTimeline {
 
             let remote_timeline_path = &self.tli.remote_path;
             wal_backup::copy_partial_segment(
-                &*storage.context("remote storage not configured")?,
                 &replace.previous.remote_path(remote_timeline_path),
                 &replace.current.remote_path(remote_timeline_path),
             )

safekeeper/src/send_wal.rs

@@ -513,7 +513,7 @@ impl SafekeeperPostgresHandler {
         let end_pos = end_watch.get();
 
         if end_pos < start_pos {
-            info!(
+            warn!(
                 "requested start_pos {} is ahead of available WAL end_pos {}",
                 start_pos, end_pos
             );

safekeeper/src/test_utils.rs

@@ -18,7 +18,7 @@ use crate::send_wal::EndWatch;
 use crate::state::{TimelinePersistentState, TimelineState};
 use crate::timeline::{SharedState, StateSK, Timeline, get_timeline_dir};
 use crate::timelines_set::TimelinesSet;
-use crate::wal_backup::{WalBackup, remote_timeline_path};
+use crate::wal_backup::remote_timeline_path;
 use crate::{SafeKeeperConf, control_file, receive_wal, wal_storage};
 
 /// A Safekeeper testing or benchmarking environment. Uses a tempdir for storage, removed on drop.
@@ -101,22 +101,18 @@ impl Env {
         let safekeeper = self.make_safekeeper(node_id, ttid, start_lsn).await?;
         let shared_state = SharedState::new(StateSK::Loaded(safekeeper));
 
-        let wal_backup = Arc::new(WalBackup::new(&conf).await?);
-
         let timeline = Timeline::new(
             ttid,
             &timeline_dir,
             &remote_path,
             shared_state,
             conf.clone(),
-            wal_backup.clone(),
         );
         timeline.bootstrap(
             &mut timeline.write_shared_state().await,
             &conf,
             Arc::new(TimelinesSet::default()), // ignored for now
             RateLimiter::new(0, 0),
-            wal_backup,
         );
         Ok(timeline)
     }

safekeeper/src/timeline.rs

@@ -35,8 +35,7 @@ use crate::state::{EvictionState, TimelineMemState, TimelinePersistentState, Tim
 use crate::timeline_guard::ResidenceGuard;
 use crate::timeline_manager::{AtomicStatus, ManagerCtl};
 use crate::timelines_set::TimelinesSet;
-use crate::wal_backup;
-use crate::wal_backup::{WalBackup, remote_timeline_path};
+use crate::wal_backup::{self, remote_timeline_path};
 use crate::wal_backup_partial::PartialRemoteSegment;
 use crate::wal_storage::{Storage as wal_storage_iface, WalReader};
 use crate::{SafeKeeperConf, control_file, debug_dump, timeline_manager, wal_storage};
@@ -453,8 +452,6 @@ pub struct Timeline {
     manager_ctl: ManagerCtl,
     conf: Arc<SafeKeeperConf>,
 
-    pub(crate) wal_backup: Arc<WalBackup>,
-
     remote_deletion: std::sync::Mutex<Option<RemoteDeletionReceiver>>,
 
     /// Hold this gate from code that depends on the Timeline's non-shut-down state.  While holding
@@ -479,7 +476,6 @@ impl Timeline {
         remote_path: &RemotePath,
         shared_state: SharedState,
         conf: Arc<SafeKeeperConf>,
-        wal_backup: Arc<WalBackup>,
     ) -> Arc<Self> {
         let (commit_lsn_watch_tx, commit_lsn_watch_rx) =
             watch::channel(shared_state.sk.state().commit_lsn);
@@ -513,7 +509,6 @@ impl Timeline {
             wal_backup_active: AtomicBool::new(false),
             last_removed_segno: AtomicU64::new(0),
             mgr_status: AtomicStatus::new(),
-            wal_backup,
         })
     }
 
@@ -521,7 +516,6 @@ impl Timeline {
     pub fn load_timeline(
         conf: Arc<SafeKeeperConf>,
         ttid: TenantTimelineId,
-        wal_backup: Arc<WalBackup>,
     ) -> Result<Arc<Timeline>> {
         let _enter = info_span!("load_timeline", timeline = %ttid.timeline_id).entered();
 
@@ -535,7 +529,6 @@ impl Timeline {
             &remote_path,
             shared_state,
             conf,
-            wal_backup,
         ))
     }
 
