Compare commits

..

5 Commits

Author SHA1 Message Date
Vlad Lazar
b3ef315041 more wip 2024-11-06 19:41:22 +01:00
Vlad Lazar
f0044b8651 wip 2024-11-06 16:13:14 +01:00
Vlad Lazar
b7ff993df6 wal_decoder: make InterpretedWalRecord serde 2024-11-06 16:13:14 +01:00
Vlad Lazar
5d096f127e safekeeper: parse new connection configs 2024-11-06 16:13:14 +01:00
Vlad Lazar
70cdd56294 pageserver: include shard id when subscribing to safekeeper 2024-11-06 16:13:14 +01:00
99 changed files with 1191 additions and 2402 deletions

View File

@@ -0,0 +1,36 @@
name: "Set custom docker config directory"
description: "Create a directory for docker config and set DOCKER_CONFIG"
# Use custom DOCKER_CONFIG directory to avoid conflicts with default settings
runs:
using: "composite"
steps:
- name: Show warning on GitHub-hosted runners
if: runner.environment == 'github-hosted'
shell: bash -euo pipefail {0}
run: |
# Using the following environment variables to find a path to the workflow file
# ${GITHUB_WORKFLOW_REF} - octocat/hello-world/.github/workflows/my-workflow.yml@refs/heads/my_branch
# ${GITHUB_REPOSITORY} - octocat/hello-world
# ${GITHUB_REF} - refs/heads/my_branch
# From https://docs.github.com/en/actions/writing-workflows/choosing-what-your-workflow-does/variables
filename_with_ref=${GITHUB_WORKFLOW_REF#"$GITHUB_REPOSITORY/"}
filename=${filename_with_ref%"@$GITHUB_REF"}
# https://docs.github.com/en/actions/writing-workflows/choosing-what-your-workflow-does/workflow-commands-for-github-actions#setting-a-warning-message
title='Unnecessary usage of `.github/actions/set-docker-config-dir`'
message='No need to use `.github/actions/set-docker-config-dir` action on GitHub-hosted runners'
echo "::warning file=${filename},title=${title}::${message}"
- uses: pyTooling/Actions/with-post-step@74afc5a42a17a046c90c68cb5cfa627e5c6c5b6b # v1.0.7
env:
DOCKER_CONFIG: .docker-custom-${{ github.run_id }}-${{ github.run_attempt }}
with:
main: |
mkdir -p "${DOCKER_CONFIG}"
echo DOCKER_CONFIG=${DOCKER_CONFIG} | tee -a $GITHUB_ENV
post: |
if [ -d "${DOCKER_CONFIG}" ]; then
rm -r "${DOCKER_CONFIG}"
fi

View File

@@ -1,37 +0,0 @@
name: Check Codestyle Python
on:
workflow_call:
inputs:
build-tools-image:
description: 'build-tools image'
required: true
type: string
defaults:
run:
shell: bash -euxo pipefail {0}
jobs:
check-codestyle-python:
runs-on: [ self-hosted, small ]
container:
image: ${{ inputs.build-tools-image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
options: --init
steps:
- uses: actions/checkout@v4
- uses: actions/cache@v4
with:
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
- run: ./scripts/pysync
- run: poetry run ruff check .
- run: poetry run ruff format --check .
- run: poetry run mypy .

View File

@@ -64,7 +64,7 @@ jobs:
- uses: actions/checkout@v4
- uses: neondatabase/dev-actions/set-docker-config-dir@6094485bf440001c94a94a3f9e221e81ff6b6193
- uses: ./.github/actions/set-docker-config-dir
- uses: docker/setup-buildx-action@v3
with:
cache-binary: false

View File

@@ -90,10 +90,35 @@ jobs:
check-codestyle-python:
needs: [ check-permissions, build-build-tools-image ]
uses: ./.github/workflows/_check-codestyle-python.yml
with:
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
secrets: inherit
runs-on: [ self-hosted, small ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
options: --init
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Cache poetry deps
uses: actions/cache@v4
with:
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
- name: Install Python deps
run: ./scripts/pysync
- name: Run `ruff check` to ensure code format
run: poetry run ruff check .
- name: Run `ruff format` to ensure code format
run: poetry run ruff format --check .
- name: Run mypy to check types
run: poetry run mypy .
check-codestyle-jsonnet:
needs: [ check-permissions, build-build-tools-image ]
@@ -116,7 +141,6 @@ jobs:
# Check that the vendor/postgres-* submodules point to the
# corresponding REL_*_STABLE_neon branches.
check-submodules:
needs: [ check-permissions ]
runs-on: ubuntu-22.04
steps:
- name: Checkout
@@ -528,7 +552,7 @@ jobs:
with:
submodules: true
- uses: neondatabase/dev-actions/set-docker-config-dir@6094485bf440001c94a94a3f9e221e81ff6b6193
- uses: ./.github/actions/set-docker-config-dir
- uses: docker/setup-buildx-action@v3
with:
cache-binary: false
@@ -619,7 +643,7 @@ jobs:
with:
submodules: true
- uses: neondatabase/dev-actions/set-docker-config-dir@6094485bf440001c94a94a3f9e221e81ff6b6193
- uses: ./.github/actions/set-docker-config-dir
- uses: docker/setup-buildx-action@v3
with:
cache-binary: false
@@ -800,7 +824,7 @@ jobs:
curl -fL https://github.com/neondatabase/autoscaling/releases/download/$VM_BUILDER_VERSION/vm-builder -o vm-builder
chmod +x vm-builder
- uses: neondatabase/dev-actions/set-docker-config-dir@6094485bf440001c94a94a3f9e221e81ff6b6193
- uses: ./.github/actions/set-docker-config-dir
- uses: docker/login-action@v3
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
@@ -836,7 +860,7 @@ jobs:
steps:
- uses: actions/checkout@v4
- uses: neondatabase/dev-actions/set-docker-config-dir@6094485bf440001c94a94a3f9e221e81ff6b6193
- uses: ./.github/actions/set-docker-config-dir
- uses: docker/login-action@v3
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}

View File

@@ -1,94 +0,0 @@
name: Pre-merge checks
on:
merge_group:
branches:
- main
defaults:
run:
shell: bash -euxo pipefail {0}
# No permission for GITHUB_TOKEN by default; the **minimal required** set of permissions should be granted in each job.
permissions: {}
jobs:
get-changed-files:
runs-on: ubuntu-22.04
outputs:
python-changed: ${{ steps.python-src.outputs.any_changed }}
steps:
- uses: actions/checkout@v4
- uses: tj-actions/changed-files@4edd678ac3f81e2dc578756871e4d00c19191daf # v45.0.4
id: python-src
with:
files: |
.github/workflows/pre-merge-checks.yml
**/**.py
poetry.lock
pyproject.toml
- name: PRINT ALL CHANGED FILES FOR DEBUG PURPOSES
env:
PYTHON_CHANGED_FILES: ${{ steps.python-src.outputs.all_changed_files }}
run: |
echo "${PYTHON_CHANGED_FILES}"
check-build-tools-image:
if: needs.get-changed-files.outputs.python-changed == 'true'
needs: [ get-changed-files ]
uses: ./.github/workflows/check-build-tools-image.yml
build-build-tools-image:
needs: [ check-build-tools-image ]
uses: ./.github/workflows/build-build-tools-image.yml
with:
image-tag: ${{ needs.check-build-tools-image.outputs.image-tag }}
secrets: inherit
check-codestyle-python:
if: needs.get-changed-files.outputs.python-changed == 'true'
needs: [ get-changed-files, build-build-tools-image ]
uses: ./.github/workflows/_check-codestyle-python.yml
with:
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
secrets: inherit
# To get items from the merge queue merged into main we need to satisfy "Status checks that are required".
# Currently we require 2 jobs (checks with exact name):
# - conclusion
# - neon-cloud-e2e
conclusion:
if: always()
permissions:
statuses: write # for `github.repos.createCommitStatus(...)`
needs:
- get-changed-files
- check-codestyle-python
runs-on: ubuntu-22.04
steps:
- name: Create fake `neon-cloud-e2e` check
uses: actions/github-script@v7
with:
# Retry script for 5XX server errors: https://github.com/actions/github-script#retries
retries: 5
script: |
const { repo, owner } = context.repo;
const targetUrl = `${context.serverUrl}/${owner}/${repo}/actions/runs/${context.runId}`;
await github.rest.repos.createCommitStatus({
owner: owner,
repo: repo,
sha: context.sha,
context: `neon-cloud-e2e`,
state: `success`,
target_url: targetUrl,
description: `fake check for merge queue`,
});
- name: Fail the job if any of the dependencies do not succeed or skipped
run: exit 1
if: |
(contains(needs.check-codestyle-python.result, 'skipped') && needs.get-changed-files.outputs.python-changed == 'true')
|| contains(needs.*.result, 'failure')
|| contains(needs.*.result, 'cancelled')

View File

@@ -23,7 +23,6 @@ on:
- Test Postgres client libraries
- Trigger E2E Tests
- cleanup caches by a branch
- Pre-merge checks
types: [completed]
jobs:

101
Cargo.lock generated
View File

@@ -1245,7 +1245,7 @@ dependencies = [
"tar",
"thiserror",
"tokio",
"tokio-postgres",
"tokio-postgres 0.7.7",
"tokio-stream",
"tokio-util",
"tracing",
@@ -1351,7 +1351,7 @@ dependencies = [
"storage_broker",
"thiserror",
"tokio",
"tokio-postgres",
"tokio-postgres 0.7.7",
"tokio-util",
"toml",
"toml_edit",
@@ -3620,8 +3620,8 @@ dependencies = [
"pageserver_compaction",
"pin-project-lite",
"postgres",
"postgres-protocol",
"postgres-types",
"postgres-protocol 0.6.4",
"postgres-types 0.2.4",
"postgres_backend",
"postgres_connection",
"postgres_ffi",
@@ -3649,7 +3649,7 @@ dependencies = [
"tokio",
"tokio-epoll-uring",
"tokio-io-timeout",
"tokio-postgres",
"tokio-postgres 0.7.7",
"tokio-stream",
"tokio-tar",
"tokio-util",
@@ -3707,7 +3707,7 @@ dependencies = [
"serde",
"thiserror",
"tokio",
"tokio-postgres",
"tokio-postgres 0.7.7",
"tokio-stream",
"tokio-util",
"utils",
@@ -4006,14 +4006,31 @@ dependencies = [
[[package]]
name = "postgres"
version = "0.19.4"
source = "git+https://github.com/neondatabase/rust-postgres.git?rev=20031d7a9ee1addeae6e0968e3899ae6bf01cee2#20031d7a9ee1addeae6e0968e3899ae6bf01cee2"
dependencies = [
"bytes",
"fallible-iterator",
"futures-util",
"log",
"tokio",
"tokio-postgres",
"tokio-postgres 0.7.7",
]
[[package]]
name = "postgres-protocol"
version = "0.6.4"
dependencies = [
"base64 0.20.0",
"byteorder",
"bytes",
"fallible-iterator",
"hmac",
"lazy_static",
"md-5",
"memchr",
"rand 0.8.5",
"sha2",
"stringprep",
"tokio",
]
[[package]]
@@ -4035,6 +4052,17 @@ dependencies = [
"tokio",
]
[[package]]
name = "postgres-types"
version = "0.2.4"
dependencies = [
"bytes",
"fallible-iterator",
"postgres-protocol 0.6.4",
"serde",
"serde_json",
]
[[package]]
name = "postgres-types"
version = "0.2.4"
@@ -4042,7 +4070,7 @@ source = "git+https://github.com/neondatabase/rust-postgres.git?rev=20031d7a9ee1
dependencies = [
"bytes",
"fallible-iterator",
"postgres-protocol",
"postgres-protocol 0.6.4 (git+https://github.com/neondatabase/rust-postgres.git?rev=20031d7a9ee1addeae6e0968e3899ae6bf01cee2)",
"serde",
"serde_json",
]
@@ -4060,7 +4088,7 @@ dependencies = [
"serde",
"thiserror",
"tokio",
"tokio-postgres",
"tokio-postgres 0.7.7",
"tokio-postgres-rustls",
"tokio-rustls 0.26.0",
"tokio-util",
@@ -4075,7 +4103,7 @@ dependencies = [
"itertools 0.10.5",
"once_cell",
"postgres",
"tokio-postgres",
"tokio-postgres 0.7.7",
"url",
]
@@ -4127,7 +4155,7 @@ dependencies = [
"byteorder",
"bytes",
"itertools 0.10.5",
"postgres-protocol",
"postgres-protocol 0.6.4",
"rand 0.8.5",
"serde",
"thiserror",
@@ -4313,7 +4341,7 @@ dependencies = [
"parquet_derive",
"pbkdf2",
"pin-project-lite",
"postgres-protocol",
"postgres-protocol 0.6.4",
"postgres_backend",
"pq_proto",
"prometheus",
@@ -4348,7 +4376,7 @@ dependencies = [
"tikv-jemalloc-ctl",
"tikv-jemallocator",
"tokio",
"tokio-postgres",
"tokio-postgres 0.7.7",
"tokio-postgres-rustls",
"tokio-rustls 0.26.0",
"tokio-tungstenite",
@@ -4743,7 +4771,6 @@ dependencies = [
"percent-encoding",
"pin-project-lite",
"rustls 0.22.4",
"rustls-native-certs 0.7.0",
"rustls-pemfile 2.1.1",
"rustls-pki-types",
"serde",
@@ -5147,7 +5174,6 @@ dependencies = [
"chrono",
"clap",
"crc32c",
"criterion",
"desim",
"fail",
"futures",
@@ -5155,12 +5181,12 @@ dependencies = [
"http 1.1.0",
"humantime",
"hyper 0.14.30",
"itertools 0.10.5",
"metrics",
"once_cell",
"pageserver_api",
"parking_lot 0.12.1",
"postgres",
"postgres-protocol",
"postgres-protocol 0.6.4",
"postgres_backend",
"postgres_ffi",
"pq_proto",
@@ -5180,7 +5206,7 @@ dependencies = [
"thiserror",
"tokio",
"tokio-io-timeout",
"tokio-postgres",
"tokio-postgres 0.7.7",
"tokio-stream",
"tokio-tar",
"tokio-util",
@@ -5188,6 +5214,7 @@ dependencies = [
"tracing-subscriber",
"url",
"utils",
"wal_decoder",
"walproposer",
"workspace_hack",
]
@@ -5824,7 +5851,7 @@ dependencies = [
"serde_json",
"storage_controller_client",
"tokio",
"tokio-postgres",
"tokio-postgres 0.7.7",
"tokio-postgres-rustls",
"tokio-stream",
"tokio-util",
@@ -6221,6 +6248,28 @@ dependencies = [
"syn 2.0.52",
]
[[package]]
name = "tokio-postgres"
version = "0.7.7"
dependencies = [
"async-trait",
"byteorder",
"bytes",
"fallible-iterator",
"futures-channel",
"futures-util",
"log",
"parking_lot 0.12.1",
"percent-encoding",
"phf",
"pin-project-lite",
"postgres-protocol 0.6.4",
"postgres-types 0.2.4",
"socket2",
"tokio",
"tokio-util",
]
[[package]]
name = "tokio-postgres"
version = "0.7.7"
@@ -6237,8 +6286,8 @@ dependencies = [
"percent-encoding",
"phf",
"pin-project-lite",
"postgres-protocol",
"postgres-types",
"postgres-protocol 0.6.4 (git+https://github.com/neondatabase/rust-postgres.git?rev=20031d7a9ee1addeae6e0968e3899ae6bf01cee2)",
"postgres-types 0.2.4 (git+https://github.com/neondatabase/rust-postgres.git?rev=20031d7a9ee1addeae6e0968e3899ae6bf01cee2)",
"socket2",
"tokio",
"tokio-util",
@@ -6253,7 +6302,7 @@ dependencies = [
"ring",
"rustls 0.23.16",
"tokio",
"tokio-postgres",
"tokio-postgres 0.7.7",
"tokio-rustls 0.26.0",
"x509-certificate",
]
@@ -6836,7 +6885,7 @@ dependencies = [
"serde_json",
"sysinfo",
"tokio",
"tokio-postgres",
"tokio-postgres 0.7.7",
"tokio-util",
"tracing",
"tracing-subscriber",
@@ -7343,7 +7392,7 @@ dependencies = [
"num-traits",
"once_cell",
"parquet",
"postgres-types",
"postgres-types 0.2.4 (git+https://github.com/neondatabase/rust-postgres.git?rev=20031d7a9ee1addeae6e0968e3899ae6bf01cee2)",
"prettyplease",
"proc-macro2",
"prost",
@@ -7368,7 +7417,7 @@ dependencies = [
"time",
"time-macros",
"tokio",
"tokio-postgres",
"tokio-postgres 0.7.7 (git+https://github.com/neondatabase/rust-postgres.git?rev=20031d7a9ee1addeae6e0968e3899ae6bf01cee2)",
"tokio-rustls 0.26.0",
"tokio-stream",
"tokio-util",

View File

@@ -214,10 +214,14 @@ log = "0.4"
#
# When those proxy changes are re-applied (see PR #8747), we can switch using
# the tip of the 'neon' branch again.
postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
postgres-protocol = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
postgres-types = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
# postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
# postgres-protocol = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
# postgres-types = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
# tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
postgres = { path = "../../.cargo/git/checkouts/rust-postgres-e2c00088c8e2b112/20031d7/postgres" }
postgres-protocol = { path = "../../.cargo/git/checkouts/rust-postgres-e2c00088c8e2b112/20031d7/postgres-protocol" }
postgres-types = { path = "../../.cargo/git/checkouts/rust-postgres-e2c00088c8e2b112/20031d7/postgres-types" }
tokio-postgres = { path = "../../.cargo/git/checkouts/rust-postgres-e2c00088c8e2b112/20031d7/tokio-postgres" }
## Local libraries
compute_api = { version = "0.1", path = "./libs/compute_api/" }
@@ -255,7 +259,8 @@ tonic-build = "0.12"
[patch.crates-io]
# Needed to get `tokio-postgres-rustls` to depend on our fork.
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
tokio-postgres = { path = "../../.cargo/git/checkouts/rust-postgres-e2c00088c8e2b112/20031d7/tokio-postgres" }
# tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
################# Binary contents sections

View File

@@ -1,66 +1,12 @@
ARG DEBIAN_VERSION=bullseye
FROM debian:bookworm-slim AS pgcopydb_builder
ARG DEBIAN_VERSION
RUN if [ "${DEBIAN_VERSION}" = "bookworm" ]; then \
set -e && \
apt update && \
apt install -y --no-install-recommends \
ca-certificates wget gpg && \
wget -qO - https://www.postgresql.org/media/keys/ACCC4CF8.asc | gpg --dearmor -o /usr/share/keyrings/postgresql-keyring.gpg && \
echo "deb [signed-by=/usr/share/keyrings/postgresql-keyring.gpg] http://apt.postgresql.org/pub/repos/apt bookworm-pgdg main" > /etc/apt/sources.list.d/pgdg.list && \
apt-get update && \
apt install -y --no-install-recommends \
build-essential \
autotools-dev \
libedit-dev \
libgc-dev \
libpam0g-dev \
libreadline-dev \
libselinux1-dev \
libxslt1-dev \
libssl-dev \
libkrb5-dev \
zlib1g-dev \
liblz4-dev \
libpq5 \
libpq-dev \
libzstd-dev \
postgresql-16 \
postgresql-server-dev-16 \
postgresql-common \
python3-sphinx && \
wget -O /tmp/pgcopydb.tar.gz https://github.com/dimitri/pgcopydb/archive/refs/tags/v0.17.tar.gz && \
mkdir /tmp/pgcopydb && \
tar -xzf /tmp/pgcopydb.tar.gz -C /tmp/pgcopydb --strip-components=1 && \
cd /tmp/pgcopydb && \
make -s clean && \
make -s -j12 install && \
libpq_path=$(find /lib /usr/lib -name "libpq.so.5" | head -n 1) && \
mkdir -p /pgcopydb/lib && \
cp "$libpq_path" /pgcopydb/lib/; \
else \
# copy command below will fail if we don't have dummy files, so we create them for other debian versions
mkdir -p /usr/lib/postgresql/16/bin && touch /usr/lib/postgresql/16/bin/pgcopydb && \
mkdir -p mkdir -p /pgcopydb/lib && touch /pgcopydb/lib/libpq.so.5; \
fi
FROM debian:${DEBIAN_VERSION}-slim AS build_tools
FROM debian:${DEBIAN_VERSION}-slim
ARG DEBIAN_VERSION
# Add nonroot user
RUN useradd -ms /bin/bash nonroot -b /home
SHELL ["/bin/bash", "-c"]
RUN mkdir -p /pgcopydb/bin && \
mkdir -p /pgcopydb/lib && \
chmod -R 755 /pgcopydb && \
chown -R nonroot:nonroot /pgcopydb
COPY --from=pgcopydb_builder /usr/lib/postgresql/16/bin/pgcopydb /pgcopydb/bin/pgcopydb
COPY --from=pgcopydb_builder /pgcopydb/lib/libpq.so.5 /pgcopydb/lib/libpq.so.5
# System deps
#
# 'gdb' is included so that we get backtraces of core dumps produced in
@@ -92,7 +38,7 @@ RUN set -e \
libseccomp-dev \
libsqlite3-dev \
libssl-dev \
$([[ "${DEBIAN_VERSION}" = "bullseye" ]] && echo libstdc++-10-dev || echo libstdc++-11-dev) \
$([[ "${DEBIAN_VERSION}" = "bullseye" ]] && libstdc++-10-dev || libstdc++-11-dev) \
libtool \
libxml2-dev \
libxmlsec1-dev \
@@ -289,13 +235,7 @@ RUN whoami \
&& cargo --version --verbose \
&& rustup --version --verbose \
&& rustc --version --verbose \
&& clang --version
RUN if [ "${DEBIAN_VERSION}" = "bookworm" ]; then \
LD_LIBRARY_PATH=/pgcopydb/lib /pgcopydb/bin/pgcopydb --version; \
else \
echo "pgcopydb is not available for ${DEBIAN_VERSION}"; \
fi
&& clang --version
# Set following flag to check in Makefile if its running in Docker
RUN touch /home/nonroot/.docker_build

