Compare commits

..

3 Commits

Author SHA1 Message Date
John Spray
62aa8f2ba2 hacky way to make tests pass 2024-10-04 09:56:56 +00:00
John Spray
efc3f1cfe5 DNM: test-log 2024-10-03 11:29:06 +00:00
John Spray
b66bf890fa storage controller: fix a disagreement between schedule + optimize
Closes: https://github.com/neondatabase/neon/issues/8969
2024-10-03 11:14:34 +00:00
412 changed files with 6373 additions and 11379 deletions

View File

@@ -5,7 +5,9 @@
!Cargo.toml
!Makefile
!rust-toolchain.toml
!scripts/combine_control_files.py
!scripts/ninstall.sh
!vm-cgconfig.conf
!docker-compose/run-tests.sh
# Directories
@@ -15,12 +17,15 @@
!compute_tools/
!control_plane/
!libs/
!neon_local/
!pageserver/
!patches/
!pgxn/
!proxy/
!storage_scrubber/
!safekeeper/
!storage_broker/
!storage_controller/
!trace/
!vendor/postgres-*/
!workspace_hack/

View File

@@ -183,7 +183,7 @@ runs:
uses: actions/cache@v4
with:
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-${{ hashFiles('poetry.lock') }}
- name: Store Allure test stat in the DB (new)
if: ${{ !cancelled() && inputs.store-test-results-into-db == 'true' }}

View File

@@ -88,7 +88,7 @@ runs:
uses: actions/cache@v4
with:
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-${{ hashFiles('poetry.lock') }}
- name: Install Python deps
shell: bash -euxo pipefail {0}
@@ -218,9 +218,6 @@ runs:
name: compatibility-snapshot-${{ runner.arch }}-${{ inputs.build_type }}-pg${{ inputs.pg_version }}
# Directory is created by test_compatibility.py::test_create_snapshot, keep the path in sync with the test
path: /tmp/test_output/compatibility_snapshot_pg${{ inputs.pg_version }}/
# The lack of compatibility snapshot shouldn't fail the job
# (for example if we didn't run the test for non build-and-test workflow)
skip-if-does-not-exist: true
- name: Upload test results
if: ${{ !cancelled() }}

View File

@@ -7,10 +7,6 @@ inputs:
path:
description: "A directory or file to upload"
required: true
skip-if-does-not-exist:
description: "Allow to skip if path doesn't exist, fail otherwise"
default: false
required: false
prefix:
description: "S3 prefix. Default is '${GITHUB_SHA}/${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}'"
required: false
@@ -19,12 +15,10 @@ runs:
using: "composite"
steps:
- name: Prepare artifact
id: prepare-artifact
shell: bash -euxo pipefail {0}
env:
SOURCE: ${{ inputs.path }}
ARCHIVE: /tmp/uploads/${{ inputs.name }}.tar.zst
SKIP_IF_DOES_NOT_EXIST: ${{ inputs.skip-if-does-not-exist }}
run: |
mkdir -p $(dirname $ARCHIVE)
@@ -39,22 +33,14 @@ runs:
elif [ -f ${SOURCE} ]; then
time tar -cf ${ARCHIVE} --zstd ${SOURCE}
elif ! ls ${SOURCE} > /dev/null 2>&1; then
if [ "${SKIP_IF_DOES_NOT_EXIST}" = "true" ]; then
echo 'SKIPPED=true' >> $GITHUB_OUTPUT
exit 0
else
echo >&2 "${SOURCE} does not exist"
exit 2
fi
echo >&2 "${SOURCE} does not exist"
exit 2
else
echo >&2 "${SOURCE} is neither a directory nor a file, do not know how to handle it"
exit 3
fi
echo 'SKIPPED=false' >> $GITHUB_OUTPUT
- name: Upload artifact
if: ${{ steps.prepare-artifact.outputs.SKIPPED == 'false' }}
shell: bash -euxo pipefail {0}
env:
SOURCE: ${{ inputs.path }}

View File

@@ -124,28 +124,28 @@ jobs:
uses: actions/cache@v4
with:
path: pg_install/v14
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
- name: Cache postgres v15 build
id: cache_pg_15
uses: actions/cache@v4
with:
path: pg_install/v15
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
- name: Cache postgres v16 build
id: cache_pg_16
uses: actions/cache@v4
with:
path: pg_install/v16
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v16_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v16_rev.outputs.pg_rev }}-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
- name: Cache postgres v17 build
id: cache_pg_17
uses: actions/cache@v4
with:
path: pg_install/v17
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v17_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v17_rev.outputs.pg_rev }}-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
- name: Build postgres v14
if: steps.cache_pg_14.outputs.cache-hit != 'true'

View File

@@ -19,16 +19,9 @@ defaults:
run:
shell: bash -euo pipefail {0}
# The initial idea was to prevent the waste of resources by not re-building the `build-tools` image
# for the same tag in parallel workflow runs, and queue them to be skipped once we have
# the first image pushed to Docker registry, but GitHub's concurrency mechanism is not working as expected.
# GitHub can't have more than 1 job in a queue and removes the previous one, it causes failures if the dependent jobs.
#
# Ref https://github.com/orgs/community/discussions/41518
#
# concurrency:
# group: build-build-tools-image-${{ inputs.image-tag }}
# cancel-in-progress: false
concurrency:
group: build-build-tools-image-${{ inputs.image-tag }}
cancel-in-progress: false
# No permission for GITHUB_TOKEN by default; the **minimal required** set of permissions should be granted in each job.
permissions: {}
@@ -43,7 +36,6 @@ jobs:
strategy:
matrix:
debian-version: [ bullseye, bookworm ]
arch: [ x64, arm64 ]
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'large-arm64' || 'large')) }}
@@ -82,22 +74,22 @@ jobs:
- uses: docker/build-push-action@v6
with:
file: Dockerfile.build-tools
context: .
provenance: false
push: true
pull: true
build-args: |
DEBIAN_VERSION=${{ matrix.debian-version }}
cache-from: type=registry,ref=cache.neon.build/build-tools:cache-${{ matrix.debian-version }}-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/build-tools:cache-{0}-{1},mode=max', matrix.debian-version, matrix.arch) || '' }}
tags: |
neondatabase/build-tools:${{ inputs.image-tag }}-${{ matrix.debian-version }}-${{ matrix.arch }}
file: Dockerfile.build-tools
cache-from: type=registry,ref=cache.neon.build/build-tools:cache-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/build-tools:cache-{0},mode=max', matrix.arch) || '' }}
tags: neondatabase/build-tools:${{ inputs.image-tag }}-${{ matrix.arch }}
merge-images:
needs: [ build-image ]
runs-on: ubuntu-22.04
env:
IMAGE_TAG: ${{ inputs.image-tag }}
steps:
- uses: docker/login-action@v3
with:
@@ -105,17 +97,7 @@ jobs:
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- name: Create multi-arch image
env:
DEFAULT_DEBIAN_VERSION: bullseye
IMAGE_TAG: ${{ inputs.image-tag }}
run: |
for debian_version in bullseye bookworm; do
tags=("-t" "neondatabase/build-tools:${IMAGE_TAG}-${debian_version}")
if [ "${debian_version}" == "${DEFAULT_DEBIAN_VERSION}" ]; then
tags+=("-t" "neondatabase/build-tools:${IMAGE_TAG}")
fi
docker buildx imagetools create "${tags[@]}" \
neondatabase/build-tools:${IMAGE_TAG}-${debian_version}-x64 \
neondatabase/build-tools:${IMAGE_TAG}-${debian_version}-arm64
done
docker buildx imagetools create -t neondatabase/build-tools:${IMAGE_TAG} \
neondatabase/build-tools:${IMAGE_TAG}-x64 \
neondatabase/build-tools:${IMAGE_TAG}-arm64

View File

@@ -92,7 +92,7 @@ jobs:
needs: [ check-permissions, build-build-tools-image ]
runs-on: [ self-hosted, small ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -106,7 +106,7 @@ jobs:
uses: actions/cache@v4
with:
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-${{ hashFiles('poetry.lock') }}
- name: Install Python deps
run: ./scripts/pysync
@@ -181,7 +181,7 @@ jobs:
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'small-arm64' || 'small')) }}
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -193,15 +193,16 @@ jobs:
with:
submodules: true
- name: Cache cargo deps
uses: actions/cache@v4
with:
path: |
~/.cargo/registry
!~/.cargo/registry/src
~/.cargo/git
target
key: v1-${{ runner.os }}-${{ runner.arch }}-cargo-${{ hashFiles('./Cargo.lock') }}-${{ hashFiles('./rust-toolchain.toml') }}-rust
# Disabled for now
# - name: Restore cargo deps cache
# id: cache_cargo
# uses: actions/cache@v4
# with:
# path: |
# !~/.cargo/registry/src
# ~/.cargo/git/
# target/
# key: v1-${{ runner.os }}-${{ runner.arch }}-cargo-clippy-${{ hashFiles('rust-toolchain.toml') }}-${{ hashFiles('Cargo.lock') }}
# Some of our rust modules use FFI and need those to be checked
- name: Get postgres headers
@@ -261,7 +262,7 @@ jobs:
uses: ./.github/workflows/_build-and-test-locally.yml
with:
arch: ${{ matrix.arch }}
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}
build-tag: ${{ needs.tag.outputs.build-tag }}
build-type: ${{ matrix.build-type }}
# Run tests on all Postgres versions in release builds and only on the latest version in debug builds
@@ -276,7 +277,7 @@ jobs:
needs: [ check-permissions, build-build-tools-image ]
runs-on: [ self-hosted, small ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -289,7 +290,7 @@ jobs:
uses: actions/cache@v4
with:
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
key: v1-${{ runner.os }}-${{ runner.arch }}-python-deps-${{ hashFiles('poetry.lock') }}
- name: Install Python deps
run: ./scripts/pysync
@@ -309,7 +310,7 @@ jobs:
needs: [ check-permissions, build-and-test-locally, build-build-tools-image, get-benchmarks-durations ]
runs-on: [ self-hosted, small ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -367,7 +368,7 @@ jobs:
runs-on: [ self-hosted, small ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -415,7 +416,7 @@ jobs:
needs: [ check-permissions, build-build-tools-image, build-and-test-locally ]
runs-on: [ self-hosted, small ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -559,16 +560,15 @@ jobs:
ADDITIONAL_RUSTFLAGS=${{ matrix.arch == 'arm64' && '-Ctarget-feature=+lse -Ctarget-cpu=neoverse-n1' || '' }}
GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
BUILD_TAG=${{ needs.tag.outputs.build-tag }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-bookworm
DEBIAN_VERSION=bookworm
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}
provenance: false
push: true
pull: true
file: Dockerfile
cache-from: type=registry,ref=cache.neon.build/neon:cache-bookworm-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/neon:cache-{0}-{1},mode=max', 'bookworm', matrix.arch) || '' }}
cache-from: type=registry,ref=cache.neon.build/neon:cache-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/neon:cache-{0},mode=max', matrix.arch) || '' }}
tags: |
neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm-${{ matrix.arch }}
neondatabase/neon:${{ needs.tag.outputs.build-tag }}-${{ matrix.arch }}
neon-image:
needs: [ neon-image-arch, tag ]
@@ -583,9 +583,8 @@ jobs:
- name: Create multi-arch image
run: |
docker buildx imagetools create -t neondatabase/neon:${{ needs.tag.outputs.build-tag }} \
-t neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm \
neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm-x64 \
neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm-arm64
neondatabase/neon:${{ needs.tag.outputs.build-tag }}-x64 \
neondatabase/neon:${{ needs.tag.outputs.build-tag }}-arm64
- uses: docker/login-action@v3
with:
@@ -606,16 +605,17 @@ jobs:
version:
# Much data was already generated on old PG versions with bullseye's
# libraries, the locales of which can cause data incompatibilities.
# However, new PG versions should be build on newer images,
# as that reduces the support burden of old and ancient distros.
# However, new PG versions should check if they can be built on newer
# images, as that reduces the support burden of old and ancient
# distros.
- pg: v14
debian: bullseye
debian: bullseye-slim
- pg: v15
debian: bullseye
debian: bullseye-slim
- pg: v16
debian: bullseye
debian: bullseye-slim
- pg: v17
debian: bookworm
debian: bookworm-slim
arch: [ x64, arm64 ]
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'large-arm64' || 'large')) }}
@@ -660,16 +660,16 @@ jobs:
GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
PG_VERSION=${{ matrix.version.pg }}
BUILD_TAG=${{ needs.tag.outputs.build-tag }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-${{ matrix.version.debian }}
DEBIAN_VERSION=${{ matrix.version.debian }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}
DEBIAN_FLAVOR=${{ matrix.version.debian }}
provenance: false
push: true
pull: true
file: compute/Dockerfile.compute-node
cache-from: type=registry,ref=cache.neon.build/compute-node-${{ matrix.version.pg }}:cache-${{ matrix.version.debian }}-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/compute-node-{0}:cache-{1}-{2},mode=max', matrix.version.pg, matrix.version.debian, matrix.arch) || '' }}
cache-from: type=registry,ref=cache.neon.build/compute-node-${{ matrix.version.pg }}:cache-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/compute-node-{0}:cache-{1},mode=max', matrix.version.pg, matrix.arch) || '' }}
tags: |
neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-${{ matrix.arch }}
neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.arch }}
- name: Build neon extensions test image
if: matrix.version.pg == 'v16'
@@ -680,17 +680,17 @@ jobs:
GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
PG_VERSION=${{ matrix.version.pg }}
BUILD_TAG=${{ needs.tag.outputs.build-tag }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-${{ matrix.version.debian }}
DEBIAN_VERSION=${{ matrix.version.debian }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}
DEBIAN_FLAVOR=${{ matrix.version.debian }}
provenance: false
push: true
pull: true
file: compute/Dockerfile.compute-node
target: neon-pg-ext-test
cache-from: type=registry,ref=cache.neon.build/neon-test-extensions-${{ matrix.version.pg }}:cache-${{ matrix.version.debian }}-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/neon-test-extensions-{0}:cache-{1}-{2},mode=max', matrix.version.pg, matrix.version.debian, matrix.arch) || '' }}
cache-from: type=registry,ref=cache.neon.build/neon-test-extensions-${{ matrix.version.pg }}:cache-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/neon-test-extensions-{0}:cache-{1},mode=max', matrix.version.pg, matrix.arch) || '' }}
tags: |
neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{needs.tag.outputs.build-tag}}-${{ matrix.version.debian }}-${{ matrix.arch }}
neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{needs.tag.outputs.build-tag}}-${{ matrix.arch }}
- name: Build compute-tools image
# compute-tools are Postgres independent, so build it only once
@@ -705,16 +705,14 @@ jobs:
build-args: |
GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
BUILD_TAG=${{ needs.tag.outputs.build-tag }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-${{ matrix.version.debian }}
DEBIAN_VERSION=${{ matrix.version.debian }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}
DEBIAN_FLAVOR=${{ matrix.version.debian }}
provenance: false
push: true
pull: true
file: compute/Dockerfile.compute-node
cache-from: type=registry,ref=cache.neon.build/neon-test-extensions-${{ matrix.version.pg }}:cache-${{ matrix.version.debian }}-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/compute-tools-{0}:cache-{1}-{2},mode=max', matrix.version.pg, matrix.version.debian, matrix.arch) || '' }}
tags: |
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-${{ matrix.arch }}
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.arch }}
compute-node-image:
needs: [ compute-node-image-arch, tag ]
@@ -722,16 +720,7 @@ jobs:
strategy:
matrix:
version:
# see the comment for `compute-node-image-arch` job
- pg: v14
debian: bullseye
- pg: v15
debian: bullseye
- pg: v16
debian: bullseye
- pg: v17
debian: bookworm
version: [ v14, v15, v16, v17 ]
steps:
- uses: docker/login-action@v3
@@ -741,26 +730,23 @@ jobs:
- name: Create multi-arch compute-node image
run: |
docker buildx imagetools create -t neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }} \
-t neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }} \
neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
docker buildx imagetools create -t neondatabase/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }} \
neondatabase/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}-x64 \
neondatabase/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}-arm64
- name: Create multi-arch neon-test-extensions image
if: matrix.version.pg == 'v16'
if: matrix.version == 'v16'
run: |
docker buildx imagetools create -t neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }} \
-t neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }} \
neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
docker buildx imagetools create -t neondatabase/neon-test-extensions-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }} \
neondatabase/neon-test-extensions-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}-x64 \
neondatabase/neon-test-extensions-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}-arm64
- name: Create multi-arch compute-tools image
if: matrix.version.pg == 'v16'
if: matrix.version == 'v17'
run: |
docker buildx imagetools create -t neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }} \
-t neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }} \
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-x64 \
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-arm64
- uses: docker/login-action@v3
with:
@@ -768,13 +754,13 @@ jobs:
username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
password: ${{ secrets.AWS_SECRET_KEY_DEV }}
- name: Push multi-arch compute-node-${{ matrix.version.pg }} image to ECR
- name: Push multi-arch compute-node-${{ matrix.version }} image to ECR
run: |
docker buildx imagetools create -t 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }} \
neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}
docker buildx imagetools create -t 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }} \
neondatabase/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}
- name: Push multi-arch compute-tools image to ECR
if: matrix.version.pg == 'v16'
if: matrix.version == 'v17'
run: |
docker buildx imagetools create -t 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:${{ needs.tag.outputs.build-tag }} \
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}
@@ -785,16 +771,7 @@ jobs:
strategy:
fail-fast: false
matrix:
version:
# see the comment for `compute-node-image-arch` job
- pg: v14
debian: bullseye
- pg: v15
debian: bullseye
- pg: v16
debian: bullseye
- pg: v17
debian: bookworm
version: [ v14, v15, v16, v17 ]
env:
VM_BUILDER_VERSION: v0.35.0
@@ -816,18 +793,18 @@ jobs:
# it won't have the proper authentication (written at v0.6.0)
- name: Pulling compute-node image
run: |
docker pull neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}
docker pull neondatabase/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}
- name: Build vm image
run: |
./vm-builder \
-spec=compute/vm-image-spec-${{ matrix.version.debian }}.yaml \
-src=neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }} \
-dst=neondatabase/vm-compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}
-spec=compute/vm-image-spec.yaml \
-src=neondatabase/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }} \
-dst=neondatabase/vm-compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}
- name: Pushing vm-compute-node image
run: |
docker push neondatabase/vm-compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}
docker push neondatabase/vm-compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}
test-images:
needs: [ check-permissions, tag, neon-image, compute-node-image ]

View File

@@ -155,7 +155,7 @@ jobs:
github.ref_name == 'main'
runs-on: [ self-hosted, large ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}

View File

@@ -55,7 +55,7 @@ jobs:
runs-on: ubuntu-22.04
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -150,7 +150,7 @@ jobs:
runs-on: ubuntu-22.04
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}

View File

@@ -71,6 +71,7 @@ jobs:
steps:
- uses: docker/login-action@v3
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -93,22 +94,8 @@ jobs:
az acr login --name=neoneastus2
- name: Tag build-tools with `${{ env.TO_TAG }}` in Docker Hub, ECR, and ACR
env:
DEFAULT_DEBIAN_VERSION: bullseye
run: |
for debian_version in bullseye bookworm; do
tags=()
tags+=("-t" "neondatabase/build-tools:${TO_TAG}-${debian_version}")
tags+=("-t" "369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:${TO_TAG}-${debian_version}")
tags+=("-t" "neoneastus2.azurecr.io/neondatabase/build-tools:${TO_TAG}-${debian_version}")
if [ "${debian_version}" == "${DEFAULT_DEBIAN_VERSION}" ]; then
tags+=("-t" "neondatabase/build-tools:${TO_TAG}")
tags+=("-t" "369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:${TO_TAG}")
tags+=("-t" "neoneastus2.azurecr.io/neondatabase/build-tools:${TO_TAG}")
fi
docker buildx imagetools create "${tags[@]}" \
neondatabase/build-tools:${FROM_TAG}-${debian_version}
done
docker buildx imagetools create -t 369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:${TO_TAG} \
-t neoneastus2.azurecr.io/neondatabase/build-tools:${TO_TAG} \
-t neondatabase/build-tools:${TO_TAG} \
neondatabase/build-tools:${FROM_TAG}

View File

@@ -1,41 +0,0 @@
name: Report Workflow Stats
on:
workflow_run:
workflows:
- Add `external` label to issues and PRs created by external users
- Benchmarking
- Build and Test
- Build and Test Locally
- Build build-tools image
- Check Permissions
- Check build-tools image
- Check neon with extra platform builds
- Cloud Regression Test
- Create Release Branch
- Handle `approved-for-ci-run` label
- Lint GitHub Workflows
- Notify Slack channel about upcoming release
- Periodic pagebench performance test on dedicated EC2 machine in eu-central-1 region
- Pin build-tools image
- Prepare benchmarking databases by restoring dumps
- Push images to ACR
- Test Postgres client libraries
- Trigger E2E Tests
- cleanup caches by a branch
types: [completed]
jobs:
gh-workflow-stats:
name: Github Workflow Stats
runs-on: ubuntu-22.04
permissions:
actions: read
steps:
- name: Export GH Workflow Stats
uses: neondatabase/gh-workflow-stats-action@v0.1.4
with:
DB_URI: ${{ secrets.GH_REPORT_STATS_DB_RW_CONNSTR }}
DB_TABLE: "gh_workflow_stats_neon"
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
GH_RUN_ID: ${{ github.event.workflow_run.id }}

View File

@@ -1,6 +1,5 @@
/compute_tools/ @neondatabase/control-plane @neondatabase/compute
/storage_controller @neondatabase/storage
/storage_scrubber @neondatabase/storage
/libs/pageserver_api/ @neondatabase/storage
/libs/postgres_ffi/ @neondatabase/compute @neondatabase/storage
/libs/remote_storage/ @neondatabase/storage

230
Cargo.lock generated
View File

@@ -82,12 +82,27 @@ dependencies = [
"anstyle",
"anstyle-parse",
"anstyle-query",
"anstyle-wincon",
"anstyle-wincon 1.0.1",
"colorchoice",
"is-terminal",
"utf8parse",
]
[[package]]
name = "anstream"
version = "0.6.15"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "64e15c1ab1f89faffbf04a634d5e1962e9074f2741eef6d97f3c4e322426d526"
dependencies = [
"anstyle",
"anstyle-parse",
"anstyle-query",
"anstyle-wincon 3.0.4",
"colorchoice",
"is_terminal_polyfill",
"utf8parse",
]
[[package]]
name = "anstyle"
version = "1.0.8"
@@ -122,6 +137,16 @@ dependencies = [
"windows-sys 0.48.0",
]
[[package]]
name = "anstyle-wincon"
version = "3.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5bf74e1b6e971609db8ca7a9ce79fd5768ab6ae46441c572e46cf596f59e57f8"
dependencies = [
"anstyle",
"windows-sys 0.52.0",
]
[[package]]
name = "anyhow"
version = "1.0.71"
@@ -668,20 +693,19 @@ dependencies = [
[[package]]
name = "axum"
version = "0.7.5"
version = "0.6.20"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3a6c9af12842a67734c9a2e355436e5d03b22383ed60cf13cd0c18fbfe3dcbcf"
checksum = "3b829e4e32b91e643de6eafe82b1d90675f5874230191a4ffbc1b336dec4d6bf"
dependencies = [
"async-trait",
"axum-core",
"axum-core 0.3.4",
"base64 0.21.1",
"bitflags 1.3.2",
"bytes",
"futures-util",
"http 1.1.0",
"http-body 1.0.0",
"http-body-util",
"hyper 1.4.1",
"hyper-util",
"http 0.2.9",
"http-body 0.4.5",
"hyper 0.14.30",
"itoa",
"matchit 0.7.0",
"memchr",
@@ -694,13 +718,56 @@ dependencies = [
"serde_path_to_error",
"serde_urlencoded",
"sha1",
"sync_wrapper 1.0.1",
"sync_wrapper 0.1.2",
"tokio",
"tokio-tungstenite",
"tower",
"tower-layer",
"tower-service",
"tracing",
]
[[package]]
name = "axum"
version = "0.7.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3a6c9af12842a67734c9a2e355436e5d03b22383ed60cf13cd0c18fbfe3dcbcf"
dependencies = [
"async-trait",
"axum-core 0.4.5",
"bytes",
"futures-util",
"http 1.1.0",
"http-body 1.0.0",
"http-body-util",
"itoa",
"matchit 0.7.0",
"memchr",
"mime",
"percent-encoding",
"pin-project-lite",
"rustversion",
"serde",
"sync_wrapper 1.0.1",
"tower",
"tower-layer",
"tower-service",
]
[[package]]
name = "axum-core"
version = "0.3.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "759fa577a247914fd3f7f76d62972792636412fbfd634cd452f6a385a74d2d2c"
dependencies = [
"async-trait",
"bytes",
"futures-util",
"http 0.2.9",
"http-body 0.4.5",
"mime",
"rustversion",
"tower-layer",
"tower-service",
]
[[package]]
@@ -721,7 +788,6 @@ dependencies = [
"sync_wrapper 1.0.1",
"tower-layer",
"tower-service",
"tracing",
]
[[package]]
@@ -1144,7 +1210,7 @@ version = "4.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4f423e341edefb78c9caba2d9c7f7687d0e72e89df3ce3394554754393ac3990"
dependencies = [
"anstream",
"anstream 0.3.2",
"anstyle",
"bitflags 1.3.2",
"clap_lex",
@@ -1220,7 +1286,6 @@ version = "0.1.0"
dependencies = [
"anyhow",
"bytes",
"camino",
"cfg-if",
"chrono",
"clap",
@@ -1820,7 +1885,6 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b5e6043086bf7973472e0c7dff2142ea0b680d30e18d9cc40f267efbf222bd47"
dependencies = [
"base16ct 0.2.0",
"base64ct",
"crypto-bigint 0.5.5",
"digest",
"ff 0.13.0",
@@ -1830,8 +1894,6 @@ dependencies = [
"pkcs8 0.10.2",
"rand_core 0.6.4",
"sec1 0.7.3",
"serde_json",
"serdect",
"subtle",
"zeroize",
]
@@ -1887,6 +1949,15 @@ dependencies = [
"syn 2.0.52",
]
[[package]]
name = "env_filter"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4f2c92ceda6ceec50f43169f9ee8424fe2db276791afde7b2cd8bc084cb376ab"
dependencies = [
"log",
]
[[package]]
name = "env_logger"
version = "0.10.2"
@@ -1900,6 +1971,18 @@ dependencies = [
"termcolor",
]
[[package]]
name = "env_logger"
version = "0.11.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6c012a26a7f605efc424dd53697843a72be7dc86ad2d01f7814337794a12231d"
dependencies = [
"anstream 0.6.15",
"anstyle",
"env_filter",
"log",
]
[[package]]
name = "equivalent"
version = "1.0.1"
@@ -2695,7 +2778,6 @@ checksum = "ad227c3af19d4914570ad36d30409928b75967c298feb9ea1969db3a610bb14e"
dependencies = [
"equivalent",
"hashbrown 0.14.5",
"serde",
]
[[package]]
@@ -2775,6 +2857,12 @@ dependencies = [
"windows-sys 0.52.0",
]
[[package]]
name = "is_terminal_polyfill"
version = "1.70.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7943c866cc5cd64cbc25b2e01621d07fa8eb2a1a23160ee81ce38704e97b8ecf"
[[package]]
name = "itertools"
version = "0.10.5"
@@ -2795,9 +2883,9 @@ dependencies = [
[[package]]
name = "itoa"
version = "1.0.11"
version = "1.0.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "49f1f14873335454500d59611f1cf4a4b0f786f9ac11f4312a78e4cf2566695b"
checksum = "453ad9f582a441959e5f0d088b02ce04cfe8d51a8eaf077f12ac6d3e94164ca6"
[[package]]
name = "jobserver"
@@ -3218,6 +3306,16 @@ dependencies = [
"winapi",
]
[[package]]
name = "nu-ansi-term"
version = "0.46.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "77a8165726e8236064dbb45459242600304b42a5ea24ee2948e18e023bf7ba84"
dependencies = [
"overload",
"winapi",
]
[[package]]
name = "num"
version = "0.4.1"
@@ -3501,6 +3599,12 @@ version = "0.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4030760ffd992bef45b0ae3f10ce1aba99e33464c90d14dd7c039884963ddc7a"
[[package]]
name = "overload"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b15813163c1d831bf4a13c3610c05c0d03b39feb07f7e09fa234dac9b15aaf39"
[[package]]
name = "p256"
version = "0.11.1"
@@ -3656,7 +3760,6 @@ dependencies = [
"tracing",
"url",
"utils",
"wal_decoder",
"walkdir",
"workspace_hack",
]
@@ -4042,8 +4145,6 @@ dependencies = [
"bytes",
"fallible-iterator",
"postgres-protocol",
"serde",
"serde_json",
]
[[package]]
@@ -4086,7 +4187,7 @@ dependencies = [
"bindgen",
"bytes",
"crc32c",
"env_logger",
"env_logger 0.10.2",
"log",
"memoffset 0.9.0",
"once_cell",
@@ -4094,7 +4195,6 @@ dependencies = [
"regex",
"serde",
"thiserror",
"tracing",
"utils",
]
@@ -4280,7 +4380,7 @@ dependencies = [
"consumption_metrics",
"dashmap",
"ecdsa 0.16.9",
"env_logger",
"env_logger 0.10.2",
"fallible-iterator",
"framed-websockets",
"futures",
@@ -4299,7 +4399,6 @@ dependencies = [
"indexmap 2.0.1",
"ipnet",
"itertools 0.10.5",
"itoa",
"jose-jwa",
"jose-jwk",
"lasso",
@@ -5265,7 +5364,6 @@ dependencies = [
"der 0.7.8",
"generic-array",
"pkcs8 0.10.2",
"serdect",
"subtle",
"zeroize",
]
@@ -5520,16 +5618,6 @@ dependencies = [
"syn 2.0.52",
]
[[package]]
name = "serdect"
version = "0.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a84f14a19e9a014bb9f4512488d9829a68e04ecabffb0f9904cd1ace94598177"
dependencies = [
"base16ct 0.2.0",
"serde",
]
[[package]]
name = "sha1"
version = "0.10.5"
@@ -5767,6 +5855,7 @@ dependencies = [
"serde_json",
"strum",
"strum_macros",
"test-log",
"thiserror",
"tokio",
"tokio-util",
@@ -6019,6 +6108,28 @@ dependencies = [
"syn 2.0.52",
]
[[package]]
name = "test-log"
version = "0.2.16"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3dffced63c2b5c7be278154d76b479f9f9920ed34e7574201407f0b14e2bbb93"
dependencies = [
"env_logger 0.11.2",
"test-log-macros",
"tracing-subscriber",
]
[[package]]
name = "test-log-macros"
version = "0.2.16"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5999e24eaa32083191ba4e425deb75cdf25efefabe5aaccb7446dd0d4122a3f5"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.52",
]
[[package]]
name = "thiserror"
version = "1.0.57"
@@ -6310,9 +6421,9 @@ dependencies = [
[[package]]
name = "tokio-tungstenite"
version = "0.21.0"
version = "0.20.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c83b561d025642014097b66e6c1bb422783339e0909e4429cde4749d1990bc38"
checksum = "2b2dbec703c26b00d74844519606ef15d09a7d6857860f84ad223dec002ddea2"
dependencies = [
"futures-util",
"log",
@@ -6379,7 +6490,7 @@ checksum = "877c5b330756d856ffcc4553ab34a5684481ade925ecc54bcd1bf02b1d0d4d52"
dependencies = [
"async-stream",
"async-trait",
"axum",
"axum 0.7.5",
"base64 0.22.1",
"bytes",
"h2 0.4.4",
@@ -6550,6 +6661,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ad0f048c97dbd9faa9b7df56362b8ebcaa52adb06b498c050d2f4e32f90a7a8b"
dependencies = [
"matchers",
"nu-ansi-term",
"once_cell",
"regex",
"serde",
@@ -6586,14 +6698,14 @@ checksum = "e421abadd41a4225275504ea4d6566923418b7f05506fbc9c0fe86ba7396114b"
[[package]]
name = "tungstenite"
version = "0.21.0"
version = "0.20.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9ef1a641ea34f399a848dea702823bbecfb4c486f911735368f1f137cb8257e1"
checksum = "9e3dac10fd62eaf6617d3a904ae222845979aec67c615d1c842b4002c7666fb9"
dependencies = [
"byteorder",
"bytes",
"data-encoding",
"http 1.1.0",
"http 0.2.9",
"httparse",
"log",
"rand 0.8.5",
@@ -6821,7 +6933,7 @@ name = "vm_monitor"
version = "0.1.0"
dependencies = [
"anyhow",
"axum",
"axum 0.6.20",
"cgroups-rs",
"clap",
"futures",
@@ -6854,7 +6966,7 @@ dependencies = [
"anyhow",
"camino-tempfile",
"clap",
"env_logger",
"env_logger 0.10.2",
"log",
"postgres",
"postgres_ffi",
@@ -6862,19 +6974,6 @@ dependencies = [
"utils",
]
[[package]]
name = "wal_decoder"
version = "0.1.0"
dependencies = [
"anyhow",
"bytes",
"pageserver_api",
"postgres_ffi",
"serde",
"tracing",
"utils",
]
[[package]]
name = "walkdir"
version = "2.3.3"
@@ -7293,8 +7392,12 @@ version = "0.1.0"
dependencies = [
"ahash",
"anyhow",
"axum",
"axum-core",
"aws-config",
"aws-runtime",
"aws-sigv4",
"aws-smithy-async",
"aws-smithy-http",
"aws-smithy-types",
"base64 0.21.1",
"base64ct",
"bytes",
@@ -7324,7 +7427,6 @@ dependencies = [
"hyper 1.4.1",
"hyper-util",
"indexmap 1.9.3",
"indexmap 2.0.1",
"itertools 0.12.1",
"lazy_static",
"libc",
@@ -7336,7 +7438,6 @@ dependencies = [
"num-traits",
"once_cell",
"parquet",
"postgres-types",
"prettyplease",
"proc-macro2",
"prost",
@@ -7346,6 +7447,7 @@ dependencies = [
"regex-automata 0.4.3",
"regex-syntax 0.8.2",
"reqwest 0.12.4",
"rustls 0.21.11",
"scopeguard",
"serde",
"serde_json",
@@ -7361,7 +7463,6 @@ dependencies = [
"time",
"time-macros",
"tokio",
"tokio-postgres",
"tokio-stream",
"tokio-util",
"toml_edit",
@@ -7370,6 +7471,7 @@ dependencies = [
"tracing",
"tracing-core",
"url",
"uuid",
"zeroize",
"zstd",
"zstd-safe",