@@ -546,7 +539,6 @@ impl Timeline {
         conf: &SafeKeeperConf,
         broker_active_set: Arc<TimelinesSet>,
         partial_backup_rate_limiter: RateLimiter,
-        wal_backup: Arc<WalBackup>,
     ) {
         let (tx, rx) = self.manager_ctl.bootstrap_manager();
 
@@ -569,7 +561,6 @@ impl Timeline {
                     tx,
                     rx,
                     partial_backup_rate_limiter,
-                    wal_backup,
                 )
                 .await
             }
@@ -615,10 +606,9 @@ impl Timeline {
         // it is cancelled, so WAL storage won't be opened again.
         shared_state.sk.close_wal_store();
 
-        if !only_local {
+        if !only_local && self.conf.is_wal_backup_enabled() {
             self.remote_delete().await?;
         }
-
         let dir_existed = delete_dir(&self.timeline_dir).await?;
         Ok(dir_existed)
     }
@@ -685,20 +675,11 @@ impl Timeline {
         guard: &mut std::sync::MutexGuard<Option<RemoteDeletionReceiver>>,
     ) -> RemoteDeletionReceiver {
         tracing::info!("starting remote deletion");
-        let storage = self.wal_backup.get_storage().clone();
         let (result_tx, result_rx) = tokio::sync::watch::channel(None);
         let ttid = self.ttid;
         tokio::task::spawn(
             async move {
-                let r = if let Some(storage) = storage {
-                    wal_backup::delete_timeline(&storage, &ttid).await
-                } else {
-                    tracing::info!(
-                        "skipping remote deletion because no remote storage is configured; this effectively leaks the objects in remote storage"
-                    );
-                    Ok(())
-                };
-
+                let r = wal_backup::delete_timeline(&ttid).await;
                 if let Err(e) = &r {
                     // Log error here in case nobody ever listens for our result (e.g. dropped API request)
                     tracing::error!("remote deletion failed: {e}");
@@ -1065,13 +1046,14 @@ impl WalResidentTimeline {
 
     pub async fn get_walreader(&self, start_lsn: Lsn) -> Result<WalReader> {
         let (_, persisted_state) = self.get_state().await;
+        let enable_remote_read = self.conf.is_wal_backup_enabled();
 
         WalReader::new(
             &self.ttid,
             self.timeline_dir.clone(),
             &persisted_state,
             start_lsn,
-            self.wal_backup.clone(),
+            enable_remote_read,
         )
     }
 

safekeeper/src/timeline_eviction.rs

@@ -6,7 +6,7 @@
 
 use anyhow::Context;
 use camino::Utf8PathBuf;
-use remote_storage::{GenericRemoteStorage, RemotePath};
+use remote_storage::RemotePath;
 use tokio::fs::File;
 use tokio::io::{AsyncRead, AsyncWriteExt};
 use tracing::{debug, info, instrument, warn};
@@ -68,10 +68,6 @@ impl Manager {
     #[instrument(name = "evict_timeline", skip_all)]
     pub(crate) async fn evict_timeline(&mut self) -> bool {
         assert!(!self.is_offloaded);
-        let Some(storage) = self.wal_backup.get_storage() else {
-            warn!("no remote storage configured, skipping uneviction");
-            return false;
-        };
         let partial_backup_uploaded = match &self.partial_backup_uploaded {
             Some(p) => p.clone(),
             None => {
@@ -91,7 +87,7 @@ impl Manager {
                 .inc();
         });
 
-        if let Err(e) = do_eviction(self, &partial_backup_uploaded, &storage).await {
+        if let Err(e) = do_eviction(self, &partial_backup_uploaded).await {
             warn!("failed to evict timeline: {:?}", e);
             return false;
         }
@@ -106,10 +102,6 @@ impl Manager {
     #[instrument(name = "unevict_timeline", skip_all)]
     pub(crate) async fn unevict_timeline(&mut self) {
         assert!(self.is_offloaded);
-        let Some(storage) = self.wal_backup.get_storage() else {
-            warn!("no remote storage configured, skipping uneviction");
-            return;
-        };
         let partial_backup_uploaded = match &self.partial_backup_uploaded {
             Some(p) => p.clone(),
             None => {
@@ -129,7 +121,7 @@ impl Manager {
                 .inc();
         });
 