View File

@@ -559,8 +559,8 @@ RUN case "${PG_VERSION}" in \
export TIMESCALEDB_CHECKSUM=584a351c7775f0e067eaa0e7277ea88cab9077cc4c455cbbf09a5d9723dce95d \
;; \
"v17") \
export TIMESCALEDB_VERSION=2.17.1 \
export TIMESCALEDB_CHECKSUM=6277cf43f5695e23dae1c5cfeba00474d730b66ed53665a84b787a6bb1a57e28 \
export TIMESCALEDB_VERSION=2.17.0 \
export TIMESCALEDB_CHECKSUM=155bf64391d3558c42f31ca0e523cfc6252921974f75298c9039ccad1c89811a \
;; \
esac && \
wget https://github.com/timescale/timescaledb/archive/refs/tags/${TIMESCALEDB_VERSION}.tar.gz -O timescaledb.tar.gz && \
@@ -1151,8 +1151,8 @@ COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# The topmost commit in the `neon` branch at the time of writing this
# https://github.com/Mooncake-Labs/pg_mooncake/commits/neon/
# https://github.com/Mooncake-Labs/pg_mooncake/commit/077c92c452bb6896a7b7776ee95f039984f076af
ENV PG_MOONCAKE_VERSION=077c92c452bb6896a7b7776ee95f039984f076af
# https://github.com/Mooncake-Labs/pg_mooncake/commit/568b5a82b5fc16136bdf4ca5aac3e0cc261ab48d
ENV PG_MOONCAKE_VERSION=568b5a82b5fc16136bdf4ca5aac3e0cc261ab48d
ENV PATH="/usr/local/pgsql/bin/:$PATH"
RUN case "${PG_VERSION}" in \

View File

@@ -3,7 +3,7 @@
metrics: [
import 'sql_exporter/checkpoints_req.libsonnet',
import 'sql_exporter/checkpoints_timed.libsonnet',
import 'sql_exporter/compute_backpressure_throttling_seconds.libsonnet',
import 'sql_exporter/compute_backpressure_throttling_ms.libsonnet',
import 'sql_exporter/compute_current_lsn.libsonnet',
import 'sql_exporter/compute_logical_snapshot_files.libsonnet',
import 'sql_exporter/compute_receive_lsn.libsonnet',

View File

@@ -1,10 +1,10 @@
{
metric_name: 'compute_backpressure_throttling_seconds',
metric_name: 'compute_backpressure_throttling_ms',
type: 'gauge',
help: 'Time compute has spent throttled',
key_labels: null,
values: [
'throttled',
],
query: importstr 'sql_exporter/compute_backpressure_throttling_seconds.sql',
query: importstr 'sql_exporter/compute_backpressure_throttling_ms.sql',
}

View File

@@ -0,0 +1 @@
SELECT neon.backpressure_throttling_time() AS throttled;

View File

@@ -1 +0,0 @@
SELECT neon.backpressure_throttling_time()::float8 / 1000 AS throttled;

View File

@@ -364,29 +364,11 @@ impl ComputeNode {
let pageserver_connect_micros = start_time.elapsed().as_micros() as u64;
let basebackup_cmd = match lsn {
Lsn(0) => {
if spec.spec.mode != ComputeMode::Primary {
format!(
"basebackup {} {} --gzip --replica",
spec.tenant_id, spec.timeline_id
)
} else {
format!("basebackup {} {} --gzip", spec.tenant_id, spec.timeline_id)
}
}
_ => {
if spec.spec.mode != ComputeMode::Primary {
format!(
"basebackup {} {} {} --gzip --replica",
spec.tenant_id, spec.timeline_id, lsn
)
} else {
format!(
"basebackup {} {} {} --gzip",
spec.tenant_id, spec.timeline_id, lsn
)
}
}
Lsn(0) => format!("basebackup {} {} --gzip", spec.tenant_id, spec.timeline_id),
_ => format!(
"basebackup {} {} {} --gzip",
spec.tenant_id, spec.timeline_id, lsn
),
};
let copyreader = client.copy_out(basebackup_cmd.as_str())?;

View File

@@ -73,12 +73,6 @@ pub fn write_postgres_conf(
)?;
}
// Locales
writeln!(file, "lc_messages='C.UTF-8'")?;
writeln!(file, "lc_monetary='C.UTF-8'")?;
writeln!(file, "lc_time='C.UTF-8'")?;
writeln!(file, "lc_numeric='C.UTF-8'")?;
match spec.mode {
ComputeMode::Primary => {}
ComputeMode::Static(lsn) => {

View File

@@ -944,9 +944,6 @@ fn handle_init(args: &InitCmdArgs) -> anyhow::Result<LocalEnv> {
pg_auth_type: AuthType::Trust,
http_auth_type: AuthType::Trust,
other: Default::default(),
// Typical developer machines use disks with slow fsync, and we don't care
// about data integrity: disable disk syncs.
no_sync: true,
}
})
.collect(),

View File

@@ -225,7 +225,6 @@ pub struct PageServerConf {
pub listen_http_addr: String,
pub pg_auth_type: AuthType,
pub http_auth_type: AuthType,
pub no_sync: bool,
}
impl Default for PageServerConf {
@@ -236,7 +235,6 @@ impl Default for PageServerConf {
listen_http_addr: String::new(),
pg_auth_type: AuthType::Trust,
http_auth_type: AuthType::Trust,
no_sync: false,
}
}
}
@@ -251,8 +249,6 @@ pub struct NeonLocalInitPageserverConf {
pub listen_http_addr: String,
pub pg_auth_type: AuthType,
pub http_auth_type: AuthType,
#[serde(default, skip_serializing_if = "std::ops::Not::not")]
pub no_sync: bool,
#[serde(flatten)]
pub other: HashMap<String, toml::Value>,
}
@@ -265,7 +261,6 @@ impl From<&NeonLocalInitPageserverConf> for PageServerConf {
listen_http_addr,
pg_auth_type,
http_auth_type,
no_sync,
other: _,
} = conf;
Self {
@@ -274,7 +269,6 @@ impl From<&NeonLocalInitPageserverConf> for PageServerConf {
listen_http_addr: listen_http_addr.clone(),
pg_auth_type: *pg_auth_type,
http_auth_type: *http_auth_type,
no_sync: *no_sync,
}
}
}
@@ -575,8 +569,6 @@ impl LocalEnv {
listen_http_addr: String,
pg_auth_type: AuthType,
http_auth_type: AuthType,
#[serde(default)]
no_sync: bool,
}
let config_toml_path = dentry.path().join("pageserver.toml");
let config_toml: PageserverConfigTomlSubset = toml_edit::de::from_str(
@@ -599,7 +591,6 @@ impl LocalEnv {
listen_http_addr,
pg_auth_type,
http_auth_type,
no_sync,
} = config_toml;
let IdentityTomlSubset {
id: identity_toml_id,
@@ -616,7 +607,6 @@ impl LocalEnv {
listen_http_addr,
pg_auth_type,
http_auth_type,
no_sync,
};
pageservers.push(conf);
}

View File

@@ -273,7 +273,6 @@ impl PageServerNode {
)
})?;
let args = vec!["-D", datadir_path_str];
background_process::start_process(
"pageserver",
&datadir,

View File

@@ -64,7 +64,6 @@ pub struct ConfigToml {
#[serde(with = "humantime_serde")]
pub wal_redo_timeout: Duration,
pub superuser: String,
pub locale: String,
pub page_cache_size: usize,
pub max_file_descriptors: usize,
pub pg_distrib_dir: Option<Utf8PathBuf>,
@@ -107,8 +106,6 @@ pub struct ConfigToml {
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>,
#[serde(skip_serializing_if = "Option::is_none")]
pub no_sync: Option<bool>,
}
#[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
@@ -277,7 +274,6 @@ pub mod defaults {
pub const DEFAULT_WAL_REDO_TIMEOUT: &str = "60 s";
pub const DEFAULT_SUPERUSER: &str = "cloud_admin";
pub const DEFAULT_LOCALE: &str = "C.UTF-8";
pub const DEFAULT_PAGE_CACHE_SIZE: usize = 8192;
pub const DEFAULT_MAX_FILE_DESCRIPTORS: usize = 100;
@@ -328,7 +324,6 @@ impl Default for ConfigToml {
wal_redo_timeout: (humantime::parse_duration(DEFAULT_WAL_REDO_TIMEOUT)
.expect("cannot parse default wal redo timeout")),
superuser: (DEFAULT_SUPERUSER.to_string()),
locale: DEFAULT_LOCALE.to_string(),
page_cache_size: (DEFAULT_PAGE_CACHE_SIZE),
max_file_descriptors: (DEFAULT_MAX_FILE_DESCRIPTORS),
pg_distrib_dir: None, // Utf8PathBuf::from("./pg_install"), // TODO: formely, this was std::env::current_dir()
@@ -394,7 +389,6 @@ impl Default for ConfigToml {
l0_flush: None,
virtual_file_io_mode: None,
tenant_config: TenantConfigToml::default(),
no_sync: None,
}
}
}

View File

@@ -24,7 +24,7 @@ pub struct Key {
/// When working with large numbers of Keys in-memory, it is more efficient to handle them as i128 than as
/// a struct of fields.
#[derive(Clone, Copy, Hash, PartialEq, Eq, Ord, PartialOrd)]
#[derive(Clone, Copy, Hash, PartialEq, Eq, Ord, PartialOrd, Serialize, Deserialize, Debug)]
pub struct CompactKey(i128);
/// The storage key size.

View File

@@ -24,7 +24,7 @@ use postgres_ffi::Oid;
// FIXME: should move 'forknum' as last field to keep this consistent with Postgres.
// Then we could replace the custom Ord and PartialOrd implementations below with
// deriving them. This will require changes in walredoproc.c.
#[derive(Debug, PartialEq, Eq, Hash, Clone, Copy, Serialize)]
#[derive(Debug, PartialEq, Eq, Hash, Clone, Copy, Serialize, Deserialize)]
pub struct RelTag {
pub forknum: u8,
pub spcnode: Oid,

View File

@@ -1,10 +1,10 @@
use std::ffi::{CStr, CString};
use std::ffi::CStr;
use bytes::{Bytes, BytesMut};
use crc32c::crc32c_append;
use utils::lsn::Lsn;
use super::bindings::{RmgrId, XLogLongPageHeaderData, XLogPageHeaderData, XLOG_PAGE_MAGIC};
use super::bindings::{XLogLongPageHeaderData, XLogPageHeaderData, XLOG_PAGE_MAGIC};
use super::xlog_utils::{
XlLogicalMessage, XLOG_RECORD_CRC_OFFS, XLOG_SIZE_OF_XLOG_RECORD, XLP_BKP_REMOVABLE,
XLP_FIRST_IS_CONTRECORD,
@@ -16,65 +16,11 @@ use crate::pg_constants::{
};
use crate::{WAL_SEGMENT_SIZE, XLOG_BLCKSZ};
/// A WAL record payload. Will be prefixed by an XLogRecord header when encoded.
pub struct Record {
pub rmid: RmgrId,
pub info: u8,
pub data: Bytes,
}
impl Record {
/// Encodes the WAL record including an XLogRecord header. prev_lsn is the start position of
/// the previous record in the WAL -- this is ignored by the Safekeeper, but not Postgres.
pub fn encode(&self, prev_lsn: Lsn) -> Bytes {
// Prefix data with block ID and length.
let data_header = Bytes::from(match self.data.len() {
0 => vec![],
1..=255 => vec![XLR_BLOCK_ID_DATA_SHORT, self.data.len() as u8],
256.. => {
let len_bytes = (self.data.len() as u32).to_le_bytes();
[&[XLR_BLOCK_ID_DATA_LONG], len_bytes.as_slice()].concat()
}
});
// Construct the WAL record header.
let mut header = XLogRecord {
xl_tot_len: (XLOG_SIZE_OF_XLOG_RECORD + data_header.len() + self.data.len()) as u32,
xl_xid: 0,
xl_prev: prev_lsn.into(),
xl_info: self.info,
xl_rmid: self.rmid,
__bindgen_padding_0: [0; 2],
xl_crc: 0, // see below
};
// Compute the CRC checksum for the data, and the header up to the CRC field.
let mut crc = 0;
crc = crc32c_append(crc, &data_header);
crc = crc32c_append(crc, &self.data);
crc = crc32c_append(crc, &header.encode().unwrap()[0..XLOG_RECORD_CRC_OFFS]);
header.xl_crc = crc;
// Encode the final header and record.
let header = header.encode().unwrap();
[header, data_header, self.data.clone()].concat().into()
}
}
/// Generates WAL record payloads.
///
/// TODO: currently only provides LogicalMessageGenerator for trivial noop messages. Add a generator
/// that creates a table and inserts rows.
pub trait RecordGenerator: Iterator<Item = Record> {}
impl<I: Iterator<Item = Record>> RecordGenerator for I {}
/// Generates binary WAL for use in tests and benchmarks. The provided record generator constructs
/// the WAL records. It is used as an iterator which yields encoded bytes for a single WAL record,
/// including internal page headers if it spans pages. Concatenating the bytes will yield a
/// complete, well-formed WAL, which can be chunked at segment boundaries if desired. Not optimized
/// for performance.
/// Generates binary WAL records for use in tests and benchmarks. Currently only generates logical
/// messages (effectively noops) with a fixed payload. It is used as an iterator which yields
/// encoded bytes for a single WAL record, including internal page headers if it spans pages.
/// Concatenating the bytes will yield a complete, well-formed WAL, which can be chunked at segment
/// boundaries if desired. Not optimized for performance.
///
/// The WAL format is version-dependant (see e.g. `XLOG_PAGE_MAGIC`), so make sure to import this
/// for the appropriate Postgres version (e.g. `postgres_ffi::v17::wal_generator::WalGenerator`).
@@ -85,10 +31,10 @@ impl<I: Iterator<Item = Record>> RecordGenerator for I {}
/// | Segment 1 | Segment 2 | Segment 3 |
/// | Page 1 | Page 2 | Page 3 | Page 4 | Page 5 | Page 6 | Page 7 | Page 8 | Page 9 |
/// | R1 | R2 |R3| R4 | R5 | R6 | R7 | R8 |
///
/// TODO: support generating actual tables and rows.
#[derive(Default)]
pub struct WalGenerator<R: RecordGenerator> {
/// Generates record payloads for the WAL.
pub record_generator: R,
pub struct WalGenerator {
/// Current LSN to append the next record at.
///
/// Callers can modify this (and prev_lsn) to restart generation at a different LSN, but should
@@ -100,35 +46,73 @@ pub struct WalGenerator<R: RecordGenerator> {
pub prev_lsn: Lsn,
}
impl<R: RecordGenerator> WalGenerator<R> {
// Hardcode the sys and timeline ID. We can make them configurable if we care about them.
impl WalGenerator {
// For now, hardcode the message payload.
// TODO: support specifying the payload size.
const PREFIX: &CStr = c"prefix";
const MESSAGE: &[u8] = b"message";
// Hardcode the sys, timeline, and DB IDs. We can make them configurable if we care about them.
const SYS_ID: u64 = 0;
const TIMELINE_ID: u32 = 1;
const DB_ID: u32 = 0;
/// Creates a new WAL generator with the given record generator.
pub fn new(record_generator: R) -> WalGenerator<R> {
Self {
record_generator,
lsn: Lsn(0),
prev_lsn: Lsn(0),
}
/// Creates a new WAL generator, which emits logical message records (noops).
pub fn new() -> Self {
Self::default()
}
/// Appends a record with an arbitrary payload at the current LSN, then increments the LSN.
/// Returns the WAL bytes for the record, including page headers and padding, and the start LSN.
fn append_record(&mut self, record: Record) -> (Lsn, Bytes) {
let record = record.encode(self.prev_lsn);
let record = Self::insert_pages(record, self.lsn);
let record = Self::pad_record(record, self.lsn);
let lsn = self.lsn;
self.prev_lsn = self.lsn;
self.lsn += record.len() as u64;
(lsn, record)
/// Encodes a logical message (basically a noop), with the given prefix and message.
pub(crate) fn encode_logical_message(prefix: &CStr, message: &[u8]) -> Bytes {
let prefix = prefix.to_bytes_with_nul();
let header = XlLogicalMessage {
db_id: Self::DB_ID,
transactional: 0,
prefix_size: prefix.len() as u64,
message_size: message.len() as u64,
};
[&header.encode(), prefix, message].concat().into()
}
/// Inserts page headers on 8KB page boundaries. Takes the current LSN position where the record
/// Encode a WAL record with the given payload data (e.g. a logical message).
pub(crate) fn encode_record(data: Bytes, rmid: u8, info: u8, prev_lsn: Lsn) -> Bytes {
// Prefix data with block ID and length.
let data_header = Bytes::from(match data.len() {
0 => vec![],
1..=255 => vec![XLR_BLOCK_ID_DATA_SHORT, data.len() as u8],
256.. => {
let len_bytes = (data.len() as u32).to_le_bytes();
[&[XLR_BLOCK_ID_DATA_LONG], len_bytes.as_slice()].concat()
}
});
// Construct the WAL record header.
let mut header = XLogRecord {
xl_tot_len: (XLOG_SIZE_OF_XLOG_RECORD + data_header.len() + data.len()) as u32,
xl_xid: 0,
xl_prev: prev_lsn.into(),
xl_info: info,
xl_rmid: rmid,
__bindgen_padding_0: [0; 2],
xl_crc: 0, // see below
};
// Compute the CRC checksum for the data, and the header up to the CRC field.
let mut crc = 0;
crc = crc32c_append(crc, &data_header);
crc = crc32c_append(crc, &data);
crc = crc32c_append(crc, &header.encode().unwrap()[0..XLOG_RECORD_CRC_OFFS]);
header.xl_crc = crc;
// Encode the final header and record.
let header = header.encode().unwrap();
[header, data_header, data].concat().into()
}
/// Injects page headers on 8KB page boundaries. Takes the current LSN position where the record
/// is to be appended.
fn insert_pages(record: Bytes, mut lsn: Lsn) -> Bytes {
fn encode_pages(record: Bytes, mut lsn: Lsn) -> Bytes {
// Fast path: record fits in current page, and the page already has a header.
if lsn.remaining_in_block() as usize >= record.len() && lsn.block_offset() > 0 {
return record;
@@ -189,71 +173,31 @@ impl<R: RecordGenerator> WalGenerator<R> {
}
[record, Bytes::from(vec![0; padding])].concat().into()
}
/// Generates a record with an arbitrary payload at the current LSN, then increments the LSN.
pub fn generate_record(&mut self, data: Bytes, rmid: u8, info: u8) -> Bytes {
let record = Self::encode_record(data, rmid, info, self.prev_lsn);
let record = Self::encode_pages(record, self.lsn);
let record = Self::pad_record(record, self.lsn);
self.prev_lsn = self.lsn;
self.lsn += record.len() as u64;
record
}
/// Generates a logical message at the current LSN. Can be used to construct arbitrary messages.
pub fn generate_logical_message(&mut self, prefix: &CStr, message: &[u8]) -> Bytes {
let data = Self::encode_logical_message(prefix, message);
self.generate_record(data, RM_LOGICALMSG_ID, XLOG_LOGICAL_MESSAGE)
}
}
/// Generates WAL records as an iterator.
impl<R: RecordGenerator> Iterator for WalGenerator<R> {
/// Generate WAL records as an iterator.
impl Iterator for WalGenerator {
type Item = (Lsn, Bytes);
fn next(&mut self) -> Option<Self::Item> {
let record = self.record_generator.next()?;
Some(self.append_record(record))
}
}
/// Generates logical message records (effectively noops) with a fixed message.
pub struct LogicalMessageGenerator {
prefix: CString,
message: Vec<u8>,
}
impl LogicalMessageGenerator {
const DB_ID: u32 = 0; // hardcoded for now
const RM_ID: RmgrId = RM_LOGICALMSG_ID;
const INFO: u8 = XLOG_LOGICAL_MESSAGE;
/// Creates a new LogicalMessageGenerator.
pub fn new(prefix: &CStr, message: &[u8]) -> Self {
Self {
prefix: prefix.to_owned(),
message: message.to_owned(),
}
}
/// Encodes a logical message.
fn encode(prefix: &CStr, message: &[u8]) -> Bytes {
let prefix = prefix.to_bytes_with_nul();
let header = XlLogicalMessage {
db_id: Self::DB_ID,
transactional: 0,
prefix_size: prefix.len() as u64,
message_size: message.len() as u64,
};
[&header.encode(), prefix, message].concat().into()
}
}
impl Iterator for LogicalMessageGenerator {
type Item = Record;
fn next(&mut self) -> Option<Self::Item> {
Some(Record {
rmid: Self::RM_ID,
info: Self::INFO,
data: Self::encode(&self.prefix, &self.message),
})
}
}
impl WalGenerator<LogicalMessageGenerator> {
/// Convenience method for appending a WAL record with an arbitrary logical message at the
/// current WAL LSN position. Returns the start LSN and resulting WAL bytes.
pub fn append_logical_message(&mut self, prefix: &CStr, message: &[u8]) -> (Lsn, Bytes) {
let record = Record {
rmid: LogicalMessageGenerator::RM_ID,
info: LogicalMessageGenerator::INFO,
data: LogicalMessageGenerator::encode(prefix, message),
};
self.append_record(record)
let lsn = self.lsn;
let record = self.generate_logical_message(Self::PREFIX, Self::MESSAGE);
Some((lsn, record))
}
}

View File

@@ -16,7 +16,7 @@ use utils::bin_ser::DeserializeError;
use utils::lsn::Lsn;
#[repr(C)]
#[derive(Debug)]
#[derive(Debug, Serialize, Deserialize)]
pub struct XlMultiXactCreate {
pub mid: MultiXactId,
/* new MultiXact's ID */
@@ -46,7 +46,7 @@ impl XlMultiXactCreate {
}
#[repr(C)]
#[derive(Debug)]
#[derive(Debug, Serialize, Deserialize)]
pub struct XlMultiXactTruncate {
pub oldest_multi_db: Oid,
/* to-be-truncated range of multixact offsets */
@@ -72,7 +72,7 @@ impl XlMultiXactTruncate {
}
#[repr(C)]
#[derive(Debug)]
#[derive(Debug, Serialize, Deserialize)]
pub struct XlRelmapUpdate {
pub dbid: Oid, /* database ID, or 0 for shared map */
pub tsid: Oid, /* database's tablespace, or pg_global */
@@ -90,7 +90,7 @@ impl XlRelmapUpdate {
}
#[repr(C)]
#[derive(Debug)]
#[derive(Debug, Serialize, Deserialize)]
pub struct XlReploriginDrop {
pub node_id: RepOriginId,
}
@@ -104,7 +104,7 @@ impl XlReploriginDrop {
}
#[repr(C)]
#[derive(Debug)]
#[derive(Debug, Serialize, Deserialize)]
pub struct XlReploriginSet {
pub remote_lsn: Lsn,
pub node_id: RepOriginId,
@@ -120,7 +120,7 @@ impl XlReploriginSet {
}
#[repr(C)]
#[derive(Debug, Clone, Copy)]
#[derive(Debug, Clone, Copy, Serialize, Deserialize)]
pub struct RelFileNode {
pub spcnode: Oid, /* tablespace */
pub dbnode: Oid, /* database */
@@ -911,7 +911,7 @@ impl XlSmgrCreate {
}
#[repr(C)]
#[derive(Debug)]
#[derive(Debug, Serialize, Deserialize)]
pub struct XlSmgrTruncate {
pub blkno: BlockNumber,
pub rnode: RelFileNode,
@@ -984,7 +984,7 @@ impl XlDropDatabase {
/// xl_xact_parsed_abort structs in PostgreSQL, but we use the same
/// struct for commits and aborts.
///
#[derive(Debug)]
#[derive(Debug, Serialize, Deserialize)]
pub struct XlXactParsedRecord {
pub xid: TransactionId,
pub info: u8,