View File

@@ -33,7 +33,6 @@ members = [
"libs/postgres_ffi/wal_craft",
"libs/vm_monitor",
"libs/walproposer",
"libs/wal_decoder",
]
[workspace.package]
@@ -54,7 +53,7 @@ azure_storage_blobs = { version = "0.19", default-features = false, features = [
flate2 = "1.0.26"
async-stream = "0.3"
async-trait = "0.1"
aws-config = { version = "1.5", default-features = false, features=["rustls", "sso"] }
aws-config = { version = "1.5", default-features = false, features=["rustls"] }
aws-sdk-s3 = "1.52"
aws-sdk-iam = "1.46.0"
aws-smithy-async = { version = "1.2.1", default-features = false, features=["rt-tokio"] }
@@ -62,7 +61,7 @@ aws-smithy-types = "1.2"
aws-credential-types = "1.2.0"
aws-sigv4 = { version = "1.2", features = ["sign-http"] }
aws-types = "1.3"
axum = { version = "0.7.5", features = ["ws"] }
axum = { version = "0.6.20", features = ["ws"] }
base64 = "0.13.0"
bincode = "1.3"
bindgen = "0.70"
@@ -100,15 +99,14 @@ http-types = { version = "2", default-features = false }
http-body-util = "0.1.2"
humantime = "2.1"
humantime-serde = "1.1.1"
hyper0 = { package = "hyper", version = "0.14" }
hyper = "1.4"
hyper = "0.14"
hyper_1 = { package = "hyper", version = "1.4" }
hyper-util = "0.1"
tokio-tungstenite = "0.21.0"
tokio-tungstenite = "0.20.0"
indexmap = "2"
indoc = "2"
ipnet = "2.9.0"
itertools = "0.10"
itoa = "1.0.11"
jsonwebtoken = "9"
lasso = "0.7"
libc = "0.2"
@@ -239,7 +237,6 @@ tracing-utils = { version = "0.1", path = "./libs/tracing-utils/" }
utils = { version = "0.1", path = "./libs/utils/" }
vm_monitor = { version = "0.1", path = "./libs/vm_monitor/" }
walproposer = { version = "0.1", path = "./libs/walproposer/" }
wal_decoder = { version = "0.1", path = "./libs/wal_decoder" }
## Common library dependency
workspace_hack = { version = "0.1", path = "./workspace_hack/" }

View File

@@ -7,8 +7,6 @@ ARG IMAGE=build-tools
ARG TAG=pinned
ARG DEFAULT_PG_VERSION=17
ARG STABLE_PG_VERSION=16
ARG DEBIAN_VERSION=bullseye
ARG DEBIAN_FLAVOR=${DEBIAN_VERSION}-slim
# Build Postgres
FROM $REPOSITORY/$IMAGE:$TAG AS pg-build
@@ -59,7 +57,7 @@ RUN set -e \
# Build final image
#
FROM debian:${DEBIAN_FLAVOR}
FROM debian:bullseye-slim
ARG DEFAULT_PG_VERSION
WORKDIR /data

View File

@@ -1,7 +1,12 @@
ARG DEBIAN_VERSION=bullseye
FROM debian:bullseye-slim
FROM debian:${DEBIAN_VERSION}-slim
ARG DEBIAN_VERSION
# Use ARG as a build-time environment variable here to allow.
# It's not supposed to be set outside.
# Alternatively it can be obtained using the following command
# ```
# . /etc/os-release && echo "${VERSION_CODENAME}"
# ```
ARG DEBIAN_VERSION_CODENAME=bullseye
# Add nonroot user
RUN useradd -ms /bin/bash nonroot -b /home
@@ -37,14 +42,14 @@ RUN set -e \
libseccomp-dev \
libsqlite3-dev \
libssl-dev \
$([[ "${DEBIAN_VERSION}" = "bullseye" ]] && libstdc++-10-dev || libstdc++-11-dev) \
libstdc++-10-dev \
libtool \
libxml2-dev \
libxmlsec1-dev \
libxxhash-dev \
lsof \
make \
netcat-openbsd \
netcat \
net-tools \
openssh-client \
parallel \
@@ -73,7 +78,7 @@ RUN curl -sL "https://github.com/peak/s5cmd/releases/download/v${S5CMD_VERSION}/
# LLVM
ENV LLVM_VERSION=18
RUN curl -fsSL 'https://apt.llvm.org/llvm-snapshot.gpg.key' | apt-key add - \
&& echo "deb http://apt.llvm.org/${DEBIAN_VERSION}/ llvm-toolchain-${DEBIAN_VERSION}-${LLVM_VERSION} main" > /etc/apt/sources.list.d/llvm.stable.list \
&& echo "deb http://apt.llvm.org/${DEBIAN_VERSION_CODENAME}/ llvm-toolchain-${DEBIAN_VERSION_CODENAME}-${LLVM_VERSION} main" > /etc/apt/sources.list.d/llvm.stable.list \
&& apt update \
&& apt install -y clang-${LLVM_VERSION} llvm-${LLVM_VERSION} \
&& bash -c 'for f in /usr/bin/clang*-${LLVM_VERSION} /usr/bin/llvm*-${LLVM_VERSION}; do ln -s "${f}" "${f%-${LLVM_VERSION}}"; done' \
@@ -81,7 +86,7 @@ RUN curl -fsSL 'https://apt.llvm.org/llvm-snapshot.gpg.key' | apt-key add - \
# Install docker
RUN curl -fsSL https://download.docker.com/linux/ubuntu/gpg | gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg \
&& echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/debian ${DEBIAN_VERSION} stable" > /etc/apt/sources.list.d/docker.list \
&& echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/debian ${DEBIAN_VERSION_CODENAME} stable" > /etc/apt/sources.list.d/docker.list \
&& apt update \
&& apt install -y docker-ce docker-ce-cli \
&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*

View File

@@ -168,27 +168,27 @@ postgres-check-%: postgres-%
neon-pg-ext-%: postgres-%
+@echo "Compiling neon $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile install
+@echo "Compiling neon_walredo $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile install
+@echo "Compiling neon_rmgr $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-rmgr-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-rmgr-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_rmgr/Makefile install
+@echo "Compiling neon_test_utils $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile install
+@echo "Compiling neon_utils $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-utils-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_utils/Makefile install
@@ -220,7 +220,7 @@ neon-pg-clean-ext-%:
walproposer-lib: neon-pg-ext-v17
+@echo "Compiling walproposer-lib"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/walproposer-lib
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/walproposer-lib \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile walproposer-lib
cp $(POSTGRES_INSTALL_DIR)/v17/lib/libpgport.a $(POSTGRES_INSTALL_DIR)/build/walproposer-lib
@@ -333,7 +333,7 @@ postgres-%-pgindent: postgres-%-pg-bsd-indent postgres-%-typedefs.list
# Indent pxgn/neon.
.PHONY: neon-pgindent
neon-pgindent: postgres-v17-pg-bsd-indent neon-pg-ext-v17
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
FIND_TYPEDEF=$(ROOT_PROJECT_DIR)/vendor/postgres-v17/src/tools/find_typedef \
INDENT=$(POSTGRES_INSTALL_DIR)/build/v17/src/tools/pg_bsd_indent/pg_bsd_indent \
PGINDENT_SCRIPT=$(ROOT_PROJECT_DIR)/vendor/postgres-v17/src/tools/pgindent/pgindent \