-        if let Err(e) = do_uneviction(self, &partial_backup_uploaded, &storage).await {
+        if let Err(e) = do_uneviction(self, &partial_backup_uploaded).await {
             warn!("failed to unevict timeline: {:?}", e);
             return;
         }
@@ -145,12 +137,8 @@ impl Manager {
 /// Ensure that content matches the remote partial backup, if local segment exists.
 /// Then change state in control file and in-memory. If `delete_offloaded_wal` is set,
 /// delete the local segment.
-async fn do_eviction(
-    mgr: &mut Manager,
-    partial: &PartialRemoteSegment,
-    storage: &GenericRemoteStorage,
-) -> anyhow::Result<()> {
-    compare_local_segment_with_remote(mgr, partial, storage).await?;
+async fn do_eviction(mgr: &mut Manager, partial: &PartialRemoteSegment) -> anyhow::Result<()> {
+    compare_local_segment_with_remote(mgr, partial).await?;
 
     mgr.tli.switch_to_offloaded(partial).await?;
     // switch manager state as soon as possible
@@ -165,16 +153,12 @@ async fn do_eviction(
 
 /// Ensure that content matches the remote partial backup, if local segment exists.
 /// Then download segment to local disk and change state in control file and in-memory.
-async fn do_uneviction(
-    mgr: &mut Manager,
-    partial: &PartialRemoteSegment,
-    storage: &GenericRemoteStorage,
-) -> anyhow::Result<()> {
+async fn do_uneviction(mgr: &mut Manager, partial: &PartialRemoteSegment) -> anyhow::Result<()> {
     // if the local segment is present, validate it
-    compare_local_segment_with_remote(mgr, partial, storage).await?;
+    compare_local_segment_with_remote(mgr, partial).await?;
 
     // atomically download the partial segment
-    redownload_partial_segment(mgr, partial, storage).await?;
+    redownload_partial_segment(mgr, partial).await?;
 
     mgr.tli.switch_to_present().await?;
     // switch manager state as soon as possible
@@ -197,7 +181,6 @@ async fn delete_local_segment(mgr: &Manager, partial: &PartialRemoteSegment) ->
 async fn redownload_partial_segment(
     mgr: &Manager,
     partial: &PartialRemoteSegment,
-    storage: &GenericRemoteStorage,
 ) -> anyhow::Result<()> {
     let tmp_file = mgr.tli.timeline_dir().join("remote_partial.tmp");
     let remote_segfile = remote_segment_path(mgr, partial);
@@ -207,7 +190,7 @@ async fn redownload_partial_segment(
         remote_segfile, tmp_file
     );
 
-    let mut reader = wal_backup::read_object(storage, &remote_segfile, 0).await?;
+    let mut reader = wal_backup::read_object(&remote_segfile, 0).await?;
     let mut file = File::create(&tmp_file).await?;
 
     let actual_len = tokio::io::copy(&mut reader, &mut file).await?;
@@ -251,16 +234,13 @@ async fn redownload_partial_segment(
 async fn compare_local_segment_with_remote(
     mgr: &Manager,
     partial: &PartialRemoteSegment,
-    storage: &GenericRemoteStorage,
 ) -> anyhow::Result<()> {
     let local_path = local_segment_path(mgr, partial);
 
     match File::open(&local_path).await {
-        Ok(mut local_file) => {
-            do_validation(mgr, &mut local_file, mgr.wal_seg_size, partial, storage)
-                .await
-                .context("validation failed")
-        }
+        Ok(mut local_file) => do_validation(mgr, &mut local_file, mgr.wal_seg_size, partial)
+            .await
+            .context("validation failed"),
         Err(_) => {
             info!(
                 "local WAL file {} is not present, skipping validation",
@@ -278,7 +258,6 @@ async fn do_validation(
     file: &mut File,
     wal_seg_size: usize,
     partial: &PartialRemoteSegment,
-    storage: &GenericRemoteStorage,
 ) -> anyhow::Result<()> {
     let local_size = file.metadata().await?.len() as usize;
     if local_size != wal_seg_size {
@@ -291,7 +270,7 @@ async fn do_validation(
 
     let remote_segfile = remote_segment_path(mgr, partial);
     let mut remote_reader: std::pin::Pin<Box<dyn AsyncRead + Send + Sync>> =
-        wal_backup::read_object(storage, &remote_segfile, 0).await?;
+        wal_backup::read_object(&remote_segfile, 0).await?;
 