View File

@@ -12,9 +12,9 @@ use super::bindings::{
CheckPoint, ControlFileData, DBState_DB_SHUTDOWNED, FullTransactionId, TimeLineID, TimestampTz,
XLogLongPageHeaderData, XLogPageHeaderData, XLogRecPtr, XLogRecord, XLogSegNo, XLOG_PAGE_MAGIC,
};
use super::wal_generator::LogicalMessageGenerator;
use super::wal_generator::WalGenerator;
use super::PG_MAJORVERSION;
use crate::pg_constants::{self, XLOG_XACT_COMMIT, XLOG_XACT_COMMIT_PREPARED};
use crate::pg_constants::{self, RM_LOGICALMSG_ID, XLOG_LOGICAL_MESSAGE};
use crate::PG_TLI;
use crate::{uint32, uint64, Oid};
use crate::{WAL_SEGMENT_SIZE, XLOG_BLCKSZ};
@@ -296,13 +296,6 @@ impl XLogRecord {
pub fn is_xlog_switch_record(&self) -> bool {
self.xl_info == pg_constants::XLOG_SWITCH && self.xl_rmid == pg_constants::RM_XLOG_ID
}
// Is this record a transaction commit?
pub fn is_xact_commit(&self) -> bool {
self.xl_rmid == pg_constants::RM_XACT_ID
&& (self.xl_info & pg_constants::XLOG_XACT_OPMASK == XLOG_XACT_COMMIT
|| self.xl_info & pg_constants::XLOG_XACT_OPMASK == XLOG_XACT_COMMIT_PREPARED)
}
}
impl XLogPageHeaderData {
@@ -500,10 +493,12 @@ pub fn encode_logical_message(prefix: &str, message: &str) -> Bytes {
// This function can take untrusted input, so discard any NUL bytes in the prefix string.
let prefix = CString::new(prefix.replace('\0', "")).expect("no NULs");
let message = message.as_bytes();
LogicalMessageGenerator::new(&prefix, message)
.next()
.unwrap()
.encode(Lsn(0))
WalGenerator::encode_record(
WalGenerator::encode_logical_message(&prefix, message),
RM_LOGICALMSG_ID,
XLOG_LOGICAL_MESSAGE,
Lsn(0),
)
}
#[cfg(test)]

View File

@@ -13,3 +13,4 @@ rand.workspace = true
tokio = { workspace = true, features = ["io-util"] }
thiserror.workspace = true
serde.workspace = true
# wal_decoder.workspace = true

View File

@@ -562,6 +562,7 @@ pub enum BeMessage<'a> {
options: &'a [&'a str],
},
KeepAlive(WalSndKeepAlive),
InterpretedWalRecord(InterpretedWalRecordBody<'a>),
}
/// Common shorthands.
@@ -665,6 +666,12 @@ pub struct XLogDataBody<'a> {
pub data: &'a [u8],
}
#[derive(Debug)]
pub struct InterpretedWalRecordBody<'a> {
pub wal_end: u64,
pub data: &'a [u8],
}
#[derive(Debug)]
pub struct WalSndKeepAlive {
pub wal_end: u64, // current end of WAL on the server
@@ -996,6 +1003,15 @@ impl BeMessage<'_> {
Ok(())
})?
}
BeMessage::InterpretedWalRecord(rec) => {
buf.put_u8(b'd'); // arbitrary?
write_body(buf, |buf| {
buf.put_u8(b'0');
buf.put_u64(rec.wal_end);
buf.put_slice(rec.data);
});
}
}
Ok(())
}

View File

@@ -1,4 +1,4 @@
#!/usr/bin/env bash
#!/bin/bash
set -euxo pipefail
@@ -6,44 +6,9 @@ PG_BIN=$1
WAL_PATH=$2
DATA_DIR=$3
PORT=$4
PG_VERSION=$5
SYSID=$(od -A n -j 24 -N 8 -t d8 "$WAL_PATH"/000000010000000000000002* | cut -c 3-)
# The way that initdb is invoked must match how the pageserver runs initdb.
function initdb_with_args {
local cmd=(
"$PG_BIN"/initdb
-E utf8
-U cloud_admin
-D "$DATA_DIR"
--locale 'C.UTF-8'
--lc-collate 'C.UTF-8'
--lc-ctype 'C.UTF-8'
--lc-messages 'C.UTF-8'
--lc-monetary 'C.UTF-8'
--lc-numeric 'C.UTF-8'
--lc-time 'C.UTF-8'
--sysid="$SYSID"
)
case "$PG_VERSION" in
14)
# Postgres 14 and below didn't support --locale-provider
;;
15 | 16)
cmd+=(--locale-provider 'libc')
;;
*)
# Postgres 17 added the builtin provider
cmd+=(--locale-provider 'builtin')
;;
esac
eval env -i LD_LIBRARY_PATH="$PG_BIN"/../lib "${cmd[*]}"
}
rm -fr "$DATA_DIR"
initdb_with_args
env -i LD_LIBRARY_PATH="$PG_BIN"/../lib "$PG_BIN"/initdb -E utf8 -U cloud_admin -D "$DATA_DIR" --sysid="$SYSID"
echo "port=$PORT" >> "$DATA_DIR"/postgresql.conf
echo "shared_preload_libraries='\$libdir/neon_rmgr.so'" >> "$DATA_DIR"/postgresql.conf
REDO_POS=0x$("$PG_BIN"/pg_controldata -D "$DATA_DIR" | grep -F "REDO location"| cut -c 42-)

View File

@@ -7,29 +7,65 @@ use postgres_connection::{parse_host_port, PgConnectionConfig};
use crate::id::TenantTimelineId;
/// Protocol used for safekeeper recovery. This sends raw Postgres WAL.
pub const POSTGRES_PROTO_VERSION: u8 = 0;
/// Protocol used for safekeeper to pageserver communication.
/// This sends interpreted WAL records for the pageserver to ingest
/// and is shard-aware.
pub const PAGESERVER_SAFEKEEPER_PROTO_VERSION: u8 = 1;
pub struct ConnectionConfigArgs<'a> {
pub protocol_version: u8,
pub ttid: TenantTimelineId,
pub shard_number: Option<u8>,
pub shard_count: Option<u8>,
pub shard_stripe_size: Option<u32>,
pub listen_pg_addr_str: &'a str,
pub auth_token: Option<&'a str>,
pub availability_zone: Option<&'a str>,
}
impl<'a> ConnectionConfigArgs<'a> {
fn options(&'a self) -> Vec<String> {
let mut options = vec![
"-c".to_owned(),
format!("timeline_id={}", self.ttid.timeline_id),
format!("tenant_id={}", self.ttid.tenant_id),
format!("protocol_version={}", self.protocol_version),
];
if self.shard_number.is_some() {
assert!(self.shard_count.is_some());
assert!(self.shard_stripe_size.is_some());
options.push(format!("shard_count={}", self.shard_count.unwrap()));
options.push(format!("shard_number={}", self.shard_number.unwrap()));
options.push(format!(
"shard_stripe_size={}",
self.shard_stripe_size.unwrap()
));
}
options
}
}
/// Create client config for fetching WAL from safekeeper on particular timeline.
/// listen_pg_addr_str is in form host:\[port\].
pub fn wal_stream_connection_config(
TenantTimelineId {
tenant_id,
timeline_id,
}: TenantTimelineId,
listen_pg_addr_str: &str,
auth_token: Option<&str>,
availability_zone: Option<&str>,
args: ConnectionConfigArgs,
) -> anyhow::Result<PgConnectionConfig> {
let (host, port) =
parse_host_port(listen_pg_addr_str).context("Unable to parse listen_pg_addr_str")?;
parse_host_port(args.listen_pg_addr_str).context("Unable to parse listen_pg_addr_str")?;
let port = port.unwrap_or(5432);
let mut connstr = PgConnectionConfig::new_host_port(host, port)
.extend_options([
"-c".to_owned(),
format!("timeline_id={}", timeline_id),
format!("tenant_id={}", tenant_id),
])
.set_password(auth_token.map(|s| s.to_owned()));
.extend_options(args.options())
.set_password(args.auth_token.map(|s| s.to_owned()));
if let Some(availability_zone) = availability_zone {
if let Some(availability_zone) = args.availability_zone {
connstr = connstr.extend_options([format!("availability_zone={}", availability_zone)]);
}

View File

@@ -32,16 +32,19 @@ use postgres_ffi::walrecord::{
XlSmgrTruncate, XlXactParsedRecord,
};
use postgres_ffi::{Oid, TransactionId};
use serde::{Deserialize, Serialize};
use utils::lsn::Lsn;
use crate::serialized_batch::SerializedValueBatch;
#[derive(Serialize, Deserialize)]
pub enum FlushUncommittedRecords {
Yes,
No,
}
/// An interpreted Postgres WAL record, ready to be handled by the pageserver
#[derive(Serialize, Deserialize)]
pub struct InterpretedWalRecord {
/// Optional metadata record - may cause writes to metadata keys
/// in the storage engine
@@ -62,6 +65,7 @@ pub struct InterpretedWalRecord {
/// The interpreted part of the Postgres WAL record which requires metadata
/// writes to the underlying storage engine.
#[derive(Serialize, Deserialize)]
pub enum MetadataRecord {
Heapam(HeapamRecord),
Neonrmgr(NeonrmgrRecord),
@@ -77,10 +81,12 @@ pub enum MetadataRecord {
Replorigin(ReploriginRecord),
}
#[derive(Serialize, Deserialize)]
pub enum HeapamRecord {
ClearVmBits(ClearVmBits),
}
#[derive(Serialize, Deserialize)]
pub struct ClearVmBits {
pub new_heap_blkno: Option<u32>,
pub old_heap_blkno: Option<u32>,
@@ -88,24 +94,29 @@ pub struct ClearVmBits {
pub flags: u8,
}
#[derive(Serialize, Deserialize)]
pub enum NeonrmgrRecord {
ClearVmBits(ClearVmBits),
}
#[derive(Serialize, Deserialize)]
pub enum SmgrRecord {
Create(SmgrCreate),
Truncate(XlSmgrTruncate),
}
#[derive(Serialize, Deserialize)]
pub struct SmgrCreate {
pub rel: RelTag,
}
#[derive(Serialize, Deserialize)]
pub enum DbaseRecord {
Create(DbaseCreate),
Drop(DbaseDrop),
}
#[derive(Serialize, Deserialize)]
pub struct DbaseCreate {
pub db_id: Oid,
pub tablespace_id: Oid,
@@ -113,27 +124,32 @@ pub struct DbaseCreate {
pub src_tablespace_id: Oid,
}
#[derive(Serialize, Deserialize)]
pub struct DbaseDrop {
pub db_id: Oid,
pub tablespace_ids: Vec<Oid>,
}
#[derive(Serialize, Deserialize)]
pub enum ClogRecord {
ZeroPage(ClogZeroPage),
Truncate(ClogTruncate),
}
#[derive(Serialize, Deserialize)]
pub struct ClogZeroPage {
pub segno: u32,
pub rpageno: u32,
}
#[derive(Serialize, Deserialize)]
pub struct ClogTruncate {
pub pageno: u32,
pub oldest_xid: TransactionId,
pub oldest_xid_db: Oid,
}
#[derive(Serialize, Deserialize)]
pub enum XactRecord {
Commit(XactCommon),
Abort(XactCommon),
@@ -142,6 +158,7 @@ pub enum XactRecord {
Prepare(XactPrepare),
}
#[derive(Serialize, Deserialize)]
pub struct XactCommon {
pub parsed: XlXactParsedRecord,
pub origin_id: u16,
@@ -150,61 +167,73 @@ pub struct XactCommon {
pub lsn: Lsn,
}
#[derive(Serialize, Deserialize)]
pub struct XactPrepare {
pub xl_xid: TransactionId,
pub data: Bytes,
}
#[derive(Serialize, Deserialize)]
pub enum MultiXactRecord {
ZeroPage(MultiXactZeroPage),
Create(XlMultiXactCreate),
Truncate(XlMultiXactTruncate),
}
#[derive(Serialize, Deserialize)]
pub struct MultiXactZeroPage {
pub slru_kind: SlruKind,
pub segno: u32,
pub rpageno: u32,
}
#[derive(Serialize, Deserialize)]
pub enum RelmapRecord {
Update(RelmapUpdate),
}
#[derive(Serialize, Deserialize)]
pub struct RelmapUpdate {
pub update: XlRelmapUpdate,
pub buf: Bytes,
}
#[derive(Serialize, Deserialize)]
pub enum XlogRecord {
Raw(RawXlogRecord),
}
#[derive(Serialize, Deserialize)]
pub struct RawXlogRecord {
pub info: u8,
pub lsn: Lsn,
pub buf: Bytes,
}
#[derive(Serialize, Deserialize)]
pub enum LogicalMessageRecord {
Put(PutLogicalMessage),
#[cfg(feature = "testing")]
Failpoint,
}
#[derive(Serialize, Deserialize)]
pub struct PutLogicalMessage {
pub path: String,
pub buf: Bytes,
}
#[derive(Serialize, Deserialize)]
pub enum StandbyRecord {
RunningXacts(StandbyRunningXacts),
}
#[derive(Serialize, Deserialize)]
pub struct StandbyRunningXacts {
pub oldest_running_xid: TransactionId,
}
#[derive(Serialize, Deserialize)]
pub enum ReploriginRecord {
Set(XlReploriginSet),
Drop(XlReploriginDrop),

View File

@@ -16,6 +16,7 @@ use pageserver_api::shard::ShardIdentity;
use pageserver_api::{key::CompactKey, value::Value};
use postgres_ffi::walrecord::{DecodedBkpBlock, DecodedWALRecord};
use postgres_ffi::{page_is_new, page_set_lsn, pg_constants, BLCKSZ};
use serde::{Deserialize, Serialize};
use utils::bin_ser::BeSer;
use utils::lsn::Lsn;
@@ -29,6 +30,7 @@ static ZERO_PAGE: Bytes = Bytes::from_static(&[0u8; BLCKSZ as usize]);
/// relation sizes. In the case of "observed" values, we only need to know
/// the key and LSN, so two types of metadata are supported to save on network
/// bandwidth.
#[derive(Serialize, Deserialize, Debug)]
pub enum ValueMeta {
Serialized(SerializedValueMeta),
Observed(ObservedValueMeta),
@@ -75,6 +77,7 @@ impl PartialEq for OrderedValueMeta {
impl Eq for OrderedValueMeta {}
/// Metadata for a [`Value`] serialized into the batch.
#[derive(Serialize, Deserialize, Debug)]
pub struct SerializedValueMeta {
pub key: CompactKey,
pub lsn: Lsn,
@@ -86,12 +89,14 @@ pub struct SerializedValueMeta {
}
/// Metadata for a [`Value`] observed by the batch
#[derive(Serialize, Deserialize, Debug)]
pub struct ObservedValueMeta {
pub key: CompactKey,
pub lsn: Lsn,
}
/// Batch of serialized [`Value`]s.
#[derive(Serialize, Deserialize)]
pub struct SerializedValueBatch {
/// [`Value`]s serialized in EphemeralFile's native format,
/// ready for disk write by the pageserver

View File

@@ -154,17 +154,13 @@ fn main() -> anyhow::Result<()> {
},
};
if conf.no_sync {
info!("Skipping syncfs on startup");
} else {
let started = Instant::now();
syncfs(dirfd)?;
let elapsed = started.elapsed();
info!(
elapsed_ms = elapsed.as_millis(),
"made tenant directory contents durable"
);
}
let started = Instant::now();
syncfs(dirfd)?;
let elapsed = started.elapsed();
info!(
elapsed_ms = elapsed.as_millis(),
"made tenant directory contents durable"
);
}
// Initialize up failpoints support

View File

@@ -69,7 +69,6 @@ pub struct PageServerConf {
pub wal_redo_timeout: Duration,
pub superuser: String,
pub locale: String,
pub page_cache_size: usize,
pub max_file_descriptors: usize,
@@ -179,9 +178,6 @@ pub struct PageServerConf {
/// Direct IO settings
pub virtual_file_io_mode: virtual_file::IoMode,
/// Optionally disable disk syncs (unsafe!)
pub no_sync: bool,
}
/// Token for authentication to safekeepers
@@ -302,7 +298,6 @@ impl PageServerConf {
wait_lsn_timeout,
wal_redo_timeout,
superuser,
locale,
page_cache_size,
max_file_descriptors,
pg_distrib_dir,
@@ -337,7 +332,6 @@ impl PageServerConf {
concurrent_tenant_size_logical_size_queries,
virtual_file_io_engine,
tenant_config,
no_sync,
} = config_toml;
let mut conf = PageServerConf {
@@ -350,7 +344,6 @@ impl PageServerConf {
wait_lsn_timeout,
wal_redo_timeout,
superuser,
locale,
page_cache_size,
max_file_descriptors,
http_auth_type,
@@ -416,7 +409,6 @@ impl PageServerConf {
.map(crate::l0_flush::L0FlushConfig::from)
.unwrap_or_default(),
virtual_file_io_mode: virtual_file_io_mode.unwrap_or(virtual_file::IoMode::preferred()),
no_sync: no_sync.unwrap_or(false),
};
// ------------------------------------------------------------

View File

@@ -2002,9 +2002,9 @@ async fn timeline_offload_handler(
"timeline has attached children".into(),
));
}
if let (false, reason) = timeline.can_offload() {
if !timeline.can_offload() {
return Err(ApiError::PreconditionFailed(
format!("Timeline::can_offload() check failed: {}", reason) .into(),
"Timeline::can_offload() returned false".into(),
));
}
offload_timeline(&tenant, &timeline)
@@ -2169,21 +2169,6 @@ async fn timeline_detach_ancestor_handler(
let ctx = RequestContext::new(TaskKind::DetachAncestor, DownloadBehavior::Download);
let ctx = &ctx;
// Flush the upload queues of all timelines before detaching ancestor. We do the same thing again
// during shutdown. This early upload ensures the pageserver does not need to upload too many
// things and creates downtime during timeline reloads.
for timeline in tenant.list_timelines() {
timeline
.remote_client
.wait_completion()
.await
.map_err(|e| {
ApiError::PreconditionFailed(format!("cannot drain upload queue: {e}").into())
})?;
}
tracing::info!("all timeline upload queues are drained");
let timeline = tenant.get_timeline(timeline_id, true)?;
let progress = timeline