View File

@@ -58,7 +58,7 @@ curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
1. Install XCode and dependencies
```
xcode-select --install
brew install protobuf openssl flex bison icu4c pkg-config m4
brew install protobuf openssl flex bison icu4c pkg-config
# add openssl to PATH, required for ed25519 keys generation in neon_local
echo 'export PATH="$(brew --prefix openssl)/bin:$PATH"' >> ~/.zshrc

View File

@@ -3,8 +3,7 @@ ARG REPOSITORY=neondatabase
ARG IMAGE=build-tools
ARG TAG=pinned
ARG BUILD_TAG
ARG DEBIAN_VERSION=bullseye
ARG DEBIAN_FLAVOR=${DEBIAN_VERSION}-slim
ARG DEBIAN_FLAVOR=bullseye-slim
#########################################################################################
#
@@ -12,23 +11,20 @@ ARG DEBIAN_FLAVOR=${DEBIAN_VERSION}-slim
#
#########################################################################################
FROM debian:$DEBIAN_FLAVOR AS build-deps
ARG DEBIAN_VERSION
ARG DEBIAN_FLAVOR
RUN case $DEBIAN_VERSION in \
RUN case $DEBIAN_FLAVOR in \
# Version-specific installs for Bullseye (PG14-PG16):
# The h3_pg extension needs a cmake 3.20+, but Debian bullseye has 3.18.
# Install newer version (3.25) from backports.
bullseye) \
bullseye*) \
echo "deb http://deb.debian.org/debian bullseye-backports main" > /etc/apt/sources.list.d/bullseye-backports.list; \
VERSION_INSTALLS="cmake/bullseye-backports cmake-data/bullseye-backports"; \
;; \
# Version-specific installs for Bookworm (PG17):
bookworm) \
bookworm*) \
VERSION_INSTALLS="cmake"; \
;; \
*) \
echo "Unknown Debian version ${DEBIAN_VERSION}" && exit 1 \
;; \
esac && \
apt update && \
apt install --no-install-recommends -y git autoconf automake libtool build-essential bison flex libreadline-dev \
@@ -113,30 +109,13 @@ RUN apt update && \
libcgal-dev libgdal-dev libgmp-dev libmpfr-dev libopenscenegraph-dev libprotobuf-c-dev \
protobuf-c-compiler xsltproc
# Postgis 3.5.0 requires SFCGAL 1.4+
#
# It would be nice to update all versions together, but we must solve the SFCGAL dependency first.
# SFCGAL > 1.3 requires CGAL > 5.2, Bullseye's libcgal-dev is 5.2
# and also we must check backward compatibility with older versions of PostGIS.
#
# Use new version only for v17
RUN case "${PG_VERSION}" in \
"v17") \
export SFCGAL_VERSION=1.4.1 \
export SFCGAL_CHECKSUM=1800c8a26241588f11cddcf433049e9b9aea902e923414d2ecef33a3295626c3 \
;; \
"v14" | "v15" | "v16") \
export SFCGAL_VERSION=1.3.10 \
export SFCGAL_CHECKSUM=4e39b3b2adada6254a7bdba6d297bb28e1a9835a9f879b74f37e2dab70203232 \
;; \
*) \
echo "unexpected PostgreSQL version" && exit 1 \
;; \
esac && \
RUN case "${PG_VERSION}" in "v17") \
mkdir -p /sfcgal && \
wget https://gitlab.com/sfcgal/SFCGAL/-/archive/v${SFCGAL_VERSION}/SFCGAL-v${SFCGAL_VERSION}.tar.gz -O SFCGAL.tar.gz && \
echo "${SFCGAL_CHECKSUM} SFCGAL.tar.gz" | sha256sum --check && \
echo "Postgis doensn't yet support PG17 (needs 3.4.3, if not higher)" && exit 0;; \
esac && \
wget https://gitlab.com/Oslandia/SFCGAL/-/archive/v1.3.10/SFCGAL-v1.3.10.tar.gz -O SFCGAL.tar.gz && \
echo "4e39b3b2adada6254a7bdba6d297bb28e1a9835a9f879b74f37e2dab70203232 SFCGAL.tar.gz" | sha256sum --check && \
mkdir sfcgal-src && cd sfcgal-src && tar xzf ../SFCGAL.tar.gz --strip-components=1 -C . && \
cmake -DCMAKE_BUILD_TYPE=Release . && make -j $(getconf _NPROCESSORS_ONLN) && \
DESTDIR=/sfcgal make install -j $(getconf _NPROCESSORS_ONLN) && \
@@ -144,27 +123,15 @@ RUN case "${PG_VERSION}" in \
ENV PATH="/usr/local/pgsql/bin:$PATH"
# Postgis 3.5.0 supports v17
RUN case "${PG_VERSION}" in \
"v17") \
export POSTGIS_VERSION=3.5.0 \
export POSTGIS_CHECKSUM=ca698a22cc2b2b3467ac4e063b43a28413f3004ddd505bdccdd74c56a647f510 \
;; \
"v14" | "v15" | "v16") \
export POSTGIS_VERSION=3.3.3 \
export POSTGIS_CHECKSUM=74eb356e3f85f14233791013360881b6748f78081cc688ff9d6f0f673a762d13 \
;; \
*) \
echo "unexpected PostgreSQL version" && exit 1 \
;; \
RUN case "${PG_VERSION}" in "v17") \
echo "Postgis doensn't yet support PG17 (needs 3.4.3, if not higher)" && exit 0;; \
esac && \
wget https://download.osgeo.org/postgis/source/postgis-${POSTGIS_VERSION}.tar.gz -O postgis.tar.gz && \
echo "${POSTGIS_CHECKSUM} postgis.tar.gz" | sha256sum --check && \
wget https://download.osgeo.org/postgis/source/postgis-3.3.3.tar.gz -O postgis.tar.gz && \
echo "74eb356e3f85f14233791013360881b6748f78081cc688ff9d6f0f673a762d13 postgis.tar.gz" | sha256sum --check && \
mkdir postgis-src && cd postgis-src && tar xzf ../postgis.tar.gz --strip-components=1 -C . && \
find /usr/local/pgsql -type f | sed 's|^/usr/local/pgsql/||' > /before.txt &&\
./autogen.sh && \
./configure --with-sfcgal=/usr/local/bin/sfcgal-config && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
cd extensions/postgis && \
make clean && \
@@ -185,27 +152,11 @@ RUN case "${PG_VERSION}" in \
cp /usr/local/pgsql/share/extension/address_standardizer.control /extensions/postgis && \
cp /usr/local/pgsql/share/extension/address_standardizer_data_us.control /extensions/postgis
# Uses versioned libraries, i.e. libpgrouting-3.4
# and may introduce function signature changes between releases
# i.e. release 3.5.0 has new signature for pg_dijkstra function
#
# Use new version only for v17
# last release v3.6.2 - Mar 30, 2024
RUN case "${PG_VERSION}" in \
"v17") \
export PGROUTING_VERSION=3.6.2 \
export PGROUTING_CHECKSUM=f4a1ed79d6f714e52548eca3bb8e5593c6745f1bde92eb5fb858efd8984dffa2 \
;; \
"v14" | "v15" | "v16") \
export PGROUTING_VERSION=3.4.2 \
export PGROUTING_CHECKSUM=cac297c07d34460887c4f3b522b35c470138760fe358e351ad1db4edb6ee306e \
;; \
*) \
echo "unexpected PostgreSQL version" && exit 1 \
;; \
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/pgRouting/pgrouting/archive/v${PGROUTING_VERSION}.tar.gz -O pgrouting.tar.gz && \
echo "${PGROUTING_CHECKSUM} pgrouting.tar.gz" | sha256sum --check && \
wget https://github.com/pgRouting/pgrouting/archive/v3.4.2.tar.gz -O pgrouting.tar.gz && \
echo "cac297c07d34460887c4f3b522b35c470138760fe358e351ad1db4edb6ee306e pgrouting.tar.gz" | sha256sum --check && \
mkdir pgrouting-src && cd pgrouting-src && tar xzf ../pgrouting.tar.gz --strip-components=1 -C . && \
mkdir build && cd build && \
cmake -DCMAKE_BUILD_TYPE=Release .. && \
@@ -264,9 +215,10 @@ FROM build-deps AS h3-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# not version-specific
# last release v4.1.0 - Jan 18, 2023
RUN mkdir -p /h3/usr/ && \
RUN case "${PG_VERSION}" in "v17") \
mkdir -p /h3/usr/ && \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/uber/h3/archive/refs/tags/v4.1.0.tar.gz -O h3.tar.gz && \
echo "ec99f1f5974846bde64f4513cf8d2ea1b8d172d2218ab41803bf6a63532272bc h3.tar.gz" | sha256sum --check && \
mkdir h3-src && cd h3-src && tar xzf ../h3.tar.gz --strip-components=1 -C . && \
@@ -277,9 +229,10 @@ RUN mkdir -p /h3/usr/ && \
cp -R /h3/usr / && \
rm -rf build
# not version-specific
# last release v4.1.3 - Jul 26, 2023
RUN wget https://github.com/zachasme/h3-pg/archive/refs/tags/v4.1.3.tar.gz -O h3-pg.tar.gz && \
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/zachasme/h3-pg/archive/refs/tags/v4.1.3.tar.gz -O h3-pg.tar.gz && \
echo "5c17f09a820859ffe949f847bebf1be98511fb8f1bd86f94932512c00479e324 h3-pg.tar.gz" | sha256sum --check && \
mkdir h3-pg-src && cd h3-pg-src && tar xzf ../h3-pg.tar.gz --strip-components=1 -C . && \
export PATH="/usr/local/pgsql/bin:$PATH" && \
@@ -298,10 +251,11 @@ FROM build-deps AS unit-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# not version-specific
# last release 7.9 - Sep 15, 2024
RUN wget https://github.com/df7cb/postgresql-unit/archive/refs/tags/7.9.tar.gz -O postgresql-unit.tar.gz && \
echo "e46de6245dcc8b2c2ecf29873dbd43b2b346773f31dd5ce4b8315895a052b456 postgresql-unit.tar.gz" | sha256sum --check && \
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/df7cb/postgresql-unit/archive/refs/tags/7.7.tar.gz -O postgresql-unit.tar.gz && \
echo "411d05beeb97e5a4abf17572bfcfbb5a68d98d1018918feff995f6ee3bb03e79 postgresql-unit.tar.gz" | sha256sum --check && \
mkdir postgresql-unit-src && cd postgresql-unit-src && tar xzf ../postgresql-unit.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
@@ -348,10 +302,12 @@ FROM build-deps AS pgjwt-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# not version-specific
# doesn't use releases, last commit f3d82fd - Mar 2, 2023
RUN wget https://github.com/michelp/pgjwt/archive/f3d82fd30151e754e19ce5d6a06c71c20689ce3d.tar.gz -O pgjwt.tar.gz && \
echo "dae8ed99eebb7593b43013f6532d772b12dfecd55548d2673f2dfd0163f6d2b9 pgjwt.tar.gz" | sha256sum --check && \
# 9742dab1b2f297ad3811120db7b21451bca2d3c9 made on 13/11/2021
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/michelp/pgjwt/archive/9742dab1b2f297ad3811120db7b21451bca2d3c9.tar.gz -O pgjwt.tar.gz && \
echo "cfdefb15007286f67d3d45510f04a6a7a495004be5b3aecb12cda667e774203f pgjwt.tar.gz" | sha256sum --check && \
mkdir pgjwt-src && cd pgjwt-src && tar xzf ../pgjwt.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgjwt.control
@@ -386,9 +342,10 @@ FROM build-deps AS pg-hashids-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# not version-specific
# last release v1.2.1 -Jan 12, 2018
RUN wget https://github.com/iCyberon/pg_hashids/archive/refs/tags/v1.2.1.tar.gz -O pg_hashids.tar.gz && \
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/iCyberon/pg_hashids/archive/refs/tags/v1.2.1.tar.gz -O pg_hashids.tar.gz && \
echo "74576b992d9277c92196dd8d816baa2cc2d8046fe102f3dcd7f3c3febed6822a pg_hashids.tar.gz" | sha256sum --check && \
mkdir pg_hashids-src && cd pg_hashids-src && tar xzf ../pg_hashids.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
@@ -448,9 +405,10 @@ FROM build-deps AS ip4r-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# not version-specific
# last release v2.4.2 - Jul 29, 2023
RUN wget https://github.com/RhodiumToad/ip4r/archive/refs/tags/2.4.2.tar.gz -O ip4r.tar.gz && \
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/RhodiumToad/ip4r/archive/refs/tags/2.4.2.tar.gz -O ip4r.tar.gz && \
echo "0f7b1f159974f49a47842a8ab6751aecca1ed1142b6d5e38d81b064b2ead1b4b ip4r.tar.gz" | sha256sum --check && \
mkdir ip4r-src && cd ip4r-src && tar xzf ../ip4r.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
@@ -467,9 +425,10 @@ FROM build-deps AS prefix-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# not version-specific
# last release v1.2.10 - Jul 5, 2023
RUN wget https://github.com/dimitri/prefix/archive/refs/tags/v1.2.10.tar.gz -O prefix.tar.gz && \
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/dimitri/prefix/archive/refs/tags/v1.2.10.tar.gz -O prefix.tar.gz && \
echo "4342f251432a5f6fb05b8597139d3ccde8dcf87e8ca1498e7ee931ca057a8575 prefix.tar.gz" | sha256sum --check && \
mkdir prefix-src && cd prefix-src && tar xzf ../prefix.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
@@ -486,9 +445,10 @@ FROM build-deps AS hll-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# not version-specific
# last release v2.18 - Aug 29, 2023
RUN wget https://github.com/citusdata/postgresql-hll/archive/refs/tags/v2.18.tar.gz -O hll.tar.gz && \
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions are not supported yet. Quit" && exit 0;; \
esac && \
wget https://github.com/citusdata/postgresql-hll/archive/refs/tags/v2.18.tar.gz -O hll.tar.gz && \
echo "e2f55a6f4c4ab95ee4f1b4a2b73280258c5136b161fe9d059559556079694f0e hll.tar.gz" | sha256sum --check && \
mkdir hll-src && cd hll-src && tar xzf ../hll.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
@@ -699,10 +659,11 @@ FROM build-deps AS pg-roaringbitmap-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# not version-specific
# last release v0.5.4 - Jun 28, 2022
ENV PATH="/usr/local/pgsql/bin/:$PATH"
RUN wget https://github.com/ChenHuajun/pg_roaringbitmap/archive/refs/tags/v0.5.4.tar.gz -O pg_roaringbitmap.tar.gz && \
RUN case "${PG_VERSION}" in "v17") \
echo "v17 extensions is not supported yet by pg_roaringbitmap. Quit" && exit 0;; \
esac && \
wget https://github.com/ChenHuajun/pg_roaringbitmap/archive/refs/tags/v0.5.4.tar.gz -O pg_roaringbitmap.tar.gz && \
echo "b75201efcb1c2d1b014ec4ae6a22769cc7a224e6e406a587f5784a37b6b5a2aa pg_roaringbitmap.tar.gz" | sha256sum --check && \
mkdir pg_roaringbitmap-src && cd pg_roaringbitmap-src && tar xzf ../pg_roaringbitmap.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) && \
@@ -719,27 +680,12 @@ FROM build-deps AS pg-semver-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# Release 0.40.0 breaks backward compatibility with previous versions
# see release note https://github.com/theory/pg-semver/releases/tag/v0.40.0
# Use new version only for v17
#
# last release v0.40.0 - Jul 22, 2024
ENV PATH="/usr/local/pgsql/bin/:$PATH"
RUN case "${PG_VERSION}" in \
"v17") \
export SEMVER_VERSION=0.40.0 \
export SEMVER_CHECKSUM=3e50bcc29a0e2e481e7b6d2bc937cadc5f5869f55d983b5a1aafeb49f5425cfc \
;; \
"v14" | "v15" | "v16") \
export SEMVER_VERSION=0.32.1 \
export SEMVER_CHECKSUM=fbdaf7512026d62eec03fad8687c15ed509b6ba395bff140acd63d2e4fbe25d7 \
;; \
*) \
echo "unexpected PostgreSQL version" && exit 1 \
;; \
RUN case "${PG_VERSION}" in "v17") \
echo "v17 is not supported yet by pg_semver. Quit" && exit 0;; \
esac && \
wget https://github.com/theory/pg-semver/archive/refs/tags/v${SEMVER_VERSION}.tar.gz -O pg_semver.tar.gz && \
echo "${SEMVER_CHECKSUM} pg_semver.tar.gz" | sha256sum --check && \
wget https://github.com/theory/pg-semver/archive/refs/tags/v0.32.1.tar.gz -O pg_semver.tar.gz && \
echo "fbdaf7512026d62eec03fad8687c15ed509b6ba395bff140acd63d2e4fbe25d7 pg_semver.tar.gz" | sha256sum --check && \
mkdir pg_semver-src && cd pg_semver-src && tar xzf ../pg_semver.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
@@ -929,11 +875,14 @@ ARG PG_VERSION
RUN case "${PG_VERSION}" in "v17") \
echo "pg_session_jwt does not yet have a release that supports pg17" && exit 0;; \
esac && \
wget https://github.com/neondatabase/pg_session_jwt/archive/5aee2625af38213650e1a07ae038fdc427250ee4.tar.gz -O pg_session_jwt.tar.gz && \
echo "5d91b10bc1347d36cffc456cb87bec25047935d6503dc652ca046f04760828e7 pg_session_jwt.tar.gz" | sha256sum --check && \
wget https://github.com/neondatabase/pg_session_jwt/archive/ff0a72440e8ff584dab24b3f9b7c00c56c660b8e.tar.gz -O pg_session_jwt.tar.gz && \
echo "1fbb2b5a339263bcf6daa847fad8bccbc0b451cea6a62e6d3bf232b0087f05cb pg_session_jwt.tar.gz" | sha256sum --check && \
mkdir pg_session_jwt-src && cd pg_session_jwt-src && tar xzf ../pg_session_jwt.tar.gz --strip-components=1 -C . && \
sed -i 's/pgrx = "=0.11.3"/pgrx = { version = "=0.11.3", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
cargo pgrx install --release
# it's needed to enable extension because it uses untrusted C language
# sed -i 's/superuser = false/superuser = true/g' /usr/local/pgsql/share/extension/pg_session_jwt.control && \
# echo "trusted = true" >> /usr/local/pgsql/share/extension/pg_session_jwt.control
#########################################################################################
#
@@ -1095,6 +1044,7 @@ RUN cd compute_tools && mold -run cargo build --locked --profile release-line-de
#########################################################################################
FROM debian:$DEBIAN_FLAVOR AS compute-tools-image
ARG DEBIAN_FLAVOR
COPY --from=compute-tools /home/nonroot/target/release-line-debug-size-lto/compute_ctl /usr/local/bin/compute_ctl
@@ -1105,6 +1055,7 @@ COPY --from=compute-tools /home/nonroot/target/release-line-debug-size-lto/compu
#########################################################################################
FROM debian:$DEBIAN_FLAVOR AS pgbouncer
ARG DEBIAN_FLAVOR
RUN set -e \
&& apt-get update \
&& apt-get install --no-install-recommends -y \
@@ -1127,20 +1078,6 @@ RUN set -e \
&& make -j $(nproc) dist_man_MANS= \
&& make install dist_man_MANS=
#########################################################################################
#
# Compile the Neon-specific `local_proxy` binary
#
#########################################################################################
FROM $REPOSITORY/$IMAGE:$TAG AS local_proxy
ARG BUILD_TAG
ENV BUILD_TAG=$BUILD_TAG
USER nonroot
# Copy entire project to get Cargo.* files with proper dependencies for the whole project
COPY --chown=nonroot . .
RUN mold -run cargo build --locked --profile release-line-debug-size-lto --bin local_proxy
#########################################################################################
#
# Layers "postgres-exporter" and "sql-exporter"
@@ -1259,7 +1196,7 @@ ENV PGDATABASE=postgres
#
#########################################################################################
FROM debian:$DEBIAN_FLAVOR
ARG DEBIAN_VERSION
ARG DEBIAN_FLAVOR
# Add user postgres
RUN mkdir /var/db && useradd -m -d /var/db/postgres postgres && \
echo "postgres:test_console_pass" | chpasswd && \
@@ -1279,10 +1216,6 @@ COPY --from=compute-tools --chown=postgres /home/nonroot/target/release-line-deb
COPY --from=pgbouncer /usr/local/pgbouncer/bin/pgbouncer /usr/local/bin/pgbouncer
COPY --chmod=0666 --chown=postgres compute/etc/pgbouncer.ini /etc/pgbouncer.ini
# local_proxy and its config
COPY --from=local_proxy --chown=postgres /home/nonroot/target/release-line-debug-size-lto/local_proxy /usr/local/bin/local_proxy
RUN mkdir -p /etc/local_proxy && chown postgres:postgres /etc/local_proxy
# Metrics exporter binaries and configuration files
COPY --from=postgres-exporter /bin/postgres_exporter /bin/postgres_exporter
COPY --from=sql-exporter /bin/sql_exporter /bin/sql_exporter
@@ -1307,22 +1240,19 @@ RUN mkdir /usr/local/download_extensions && chown -R postgres:postgres /usr/loca
RUN apt update && \
case $DEBIAN_VERSION in \
case $DEBIAN_FLAVOR in \
# Version-specific installs for Bullseye (PG14-PG16):
# libicu67, locales for collations (including ICU and plpgsql_check)
# libgdal28, libproj19 for PostGIS
bullseye) \
bullseye*) \
VERSION_INSTALLS="libicu67 libgdal28 libproj19"; \
;; \
# Version-specific installs for Bookworm (PG17):
# libicu72, locales for collations (including ICU and plpgsql_check)
# libgdal32, libproj25 for PostGIS
bookworm) \
bookworm*) \
VERSION_INSTALLS="libicu72 libgdal32 libproj25"; \
;; \
*) \
echo "Unknown Debian version ${DEBIAN_VERSION}" && exit 1 \
;; \
esac && \
apt install --no-install-recommends -y \
gdb \

View File

@@ -1,126 +0,0 @@
# Supplemental file for neondatabase/autoscaling's vm-builder, for producing the VM compute image.
---
commands:
- name: cgconfigparser
user: root
sysvInitAction: sysinit
shell: 'cgconfigparser -l /etc/cgconfig.conf -s 1664'
# restrict permissions on /neonvm/bin/resize-swap, because we grant access to compute_ctl for
# running it as root.
- name: chmod-resize-swap
user: root
sysvInitAction: sysinit
shell: 'chmod 711 /neonvm/bin/resize-swap'
- name: chmod-set-disk-quota
user: root
sysvInitAction: sysinit
shell: 'chmod 711 /neonvm/bin/set-disk-quota'
- name: pgbouncer
user: postgres
sysvInitAction: respawn
shell: '/usr/local/bin/pgbouncer /etc/pgbouncer.ini'
- name: local_proxy
user: postgres
sysvInitAction: respawn
shell: '/usr/local/bin/local_proxy --config-path /etc/local_proxy/config.json --pid-path /etc/local_proxy/pid --http 0.0.0.0:10432'
- name: postgres-exporter
user: nobody
sysvInitAction: respawn
shell: 'DATA_SOURCE_NAME="user=cloud_admin sslmode=disable dbname=postgres application_name=postgres-exporter" /bin/postgres_exporter'
- name: sql-exporter
user: nobody
sysvInitAction: respawn
shell: '/bin/sql_exporter -config.file=/etc/sql_exporter.yml -web.listen-address=:9399'
- name: sql-exporter-autoscaling
user: nobody
sysvInitAction: respawn
shell: '/bin/sql_exporter -config.file=/etc/sql_exporter_autoscaling.yml -web.listen-address=:9499'
shutdownHook: |
su -p postgres --session-command '/usr/local/bin/pg_ctl stop -D /var/db/postgres/compute/pgdata -m fast --wait -t 10'
files:
- filename: compute_ctl-sudoers
content: |
# Allow postgres user (which is what compute_ctl runs as) to run /neonvm/bin/resize-swap
# and /neonvm/bin/set-disk-quota as root without requiring entering a password (NOPASSWD),
# regardless of hostname (ALL)
postgres ALL=(root) NOPASSWD: /neonvm/bin/resize-swap, /neonvm/bin/set-disk-quota
- filename: cgconfig.conf
content: |
# Configuration for cgroups in VM compute nodes
group neon-postgres {
perm {
admin {
uid = postgres;
}
task {
gid = users;
}
}
memory {}
}
build: |
# Build cgroup-tools
#
# At time of writing (2023-03-14), debian bullseye has a version of cgroup-tools (technically
# libcgroup) that doesn't support cgroup v2 (version 0.41-11). Unfortunately, the vm-monitor
# requires cgroup v2, so we'll build cgroup-tools ourselves.
#
# At time of migration to bookworm (2024-10-09), debian has a version of libcgroup/cgroup-tools 2.0.2,
# and it _probably_ can be used as-is. However, we'll build it ourselves to minimise the changeset
# for debian version migration.
#
FROM debian:bookworm-slim as libcgroup-builder
ENV LIBCGROUP_VERSION=v2.0.3
RUN set -exu \
&& apt update \
&& apt install --no-install-recommends -y \
git \
ca-certificates \
automake \
cmake \
make \
gcc \
byacc \
flex \
libtool \
libpam0g-dev \
&& git clone --depth 1 -b $LIBCGROUP_VERSION https://github.com/libcgroup/libcgroup \
&& INSTALL_DIR="/libcgroup-install" \
&& mkdir -p "$INSTALL_DIR/bin" "$INSTALL_DIR/include" \
&& cd libcgroup \
# extracted from bootstrap.sh, with modified flags:
&& (test -d m4 || mkdir m4) \
&& autoreconf -fi \
&& rm -rf autom4te.cache \
&& CFLAGS="-O3" ./configure --prefix="$INSTALL_DIR" --sysconfdir=/etc --localstatedir=/var --enable-opaque-hierarchy="name=systemd" \
# actually build the thing...
&& make install
merge: |
# tweak nofile limits
RUN set -e \
&& echo 'fs.file-max = 1048576' >>/etc/sysctl.conf \
&& test ! -e /etc/security || ( \
echo '* - nofile 1048576' >>/etc/security/limits.conf \
&& echo 'root - nofile 1048576' >>/etc/security/limits.conf \
)
# Allow postgres user (compute_ctl) to run swap resizer.
# Need to install sudo in order to allow this.
#
# Also, remove the 'read' permission from group/other on /neonvm/bin/resize-swap, just to be safe.
RUN set -e \
&& apt update \
&& apt install --no-install-recommends -y \
sudo \
&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
COPY compute_ctl-sudoers /etc/sudoers.d/compute_ctl-sudoers
COPY cgconfig.conf /etc/cgconfig.conf
RUN set -e \
&& chmod 0644 /etc/cgconfig.conf
COPY --from=libcgroup-builder /libcgroup-install/bin/* /usr/bin/
COPY --from=libcgroup-builder /libcgroup-install/lib/* /usr/lib/
COPY --from=libcgroup-builder /libcgroup-install/sbin/* /usr/sbin/

View File

@@ -19,10 +19,6 @@ commands:
user: postgres
sysvInitAction: respawn
shell: '/usr/local/bin/pgbouncer /etc/pgbouncer.ini'
- name: local_proxy
user: postgres
sysvInitAction: respawn
shell: '/usr/local/bin/local_proxy --config-path /etc/local_proxy/config.json --pid-path /etc/local_proxy/pid --http 0.0.0.0:10432'
- name: postgres-exporter
user: nobody
sysvInitAction: respawn

View File

@@ -11,13 +11,12 @@ testing = []
[dependencies]
anyhow.workspace = true
camino.workspace = true
chrono.workspace = true
cfg-if.workspace = true
clap.workspace = true
flate2.workspace = true
futures.workspace = true
hyper0 = { workspace = true, features = ["full"] }
hyper = { workspace = true, features = ["full"] }
nix.workspace = true
notify.workspace = true
num_cpus.workspace = true

View File

@@ -402,7 +402,8 @@ fn start_postgres(
) -> Result<(Option<PostgresHandle>, StartPostgresResult)> {
// We got all we need, update the state.
let mut state = compute.state.lock().unwrap();
state.set_status(ComputeStatus::Init, &compute.state_changed);
state.status = ComputeStatus::Init;
compute.state_changed.notify_all();
info!(
"running compute with features: {:?}",

View File

@@ -34,7 +34,6 @@ use nix::sys::signal::{kill, Signal};
use remote_storage::{DownloadError, RemotePath};
use crate::checker::create_availability_check_data;
use crate::local_proxy;
use crate::logger::inlinify;
use crate::pg_helpers::*;
use crate::spec::*;
@@ -109,18 +108,6 @@ impl ComputeState {
metrics: ComputeMetrics::default(),
}
}
pub fn set_status(&mut self, status: ComputeStatus, state_changed: &Condvar) {
let prev = self.status;
info!("Changing compute status from {} to {}", prev, status);
self.status = status;
state_changed.notify_all();
}
pub fn set_failed_status(&mut self, err: anyhow::Error, state_changed: &Condvar) {
self.error = Some(format!("{err:?}"));
self.set_status(ComputeStatus::Failed, state_changed);
}
}
impl Default for ComputeState {
@@ -315,12 +302,15 @@ impl ComputeNode {
pub fn set_status(&self, status: ComputeStatus) {
let mut state = self.state.lock().unwrap();
state.set_status(status, &self.state_changed);
state.status = status;
self.state_changed.notify_all();
}
pub fn set_failed_status(&self, err: anyhow::Error) {
let mut state = self.state.lock().unwrap();
state.set_failed_status(err, &self.state_changed);
state.error = Some(format!("{err:?}"));
state.status = ComputeStatus::Failed;
self.state_changed.notify_all();
}
pub fn get_status(&self) -> ComputeStatus {
@@ -896,11 +886,6 @@ impl ComputeNode {
// 'Close' connection
drop(client);
if let Some(ref local_proxy) = spec.local_proxy_config {
info!("configuring local_proxy");
local_proxy::configure(local_proxy).context("apply_config local_proxy")?;
}
// Run migrations separately to not hold up cold starts
thread::spawn(move || {
let mut connstr = connstr.clone();
@@ -951,19 +936,6 @@ impl ComputeNode {
});
}
if let Some(ref local_proxy) = spec.local_proxy_config {
info!("configuring local_proxy");
// Spawn a thread to do the configuration,
// so that we don't block the main thread that starts Postgres.
let local_proxy = local_proxy.clone();
let _handle = Some(thread::spawn(move || {
if let Err(err) = local_proxy::configure(&local_proxy) {
error!("error while configuring local_proxy: {err:?}");
}
}));
}
// Write new config
let pgdata_path = Path::new(&self.pgdata);
let postgresql_conf_path = pgdata_path.join("postgresql.conf");
@@ -1051,19 +1023,6 @@ impl ComputeNode {
});
}
if let Some(local_proxy) = &pspec.spec.local_proxy_config {
info!("configuring local_proxy");
// Spawn a thread to do the configuration,
// so that we don't block the main thread that starts Postgres.
let local_proxy = local_proxy.clone();
let _handle = thread::spawn(move || {
if let Err(err) = local_proxy::configure(&local_proxy) {
error!("error while configuring local_proxy: {err:?}");
}
});
}
info!(
"start_compute spec.remote_extensions {:?}",
pspec.spec.remote_extensions
@@ -1484,28 +1443,6 @@ LIMIT 100",
info!("Pageserver config changed");
}
}
// Gather info about installed extensions
pub fn get_installed_extensions(&self) -> Result<()> {
let connstr = self.connstr.clone();