     // remote segment should have bytes excatly up to `flush_lsn`
     let expected_remote_size = partial.flush_lsn.segment_offset(mgr.wal_seg_size);

safekeeper/src/timeline_manager.rs

@@ -35,7 +35,7 @@ use crate::state::TimelineState;
 use crate::timeline::{ManagerTimeline, ReadGuardSharedState, StateSK, WalResidentTimeline};
 use crate::timeline_guard::{AccessService, GuardId, ResidenceGuard};
 use crate::timelines_set::{TimelineSetGuard, TimelinesSet};
-use crate::wal_backup::{self, WalBackup, WalBackupTaskHandle};
+use crate::wal_backup::{self, WalBackupTaskHandle};
 use crate::wal_backup_partial::{self, PartialBackup, PartialRemoteSegment};
 
 pub(crate) struct StateSnapshot {
@@ -200,7 +200,6 @@ pub(crate) struct Manager {
     pub(crate) conf: SafeKeeperConf,
     pub(crate) wal_seg_size: usize,
     pub(crate) walsenders: Arc<WalSenders>,
-    pub(crate) wal_backup: Arc<WalBackup>,
 
     // current state
     pub(crate) state_version_rx: tokio::sync::watch::Receiver<usize>,
@@ -239,7 +238,6 @@ pub async fn main_task(
     manager_tx: tokio::sync::mpsc::UnboundedSender<ManagerCtlMessage>,
     mut manager_rx: tokio::sync::mpsc::UnboundedReceiver<ManagerCtlMessage>,
     global_rate_limiter: RateLimiter,
-    wal_backup: Arc<WalBackup>,
 ) {
     tli.set_status(Status::Started);
 
@@ -258,7 +256,6 @@ pub async fn main_task(
         broker_active_set,
         manager_tx,
         global_rate_limiter,
-        wal_backup,
     )
     .await;
 
@@ -374,7 +371,7 @@ pub async fn main_task(
     mgr.tli_broker_active.set(false);
 
     // shutdown background tasks
-    if let Some(storage) = mgr.wal_backup.get_storage() {
+    if mgr.conf.is_wal_backup_enabled() {
         if let Some(backup_task) = mgr.backup_task.take() {
             // If we fell through here, then the timeline is shutting down. This is important
             // because otherwise joining on the wal_backup handle might hang.
@@ -382,7 +379,7 @@ pub async fn main_task(
 
             backup_task.join().await;
         }
-        wal_backup::update_task(&mut mgr, storage, false, &last_state).await;
+        wal_backup::update_task(&mut mgr, false, &last_state).await;
     }
 
     if let Some(recovery_task) = &mut mgr.recovery_task {
@@ -418,13 +415,11 @@ impl Manager {
         broker_active_set: Arc<TimelinesSet>,
         manager_tx: tokio::sync::mpsc::UnboundedSender<ManagerCtlMessage>,
         global_rate_limiter: RateLimiter,
-        wal_backup: Arc<WalBackup>,
     ) -> Manager {
         let (is_offloaded, partial_backup_uploaded) = tli.bootstrap_mgr().await;
         Manager {
             wal_seg_size: tli.get_wal_seg_size().await,
             walsenders: tli.get_walsenders().clone(),
-            wal_backup,
             state_version_rx: tli.get_state_version_rx(),
             num_computes_rx: tli.get_walreceivers().get_num_rx(),
             tli_broker_active: broker_active_set.guard(tli.clone()),
@@ -482,8 +477,8 @@ impl Manager {
         let is_wal_backup_required =
             wal_backup::is_wal_backup_required(self.wal_seg_size, num_computes, state);
 
-        if let Some(storage) = self.wal_backup.get_storage() {
-            wal_backup::update_task(self, storage, is_wal_backup_required, state).await;
+        if self.conf.is_wal_backup_enabled() {
+            wal_backup::update_task(self, is_wal_backup_required, state).await;
         }
 
         // update the state in Arc<Timeline>
@@ -629,9 +624,9 @@ impl Manager {
     /// Spawns partial WAL backup task if needed.
     async fn update_partial_backup(&mut self, state: &StateSnapshot) {
         // check if WAL backup is enabled and should be started
-        let Some(storage) = self.wal_backup.get_storage() else {
+        if !self.conf.is_wal_backup_enabled() {
             return;
-        };
+        }
 