View File

@@ -1,11 +1,10 @@
//! The Page Service listens for client connections and serves their GetPage@LSN
//! requests.
use anyhow::{bail, Context};
use anyhow::Context;
use async_compression::tokio::write::GzipEncoder;
use bytes::Buf;
use futures::FutureExt;
use itertools::Itertools;
use once_cell::sync::OnceCell;
use pageserver_api::models::TenantState;
use pageserver_api::models::{
@@ -1222,222 +1221,6 @@ impl PageServerHandler {
}
}
/// `basebackup tenant timeline [lsn] [--gzip] [--replica]`
#[derive(Debug, Clone, Eq, PartialEq)]
struct BaseBackupCmd {
tenant_id: TenantId,
timeline_id: TimelineId,
lsn: Option<Lsn>,
gzip: bool,
replica: bool,
}
/// `fullbackup tenant timeline [lsn] [prev_lsn]`
#[derive(Debug, Clone, Eq, PartialEq)]
struct FullBackupCmd {
tenant_id: TenantId,
timeline_id: TimelineId,
lsn: Option<Lsn>,
prev_lsn: Option<Lsn>,
}
/// `pagestream_v2 tenant timeline`
#[derive(Debug, Clone, Eq, PartialEq)]
struct PageStreamCmd {
tenant_id: TenantId,
timeline_id: TimelineId,
}
/// `lease lsn tenant timeline lsn`
#[derive(Debug, Clone, Eq, PartialEq)]
struct LeaseLsnCmd {
tenant_shard_id: TenantShardId,
timeline_id: TimelineId,
lsn: Lsn,
}
#[derive(Debug, Clone, Eq, PartialEq)]
enum PageServiceCmd {
Set,
PageStream(PageStreamCmd),
BaseBackup(BaseBackupCmd),
FullBackup(FullBackupCmd),
LeaseLsn(LeaseLsnCmd),
}
impl PageStreamCmd {
fn parse(query: &str) -> anyhow::Result<Self> {
let parameters = query.split_whitespace().collect_vec();
if parameters.len() != 2 {
bail!(
"invalid number of parameters for pagestream command: {}",
query
);
}
let tenant_id = TenantId::from_str(parameters[0])
.with_context(|| format!("Failed to parse tenant id from {}", parameters[0]))?;
let timeline_id = TimelineId::from_str(parameters[1])
.with_context(|| format!("Failed to parse timeline id from {}", parameters[1]))?;
Ok(Self {
tenant_id,
timeline_id,
})
}
}
impl FullBackupCmd {
fn parse(query: &str) -> anyhow::Result<Self> {
let parameters = query.split_whitespace().collect_vec();
if parameters.len() < 2 || parameters.len() > 4 {
bail!(
"invalid number of parameters for basebackup command: {}",
query
);
}
let tenant_id = TenantId::from_str(parameters[0])
.with_context(|| format!("Failed to parse tenant id from {}", parameters[0]))?;
let timeline_id = TimelineId::from_str(parameters[1])
.with_context(|| format!("Failed to parse timeline id from {}", parameters[1]))?;
// The caller is responsible for providing correct lsn and prev_lsn.
let lsn = if let Some(lsn_str) = parameters.get(2) {
Some(
Lsn::from_str(lsn_str)
.with_context(|| format!("Failed to parse Lsn from {lsn_str}"))?,
)
} else {
None
};
let prev_lsn = if let Some(prev_lsn_str) = parameters.get(3) {
Some(
Lsn::from_str(prev_lsn_str)
.with_context(|| format!("Failed to parse Lsn from {prev_lsn_str}"))?,
)
} else {
None
};
Ok(Self {
tenant_id,
timeline_id,
lsn,
prev_lsn,
})
}
}
impl BaseBackupCmd {
fn parse(query: &str) -> anyhow::Result<Self> {
let parameters = query.split_whitespace().collect_vec();
if parameters.len() < 2 {
bail!(
"invalid number of parameters for basebackup command: {}",
query
);
}
let tenant_id = TenantId::from_str(parameters[0])
.with_context(|| format!("Failed to parse tenant id from {}", parameters[0]))?;
let timeline_id = TimelineId::from_str(parameters[1])
.with_context(|| format!("Failed to parse timeline id from {}", parameters[1]))?;
let lsn;
let flags_parse_from;
if let Some(maybe_lsn) = parameters.get(2) {
if *maybe_lsn == "latest" {
lsn = None;
flags_parse_from = 3;
} else if maybe_lsn.starts_with("--") {
lsn = None;
flags_parse_from = 2;
} else {
lsn = Some(
Lsn::from_str(maybe_lsn)
.with_context(|| format!("Failed to parse lsn from {maybe_lsn}"))?,
);
flags_parse_from = 3;
}
} else {
lsn = None;
flags_parse_from = 2;
}
let mut gzip = false;
let mut replica = false;
for &param in &parameters[flags_parse_from..] {
match param {
"--gzip" => {
if gzip {
bail!("duplicate parameter for basebackup command: {param}")
}
gzip = true
}
"--replica" => {
if replica {
bail!("duplicate parameter for basebackup command: {param}")
}
replica = true
}
_ => bail!("invalid parameter for basebackup command: {param}"),
}
}
Ok(Self {
tenant_id,
timeline_id,
lsn,
gzip,
replica,
})
}
}
impl LeaseLsnCmd {
fn parse(query: &str) -> anyhow::Result<Self> {
let parameters = query.split_whitespace().collect_vec();
if parameters.len() != 3 {
bail!(
"invalid number of parameters for lease lsn command: {}",
query
);
}
let tenant_shard_id = TenantShardId::from_str(parameters[0])
.with_context(|| format!("Failed to parse tenant id from {}", parameters[0]))?;
let timeline_id = TimelineId::from_str(parameters[1])
.with_context(|| format!("Failed to parse timeline id from {}", parameters[1]))?;
let lsn = Lsn::from_str(parameters[2])
.with_context(|| format!("Failed to parse lsn from {}", parameters[2]))?;
Ok(Self {
tenant_shard_id,
timeline_id,
lsn,
})
}
}
impl PageServiceCmd {
fn parse(query: &str) -> anyhow::Result<Self> {
let query = query.trim();
let Some((cmd, other)) = query.split_once(' ') else {
bail!("cannot parse query: {query}")
};
match cmd.to_ascii_lowercase().as_str() {
"pagestream_v2" => Ok(Self::PageStream(PageStreamCmd::parse(other)?)),
"basebackup" => Ok(Self::BaseBackup(BaseBackupCmd::parse(other)?)),
"fullbackup" => Ok(Self::FullBackup(FullBackupCmd::parse(other)?)),
"lease" => {
let Some((cmd2, other)) = other.split_once(' ') else {
bail!("invalid lease command: {cmd}");
};
let cmd2 = cmd2.to_ascii_lowercase();
if cmd2 == "lsn" {
Ok(Self::LeaseLsn(LeaseLsnCmd::parse(other)?))
} else {
bail!("invalid lease command: {cmd}");
}
}
"set" => Ok(Self::Set),
_ => Err(anyhow::anyhow!("unsupported command {cmd} in {query}")),
}
}
}
impl<IO> postgres_backend::Handler<IO> for PageServerHandler
where
IO: AsyncRead + AsyncWrite + Send + Sync + Unpin,
@@ -1494,137 +1277,206 @@ where
fail::fail_point!("ps::connection-start::process-query");
let ctx = self.connection_ctx.attached_child();
debug!("process query {query_string}");
let query = PageServiceCmd::parse(query_string)?;
match query {
PageServiceCmd::PageStream(PageStreamCmd {
tenant_id,
timeline_id,
}) => {
tracing::Span::current()
.record("tenant_id", field::display(tenant_id))
.record("timeline_id", field::display(timeline_id));
self.check_permission(Some(tenant_id))?;
COMPUTE_COMMANDS_COUNTERS
.for_command(ComputeCommandKind::PageStreamV2)
.inc();
self.handle_pagerequests(
pgb,
tenant_id,
timeline_id,
PagestreamProtocolVersion::V2,
ctx,
)
.await?;
debug!("process query {query_string:?}");
let parts = query_string.split_whitespace().collect::<Vec<_>>();
if let Some(params) = parts.strip_prefix(&["pagestream_v2"]) {
if params.len() != 2 {
return Err(QueryError::Other(anyhow::anyhow!(
"invalid param number for pagestream command"
)));
}
PageServiceCmd::BaseBackup(BaseBackupCmd {
let tenant_id = TenantId::from_str(params[0])
.with_context(|| format!("Failed to parse tenant id from {}", params[0]))?;
let timeline_id = TimelineId::from_str(params[1])
.with_context(|| format!("Failed to parse timeline id from {}", params[1]))?;
tracing::Span::current()
.record("tenant_id", field::display(tenant_id))
.record("timeline_id", field::display(timeline_id));
self.check_permission(Some(tenant_id))?;
COMPUTE_COMMANDS_COUNTERS
.for_command(ComputeCommandKind::PageStreamV2)
.inc();
self.handle_pagerequests(
pgb,
tenant_id,
timeline_id,
lsn,
gzip,
replica,
}) => {
tracing::Span::current()
.record("tenant_id", field::display(tenant_id))
.record("timeline_id", field::display(timeline_id));
PagestreamProtocolVersion::V2,
ctx,
)
.await?;
} else if let Some(params) = parts.strip_prefix(&["basebackup"]) {
if params.len() < 2 {
return Err(QueryError::Other(anyhow::anyhow!(
"invalid param number for basebackup command"
)));
}
self.check_permission(Some(tenant_id))?;
let tenant_id = TenantId::from_str(params[0])
.with_context(|| format!("Failed to parse tenant id from {}", params[0]))?;
let timeline_id = TimelineId::from_str(params[1])
.with_context(|| format!("Failed to parse timeline id from {}", params[1]))?;
COMPUTE_COMMANDS_COUNTERS
.for_command(ComputeCommandKind::Basebackup)
.inc();
let metric_recording = metrics::BASEBACKUP_QUERY_TIME.start_recording(&ctx);
let res = async {
self.handle_basebackup_request(
pgb,
tenant_id,
timeline_id,
lsn,
None,
false,
gzip,
replica,
&ctx,
)
.await?;
pgb.write_message_noflush(&BeMessage::CommandComplete(b"SELECT 1"))?;
Result::<(), QueryError>::Ok(())
tracing::Span::current()
.record("tenant_id", field::display(tenant_id))
.record("timeline_id", field::display(timeline_id));
self.check_permission(Some(tenant_id))?;
COMPUTE_COMMANDS_COUNTERS
.for_command(ComputeCommandKind::Basebackup)
.inc();
let mut lsn = None;
let mut replica = false;
let mut gzip = false;
for param in &params[2..] {
if param.starts_with("--") {
match *param {
"--gzip" => gzip = true,
"--replica" => replica = true,
_ => {
return Err(QueryError::Other(anyhow::anyhow!(
"Unknown parameter {param}",
)))
}
}
} else {
lsn = Some(
Lsn::from_str(param)
.with_context(|| format!("Failed to parse Lsn from {param}"))?,
);
}
.await;
metric_recording.observe(&res);
res?;
}
// same as basebackup, but result includes relational data as well
PageServiceCmd::FullBackup(FullBackupCmd {
tenant_id,
timeline_id,
lsn,
prev_lsn,
}) => {
tracing::Span::current()
.record("tenant_id", field::display(tenant_id))
.record("timeline_id", field::display(timeline_id));
self.check_permission(Some(tenant_id))?;
COMPUTE_COMMANDS_COUNTERS
.for_command(ComputeCommandKind::Fullbackup)
.inc();
// Check that the timeline exists
let metric_recording = metrics::BASEBACKUP_QUERY_TIME.start_recording(&ctx);
let res = async {
self.handle_basebackup_request(
pgb,
tenant_id,
timeline_id,
lsn,
prev_lsn,
true,
false,
None,
false,
gzip,
replica,
&ctx,
)
.await?;
pgb.write_message_noflush(&BeMessage::CommandComplete(b"SELECT 1"))?;
Result::<(), QueryError>::Ok(())
}
PageServiceCmd::Set => {
// important because psycopg2 executes "SET datestyle TO 'ISO'"
// on connect
pgb.write_message_noflush(&BeMessage::CommandComplete(b"SELECT 1"))?;
.await;
metric_recording.observe(&res);
res?;
}
// same as basebackup, but result includes relational data as well
else if let Some(params) = parts.strip_prefix(&["fullbackup"]) {
if params.len() < 2 {
return Err(QueryError::Other(anyhow::anyhow!(
"invalid param number for fullbackup command"
)));
}
PageServiceCmd::LeaseLsn(LeaseLsnCmd {
tenant_shard_id,
let tenant_id = TenantId::from_str(params[0])
.with_context(|| format!("Failed to parse tenant id from {}", params[0]))?;
let timeline_id = TimelineId::from_str(params[1])
.with_context(|| format!("Failed to parse timeline id from {}", params[1]))?;
tracing::Span::current()
.record("tenant_id", field::display(tenant_id))
.record("timeline_id", field::display(timeline_id));
// The caller is responsible for providing correct lsn and prev_lsn.
let lsn = if let Some(lsn_str) = params.get(2) {
Some(
Lsn::from_str(lsn_str)
.with_context(|| format!("Failed to parse Lsn from {lsn_str}"))?,
)
} else {
None
};
let prev_lsn = if let Some(prev_lsn_str) = params.get(3) {
Some(
Lsn::from_str(prev_lsn_str)
.with_context(|| format!("Failed to parse Lsn from {prev_lsn_str}"))?,
)
} else {
None
};
self.check_permission(Some(tenant_id))?;
COMPUTE_COMMANDS_COUNTERS
.for_command(ComputeCommandKind::Fullbackup)
.inc();
// Check that the timeline exists
self.handle_basebackup_request(
pgb,
tenant_id,
timeline_id,
lsn,
}) => {
tracing::Span::current()
.record("tenant_id", field::display(tenant_shard_id))
.record("timeline_id", field::display(timeline_id));
self.check_permission(Some(tenant_shard_id.tenant_id))?;
COMPUTE_COMMANDS_COUNTERS
.for_command(ComputeCommandKind::LeaseLsn)
.inc();
match self
.handle_make_lsn_lease(pgb, tenant_shard_id, timeline_id, lsn, &ctx)
.await
{
Ok(()) => {
pgb.write_message_noflush(&BeMessage::CommandComplete(b"SELECT 1"))?
}
Err(e) => {
error!("error obtaining lsn lease for {lsn}: {e:?}");
pgb.write_message_noflush(&BeMessage::ErrorResponse(
&e.to_string(),
Some(e.pg_error_code()),
))?
}
};
prev_lsn,
true,
false,
false,
&ctx,
)
.await?;
pgb.write_message_noflush(&BeMessage::CommandComplete(b"SELECT 1"))?;
} else if query_string.to_ascii_lowercase().starts_with("set ") {
// important because psycopg2 executes "SET datestyle TO 'ISO'"
// on connect
pgb.write_message_noflush(&BeMessage::CommandComplete(b"SELECT 1"))?;
} else if query_string.starts_with("lease lsn ") {
let params = &parts[2..];
if params.len() != 3 {
return Err(QueryError::Other(anyhow::anyhow!(
"invalid param number {} for lease lsn command",
params.len()
)));
}
let tenant_shard_id = TenantShardId::from_str(params[0])
.with_context(|| format!("Failed to parse tenant id from {}", params[0]))?;
let timeline_id = TimelineId::from_str(params[1])
.with_context(|| format!("Failed to parse timeline id from {}", params[1]))?;
tracing::Span::current()
.record("tenant_id", field::display(tenant_shard_id))
.record("timeline_id", field::display(timeline_id));
self.check_permission(Some(tenant_shard_id.tenant_id))?;
COMPUTE_COMMANDS_COUNTERS
.for_command(ComputeCommandKind::LeaseLsn)
.inc();
// The caller is responsible for providing correct lsn.
let lsn = Lsn::from_str(params[2])
.with_context(|| format!("Failed to parse Lsn from {}", params[2]))?;
match self
.handle_make_lsn_lease(pgb, tenant_shard_id, timeline_id, lsn, &ctx)
.await
{
Ok(()) => pgb.write_message_noflush(&BeMessage::CommandComplete(b"SELECT 1"))?,
Err(e) => {
error!("error obtaining lsn lease for {lsn}: {e:?}");
pgb.write_message_noflush(&BeMessage::ErrorResponse(
&e.to_string(),
Some(e.pg_error_code()),
))?
}
};
} else {
return Err(QueryError::Other(anyhow::anyhow!(
"unknown command {query_string}"
)));
}
Ok(())
@@ -1673,181 +1525,3 @@ fn set_tracing_field_shard_id(timeline: &Timeline) {
);
debug_assert_current_span_has_tenant_and_timeline_id();
}
#[cfg(test)]
mod tests {
use utils::shard::ShardCount;
use super::*;
#[test]
fn pageservice_cmd_parse() {
let tenant_id = TenantId::generate();
let timeline_id = TimelineId::generate();
let cmd =
PageServiceCmd::parse(&format!("pagestream_v2 {tenant_id} {timeline_id}")).unwrap();
assert_eq!(
cmd,
PageServiceCmd::PageStream(PageStreamCmd {
tenant_id,
timeline_id
})
);
let cmd = PageServiceCmd::parse(&format!("basebackup {tenant_id} {timeline_id}")).unwrap();
assert_eq!(
cmd,
PageServiceCmd::BaseBackup(BaseBackupCmd {
tenant_id,
timeline_id,
lsn: None,
gzip: false,
replica: false
})
);
let cmd =
PageServiceCmd::parse(&format!("basebackup {tenant_id} {timeline_id} --gzip")).unwrap();
assert_eq!(
cmd,
PageServiceCmd::BaseBackup(BaseBackupCmd {
tenant_id,
timeline_id,
lsn: None,
gzip: true,
replica: false
})
);
let cmd =
PageServiceCmd::parse(&format!("basebackup {tenant_id} {timeline_id} latest")).unwrap();
assert_eq!(
cmd,
PageServiceCmd::BaseBackup(BaseBackupCmd {
tenant_id,
timeline_id,
lsn: None,
gzip: false,
replica: false
})
);
let cmd = PageServiceCmd::parse(&format!("basebackup {tenant_id} {timeline_id} 0/16ABCDE"))
.unwrap();
assert_eq!(
cmd,
PageServiceCmd::BaseBackup(BaseBackupCmd {
tenant_id,
timeline_id,
lsn: Some(Lsn::from_str("0/16ABCDE").unwrap()),
gzip: false,
replica: false
})
);
let cmd = PageServiceCmd::parse(&format!(
"basebackup {tenant_id} {timeline_id} --replica --gzip"
))
.unwrap();
assert_eq!(
cmd,
PageServiceCmd::BaseBackup(BaseBackupCmd {
tenant_id,
timeline_id,
lsn: None,
gzip: true,
replica: true
})
);
let cmd = PageServiceCmd::parse(&format!(
"basebackup {tenant_id} {timeline_id} 0/16ABCDE --replica --gzip"
))
.unwrap();
assert_eq!(
cmd,
PageServiceCmd::BaseBackup(BaseBackupCmd {
tenant_id,
timeline_id,
lsn: Some(Lsn::from_str("0/16ABCDE").unwrap()),
gzip: true,
replica: true
})
);
let cmd = PageServiceCmd::parse(&format!("fullbackup {tenant_id} {timeline_id}")).unwrap();
assert_eq!(
cmd,
PageServiceCmd::FullBackup(FullBackupCmd {
tenant_id,
timeline_id,
lsn: None,
prev_lsn: None
})
);
let cmd = PageServiceCmd::parse(&format!(
"fullbackup {tenant_id} {timeline_id} 0/16ABCDE 0/16ABCDF"
))
.unwrap();
assert_eq!(
cmd,
PageServiceCmd::FullBackup(FullBackupCmd {
tenant_id,
timeline_id,
lsn: Some(Lsn::from_str("0/16ABCDE").unwrap()),
prev_lsn: Some(Lsn::from_str("0/16ABCDF").unwrap()),
})
);
let tenant_shard_id = TenantShardId::unsharded(tenant_id);
let cmd = PageServiceCmd::parse(&format!(
"lease lsn {tenant_shard_id} {timeline_id} 0/16ABCDE"
))
.unwrap();
assert_eq!(
cmd,
PageServiceCmd::LeaseLsn(LeaseLsnCmd {
tenant_shard_id,
timeline_id,
lsn: Lsn::from_str("0/16ABCDE").unwrap(),
})
);
let tenant_shard_id = TenantShardId::split(&tenant_shard_id, ShardCount(8))[1];
let cmd = PageServiceCmd::parse(&format!(
"lease lsn {tenant_shard_id} {timeline_id} 0/16ABCDE"
))
.unwrap();
assert_eq!(
cmd,
PageServiceCmd::LeaseLsn(LeaseLsnCmd {
tenant_shard_id,
timeline_id,
lsn: Lsn::from_str("0/16ABCDE").unwrap(),
})
);
let cmd = PageServiceCmd::parse("set a = b").unwrap();
assert_eq!(cmd, PageServiceCmd::Set);
let cmd = PageServiceCmd::parse("SET foo").unwrap();
assert_eq!(cmd, PageServiceCmd::Set);
}
#[test]
fn pageservice_cmd_err_handling() {
let tenant_id = TenantId::generate();
let timeline_id = TimelineId::generate();
let cmd = PageServiceCmd::parse("unknown_command");
assert!(cmd.is_err());
let cmd = PageServiceCmd::parse("pagestream_v2");
assert!(cmd.is_err());
let cmd = PageServiceCmd::parse(&format!("pagestream_v2 {tenant_id}xxx"));
assert!(cmd.is_err());
let cmd = PageServiceCmd::parse(&format!("pagestream_v2 {tenant_id}xxx {timeline_id}xxx"));
assert!(cmd.is_err());
let cmd = PageServiceCmd::parse(&format!(
"basebackup {tenant_id} {timeline_id} --gzip --gzip"
));
assert!(cmd.is_err());
let cmd = PageServiceCmd::parse(&format!(
"basebackup {tenant_id} {timeline_id} --gzip --unknown"
));
assert!(cmd.is_err());
let cmd = PageServiceCmd::parse(&format!(
"basebackup {tenant_id} {timeline_id} --gzip 0/16ABCDE"
));
assert!(cmd.is_err());
let cmd = PageServiceCmd::parse(&format!("lease {tenant_id} {timeline_id} gzip 0/16ABCDE"));
assert!(cmd.is_err());
}
}

View File

@@ -45,7 +45,7 @@ use wal_decoder::serialized_batch::SerializedValueBatch;
pub const MAX_AUX_FILE_DELTAS: usize = 1024;
/// Max number of aux-file-related delta layers. The compaction will create a new image layer once this threshold is reached.
pub const MAX_AUX_FILE_V2_DELTAS: usize = 16;
pub const MAX_AUX_FILE_V2_DELTAS: usize = 64;
#[derive(Debug)]
pub enum LsnForTimestamp {
@@ -1164,12 +1164,19 @@ impl<'a> DatadirModification<'a> {
.get_rel_exists(rel, Version::Modified(self), ctx)
.await?
{
tracing::debug!("Creating relation {rel:?} at lsn {}", self.get_lsn());
// create it with 0 size initially, the logic below will extend it
self.put_rel_creation(rel, 0, ctx)
.await
.context("Relation Error")?;
Ok(0)
} else {
tracing::debug!(
"Skipping relation {rel:?} creation at lsn {}",
self.get_lsn()
);
self.tline
.get_rel_size(rel, Version::Modified(self), ctx)
.await
@@ -1210,6 +1217,8 @@ impl<'a> DatadirModification<'a> {
shard: &ShardIdentity,
ctx: &RequestContext,
) -> anyhow::Result<()> {
tracing::debug!("Ingesting batch with metadata: {:?}", batch.metadata);
let mut gaps_at_lsns = Vec::default();
for meta in batch.metadata.iter() {

View File

@@ -2493,8 +2493,7 @@ impl Tenant {
timelines_to_compact_or_offload = timelines
.iter()
.filter_map(|(timeline_id, timeline)| {
let (is_active, (can_offload, _)) =
(timeline.is_active(), timeline.can_offload());
let (is_active, can_offload) = (timeline.is_active(), timeline.can_offload());
let has_no_unoffloaded_children = {
!timelines
.iter()
@@ -4780,18 +4779,10 @@ async fn run_initdb(
let _permit = INIT_DB_SEMAPHORE.acquire().await;
let mut initdb_command = tokio::process::Command::new(&initdb_bin_path);
initdb_command
let initdb_command = tokio::process::Command::new(&initdb_bin_path)
.args(["--pgdata", initdb_target_dir.as_ref()])
.args(["--username", &conf.superuser])
.args(["--encoding", "utf8"])
.args(["--locale", &conf.locale])
.args(["--lc-collate", &conf.locale])
.args(["--lc-ctype", &conf.locale])
.args(["--lc-messages", &conf.locale])
.args(["--lc-monetary", &conf.locale])
.args(["--lc-numeric", &conf.locale])
.args(["--lc-time", &conf.locale])
.arg("--no-instructions")
.arg("--no-sync")
.env_clear()
@@ -4801,27 +4792,15 @@ async fn run_initdb(
// stdout invocation produces the same output every time, we don't need it
.stdout(std::process::Stdio::null())
// we would be interested in the stderr output, if there was any
.stderr(std::process::Stdio::piped());
// Before version 14, only the libc provide was available.
if pg_version > 14 {
// Version 17 brought with it a builtin locale provider which only provides
// C and C.UTF-8. While being safer for collation purposes since it is
// guaranteed to be consistent throughout a major release, it is also more
// performant.
let locale_provider = if pg_version >= 17 { "builtin" } else { "libc" };
initdb_command.args(["--locale-provider", locale_provider]);
}
let initdb_proc = initdb_command.spawn()?;
.stderr(std::process::Stdio::piped())
.spawn()?;
// Ideally we'd select here with the cancellation token, but the problem is that
// we can't safely terminate initdb: it launches processes of its own, and killing
// initdb doesn't kill them. After we return from this function, we want the target
// directory to be able to be cleaned up.
// See https://github.com/neondatabase/neon/issues/6385
let initdb_output = initdb_proc.wait_with_output().await?;
let initdb_output = initdb_command.wait_with_output().await?;
if !initdb_output.status.success() {
return Err(InitdbError::Failed(
initdb_output.status,