let rt = tokio::runtime::Builder::new_current_thread()
.enable_all()
.build()
.expect("failed to create runtime");
let result = rt
.block_on(crate::installed_extensions::get_installed_extensions(
connstr,
))
.expect("failed to get installed extensions");
info!(
"{}",
serde_json::to_string(&result).expect("failed to serialize extensions list")
);
Ok(())
}
}
pub fn forward_termination_signal() {

View File

@@ -24,7 +24,8 @@ fn configurator_main_loop(compute: &Arc<ComputeNode>) {
// Re-check the status after waking up
if state.status == ComputeStatus::ConfigurationPending {
info!("got configuration request");
state.set_status(ComputeStatus::Configuration, &compute.state_changed);
state.status = ComputeStatus::Configuration;
compute.state_changed.notify_all();
drop(state);
let mut new_status = ComputeStatus::Failed;

View File

@@ -165,32 +165,6 @@ async fn routes(req: Request<Body>, compute: &Arc<ComputeNode>) -> Response<Body
}
}
// get the list of installed extensions
// currently only used in python tests
// TODO: call it from cplane
(&Method::GET, "/installed_extensions") => {
info!("serving /installed_extensions GET request");
let status = compute.get_status();
if status != ComputeStatus::Running {
let msg = format!(
"invalid compute status for extensions request: {:?}",
status
);
error!(msg);
return Response::new(Body::from(msg));
}
let connstr = compute.connstr.clone();
let res = crate::installed_extensions::get_installed_extensions(connstr).await;
match res {
Ok(res) => render_json(Body::from(serde_json::to_string(&res).unwrap())),
Err(e) => render_json_error(
&format!("could not get list of installed extensions: {}", e),
StatusCode::INTERNAL_SERVER_ERROR,
),
}
}
// download extension files from remote extension storage on demand
(&Method::POST, route) if route.starts_with("/extension_server/") => {
info!("serving {:?} POST request", route);
@@ -314,7 +288,8 @@ async fn handle_configure_request(
return Err((msg, StatusCode::PRECONDITION_FAILED));
}
state.pspec = Some(parsed_spec);
state.set_status(ComputeStatus::ConfigurationPending, &compute.state_changed);
state.status = ComputeStatus::ConfigurationPending;
compute.state_changed.notify_all();
drop(state);
info!("set new spec and notified waiters");
}
@@ -387,15 +362,15 @@ async fn handle_terminate_request(compute: &Arc<ComputeNode>) -> Result<(), (Str
}
if state.status != ComputeStatus::Empty && state.status != ComputeStatus::Running {
let msg = format!(
"invalid compute status for termination request: {}",
state.status
"invalid compute status for termination request: {:?}",
state.status.clone()
);
return Err((msg, StatusCode::PRECONDITION_FAILED));
}
state.set_status(ComputeStatus::TerminationPending, &compute.state_changed);
state.status = ComputeStatus::TerminationPending;
compute.state_changed.notify_all();
drop(state);
}
forward_termination_signal();
info!("sent signal and notified waiters");
@@ -409,8 +384,7 @@ async fn handle_terminate_request(compute: &Arc<ComputeNode>) -> Result<(), (Str
while state.status != ComputeStatus::Terminated {
state = c.state_changed.wait(state).unwrap();
info!(
"waiting for compute to become {}, current status: {:?}",
ComputeStatus::Terminated,
"waiting for compute to become Terminated, current status: {:?}",
state.status
);
}

View File

@@ -53,20 +53,6 @@ paths:
schema:
$ref: "#/components/schemas/ComputeInsights"
/installed_extensions:
get:
tags:
- Info
summary: Get installed extensions.
description: ""
operationId: getInstalledExtensions
responses:
200:
description: List of installed extensions
content:
application/json:
schema:
$ref: "#/components/schemas/InstalledExtensions"
/info:
get:
tags:
@@ -409,24 +395,6 @@ components:
- configuration
example: running
InstalledExtensions:
type: object
properties:
extensions:
description: Contains list of installed extensions.
type: array
items:
type: object
properties:
extname:
type: string
versions:
type: array
items:
type: string
n_databases:
type: integer
#
# Errors
#

View File

@@ -1,80 +0,0 @@
use compute_api::responses::{InstalledExtension, InstalledExtensions};
use std::collections::HashMap;
use std::collections::HashSet;
use url::Url;
use anyhow::Result;
use postgres::{Client, NoTls};
use tokio::task;
/// We don't reuse get_existing_dbs() just for code clarity
/// and to make database listing query here more explicit.
///
/// Limit the number of databases to 500 to avoid excessive load.
fn list_dbs(client: &mut Client) -> Result<Vec<String>> {
// `pg_database.datconnlimit = -2` means that the database is in the
// invalid state
let databases = client
.query(
"SELECT datname FROM pg_catalog.pg_database
WHERE datallowconn
AND datconnlimit <> - 2
LIMIT 500",
&[],
)?
.iter()
.map(|row| {
let db: String = row.get("datname");
db
})
.collect();
Ok(databases)
}
/// Connect to every database (see list_dbs above) and get the list of installed extensions.
/// Same extension can be installed in multiple databases with different versions,
/// we only keep the highest and lowest version across all databases.
pub async fn get_installed_extensions(connstr: Url) -> Result<InstalledExtensions> {
let mut connstr = connstr.clone();
task::spawn_blocking(move || {
let mut client = Client::connect(connstr.as_str(), NoTls)?;
let databases: Vec<String> = list_dbs(&mut client)?;
let mut extensions_map: HashMap<String, InstalledExtension> = HashMap::new();
for db in databases.iter() {
connstr.set_path(db);
let mut db_client = Client::connect(connstr.as_str(), NoTls)?;
let extensions: Vec<(String, String)> = db_client
.query(
"SELECT extname, extversion FROM pg_catalog.pg_extension;",
&[],
)?
.iter()
.map(|row| (row.get("extname"), row.get("extversion")))
.collect();
for (extname, v) in extensions.iter() {
let version = v.to_string();
extensions_map
.entry(extname.to_string())
.and_modify(|e| {
e.versions.insert(version.clone());
// count the number of databases where the extension is installed
e.n_databases += 1;
})
.or_insert(InstalledExtension {
extname: extname.to_string(),
versions: HashSet::from([version.clone()]),
n_databases: 1,
});
}
}
Ok(InstalledExtensions {
extensions: extensions_map.values().cloned().collect(),
})
})
.await?
}

View File

@@ -2,9 +2,6 @@
//! configuration.
#![deny(unsafe_code)]
#![deny(clippy::undocumented_unsafe_blocks)]
extern crate hyper0 as hyper;
pub mod checker;
pub mod config;
pub mod configurator;
@@ -15,8 +12,6 @@ pub mod catalog;
pub mod compute;
pub mod disk_quota;
pub mod extension_server;
pub mod installed_extensions;
pub mod local_proxy;
pub mod lsn_lease;
mod migration;
pub mod monitor;

View File

@@ -1,56 +0,0 @@
//! Local Proxy is a feature of our BaaS Neon Authorize project.
//!
//! Local Proxy validates JWTs and manages the pg_session_jwt extension.
//! It also maintains a connection pool to postgres.
use anyhow::{Context, Result};
use camino::Utf8Path;
use compute_api::spec::LocalProxySpec;
use nix::sys::signal::Signal;
use utils::pid_file::{self, PidFileRead};
pub fn configure(local_proxy: &LocalProxySpec) -> Result<()> {
write_local_proxy_conf("/etc/local_proxy/config.json".as_ref(), local_proxy)?;
notify_local_proxy("/etc/local_proxy/pid".as_ref())?;
Ok(())
}
/// Create or completely rewrite configuration file specified by `path`
fn write_local_proxy_conf(path: &Utf8Path, local_proxy: &LocalProxySpec) -> Result<()> {
let config =
serde_json::to_string_pretty(local_proxy).context("serializing LocalProxySpec to json")?;
std::fs::write(path, config).with_context(|| format!("writing {path}"))?;
Ok(())
}
/// Notify local proxy about a new config file.
fn notify_local_proxy(path: &Utf8Path) -> Result<()> {
match pid_file::read(path)? {
// if the file doesn't exist, or isn't locked, local_proxy isn't running
// and will naturally pick up our config later
PidFileRead::NotExist | PidFileRead::NotHeldByAnyProcess(_) => {}
PidFileRead::LockedByOtherProcess(pid) => {
// From the pid_file docs:
//
// > 1. The other process might exit at any time, turning the given PID stale.
// > 2. There is a small window in which `claim_for_current_process` has already
// > locked the file but not yet updates its contents. [`read`] will return
// > this variant here, but with the old file contents, i.e., a stale PID.
// >
// > The kernel is free to recycle PID once it has been `wait(2)`ed upon by
// > its creator. Thus, acting upon a stale PID, e.g., by issuing a `kill`
// > system call on it, bears the risk of killing an unrelated process.
// > This is an inherent limitation of using pidfiles.
// > The only race-free solution is to have a supervisor-process with a lifetime
// > that exceeds that of all of its child-processes (e.g., `runit`, `supervisord`).
//
// This is an ok risk as we only send a SIGHUP which likely won't actually
// kill the process, only reload config.
nix::sys::signal::kill(pid, Signal::SIGHUP).context("sending signal to local_proxy")?;
}
}
Ok(())
}

View File

@@ -1,4 +1,3 @@
use std::collections::HashSet;
use std::fs::File;
use std::path::Path;
use std::str::FromStr;
@@ -190,15 +189,6 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
let mut xact = client.transaction()?;
let existing_roles: Vec<Role> = get_existing_roles(&mut xact)?;
let mut jwks_roles = HashSet::new();
if let Some(local_proxy) = &spec.local_proxy_config {
for jwks_setting in local_proxy.jwks.iter().flatten() {
for role_name in &jwks_setting.role_names {
jwks_roles.insert(role_name.clone());
}
}
}
// Print a list of existing Postgres roles (only in debug mode)
if span_enabled!(Level::INFO) {
let mut vec = Vec::new();
@@ -318,9 +308,6 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
"CREATE ROLE {} INHERIT CREATEROLE CREATEDB BYPASSRLS REPLICATION IN ROLE neon_superuser",
name.pg_quote()
);
if jwks_roles.contains(name.as_str()) {
query = format!("CREATE ROLE {}", name.pg_quote());
}
info!("running role create query: '{}'", &query);
query.push_str(&role.to_pg_options());
xact.execute(query.as_str(), &[])?;

View File

@@ -14,7 +14,7 @@ humantime.workspace = true
nix.workspace = true
once_cell.workspace = true
humantime-serde.workspace = true
hyper0.workspace = true
hyper.workspace = true
regex.workspace = true
reqwest = { workspace = true, features = ["blocking", "json"] }
scopeguard.workspace = true

View File

@@ -97,21 +97,7 @@ impl ComputeControlPlane {
for endpoint_dir in std::fs::read_dir(env.endpoints_path())
.with_context(|| format!("failed to list {}", env.endpoints_path().display()))?
{
let ep_res = Endpoint::from_dir_entry(endpoint_dir?, &env);
let ep = match ep_res {
Ok(ep) => ep,
Err(e) => match e.downcast::<std::io::Error>() {
Ok(e) => {
// A parallel task could delete an endpoint while we have just scanned the directory
if e.kind() == std::io::ErrorKind::NotFound {
continue;
} else {
Err(e)?
}
}
Err(e) => Err(e)?,
},
};
let ep = Endpoint::from_dir_entry(endpoint_dir?, &env)?;
endpoints.insert(ep.endpoint_id.clone(), Arc::new(ep));
}
@@ -613,7 +599,6 @@ impl Endpoint {
remote_extensions,
pgbouncer_settings: None,
shard_stripe_size: Some(shard_stripe_size),
local_proxy_config: None,
};
let spec_path = self.endpoint_path().join("spec.json");
std::fs::write(spec_path, serde_json::to_string_pretty(&spec)?)?;

View File

@@ -3,7 +3,7 @@ use crate::{
local_env::{LocalEnv, NeonStorageControllerConf},
};
use camino::{Utf8Path, Utf8PathBuf};
use hyper0::Uri;
use hyper::Uri;
use nix::unistd::Pid;
use pageserver_api::{
controller_api::{

View File

@@ -5,7 +5,7 @@
Currently we build two main images:
- [neondatabase/neon](https://hub.docker.com/repository/docker/neondatabase/neon) — image with pre-built `pageserver`, `safekeeper` and `proxy` binaries and all the required runtime dependencies. Built from [/Dockerfile](/Dockerfile).
- [neondatabase/compute-node-v16](https://hub.docker.com/repository/docker/neondatabase/compute-node-v16) — compute node image with pre-built Postgres binaries from [neondatabase/postgres](https://github.com/neondatabase/postgres). Similar images exist for v15 and v14. Built from [/compute-node/Dockerfile](/compute/Dockerfile.compute-node).
- [neondatabase/compute-node-v16](https://hub.docker.com/repository/docker/neondatabase/compute-node-v16) — compute node image with pre-built Postgres binaries from [neondatabase/postgres](https://github.com/neondatabase/postgres). Similar images exist for v15 and v14.
And additional intermediate image:

View File

@@ -1,8 +1,5 @@
//! Structs representing the JSON formats used in the compute_ctl's HTTP API.
use std::collections::HashSet;
use std::fmt::Display;
use chrono::{DateTime, Utc};
use serde::{Deserialize, Serialize, Serializer};
@@ -61,21 +58,6 @@ pub enum ComputeStatus {
Terminated,
}
impl Display for ComputeStatus {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
ComputeStatus::Empty => f.write_str("empty"),
ComputeStatus::ConfigurationPending => f.write_str("configuration-pending"),
ComputeStatus::Init => f.write_str("init"),
ComputeStatus::Running => f.write_str("running"),
ComputeStatus::Configuration => f.write_str("configuration"),
ComputeStatus::Failed => f.write_str("failed"),
ComputeStatus::TerminationPending => f.write_str("termination-pending"),
ComputeStatus::Terminated => f.write_str("terminated"),
}
}
}
fn rfc3339_serialize<S>(x: &Option<DateTime<Utc>>, s: S) -> Result<S::Ok, S::Error>
where
S: Serializer,
@@ -156,15 +138,3 @@ pub enum ControlPlaneComputeStatus {
// should be able to start with provided spec.
Attached,
}
#[derive(Clone, Debug, Default, Serialize)]
pub struct InstalledExtension {
pub extname: String,
pub versions: HashSet<String>,
pub n_databases: u32, // Number of databases using this extension
}
#[derive(Clone, Debug, Default, Serialize)]
pub struct InstalledExtensions {
pub extensions: Vec<InstalledExtension>,
}

View File

@@ -106,10 +106,6 @@ pub struct ComputeSpec {
// Stripe size for pageserver sharding, in pages
#[serde(default)]
pub shard_stripe_size: Option<usize>,
/// Local Proxy configuration used for JWT authentication
#[serde(default)]
pub local_proxy_config: Option<LocalProxySpec>,
}
/// Feature flag to signal `compute_ctl` to enable certain experimental functionality.
@@ -282,13 +278,11 @@ pub struct GenericOption {
/// declare a `trait` on it.
pub type GenericOptions = Option<Vec<GenericOption>>;
/// Configured the local_proxy application with the relevant JWKS and roles it should
/// Configured the local-proxy application with the relevant JWKS and roles it should
/// use for authorizing connect requests using JWT.
#[derive(Clone, Debug, Deserialize, Serialize)]
pub struct LocalProxySpec {
#[serde(default)]
#[serde(skip_serializing_if = "Option::is_none")]
pub jwks: Option<Vec<JwksSettings>>,
pub jwks: Vec<JwksSettings>,
}
#[derive(Clone, Debug, Deserialize, Serialize)]

View File

@@ -104,7 +104,8 @@ pub struct ConfigToml {
pub image_compression: ImageCompressionAlgorithm,
pub ephemeral_bytes_per_memory_kb: usize,
pub l0_flush: Option<crate::models::L0FlushConfig>,
pub virtual_file_io_mode: Option<crate::models::virtual_file::IoMode>,
pub virtual_file_direct_io: crate::models::virtual_file::DirectIoMode,
pub io_buffer_alignment: usize,
}
#[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
@@ -295,14 +296,7 @@ pub mod defaults {
pub const DEFAULT_INGEST_BATCH_SIZE: u64 = 100;
/// Soft limit for the maximum size of a vectored read.
///
/// This is determined by the largest NeonWalRecord that can exist (minus dbdir and reldir keys
/// which are bounded by the blob io limits only). As of this writing, that is a `NeonWalRecord::ClogSetCommitted` record,
/// with 32k xids. That's the max number of XIDS on a single CLOG page. The size of such a record
/// is `sizeof(Transactionid) * 32768 + (some fixed overhead from 'timestamp`, the Vec length and whatever extra serde serialization adds)`.
/// That is, slightly above 128 kB.
pub const DEFAULT_MAX_VECTORED_READ_BYTES: usize = 130 * 1024; // 130 KiB
pub const DEFAULT_MAX_VECTORED_READ_BYTES: usize = 128 * 1024; // 128 KiB
pub const DEFAULT_IMAGE_COMPRESSION: ImageCompressionAlgorithm =
ImageCompressionAlgorithm::Zstd { level: Some(1) };
@@ -387,7 +381,10 @@ impl Default for ConfigToml {
image_compression: (DEFAULT_IMAGE_COMPRESSION),
ephemeral_bytes_per_memory_kb: (DEFAULT_EPHEMERAL_BYTES_PER_MEMORY_KB),
l0_flush: None,
virtual_file_io_mode: None,
virtual_file_direct_io: crate::models::virtual_file::DirectIoMode::default(),
io_buffer_alignment: DEFAULT_IO_BUFFER_ALIGNMENT,
tenant_config: TenantConfigToml::default(),
}
}

View File

@@ -748,16 +748,6 @@ impl Key {
self.field1 == 0x00 && self.field4 != 0 && self.field6 != 0xffffffff
}
#[inline(always)]
pub fn is_rel_dir_key(&self) -> bool {
self.field1 == 0x00
&& self.field2 != 0
&& self.field3 != 0
&& self.field4 == 0
&& self.field5 == 0
&& self.field6 == 1
}
/// Guaranteed to return `Ok()` if [`Self::is_rel_block_key`] returns `true` for `key`.
#[inline(always)]
pub fn to_rel_block(self) -> anyhow::Result<(RelTag, BlockNumber)> {

View File

@@ -5,11 +5,9 @@ pub mod controller_api;
pub mod key;
pub mod keyspace;
pub mod models;
pub mod record;
pub mod reltag;
pub mod shard;
/// Public API types
pub mod upcall_api;
pub mod value;
pub mod config;

View File

@@ -972,6 +972,8 @@ pub struct TopTenantShardsResponse {
}
pub mod virtual_file {
use std::path::PathBuf;
#[derive(
Copy,
Clone,
@@ -992,45 +994,50 @@ pub mod virtual_file {
}
/// Direct IO modes for a pageserver.
#[derive(
Copy,
Clone,
PartialEq,
Eq,
Hash,
strum_macros::EnumString,
strum_macros::Display,
serde_with::DeserializeFromStr,
serde_with::SerializeDisplay,
Debug,
)]
#[strum(serialize_all = "kebab-case")]
#[repr(u8)]
pub enum IoMode {
/// Uses buffered IO.
Buffered,
/// Uses direct IO, error out if the operation fails.
#[cfg(target_os = "linux")]
Direct,
#[derive(Debug, PartialEq, Eq, Clone, serde::Deserialize, serde::Serialize, Default)]
#[serde(tag = "mode", rename_all = "kebab-case", deny_unknown_fields)]
pub enum DirectIoMode {
/// Direct IO disabled (uses usual buffered IO).
#[default]
Disabled,
/// Direct IO disabled (performs checks and perf simulations).
Evaluate {
/// Alignment check level
alignment_check: DirectIoAlignmentCheckLevel,
/// Latency padded for performance simulation.
latency_padding: DirectIoLatencyPadding,
},
/// Direct IO enabled.
Enabled {
/// Actions to perform on alignment error.
on_alignment_error: DirectIoOnAlignmentErrorAction,
},
}
impl IoMode {
pub const fn preferred() -> Self {
Self::Buffered
}
#[derive(Debug, PartialEq, Eq, Clone, serde::Deserialize, serde::Serialize, Default)]
#[serde(rename_all = "kebab-case")]
pub enum DirectIoAlignmentCheckLevel {
#[default]
Error,
Log,
None,
}
impl TryFrom<u8> for IoMode {
type Error = u8;
#[derive(Debug, PartialEq, Eq, Clone, serde::Deserialize, serde::Serialize, Default)]
#[serde(rename_all = "kebab-case")]
pub enum DirectIoOnAlignmentErrorAction {
Error,
#[default]
FallbackToBuffered,
}
fn try_from(value: u8) -> Result<Self, Self::Error> {
Ok(match value {
v if v == (IoMode::Buffered as u8) => IoMode::Buffered,
#[cfg(target_os = "linux")]
v if v == (IoMode::Direct as u8) => IoMode::Direct,
x => return Err(x),
})
}
#[derive(Debug, PartialEq, Eq, Clone, serde::Deserialize, serde::Serialize, Default)]
#[serde(tag = "type", rename_all = "kebab-case")]
pub enum DirectIoLatencyPadding {
/// Pad virtual file operations with IO to a fake file.
FakeFileRW { path: PathBuf },
#[default]
None,
}
}

View File

@@ -1,113 +0,0 @@
//! This module defines the WAL record format used within the pageserver.
use bytes::Bytes;
use postgres_ffi::record::{describe_postgres_wal_record, MultiXactMember};
use postgres_ffi::{MultiXactId, MultiXactOffset, TimestampTz, TransactionId};
use serde::{Deserialize, Serialize};
use utils::bin_ser::DeserializeError;
/// Each update to a page is represented by a NeonWalRecord. It can be a wrapper
/// around a PostgreSQL WAL record, or a custom neon-specific "record".
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
pub enum NeonWalRecord {
/// Native PostgreSQL WAL record
Postgres { will_init: bool, rec: Bytes },
/// Clear bits in heap visibility map. ('flags' is bitmap of bits to clear)
ClearVisibilityMapFlags {
new_heap_blkno: Option<u32>,
old_heap_blkno: Option<u32>,
flags: u8,
},
/// Mark transaction IDs as committed on a CLOG page
ClogSetCommitted {
xids: Vec<TransactionId>,
timestamp: TimestampTz,
},
/// Mark transaction IDs as aborted on a CLOG page
ClogSetAborted { xids: Vec<TransactionId> },
/// Extend multixact offsets SLRU
MultixactOffsetCreate {
mid: MultiXactId,
moff: MultiXactOffset,
},
/// Extend multixact members SLRU.
MultixactMembersCreate {
moff: MultiXactOffset,
members: Vec<MultiXactMember>,
},
/// Update the map of AUX files, either writing or dropping an entry
AuxFile {
file_path: String,
content: Option<Bytes>,
},
/// A testing record for unit testing purposes. It supports append data to an existing image, or clear it.
#[cfg(feature = "testing")]
Test {
/// Append a string to the image.
append: String,
/// Clear the image before appending.
clear: bool,
/// Treat this record as an init record. `clear` should be set to true if this field is set
/// to true. This record does not need the history WALs to reconstruct. See [`NeonWalRecord::will_init`] and
/// its references in `timeline.rs`.
will_init: bool,
},
}
impl NeonWalRecord {
/// Does replaying this WAL record initialize the page from scratch, or does
/// it need to be applied over the previous image of the page?
pub fn will_init(&self) -> bool {
// If you change this function, you'll also need to change ValueBytes::will_init
match self {
NeonWalRecord::Postgres { will_init, rec: _ } => *will_init,
#[cfg(feature = "testing")]
NeonWalRecord::Test { will_init, .. } => *will_init,
// None of the special neon record types currently initialize the page
_ => false,
}
}
#[cfg(feature = "testing")]
pub fn wal_append(s: impl AsRef<str>) -> Self {
Self::Test {
append: s.as_ref().to_string(),
clear: false,
will_init: false,
}
}
#[cfg(feature = "testing")]
pub fn wal_clear() -> Self {
Self::Test {
append: "".to_string(),
clear: true,
will_init: false,
}
}
#[cfg(feature = "testing")]
pub fn wal_init() -> Self {
Self::Test {
append: "".to_string(),
clear: true,
will_init: true,
}
}
}
/// Build a human-readable string to describe a WAL record
///
/// For debugging purposes
pub fn describe_wal_record(rec: &NeonWalRecord) -> Result<String, DeserializeError> {
match rec {
NeonWalRecord::Postgres { will_init, rec } => Ok(format!(
"will_init: {}, {}",
will_init,
describe_postgres_wal_record(rec)?
)),
_ => Ok(format!("{:?}", rec)),
}
}

View File

@@ -15,7 +15,6 @@ memoffset.workspace = true
thiserror.workspace = true
serde.workspace = true
utils.workspace = true
tracing.workspace = true
[dev-dependencies]
env_logger.workspace = true

View File

@@ -216,7 +216,6 @@ macro_rules! enum_pgversion {
}
pub mod pg_constants;
pub mod record;
pub mod relfile_utils;
// Export some widely used datatypes that are unlikely to change across Postgres versions

View File

@@ -16,7 +16,7 @@ aws-sdk-s3.workspace = true
bytes.workspace = true
camino = { workspace = true, features = ["serde1"] }
humantime-serde.workspace = true
hyper0 = { workspace = true, features = ["stream"] }
hyper = { workspace = true, features = ["stream"] }
futures.workspace = true
serde.workspace = true
serde_json.workspace = true

View File

@@ -14,7 +14,7 @@ use std::time::SystemTime;
use super::REMOTE_STORAGE_PREFIX_SEPARATOR;
use anyhow::Result;
use azure_core::request_options::{IfMatchCondition, MaxResults, Metadata, Range};
use azure_core::request_options::{MaxResults, Metadata, Range};
use azure_core::{Continuable, RetryOptions};
use azure_identity::DefaultAzureCredential;
use azure_storage::StorageCredentials;
@@ -33,10 +33,10 @@ use tracing::debug;
use utils::backoff;
use crate::metrics::{start_measuring_requests, AttemptOutcome, RequestKind};
use crate::ListingObject;
use crate::{
config::AzureConfig, error::Cancelled, ConcurrencyLimiter, Download, DownloadError,
DownloadOpts, Listing, ListingMode, ListingObject, RemotePath, RemoteStorage, StorageMetadata,
TimeTravelError, TimeoutOrCancel,
config::AzureConfig, error::Cancelled, ConcurrencyLimiter, Download, DownloadError, Listing,
ListingMode, RemotePath, RemoteStorage, StorageMetadata, TimeTravelError, TimeoutOrCancel,
};
pub struct AzureBlobStorage {
@@ -259,7 +259,6 @@ fn to_download_error(error: azure_core::Error) -> DownloadError {
if let Some(http_err) = error.as_http_error() {
match http_err.status() {
StatusCode::NotFound => DownloadError::NotFound,
StatusCode::NotModified => DownloadError::Unmodified,
StatusCode::BadRequest => DownloadError::BadInput(anyhow::Error::new(error)),
_ => DownloadError::Other(anyhow::Error::new(error)),
}
@@ -485,23 +484,32 @@ impl RemoteStorage for AzureBlobStorage {
async fn download(
&self,
from: &RemotePath,
opts: &DownloadOpts,
cancel: &CancellationToken,
) -> Result<Download, DownloadError> {
let blob_client = self.client.blob_client(self.relative_path_to_name(from));
let builder = blob_client.get();
self.download_for_builder(builder, cancel).await
}
async fn download_byte_range(
&self,
from: &RemotePath,
start_inclusive: u64,
end_exclusive: Option<u64>,
cancel: &CancellationToken,
) -> Result<Download, DownloadError> {
let blob_client = self.client.blob_client(self.relative_path_to_name(from));
let mut builder = blob_client.get();
if let Some(ref etag) = opts.etag {
builder = builder.if_match(IfMatchCondition::NotMatch(etag.to_string()))
}
if let Some((start, end)) = opts.byte_range() {
builder = builder.range(match end {
Some(end) => Range::Range(start..end),
None => Range::RangeFrom(start..),
});
}
let range: Range = if let Some(end_exclusive) = end_exclusive {
(start_inclusive..end_exclusive).into()
} else {
(start_inclusive..).into()
};
builder = builder.range(range);
self.download_for_builder(builder, cancel).await
}

View File

@@ -5,8 +5,6 @@ pub enum DownloadError {
BadInput(anyhow::Error),
/// The file was not found in the remote storage.
NotFound,
/// The caller provided an ETag, and the file was not modified.
Unmodified,
/// A cancellation token aborted the download, typically during
/// tenant detach or process shutdown.
Cancelled,
@@ -26,7 +24,6 @@ impl std::fmt::Display for DownloadError {
write!(f, "Failed to download a remote file due to user input: {e}")
}
DownloadError::NotFound => write!(f, "No file found for the remote object id given"),
DownloadError::Unmodified => write!(f, "File was not modified"),
DownloadError::Cancelled => write!(f, "Cancelled, shutting down"),
DownloadError::Timeout => write!(f, "timeout"),
DownloadError::Other(e) => write!(f, "Failed to download a remote file: {e:?}"),