         if self.partial_backup_task.is_some() {
             // partial backup is already running
@@ -655,7 +650,6 @@ impl Manager {
             self.conf.clone(),
             self.global_rate_limiter.clone(),
             cancel.clone(),
-            storage,
         ));
         self.partial_backup_task = Some((handle, cancel));
     }
@@ -675,10 +669,6 @@ impl Manager {
     /// Reset partial backup state and remove its remote storage data. Since it
     /// might concurrently uploading something, cancel the task first.
     async fn backup_partial_reset(&mut self) -> anyhow::Result<Vec<String>> {
-        let Some(storage) = self.wal_backup.get_storage() else {
-            anyhow::bail!("remote storage is not enabled");
-        };
-
         info!("resetting partial backup state");
         // Force unevict timeline if it is evicted before erasing partial backup
         // state. The intended use of this function is to drop corrupted remote
@@ -699,7 +689,7 @@ impl Manager {
         }
 
         let tli = self.wal_resident_timeline()?;
-        let mut partial_backup = PartialBackup::new(tli, self.conf.clone(), storage).await;
+        let mut partial_backup = PartialBackup::new(tli, self.conf.clone()).await;
         // Reset might fail e.g. when cfile is already reset but s3 removal
         // failed, so set manager state to None beforehand. In any case caller
         // is expected to retry until success.

safekeeper/src/timelines_global_map.rs

@@ -25,7 +25,6 @@ use crate::rate_limit::RateLimiter;
 use crate::state::TimelinePersistentState;
 use crate::timeline::{Timeline, TimelineError, delete_dir, get_tenant_dir, get_timeline_dir};
 use crate::timelines_set::TimelinesSet;
-use crate::wal_backup::WalBackup;
 use crate::wal_storage::Storage;
 use crate::{SafeKeeperConf, control_file, wal_storage};
 
@@ -48,24 +47,15 @@ struct GlobalTimelinesState {
     conf: Arc<SafeKeeperConf>,
     broker_active_set: Arc<TimelinesSet>,
     global_rate_limiter: RateLimiter,
-    wal_backup: Arc<WalBackup>,
 }
 
 impl GlobalTimelinesState {
     /// Get dependencies for a timeline constructor.
-    fn get_dependencies(
-        &self,
-    ) -> (
-        Arc<SafeKeeperConf>,
-        Arc<TimelinesSet>,
-        RateLimiter,
-        Arc<WalBackup>,
-    ) {
+    fn get_dependencies(&self) -> (Arc<SafeKeeperConf>, Arc<TimelinesSet>, RateLimiter) {
         (
             self.conf.clone(),
             self.broker_active_set.clone(),
             self.global_rate_limiter.clone(),
-            self.wal_backup.clone(),
         )
     }
 
@@ -94,7 +84,7 @@ pub struct GlobalTimelines {
 
 impl GlobalTimelines {
     /// Create a new instance of the global timelines map.
-    pub fn new(conf: Arc<SafeKeeperConf>, wal_backup: Arc<WalBackup>) -> Self {
+    pub fn new(conf: Arc<SafeKeeperConf>) -> Self {
         Self {
             state: Mutex::new(GlobalTimelinesState {
                 timelines: HashMap::new(),
@@ -102,7 +92,6 @@ impl GlobalTimelines {
                 conf,
                 broker_active_set: Arc::new(TimelinesSet::default()),
                 global_rate_limiter: RateLimiter::new(1, 1),
-                wal_backup,
             }),
         }
     }
@@ -158,7 +147,7 @@ impl GlobalTimelines {
     /// just lock and unlock it for each timeline -- this function is called
     /// during init when nothing else is running, so this is fine.
     async fn load_tenant_timelines(&self, tenant_id: TenantId) -> Result<()> {
-        let (conf, broker_active_set, partial_backup_rate_limiter, wal_backup) = {
+        let (conf, broker_active_set, partial_backup_rate_limiter) = {
             let state = self.state.lock().unwrap();
             state.get_dependencies()
         };
@@ -173,7 +162,7 @@ impl GlobalTimelines {
                         TimelineId::from_str(timeline_dir_entry.file_name().to_str().unwrap_or(""))
                     {
                         let ttid = TenantTimelineId::new(tenant_id, timeline_id);
-                        match Timeline::load_timeline(conf.clone(), ttid, wal_backup.clone()) {
+                        match Timeline::load_timeline(conf.clone(), ttid) {
                             Ok(tli) => {
                                 let mut shared_state = tli.write_shared_state().await;
                                 self.state
@@ -186,7 +175,6 @@ impl GlobalTimelines {
                                     &conf,
                                     broker_active_set.clone(),
                                     partial_backup_rate_limiter.clone(),
-                                    wal_backup.clone(),
                                 );
                             }
                             // If we can't load a timeline, it's most likely because of a corrupted
@@ -224,10 +212,6 @@ impl GlobalTimelines {
         self.state.lock().unwrap().broker_active_set.clone()
     }
 