View File

@@ -1959,7 +1959,7 @@ impl TenantManager {
attempt.before_reset_tenant();
let (_guard, progress) = utils::completion::channel();
match tenant.shutdown(progress, ShutdownMode::Flush).await {
match tenant.shutdown(progress, ShutdownMode::Hard).await {
Ok(()) => {
slot_guard.drop_old_value().expect("it was just shutdown");
}

View File

@@ -1445,7 +1445,7 @@ impl RemoteTimelineClient {
let remote_path = remote_layer_path(
&self.tenant_shard_id.tenant_id,
&self.timeline_id,
uploaded.metadata().shard,
self.tenant_shard_id.to_index(),
&uploaded.layer_desc().layer_name(),
uploaded.metadata().generation,
);
@@ -1486,7 +1486,7 @@ impl RemoteTimelineClient {
&adopted
.get_timeline_id()
.expect("Source timeline should be alive"),
adopted.metadata().shard,
self.tenant_shard_id.to_index(),
&adopted.layer_desc().layer_name(),
adopted.metadata().generation,
);
@@ -1494,7 +1494,7 @@ impl RemoteTimelineClient {
let target_remote_path = remote_layer_path(
&self.tenant_shard_id.tenant_id,
&self.timeline_id,
adopted_as.metadata().shard,
self.tenant_shard_id.to_index(),
&adopted_as.layer_desc().layer_name(),
adopted_as.metadata().generation,
);
@@ -2201,18 +2201,6 @@ impl RemoteTimelineClient {
inner.initialized_mut()?;
Ok(UploadQueueAccessor { inner })
}
pub(crate) fn no_pending_work(&self) -> bool {
let inner = self.upload_queue.lock().unwrap();
match &*inner {
UploadQueue::Uninitialized
| UploadQueue::Stopped(UploadQueueStopped::Uninitialized) => true,
UploadQueue::Stopped(UploadQueueStopped::Deletable(x)) => {
x.upload_queue_for_deletion.no_pending_work()
}
UploadQueue::Initialized(x) => x.no_pending_work(),
}
}
}
pub(crate) struct UploadQueueAccessor<'a> {

View File

@@ -12,7 +12,7 @@ pub mod merge_iterator;
use crate::context::{AccessStatsBehavior, RequestContext};
use bytes::Bytes;
use pageserver_api::key::{Key, NON_INHERITED_SPARSE_RANGE};
use pageserver_api::key::Key;
use pageserver_api::keyspace::{KeySpace, KeySpaceRandomAccum};
use pageserver_api::record::NeonWalRecord;
use pageserver_api::value::Value;
@@ -196,9 +196,6 @@ impl ValuesReconstructState {
/// Returns true if this was the last value needed for the key and false otherwise.
///
/// If the key is done after the update, mark it as such.
///
/// If the key is in the sparse keyspace (i.e., aux files), we do not track them in
/// `key_done`.
pub(crate) fn update_key(
&mut self,
key: &Key,
@@ -209,18 +206,10 @@ impl ValuesReconstructState {
.keys
.entry(*key)
.or_insert(Ok(VectoredValueReconstructState::default()));
let is_sparse_key = NON_INHERITED_SPARSE_RANGE.contains(key);
if let Ok(state) = state {
let key_done = match state.situation {
ValueReconstructSituation::Complete => {
if is_sparse_key {
// Sparse keyspace might be visited multiple times because
// we don't track unmapped keyspaces.
return ValueReconstructSituation::Complete;
} else {
unreachable!()
}
}
ValueReconstructSituation::Complete => unreachable!(),
ValueReconstructSituation::Continue => match value {
Value::Image(img) => {
state.img = Some((lsn, img));
@@ -245,9 +234,7 @@ impl ValuesReconstructState {
if key_done && state.situation == ValueReconstructSituation::Continue {
state.situation = ValueReconstructSituation::Complete;
if !is_sparse_key {
self.keys_done.add_key(*key);
}
self.keys_done.add_key(*key);
}
state.situation

View File

@@ -67,8 +67,6 @@ pub struct InMemoryLayer {
/// The above fields never change, except for `end_lsn`, which is only set once.
/// All other changing parts are in `inner`, and protected by a mutex.
inner: RwLock<InMemoryLayerInner>,
estimated_in_mem_size: AtomicU64,
}
impl std::fmt::Debug for InMemoryLayer {
@@ -545,10 +543,6 @@ impl InMemoryLayer {
Ok(inner.file.len())
}
pub fn estimated_in_mem_size(&self) -> u64 {
self.estimated_in_mem_size.load(AtomicOrdering::Relaxed)
}
/// Create a new, empty, in-memory layer
pub async fn create(
conf: &'static PageServerConf,
@@ -578,7 +572,6 @@ impl InMemoryLayer {
file,
resource_units: GlobalResourceUnits::new(),
}),
estimated_in_mem_size: AtomicU64::new(0),
})
}
@@ -649,12 +642,6 @@ impl InMemoryLayer {
// because this case is unexpected, and we would like tests to fail if this happens.
warn!("Key {} at {} written twice at same LSN", key, lsn);
}
self.estimated_in_mem_size.fetch_add(
(std::mem::size_of::<CompactKey>()
+ std::mem::size_of::<Lsn>()
+ std::mem::size_of::<IndexEntry>()) as u64,
AtomicOrdering::Relaxed,
);
}
inner.resource_units.maybe_publish_size(new_size);

View File

@@ -23,7 +23,6 @@ use handle::ShardTimelineId;
use offload::OffloadError;
use once_cell::sync::Lazy;
use pageserver_api::{
config::tenant_conf_defaults::DEFAULT_COMPACTION_THRESHOLD,
key::{
KEY_SIZE, METADATA_KEY_BEGIN_PREFIX, METADATA_KEY_END_PREFIX, NON_INHERITED_RANGE,
NON_INHERITED_SPARSE_RANGE,
@@ -853,10 +852,6 @@ pub(crate) enum ShutdownMode {
/// While we are flushing, we continue to accept read I/O for LSNs ingested before
/// the call to [`Timeline::shutdown`].
FreezeAndFlush,
/// Only flush the layers to the remote storage without freezing any open layers. This is the
/// mode used by ancestor detach and any other operations that reloads a tenant but not increasing
/// the generation number.
Flush,
/// Shut down immediately, without waiting for any open layers to flush.
Hard,
}
@@ -1570,16 +1565,12 @@ impl Timeline {
///
/// This is neccessary but not sufficient for offloading of the timeline as it might have
/// child timelines that are not offloaded yet.
pub(crate) fn can_offload(&self) -> (bool, &'static str) {
pub(crate) fn can_offload(&self) -> bool {
if self.remote_client.is_archived() != Some(true) {
return (false, "the timeline is not archived");
}
if !self.remote_client.no_pending_work() {
// if the remote client is still processing some work, we can't offload
return (false, "the upload queue is not drained yet");
return false;
}
(true, "ok")
true
}
/// Outermost timeline compaction operation; downloads needed layers. Returns whether we have pending
@@ -1687,6 +1678,11 @@ impl Timeline {
pub(crate) async fn shutdown(&self, mode: ShutdownMode) {
debug_assert_current_span_has_tenant_and_timeline_id();
let try_freeze_and_flush = match mode {
ShutdownMode::FreezeAndFlush => true,
ShutdownMode::Hard => false,
};
// Regardless of whether we're going to try_freeze_and_flush
// or not, stop ingesting any more data. Walreceiver only provides
// cancellation but no "wait until gone", because it uses the Timeline::gate.
@@ -1708,7 +1704,7 @@ impl Timeline {
// ... and inform any waiters for newer LSNs that there won't be any.
self.last_record_lsn.shutdown();
if let ShutdownMode::FreezeAndFlush = mode {
if try_freeze_and_flush {
if let Some((open, frozen)) = self
.layers
.read()
@@ -1750,20 +1746,6 @@ impl Timeline {
warn!("failed to freeze and flush: {e:#}");
}
}
// `self.remote_client.shutdown().await` above should have already flushed everything from the queue, but
// we also do a final check here to ensure that the queue is empty.
if !self.remote_client.no_pending_work() {
warn!("still have pending work in remote upload queue, but continuing shutting down anyways");
}
}
if let ShutdownMode::Flush = mode {
// drain the upload queue
self.remote_client.shutdown().await;
if !self.remote_client.no_pending_work() {
warn!("still have pending work in remote upload queue, but continuing shutting down anyways");
}
}
// Signal any subscribers to our cancellation token to drop out
@@ -3506,37 +3488,18 @@ impl Timeline {
let timer = self.metrics.flush_time_histo.start_timer();
let num_frozen_layers;
let frozen_layer_total_size;
let layer_to_flush = {
let guard = self.layers.read().await;
let Ok(lm) = guard.layer_map() else {
info!("dropping out of flush loop for timeline shutdown");
return;
};
num_frozen_layers = lm.frozen_layers.len();
frozen_layer_total_size = lm
.frozen_layers
.iter()
.map(|l| l.estimated_in_mem_size())
.sum::<u64>();
lm.frozen_layers.front().cloned()
// drop 'layers' lock to allow concurrent reads and writes
};
let Some(layer_to_flush) = layer_to_flush else {
break Ok(());
};
if num_frozen_layers
> std::cmp::max(
self.get_compaction_threshold(),
DEFAULT_COMPACTION_THRESHOLD,
)
&& frozen_layer_total_size >= /* 64 MB */ 64000000
{
tracing::warn!(
"too many frozen layers: {num_frozen_layers} layers with estimated in-mem size of {frozen_layer_total_size} bytes",
);
}
match self.flush_frozen_layer(layer_to_flush, ctx).await {
Ok(this_layer_to_lsn) => {
flushed_to_lsn = std::cmp::max(flushed_to_lsn, this_layer_to_lsn);
@@ -4127,7 +4090,6 @@ impl Timeline {
) -> Result<ImageLayerCreationOutcome, CreateImageLayersError> {
// Metadata keys image layer creation.
let mut reconstruct_state = ValuesReconstructState::default();
let begin = Instant::now();
let data = self
.get_vectored_impl(partition.clone(), lsn, &mut reconstruct_state, ctx)
.await?;
@@ -4144,11 +4106,14 @@ impl Timeline {
(new_data, total_kb_retrieved / 1024, total_keys_retrieved)
};
let delta_files_accessed = reconstruct_state.get_delta_layers_visited();
let elapsed = begin.elapsed();
let trigger_generation = delta_files_accessed as usize >= MAX_AUX_FILE_V2_DELTAS;
info!(
"metadata key compaction: trigger_generation={trigger_generation}, delta_files_accessed={delta_files_accessed}, total_kb_retrieved={total_kb_retrieved}, total_keys_retrieved={total_keys_retrieved}, read_time={}s", elapsed.as_secs_f64()
debug!(
trigger_generation,
delta_files_accessed,
total_kb_retrieved,
total_keys_retrieved,
"generate metadata images"
);
if !trigger_generation && mode == ImageLayerCreationMode::Try {

View File

@@ -12,7 +12,7 @@ use crate::{
virtual_file::{MaybeFatalIo, VirtualFile},
};
use anyhow::Context;
use pageserver_api::{models::detach_ancestor::AncestorDetached, shard::ShardIdentity};
use pageserver_api::models::detach_ancestor::AncestorDetached;
use tokio::sync::Semaphore;
use tokio_util::sync::CancellationToken;
use tracing::Instrument;
@@ -376,14 +376,8 @@ pub(super) async fn prepare(
tasks.spawn(
async move {
let _permit = limiter.acquire().await;
let owned = remote_copy(
&adopted,
&timeline,
timeline.generation,
timeline.shard_identity,
&timeline.cancel,
)
.await?;
let owned =
remote_copy(&adopted, &timeline, timeline.generation, &timeline.cancel).await?;
tracing::info!(layer=%owned, "remote copied");
Ok(owned)
}
@@ -635,7 +629,6 @@ async fn remote_copy(
adopted: &Layer,
adoptee: &Arc<Timeline>,
generation: Generation,
shard_identity: ShardIdentity,
cancel: &CancellationToken,
) -> Result<Layer, Error> {
// depending if Layer::keep_resident we could hardlink
@@ -643,7 +636,6 @@ async fn remote_copy(
let mut metadata = adopted.metadata();
debug_assert!(metadata.generation <= generation);
metadata.generation = generation;
metadata.shard = shard_identity.shard_index();
let owned = crate::tenant::storage_layer::Layer::for_evicted(
adoptee.conf,

View File

@@ -47,18 +47,21 @@ pub(crate) async fn offload_timeline(
match is_archived {
Some(true) => (),
Some(false) => {
tracing::warn!("tried offloading a non-archived timeline");
tracing::warn!(?is_archived, "tried offloading a non-archived timeline");
return Err(OffloadError::NotArchived);
}
None => {
// This is legal: calls to this function can race with the timeline shutting down
tracing::info!("tried offloading a timeline whose remote storage is not initialized");
tracing::info!(
?is_archived,
"tried offloading a timeline whose remote storage is not initialized"
);
return Err(OffloadError::Cancelled);
}
}
// Now that the Timeline is in Stopping state, request all the related tasks to shut down.
timeline.shutdown(super::ShutdownMode::Flush).await;
timeline.shutdown(super::ShutdownMode::Hard).await;
// TODO extend guard mechanism above with method
// to make deletions possible while offloading is in progress

View File

@@ -36,7 +36,9 @@ use postgres_connection::PgConnectionConfig;
use utils::backoff::{
exponential_backoff, DEFAULT_BASE_BACKOFF_SECONDS, DEFAULT_MAX_BACKOFF_SECONDS,
};
use utils::postgres_client::wal_stream_connection_config;
use utils::postgres_client::{
wal_stream_connection_config, ConnectionConfigArgs, PAGESERVER_SAFEKEEPER_PROTO_VERSION, POSTGRES_PROTO_VERSION,
};
use utils::{
id::{NodeId, TenantTimelineId},
lsn::Lsn,
@@ -984,15 +986,29 @@ impl ConnectionManagerState {
if info.safekeeper_connstr.is_empty() {
return None; // no connection string, ignore sk
}
match wal_stream_connection_config(
self.id,
info.safekeeper_connstr.as_ref(),
match &self.conf.auth_token {
None => None,
Some(x) => Some(x),
},
self.conf.availability_zone.as_deref(),
) {
let shard_identity = self.timeline.get_shard_identity();
let connection_conf_args = ConnectionConfigArgs {
protocol_version: PAGESERVER_SAFEKEEPER_PROTO_VERSION,
ttid: self.id,
shard_number: Some(shard_identity.number.0),
shard_count: Some(shard_identity.count.0),
shard_stripe_size: Some(shard_identity.stripe_size.0),
listen_pg_addr_str: info.safekeeper_connstr.as_ref(),
auth_token: self.conf.auth_token.as_ref().map(|t| t.as_str()),
availability_zone: self.conf.availability_zone.as_deref()
};
// let connection_conf_args = ConnectionConfigArgs {
// protocol_version: POSTGRES_PROTO_VERSION,
// ttid: self.id,
// shard_number: None,
// shard_count: None,
// shard_stripe_size: None,
// listen_pg_addr_str: info.safekeeper_connstr.as_ref(),
// auth_token: self.conf.auth_token.as_ref().map(|t| t.as_str()),
// availability_zone: self.conf.availability_zone.as_deref()
// };
match wal_stream_connection_config(connection_conf_args) {
Ok(connstr) => Some((*sk_id, info, connstr)),
Err(e) => {
error!("Failed to create wal receiver connection string from broker data of safekeeper node {}: {e:#}", sk_id);

View File

@@ -36,7 +36,7 @@ use crate::{
use postgres_backend::is_expected_io_error;
use postgres_connection::PgConnectionConfig;
use postgres_ffi::waldecoder::WalStreamDecoder;
use utils::{id::NodeId, lsn::Lsn};
use utils::{bin_ser::BeSer, id::NodeId, lsn::Lsn};
use utils::{pageserver_feedback::PageserverFeedback, sync::gate::GateError};
/// Status of the connection.
@@ -278,6 +278,7 @@ pub(super) async fn handle_walreceiver_connection(
// fails (e.g. in walingest), we still want to know latests LSNs from the safekeeper.
match &replication_message {
ReplicationMessage::XLogData(xlog_data) => {
// TODO(vlad) Is this crap needed?
connection_status.latest_connection_update = now;
connection_status.commit_lsn = Some(Lsn::from(xlog_data.wal_end()));
connection_status.streaming_lsn = Some(Lsn::from(
@@ -299,6 +300,24 @@ pub(super) async fn handle_walreceiver_connection(
}
let status_update = match replication_message {
ReplicationMessage::RawInterpretedWalRecord(raw) => {
connection_status.latest_connection_update = now;
connection_status.latest_wal_update = now;
connection_status.commit_lsn = Some(Lsn::from(raw.wal_end()));
let interpreted = InterpretedWalRecord::des(raw.data()).unwrap();
let end_lsn = interpreted.end_lsn;
let mut modification = timeline.begin_modification(end_lsn);
walingest
.ingest_record(interpreted, &mut modification, &ctx)
.await
.with_context(|| format!("could not ingest record at {}", end_lsn))?;
modification.commit(&ctx).await?;
Some(end_lsn)
}
ReplicationMessage::XLogData(xlog_data) => {
// Pass the WAL data to the decoder, and see if we can decode
// more records as a result.

View File

@@ -611,17 +611,6 @@ NeonWALReadLocal(NeonWALReader *state, char *buf, XLogRecPtr startptr, Size coun
recptr = startptr;
nbytes = count;
/* Try to read directly from WAL buffers first. */
#if PG_MAJORVERSION_NUM >= 17
{
Size rbytes;
rbytes = WALReadFromBuffers(p, recptr, nbytes, tli);
recptr += rbytes;
nbytes -= rbytes;
p += rbytes;
}
#endif
while (nbytes > 0)
{
uint32 startoff;

View File

@@ -1361,35 +1361,29 @@ SendAppendRequests(Safekeeper *sk)
if (sk->active_state == SS_ACTIVE_READ_WAL)
{
char *errmsg;
int req_len;
req = &sk->appendRequest;
req_len = req->endLsn - req->beginLsn;
/* We send zero sized AppenRequests as heartbeats; don't wal_read for these. */
if (req_len > 0)
switch (wp->api.wal_read(sk,
&sk->outbuf.data[sk->outbuf.len],
req->beginLsn,
req->endLsn - req->beginLsn,
&errmsg))
{
switch (wp->api.wal_read(sk,
&sk->outbuf.data[sk->outbuf.len],
req->beginLsn,
req_len,
&errmsg))
{
case NEON_WALREAD_SUCCESS:
break;
case NEON_WALREAD_WOULDBLOCK:
return true;
case NEON_WALREAD_ERROR:
wp_log(WARNING, "WAL reading for node %s:%s failed: %s",
sk->host, sk->port, errmsg);
ShutdownConnection(sk);
return false;
default:
Assert(false);
}
case NEON_WALREAD_SUCCESS:
break;
case NEON_WALREAD_WOULDBLOCK:
return true;
case NEON_WALREAD_ERROR:
wp_log(WARNING, "WAL reading for node %s:%s failed: %s",
sk->host, sk->port, errmsg);
ShutdownConnection(sk);
return false;
default:
Assert(false);
}
sk->outbuf.len += req_len;
sk->outbuf.len += req->endLsn - req->beginLsn;
writeResult = wp->api.conn_async_write(sk, sk->outbuf.data, sk->outbuf.len);

View File

@@ -1489,11 +1489,33 @@ walprop_pg_wal_read(Safekeeper *sk, char *buf, XLogRecPtr startptr, Size count,
{
NeonWALReadResult res;
res = NeonWALRead(sk->xlogreader,
buf,
startptr,
count,
walprop_pg_get_timeline_id());
#if PG_MAJORVERSION_NUM >= 17
if (!sk->wp->config->syncSafekeepers)
{
Size rbytes;
rbytes = WALReadFromBuffers(buf, startptr, count,
walprop_pg_get_timeline_id());
startptr += rbytes;
count -= rbytes;
}
#endif
if (count == 0)
{
res = NEON_WALREAD_SUCCESS;
}
else
{
Assert(count > 0);
/* Now read the remaining WAL from the WAL file */
res = NeonWALRead(sk->xlogreader,
buf,
startptr,
count,
walprop_pg_get_timeline_id());
}
if (res == NEON_WALREAD_SUCCESS)
{

View File

@@ -60,7 +60,7 @@ prometheus.workspace = true
rand.workspace = true
regex.workspace = true
remote_storage = { version = "0.1", path = "../libs/remote_storage/" }
reqwest = { workspace = true, features = ["rustls-tls-native-roots"] }
reqwest.workspace = true
reqwest-middleware = { workspace = true, features = ["json"] }
reqwest-retry.workspace = true
reqwest-tracing.workspace = true