@@ -41,7 +38,7 @@ impl DownloadError {
pub fn is_permanent(&self) -> bool {
use DownloadError::*;
match self {
BadInput(_) | NotFound | Unmodified | Cancelled => true,
BadInput(_) | NotFound | Cancelled => true,
Timeout | Other(_) => false,
}
}

View File

@@ -19,8 +19,7 @@ mod simulate_failures;
mod support;
use std::{
collections::HashMap, fmt::Debug, num::NonZeroU32, ops::Bound, pin::Pin, sync::Arc,
time::SystemTime,
collections::HashMap, fmt::Debug, num::NonZeroU32, pin::Pin, sync::Arc, time::SystemTime,
};
use anyhow::Context;
@@ -162,63 +161,6 @@ pub struct Listing {
pub keys: Vec<ListingObject>,
}
/// Options for downloads. The default value is a plain GET.
pub struct DownloadOpts {
/// If given, returns [`DownloadError::Unmodified`] if the object still has
/// the same ETag (using If-None-Match).
pub etag: Option<Etag>,
/// The start of the byte range to download, or unbounded.
pub byte_start: Bound<u64>,
/// The end of the byte range to download, or unbounded. Must be after the
/// start bound.
pub byte_end: Bound<u64>,
}
impl Default for DownloadOpts {
fn default() -> Self {
Self {
etag: Default::default(),
byte_start: Bound::Unbounded,
byte_end: Bound::Unbounded,
}
}
}
impl DownloadOpts {
/// Returns the byte range with inclusive start and exclusive end, or None
/// if unbounded.
pub fn byte_range(&self) -> Option<(u64, Option<u64>)> {
if self.byte_start == Bound::Unbounded && self.byte_end == Bound::Unbounded {
return None;
}
let start = match self.byte_start {
Bound::Excluded(i) => i + 1,
Bound::Included(i) => i,
Bound::Unbounded => 0,
};
let end = match self.byte_end {
Bound::Excluded(i) => Some(i),
Bound::Included(i) => Some(i + 1),
Bound::Unbounded => None,
};
if let Some(end) = end {
assert!(start < end, "range end {end} at or before start {start}");
}
Some((start, end))
}
/// Returns the byte range as an RFC 2616 Range header value with inclusive
/// bounds, or None if unbounded.
pub fn byte_range_header(&self) -> Option<String> {
self.byte_range()
.map(|(start, end)| (start, end.map(|end| end - 1))) // make end inclusive
.map(|(start, end)| match end {
Some(end) => format!("bytes={start}-{end}"),
None => format!("bytes={start}-"),
})
}
}
/// Storage (potentially remote) API to manage its state.
/// This storage tries to be unaware of any layered repository context,
/// providing basic CRUD operations for storage files.
@@ -303,7 +245,21 @@ pub trait RemoteStorage: Send + Sync + 'static {
async fn download(
&self,
from: &RemotePath,
opts: &DownloadOpts,
cancel: &CancellationToken,
) -> Result<Download, DownloadError>;
/// Streams a given byte range of the remote storage entry contents.
///
/// The returned download stream will obey initial timeout and cancellation signal by erroring
/// on whichever happens first. Only one of the reasons will fail the stream, which is usually
/// enough for `tokio::io::copy_buf` usage. If needed the error can be filtered out.
///
/// Returns the metadata, if any was stored with the file previously.
async fn download_byte_range(
&self,
from: &RemotePath,
start_inclusive: u64,
end_exclusive: Option<u64>,
cancel: &CancellationToken,
) -> Result<Download, DownloadError>;
@@ -445,18 +401,43 @@ impl<Other: RemoteStorage> GenericRemoteStorage<Arc<Other>> {
}
}
/// See [`RemoteStorage::download`]
pub async fn download(
&self,
from: &RemotePath,
opts: &DownloadOpts,
cancel: &CancellationToken,
) -> Result<Download, DownloadError> {
match self {
Self::LocalFs(s) => s.download(from, opts, cancel).await,
Self::AwsS3(s) => s.download(from, opts, cancel).await,
Self::AzureBlob(s) => s.download(from, opts, cancel).await,
Self::Unreliable(s) => s.download(from, opts, cancel).await,
Self::LocalFs(s) => s.download(from, cancel).await,
Self::AwsS3(s) => s.download(from, cancel).await,
Self::AzureBlob(s) => s.download(from, cancel).await,
Self::Unreliable(s) => s.download(from, cancel).await,
}
}
pub async fn download_byte_range(
&self,
from: &RemotePath,
start_inclusive: u64,
end_exclusive: Option<u64>,
cancel: &CancellationToken,
) -> Result<Download, DownloadError> {
match self {
Self::LocalFs(s) => {
s.download_byte_range(from, start_inclusive, end_exclusive, cancel)
.await
}
Self::AwsS3(s) => {
s.download_byte_range(from, start_inclusive, end_exclusive, cancel)
.await
}
Self::AzureBlob(s) => {
s.download_byte_range(from, start_inclusive, end_exclusive, cancel)
.await
}
Self::Unreliable(s) => {
s.download_byte_range(from, start_inclusive, end_exclusive, cancel)
.await
}
}
}
@@ -581,6 +562,20 @@ impl GenericRemoteStorage {
})
}
/// Downloads the storage object into the `to_path` provided.
/// `byte_range` could be specified to dowload only a part of the file, if needed.
pub async fn download_storage_object(
&self,
byte_range: Option<(u64, Option<u64>)>,
from: &RemotePath,
cancel: &CancellationToken,
) -> Result<Download, DownloadError> {
match byte_range {
Some((start, end)) => self.download_byte_range(from, start, end, cancel).await,
None => self.download(from, cancel).await,
}
}
/// The name of the bucket/container/etc.
pub fn bucket_name(&self) -> Option<&str> {
match self {
@@ -654,76 +649,6 @@ impl ConcurrencyLimiter {
mod tests {
use super::*;
/// DownloadOpts::byte_range() should generate (inclusive, exclusive) ranges
/// with optional end bound, or None when unbounded.
#[test]
fn download_opts_byte_range() {
// Consider using test_case or a similar table-driven test framework.
let cases = [
// (byte_start, byte_end, expected)
(Bound::Unbounded, Bound::Unbounded, None),
(Bound::Unbounded, Bound::Included(7), Some((0, Some(8)))),
(Bound::Unbounded, Bound::Excluded(7), Some((0, Some(7)))),
(Bound::Included(3), Bound::Unbounded, Some((3, None))),
(Bound::Included(3), Bound::Included(7), Some((3, Some(8)))),
(Bound::Included(3), Bound::Excluded(7), Some((3, Some(7)))),
(Bound::Excluded(3), Bound::Unbounded, Some((4, None))),
(Bound::Excluded(3), Bound::Included(7), Some((4, Some(8)))),
(Bound::Excluded(3), Bound::Excluded(7), Some((4, Some(7)))),
// 1-sized ranges are fine, 0 aren't and will panic (separate test).
(Bound::Included(3), Bound::Included(3), Some((3, Some(4)))),
(Bound::Included(3), Bound::Excluded(4), Some((3, Some(4)))),
];
for (byte_start, byte_end, expect) in cases {
let opts = DownloadOpts {
byte_start,
byte_end,
..Default::default()
};
let result = opts.byte_range();
assert_eq!(
result, expect,
"byte_start={byte_start:?} byte_end={byte_end:?}"
);
// Check generated HTTP header, which uses an inclusive range.
let expect_header = expect.map(|(start, end)| match end {
Some(end) => format!("bytes={start}-{}", end - 1), // inclusive end
None => format!("bytes={start}-"),
});
assert_eq!(
opts.byte_range_header(),
expect_header,
"byte_start={byte_start:?} byte_end={byte_end:?}"
);
}
}
/// DownloadOpts::byte_range() zero-sized byte range should panic.
#[test]
#[should_panic]
fn download_opts_byte_range_zero() {
DownloadOpts {
byte_start: Bound::Included(3),
byte_end: Bound::Excluded(3),
..Default::default()
}
.byte_range();
}
/// DownloadOpts::byte_range() negative byte range should panic.
#[test]
#[should_panic]
fn download_opts_byte_range_negative() {
DownloadOpts {
byte_start: Bound::Included(3),
byte_end: Bound::Included(2),
..Default::default()
}
.byte_range();
}
#[test]
fn test_object_name() {
let k = RemotePath::new(Utf8Path::new("a/b/c")).unwrap();

View File

@@ -23,8 +23,8 @@ use tokio_util::{io::ReaderStream, sync::CancellationToken};
use utils::crashsafe::path_with_suffix_extension;
use crate::{
Download, DownloadError, DownloadOpts, Listing, ListingMode, ListingObject, RemotePath,
TimeTravelError, TimeoutOrCancel, REMOTE_STORAGE_PREFIX_SEPARATOR,
Download, DownloadError, Listing, ListingMode, ListingObject, RemotePath, TimeTravelError,
TimeoutOrCancel, REMOTE_STORAGE_PREFIX_SEPARATOR,
};
use super::{RemoteStorage, StorageMetadata};
@@ -494,41 +494,22 @@ impl RemoteStorage for LocalFs {
async fn download(
&self,
from: &RemotePath,
opts: &DownloadOpts,
cancel: &CancellationToken,
) -> Result<Download, DownloadError> {
let target_path = from.with_base(&self.storage_root);
let file_metadata = file_metadata(&target_path).await?;
let etag = mock_etag(&file_metadata);
if opts.etag.as_ref() == Some(&etag) {
return Err(DownloadError::Unmodified);
}
let mut file = fs::OpenOptions::new()
.read(true)
.open(&target_path)
.await
.with_context(|| {
format!("Failed to open source file {target_path:?} to use in the download")
})
.map_err(DownloadError::Other)?;
let mut take = file_metadata.len();
if let Some((start, end)) = opts.byte_range() {
if start > 0 {
file.seek(io::SeekFrom::Start(start))
.await
.context("Failed to seek to the range start in a local storage file")
.map_err(DownloadError::Other)?;
}
if let Some(end) = end {
take = end - start;
}
}
let source = ReaderStream::new(file.take(take));
let source = ReaderStream::new(
fs::OpenOptions::new()
.read(true)
.open(&target_path)
.await
.with_context(|| {
format!("Failed to open source file {target_path:?} to use in the download")
})
.map_err(DownloadError::Other)?,
);
let metadata = self
.read_storage_metadata(&target_path)
@@ -538,6 +519,69 @@ impl RemoteStorage for LocalFs {
let cancel_or_timeout = crate::support::cancel_or_timeout(self.timeout, cancel.clone());
let source = crate::support::DownloadStream::new(cancel_or_timeout, source);
let etag = mock_etag(&file_metadata);
Ok(Download {
metadata,
last_modified: file_metadata
.modified()
.map_err(|e| DownloadError::Other(anyhow::anyhow!(e).context("Reading mtime")))?,
etag,
download_stream: Box::pin(source),
})
}
async fn download_byte_range(
&self,
from: &RemotePath,
start_inclusive: u64,
end_exclusive: Option<u64>,
cancel: &CancellationToken,
) -> Result<Download, DownloadError> {
if let Some(end_exclusive) = end_exclusive {
if end_exclusive <= start_inclusive {
return Err(DownloadError::Other(anyhow::anyhow!("Invalid range, start ({start_inclusive}) is not less than end_exclusive ({end_exclusive:?})")));
};
if start_inclusive == end_exclusive.saturating_sub(1) {
return Err(DownloadError::Other(anyhow::anyhow!("Invalid range, start ({start_inclusive}) and end_exclusive ({end_exclusive:?}) difference is zero bytes")));
}
}
let target_path = from.with_base(&self.storage_root);
let file_metadata = file_metadata(&target_path).await?;
let mut source = tokio::fs::OpenOptions::new()
.read(true)
.open(&target_path)
.await
.with_context(|| {
format!("Failed to open source file {target_path:?} to use in the download")
})
.map_err(DownloadError::Other)?;
let len = source
.metadata()
.await
.context("query file length")
.map_err(DownloadError::Other)?
.len();
source
.seek(io::SeekFrom::Start(start_inclusive))
.await
.context("Failed to seek to the range start in a local storage file")
.map_err(DownloadError::Other)?;
let metadata = self
.read_storage_metadata(&target_path)
.await
.map_err(DownloadError::Other)?;
let source = source.take(end_exclusive.unwrap_or(len) - start_inclusive);
let source = ReaderStream::new(source);
let cancel_or_timeout = crate::support::cancel_or_timeout(self.timeout, cancel.clone());
let source = crate::support::DownloadStream::new(cancel_or_timeout, source);
let etag = mock_etag(&file_metadata);
Ok(Download {
metadata,
last_modified: file_metadata
@@ -639,7 +683,7 @@ mod fs_tests {
use super::*;
use camino_tempfile::tempdir;
use std::{collections::HashMap, io::Write, ops::Bound};
use std::{collections::HashMap, io::Write};
async fn read_and_check_metadata(
storage: &LocalFs,
@@ -648,7 +692,7 @@ mod fs_tests {
) -> anyhow::Result<String> {
let cancel = CancellationToken::new();
let download = storage
.download(remote_storage_path, &DownloadOpts::default(), &cancel)
.download(remote_storage_path, &cancel)
.await
.map_err(|e| anyhow::anyhow!("Download failed: {e}"))?;
ensure!(
@@ -729,8 +773,8 @@ mod fs_tests {
"We should upload and download the same contents"
);
let non_existing_path = RemotePath::new(Utf8Path::new("somewhere/else"))?;
match storage.download(&non_existing_path, &DownloadOpts::default(), &cancel).await {
let non_existing_path = "somewhere/else";
match storage.download(&RemotePath::new(Utf8Path::new(non_existing_path))?, &cancel).await {
Err(DownloadError::NotFound) => {} // Should get NotFound for non existing keys
other => panic!("Should get a NotFound error when downloading non-existing storage files, but got: {other:?}"),
}
@@ -755,12 +799,10 @@ mod fs_tests {
let (first_part_local, second_part_local) = uploaded_bytes.split_at(3);
let first_part_download = storage
.download(
.download_byte_range(
&upload_target,
&DownloadOpts {
byte_end: Bound::Excluded(first_part_local.len() as u64),
..Default::default()
},
0,
Some(first_part_local.len() as u64),
&cancel,
)
.await?;
@@ -776,15 +818,10 @@ mod fs_tests {
);
let second_part_download = storage
.download(
.download_byte_range(
&upload_target,
&DownloadOpts {
byte_start: Bound::Included(first_part_local.len() as u64),
byte_end: Bound::Excluded(
(first_part_local.len() + second_part_local.len()) as u64,
),
..Default::default()
},
first_part_local.len() as u64,
Some((first_part_local.len() + second_part_local.len()) as u64),
&cancel,
)
.await?;
@@ -800,14 +837,7 @@ mod fs_tests {
);
let suffix_bytes = storage
.download(
&upload_target,
&DownloadOpts {
byte_start: Bound::Included(13),
..Default::default()
},
&cancel,
)
.download_byte_range(&upload_target, 13, None, &cancel)
.await?
.download_stream;
let suffix_bytes = aggregate(suffix_bytes).await?;
@@ -815,7 +845,7 @@ mod fs_tests {
assert_eq!(upload_name, suffix);
let all_bytes = storage
.download(&upload_target, &DownloadOpts::default(), &cancel)
.download_byte_range(&upload_target, 0, None, &cancel)
.await?
.download_stream;
let all_bytes = aggregate(all_bytes).await?;
@@ -826,26 +856,48 @@ mod fs_tests {
}
#[tokio::test]
#[should_panic(expected = "at or before start")]
async fn download_file_range_negative() {
let (storage, cancel) = create_storage().unwrap();
async fn download_file_range_negative() -> anyhow::Result<()> {
let (storage, cancel) = create_storage()?;
let upload_name = "upload_1";
let upload_target = upload_dummy_file(&storage, upload_name, None, &cancel)
.await
.unwrap();
let upload_target = upload_dummy_file(&storage, upload_name, None, &cancel).await?;
storage
.download(
let start = 1_000_000_000;
let end = start + 1;
match storage
.download_byte_range(
&upload_target,
&DownloadOpts {
byte_start: Bound::Included(10),
byte_end: Bound::Excluded(10),
..Default::default()
},
start,
Some(end), // exclusive end
&cancel,
)
.await
.unwrap();
{
Ok(_) => panic!("Should not allow downloading wrong ranges"),
Err(e) => {
let error_string = e.to_string();
assert!(error_string.contains("zero bytes"));
assert!(error_string.contains(&start.to_string()));
assert!(error_string.contains(&end.to_string()));
}
}
let start = 10000;
let end = 234;
assert!(start > end, "Should test an incorrect range");
match storage
.download_byte_range(&upload_target, start, Some(end), &cancel)
.await
{
Ok(_) => panic!("Should not allow downloading wrong ranges"),
Err(e) => {
let error_string = e.to_string();
assert!(error_string.contains("Invalid range"));
assert!(error_string.contains(&start.to_string()));
assert!(error_string.contains(&end.to_string()));
}
}
Ok(())
}
#[tokio::test]
@@ -888,12 +940,10 @@ mod fs_tests {
let (first_part_local, _) = uploaded_bytes.split_at(3);
let partial_download_with_metadata = storage
.download(
.download_byte_range(
&upload_target,
&DownloadOpts {
byte_end: Bound::Excluded(first_part_local.len() as u64),
..Default::default()
},
0,
Some(first_part_local.len() as u64),
&cancel,
)
.await?;
@@ -1051,13 +1101,7 @@ mod fs_tests {
storage.upload(body, len, &path, None, &cancel).await?;
}
let read = aggregate(
storage
.download(&path, &DownloadOpts::default(), &cancel)
.await?
.download_stream,
)
.await?;
let read = aggregate(storage.download(&path, &cancel).await?.download_stream).await?;
assert_eq!(body, read);
let shorter = Bytes::from_static(b"shorter body");
@@ -1068,13 +1112,7 @@ mod fs_tests {
storage.upload(body, len, &path, None, &cancel).await?;
}
let read = aggregate(
storage
.download(&path, &DownloadOpts::default(), &cancel)
.await?
.download_stream,
)
.await?;
let read = aggregate(storage.download(&path, &cancel).await?.download_stream).await?;
assert_eq!(shorter, read);
Ok(())
}
@@ -1107,13 +1145,7 @@ mod fs_tests {
storage.upload(body, len, &path, None, &cancel).await?;
}
let read = aggregate(
storage
.download(&path, &DownloadOpts::default(), &cancel)
.await?
.download_stream,
)
.await?;
let read = aggregate(storage.download(&path, &cancel).await?.download_stream).await?;
assert_eq!(body, read);
Ok(())

View File

@@ -28,13 +28,12 @@ use aws_sdk_s3::{
Client,
};
use aws_smithy_async::rt::sleep::TokioSleep;
use http_types::StatusCode;
use aws_smithy_types::{body::SdkBody, DateTime};
use aws_smithy_types::{byte_stream::ByteStream, date_time::ConversionError};
use bytes::Bytes;
use futures::stream::Stream;
use hyper0::Body;
use hyper::Body;
use scopeguard::ScopeGuard;
use tokio_util::sync::CancellationToken;
use utils::backoff;
@@ -45,8 +44,8 @@ use crate::{
error::Cancelled,
metrics::{start_counting_cancelled_wait, start_measuring_requests},
support::PermitCarrying,
ConcurrencyLimiter, Download, DownloadError, DownloadOpts, Listing, ListingMode, ListingObject,
RemotePath, RemoteStorage, TimeTravelError, TimeoutOrCancel, MAX_KEYS_PER_DELETE,
ConcurrencyLimiter, Download, DownloadError, Listing, ListingMode, ListingObject, RemotePath,
RemoteStorage, TimeTravelError, TimeoutOrCancel, MAX_KEYS_PER_DELETE,
REMOTE_STORAGE_PREFIX_SEPARATOR,
};
@@ -68,7 +67,6 @@ pub struct S3Bucket {
struct GetObjectRequest {
bucket: String,
key: String,
etag: Option<String>,
range: Option<String>,
}
impl S3Bucket {
@@ -250,18 +248,13 @@ impl S3Bucket {
let started_at = start_measuring_requests(kind);
let mut builder = self
let get_object = self
.client
.get_object()
.bucket(request.bucket)
.key(request.key)
.set_range(request.range);
if let Some(etag) = request.etag {
builder = builder.if_none_match(etag);
}
let get_object = builder.send();
.set_range(request.range)
.send();
let get_object = tokio::select! {
res = get_object => res,
@@ -284,20 +277,6 @@ impl S3Bucket {
);
return Err(DownloadError::NotFound);
}
Err(SdkError::ServiceError(e))
// aws_smithy_runtime_api::http::response::StatusCode isn't
// re-exported by any aws crates, so just check the numeric
// status against http_types::StatusCode instead of pulling it.
if e.raw().status().as_u16() == StatusCode::NotModified =>
{
// Count an unmodified file as a success.
crate::metrics::BUCKET_METRICS.req_seconds.observe_elapsed(
kind,
AttemptOutcome::Ok,
started_at,
);
return Err(DownloadError::Unmodified);
}
Err(e) => {
crate::metrics::BUCKET_METRICS.req_seconds.observe_elapsed(
kind,
@@ -794,7 +773,6 @@ impl RemoteStorage for S3Bucket {
async fn download(
&self,
from: &RemotePath,
opts: &DownloadOpts,
cancel: &CancellationToken,
) -> Result<Download, DownloadError> {
// if prefix is not none then download file `prefix/from`
@@ -803,8 +781,33 @@ impl RemoteStorage for S3Bucket {
GetObjectRequest {
bucket: self.bucket_name.clone(),
key: self.relative_path_to_s3_object(from),
etag: opts.etag.as_ref().map(|e| e.to_string()),
range: opts.byte_range_header(),
range: None,
},
cancel,
)
.await
}
async fn download_byte_range(
&self,
from: &RemotePath,
start_inclusive: u64,
end_exclusive: Option<u64>,
cancel: &CancellationToken,
) -> Result<Download, DownloadError> {
// S3 accepts ranges as https://www.w3.org/Protocols/rfc2616/rfc2616-sec14.html#sec14.35
// and needs both ends to be exclusive
let end_inclusive = end_exclusive.map(|end| end.saturating_sub(1));
let range = Some(match end_inclusive {
Some(end_inclusive) => format!("bytes={start_inclusive}-{end_inclusive}"),
None => format!("bytes={start_inclusive}-"),
});
self.download_object(
GetObjectRequest {
bucket: self.bucket_name.clone(),
key: self.relative_path_to_s3_object(from),
range,
},
cancel,
)

View File

@@ -12,8 +12,8 @@ use std::{collections::hash_map::Entry, sync::Arc};
use tokio_util::sync::CancellationToken;
use crate::{
Download, DownloadError, DownloadOpts, GenericRemoteStorage, Listing, ListingMode, RemotePath,
RemoteStorage, StorageMetadata, TimeTravelError,
Download, DownloadError, GenericRemoteStorage, Listing, ListingMode, RemotePath, RemoteStorage,
StorageMetadata, TimeTravelError,
};
pub struct UnreliableWrapper {
@@ -167,14 +167,28 @@ impl RemoteStorage for UnreliableWrapper {
async fn download(
&self,
from: &RemotePath,
opts: &DownloadOpts,
cancel: &CancellationToken,
) -> Result<Download, DownloadError> {
// Note: We treat any byte range as an "attempt" of the same operation.
// We don't pay attention to the ranges. That's good enough for now.
self.attempt(RemoteOp::Download(from.clone()))
.map_err(DownloadError::Other)?;
self.inner.download(from, opts, cancel).await
self.inner.download(from, cancel).await
}
async fn download_byte_range(
&self,
from: &RemotePath,
start_inclusive: u64,
end_exclusive: Option<u64>,
cancel: &CancellationToken,
) -> Result<Download, DownloadError> {
// Note: We treat any download_byte_range as an "attempt" of the same
// operation. We don't pay attention to the ranges. That's good enough
// for now.
self.attempt(RemoteOp::Download(from.clone()))
.map_err(DownloadError::Other)?;
self.inner
.download_byte_range(from, start_inclusive, end_exclusive, cancel)
.await
}
async fn delete(&self, path: &RemotePath, cancel: &CancellationToken) -> anyhow::Result<()> {

View File

@@ -1,8 +1,8 @@
use anyhow::Context;
use camino::Utf8Path;
use futures::StreamExt;
use remote_storage::{DownloadError, DownloadOpts, ListingMode, ListingObject, RemotePath};
use std::ops::Bound;
use remote_storage::ListingMode;
use remote_storage::RemotePath;
use std::sync::Arc;
use std::{collections::HashSet, num::NonZeroU32};
use test_context::test_context;
@@ -284,25 +284,14 @@ async fn upload_download_works(ctx: &mut MaybeEnabledStorage) -> anyhow::Result<
ctx.client.upload(data, len, &path, None, &cancel).await?;
// Normal download request
let dl = ctx
.client
.download(&path, &DownloadOpts::default(), &cancel)
.await?;
let dl = ctx.client.download(&path, &cancel).await?;
let buf = download_to_vec(dl).await?;
assert_eq!(&buf, &orig);
// Full range (end specified)
let dl = ctx
.client
.download(
&path,
&DownloadOpts {
byte_start: Bound::Included(0),
byte_end: Bound::Excluded(len as u64),
..Default::default()
},
&cancel,
)
.download_byte_range(&path, 0, Some(len as u64), &cancel)
.await?;
let buf = download_to_vec(dl).await?;
assert_eq!(&buf, &orig);
@@ -310,15 +299,7 @@ async fn upload_download_works(ctx: &mut MaybeEnabledStorage) -> anyhow::Result<
// partial range (end specified)
let dl = ctx
.client
.download(
&path,
&DownloadOpts {
byte_start: Bound::Included(4),
byte_end: Bound::Excluded(10),
..Default::default()
},
&cancel,
)
.download_byte_range(&path, 4, Some(10), &cancel)
.await?;
let buf = download_to_vec(dl).await?;
assert_eq!(&buf, &orig[4..10]);
@@ -326,15 +307,7 @@ async fn upload_download_works(ctx: &mut MaybeEnabledStorage) -> anyhow::Result<
// partial range (end beyond real end)
let dl = ctx
.client
.download(
&path,
&DownloadOpts {
byte_start: Bound::Included(8),
byte_end: Bound::Excluded(len as u64 * 100),
..Default::default()
},
&cancel,
)
.download_byte_range(&path, 8, Some(len as u64 * 100), &cancel)
.await?;
let buf = download_to_vec(dl).await?;
assert_eq!(&buf, &orig[8..]);
@@ -342,14 +315,7 @@ async fn upload_download_works(ctx: &mut MaybeEnabledStorage) -> anyhow::Result<
// Partial range (end unspecified)
let dl = ctx
.client
.download(
&path,
&DownloadOpts {
byte_start: Bound::Included(4),
..Default::default()
},
&cancel,
)
.download_byte_range(&path, 4, None, &cancel)
.await?;
let buf = download_to_vec(dl).await?;
assert_eq!(&buf, &orig[4..]);
@@ -357,14 +323,7 @@ async fn upload_download_works(ctx: &mut MaybeEnabledStorage) -> anyhow::Result<
// Full range (end unspecified)
let dl = ctx
.client
.download(
&path,
&DownloadOpts {
byte_start: Bound::Included(0),
..Default::default()
},
&cancel,
)
.download_byte_range(&path, 0, None, &cancel)
.await?;
let buf = download_to_vec(dl).await?;
assert_eq!(&buf, &orig);
@@ -378,54 +337,6 @@ async fn upload_download_works(ctx: &mut MaybeEnabledStorage) -> anyhow::Result<
Ok(())
}
/// Tests that conditional downloads work properly, by returning
/// DownloadError::Unmodified when the object ETag matches the given ETag.
#[test_context(MaybeEnabledStorage)]
#[tokio::test]
async fn download_conditional(ctx: &mut MaybeEnabledStorage) -> anyhow::Result<()> {
let MaybeEnabledStorage::Enabled(ctx) = ctx else {
return Ok(());
};
let cancel = CancellationToken::new();
// Create a file.
let path = RemotePath::new(Utf8Path::new(format!("{}/file", ctx.base_prefix).as_str()))?;
let data = bytes::Bytes::from_static("foo".as_bytes());
let (stream, len) = wrap_stream(data);
ctx.client.upload(stream, len, &path, None, &cancel).await?;
// Download it to obtain its etag.
let mut opts = DownloadOpts::default();
let download = ctx.client.download(&path, &opts, &cancel).await?;
// Download with the etag yields DownloadError::Unmodified.
opts.etag = Some(download.etag);
let result = ctx.client.download(&path, &opts, &cancel).await;
assert!(
matches!(result, Err(DownloadError::Unmodified)),
"expected DownloadError::Unmodified, got {result:?}"
);
// Replace the file contents.
let data = bytes::Bytes::from_static("bar".as_bytes());
let (stream, len) = wrap_stream(data);
ctx.client.upload(stream, len, &path, None, &cancel).await?;
// A download with the old etag should yield the new file.
let download = ctx.client.download(&path, &opts, &cancel).await?;
assert_ne!(download.etag, opts.etag.unwrap(), "ETag did not change");
// A download with the new etag should yield Unmodified again.
opts.etag = Some(download.etag);
let result = ctx.client.download(&path, &opts, &cancel).await;
assert!(
matches!(result, Err(DownloadError::Unmodified)),
"expected DownloadError::Unmodified, got {result:?}"
);
Ok(())
}
#[test_context(MaybeEnabledStorage)]
#[tokio::test]
async fn copy_works(ctx: &mut MaybeEnabledStorage) -> anyhow::Result<()> {
@@ -453,10 +364,7 @@ async fn copy_works(ctx: &mut MaybeEnabledStorage) -> anyhow::Result<()> {
// Normal download request
ctx.client.copy_object(&path, &path_dest, &cancel).await?;
let dl = ctx
.client
.download(&path_dest, &DownloadOpts::default(), &cancel)
.await?;
let dl = ctx.client.download(&path_dest, &cancel).await?;
let buf = download_to_vec(dl).await?;
assert_eq!(&buf, &orig);