-    pub fn get_wal_backup(&self) -> Arc<WalBackup> {
-        self.state.lock().unwrap().wal_backup.clone()
-    }
-
     /// Create a new timeline with the given id. If the timeline already exists, returns
     /// an existing timeline.
     pub(crate) async fn create(
@@ -238,7 +222,7 @@ impl GlobalTimelines {
         start_lsn: Lsn,
         commit_lsn: Lsn,
     ) -> Result<Arc<Timeline>> {
-        let (conf, _, _, _) = {
+        let (conf, _, _) = {
             let state = self.state.lock().unwrap();
             if let Ok(timeline) = state.get(&ttid) {
                 // Timeline already exists, return it.
@@ -283,7 +267,7 @@ impl GlobalTimelines {
         check_tombstone: bool,
     ) -> Result<Arc<Timeline>> {
         // Check for existence and mark that we're creating it.
-        let (conf, broker_active_set, partial_backup_rate_limiter, wal_backup) = {
+        let (conf, broker_active_set, partial_backup_rate_limiter) = {
             let mut state = self.state.lock().unwrap();
             match state.timelines.get(&ttid) {
                 Some(GlobalMapTimeline::CreationInProgress) => {
@@ -312,14 +296,7 @@ impl GlobalTimelines {
         };
 
         // Do the actual move and reflect the result in the map.
-        match GlobalTimelines::install_temp_timeline(
-            ttid,
-            tmp_path,
-            conf.clone(),
-            wal_backup.clone(),
-        )
-        .await
-        {
+        match GlobalTimelines::install_temp_timeline(ttid, tmp_path, conf.clone()).await {
             Ok(timeline) => {
                 let mut timeline_shared_state = timeline.write_shared_state().await;
                 let mut state = self.state.lock().unwrap();
@@ -337,7 +314,6 @@ impl GlobalTimelines {
                     &conf,
                     broker_active_set,
                     partial_backup_rate_limiter,
-                    wal_backup,
                 );
                 drop(timeline_shared_state);
                 Ok(timeline)
@@ -360,7 +336,6 @@ impl GlobalTimelines {
         ttid: TenantTimelineId,
         tmp_path: &Utf8PathBuf,
         conf: Arc<SafeKeeperConf>,
-        wal_backup: Arc<WalBackup>,
     ) -> Result<Arc<Timeline>> {
         let tenant_path = get_tenant_dir(conf.as_ref(), &ttid.tenant_id);
         let timeline_path = get_timeline_dir(conf.as_ref(), &ttid);
@@ -402,7 +377,7 @@ impl GlobalTimelines {
         // Do the move.
         durable_rename(tmp_path, &timeline_path, !conf.no_sync).await?;
 
-        Timeline::load_timeline(conf, ttid, wal_backup)
+        Timeline::load_timeline(conf, ttid)
     }
 
     /// Get a timeline from the global map. If it's not present, it doesn't exist on disk,

safekeeper/src/wal_backup.rs

@@ -2,7 +2,6 @@ use std::cmp::min;
 use std::collections::HashSet;
 use std::num::NonZeroU32;
 use std::pin::Pin;
-use std::sync::Arc;
 use std::time::Duration;
 
 use anyhow::{Context, Result};
@@ -18,7 +17,7 @@ use safekeeper_api::models::PeerInfo;
 use tokio::fs::File;
 use tokio::select;
 use tokio::sync::mpsc::{self, Receiver, Sender};
-use tokio::sync::watch;
+use tokio::sync::{OnceCell, watch};
 use tokio::task::JoinHandle;
 use tokio_util::sync::CancellationToken;
 use tracing::*;
@@ -64,12 +63,7 @@ pub(crate) fn is_wal_backup_required(
 /// Based on peer information determine which safekeeper should offload; if it
 /// is me, run (per timeline) task, if not yet. OTOH, if it is not me and task
 /// is running, kill it.
-pub(crate) async fn update_task(
-    mgr: &mut Manager,
-    storage: Arc<GenericRemoteStorage>,
-    need_backup: bool,
-    state: &StateSnapshot,
-) {
+pub(crate) async fn update_task(mgr: &mut Manager, need_backup: bool, state: &StateSnapshot) {
     let (offloader, election_dbg_str) =
         determine_offloader(&state.peers, state.backup_lsn, mgr.tli.ttid, &mgr.conf);
     let elected_me = Some(mgr.conf.my_id) == offloader;
@@ -88,12 +82,7 @@ pub(crate) async fn update_task(
                 return;
             };
 