View File

@@ -7,11 +7,8 @@ use arc_swap::ArcSwapOption;
use dashmap::DashMap;
use jose_jwk::crypto::KeyInfo;
use reqwest::{redirect, Client};
use reqwest_retry::policies::ExponentialBackoff;
use reqwest_retry::RetryTransientMiddleware;
use serde::de::Visitor;
use serde::{Deserialize, Deserializer};
use serde_json::value::RawValue;
use signature::Verifier;
use thiserror::Error;
use tokio::time::Instant;
@@ -19,7 +16,7 @@ use tokio::time::Instant;
use crate::auth::backend::ComputeCredentialKeys;
use crate::context::RequestMonitoring;
use crate::control_plane::errors::GetEndpointJwksError;
use crate::http::read_body_with_limit;
use crate::http::parse_json_body_with_limit;
use crate::intern::RoleNameInt;
use crate::types::{EndpointId, RoleName};
@@ -31,10 +28,6 @@ const MAX_RENEW: Duration = Duration::from_secs(3600);
const MAX_JWK_BODY_SIZE: usize = 64 * 1024;
const JWKS_USER_AGENT: &str = "neon-proxy";
const JWKS_CONNECT_TIMEOUT: Duration = Duration::from_secs(2);
const JWKS_FETCH_TIMEOUT: Duration = Duration::from_secs(5);
const JWKS_FETCH_RETRIES: u32 = 3;
/// How to get the JWT auth rules
pub(crate) trait FetchAuthRules: Clone + Send + Sync + 'static {
fn fetch_auth_rules(
@@ -62,7 +55,7 @@ pub(crate) struct AuthRule {
}
pub struct JwkCache {
client: reqwest_middleware::ClientWithMiddleware,
client: reqwest::Client,
map: DashMap<(EndpointId, RoleName), Arc<JwkCacheEntryLock>>,
}
@@ -124,14 +117,6 @@ impl Default for JwkCacheEntryLock {
}
}
#[derive(Deserialize)]
struct JwkSet<'a> {
/// we parse into raw-value because not all keys in a JWKS are ones
/// we can parse directly, so we parse them lazily.
#[serde(borrow)]
keys: Vec<&'a RawValue>,
}
impl JwkCacheEntryLock {
async fn acquire_permit<'a>(self: &'a Arc<Self>) -> JwkRenewalPermit<'a> {
JwkRenewalPermit::acquire_permit(self).await
@@ -145,7 +130,7 @@ impl JwkCacheEntryLock {
&self,
_permit: JwkRenewalPermit<'_>,
ctx: &RequestMonitoring,
client: &reqwest_middleware::ClientWithMiddleware,
client: &reqwest::Client,
endpoint: EndpointId,
auth_rules: &F,
) -> Result<Arc<JwkCacheEntry>, JwtError> {
@@ -169,73 +154,22 @@ impl JwkCacheEntryLock {
let req = client.get(rule.jwks_url.clone());
// TODO(conrad): eventually switch to using reqwest_middleware/`new_client_with_timeout`.
// TODO(conrad): We need to filter out URLs that point to local resources. Public internet only.
match req.send().await.and_then(|r| {
r.error_for_status()
.map_err(reqwest_middleware::Error::Reqwest)
}) {
match req.send().await.and_then(|r| r.error_for_status()) {
// todo: should we re-insert JWKs if we want to keep this JWKs URL?
// I expect these failures would be quite sparse.
Err(e) => tracing::warn!(url=?rule.jwks_url, error=?e, "could not fetch JWKs"),
Ok(r) => {
let resp: http::Response<reqwest::Body> = r.into();
let bytes = match read_body_with_limit(resp.into_body(), MAX_JWK_BODY_SIZE)
.await
match parse_json_body_with_limit::<jose_jwk::JwkSet>(
resp.into_body(),
MAX_JWK_BODY_SIZE,
)
.await
{
Ok(bytes) => bytes,
Err(e) => {
tracing::warn!(url=?rule.jwks_url, error=?e, "could not decode JWKs");
continue;
}
};
match serde_json::from_slice::<JwkSet>(&bytes) {
Err(e) => {
tracing::warn!(url=?rule.jwks_url, error=?e, "could not decode JWKs");
}
Ok(jwks) => {
// size_of::<&RawValue>() == 16
// size_of::<jose_jwk::Jwk>() == 288
// better to not pre-allocate this as it might be pretty large - especially if it has many
// keys we don't want or need.
// trivial 'attack': `{"keys":[` + repeat(`0`).take(30000).join(`,`) + `]}`
// this would consume 8MiB just like that!
let mut keys = vec![];
let mut failed = 0;
for key in jwks.keys {
match serde_json::from_str::<jose_jwk::Jwk>(key.get()) {
Ok(key) => {
// if `use` (called `cls` in rust) is specified to be something other than signing,
// we can skip storing it.
if key
.prm
.cls
.as_ref()
.is_some_and(|c| *c != jose_jwk::Class::Signing)
{
continue;
}
keys.push(key);
}
Err(e) => {
tracing::debug!(url=?rule.jwks_url, failed=?e, "could not decode JWK");
failed += 1;
}
}
}
keys.shrink_to_fit();
if failed > 0 {
tracing::warn!(url=?rule.jwks_url, failed, "could not decode JWKs");
}
if keys.is_empty() {
tracing::warn!(url=?rule.jwks_url, "no valid JWKs found inside the response body");
continue;
}
let jwks = jose_jwk::JwkSet { keys };
key_sets.insert(
rule.id,
KeySet {
@@ -245,7 +179,7 @@ impl JwkCacheEntryLock {
},
);
}
};
}
}
}
}
@@ -262,7 +196,7 @@ impl JwkCacheEntryLock {
async fn get_or_update_jwk_cache<F: FetchAuthRules>(
self: &Arc<Self>,
ctx: &RequestMonitoring,
client: &reqwest_middleware::ClientWithMiddleware,
client: &reqwest::Client,
endpoint: EndpointId,
fetch: &F,
) -> Result<Arc<JwkCacheEntry>, JwtError> {
@@ -316,7 +250,7 @@ impl JwkCacheEntryLock {
self: &Arc<Self>,
ctx: &RequestMonitoring,
jwt: &str,
client: &reqwest_middleware::ClientWithMiddleware,
client: &reqwest::Client,
endpoint: EndpointId,
role_name: &RoleName,
fetch: &F,
@@ -435,19 +369,8 @@ impl Default for JwkCache {
let client = Client::builder()
.user_agent(JWKS_USER_AGENT)
.redirect(redirect::Policy::none())
.tls_built_in_native_certs(true)
.connect_timeout(JWKS_CONNECT_TIMEOUT)
.timeout(JWKS_FETCH_TIMEOUT)
.build()
.expect("client config should be valid");
// Retry up to 3 times with increasing intervals between attempts.
let retry_policy = ExponentialBackoff::builder().build_with_max_retries(JWKS_FETCH_RETRIES);
let client = reqwest_middleware::ClientBuilder::new(client)
.with(RetryTransientMiddleware::new_with_policy(retry_policy))
.build();
.expect("using &str and standard redirect::Policy");
JwkCache {
client,
map: DashMap::default(),
@@ -1286,63 +1209,4 @@ X0n5X2/pBLJzxZc62ccvZYVnctBiFs6HbSnxpuMQCfkt/BcR/ttIepBQQIW86wHL
}
}
}
#[tokio::test]
async fn check_jwk_keycloak_regression() {
let (rs, valid_jwk) = new_rsa_jwk(RS1, "rs1".into());
let valid_jwk = serde_json::to_value(valid_jwk).unwrap();
// This is valid, but we cannot parse it as we have no support for encryption JWKs, only signature based ones.
// This is taken directly from keycloak.
let invalid_jwk = serde_json::json! {
{
"kid": "U-Jc9xRli84eNqRpYQoIPF-GNuRWV3ZvAIhziRW2sbQ",
"kty": "RSA",
"alg": "RSA-OAEP",
"use": "enc",
"n": "yypYWsEKmM_wWdcPnSGLSm5ytw1WG7P7EVkKSulcDRlrM6HWj3PR68YS8LySYM2D9Z-79oAdZGKhIfzutqL8rK1vS14zDuPpAM-RWY3JuQfm1O_-1DZM8-07PmVRegP5KPxsKblLf_My8ByH6sUOIa1p2rbe2q_b0dSTXYu1t0dW-cGL5VShc400YymvTwpc-5uYNsaVxZajnB7JP1OunOiuCJ48AuVp3PqsLzgoXqlXEB1ZZdch3xT3bxaTtNruGvG4xmLZY68O_T3yrwTCNH2h_jFdGPyXdyZToCMSMK2qSbytlfwfN55pT9Vv42Lz1YmoB7XRjI9aExKPc5AxFw",
"e": "AQAB",
"x5c": [
"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"
],
"x5t": "QhfzMMnuAfkReTgZ1HtrfyOeeZs",
"x5t#S256": "cmHDUdKgLiRCEN28D5FBy9IJLFmR7QWfm77SLhGTCTU"
}
};
let jwks = serde_json::json! {{ "keys": [invalid_jwk, valid_jwk ] }};
let jwks_addr = jwks_server(move |path| match path {
"/" => Some(serde_json::to_vec(&jwks).unwrap()),
_ => None,
})
.await;
let role_name = RoleName::from("anonymous");
let role = RoleNameInt::from(&role_name);
let rules = vec![AuthRule {
id: "foo".to_owned(),
jwks_url: format!("http://{jwks_addr}/").parse().unwrap(),
audience: None,
role_names: vec![role],
}];
let fetch = Fetch(rules);
let jwk_cache = JwkCache::default();
let endpoint = EndpointId::from("ep");
let token = new_rsa_jwt("rs1".into(), rs);
jwk_cache
.check_jwt(
&RequestMonitoring::test(),
endpoint.clone(),
&role_name,
&fetch,
&token,
)
.await
.unwrap();
}
}

View File

@@ -1,12 +1,13 @@
use std::convert::Infallible;
use std::future::pending;
use std::sync::atomic::{AtomicBool, Ordering};
use std::sync::{Arc, Mutex};
use std::sync::Arc;
use dashmap::DashSet;
use redis::streams::{StreamReadOptions, StreamReadReply};
use redis::{AsyncCommands, FromRedisValue, Value};
use serde::Deserialize;
use tokio::sync::Mutex;
use tokio_util::sync::CancellationToken;
use tracing::info;
@@ -31,17 +32,17 @@ struct ControlPlaneEvent {
#[derive(Deserialize, Debug, Clone, PartialEq)]
struct EndpointCreated {
endpoint_id: EndpointIdInt,
endpoint_id: String,
}
#[derive(Deserialize, Debug, Clone, PartialEq)]
struct BranchCreated {
branch_id: BranchIdInt,
branch_id: String,
}
#[derive(Deserialize, Debug, Clone, PartialEq)]
struct ProjectCreated {
project_id: ProjectIdInt,
project_id: String,
}
impl TryFrom<&Value> for ControlPlaneEvent {
@@ -75,72 +76,53 @@ impl EndpointsCache {
}
}
pub(crate) fn is_valid(&self, ctx: &RequestMonitoring, endpoint: &EndpointId) -> bool {
pub(crate) async fn is_valid(&self, ctx: &RequestMonitoring, endpoint: &EndpointId) -> bool {
if !self.ready.load(Ordering::Acquire) {
// the endpoint cache is not yet fully initialised.
return true;
}
if !self.should_reject(endpoint) {
ctx.set_rejected(false);
let rejected = self.should_reject(endpoint);
ctx.set_rejected(rejected);
info!(?rejected, "check endpoint is valid, disabled cache");
// If cache is disabled, just collect the metrics and return or
// If the limiter allows, we don't need to check the cache.
if self.config.disable_cache || self.limiter.lock().await.check() {
return true;
}
// report that we might want to reject this endpoint
ctx.set_rejected(true);
// If cache is disabled, just collect the metrics and return.
if self.config.disable_cache {
return true;
}
// If the limiter allows, we can pretend like it's valid
// (incase it is, due to redis channel lag).
if self.limiter.lock().unwrap().check() {
return true;
}
// endpoint not found, and there's too much load.
false
!rejected
}
fn should_reject(&self, endpoint: &EndpointId) -> bool {
if endpoint.is_endpoint() {
let Some(endpoint) = EndpointIdInt::get(endpoint) else {
// if we haven't interned this endpoint, it's not in the cache.
return true;
};
!self.endpoints.contains(&endpoint)
!self.endpoints.contains(&EndpointIdInt::from(endpoint))
} else if endpoint.is_branch() {
let Some(branch) = BranchIdInt::get(endpoint) else {
// if we haven't interned this branch, it's not in the cache.
return true;
};
!self.branches.contains(&branch)
!self
.branches
.contains(&BranchIdInt::from(&endpoint.as_branch()))
} else {
let Some(project) = ProjectIdInt::get(endpoint) else {
// if we haven't interned this project, it's not in the cache.
return true;
};
!self.projects.contains(&project)
!self
.projects
.contains(&ProjectIdInt::from(&endpoint.as_project()))
}
}
fn insert_event(&self, event: ControlPlaneEvent) {
if let Some(endpoint_created) = event.endpoint_created {
self.endpoints.insert(endpoint_created.endpoint_id);
self.endpoints
.insert(EndpointIdInt::from(&endpoint_created.endpoint_id.into()));
Metrics::get()
.proxy
.redis_events_count
.inc(RedisEventsCount::EndpointCreated);
} else if let Some(branch_created) = event.branch_created {
self.branches.insert(branch_created.branch_id);
self.branches
.insert(BranchIdInt::from(&branch_created.branch_id.into()));
Metrics::get()
.proxy
.redis_events_count
.inc(RedisEventsCount::BranchCreated);
} else if let Some(project_created) = event.project_created {
self.projects.insert(project_created.project_id);
self.projects
.insert(ProjectIdInt::from(&project_created.project_id.into()));
Metrics::get()
.proxy
.redis_events_count
@@ -265,13 +247,11 @@ mod tests {
fn test_parse_control_plane_event() {
let s = r#"{"branch_created":null,"endpoint_created":{"endpoint_id":"ep-rapid-thunder-w0qqw2q9"},"project_created":null,"type":"endpoint_created"}"#;
let endpoint_id: EndpointId = "ep-rapid-thunder-w0qqw2q9".into();
assert_eq!(
serde_json::from_str::<ControlPlaneEvent>(s).unwrap(),
ControlPlaneEvent {
endpoint_created: Some(EndpointCreated {
endpoint_id: endpoint_id.into(),
endpoint_id: "ep-rapid-thunder-w0qqw2q9".into()
}),
branch_created: None,
project_created: None,

View File

@@ -316,6 +316,7 @@ impl ConnCfg {
let client_config = client_config.with_no_client_auth();
let mut mk_tls = tokio_postgres_rustls::MakeRustlsConnect::new(client_config);
// TODO(vlad): que?
let tls = <MakeRustlsConnect as MakeTlsConnect<tokio::net::TcpStream>>::make_tls_connect(
&mut mk_tls,
host,

View File

@@ -72,6 +72,7 @@ impl NeonControlPlaneClient {
.caches
.endpoints_cache
.is_valid(ctx, &user_info.endpoint.normalize())
.await
{
info!("endpoint is not valid, skipping the request");
return Ok(AuthInfo::default());
@@ -144,6 +145,7 @@ impl NeonControlPlaneClient {
.caches
.endpoints_cache
.is_valid(ctx, &endpoint.normalize())
.await
{
return Err(GetEndpointJwksError::EndpointNotFound);
}

View File

@@ -6,6 +6,7 @@ pub mod health_server;
use std::time::Duration;
use anyhow::bail;
use bytes::Bytes;
use http::Method;
use http_body_util::BodyExt;
@@ -15,7 +16,7 @@ use reqwest_middleware::RequestBuilder;
pub(crate) use reqwest_middleware::{ClientWithMiddleware, Error};
pub(crate) use reqwest_retry::policies::ExponentialBackoff;
pub(crate) use reqwest_retry::RetryTransientMiddleware;
use thiserror::Error;
use serde::de::DeserializeOwned;
use crate::metrics::{ConsoleRequest, Metrics};
use crate::url::ApiUrl;
@@ -121,19 +122,10 @@ impl Endpoint {
}
}
#[derive(Error, Debug)]
pub(crate) enum ReadBodyError {
#[error("Content length exceeds limit of {limit} bytes")]
BodyTooLarge { limit: usize },
#[error(transparent)]
Read(#[from] reqwest::Error),
}
pub(crate) async fn read_body_with_limit(
pub(crate) async fn parse_json_body_with_limit<D: DeserializeOwned>(
mut b: impl Body<Data = Bytes, Error = reqwest::Error> + Unpin,
limit: usize,
) -> Result<Vec<u8>, ReadBodyError> {
) -> anyhow::Result<D> {
// We could use `b.limited().collect().await.to_bytes()` here
// but this ends up being slightly more efficient as far as I can tell.
@@ -141,20 +133,20 @@ pub(crate) async fn read_body_with_limit(
// in reqwest, this value is influenced by the Content-Length header.
let lower_bound = match usize::try_from(b.size_hint().lower()) {
Ok(bound) if bound <= limit => bound,
_ => return Err(ReadBodyError::BodyTooLarge { limit }),
_ => bail!("Content length exceeds limit of {limit} bytes"),
};
let mut bytes = Vec::with_capacity(lower_bound);
while let Some(frame) = b.frame().await.transpose()? {
if let Ok(data) = frame.into_data() {
if bytes.len() + data.len() > limit {
return Err(ReadBodyError::BodyTooLarge { limit });
bail!("Content length exceeds limit of {limit} bytes")
}
bytes.extend_from_slice(&data);
}
}
Ok(bytes)
Ok(serde_json::from_slice::<D>(&bytes)?)
}
#[cfg(test)]

View File

@@ -1,6 +1,12 @@
// rustc lints/lint groups
// https://doc.rust-lang.org/rustc/lints/groups.html
#![deny(deprecated, future_incompatible, let_underscore, nonstandard_style)]
#![deny(
deprecated,
future_incompatible,
let_underscore,
nonstandard_style,
rust_2024_compatibility
)]
#![warn(clippy::all, clippy::pedantic, clippy::cargo)]
// List of denied lints from the clippy::restriction group.
// https://rust-lang.github.io/rust-clippy/master/index.html#?groups=restriction

View File

@@ -16,7 +16,8 @@ use super::http_conn_pool::ClientDataHttp;
use super::local_conn_pool::ClientDataLocal;
use crate::auth::backend::ComputeUserInfo;
use crate::context::RequestMonitoring;
use crate::control_plane::messages::{ColdStartInfo, MetricsAuxInfo};
use crate::control_plane::messages::ColdStartInfo;
use crate::control_plane::messages::MetricsAuxInfo;
use crate::metrics::{HttpEndpointPoolsGuard, Metrics};
use crate::types::{DbName, EndpointCacheKey, RoleName};
use crate::usage_metrics::{Ids, MetricCounter, USAGE_METRICS};

View File

@@ -7,6 +7,7 @@ use hyper::client::conn::http2;
use hyper_util::rt::{TokioExecutor, TokioIo};
use parking_lot::RwLock;
use rand::Rng;
use std::result::Result::Ok;
use tokio::net::TcpStream;
use tracing::{debug, error, info, info_span, Instrument};

View File

@@ -64,28 +64,24 @@ macro_rules! smol_str_wrapper {
}
const POOLER_SUFFIX: &str = "-pooler";
pub(crate) const LOCAL_PROXY_SUFFIX: &str = "-local-proxy";
impl EndpointId {
#[must_use]
fn normalize_str(&self) -> &str {
pub fn normalize(&self) -> Self {
if let Some(stripped) = self.as_ref().strip_suffix(POOLER_SUFFIX) {
stripped
} else if let Some(stripped) = self.as_ref().strip_suffix(LOCAL_PROXY_SUFFIX) {
stripped
stripped.into()
} else {
self
self.clone()
}
}
#[must_use]
pub fn normalize(&self) -> Self {
self.normalize_str().into()
}
#[must_use]
pub fn normalize_intern(&self) -> EndpointIdInt {
EndpointIdTag::get_interner().get_or_intern(self.normalize_str())
if let Some(stripped) = self.as_ref().strip_suffix(POOLER_SUFFIX) {
EndpointIdTag::get_interner().get_or_intern(stripped)
} else {
self.into()
}
}
}
@@ -114,4 +110,13 @@ impl EndpointId {
pub(crate) fn is_branch(&self) -> bool {
self.0.starts_with("br-")
}
// pub(crate) fn is_project(&self) -> bool {
// !self.is_endpoint() && !self.is_branch()
// }
pub(crate) fn as_branch(&self) -> BranchId {
BranchId(self.0.clone())
}
pub(crate) fn as_project(&self) -> ProjectId {
ProjectId(self.0.clone())
}
}

View File

@@ -28,6 +28,7 @@ hyper0.workspace = true
futures.workspace = true
once_cell.workspace = true
parking_lot.workspace = true
pageserver_api.workspace = true
postgres.workspace = true
postgres-protocol.workspace = true
rand.workspace = true
@@ -57,18 +58,13 @@ sd-notify.workspace = true
storage_broker.workspace = true
tokio-stream.workspace = true
utils.workspace = true
wal_decoder.workspace = true
workspace_hack.workspace = true
[dev-dependencies]
criterion.workspace = true
itertools.workspace = true
walproposer.workspace = true
rand.workspace = true
desim.workspace = true
tracing.workspace = true
tracing-subscriber = { workspace = true, features = ["json"] }
[[bench]]
name = "receive_wal"
harness = false

View File

@@ -1,22 +0,0 @@
## Safekeeper Benchmarks
To run benchmarks:
```sh
# All benchmarks.
cargo bench --package safekeeper
# Specific file.
cargo bench --package safekeeper --bench receive_wal
# Specific benchmark.
cargo bench --package safekeeper --bench receive_wal process_msg/fsync=false
# List available benchmarks.
cargo bench --package safekeeper --benches -- --list
```
Additional charts and statistics are available in `target/criterion/report/index.html`.
Benchmarks are automatically compared against the previous run. To compare against other runs, see
`--baseline` and `--save-baseline`.