@@ -468,56 +376,3 @@ async fn copy_works(ctx: &mut MaybeEnabledStorage) -> anyhow::Result<()> {
Ok(())
}
/// Tests that head_object works properly.
#[test_context(MaybeEnabledStorage)]
#[tokio::test]
async fn head_object(ctx: &mut MaybeEnabledStorage) -> anyhow::Result<()> {
let MaybeEnabledStorage::Enabled(ctx) = ctx else {
return Ok(());
};
let cancel = CancellationToken::new();
let path = RemotePath::new(Utf8Path::new(format!("{}/file", ctx.base_prefix).as_str()))?;
// Errors on missing file.
let result = ctx.client.head_object(&path, &cancel).await;
assert!(
matches!(result, Err(DownloadError::NotFound)),
"expected NotFound, got {result:?}"
);
// Create the file.
let data = bytes::Bytes::from_static("foo".as_bytes());
let (stream, len) = wrap_stream(data);
ctx.client.upload(stream, len, &path, None, &cancel).await?;
// Fetch the head metadata.
let object = ctx.client.head_object(&path, &cancel).await?;
assert_eq!(
object,
ListingObject {
key: path.clone(),
last_modified: object.last_modified, // ignore
size: 3
}
);
// Wait for a couple of seconds, and then update the file to check the last
// modified timestamp.
tokio::time::sleep(std::time::Duration::from_secs(2)).await;
let data = bytes::Bytes::from_static("bar".as_bytes());
let (stream, len) = wrap_stream(data);
ctx.client.upload(stream, len, &path, None, &cancel).await?;
let new = ctx.client.head_object(&path, &cancel).await?;
assert!(
!new.last_modified
.duration_since(object.last_modified)?
.is_zero(),
"last_modified did not advance"
);
Ok(())
}

View File

@@ -12,8 +12,8 @@ use anyhow::Context;
use camino::Utf8Path;
use futures_util::StreamExt;
use remote_storage::{
DownloadError, DownloadOpts, GenericRemoteStorage, ListingMode, RemotePath,
RemoteStorageConfig, RemoteStorageKind, S3Config,
DownloadError, GenericRemoteStorage, ListingMode, RemotePath, RemoteStorageConfig,
RemoteStorageKind, S3Config,
};
use test_context::test_context;
use test_context::AsyncTestContext;
@@ -121,8 +121,7 @@ async fn s3_time_travel_recovery_works(ctx: &mut MaybeEnabledStorage) -> anyhow:
// A little check to ensure that our clock is not too far off from the S3 clock
{
let opts = DownloadOpts::default();
let dl = retry(|| ctx.client.download(&path2, &opts, &cancel)).await?;
let dl = retry(|| ctx.client.download(&path2, &cancel)).await?;
let last_modified = dl.last_modified;
let half_wt = WAIT_TIME.mul_f32(0.5);
let t0_hwt = t0 + half_wt;
@@ -160,12 +159,7 @@ async fn s3_time_travel_recovery_works(ctx: &mut MaybeEnabledStorage) -> anyhow:
let t2_files_recovered = list_files(&ctx.client, &cancel).await?;
println!("after recovery to t2: {t2_files_recovered:?}");
assert_eq!(t2_files, t2_files_recovered);
let path2_recovered_t2 = download_to_vec(
ctx.client
.download(&path2, &DownloadOpts::default(), &cancel)
.await?,
)
.await?;
let path2_recovered_t2 = download_to_vec(ctx.client.download(&path2, &cancel).await?).await?;
assert_eq!(path2_recovered_t2, new_data.as_bytes());
// after recovery to t1: path1 is back, path2 has the old content
@@ -176,12 +170,7 @@ async fn s3_time_travel_recovery_works(ctx: &mut MaybeEnabledStorage) -> anyhow:
let t1_files_recovered = list_files(&ctx.client, &cancel).await?;
println!("after recovery to t1: {t1_files_recovered:?}");
assert_eq!(t1_files, t1_files_recovered);
let path2_recovered_t1 = download_to_vec(
ctx.client
.download(&path2, &DownloadOpts::default(), &cancel)
.await?,
)
.await?;
let path2_recovered_t1 = download_to_vec(ctx.client.download(&path2, &cancel).await?).await?;
assert_eq!(path2_recovered_t1, old_data.as_bytes());
// after recovery to t0: everything is gone except for path1
@@ -427,7 +416,7 @@ async fn download_is_timeouted(ctx: &mut MaybeEnabledStorage) {
let started_at = std::time::Instant::now();
let mut stream = ctx
.client
.download(&path, &DownloadOpts::default(), &cancel)
.download(&path, &cancel)
.await
.expect("download succeeds")
.download_stream;
@@ -502,7 +491,7 @@ async fn download_is_cancelled(ctx: &mut MaybeEnabledStorage) {
{
let stream = ctx
.client
.download(&path, &DownloadOpts::default(), &cancel)
.download(&path, &cancel)
.await
.expect("download succeeds")
.download_stream;

View File

@@ -5,7 +5,7 @@ edition.workspace = true
license.workspace = true
[dependencies]
hyper0.workspace = true
hyper.workspace = true
opentelemetry = { workspace = true, features = ["trace"] }
opentelemetry_sdk = { workspace = true, features = ["rt-tokio"] }
opentelemetry-otlp = { workspace = true, default-features = false, features = ["http-proto", "trace", "http", "reqwest-client"] }

View File

@@ -1,7 +1,7 @@
//! Tracing wrapper for Hyper HTTP server
use hyper0::HeaderMap;
use hyper0::{Body, Request, Response};
use hyper::HeaderMap;
use hyper::{Body, Request, Response};
use std::future::Future;
use tracing::Instrument;
use tracing_opentelemetry::OpenTelemetrySpanExt;

View File

@@ -22,7 +22,7 @@ chrono.workspace = true
git-version.workspace = true
hex = { workspace = true, features = ["serde"] }
humantime.workspace = true
hyper0 = { workspace = true, features = ["full"] }
hyper = { workspace = true, features = ["full"] }
fail.workspace = true
futures = { workspace = true}
jsonwebtoken.workspace = true

View File

@@ -31,12 +31,9 @@ pub enum Scope {
/// The scope used by pageservers in upcalls to storage controller and cloud control plane
#[serde(rename = "generations_api")]
GenerationsApi,
/// Allows access to control plane managment API and all storage controller endpoints.
/// Allows access to control plane managment API and some storage controller endpoints.
Admin,
/// Allows access to control plane & storage controller endpoints used in infrastructure automation (e.g. node registration)
Infra,
/// Allows access to storage controller APIs used by the scrubber, to interrogate the state
/// of a tenant & post scrub results.
Scrubber,

View File

@@ -28,9 +28,6 @@ pub enum ApiError {
#[error("Resource temporarily unavailable: {0}")]
ResourceUnavailable(Cow<'static, str>),
#[error("Too many requests: {0}")]
TooManyRequests(Cow<'static, str>),
#[error("Shutting down")]
ShuttingDown,
@@ -76,10 +73,6 @@ impl ApiError {
err.to_string(),
StatusCode::SERVICE_UNAVAILABLE,
),
ApiError::TooManyRequests(err) => HttpErrorBody::response_from_msg_and_status(
err.to_string(),
StatusCode::TOO_MANY_REQUESTS,
),
ApiError::Timeout(err) => HttpErrorBody::response_from_msg_and_status(
err.to_string(),
StatusCode::REQUEST_TIMEOUT,

View File

@@ -2,8 +2,6 @@
//! between other crates in this repository.
#![deny(clippy::undocumented_unsafe_blocks)]
extern crate hyper0 as hyper;
pub mod backoff;
/// `Lsn` type implements common tasks on Log Sequence Numbers

View File

@@ -7,13 +7,11 @@ use axum::{
extract::{ws::WebSocket, State, WebSocketUpgrade},
response::Response,
};
use axum::{routing::get, Router};
use axum::{routing::get, Router, Server};
use clap::Parser;
use futures::Future;
use std::net::SocketAddr;
use std::{fmt::Debug, time::Duration};
use sysinfo::{RefreshKind, System, SystemExt};
use tokio::net::TcpListener;
use tokio::{sync::broadcast, task::JoinHandle};
use tokio_util::sync::CancellationToken;
use tracing::{error, info};
@@ -134,14 +132,14 @@ pub async fn start(args: &'static Args, token: CancellationToken) -> anyhow::Res
args,
});
let addr_str = args.addr();
let addr: SocketAddr = addr_str.parse().expect("parsing address should not fail");
let listener = TcpListener::bind(&addr)
.await
let addr = args.addr();
let bound = Server::try_bind(&addr.parse().expect("parsing address should not fail"))
.with_context(|| format!("failed to bind to {addr}"))?;
info!(addr_str, "server bound");
axum::serve(listener, app.into_make_service())
info!(addr, "server bound");
bound
.serve(app.into_make_service())
.await
.context("server exited")?;

View File

@@ -79,7 +79,8 @@ pub struct Config {
/// memory.
///
/// The default value of `0.15` means that we *guarantee* sending upscale requests if the
/// cgroup is using more than 85% of total memory.
/// cgroup is using more than 85% of total memory (even if we're *not* separately reserving
/// memory for the file cache).
cgroup_min_overhead_fraction: f64,
cgroup_downscale_threshold_buffer_bytes: u64,
@@ -96,12 +97,24 @@ impl Default for Config {
}
impl Config {
fn cgroup_threshold(&self, total_mem: u64) -> u64 {
// We want our threshold to be met gracefully instead of letting postgres get OOM-killed
// (or if there's room, spilling to swap).
fn cgroup_threshold(&self, total_mem: u64, file_cache_disk_size: u64) -> u64 {
// If the file cache is in tmpfs, then it will count towards shmem usage of the cgroup,
// and thus be non-reclaimable, so we should allow for additional memory usage.
//
// If the file cache sits on disk, our desired stable system state is for it to be fully
// page cached (its contents should only be paged to/from disk in situations where we can't
// upscale fast enough). Page-cached memory is reclaimable, so we need to lower the
// threshold for non-reclaimable memory so we scale up *before* the kernel starts paging
// out the file cache.
let memory_remaining_for_cgroup = total_mem.saturating_sub(file_cache_disk_size);
// Even if we're not separately making room for the file cache (if it's in tmpfs), we still
// want our threshold to be met gracefully instead of letting postgres get OOM-killed.
// So we guarantee that there's at least `cgroup_min_overhead_fraction` of total memory
// remaining above the threshold.
(total_mem as f64 * (1.0 - self.cgroup_min_overhead_fraction)) as u64
let max_threshold = (total_mem as f64 * (1.0 - self.cgroup_min_overhead_fraction)) as u64;
memory_remaining_for_cgroup.min(max_threshold)
}
}
@@ -136,6 +149,11 @@ impl Runner {
let mem = get_total_system_memory();
let mut file_cache_disk_size = 0;
// We need to process file cache initialization before cgroup initialization, so that the memory
// allocated to the file cache is appropriately taken into account when we decide the cgroup's
// memory limits.
if let Some(connstr) = &args.pgconnstr {
info!("initializing file cache");
let config = FileCacheConfig::default();
@@ -166,6 +184,7 @@ impl Runner {
info!("file cache size actually got set to {actual_size}")
}
file_cache_disk_size = actual_size;
state.filecache = Some(file_cache);
}
@@ -188,7 +207,7 @@ impl Runner {
cgroup.watch(hist_tx).await
});
let threshold = state.config.cgroup_threshold(mem);
let threshold = state.config.cgroup_threshold(mem, file_cache_disk_size);
info!(threshold, "set initial cgroup threshold",);
state.cgroup = Some(CgroupState {
@@ -240,7 +259,9 @@ impl Runner {
return Ok((false, status.to_owned()));
}
let new_threshold = self.config.cgroup_threshold(usable_system_memory);
let new_threshold = self
.config
.cgroup_threshold(usable_system_memory, expected_file_cache_size);
let current = last_history.avg_non_reclaimable;
@@ -261,11 +282,13 @@ impl Runner {
// The downscaling has been approved. Downscale the file cache, then the cgroup.
let mut status = vec![];
let mut file_cache_disk_size = 0;
if let Some(file_cache) = &mut self.filecache {
let actual_usage = file_cache
.set_file_cache_size(expected_file_cache_size)
.await
.context("failed to set file cache size")?;
file_cache_disk_size = actual_usage;
let message = format!(
"set file cache size to {} MiB",
bytes_to_mebibytes(actual_usage),
@@ -275,7 +298,9 @@ impl Runner {
}
if let Some(cgroup) = &mut self.cgroup {
let new_threshold = self.config.cgroup_threshold(usable_system_memory);
let new_threshold = self
.config
.cgroup_threshold(usable_system_memory, file_cache_disk_size);
let message = format!(
"set cgroup memory threshold from {} MiB to {} MiB, of new total {} MiB",
@@ -304,6 +329,7 @@ impl Runner {
let new_mem = resources.mem;
let usable_system_memory = new_mem.saturating_sub(self.config.sys_buffer_bytes);
let mut file_cache_disk_size = 0;
if let Some(file_cache) = &mut self.filecache {
let expected_usage = file_cache.config.calculate_cache_size(usable_system_memory);
info!(
@@ -316,6 +342,7 @@ impl Runner {
.set_file_cache_size(expected_usage)
.await
.context("failed to set file cache size")?;
file_cache_disk_size = actual_usage;
if actual_usage != expected_usage {
warn!(
@@ -327,7 +354,9 @@ impl Runner {
}
if let Some(cgroup) = &mut self.cgroup {
let new_threshold = self.config.cgroup_threshold(usable_system_memory);
let new_threshold = self
.config
.cgroup_threshold(usable_system_memory, file_cache_disk_size);
info!(
"set cgroup memory threshold from {} MiB to {} MiB of new total {} MiB",

View File

@@ -1,14 +0,0 @@
[package]
name = "wal_decoder"
version = "0.1.0"
edition.workspace = true
license.workspace = true
[dependencies]
anyhow.workspace = true
bytes.workspace = true
pageserver_api.workspace = true
postgres_ffi.workspace = true
serde.workspace = true
tracing.workspace = true
utils.workspace = true

File diff suppressed because it is too large Load Diff

View File

@@ -1,2 +0,0 @@
pub mod decoder;
pub mod models;

View File

@@ -1,177 +0,0 @@
//! This module houses types which represent decoded PG WAL records
//! ready for the pageserver to interpret.
use bytes::Bytes;
use pageserver_api::key::CompactKey;
use pageserver_api::reltag::{BlockNumber, RelTag, SlruKind};
use pageserver_api::value::Value;
use postgres_ffi::record::{
XlMultiXactCreate, XlMultiXactTruncate, XlRelmapUpdate, XlReploriginDrop, XlReploriginSet,
XlXactParsedRecord,
};
use postgres_ffi::{Oid, TransactionId};
use utils::lsn::Lsn;
pub enum FlushUncommittedRecords {
Yes,
No,
}
pub struct InterpretedWalRecord {
pub metadata_record: Option<MetadataRecord>,
pub blocks: Vec<(CompactKey, Option<Value>)>,
pub lsn: Lsn,
pub flush_uncommitted: FlushUncommittedRecords,
pub xid: TransactionId,
}
pub enum MetadataRecord {
Heapam(HeapamRecord),
Neonrmgr(NeonrmgrRecord),
Smgr(SmgrRecord),
Dbase(DbaseRecord),
Clog(ClogRecord),
Xact(XactRecord),
MultiXact(MultiXactRecord),
Relmap(RelmapRecord),
Xlog(XlogRecord),
LogicalMessage(LogicalMessageRecord),
Standby(StandbyRecord),
Replorigin(ReploriginRecord),
}
pub enum HeapamRecord {
ClearVmBits(ClearVmBits),
}
pub struct ClearVmBits {
pub new_heap_blkno: Option<u32>,
pub old_heap_blkno: Option<u32>,
pub vm_rel: RelTag,
pub flags: u8,
}
pub enum NeonrmgrRecord {
ClearVmBits(ClearVmBits),
}
pub enum SmgrRecord {
Create(SmgrCreate),
Truncate(SmgrTruncate),
}
pub struct SmgrCreate {
pub rel: RelTag,
}
pub struct SmgrTruncate {
pub rel: RelTag,
pub to: BlockNumber,
}
pub enum DbaseRecord {
Create(DbaseCreate),
Drop(DbaseDrop),
}
pub struct DbaseCreate {
pub db_id: Oid,
pub tablespace_id: Oid,
pub src_db_id: Oid,
pub src_tablespace_id: Oid,
}
pub struct DbaseDrop {
pub db_id: Oid,
pub tablespace_ids: Vec<Oid>,
}
pub enum ClogRecord {
ZeroPage(ClogZeroPage),
Truncate(ClogTruncate),
}
pub struct ClogZeroPage {
pub segno: u32,
pub rpageno: u32,
}
pub struct ClogTruncate {
pub pageno: u32,
pub oldest_xid: TransactionId,
pub oldest_xid_db: Oid,
}
pub enum XactRecord {
Commit(XactCommon),
Abort(XactCommon),
CommitPrepared(XactCommon),
AbortPrepared(XactCommon),
Prepare(XactPrepare),
}
pub struct XactCommon {
pub parsed: XlXactParsedRecord,
pub origin_id: u16,
// Fields below are only used for logging
pub xl_xid: TransactionId,
pub lsn: Lsn,
}
pub struct XactPrepare {
pub xl_xid: TransactionId,
pub data: Bytes,
}
pub enum MultiXactRecord {
ZeroPage(MultiXactZeroPage),
Create(XlMultiXactCreate),
Truncate(XlMultiXactTruncate),
}
pub struct MultiXactZeroPage {
pub slru_kind: SlruKind,
pub segno: u32,
pub rpageno: u32,
}
pub enum RelmapRecord {
Update(RelmapUpdate),
}
pub struct RelmapUpdate {
pub update: XlRelmapUpdate,
pub buf: Bytes,
}
pub enum XlogRecord {
Raw(RawXlogRecord),
}
pub struct RawXlogRecord {
pub info: u8,
pub lsn: Lsn,
pub buf: Bytes,
}
pub enum LogicalMessageRecord {
Put(PutLogicalMessage),
}
pub struct PutLogicalMessage {
pub buf: Bytes,
pub prefix_size: usize,
}
pub enum StandbyRecord {
RunningXacts(StandbyRunningXacts),
}
pub struct StandbyRunningXacts {
pub oldest_running_xid: TransactionId,
}
pub enum ReploriginRecord {
Set(XlReploriginSet),
Drop(XlReploriginDrop),
}

View File

@@ -30,7 +30,7 @@ futures.workspace = true
hex.workspace = true
humantime.workspace = true
humantime-serde.workspace = true
hyper0.workspace = true
hyper.workspace = true
itertools.workspace = true
md5.workspace = true
nix.workspace = true
@@ -83,7 +83,6 @@ enum-map.workspace = true
enumset = { workspace = true, features = ["serde"]}
strum.workspace = true
strum_macros.workspace = true
wal_decoder.workspace = true
[target.'cfg(target_os = "linux")'.dependencies]
procfs.workspace = true
@@ -93,7 +92,6 @@ criterion.workspace = true
hex-literal.workspace = true
tokio = { workspace = true, features = ["process", "sync", "fs", "rt", "io-util", "time", "test-util"] }
indoc.workspace = true
# pageserver_api = { workspace = true, features = ["testing"] }
[[bench]]
name = "bench_layer_map"

View File

@@ -6,15 +6,15 @@ use criterion::{criterion_group, criterion_main, Criterion};
use pageserver::{
config::PageServerConf,
context::{DownloadBehavior, RequestContext},
gc_result::Value,
l0_flush::{L0FlushConfig, L0FlushGlobalState},
page_cache,
repository::Value,
task_mgr::TaskKind,
tenant::storage_layer::inmemory_layer::SerializedBatch,
tenant::storage_layer::InMemoryLayer,
virtual_file,
};
use pageserver_api::{key::Key, shard::TenantShardId, value::Value};
use pageserver_api::{key::Key, shard::TenantShardId};
use utils::{
bin_ser::BeSer,
id::{TenantId, TimelineId},
@@ -164,7 +164,11 @@ fn criterion_benchmark(c: &mut Criterion) {
let conf: &'static PageServerConf = Box::leak(Box::new(
pageserver::config::PageServerConf::dummy_conf(temp_dir.path().to_path_buf()),
));
virtual_file::init(16384, virtual_file::io_engine_for_bench());
virtual_file::init(
16384,
virtual_file::io_engine_for_bench(),
pageserver_api::config::defaults::DEFAULT_IO_BUFFER_ALIGNMENT,
);
page_cache::init(conf.page_cache_size);
{

View File

@@ -1,9 +1,9 @@
use criterion::measurement::WallTime;
use pageserver::keyspace::{KeyPartitioning, KeySpace};
use pageserver::repository::Key;
use pageserver::tenant::layer_map::LayerMap;
use pageserver::tenant::storage_layer::LayerName;
use pageserver::tenant::storage_layer::PersistentLayerDesc;
use pageserver_api::key::Key;
use pageserver_api::shard::TenantShardId;
use rand::prelude::{SeedableRng, SliceRandom, StdRng};
use std::cmp::{max, min};

View File

@@ -60,8 +60,7 @@ use anyhow::Context;
use bytes::{Buf, Bytes};
use criterion::{BenchmarkId, Criterion};
use once_cell::sync::Lazy;
use pageserver::{config::PageServerConf, walredo::PostgresRedoManager};
use pageserver_api::record::NeonWalRecord;
use pageserver::{config::PageServerConf, walrecord::NeonWalRecord, walredo::PostgresRedoManager};
use pageserver_api::{key::Key, shard::TenantShardId};
use std::{
future::Future,

View File

@@ -540,13 +540,10 @@ impl Client {
.map_err(Error::ReceiveBody)
}
/// Configs io mode at runtime.
pub async fn put_io_mode(
&self,
mode: &pageserver_api::models::virtual_file::IoMode,
) -> Result<()> {
let uri = format!("{}/v1/io_mode", self.mgmt_api_endpoint);
self.request(Method::PUT, uri, mode)
/// Configs io buffer alignment at runtime.
pub async fn put_io_alignment(&self, align: usize) -> Result<()> {
let uri = format!("{}/v1/io_alignment", self.mgmt_api_endpoint);
self.request(Method::PUT, uri, align)
.await?
.json()
.await

View File

@@ -51,7 +51,7 @@
//!
use anyhow::{Context, Result};
use pageserver_api::key::Key;
use pageserver::repository::Key;
use std::cmp::Ordering;
use std::io::{self, BufRead};
use std::path::PathBuf;

View File

@@ -13,12 +13,12 @@ use std::ops::Range;
use std::{fs, str};
use pageserver::page_cache::{self, PAGE_SZ};
use pageserver::repository::{Key, KEY_SIZE};
use pageserver::tenant::block_io::FileBlockReader;
use pageserver::tenant::disk_btree::{DiskBtreeReader, VisitDirection};
use pageserver::tenant::storage_layer::delta_layer::{Summary, DELTA_KEY_SIZE};
use pageserver::tenant::storage_layer::range_overlaps;
use pageserver::virtual_file::{self, VirtualFile};
use pageserver_api::key::{Key, KEY_SIZE};
use utils::{bin_ser::BeSer, lsn::Lsn};
@@ -152,7 +152,11 @@ pub(crate) async fn main(cmd: &AnalyzeLayerMapCmd) -> Result<()> {
let ctx = RequestContext::new(TaskKind::DebugTool, DownloadBehavior::Error);
// Initialize virtual_file (file desriptor cache) and page cache which are needed to access layer persistent B-Tree.
pageserver::virtual_file::init(10, virtual_file::api::IoEngineKind::StdFs);
pageserver::virtual_file::init(
10,
virtual_file::api::IoEngineKind::StdFs,
pageserver_api::config::defaults::DEFAULT_IO_BUFFER_ALIGNMENT,
);
pageserver::page_cache::init(100);
let mut total_delta_layers = 0usize;

View File

@@ -13,13 +13,13 @@ use pageserver::tenant::storage_layer::{DeltaLayer, ImageLayer};
use pageserver::tenant::{TENANTS_SEGMENT_NAME, TIMELINES_SEGMENT_NAME};
use pageserver::{page_cache, virtual_file};
use pageserver::{
repository::{Key, KEY_SIZE},
tenant::{
block_io::FileBlockReader, disk_btree::VisitDirection,
storage_layer::delta_layer::DELTA_KEY_SIZE,
},
virtual_file::VirtualFile,
};
use pageserver_api::key::{Key, KEY_SIZE};
use std::fs;
use utils::bin_ser::BeSer;
use utils::id::{TenantId, TimelineId};
@@ -59,7 +59,7 @@ pub(crate) enum LayerCmd {
async fn read_delta_file(path: impl AsRef<Path>, ctx: &RequestContext) -> Result<()> {
let path = Utf8Path::from_path(path.as_ref()).expect("non-Unicode path");
virtual_file::init(10, virtual_file::api::IoEngineKind::StdFs);
virtual_file::init(10, virtual_file::api::IoEngineKind::StdFs, 1);
page_cache::init(100);
let file = VirtualFile::open(path, ctx).await?;
let file_id = page_cache::next_file_id();
@@ -190,7 +190,11 @@ pub(crate) async fn main(cmd: &LayerCmd) -> Result<()> {
new_tenant_id,
new_timeline_id,
} => {
pageserver::virtual_file::init(10, virtual_file::api::IoEngineKind::StdFs);
pageserver::virtual_file::init(
10,
virtual_file::api::IoEngineKind::StdFs,
pageserver_api::config::defaults::DEFAULT_IO_BUFFER_ALIGNMENT,
);
pageserver::page_cache::init(100);
let ctx = RequestContext::new(TaskKind::DebugTool, DownloadBehavior::Error);

View File

@@ -26,7 +26,7 @@ use pageserver::{
tenant::{dump_layerfile_from_path, metadata::TimelineMetadata},
virtual_file,
};
use pageserver_api::shard::TenantShardId;
use pageserver_api::{config::defaults::DEFAULT_IO_BUFFER_ALIGNMENT, shard::TenantShardId};
use postgres_ffi::ControlFileData;
use remote_storage::{RemotePath, RemoteStorageConfig};
use tokio_util::sync::CancellationToken;
@@ -205,7 +205,11 @@ fn read_pg_control_file(control_file_path: &Utf8Path) -> anyhow::Result<()> {
async fn print_layerfile(path: &Utf8Path) -> anyhow::Result<()> {
// Basic initialization of things that don't change after startup
virtual_file::init(10, virtual_file::api::IoEngineKind::StdFs);
virtual_file::init(
10,
virtual_file::api::IoEngineKind::StdFs,
DEFAULT_IO_BUFFER_ALIGNMENT,
);
page_cache::init(100);
let ctx = RequestContext::new(TaskKind::DebugTool, DownloadBehavior::Error);
dump_layerfile_from_path(path, true, &ctx).await

View File

@@ -59,9 +59,9 @@ pub(crate) struct Args {
#[clap(long)]
set_io_engine: Option<pageserver_api::models::virtual_file::IoEngineKind>,
/// Before starting the benchmark, live-reconfigure the pageserver to use specified io mode (buffered vs. direct).
/// Before starting the benchmark, live-reconfigure the pageserver to use specified alignment for io buffers.
#[clap(long)]
set_io_mode: Option<pageserver_api::models::virtual_file::IoMode>,
set_io_alignment: Option<usize>,
targets: Option<Vec<TenantTimelineId>>,
}
@@ -129,8 +129,8 @@ async fn main_impl(
mgmt_api_client.put_io_engine(engine_str).await?;
}
if let Some(mode) = &args.set_io_mode {
mgmt_api_client.put_io_mode(mode).await?;
if let Some(align) = args.set_io_alignment {
mgmt_api_client.put_io_alignment(align).await?;
}
// discover targets

View File

@@ -14,19 +14,14 @@ pub fn check_permission(claims: &Claims, tenant_id: Option<TenantId>) -> Result<
}
(Scope::PageServerApi, None) => Ok(()), // access to management api for PageServerApi scope
(Scope::PageServerApi, Some(_)) => Ok(()), // access to tenant api using PageServerApi scope
(
Scope::Admin
| Scope::SafekeeperData
| Scope::GenerationsApi
| Scope::Infra
| Scope::Scrubber,
_,
) => Err(AuthError(
format!(
"JWT scope '{:?}' is ineligible for Pageserver auth",
claims.scope
)
.into(),
)),
(Scope::Admin | Scope::SafekeeperData | Scope::GenerationsApi | Scope::Scrubber, _) => {
Err(AuthError(
format!(
"JWT scope '{:?}' is ineligible for Pageserver auth",
claims.scope
)
.into(),
))
}
}
}

View File

@@ -125,7 +125,8 @@ fn main() -> anyhow::Result<()> {
// after setting up logging, log the effective IO engine choice and read path implementations
info!(?conf.virtual_file_io_engine, "starting with virtual_file IO engine");
info!(?conf.virtual_file_io_mode, "starting with virtual_file IO mode");
info!(?conf.virtual_file_direct_io, "starting with virtual_file Direct IO settings");
info!(?conf.io_buffer_alignment, "starting with setting for IO buffer alignment");
// The tenants directory contains all the pageserver local disk state.
// Create if not exists and make sure all the contents are durable before proceeding.
@@ -167,7 +168,11 @@ fn main() -> anyhow::Result<()> {
let scenario = failpoint_support::init();
// Basic initialization of things that don't change after startup
virtual_file::init(conf.max_file_descriptors, conf.virtual_file_io_engine);
virtual_file::init(
conf.max_file_descriptors,
conf.virtual_file_io_engine,
conf.io_buffer_alignment,
);
page_cache::init(conf.page_cache_size);
start_pageserver(launch_ts, conf).context("Failed to start pageserver")?;
@@ -570,7 +575,7 @@ fn start_pageserver(
.build()
.map_err(|err| anyhow!(err))?;
let service = utils::http::RouterService::new(router).unwrap();
let server = hyper0::Server::from_tcp(http_listener)?
let server = hyper::Server::from_tcp(http_listener)?
.serve(service)
.with_graceful_shutdown({
let cancel = cancel.clone();

View File

@@ -174,7 +174,9 @@ pub struct PageServerConf {
pub l0_flush: crate::l0_flush::L0FlushConfig,
/// Direct IO settings
pub virtual_file_io_mode: virtual_file::IoMode,
pub virtual_file_direct_io: virtual_file::DirectIoMode,
pub io_buffer_alignment: usize,
}
/// Token for authentication to safekeepers
@@ -323,10 +325,11 @@ impl PageServerConf {
image_compression,
ephemeral_bytes_per_memory_kb,
l0_flush,
virtual_file_io_mode,
virtual_file_direct_io,
concurrent_tenant_warmup,
concurrent_tenant_size_logical_size_queries,
virtual_file_io_engine,
io_buffer_alignment,
tenant_config,
} = config_toml;
@@ -365,6 +368,8 @@ impl PageServerConf {
max_vectored_read_bytes,
image_compression,
ephemeral_bytes_per_memory_kb,