-            let async_task = backup_task_main(
-                resident,
-                storage,
-                mgr.conf.backup_parallel_jobs,
-                shutdown_rx,
-            );
+            let async_task = backup_task_main(resident, mgr.conf.backup_parallel_jobs, shutdown_rx);
 
             let handle = if mgr.conf.current_thread_runtime {
                 tokio::spawn(async_task)
@@ -180,31 +169,33 @@ fn determine_offloader(
     }
 }
 
-pub struct WalBackup {
-    storage: Option<Arc<GenericRemoteStorage>>,
+static REMOTE_STORAGE: OnceCell<Option<GenericRemoteStorage>> = OnceCell::const_new();
+
+// Storage must be configured and initialized when this is called.
+fn get_configured_remote_storage() -> &'static GenericRemoteStorage {
+    REMOTE_STORAGE
+        .get()
+        .expect("failed to get remote storage")
+        .as_ref()
+        .unwrap()
 }
 
-impl WalBackup {
-    /// Create a new WalBackup instance.
-    pub async fn new(conf: &SafeKeeperConf) -> Result<Self> {
-        if !conf.wal_backup_enabled {
-            return Ok(Self { storage: None });
-        }
-
-        match conf.remote_storage.as_ref() {
-            Some(config) => {
-                let storage = GenericRemoteStorage::from_config(config).await?;
-                Ok(Self {
-                    storage: Some(Arc::new(storage)),
-                })
+pub async fn init_remote_storage(conf: &SafeKeeperConf) {
+    // TODO: refactor REMOTE_STORAGE to avoid using global variables, and provide
+    // dependencies to all tasks instead.
+    REMOTE_STORAGE
+        .get_or_init(|| async {
+            if let Some(conf) = conf.remote_storage.as_ref() {
+                Some(
+                    GenericRemoteStorage::from_config(conf)
+                        .await
+                        .expect("failed to create remote storage"),
+                )
+            } else {
+                None
             }
-            None => Ok(Self { storage: None }),
-        }
-    }
-
-    pub fn get_storage(&self) -> Option<Arc<GenericRemoteStorage>> {
-        self.storage.clone()
-    }
+        })
+        .await;
 }
 
 struct WalBackupTask {
@@ -213,14 +204,12 @@ struct WalBackupTask {
     wal_seg_size: usize,
     parallel_jobs: usize,
     commit_lsn_watch_rx: watch::Receiver<Lsn>,
-    storage: Arc<GenericRemoteStorage>,
 }
 
 /// Offload single timeline.
 #[instrument(name = "wal_backup", skip_all, fields(ttid = %tli.ttid))]
 async fn backup_task_main(
     tli: WalResidentTimeline,
-    storage: Arc<GenericRemoteStorage>,
     parallel_jobs: usize,
     mut shutdown_rx: Receiver<()>,
 ) {
@@ -234,7 +223,6 @@ async fn backup_task_main(
         timeline_dir: tli.get_timeline_dir(),
         timeline: tli,
         parallel_jobs,
-        storage,
     };
 
     // task is spinned up only when wal_seg_size already initialized
@@ -305,7 +293,6 @@ impl WalBackupTask {
 
             match backup_lsn_range(
                 &self.timeline,
-                self.storage.clone(),
                 &mut backup_lsn,
                 commit_lsn,
                 self.wal_seg_size,
@@ -335,7 +322,6 @@ impl WalBackupTask {
 
 async fn backup_lsn_range(
     timeline: &WalResidentTimeline,
-    storage: Arc<GenericRemoteStorage>,
     backup_lsn: &mut Lsn,
     end_lsn: Lsn,
     wal_seg_size: usize,
@@ -366,12 +352,7 @@ async fn backup_lsn_range(
     loop {
         let added_task = match iter.next() {
             Some(s) => {
-                uploads.push_back(backup_single_segment(
-                    &storage,
-                    s,
-                    timeline_dir,
-                    remote_timeline_path,
-                ));
+                uploads.push_back(backup_single_segment(s, timeline_dir, remote_timeline_path));
                 true
             }
             None => false,
@@ -407,7 +388,6 @@ async fn backup_lsn_range(
 }
 
 async fn backup_single_segment(
-    storage: &GenericRemoteStorage,
     seg: &Segment,
     timeline_dir: &Utf8Path,
     remote_timeline_path: &RemotePath,
@@ -415,13 +395,7 @@ async fn backup_single_segment(
     let segment_file_path = seg.file_path(timeline_dir)?;
     let remote_segment_path = seg.remote_path(remote_timeline_path);
 