View File

@@ -1,102 +0,0 @@
use std::sync::Arc;
use camino_tempfile::Utf8TempDir;
use safekeeper::rate_limit::RateLimiter;
use safekeeper::safekeeper::{ProposerAcceptorMessage, ProposerElected, SafeKeeper, TermHistory};
use safekeeper::state::{TimelinePersistentState, TimelineState};
use safekeeper::timeline::{get_timeline_dir, SharedState, StateSK, Timeline};
use safekeeper::timelines_set::TimelinesSet;
use safekeeper::wal_backup::remote_timeline_path;
use safekeeper::{control_file, wal_storage, SafeKeeperConf};
use tokio::fs::create_dir_all;
use utils::id::{NodeId, TenantTimelineId};
use utils::lsn::Lsn;
/// A Safekeeper benchmarking environment. Uses a tempdir for storage, removed on drop.
pub struct Env {
/// Whether to enable fsync.
pub fsync: bool,
/// Benchmark directory. Deleted when dropped.
pub tempdir: Utf8TempDir,
}
impl Env {
/// Creates a new benchmarking environment in a temporary directory. fsync controls whether to
/// enable fsyncing.
pub fn new(fsync: bool) -> anyhow::Result<Self> {
let tempdir = camino_tempfile::tempdir()?;
Ok(Self { fsync, tempdir })
}
/// Constructs a Safekeeper config for the given node ID.
fn make_conf(&self, node_id: NodeId) -> SafeKeeperConf {
let mut conf = SafeKeeperConf::dummy();
conf.my_id = node_id;
conf.no_sync = !self.fsync;
conf.workdir = self.tempdir.path().join(format!("safekeeper-{node_id}"));
conf
}
/// Constructs a Safekeeper with the given node and tenant/timeline ID.
///
/// TODO: we should support using in-memory storage, to measure non-IO costs. This would be
/// easier if SafeKeeper used trait objects for storage rather than generics. It's also not
/// currently possible to construct a timeline using non-file storage since StateSK only accepts
/// SafeKeeper<control_file::FileStorage, wal_storage::PhysicalStorage>.
pub async fn make_safekeeper(
&self,
node_id: NodeId,
ttid: TenantTimelineId,
) -> anyhow::Result<SafeKeeper<control_file::FileStorage, wal_storage::PhysicalStorage>> {
let conf = self.make_conf(node_id);
let timeline_dir = get_timeline_dir(&conf, &ttid);
create_dir_all(&timeline_dir).await?;
let mut pstate = TimelinePersistentState::empty();
pstate.tenant_id = ttid.tenant_id;
pstate.timeline_id = ttid.timeline_id;
let wal = wal_storage::PhysicalStorage::new(&ttid, &timeline_dir, &pstate, conf.no_sync)?;
let ctrl =
control_file::FileStorage::create_new(&timeline_dir, pstate, conf.no_sync).await?;
let state = TimelineState::new(ctrl);
let mut safekeeper = SafeKeeper::new(state, wal, conf.my_id)?;
// Emulate an initial election.
safekeeper
.process_msg(&ProposerAcceptorMessage::Elected(ProposerElected {
term: 1,
start_streaming_at: Lsn(0),
term_history: TermHistory(vec![(1, Lsn(0)).into()]),
timeline_start_lsn: Lsn(0),
}))
.await?;
Ok(safekeeper)
}
/// Constructs a timeline, including a new Safekeeper with the given node ID, and spawns its
/// manager task.
pub async fn make_timeline(
&self,
node_id: NodeId,
ttid: TenantTimelineId,
) -> anyhow::Result<Arc<Timeline>> {
let conf = self.make_conf(node_id);
let timeline_dir = get_timeline_dir(&conf, &ttid);
let remote_path = remote_timeline_path(&ttid)?;
let safekeeper = self.make_safekeeper(node_id, ttid).await?;
let shared_state = SharedState::new(StateSK::Loaded(safekeeper));
let timeline = Timeline::new(ttid, &timeline_dir, &remote_path, shared_state);
timeline.bootstrap(
&mut timeline.write_shared_state().await,
&conf,
Arc::new(TimelinesSet::default()), // ignored for now
RateLimiter::new(0, 0),
);
Ok(timeline)
}
}

View File

@@ -1,341 +0,0 @@
//! WAL ingestion benchmarks.
#[path = "benchutils.rs"]
mod benchutils;
use std::io::Write as _;
use benchutils::Env;
use camino_tempfile::tempfile;
use criterion::{criterion_group, criterion_main, BatchSize, Bencher, Criterion};
use itertools::Itertools as _;
use postgres_ffi::v17::wal_generator::{LogicalMessageGenerator, WalGenerator};
use safekeeper::receive_wal::{self, WalAcceptor};
use safekeeper::safekeeper::{
AcceptorProposerMessage, AppendRequest, AppendRequestHeader, ProposerAcceptorMessage,
};
use tokio::io::AsyncWriteExt as _;
use utils::id::{NodeId, TenantTimelineId};
use utils::lsn::Lsn;
const KB: usize = 1024;
const MB: usize = 1024 * KB;
const GB: usize = 1024 * MB;
// Register benchmarks with Criterion.
criterion_group!(
benches,
bench_process_msg,
bench_wal_acceptor,
bench_wal_acceptor_throughput,
bench_file_write
);
criterion_main!(benches);
/// Benchmarks SafeKeeper::process_msg() as time per message and throughput. Each message is an
/// AppendRequest with a single WAL record containing an XlLogicalMessage of varying size. When
/// measuring throughput, only the logical message payload is considered, excluding
/// segment/page/record headers.
fn bench_process_msg(c: &mut Criterion) {
let mut g = c.benchmark_group("process_msg");
for fsync in [false, true] {
for commit in [false, true] {
for size in [8, KB, 8 * KB, 128 * KB, MB] {
// Kind of weird to change the group throughput per benchmark, but it's the only way
// to vary it per benchmark. It works.
g.throughput(criterion::Throughput::Bytes(size as u64));
g.bench_function(format!("fsync={fsync}/commit={commit}/size={size}"), |b| {
run_bench(b, size, fsync, commit).unwrap()
});
}
}
}
// The actual benchmark. If commit is true, advance the commit LSN on every message.
fn run_bench(b: &mut Bencher, size: usize, fsync: bool, commit: bool) -> anyhow::Result<()> {
let runtime = tokio::runtime::Builder::new_current_thread() // single is fine, sync IO only
.enable_all()
.build()?;
// Construct the payload. The prefix counts towards the payload (including NUL terminator).
let prefix = c"p";
let prefixlen = prefix.to_bytes_with_nul().len();
assert!(size >= prefixlen);
let message = vec![0; size - prefixlen];
let walgen = &mut WalGenerator::new(LogicalMessageGenerator::new(prefix, &message));
// Set up the Safekeeper.
let env = Env::new(fsync)?;
let mut safekeeper =
runtime.block_on(env.make_safekeeper(NodeId(1), TenantTimelineId::generate()))?;
b.iter_batched_ref(
// Pre-construct WAL records and requests. Criterion will batch them.
|| {
let (lsn, record) = walgen.next().expect("endless WAL");
ProposerAcceptorMessage::AppendRequest(AppendRequest {
h: AppendRequestHeader {
term: 1,
term_start_lsn: Lsn(0),
begin_lsn: lsn,
end_lsn: lsn + record.len() as u64,
commit_lsn: if commit { lsn } else { Lsn(0) }, // commit previous record
truncate_lsn: Lsn(0),
proposer_uuid: [0; 16],
},
wal_data: record,
})
},
// Benchmark message processing (time per message).
|msg| {
runtime
.block_on(safekeeper.process_msg(msg))
.expect("message failed")
},
BatchSize::SmallInput, // automatically determine a batch size
);
Ok(())
}
}
/// Benchmarks WalAcceptor message processing time by sending it a batch of WAL records and waiting
/// for it to confirm that the last LSN has been flushed to storage. We pipeline a bunch of messages
/// instead of measuring each individual message to amortize costs (e.g. fsync), which is more
/// realistic. Records are XlLogicalMessage with a tiny payload (~64 bytes per record including
/// headers). Records are pre-constructed to avoid skewing the benchmark.
///
/// TODO: add benchmarks with in-memory storage, see comment on `Env::make_safekeeper()`:
fn bench_wal_acceptor(c: &mut Criterion) {
let mut g = c.benchmark_group("wal_acceptor");
for fsync in [false, true] {
for n in [1, 100, 10000] {
g.bench_function(format!("fsync={fsync}/n={n}"), |b| {
run_bench(b, n, fsync).unwrap()
});
}
}
/// The actual benchmark. n is the number of WAL records to send in a pipelined batch.
fn run_bench(b: &mut Bencher, n: usize, fsync: bool) -> anyhow::Result<()> {
let runtime = tokio::runtime::Runtime::new()?; // needs multithreaded
let env = Env::new(fsync)?;
let walgen = &mut WalGenerator::new(LogicalMessageGenerator::new(c"prefix", b"message"));
// Create buffered channels that can fit all requests, to avoid blocking on channels.
let (msg_tx, msg_rx) = tokio::sync::mpsc::channel(n);
let (reply_tx, mut reply_rx) = tokio::sync::mpsc::channel(n);
// Spawn the WalAcceptor task.
runtime.block_on(async {
// TODO: WalAcceptor doesn't actually need a full timeline, only
// Safekeeper::process_msg(). Consider decoupling them to simplify the setup.
let tli = env
.make_timeline(NodeId(1), TenantTimelineId::generate())
.await?
.wal_residence_guard()
.await?;
WalAcceptor::spawn(tli, msg_rx, reply_tx, Some(0));
anyhow::Ok(())
})?;
b.iter_batched(
// Pre-construct a batch of WAL records and requests.
|| {
walgen
.take(n)
.map(|(lsn, record)| AppendRequest {
h: AppendRequestHeader {
term: 1,
term_start_lsn: Lsn(0),
begin_lsn: lsn,
end_lsn: lsn + record.len() as u64,
commit_lsn: Lsn(0),
truncate_lsn: Lsn(0),
proposer_uuid: [0; 16],
},
wal_data: record,
})
.collect_vec()
},
// Benchmark batch ingestion (time per batch).
|reqs| {
runtime.block_on(async {
let final_lsn = reqs.last().unwrap().h.end_lsn;
// Stuff all the messages into the buffered channel to pipeline them.
for req in reqs {
let msg = ProposerAcceptorMessage::AppendRequest(req);
msg_tx.send(msg).await.expect("send failed");
}
// Wait for the last message to get flushed.
while let Some(reply) = reply_rx.recv().await {
if let AcceptorProposerMessage::AppendResponse(resp) = reply {
if resp.flush_lsn >= final_lsn {
return;
}
}
}
panic!("disconnected")
})
},
BatchSize::PerIteration, // only run one request batch at a time
);
Ok(())
}
}
/// Benchmarks WalAcceptor throughput by sending 1 GB of data with varying message sizes and waiting
/// for the last LSN to be flushed to storage. Only the actual message payload counts towards
/// throughput, headers are excluded and considered overhead. Records are XlLogicalMessage.
///
/// To avoid running out of memory, messages are constructed during the benchmark.
fn bench_wal_acceptor_throughput(c: &mut Criterion) {
const VOLUME: usize = GB; // NB: excludes message/page/segment headers and padding
let mut g = c.benchmark_group("wal_acceptor_throughput");
g.sample_size(10);
g.throughput(criterion::Throughput::Bytes(VOLUME as u64));
for fsync in [false, true] {
for commit in [false, true] {
for size in [KB, 8 * KB, 128 * KB, MB] {
assert_eq!(VOLUME % size, 0, "volume must be divisible by size");
let count = VOLUME / size;
g.bench_function(format!("fsync={fsync}/commit={commit}/size={size}"), |b| {
run_bench(b, count, size, fsync, commit).unwrap()
});
}
}
}
/// The actual benchmark. size is the payload size per message, count is the number of messages.
/// If commit is true, advance the commit LSN on each message.
fn run_bench(
b: &mut Bencher,
count: usize,
size: usize,
fsync: bool,
commit: bool,
) -> anyhow::Result<()> {
let runtime = tokio::runtime::Runtime::new()?; // needs multithreaded
// Construct the payload. The prefix counts towards the payload (including NUL terminator).
let prefix = c"p";
let prefixlen = prefix.to_bytes_with_nul().len();
assert!(size >= prefixlen);
let message = vec![0; size - prefixlen];
let walgen = &mut WalGenerator::new(LogicalMessageGenerator::new(prefix, &message));
// Construct and spawn the WalAcceptor task.
let env = Env::new(fsync)?;
let (msg_tx, msg_rx) = tokio::sync::mpsc::channel(receive_wal::MSG_QUEUE_SIZE);
let (reply_tx, mut reply_rx) = tokio::sync::mpsc::channel(receive_wal::REPLY_QUEUE_SIZE);
runtime.block_on(async {
let tli = env
.make_timeline(NodeId(1), TenantTimelineId::generate())
.await?
.wal_residence_guard()
.await?;
WalAcceptor::spawn(tli, msg_rx, reply_tx, Some(0));
anyhow::Ok(())
})?;
// Ingest the WAL.
b.iter(|| {
runtime.block_on(async {
let reqgen = walgen.take(count).map(|(lsn, record)| AppendRequest {
h: AppendRequestHeader {
term: 1,
term_start_lsn: Lsn(0),
begin_lsn: lsn,
end_lsn: lsn + record.len() as u64,
commit_lsn: if commit { lsn } else { Lsn(0) }, // commit previous record
truncate_lsn: Lsn(0),
proposer_uuid: [0; 16],
},
wal_data: record,
});
// Send requests.
for req in reqgen {
_ = reply_rx.try_recv(); // discard any replies, to avoid blocking
let msg = ProposerAcceptorMessage::AppendRequest(req);
msg_tx.send(msg).await.expect("send failed");
}
// Wait for last message to get flushed.
while let Some(reply) = reply_rx.recv().await {
if let AcceptorProposerMessage::AppendResponse(resp) = reply {
if resp.flush_lsn >= walgen.lsn {
return;
}
}
}
panic!("disconnected")
})
});
Ok(())
}
}
/// Benchmarks OS write throughput by appending blocks of a given size to a file. This is intended
/// to compare Tokio and stdlib writes, and give a baseline for optimal WAL throughput.
fn bench_file_write(c: &mut Criterion) {
let mut g = c.benchmark_group("file_write");
for kind in ["stdlib", "tokio"] {
for fsync in [false, true] {
for size in [8, KB, 8 * KB, 128 * KB, MB] {
// Kind of weird to change the group throughput per benchmark, but it's the only way to
// vary it per benchmark. It works.
g.throughput(criterion::Throughput::Bytes(size as u64));
g.bench_function(
format!("{kind}/fsync={fsync}/size={size}"),
|b| match kind {
"stdlib" => run_bench_stdlib(b, size, fsync).unwrap(),
"tokio" => run_bench_tokio(b, size, fsync).unwrap(),
name => panic!("unknown kind {name}"),
},
);
}
}
}
fn run_bench_stdlib(b: &mut Bencher, size: usize, fsync: bool) -> anyhow::Result<()> {
let mut file = tempfile()?;
let buf = vec![0u8; size];
b.iter(|| {
file.write_all(&buf).unwrap();
file.flush().unwrap();
if fsync {
file.sync_data().unwrap();
}
});
Ok(())
}
fn run_bench_tokio(b: &mut Bencher, size: usize, fsync: bool) -> anyhow::Result<()> {
let runtime = tokio::runtime::Runtime::new()?; // needs multithreaded
let mut file = tokio::fs::File::from_std(tempfile()?);
let buf = vec![0u8; size];
b.iter(|| {
runtime.block_on(async {
file.write_all(&buf).await.unwrap();
file.flush().await.unwrap();
if fsync {
file.sync_data().await.unwrap();
}
})
});
Ok(())
}
}

View File

@@ -2,11 +2,14 @@
//! protocol commands.
use anyhow::Context;
use pageserver_api::shard::{ShardIdentity, ShardStripeSize};
use std::future::Future;
use std::str::{self, FromStr};
use std::sync::Arc;
use tokio::io::{AsyncRead, AsyncWrite};
use tracing::{debug, info, info_span, Instrument};
use utils::postgres_client::PAGESERVER_SAFEKEEPER_PROTO_VERSION;
use utils::shard::{ShardCount, ShardNumber};
use crate::auth::check_permission;
use crate::json_ctrl::{handle_json_ctrl, AppendLogicalMessage};
@@ -35,6 +38,8 @@ pub struct SafekeeperPostgresHandler {
pub tenant_id: Option<TenantId>,
pub timeline_id: Option<TimelineId>,
pub ttid: TenantTimelineId,
pub shard: Option<ShardIdentity>,
pub protocol_version: Option<u8>,
/// Unique connection id is logged in spans for observability.
pub conn_id: ConnectionId,
/// Auth scope allowed on the connections and public key used to check auth tokens. None if auth is not configured.
@@ -107,11 +112,21 @@ impl<IO: AsyncRead + AsyncWrite + Unpin + Send> postgres_backend::Handler<IO>
) -> Result<(), QueryError> {
if let FeStartupPacket::StartupMessage { params, .. } = sm {
if let Some(options) = params.options_raw() {
let mut shard_count: Option<u8> = None;
let mut shard_number: Option<u8> = None;
let mut shard_stripe_size: Option<u32> = None;
for opt in options {
// FIXME `ztenantid` and `ztimelineid` left for compatibility during deploy,
// remove these after the PR gets deployed:
// https://github.com/neondatabase/neon/pull/2433#discussion_r970005064
match opt.split_once('=') {
Some(("protocol_version", value)) => {
self.protocol_version =
Some(value.parse::<u8>().with_context(|| {
format!("Failed to parse {value} as protocol_version")
})?);
}
Some(("ztenantid", value)) | Some(("tenant_id", value)) => {
self.tenant_id = Some(value.parse().with_context(|| {
format!("Failed to parse {value} as tenant id")
@@ -127,9 +142,44 @@ impl<IO: AsyncRead + AsyncWrite + Unpin + Send> postgres_backend::Handler<IO>
metrics.set_client_az(client_az)
}
}
Some(("shard_count", value)) => {
shard_count = Some(value.parse::<u8>().with_context(|| {
format!("Failed to parse {value} as shard count")
})?);
}
Some(("shard_number", value)) => {
shard_number = Some(value.parse::<u8>().with_context(|| {
format!("Failed to parse {value} as shard number")
})?);
}
Some(("shard_stripe_size", value)) => {
shard_stripe_size = Some(value.parse::<u32>().with_context(|| {
format!("Failed to parse {value} as shard stripe size")
})?);
}
_ => continue,
}
}
if self.protocol_version == Some(PAGESERVER_SAFEKEEPER_PROTO_VERSION) {
match (shard_count, shard_number, shard_stripe_size) {
(Some(count), Some(number), Some(stripe_size)) => {
self.shard = Some(
ShardIdentity::new(
ShardNumber(number),
ShardCount(count),
ShardStripeSize(stripe_size),
)
.with_context(|| "Failed to create shard identity")?,
);
}
_ => {
return Err(QueryError::Other(anyhow::anyhow!(
"Shard params were not specified"
)));
}
}
}
}
if let Some(app_name) = params.get("application_name") {
@@ -150,6 +200,11 @@ impl<IO: AsyncRead + AsyncWrite + Unpin + Send> postgres_backend::Handler<IO>
tracing::field::debug(self.appname.clone()),
);
if let Some(shard) = self.shard.as_ref() {
tracing::Span::current()
.record("shard", tracing::field::display(shard.shard_slug()));
}
Ok(())
} else {
Err(QueryError::Other(anyhow::anyhow!(
@@ -258,6 +313,8 @@ impl SafekeeperPostgresHandler {
tenant_id: None,
timeline_id: None,
ttid: TenantTimelineId::empty(),
shard: None,
protocol_version: None,
conn_id,
claims: None,
auth,

View File

@@ -112,7 +112,9 @@ impl SafeKeeperConf {
}
impl SafeKeeperConf {
pub fn dummy() -> Self {
#[cfg(test)]
#[allow(unused)]
fn dummy() -> Self {
SafeKeeperConf {
workdir: Utf8PathBuf::from("./"),
no_sync: false,

View File

@@ -562,9 +562,6 @@ impl WalAcceptor {
// Don't flush the WAL on every append, only periodically via flush_ticker.
// This batches multiple appends per fsync. If the channel is empty after
// sending the reply, we'll schedule an immediate flush.
//
// Note that a flush can still happen on segment bounds, which will result
// in an AppendResponse.
if let ProposerAcceptorMessage::AppendRequest(append_request) = msg {
msg = ProposerAcceptorMessage::NoFlushAppendRequest(append_request);
dirty = true;

View File

@@ -17,6 +17,7 @@ use tokio::{
use tokio_postgres::replication::ReplicationStream;
use tokio_postgres::types::PgLsn;
use tracing::*;
use utils::postgres_client::{ConnectionConfigArgs, POSTGRES_PROTO_VERSION};
use utils::{id::NodeId, lsn::Lsn, postgres_client::wal_stream_connection_config};
use crate::receive_wal::{WalAcceptor, REPLY_QUEUE_SIZE};
@@ -325,7 +326,17 @@ async fn recovery_stream(
conf: &SafeKeeperConf,
) -> anyhow::Result<String> {
// TODO: pass auth token
let cfg = wal_stream_connection_config(tli.ttid, &donor.pg_connstr, None, None)?;
let connection_conf_args = ConnectionConfigArgs {
protocol_version: POSTGRES_PROTO_VERSION,
ttid: tli.ttid,
shard_number: None,
shard_count: None,
shard_stripe_size: None,
listen_pg_addr_str: &donor.pg_connstr,
auth_token: None,
availability_zone: None,
};
let cfg = wal_stream_connection_config(connection_conf_args)?;
let mut cfg = cfg.to_tokio_postgres_config();
// It will make safekeeper give out not committed WAL (up to flush_lsn).
cfg.application_name(&format!("safekeeper_{}", conf.my_id));

View File

@@ -947,7 +947,6 @@ where
// while first connection still gets some packets later. It might be
// better to not log this as error! above.
let write_lsn = self.wal_store.write_lsn();
let flush_lsn = self.wal_store.flush_lsn();
if write_lsn > msg.h.begin_lsn {
bail!(
"append request rewrites WAL written before, write_lsn={}, msg lsn={}",
@@ -1013,9 +1012,7 @@ where
);
// If flush_lsn hasn't updated, AppendResponse is not very useful.
// This is the common case for !require_flush, but a flush can still
// happen on segment bounds.
if flush_lsn == self.flush_lsn() {
if !require_flush {
return Ok(None);
}