virtual_file_direct_io,
io_buffer_alignment,
// ------------------------------------------------------------
// fields that require additional validation or custom handling
@@ -403,7 +408,6 @@ impl PageServerConf {
l0_flush: l0_flush
.map(crate::l0_flush::L0FlushConfig::from)
.unwrap_or_default(),
virtual_file_io_mode: virtual_file_io_mode.unwrap_or(virtual_file::IoMode::preferred()),
};
// ------------------------------------------------------------

View File

@@ -696,7 +696,7 @@ impl DeletionQueue {
mod test {
use camino::Utf8Path;
use hex_literal::hex;
use pageserver_api::{key::Key, shard::ShardIndex, upcall_api::ReAttachResponseTenant};
use pageserver_api::{shard::ShardIndex, upcall_api::ReAttachResponseTenant};
use std::{io::ErrorKind, time::Duration};
use tracing::info;
@@ -705,6 +705,7 @@ mod test {
use crate::{
controller_upcall_client::RetryForeverError,
repository::Key,
tenant::{harness::TenantHarness, storage_layer::DeltaLayerName},
};

View File

@@ -1,57 +0,0 @@
use anyhow::Result;
use serde::Serialize;
use std::ops::AddAssign;
use std::time::Duration;
///
/// Result of performing GC
///
#[derive(Default, Serialize, Debug)]
pub struct GcResult {
pub layers_total: u64,
pub layers_needed_by_cutoff: u64,
pub layers_needed_by_pitr: u64,
pub layers_needed_by_branches: u64,
pub layers_needed_by_leases: u64,
pub layers_not_updated: u64,
pub layers_removed: u64, // # of layer files removed because they have been made obsolete by newer ondisk files.
#[serde(serialize_with = "serialize_duration_as_millis")]
pub elapsed: Duration,
/// The layers which were garbage collected.
///
/// Used in `/v1/tenant/:tenant_id/timeline/:timeline_id/do_gc` to wait for the layers to be
/// dropped in tests.
#[cfg(feature = "testing")]
#[serde(skip)]
pub(crate) doomed_layers: Vec<crate::tenant::storage_layer::Layer>,
}
// helper function for `GcResult`, serializing a `Duration` as an integer number of milliseconds
fn serialize_duration_as_millis<S>(d: &Duration, serializer: S) -> Result<S::Ok, S::Error>
where
S: serde::Serializer,
{
d.as_millis().serialize(serializer)
}
impl AddAssign for GcResult {
fn add_assign(&mut self, other: Self) {
self.layers_total += other.layers_total;
self.layers_needed_by_pitr += other.layers_needed_by_pitr;
self.layers_needed_by_cutoff += other.layers_needed_by_cutoff;
self.layers_needed_by_branches += other.layers_needed_by_branches;
self.layers_needed_by_leases += other.layers_needed_by_leases;
self.layers_not_updated += other.layers_not_updated;
self.layers_removed += other.layers_removed;
self.elapsed += other.elapsed;
#[cfg(feature = "testing")]
{
let mut other = other;
self.doomed_layers.append(&mut other.doomed_layers);
}
}
}

View File

@@ -17,7 +17,6 @@ use hyper::header;
use hyper::StatusCode;
use hyper::{Body, Request, Response, Uri};
use metrics::launch_timestamp::LaunchTimestamp;
use pageserver_api::models::virtual_file::IoMode;
use pageserver_api::models::AuxFilePolicy;
use pageserver_api::models::DownloadRemoteLayersTaskSpawnRequest;
use pageserver_api::models::IngestAuxFilesRequest;
@@ -77,7 +76,6 @@ use crate::tenant::secondary::SecondaryController;
use crate::tenant::size::ModelInputs;
use crate::tenant::storage_layer::LayerAccessStatsReset;
use crate::tenant::storage_layer::LayerName;
use crate::tenant::timeline::offload::offload_timeline;
use crate::tenant::timeline::CompactFlags;
use crate::tenant::timeline::CompactionError;
use crate::tenant::timeline::Timeline;
@@ -326,7 +324,6 @@ impl From<crate::tenant::TimelineArchivalError> for ApiError {
match value {
NotFound => ApiError::NotFound(anyhow::anyhow!("timeline not found").into()),
Timeout => ApiError::Timeout("hit pageserver internal timeout".into()),
Cancelled => ApiError::ShuttingDown,
e @ HasArchivedParent(_) => {
ApiError::PreconditionFailed(e.to_string().into_boxed_str())
}
@@ -706,8 +703,6 @@ async fn timeline_archival_config_handler(
let tenant_shard_id: TenantShardId = parse_request_param(&request, "tenant_shard_id")?;
let timeline_id: TimelineId = parse_request_param(&request, "timeline_id")?;
let ctx = RequestContext::new(TaskKind::MgmtRequest, DownloadBehavior::Warn);
let request_data: TimelineArchivalConfigRequest = json_request(&mut request).await?;
check_permission(&request, Some(tenant_shard_id.tenant_id))?;
let state = get_state(&request);
@@ -717,10 +712,8 @@ async fn timeline_archival_config_handler(
.tenant_manager
.get_attached_tenant_shard(tenant_shard_id)?;
tenant.wait_to_become_active(ACTIVE_TENANT_TIMEOUT).await?;
tenant
.apply_timeline_archival_config(timeline_id, request_data.state, ctx)
.apply_timeline_archival_config(timeline_id, request_data.state)
.await?;
Ok::<_, ApiError>(())
}
@@ -1787,49 +1780,6 @@ async fn timeline_compact_handler(
.await
}
// Run offload immediately on given timeline.
async fn timeline_offload_handler(
request: Request<Body>,
_cancel: CancellationToken,
) -> Result<Response<Body>, ApiError> {
let tenant_shard_id: TenantShardId = parse_request_param(&request, "tenant_shard_id")?;
let timeline_id: TimelineId = parse_request_param(&request, "timeline_id")?;
check_permission(&request, Some(tenant_shard_id.tenant_id))?;
let state = get_state(&request);
async {
let tenant = state
.tenant_manager
.get_attached_tenant_shard(tenant_shard_id)?;
if tenant.get_offloaded_timeline(timeline_id).is_ok() {
return json_response(StatusCode::OK, ());
}
let timeline =
active_timeline_of_active_tenant(&state.tenant_manager, tenant_shard_id, timeline_id)
.await?;
if !tenant.timeline_has_no_attached_children(timeline_id) {
return Err(ApiError::PreconditionFailed(
"timeline has attached children".into(),
));
}
if !timeline.can_offload() {
return Err(ApiError::PreconditionFailed(
"Timeline::can_offload() returned false".into(),
));
}
offload_timeline(&tenant, &timeline)
.await
.map_err(ApiError::InternalServerError)?;
json_response(StatusCode::OK, ())
}
.instrument(info_span!("manual_timeline_offload", tenant_id = %tenant_shard_id.tenant_id, shard_id = %tenant_shard_id.shard_slug(), %timeline_id))
.await
}
// Run checkpoint immediately on given timeline.
async fn timeline_checkpoint_handler(
request: Request<Body>,
@@ -2050,13 +2000,13 @@ async fn getpage_at_lsn_handler(
check_permission(&request, Some(tenant_shard_id.tenant_id))?;
let state = get_state(&request);
struct Key(pageserver_api::key::Key);
struct Key(crate::repository::Key);
impl std::str::FromStr for Key {
type Err = anyhow::Error;
fn from_str(s: &str) -> std::result::Result<Self, Self::Err> {
pageserver_api::key::Key::from_hex(s).map(Key)
crate::repository::Key::from_hex(s).map(Key)
}
}
@@ -2429,13 +2379,17 @@ async fn put_io_engine_handler(
json_response(StatusCode::OK, ())
}
async fn put_io_mode_handler(
async fn put_io_alignment_handler(
mut r: Request<Body>,
_cancel: CancellationToken,
) -> Result<Response<Body>, ApiError> {
check_permission(&r, None)?;
let mode: IoMode = json_request(&mut r).await?;
crate::virtual_file::set_io_mode(mode);
let align: usize = json_request(&mut r).await?;
crate::virtual_file::set_io_buffer_alignment(align).map_err(|align| {
ApiError::PreconditionFailed(
format!("Requested io alignment ({align}) is not a power of two").into(),
)
})?;
json_response(StatusCode::OK, ())
}
@@ -3053,10 +3007,6 @@ pub fn make_router(
"/v1/tenant/:tenant_shard_id/timeline/:timeline_id/compact",
|r| api_handler(r, timeline_compact_handler),
)
.put(
"/v1/tenant/:tenant_shard_id/timeline/:timeline_id/offload",
|r| testing_api_handler("attempt timeline offload", r, timeline_offload_handler),
)
.put(
"/v1/tenant/:tenant_shard_id/timeline/:timeline_id/checkpoint",
|r| testing_api_handler("run timeline checkpoint", r, timeline_checkpoint_handler),
@@ -3130,7 +3080,9 @@ pub fn make_router(
|r| api_handler(r, timeline_collect_keyspace),
)
.put("/v1/io_engine", |r| api_handler(r, put_io_engine_handler))
.put("/v1/io_mode", |r| api_handler(r, put_io_mode_handler))
.put("/v1/io_alignment", |r| {
api_handler(r, put_io_alignment_handler)
})
.put(
"/v1/tenant/:tenant_shard_id/timeline/:timeline_id/force_aux_policy_switch",
|r| api_handler(r, force_aux_policy_switch_handler),

View File

@@ -12,7 +12,6 @@ use pageserver_api::key::rel_block_to_key;
use tokio::io::{AsyncRead, AsyncReadExt};
use tokio_tar::Archive;
use tracing::*;
use wal_decoder::models::InterpretedWalRecord;
use walkdir::WalkDir;
use crate::context::RequestContext;
@@ -20,6 +19,8 @@ use crate::metrics::WAL_INGEST;
use crate::pgdatadir_mapping::*;
use crate::tenant::Timeline;
use crate::walingest::WalIngest;
use crate::walrecord::decode_wal_record;
use crate::walrecord::DecodedWALRecord;
use pageserver_api::reltag::{RelTag, SlruKind};
use postgres_ffi::pg_constants;
use postgres_ffi::relfile_utils::*;
@@ -312,15 +313,11 @@ async fn import_wal(
let mut modification = tline.begin_modification(last_lsn);
while last_lsn <= endpoint {
if let Some((lsn, recdata)) = waldecoder.poll_decode()? {
let interpreted = InterpretedWalRecord::from_bytes(
recdata,
tline.get_shard_identity(),
lsn,
tline.pg_version,
)?;
let mut decoded = DecodedWALRecord::default();
decode_wal_record(recdata, &mut decoded, tline.pg_version)?;
walingest
.ingest_record(interpreted, &mut modification, ctx)
.ingest_record(decoded, lsn, &mut modification, ctx)
.await?;
WAL_INGEST.records_committed.inc();
@@ -457,15 +454,10 @@ pub async fn import_wal_from_tar(
let mut modification = tline.begin_modification(last_lsn);
while last_lsn <= end_lsn {
if let Some((lsn, recdata)) = waldecoder.poll_decode()? {
let interpreted = InterpretedWalRecord::from_bytes(
recdata,
tline.get_shard_identity(),
lsn,
tline.pg_version,
)?;
let mut decoded = DecodedWALRecord::default();
decode_wal_record(recdata, &mut decoded, tline.pg_version)?;
walingest
.ingest_record(interpreted, &mut modification, ctx)
.ingest_record(decoded, lsn, &mut modification, ctx)
.await?;
modification.commit(ctx).await?;
last_lsn = lsn;

View File

@@ -13,18 +13,16 @@ pub mod http;
pub mod import_datadir;
pub mod l0_flush;
extern crate hyper0 as hyper;
use futures::{stream::FuturesUnordered, StreamExt};
pub use pageserver_api::keyspace;
use tokio_util::sync::CancellationToken;
mod assert_u64_eq_usize;
pub mod aux_file;
pub mod gc_result;
pub mod metrics;
pub mod page_cache;
pub mod page_service;
pub mod pgdatadir_mapping;
pub mod repository;
pub mod span;
pub(crate) mod statvfs;
pub mod task_mgr;
@@ -32,6 +30,7 @@ pub mod tenant;
pub mod utilization;
pub mod virtual_file;
pub mod walingest;
pub mod walrecord;
pub mod walredo;
use camino::Utf8Path;

View File

@@ -7,14 +7,14 @@
//! Clarify that)
//!
use super::tenant::{PageReconstructError, Timeline};
use crate::aux_file;
use crate::context::RequestContext;
use crate::keyspace::{KeySpace, KeySpaceAccum};
use crate::span::debug_assert_current_span_has_tenant_and_timeline_id_no_shard_id;
use crate::walrecord::NeonWalRecord;
use crate::{aux_file, repository::*};
use anyhow::{ensure, Context};
use bytes::{Buf, Bytes, BytesMut};
use enum_map::Enum;
use pageserver_api::key::Key;
use pageserver_api::key::{
dbdir_key_range, rel_block_to_key, rel_dir_to_key, rel_key_range, rel_size_to_key,
relmap_file_key, repl_origin_key, repl_origin_key_range, slru_block_to_key, slru_dir_to_key,
@@ -23,9 +23,7 @@ use pageserver_api::key::{
};
use pageserver_api::keyspace::SparseKeySpace;
use pageserver_api::models::AuxFilePolicy;
use pageserver_api::record::NeonWalRecord;
use pageserver_api::reltag::{BlockNumber, RelTag, SlruKind};
use pageserver_api::value::Value;
use postgres_ffi::relfile_utils::{FSM_FORKNUM, VISIBILITYMAP_FORKNUM};
use postgres_ffi::BLCKSZ;
use postgres_ffi::{Oid, RepOriginId, TimestampTz, TransactionId};

View File

@@ -1,9 +1,13 @@
//! This module defines the value type used by the storage engine.
use crate::record::NeonWalRecord;
use crate::walrecord::NeonWalRecord;
use anyhow::Result;
use bytes::Bytes;
use serde::{Deserialize, Serialize};
use std::ops::AddAssign;
use std::time::Duration;
pub use pageserver_api::key::{Key, KEY_SIZE};
/// A 'value' stored for a one Key.
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
pub enum Value {
/// An Image value contains a full copy of the value
@@ -29,17 +33,17 @@ impl Value {
}
#[derive(Debug, PartialEq)]
pub enum InvalidInput {
pub(crate) enum InvalidInput {
TooShortValue,
TooShortPostgresRecord,
}
/// We could have a ValueRef where everything is `serde(borrow)`. Before implementing that, lets
/// use this type for querying if a slice looks some particular way.
pub struct ValueBytes;
pub(crate) struct ValueBytes;
impl ValueBytes {
pub fn will_init(raw: &[u8]) -> Result<bool, InvalidInput> {
pub(crate) fn will_init(raw: &[u8]) -> Result<bool, InvalidInput> {
if raw.len() < 12 {
return Err(InvalidInput::TooShortValue);
}
@@ -75,7 +79,6 @@ impl ValueBytes {
mod test {
use super::*;
use bytes::Bytes;
use utils::bin_ser::BeSer;
macro_rules! roundtrip {
@@ -226,3 +229,56 @@ mod test {
assert!(!ValueBytes::will_init(&expected).unwrap());
}
}
///
/// Result of performing GC
///
#[derive(Default, Serialize, Debug)]
pub struct GcResult {
pub layers_total: u64,
pub layers_needed_by_cutoff: u64,
pub layers_needed_by_pitr: u64,
pub layers_needed_by_branches: u64,
pub layers_needed_by_leases: u64,
pub layers_not_updated: u64,
pub layers_removed: u64, // # of layer files removed because they have been made obsolete by newer ondisk files.
#[serde(serialize_with = "serialize_duration_as_millis")]
pub elapsed: Duration,
/// The layers which were garbage collected.
///
/// Used in `/v1/tenant/:tenant_id/timeline/:timeline_id/do_gc` to wait for the layers to be
/// dropped in tests.
#[cfg(feature = "testing")]
#[serde(skip)]
pub(crate) doomed_layers: Vec<crate::tenant::storage_layer::Layer>,
}
// helper function for `GcResult`, serializing a `Duration` as an integer number of milliseconds
fn serialize_duration_as_millis<S>(d: &Duration, serializer: S) -> Result<S::Ok, S::Error>
where
S: serde::Serializer,
{
d.as_millis().serialize(serializer)
}
impl AddAssign for GcResult {
fn add_assign(&mut self, other: Self) {
self.layers_total += other.layers_total;
self.layers_needed_by_pitr += other.layers_needed_by_pitr;
self.layers_needed_by_cutoff += other.layers_needed_by_cutoff;
self.layers_needed_by_branches += other.layers_needed_by_branches;
self.layers_needed_by_leases += other.layers_needed_by_leases;
self.layers_not_updated += other.layers_not_updated;
self.layers_removed += other.layers_removed;
self.elapsed += other.elapsed;
#[cfg(feature = "testing")]
{
let mut other = other;
self.doomed_layers.append(&mut other.doomed_layers);
}
}
}

View File

@@ -38,7 +38,6 @@ use std::future::Future;
use std::sync::Weak;
use std::time::SystemTime;
use storage_broker::BrokerClientChannel;
use timeline::offload::offload_timeline;
use tokio::io::BufReader;
use tokio::sync::watch;
use tokio::task::JoinSet;
@@ -79,7 +78,6 @@ use crate::config::PageServerConf;
use crate::context::{DownloadBehavior, RequestContext};
use crate::deletion_queue::DeletionQueueClient;
use crate::deletion_queue::DeletionQueueError;
use crate::gc_result::GcResult;
use crate::import_datadir;
use crate::is_uninit_mark;
use crate::l0_flush::L0FlushGlobalState;
@@ -88,6 +86,7 @@ use crate::metrics::{
remove_tenant_metrics, BROKEN_TENANTS_SET, CIRCUIT_BREAKERS_BROKEN, CIRCUIT_BREAKERS_UNBROKEN,
TENANT_STATE_METRIC, TENANT_SYNTHETIC_SIZE_METRIC,
};
use crate::repository::GcResult;
use crate::task_mgr;
use crate::task_mgr::TaskKind;
use crate::tenant::config::LocationMode;
@@ -288,13 +287,9 @@ pub struct Tenant {
/// During timeline creation, we first insert the TimelineId to the
/// creating map, then `timelines`, then remove it from the creating map.
/// **Lock order**: if acquiring both, acquire`timelines` before `timelines_creating`
/// **Lock order**: if acquring both, acquire`timelines` before `timelines_creating`
timelines_creating: std::sync::Mutex<HashSet<TimelineId>>,
/// Possibly offloaded and archived timelines
/// **Lock order**: if acquiring both, acquire`timelines` before `timelines_offloaded`
timelines_offloaded: Mutex<HashMap<TimelineId, Arc<OffloadedTimeline>>>,
// This mutex prevents creation of new timelines during GC.
// Adding yet another mutex (in addition to `timelines`) is needed because holding
// `timelines` mutex during all GC iteration
@@ -461,10 +456,10 @@ impl WalRedoManager {
/// This method is cancellation-safe.
pub async fn request_redo(
&self,
key: pageserver_api::key::Key,
key: crate::repository::Key,
lsn: Lsn,
base_img: Option<(Lsn, bytes::Bytes)>,
records: Vec<(Lsn, pageserver_api::record::NeonWalRecord)>,
records: Vec<(Lsn, crate::walrecord::NeonWalRecord)>,
pg_version: u32,
) -> Result<bytes::Bytes, walredo::Error> {
match self {
@@ -489,77 +484,6 @@ impl WalRedoManager {
}
}
pub struct OffloadedTimeline {
pub tenant_shard_id: TenantShardId,
pub timeline_id: TimelineId,
pub ancestor_timeline_id: Option<TimelineId>,
/// Whether to retain the branch lsn at the ancestor or not
pub ancestor_retain_lsn: Option<Lsn>,
// TODO: once we persist offloaded state, make this lazily constructed
pub remote_client: Arc<RemoteTimelineClient>,
/// Prevent two tasks from deleting the timeline at the same time. If held, the
/// timeline is being deleted. If 'true', the timeline has already been deleted.
pub delete_progress: Arc<tokio::sync::Mutex<DeleteTimelineFlow>>,
}
impl OffloadedTimeline {
fn from_timeline(timeline: &Timeline) -> Self {
let ancestor_retain_lsn = timeline
.get_ancestor_timeline_id()
.map(|_timeline_id| timeline.get_ancestor_lsn());
Self {
tenant_shard_id: timeline.tenant_shard_id,
timeline_id: timeline.timeline_id,
ancestor_timeline_id: timeline.get_ancestor_timeline_id(),
ancestor_retain_lsn,
remote_client: timeline.remote_client.clone(),
delete_progress: timeline.delete_progress.clone(),
}
}
}
#[derive(Copy, Clone, PartialEq, Eq, Hash, Debug)]
pub enum MaybeOffloaded {
Yes,
No,
}
#[derive(Clone)]
pub enum TimelineOrOffloaded {
Timeline(Arc<Timeline>),
Offloaded(Arc<OffloadedTimeline>),
}
impl TimelineOrOffloaded {
pub fn tenant_shard_id(&self) -> TenantShardId {
match self {
TimelineOrOffloaded::Timeline(timeline) => timeline.tenant_shard_id,
TimelineOrOffloaded::Offloaded(offloaded) => offloaded.tenant_shard_id,
}
}
pub fn timeline_id(&self) -> TimelineId {
match self {
TimelineOrOffloaded::Timeline(timeline) => timeline.timeline_id,
TimelineOrOffloaded::Offloaded(offloaded) => offloaded.timeline_id,
}
}
pub fn delete_progress(&self) -> &Arc<tokio::sync::Mutex<DeleteTimelineFlow>> {
match self {
TimelineOrOffloaded::Timeline(timeline) => &timeline.delete_progress,
TimelineOrOffloaded::Offloaded(offloaded) => &offloaded.delete_progress,
}
}
pub fn remote_client(&self) -> &Arc<RemoteTimelineClient> {
match self {
TimelineOrOffloaded::Timeline(timeline) => &timeline.remote_client,
TimelineOrOffloaded::Offloaded(offloaded) => &offloaded.remote_client,
}
}
}
#[derive(Debug, thiserror::Error, PartialEq, Eq)]
pub enum GetTimelineError {
#[error("Timeline is shutting down")]
@@ -619,9 +543,6 @@ pub enum TimelineArchivalError {
#[error("Timeout")]
Timeout,
#[error("Cancelled")]
Cancelled,
#[error("ancestor is archived: {}", .0)]
HasArchivedParent(TimelineId),
@@ -640,7 +561,6 @@ impl Debug for TimelineArchivalError {
match self {
Self::NotFound => write!(f, "NotFound"),
Self::Timeout => write!(f, "Timeout"),
Self::Cancelled => write!(f, "Cancelled"),
Self::HasArchivedParent(p) => f.debug_tuple("HasArchivedParent").field(p).finish(),
Self::HasUnarchivedChildren(c) => {
f.debug_tuple("HasUnarchivedChildren").field(c).finish()
@@ -1486,195 +1406,52 @@ impl Tenant {
}
}
fn check_to_be_archived_has_no_unarchived_children(
timeline_id: TimelineId,
timelines: &std::sync::MutexGuard<'_, HashMap<TimelineId, Arc<Timeline>>>,
) -> Result<(), TimelineArchivalError> {
let children: Vec<TimelineId> = timelines
.iter()
.filter_map(|(id, entry)| {
if entry.get_ancestor_timeline_id() != Some(timeline_id) {
return None;
}
if entry.is_archived() == Some(true) {
return None;
}
Some(*id)
})
.collect();
if !children.is_empty() {
return Err(TimelineArchivalError::HasUnarchivedChildren(children));
}
Ok(())
}
fn check_ancestor_of_to_be_unarchived_is_not_archived(
ancestor_timeline_id: TimelineId,
timelines: &std::sync::MutexGuard<'_, HashMap<TimelineId, Arc<Timeline>>>,
offloaded_timelines: &std::sync::MutexGuard<
'_,
HashMap<TimelineId, Arc<OffloadedTimeline>>,
>,
) -> Result<(), TimelineArchivalError> {
let has_archived_parent =
if let Some(ancestor_timeline) = timelines.get(&ancestor_timeline_id) {
ancestor_timeline.is_archived() == Some(true)
} else if offloaded_timelines.contains_key(&ancestor_timeline_id) {
true
} else {
error!("ancestor timeline {ancestor_timeline_id} not found");
if cfg!(debug_assertions) {
panic!("ancestor timeline {ancestor_timeline_id} not found");
}
return Err(TimelineArchivalError::NotFound);
};
if has_archived_parent {
return Err(TimelineArchivalError::HasArchivedParent(
ancestor_timeline_id,
));
}
Ok(())
}
fn check_to_be_unarchived_timeline_has_no_archived_parent(
timeline: &Arc<Timeline>,
) -> Result<(), TimelineArchivalError> {
if let Some(ancestor_timeline) = timeline.ancestor_timeline() {
if ancestor_timeline.is_archived() == Some(true) {
return Err(TimelineArchivalError::HasArchivedParent(
ancestor_timeline.timeline_id,
));
}
}
Ok(())
}
/// Loads the specified (offloaded) timeline from S3 and attaches it as a loaded timeline
async fn unoffload_timeline(
self: &Arc<Self>,
timeline_id: TimelineId,
ctx: RequestContext,
) -> Result<Arc<Timeline>, TimelineArchivalError> {
info!("unoffloading timeline");
let cancel = self.cancel.clone();
let timeline_preload = self
.load_timeline_metadata(timeline_id, self.remote_storage.clone(), cancel)
.await;
let index_part = match timeline_preload.index_part {
Ok(index_part) => {
debug!("remote index part exists for timeline {timeline_id}");
index_part
}
Err(DownloadError::NotFound) => {
error!(%timeline_id, "index_part not found on remote");
return Err(TimelineArchivalError::NotFound);
}
Err(DownloadError::Cancelled) => return Err(TimelineArchivalError::Cancelled),
Err(e) => {
// Some (possibly ephemeral) error happened during index_part download.
warn!(%timeline_id, "Failed to load index_part from remote storage, failed creation? ({e})");
return Err(TimelineArchivalError::Other(
anyhow::Error::new(e).context("downloading index_part from remote storage"),
));
}
};
let index_part = match index_part {
MaybeDeletedIndexPart::IndexPart(index_part) => index_part,
MaybeDeletedIndexPart::Deleted(_index_part) => {
info!("timeline is deleted according to index_part.json");
return Err(TimelineArchivalError::NotFound);
}
};
let remote_metadata = index_part.metadata.clone();
let timeline_resources = self.build_timeline_resources(timeline_id);
self.load_remote_timeline(
timeline_id,
index_part,
remote_metadata,
timeline_resources,
&ctx,
)
.await
.with_context(|| {
format!(
"failed to load remote timeline {} for tenant {}",
timeline_id, self.tenant_shard_id
)
})?;
let timelines = self.timelines.lock().unwrap();
if let Some(timeline) = timelines.get(&timeline_id) {
let mut offloaded_timelines = self.timelines_offloaded.lock().unwrap();
if offloaded_timelines.remove(&timeline_id).is_none() {
warn!("timeline already removed from offloaded timelines");
}
info!("timeline unoffloading complete");
Ok(Arc::clone(timeline))
} else {
warn!("timeline not available directly after attach");
Err(TimelineArchivalError::Other(anyhow::anyhow!(
"timeline not available directly after attach"
)))
}
}
pub(crate) async fn apply_timeline_archival_config(
self: &Arc<Self>,
&self,
timeline_id: TimelineId,
new_state: TimelineArchivalState,
ctx: RequestContext,
state: TimelineArchivalState,
) -> Result<(), TimelineArchivalError> {
info!("setting timeline archival config");
// First part: figure out what is needed to do, and do validation
let timeline_or_unarchive_offloaded = 'outer: {
let timeline = {
let timelines = self.timelines.lock().unwrap();
let Some(timeline) = timelines.get(&timeline_id) else {
let offloaded_timelines = self.timelines_offloaded.lock().unwrap();
let Some(offloaded) = offloaded_timelines.get(&timeline_id) else {
return Err(TimelineArchivalError::NotFound);
};
if new_state == TimelineArchivalState::Archived {
// It's offloaded already, so nothing to do
return Ok(());
}
if let Some(ancestor_timeline_id) = offloaded.ancestor_timeline_id {
Self::check_ancestor_of_to_be_unarchived_is_not_archived(
ancestor_timeline_id,
&timelines,
&offloaded_timelines,
)?;
}
break 'outer None;
return Err(TimelineArchivalError::NotFound);
};
// Do some validation. We release the timelines lock below, so there is potential
// for race conditions: these checks are more present to prevent misunderstandings of
// the API's capabilities, instead of serving as the sole way to defend their invariants.
match new_state {
TimelineArchivalState::Unarchived => {
Self::check_to_be_unarchived_timeline_has_no_archived_parent(timeline)?
}
TimelineArchivalState::Archived => {
Self::check_to_be_archived_has_no_unarchived_children(timeline_id, &timelines)?
if state == TimelineArchivalState::Unarchived {
if let Some(ancestor_timeline) = timeline.ancestor_timeline() {
if ancestor_timeline.is_archived() == Some(true) {
return Err(TimelineArchivalError::HasArchivedParent(
ancestor_timeline.timeline_id,
));
}
}
}
Some(Arc::clone(timeline))
// Ensure that there are no non-archived child timelines
let children: Vec<TimelineId> = timelines
.iter()
.filter_map(|(id, entry)| {
if entry.get_ancestor_timeline_id() != Some(timeline_id) {
return None;
}
if entry.is_archived() == Some(true) {
return None;
}
Some(*id)
})
.collect();
if !children.is_empty() && state == TimelineArchivalState::Archived {
return Err(TimelineArchivalError::HasUnarchivedChildren(children));
}
Arc::clone(timeline)
};
// Second part: unarchive timeline (if needed)
let timeline = if let Some(timeline) = timeline_or_unarchive_offloaded {
timeline
} else {
// Turn offloaded timeline into a non-offloaded one
self.unoffload_timeline(timeline_id, ctx).await?
};
// Third part: upload new timeline archival state and block until it is present in S3
let upload_needed = timeline
.remote_client
.schedule_index_upload_for_timeline_archival_state(new_state)?;
.schedule_index_upload_for_timeline_archival_state(state)?;
if upload_needed {
info!("Uploading new state");
@@ -1690,21 +1467,6 @@ impl Tenant {
Ok(())
}
pub fn get_offloaded_timeline(
&self,
timeline_id: TimelineId,
) -> Result<Arc<OffloadedTimeline>, GetTimelineError> {
self.timelines_offloaded
.lock()
.unwrap()
.get(&timeline_id)
.map(Arc::clone)
.ok_or(GetTimelineError::NotFound {
tenant_id: self.tenant_shard_id,