-    let res = backup_object(
-        storage,
-        &segment_file_path,
-        &remote_segment_path,
-        seg.size(),
-    )
-    .await;
+    let res = backup_object(&segment_file_path, &remote_segment_path, seg.size()).await;
     if res.is_ok() {
         BACKED_UP_SEGMENTS.inc();
     } else {
@@ -481,11 +455,12 @@ fn get_segments(start: Lsn, end: Lsn, seg_size: usize) -> Vec<Segment> {
 }
 
 async fn backup_object(
-    storage: &GenericRemoteStorage,
     source_file: &Utf8Path,
     target_file: &RemotePath,
     size: usize,
 ) -> Result<()> {
+    let storage = get_configured_remote_storage();
+
     let file = File::open(&source_file)
         .await
         .with_context(|| format!("Failed to open file {source_file:?} for wal backup"))?;
@@ -500,11 +475,12 @@ async fn backup_object(
 }
 
 pub(crate) async fn backup_partial_segment(
-    storage: &GenericRemoteStorage,
     source_file: &Utf8Path,
     target_file: &RemotePath,
     size: usize,
 ) -> Result<()> {
+    let storage = get_configured_remote_storage();
+
     let file = File::open(&source_file)
         .await
         .with_context(|| format!("Failed to open file {source_file:?} for wal backup"))?;
@@ -528,20 +504,25 @@ pub(crate) async fn backup_partial_segment(
 }
 
 pub(crate) async fn copy_partial_segment(
-    storage: &GenericRemoteStorage,
     source: &RemotePath,
     destination: &RemotePath,
 ) -> Result<()> {
+    let storage = get_configured_remote_storage();
     let cancel = CancellationToken::new();
 
     storage.copy_object(source, destination, &cancel).await
 }
 
 pub async fn read_object(
-    storage: &GenericRemoteStorage,
     file_path: &RemotePath,
     offset: u64,
 ) -> anyhow::Result<Pin<Box<dyn tokio::io::AsyncRead + Send + Sync>>> {
+    let storage = REMOTE_STORAGE
+        .get()
+        .context("Failed to get remote storage")?
+        .as_ref()
+        .context("No remote storage configured")?;
+
     info!("segment download about to start from remote path {file_path:?} at offset {offset}");
 
     let cancel = CancellationToken::new();
@@ -566,10 +547,8 @@ pub async fn read_object(
 
 /// Delete WAL files for the given timeline. Remote storage must be configured
 /// when called.
-pub async fn delete_timeline(
-    storage: &GenericRemoteStorage,
-    ttid: &TenantTimelineId,
-) -> Result<()> {
+pub async fn delete_timeline(ttid: &TenantTimelineId) -> Result<()> {
+    let storage = get_configured_remote_storage();
     let remote_path = remote_timeline_path(ttid)?;
 
     // see DEFAULT_MAX_KEYS_PER_LIST_RESPONSE
@@ -639,14 +618,14 @@ pub async fn delete_timeline(
 }
 
 /// Used by wal_backup_partial.
-pub async fn delete_objects(storage: &GenericRemoteStorage, paths: &[RemotePath]) -> Result<()> {
+pub async fn delete_objects(paths: &[RemotePath]) -> Result<()> {
     let cancel = CancellationToken::new(); // not really used
+    let storage = get_configured_remote_storage();
     storage.delete_objects(paths, &cancel).await
 }
 
 /// Copy segments from one timeline to another. Used in copy_timeline.
 pub async fn copy_s3_segments(
-    storage: &GenericRemoteStorage,
     wal_seg_size: usize,
     src_ttid: &TenantTimelineId,
     dst_ttid: &TenantTimelineId,
@@ -655,6 +634,12 @@ pub async fn copy_s3_segments(
 ) -> Result<()> {
     const SEGMENTS_PROGRESS_REPORT_INTERVAL: u64 = 1024;
 
+    let storage = REMOTE_STORAGE
+        .get()
+        .expect("failed to get remote storage")
+        .as_ref()
+        .unwrap();
+
     let remote_dst_path = remote_timeline_path(dst_ttid)?;
 
     let cancel = CancellationToken::new();