timeline_id,
})
}
pub(crate) fn tenant_shard_id(&self) -> TenantShardId {
self.tenant_shard_id
}
@@ -2122,7 +1884,7 @@ impl Tenant {
///
/// Returns whether we have pending compaction task.
async fn compaction_iteration(
self: &Arc<Self>,
&self,
cancel: &CancellationToken,
ctx: &RequestContext,
) -> Result<bool, timeline::CompactionError> {
@@ -2143,28 +1905,21 @@ impl Tenant {
// while holding the lock. Then drop the lock and actually perform the
// compactions. We don't want to block everything else while the
// compaction runs.
let timelines_to_compact_or_offload;
{
let timelines_to_compact = {
let timelines = self.timelines.lock().unwrap();
timelines_to_compact_or_offload = timelines
let timelines_to_compact = timelines
.iter()
.filter_map(|(timeline_id, timeline)| {
let (is_active, can_offload) = (timeline.is_active(), timeline.can_offload());
let has_no_unoffloaded_children = {
!timelines
.iter()
.any(|(_id, tl)| tl.get_ancestor_timeline_id() == Some(*timeline_id))
};
let can_offload = can_offload && has_no_unoffloaded_children;
if (is_active, can_offload) == (false, false) {
None
if timeline.is_active() {
Some((*timeline_id, timeline.clone()))
} else {
Some((*timeline_id, timeline.clone(), (is_active, can_offload)))
None
}
})
.collect::<Vec<_>>();
drop(timelines);
}
timelines_to_compact
};
// Before doing any I/O work, check our circuit breaker
if self.compaction_circuit_breaker.lock().unwrap().is_broken() {
@@ -2174,34 +1929,20 @@ impl Tenant {
let mut has_pending_task = false;
for (timeline_id, timeline, (can_compact, can_offload)) in &timelines_to_compact_or_offload
{
let pending_task_left = if *can_compact {
Some(
timeline
.compact(cancel, EnumSet::empty(), ctx)
.instrument(info_span!("compact_timeline", %timeline_id))
.await
.inspect_err(|e| match e {
timeline::CompactionError::ShuttingDown => (),
timeline::CompactionError::Other(e) => {
self.compaction_circuit_breaker
.lock()
.unwrap()
.fail(&CIRCUIT_BREAKERS_BROKEN, e);
}
})?,
)
} else {
None
};
has_pending_task |= pending_task_left.unwrap_or(false);
if pending_task_left == Some(false) && *can_offload {
offload_timeline(self, timeline)
.instrument(info_span!("offload_timeline", %timeline_id))
.await
.map_err(timeline::CompactionError::Other)?;
}
for (timeline_id, timeline) in &timelines_to_compact {
has_pending_task |= timeline
.compact(cancel, EnumSet::empty(), ctx)
.instrument(info_span!("compact_timeline", %timeline_id))
.await
.inspect_err(|e| match e {
timeline::CompactionError::ShuttingDown => (),
timeline::CompactionError::Other(e) => {
self.compaction_circuit_breaker
.lock()
.unwrap()
.fail(&CIRCUIT_BREAKERS_BROKEN, e);
}
})?;
}
self.compaction_circuit_breaker
@@ -2240,13 +1981,6 @@ impl Tenant {
}
}
pub fn timeline_has_no_attached_children(&self, timeline_id: TimelineId) -> bool {
let timelines = self.timelines.lock().unwrap();
!timelines
.iter()
.any(|(_id, tl)| tl.get_ancestor_timeline_id() == Some(timeline_id))
}
pub fn current_state(&self) -> TenantState {
self.state.borrow().clone()
}
@@ -2294,13 +2028,12 @@ impl Tenant {
if activating {
let timelines_accessor = self.timelines.lock().unwrap();
let timelines_offloaded_accessor = self.timelines_offloaded.lock().unwrap();
let timelines_to_activate = timelines_accessor
.values()
.filter(|timeline| !(timeline.is_broken() || timeline.is_stopping()));
// Before activation, populate each Timeline's GcInfo with information about its children
self.initialize_gc_info(&timelines_accessor, &timelines_offloaded_accessor);
self.initialize_gc_info(&timelines_accessor);
// Spawn gc and compaction loops. The loops will shut themselves
// down when they notice that the tenant is inactive.
@@ -3119,7 +2852,6 @@ impl Tenant {
constructed_at: Instant::now(),
timelines: Mutex::new(HashMap::new()),
timelines_creating: Mutex::new(HashSet::new()),
timelines_offloaded: Mutex::new(HashMap::new()),
gc_cs: tokio::sync::Mutex::new(()),
walredo_mgr,
remote_storage,
@@ -3340,7 +3072,6 @@ impl Tenant {
fn initialize_gc_info(
&self,
timelines: &std::sync::MutexGuard<HashMap<TimelineId, Arc<Timeline>>>,
timelines_offloaded: &std::sync::MutexGuard<HashMap<TimelineId, Arc<OffloadedTimeline>>>,
) {
// This function must be called before activation: after activation timeline create/delete operations
// might happen, and this function is not safe to run concurrently with those.
@@ -3348,37 +3079,20 @@ impl Tenant {
// Scan all timelines. For each timeline, remember the timeline ID and
// the branch point where it was created.
let mut all_branchpoints: BTreeMap<TimelineId, Vec<(Lsn, TimelineId, MaybeOffloaded)>> =
BTreeMap::new();
let mut all_branchpoints: BTreeMap<TimelineId, Vec<(Lsn, TimelineId)>> = BTreeMap::new();
timelines.iter().for_each(|(timeline_id, timeline_entry)| {
if let Some(ancestor_timeline_id) = &timeline_entry.get_ancestor_timeline_id() {
let ancestor_children = all_branchpoints.entry(*ancestor_timeline_id).or_default();
ancestor_children.push((
timeline_entry.get_ancestor_lsn(),
*timeline_id,
MaybeOffloaded::No,
));
ancestor_children.push((timeline_entry.get_ancestor_lsn(), *timeline_id));
}
});
timelines_offloaded
.iter()
.for_each(|(timeline_id, timeline_entry)| {
let Some(ancestor_timeline_id) = &timeline_entry.ancestor_timeline_id else {
return;
};
let Some(retain_lsn) = timeline_entry.ancestor_retain_lsn else {
return;
};
let ancestor_children = all_branchpoints.entry(*ancestor_timeline_id).or_default();
ancestor_children.push((retain_lsn, *timeline_id, MaybeOffloaded::Yes));
});
// The number of bytes we always keep, irrespective of PITR: this is a constant across timelines
let horizon = self.get_gc_horizon();
// Populate each timeline's GcInfo with information about its child branches
for timeline in timelines.values() {
let mut branchpoints: Vec<(Lsn, TimelineId, MaybeOffloaded)> = all_branchpoints
let mut branchpoints: Vec<(Lsn, TimelineId)> = all_branchpoints
.remove(&timeline.timeline_id)
.unwrap_or_default();
@@ -4297,8 +4011,7 @@ pub(crate) mod harness {
use crate::deletion_queue::mock::MockDeletionQueue;
use crate::l0_flush::L0FlushConfig;
use crate::walredo::apply_neon;
use pageserver_api::key::Key;
use pageserver_api::record::NeonWalRecord;
use crate::{repository::Key, walrecord::NeonWalRecord};
use super::*;
use hex_literal::hex;
@@ -4569,17 +4282,17 @@ mod tests {
use super::*;
use crate::keyspace::KeySpaceAccum;
use crate::pgdatadir_mapping::AuxFilesDirectory;
use crate::repository::{Key, Value};
use crate::tenant::harness::*;
use crate::tenant::timeline::CompactFlags;
use crate::walrecord::NeonWalRecord;
use crate::DEFAULT_PG_VERSION;
use bytes::{Bytes, BytesMut};
use hex_literal::hex;
use itertools::Itertools;
use pageserver_api::key::{Key, AUX_FILES_KEY, AUX_KEY_PREFIX, NON_INHERITED_RANGE};
use pageserver_api::key::{AUX_FILES_KEY, AUX_KEY_PREFIX, NON_INHERITED_RANGE};
use pageserver_api::keyspace::KeySpace;
use pageserver_api::models::{CompactionAlgorithm, CompactionAlgorithmSettings};
use pageserver_api::record::NeonWalRecord;
use pageserver_api::value::Value;
use rand::{thread_rng, Rng};
use storage_layer::PersistentLayerKey;
use tests::storage_layer::ValuesReconstructState;
@@ -4939,10 +4652,7 @@ mod tests {
{
let branchpoints = &tline.gc_info.read().unwrap().retain_lsns;
assert_eq!(branchpoints.len(), 1);
assert_eq!(
branchpoints[0],
(Lsn(0x40), NEW_TIMELINE_ID, MaybeOffloaded::No)
);
assert_eq!(branchpoints[0], (Lsn(0x40), NEW_TIMELINE_ID));
}
// You can read the key from the child branch even though the parent is
@@ -8325,8 +8035,8 @@ mod tests {
let mut guard = tline.gc_info.write().unwrap();
*guard = GcInfo {
retain_lsns: vec![
(Lsn(0x10), tline.timeline_id, MaybeOffloaded::No),
(Lsn(0x20), tline.timeline_id, MaybeOffloaded::No),
(Lsn(0x10), tline.timeline_id),
(Lsn(0x20), tline.timeline_id),
],
cutoffs: GcCutoffs {
time: Lsn(0x30),
@@ -8553,8 +8263,8 @@ mod tests {
let mut guard = tline.gc_info.write().unwrap();
*guard = GcInfo {
retain_lsns: vec![
(Lsn(0x10), tline.timeline_id, MaybeOffloaded::No),
(Lsn(0x20), tline.timeline_id, MaybeOffloaded::No),
(Lsn(0x10), tline.timeline_id),
(Lsn(0x20), tline.timeline_id),
],
cutoffs: GcCutoffs {
time: Lsn(0x30),
@@ -8787,7 +8497,7 @@ mod tests {
// Update GC info
let mut guard = parent_tline.gc_info.write().unwrap();
*guard = GcInfo {
retain_lsns: vec![(Lsn(0x18), branch_tline.timeline_id, MaybeOffloaded::No)],
retain_lsns: vec![(Lsn(0x18), branch_tline.timeline_id)],
cutoffs: GcCutoffs {
time: Lsn(0x10),
space: Lsn(0x10),
@@ -8801,7 +8511,7 @@ mod tests {
// Update GC info
let mut guard = branch_tline.gc_info.write().unwrap();
*guard = GcInfo {
retain_lsns: vec![(Lsn(0x40), branch_tline.timeline_id, MaybeOffloaded::No)],
retain_lsns: vec![(Lsn(0x40), branch_tline.timeline_id)],
cutoffs: GcCutoffs {
time: Lsn(0x50),
space: Lsn(0x50),

View File

@@ -84,7 +84,7 @@ impl Drop for EphemeralFile {
fn drop(&mut self) {
// unlink the file
// we are clear to do this, because we have entered a gate
let path = self.buffered_writer.as_inner().as_inner().path();
let path = &self.buffered_writer.as_inner().as_inner().path;
let res = std::fs::remove_file(path);
if let Err(e) = res {
if e.kind() != std::io::ErrorKind::NotFound {
@@ -356,7 +356,7 @@ mod tests {
}
let file_contents =
std::fs::read(file.buffered_writer.as_inner().as_inner().path()).unwrap();
std::fs::read(&file.buffered_writer.as_inner().as_inner().path).unwrap();
assert_eq!(file_contents, &content[0..cap]);
let buffer_contents = file.buffered_writer.inspect_buffer();
@@ -392,7 +392,7 @@ mod tests {
.buffered_writer
.as_inner()
.as_inner()
.path()
.path
.metadata()
.unwrap();
assert_eq!(

View File

@@ -141,14 +141,14 @@ impl GcBlock {
Ok(())
}
pub(crate) fn before_delete(&self, timeline_id: &super::TimelineId) {
pub(crate) fn before_delete(&self, timeline: &super::Timeline) {
let unblocked = {
let mut g = self.reasons.lock().unwrap();
if g.is_empty() {
return;
}
g.remove(timeline_id);
g.remove(&timeline.timeline_id);
BlockingReasons::clean_and_summarize(g).is_none()
};

View File

@@ -48,9 +48,9 @@ mod layer_coverage;
use crate::context::RequestContext;
use crate::keyspace::KeyPartitioning;
use crate::repository::Key;
use crate::tenant::storage_layer::InMemoryLayer;
use anyhow::Result;
use pageserver_api::key::Key;
use pageserver_api::keyspace::{KeySpace, KeySpaceAccum};
use range_set_blaze::{CheckSortedDisjoint, RangeSetBlaze};
use std::collections::{HashMap, VecDeque};

View File

@@ -2836,7 +2836,7 @@ where
}
use {
crate::gc_result::GcResult, pageserver_api::models::TimelineGcRequest,
crate::repository::GcResult, pageserver_api::models::TimelineGcRequest,
utils::http::error::ApiError,
};

View File

@@ -27,7 +27,7 @@ use crate::tenant::Generation;
use crate::virtual_file::owned_buffers_io::io_buf_ext::IoBufExt;
use crate::virtual_file::{on_fatal_io_error, MaybeFatalIo, VirtualFile};
use crate::TEMP_FILE_SUFFIX;
use remote_storage::{DownloadError, DownloadOpts, GenericRemoteStorage, ListingMode, RemotePath};
use remote_storage::{DownloadError, GenericRemoteStorage, ListingMode, RemotePath};
use utils::crashsafe::path_with_suffix_extension;
use utils::id::{TenantId, TimelineId};
use utils::pausable_failpoint;
@@ -153,9 +153,7 @@ async fn download_object<'a>(
.with_context(|| format!("create a destination file for layer '{dst_path}'"))
.map_err(DownloadError::Other)?;
let download = storage
.download(src_path, &DownloadOpts::default(), cancel)
.await?;
let download = storage.download(src_path, cancel).await?;
pausable_failpoint!("before-downloading-layer-stream-pausable");
@@ -206,9 +204,7 @@ async fn download_object<'a>(
.with_context(|| format!("create a destination file for layer '{dst_path}'"))
.map_err(DownloadError::Other)?;
let mut download = storage
.download(src_path, &DownloadOpts::default(), cancel)
.await?;
let mut download = storage.download(src_path, cancel).await?;
pausable_failpoint!("before-downloading-layer-stream-pausable");
@@ -348,9 +344,7 @@ async fn do_download_index_part(
let index_part_bytes = download_retry_forever(
|| async {
let download = storage
.download(&remote_path, &DownloadOpts::default(), cancel)
.await?;
let download = storage.download(&remote_path, cancel).await?;
let mut bytes = Vec::new();
@@ -532,15 +526,10 @@ pub(crate) async fn download_initdb_tar_zst(
.with_context(|| format!("tempfile creation {temp_path}"))
.map_err(DownloadError::Other)?;
let download = match storage
.download(&remote_path, &DownloadOpts::default(), cancel)
.await
{
let download = match storage.download(&remote_path, cancel).await {
Ok(dl) => dl,
Err(DownloadError::NotFound) => {
storage
.download(&remote_preserved_path, &DownloadOpts::default(), cancel)
.await?
storage.download(&remote_preserved_path, cancel).await?
}
Err(other) => Err(other)?,
};

View File

@@ -49,7 +49,7 @@ use futures::Future;
use metrics::UIntGauge;
use pageserver_api::models::SecondaryProgress;
use pageserver_api::shard::TenantShardId;
use remote_storage::{DownloadError, DownloadOpts, Etag, GenericRemoteStorage};
use remote_storage::{DownloadError, Etag, GenericRemoteStorage};
use tokio_util::sync::CancellationToken;
use tracing::{info_span, instrument, warn, Instrument};
@@ -944,35 +944,36 @@ impl<'a> TenantDownloader<'a> {
) -> Result<HeatMapDownload, UpdateError> {
debug_assert_current_span_has_tenant_id();
let tenant_shard_id = self.secondary_state.get_tenant_shard_id();
// TODO: pull up etag check into the request, to do a conditional GET rather than
// issuing a GET and then maybe ignoring the response body
// (https://github.com/neondatabase/neon/issues/6199)
tracing::debug!("Downloading heatmap for secondary tenant",);
let heatmap_path = remote_heatmap_path(tenant_shard_id);
let cancel = &self.secondary_state.cancel;
let opts = DownloadOpts {
etag: prev_etag.cloned(),
..Default::default()
};
backoff::retry(
|| async {
let download = match self
let download = self
.remote_storage
.download(&heatmap_path, &opts, cancel)
.download(&heatmap_path, cancel)
.await
{
Ok(download) => download,
Err(DownloadError::Unmodified) => return Ok(HeatMapDownload::Unmodified),
Err(err) => return Err(err.into()),
};
.map_err(UpdateError::from)?;
let mut heatmap_bytes = Vec::new();
let mut body = tokio_util::io::StreamReader::new(download.download_stream);
let _size = tokio::io::copy_buf(&mut body, &mut heatmap_bytes).await?;
Ok(HeatMapDownload::Modified(HeatMapModified {
etag: download.etag,
last_modified: download.last_modified,
bytes: heatmap_bytes,
}))
SECONDARY_MODE.download_heatmap.inc();
if Some(&download.etag) == prev_etag {
Ok(HeatMapDownload::Unmodified)
} else {
let mut heatmap_bytes = Vec::new();
let mut body = tokio_util::io::StreamReader::new(download.download_stream);
let _size = tokio::io::copy_buf(&mut body, &mut heatmap_bytes).await?;
Ok(HeatMapDownload::Modified(HeatMapModified {
etag: download.etag,
last_modified: download.last_modified,
bytes: heatmap_bytes,
}))
}
},
|e| matches!(e, UpdateError::NoData | UpdateError::Cancelled),
FAILED_DOWNLOAD_WARN_THRESHOLD,
@@ -983,7 +984,6 @@ impl<'a> TenantDownloader<'a> {
.await
.ok_or_else(|| UpdateError::Cancelled)
.and_then(|x| x)
.inspect(|_| SECONDARY_MODE.download_heatmap.inc())
}
/// Download heatmap layers that are not present on local disk, or update their

View File

@@ -12,7 +12,7 @@ use crate::context::RequestContext;
use crate::pgdatadir_mapping::CalculateLogicalSizeError;
use super::{GcError, LogicalSizeCalculationCause, Tenant};
use crate::tenant::{MaybeOffloaded, Timeline};
use crate::tenant::Timeline;
use utils::id::TimelineId;
use utils::lsn::Lsn;
@@ -264,12 +264,10 @@ pub(super) async fn gather_inputs(
let mut lsns: Vec<(Lsn, LsnKind)> = gc_info
.retain_lsns
.iter()
.filter(|(lsn, _child_id, is_offloaded)| {
lsn > &ancestor_lsn && *is_offloaded == MaybeOffloaded::No
})
.filter(|(lsn, _child_id)| lsn > &ancestor_lsn)
.copied()
// this assumes there are no other retain_lsns than the branchpoints
.map(|(lsn, _child_id, _is_offloaded)| (lsn, LsnKind::BranchPoint))
.map(|(lsn, _child_id)| (lsn, LsnKind::BranchPoint))
.collect::<Vec<_>>();
lsns.extend(lease_points.iter().map(|&lsn| (lsn, LsnKind::LeasePoint)));

View File

@@ -11,11 +11,11 @@ pub mod merge_iterator;
pub mod split_writer;
use crate::context::{AccessStatsBehavior, RequestContext};
use crate::repository::Value;
use crate::walrecord::NeonWalRecord;
use bytes::Bytes;
use pageserver_api::key::Key;
use pageserver_api::keyspace::{KeySpace, KeySpaceRandomAccum};
use pageserver_api::record::NeonWalRecord;
use pageserver_api::value::Value;
use std::cmp::{Ordering, Reverse};
use std::collections::hash_map::Entry;
use std::collections::{BinaryHeap, HashMap};

View File

@@ -30,6 +30,7 @@
use crate::config::PageServerConf;
use crate::context::{PageContentKind, RequestContext, RequestContextBuilder};
use crate::page_cache::{self, FileId, PAGE_SZ};
use crate::repository::{Key, Value, KEY_SIZE};
use crate::tenant::blob_io::BlobWriter;
use crate::tenant::block_io::{BlockBuf, BlockCursor, BlockLease, BlockReader, FileBlockReader};
use crate::tenant::disk_btree::{
@@ -44,7 +45,7 @@ use crate::tenant::vectored_blob_io::{
use crate::tenant::PageReconstructError;
use crate::virtual_file::owned_buffers_io::io_buf_ext::{FullSlice, IoBufExt};
use crate::virtual_file::{self, MaybeFatalIo, VirtualFile};
use crate::TEMP_FILE_SUFFIX;
use crate::{walrecord, TEMP_FILE_SUFFIX};
use crate::{DELTA_FILE_MAGIC, STORAGE_FORMAT_VERSION};
use anyhow::{anyhow, bail, ensure, Context, Result};
use bytes::BytesMut;
@@ -52,12 +53,9 @@ use camino::{Utf8Path, Utf8PathBuf};
use futures::StreamExt;
use itertools::Itertools;
use pageserver_api::config::MaxVectoredReadBytes;
use pageserver_api::key::DBDIR_KEY;
use pageserver_api::key::{Key, KEY_SIZE};
use pageserver_api::keyspace::KeySpace;
use pageserver_api::models::ImageCompressionAlgorithm;
use pageserver_api::shard::TenantShardId;
use pageserver_api::value::Value;
use rand::{distributions::Alphanumeric, Rng};
use serde::{Deserialize, Serialize};
use std::collections::VecDeque;
@@ -574,7 +572,7 @@ impl DeltaLayerWriterInner {
ensure!(
metadata.len() <= S3_UPLOAD_LIMIT,
"Created delta layer file at {} of size {} above limit {S3_UPLOAD_LIMIT}!",
file.path(),
file.path,
metadata.len()
);
@@ -792,7 +790,7 @@ impl DeltaLayerInner {
max_vectored_read_bytes: Option<MaxVectoredReadBytes>,
ctx: &RequestContext,
) -> anyhow::Result<Self> {
let file = VirtualFile::open_v2(path, ctx)
let file = VirtualFile::open(path, ctx)
.await
.context("open layer file")?;
@@ -965,25 +963,14 @@ impl DeltaLayerInner {
.blobs_at
.as_slice()
.iter()
.filter_map(|(_, blob_meta)| {
if blob_meta.key.is_rel_dir_key() || blob_meta.key == DBDIR_KEY {
// The size of values for these keys is unbounded and can
// grow very large in pathological cases.
None
} else {
Some(format!("{}@{}", blob_meta.key, blob_meta.lsn))
}
})
.map(|(_, blob_meta)| format!("{}@{}", blob_meta.key, blob_meta.lsn))
.join(", ");
if !offenders.is_empty() {
tracing::warn!(
"Oversized vectored read ({} > {}) for keys {}",
largest_read_size,
read_size_soft_max,
offenders
);
}
tracing::warn!(
"Oversized vectored read ({} > {}) for keys {}",
largest_read_size,
read_size_soft_max,
offenders
);
}
largest_read_size
@@ -1023,7 +1010,7 @@ impl DeltaLayerInner {
blob_meta.key,
PageReconstructError::Other(anyhow!(
"Failed to read blobs from virtual file {}: {}",
self.file.path(),
self.file.path,
kind
)),
);
@@ -1049,7 +1036,7 @@ impl DeltaLayerInner {
meta.meta.key,
PageReconstructError::Other(anyhow!(e).context(format!(
"Failed to decompress blob from virtual file {}",
self.file.path(),
self.file.path,
))),
);
@@ -1067,7 +1054,7 @@ impl DeltaLayerInner {
meta.meta.key,
PageReconstructError::Other(anyhow!(e).context(format!(
"Failed to deserialize blob from virtual file {}",
self.file.path(),
self.file.path,
))),
);
@@ -1199,6 +1186,7 @@ impl DeltaLayerInner {
let mut prev: Option<(Key, Lsn, BlobRef)> = None;
let mut read_builder: Option<ChunkedVectoredReadBuilder> = None;
let align = virtual_file::get_io_buffer_alignment();
let max_read_size = self
.max_vectored_read_bytes
@@ -1247,6 +1235,7 @@ impl DeltaLayerInner {
offsets.end.pos(),
meta,
max_read_size,
align,
))
}
} else {
@@ -1295,7 +1284,7 @@ impl DeltaLayerInner {
// is it an image or will_init walrecord?
// FIXME: this could be handled by threading the BlobRef to the
// VectoredReadBuilder
let will_init = pageserver_api::value::ValueBytes::will_init(&data)
let will_init = crate::repository::ValueBytes::will_init(&data)
.inspect_err(|_e| {
#[cfg(feature = "testing")]
tracing::error!(data=?utils::Hex(&data), err=?_e, %key, %lsn, "failed to parse will_init out of serialized value");
@@ -1358,7 +1347,7 @@ impl DeltaLayerInner {
format!(" img {} bytes", img.len())
}
Value::WalRecord(rec) => {
let wal_desc = pageserver_api::record::describe_wal_record(&rec)?;
let wal_desc = walrecord::describe_wal_record(&rec)?;
format!(
" rec {} bytes will_init: {} {}",
buf.len(),
@@ -1603,6 +1592,7 @@ pub(crate) mod test {
use rand::RngCore;
use super::*;
use crate::repository::Value;
use crate::tenant::harness::TIMELINE_ID;
use crate::tenant::storage_layer::{Layer, ResidentLayer};
use crate::tenant::vectored_blob_io::StreamingVectoredReadPlanner;
@@ -1614,7 +1604,6 @@ pub(crate) mod test {
DEFAULT_PG_VERSION,
};
use bytes::Bytes;
use pageserver_api::value::Value;
/// Construct an index for a fictional delta layer and and then
/// traverse in order to plan vectored reads for a query. Finally,
@@ -1967,8 +1956,8 @@ pub(crate) mod test {
#[tokio::test]
async fn copy_delta_prefix_smoke() {
use crate::walrecord::NeonWalRecord;
use bytes::Bytes;
use pageserver_api::record::NeonWalRecord;
let h = crate::tenant::harness::TenantHarness::create("truncate_delta_smoke")
.await

View File

@@ -7,7 +7,7 @@ use pageserver_api::{
};
use utils::lsn::Lsn;
use pageserver_api::value::Value;
use crate::repository::Value;
use super::merge_iterator::MergeIterator;
@@ -121,8 +121,8 @@ mod tests {
#[tokio::test]
async fn filter_keyspace_iterator() {
use crate::repository::Value;
use bytes::Bytes;
use pageserver_api::value::Value;
let harness = TenantHarness::create("filter_iterator_filter_keyspace_iterator")
.await

View File

@@ -28,6 +28,7 @@
use crate::config::PageServerConf;
use crate::context::{PageContentKind, RequestContext, RequestContextBuilder};
use crate::page_cache::{self, FileId, PAGE_SZ};
use crate::repository::{Key, Value, KEY_SIZE};
use crate::tenant::blob_io::BlobWriter;
use crate::tenant::block_io::{BlockBuf, FileBlockReader};
use crate::tenant::disk_btree::{
@@ -48,11 +49,8 @@ use camino::{Utf8Path, Utf8PathBuf};
use hex;
use itertools::Itertools;
use pageserver_api::config::MaxVectoredReadBytes;
use pageserver_api::key::DBDIR_KEY;
use pageserver_api::key::{Key, KEY_SIZE};
use pageserver_api::keyspace::KeySpace;
use pageserver_api::shard::{ShardIdentity, TenantShardId};
use pageserver_api::value::Value;
use rand::{distributions::Alphanumeric, Rng};
use serde::{Deserialize, Serialize};
use std::collections::VecDeque;
@@ -390,7 +388,7 @@ impl ImageLayerInner {
max_vectored_read_bytes: Option<MaxVectoredReadBytes>,
ctx: &RequestContext,
) -> anyhow::Result<Self> {
let file = VirtualFile::open_v2(path, ctx)
let file = VirtualFile::open(path, ctx)
.await
.context("open layer file")?;
let file_id = page_cache::next_file_id();
@@ -589,25 +587,14 @@ impl ImageLayerInner {
.blobs_at
.as_slice()
.iter()
.filter_map(|(_, blob_meta)| {
if blob_meta.key.is_rel_dir_key() || blob_meta.key == DBDIR_KEY {
// The size of values for these keys is unbounded and can
// grow very large in pathological cases.
None
} else {
Some(format!("{}@{}", blob_meta.key, blob_meta.lsn))
}
})
.map(|(_, blob_meta)| format!("{}@{}", blob_meta.key, blob_meta.lsn))
.join(", ");
if !offenders.is_empty() {
tracing::warn!(
"Oversized vectored read ({} > {}) for keys {}",
buf_size,
max_vectored_read_bytes,
offenders
);
}
tracing::warn!(
"Oversized vectored read ({} > {}) for keys {}",
buf_size,
max_vectored_read_bytes,
offenders
);
}
let buf = BytesMut::with_capacity(buf_size);
@@ -627,7 +614,7 @@ impl ImageLayerInner {
meta.meta.key,
PageReconstructError::Other(anyhow!(e).context(format!(
"Failed to decompress blob from virtual file {}",
self.file.path(),
self.file.path,
))),
);
@@ -648,7 +635,7 @@ impl ImageLayerInner {
blob_meta.key,
PageReconstructError::from(anyhow!(
"Failed to read blobs from virtual file {}: {}",
self.file.path(),
self.file.path,
kind
)),
);
@@ -1094,7 +1081,6 @@ mod test {
use pageserver_api::{
key::Key,
shard::{ShardCount, ShardIdentity, ShardNumber, ShardStripeSize},
value::Value,
};
use utils::{
generation::Generation,
@@ -1104,6 +1090,7 @@ mod test {
use crate::{
context::RequestContext,
repository::Value,
tenant::{
config::TenantConf,
harness::{TenantHarness, TIMELINE_ID},

View File

@@ -7,6 +7,7 @@
use crate::assert_u64_eq_usize::{u64_to_usize, U64IsUsize, UsizeIsU64};
use crate::config::PageServerConf;
use crate::context::{PageContentKind, RequestContext, RequestContextBuilder};
use crate::repository::{Key, Value};
use crate::tenant::ephemeral_file::EphemeralFile;
use crate::tenant::timeline::GetVectoredError;
use crate::tenant::PageReconstructError;
@@ -16,11 +17,9 @@ use anyhow::{anyhow, Context, Result};
use bytes::Bytes;
use camino::Utf8PathBuf;
use pageserver_api::key::CompactKey;
use pageserver_api::key::Key;
use pageserver_api::keyspace::KeySpace;
use pageserver_api::models::InMemoryLayerInfo;
use pageserver_api::shard::TenantShardId;
use pageserver_api::value::Value;
use std::collections::{BTreeMap, HashMap};
use std::sync::{Arc, OnceLock};
use std::time::Instant;

View File

@@ -760,8 +760,8 @@ async fn evict_and_wait_does_not_wait_for_download() {
/// Also checks that the same does not happen on a non-evicted layer (regression test).
#[tokio::test(start_paused = true)]
async fn eviction_cancellation_on_drop() {
use crate::repository::Value;
use bytes::Bytes;
use pageserver_api::value::Value;
// this is the runtime on which Layer spawns the blocking tasks on
let handle = tokio::runtime::Handle::current();
@@ -782,7 +782,7 @@ async fn eviction_cancellation_on_drop() {
let mut writer = timeline.writer().await;
writer
.put(
pageserver_api::key::Key::from_i128(5),
crate::repository::Key::from_i128(5),
Lsn(0x20),
&Value::Image(Bytes::from_static(b"this does not matter either")),
&ctx,

View File

@@ -3,7 +3,7 @@ use pageserver_api::shard::TenantShardId;
use std::ops::Range;
use utils::{id::TimelineId, lsn::Lsn};
use pageserver_api::key::Key;
use crate::repository::Key;
use super::{DeltaLayerName, ImageLayerName, LayerName};

Some files were not shown because too many files have changed in this diff Show More