View File

@@ -11,17 +11,21 @@ use crate::wal_storage::WalReader;
use crate::GlobalTimelines;
use anyhow::{bail, Context as AnyhowContext};
use bytes::Bytes;
use pageserver_api::shard::ShardIdentity;
use parking_lot::Mutex;
use postgres_backend::PostgresBackend;
use postgres_backend::{CopyStreamHandlerEnd, PostgresBackendReader, QueryError};
use postgres_ffi::get_current_timestamp;
use postgres_ffi::waldecoder::WalStreamDecoder;
use postgres_ffi::{TimestampTz, MAX_SEND_SIZE};
use pq_proto::{BeMessage, WalSndKeepAlive, XLogDataBody};
use pq_proto::{BeMessage, InterpretedWalRecordBody, WalSndKeepAlive, XLogDataBody};
use serde::{Deserialize, Serialize};
use tokio::io::{AsyncRead, AsyncWrite};
use utils::failpoint_support;
use utils::id::TenantTimelineId;
use utils::pageserver_feedback::PageserverFeedback;
use utils::postgres_client::{PAGESERVER_SAFEKEEPER_PROTO_VERSION, POSTGRES_PROTO_VERSION};
use wal_decoder::models::InterpretedWalRecord;
use std::cmp::{max, min};
use std::net::SocketAddr;
@@ -377,6 +381,10 @@ impl Drop for WalSenderGuard {
}
impl SafekeeperPostgresHandler {
pub fn protocol_version(&self) -> u8 {
self.protocol_version.unwrap_or(POSTGRES_PROTO_VERSION)
}
/// Wrapper around handle_start_replication_guts handling result. Error is
/// handled here while we're still in walsender ttid span; with API
/// extension, this can probably be moved into postgres_backend.
@@ -412,6 +420,7 @@ impl SafekeeperPostgresHandler {
let appname = self.appname.clone();
// Use a guard object to remove our entry from the timeline when we are done.
// TODO(vlad): maybe thread shard stuff into here
let ws_guard = Arc::new(tli.get_walsenders().register(
self.ttid,
*pgb.get_peer_addr(),
@@ -475,9 +484,10 @@ impl SafekeeperPostgresHandler {
tli,
};
let protocol_version = self.protocol_version();
let res = tokio::select! {
// todo: add read|write .context to these errors
r = sender.run() => r,
r = sender.run(protocol_version, self.shard.as_ref()) => r,
r = reply_reader.run() => r,
};
@@ -560,7 +570,35 @@ impl<IO: AsyncRead + AsyncWrite + Unpin> WalSender<'_, IO> {
///
/// Err(CopyStreamHandlerEnd) is always returned; Result is used only for ?
/// convenience.
async fn run(&mut self) -> Result<(), CopyStreamHandlerEnd> {
/// TODO(vlad): add a run variant which accumulates a full wall record
/// and interprets it.
async fn run(
&mut self,
protocol_version: u8,
shard: Option<&ShardIdentity>,
) -> Result<(), CopyStreamHandlerEnd> {
match protocol_version {
POSTGRES_PROTO_VERSION => self.run_wal_sender().await,
PAGESERVER_SAFEKEEPER_PROTO_VERSION => {
self.run_interpreted_record_sender(shard.unwrap()).await
}
// TODO: make the proto version an enum
_ => unreachable!(),
}
}
async fn run_interpreted_record_sender(
&mut self,
shard: &ShardIdentity,
) -> Result<(), CopyStreamHandlerEnd> {
let mut last_logged_at = std::time::Instant::now();
let mut interpreted_records = 0;
let mut interpreted_bytes = 0;
let mut useful_bytes = 0;
let pg_version = self.tli.tli.get_state().await.1.server.pg_version / 10000;
let mut wal_decoder = WalStreamDecoder::new(self.start_pos, pg_version);
loop {
// Wait for the next portion if it is not there yet, or just
// update our end of WAL available for sending value, we
@@ -601,6 +639,141 @@ impl<IO: AsyncRead + AsyncWrite + Unpin> WalSender<'_, IO> {
};
let send_buf = &send_buf[..send_size];
wal_decoder.feed_bytes(send_buf);
// How fast or slow is this. Write a little benchmark
// to see how quiclky we can decode 1GiB of WAL.
// If this is slow, then we have a problem since it bottlenecks
// the whole afair. SK can send about 60-70MiB of raw WAL and
// about 13-17MiB of useful interpreted WAL per second (these
// number are for one shard).
while let Some((record_end_lsn, recdata)) = wal_decoder
.poll_decode()
.with_context(|| "Failed to decode WAL")?
{
assert!(record_end_lsn.is_aligned());
// Deserialize and interpret WAL record
let interpreted = InterpretedWalRecord::from_bytes_filtered(
recdata,
shard,
record_end_lsn,
pg_version,
)
.with_context(|| "Failed to interpret WAL")?;
let useful_size = interpreted.batch.buffer_size();
let mut buf = Vec::new();
interpreted
.ser_into(&mut buf)
.with_context(|| "Failed to serialize interpreted WAL")?;
let size = buf.len();
self.pgb
.write_message(&BeMessage::InterpretedWalRecord(InterpretedWalRecordBody {
wal_end: self.end_pos.0,
data: buf.as_slice(),
}))
.await?;
interpreted_records += 1;
interpreted_bytes += size;
useful_bytes += useful_size;
}
// and send it
// self.pgb
// .write_message(&BeMessage::XLogData(XLogDataBody {
// wal_start: self.start_pos.0,
// wal_end: self.end_pos.0,
// timestamp: get_current_timestamp(),
// data: send_buf,
// }))
// .await?;
// if let Some(appname) = &self.appname {
// if appname == "replica" {
// failpoint_support::sleep_millis_async!("sk-send-wal-replica-sleep");
// }
// }
// trace!(
// "sent {} bytes of WAL {}-{}",
// send_size,
// self.start_pos,
// self.start_pos + send_size as u64
// );
self.start_pos += send_size as u64;
let elapsed = last_logged_at.elapsed();
if elapsed >= Duration::from_secs(5) {
let records_rate = interpreted_records / elapsed.as_millis() * 1000;
let bytes_rate = interpreted_bytes / elapsed.as_millis() as usize * 1000;
let useful_bytes_rate = useful_bytes / elapsed.as_millis() as usize * 1000;
tracing::info!(
"Shard {} sender rate: rps={} bps={} ubps={}",
shard.number.0,
records_rate,
bytes_rate,
useful_bytes_rate
);
last_logged_at = std::time::Instant::now();
interpreted_records = 0;
interpreted_bytes = 0;
useful_bytes = 0;
}
}
}
async fn run_wal_sender(&mut self) -> Result<(), CopyStreamHandlerEnd> {
let mut useful_bytes = 0;
let mut last_logged_at = std::time::Instant::now();
loop {
// Wait for the next portion if it is not there yet, or just
// update our end of WAL available for sending value, we
// communicate it to the receiver.
self.wait_wal().await?;
assert!(
self.end_pos > self.start_pos,
"nothing to send after waiting for WAL"
);
// try to send as much as available, capped by MAX_SEND_SIZE
let mut chunk_end_pos = self.start_pos + MAX_SEND_SIZE as u64;
// if we went behind available WAL, back off
if chunk_end_pos >= self.end_pos {
chunk_end_pos = self.end_pos;
} else {
// If sending not up to end pos, round down to page boundary to
// avoid breaking WAL record not at page boundary, as protocol
// demands. See walsender.c (XLogSendPhysical).
chunk_end_pos = chunk_end_pos
.checked_sub(chunk_end_pos.block_offset())
.unwrap();
}
let send_size = (chunk_end_pos.0 - self.start_pos.0) as usize;
let send_buf = &mut self.send_buf[..send_size];
let send_size: usize;
{
// If uncommitted part is being pulled, check that the term is
// still the expected one.
let _term_guard = if let Some(t) = self.term {
Some(self.tli.acquire_term(t).await?)
} else {
None
};
// Read WAL into buffer. send_size can be additionally capped to
// segment boundary here.
send_size = self.wal_reader.read(send_buf).await?
};
let send_buf = &send_buf[..send_size];
useful_bytes += send_buf.len();
// and send it
self.pgb
.write_message(&BeMessage::XLogData(XLogDataBody {
@@ -623,6 +796,18 @@ impl<IO: AsyncRead + AsyncWrite + Unpin> WalSender<'_, IO> {
self.start_pos + send_size as u64
);
self.start_pos += send_size as u64;
let elapsed = last_logged_at.elapsed();
if elapsed >= Duration::from_secs(5) {
let useful_bytes_rate = useful_bytes / elapsed.as_millis() as usize * 1000;
tracing::info!(
"Sender rate: ubps={}",
useful_bytes_rate
);
last_logged_at = std::time::Instant::now();
useful_bytes = 0;
}
}
}

View File

@@ -138,6 +138,7 @@ impl TimelinePersistentState {
})
}
#[cfg(test)]
pub fn empty() -> Self {
TimelinePersistentState::new(
&TenantTimelineId::empty(),

View File

@@ -2,7 +2,7 @@
//! to glue together SafeKeeper and all other background services.
use anyhow::{anyhow, bail, Result};
use camino::{Utf8Path, Utf8PathBuf};
use camino::Utf8PathBuf;
use remote_storage::RemotePath;
use safekeeper_api::models::TimelineTermBumpResponse;
use serde::{Deserialize, Serialize};
@@ -108,11 +108,16 @@ pub type ReadGuardSharedState<'a> = RwLockReadGuard<'a, SharedState>;
pub struct WriteGuardSharedState<'a> {
tli: Arc<Timeline>,
guard: RwLockWriteGuard<'a, SharedState>,
skip_update: bool,
}
impl<'a> WriteGuardSharedState<'a> {
fn new(tli: Arc<Timeline>, guard: RwLockWriteGuard<'a, SharedState>) -> Self {
WriteGuardSharedState { tli, guard }
WriteGuardSharedState {
tli,
guard,
skip_update: false,
}
}
}
@@ -154,10 +159,12 @@ impl Drop for WriteGuardSharedState<'_> {
}
});
// send notification about shared state update
self.tli.shared_state_version_tx.send_modify(|old| {
*old += 1;
});
if !self.skip_update {
// send notification about shared state update
self.tli.shared_state_version_tx.send_modify(|old| {
*old += 1;
});
}
}
}
@@ -318,17 +325,8 @@ pub struct SharedState {
}
impl SharedState {
/// Creates a new SharedState.
pub fn new(sk: StateSK) -> Self {
Self {
sk,
peers_info: PeersInfo(vec![]),
wal_removal_on_hold: false,
}
}
/// Restore SharedState from control file. If file doesn't exist, bails out.
pub fn restore(conf: &SafeKeeperConf, ttid: &TenantTimelineId) -> Result<Self> {
fn restore(conf: &SafeKeeperConf, ttid: &TenantTimelineId) -> Result<Self> {
let timeline_dir = get_timeline_dir(conf, ttid);
let control_store = control_file::FileStorage::restore_new(&timeline_dir, conf.no_sync)?;
if control_store.server.wal_seg_size == 0 {
@@ -354,7 +352,11 @@ impl SharedState {
}
};
Ok(Self::new(sk))
Ok(Self {
sk,
peers_info: PeersInfo(vec![]),
wal_removal_on_hold: false,
})
}
pub(crate) fn get_wal_seg_size(&self) -> usize {
@@ -478,13 +480,11 @@ pub struct Timeline {
}
impl Timeline {
/// Constructs a new timeline.
pub fn new(
ttid: TenantTimelineId,
timeline_dir: &Utf8Path,
remote_path: &RemotePath,
shared_state: SharedState,
) -> Arc<Self> {
/// Load existing timeline from disk.
pub fn load_timeline(conf: &SafeKeeperConf, ttid: TenantTimelineId) -> Result<Arc<Timeline>> {
let _enter = info_span!("load_timeline", timeline = %ttid.timeline_id).entered();
let shared_state = SharedState::restore(conf, &ttid)?;
let (commit_lsn_watch_tx, commit_lsn_watch_rx) =
watch::channel(shared_state.sk.state().commit_lsn);
let (term_flush_lsn_watch_tx, term_flush_lsn_watch_rx) = watch::channel(TermLsn::from((
@@ -494,11 +494,10 @@ impl Timeline {
let (shared_state_version_tx, shared_state_version_rx) = watch::channel(0);
let walreceivers = WalReceivers::new();
Arc::new(Self {
let remote_path = remote_timeline_path(&ttid)?;
Ok(Arc::new(Timeline {
ttid,
remote_path: remote_path.to_owned(),
timeline_dir: timeline_dir.to_owned(),
remote_path,
commit_lsn_watch_tx,
commit_lsn_watch_rx,
term_flush_lsn_watch_tx,
@@ -509,28 +508,13 @@ impl Timeline {
walsenders: WalSenders::new(walreceivers.clone()),
walreceivers,
cancel: CancellationToken::default(),
timeline_dir: get_timeline_dir(conf, &ttid),
manager_ctl: ManagerCtl::new(),
broker_active: AtomicBool::new(false),
wal_backup_active: AtomicBool::new(false),
last_removed_segno: AtomicU64::new(0),
mgr_status: AtomicStatus::new(),
})
}
/// Load existing timeline from disk.
pub fn load_timeline(conf: &SafeKeeperConf, ttid: TenantTimelineId) -> Result<Arc<Timeline>> {
let _enter = info_span!("load_timeline", timeline = %ttid.timeline_id).entered();
let shared_state = SharedState::restore(conf, &ttid)?;
let timeline_dir = get_timeline_dir(conf, &ttid);
let remote_path = remote_timeline_path(&ttid)?;
Ok(Timeline::new(
ttid,
&timeline_dir,
&remote_path,
shared_state,
))
}))
}
/// Initialize fresh timeline on disk and start background tasks. If init
@@ -1144,13 +1128,13 @@ async fn delete_dir(path: &Utf8PathBuf) -> Result<bool> {
/// Get a path to the tenant directory. If you just need to get a timeline directory,
/// use WalResidentTimeline::get_timeline_dir instead.
pub fn get_tenant_dir(conf: &SafeKeeperConf, tenant_id: &TenantId) -> Utf8PathBuf {
pub(crate) fn get_tenant_dir(conf: &SafeKeeperConf, tenant_id: &TenantId) -> Utf8PathBuf {
conf.workdir.join(tenant_id.to_string())
}
/// Get a path to the timeline directory. If you need to read WAL files from disk,
/// use WalResidentTimeline::get_timeline_dir instead. This function does not check
/// timeline eviction status and WAL files might not be present on disk.
pub fn get_timeline_dir(conf: &SafeKeeperConf, ttid: &TenantTimelineId) -> Utf8PathBuf {
pub(crate) fn get_timeline_dir(conf: &SafeKeeperConf, ttid: &TenantTimelineId) -> Utf8PathBuf {
get_tenant_dir(conf, &ttid.tenant_id).join(ttid.timeline_id.to_string())
}

View File

@@ -12,7 +12,7 @@ use bytes::Bytes;
use camino::{Utf8Path, Utf8PathBuf};
use futures::future::BoxFuture;
use postgres_ffi::v14::xlog_utils::{IsPartialXLogFileName, IsXLogFileName, XLogFromFileName};
use postgres_ffi::{dispatch_pgversion, XLogRecord, XLogSegNo, PG_TLI, XLOG_SIZE_OF_XLOG_RECORD};
use postgres_ffi::{dispatch_pgversion, XLogSegNo, PG_TLI};
use remote_storage::RemotePath;
use std::cmp::{max, min};
use std::future::Future;
@@ -31,6 +31,7 @@ use crate::state::TimelinePersistentState;
use crate::wal_backup::{read_object, remote_timeline_path};
use postgres_ffi::waldecoder::WalStreamDecoder;
use postgres_ffi::XLogFileName;
use postgres_ffi::XLOG_BLCKSZ;
use pq_proto::SystemId;
use utils::{id::TenantTimelineId, lsn::Lsn};
@@ -113,13 +114,6 @@ pub struct PhysicalStorage {
/// non-aligned chunks of data.
write_record_lsn: Lsn,
/// The last LSN flushed to disk. May be in the middle of a record.
///
/// NB: when the rest of the system refers to `flush_lsn`, it usually
/// actually refers to `flush_record_lsn`. This ambiguity can be dangerous
/// and should be resolved.
flush_lsn: Lsn,
/// The LSN of the last WAL record flushed to disk.
flush_record_lsn: Lsn,
@@ -212,7 +206,6 @@ impl PhysicalStorage {
system_id: state.server.system_id,
write_lsn,
write_record_lsn: write_lsn,
flush_lsn,
flush_record_lsn: flush_lsn,
decoder: WalStreamDecoder::new(write_lsn, state.server.pg_version / 10000),
file: None,
@@ -230,15 +223,6 @@ impl PhysicalStorage {
)
}
/// Call fsync if config requires so.
async fn fsync_file(&mut self, file: &File) -> Result<()> {
if !self.no_sync {
self.metrics
.observe_flush_seconds(time_io_closure(file.sync_all()).await?);
}
Ok(())
}
/// Call fdatasync if config requires so.
async fn fdatasync_file(&mut self, file: &File) -> Result<()> {
if !self.no_sync {
@@ -272,15 +256,11 @@ impl PhysicalStorage {
// half initialized segment, first bake it under tmp filename and
// then rename.
let tmp_path = self.timeline_dir.join("waltmp");
let file = File::create(&tmp_path)
let mut file = File::create(&tmp_path)
.await
.with_context(|| format!("Failed to open tmp wal file {:?}", &tmp_path))?;
fail::fail_point!("sk-zero-segment", |_| {
info!("sk-zero-segment failpoint hit");
Err(anyhow::anyhow!("failpoint: sk-zero-segment"))
});
file.set_len(self.wal_seg_size as u64).await?;
write_zeroes(&mut file, self.wal_seg_size).await?;
// Note: this doesn't get into observe_flush_seconds metric. But
// segment init should be separate metric, if any.
@@ -296,9 +276,8 @@ impl PhysicalStorage {
}
}
/// Write WAL bytes, which are known to be located in a single WAL segment. Returns true if the
/// segment was completed, closed, and flushed to disk.
async fn write_in_segment(&mut self, segno: u64, xlogoff: usize, buf: &[u8]) -> Result<bool> {
/// Write WAL bytes, which are known to be located in a single WAL segment.
async fn write_in_segment(&mut self, segno: u64, xlogoff: usize, buf: &[u8]) -> Result<()> {
let mut file = if let Some(file) = self.file.take() {
file
} else {
@@ -322,24 +301,20 @@ impl PhysicalStorage {
let (wal_file_path, wal_file_partial_path) =
wal_file_paths(&self.timeline_dir, segno, self.wal_seg_size);
fs::rename(wal_file_partial_path, wal_file_path).await?;
Ok(true)
} else {
// otherwise, file can be reused later
self.file = Some(file);
Ok(false)
}
Ok(())
}
/// Writes WAL to the segment files, until everything is writed. If some segments
/// are fully written, they are flushed to disk. The last (partial) segment can
/// be flushed separately later.
///
/// Updates `write_lsn` and `flush_lsn`.
/// Updates `write_lsn`.
async fn write_exact(&mut self, pos: Lsn, mut buf: &[u8]) -> Result<()> {
// TODO: this shouldn't be possible, except possibly with write_lsn == 0.
// Rename this method to `append_exact`, and make it append-only, removing
// the `pos` parameter and this check. For this reason, we don't update
// `flush_lsn` here.
if self.write_lsn != pos {
// need to flush the file before discarding it
if let Some(file) = self.file.take() {
@@ -361,13 +336,9 @@ impl PhysicalStorage {
buf.len()
};
let flushed = self
.write_in_segment(segno, xlogoff, &buf[..bytes_write])
self.write_in_segment(segno, xlogoff, &buf[..bytes_write])
.await?;
self.write_lsn += bytes_write as u64;
if flushed {
self.flush_lsn = self.write_lsn;
}
buf = &buf[bytes_write..];
}
@@ -381,9 +352,6 @@ impl Storage for PhysicalStorage {
self.write_lsn
}
/// flush_lsn returns LSN of last durably stored WAL record.
///
/// TODO: flush_lsn() returns flush_record_lsn, but write_lsn() returns write_lsn: confusing.
#[allow(clippy::misnamed_getters)]
fn flush_lsn(&self) -> Lsn {
self.flush_record_lsn
}
@@ -430,9 +398,8 @@ impl Storage for PhysicalStorage {
self.metrics.observe_write_seconds(write_seconds);
self.metrics.observe_write_bytes(buf.len());
// Figure out the last record's end LSN and update `write_record_lsn`
// (if we got a whole record). The write may also have closed and
// flushed a segment, so update `flush_record_lsn` as well.
// figure out last record's end lsn for reporting (if we got the
// whole record)
if self.decoder.available() != startpos {
info!(
"restart decoder from {} to {}",
@@ -443,28 +410,13 @@ impl Storage for PhysicalStorage {
self.decoder = WalStreamDecoder::new(startpos, pg_version);
}
self.decoder.feed_bytes(buf);
if self.write_record_lsn <= self.flush_lsn {
// We may have flushed a previously written record.
self.flush_record_lsn = self.write_record_lsn;
}
let mut xact_commit = false;
while let Some((lsn, rec)) = self.decoder.poll_decode()? {
self.write_record_lsn = lsn;
if lsn <= self.flush_lsn {
self.flush_record_lsn = lsn;
loop {
match self.decoder.poll_decode()? {
None => break, // no full record yet
Some((lsn, _rec)) => {
self.write_record_lsn = lsn;
}
}
// TODO: the decoder already has the record header, make it return it.
let header = XLogRecord::from_slice(&rec[0..XLOG_SIZE_OF_XLOG_RECORD])
.expect("invalid record header");
xact_commit = xact_commit || header.is_xact_commit();
}
// If a transaction committed, flush the WAL. This will emit an AppendResponse to the
// compute. Otherwise, with pipelined ingestion, the txn may have to wait until the next
// periodic flush in 1 second, causing commit latency.
if xact_commit {
self.flush_wal().await?;
}
Ok(())
@@ -480,17 +432,19 @@ impl Storage for PhysicalStorage {
self.fdatasync_file(&unflushed_file).await?;
self.file = Some(unflushed_file);
} else {
// We have unflushed data (write_lsn != flush_lsn), but no file. This
// shouldn't happen, since the segment is flushed on close.
bail!(
"unexpected unflushed data with no open file, write_lsn={}, flush_lsn={}",
self.write_lsn,
self.flush_record_lsn
);
// We have unflushed data (write_lsn != flush_lsn), but no file.
// This should only happen if last file was fully written and flushed,
// but haven't updated flush_lsn yet.
if self.write_lsn.segment_offset(self.wal_seg_size) != 0 {
bail!(
"unexpected unflushed data with no open file, write_lsn={}, flush_lsn={}",
self.write_lsn,
self.flush_record_lsn
);
}
}
// everything is flushed now, let's update flush_lsn
self.flush_lsn = self.write_lsn;
self.flush_record_lsn = self.write_record_lsn;
Ok(())
}
@@ -532,12 +486,12 @@ impl Storage for PhysicalStorage {
// Remove all segments after the given LSN.
remove_segments_from_disk(&self.timeline_dir, self.wal_seg_size, |x| x > segno).await?;
let (file, is_partial) = self.open_or_create(segno).await?;
let (mut file, is_partial) = self.open_or_create(segno).await?;
// Fill end with zeroes
file.set_len(xlogoff as u64).await?;
file.set_len(self.wal_seg_size as u64).await?;
self.fsync_file(&file).await?;
file.seek(SeekFrom::Start(xlogoff as u64)).await?;
write_zeroes(&mut file, self.wal_seg_size - xlogoff).await?;
self.fdatasync_file(&file).await?;
if !is_partial {
// Make segment partial once again
@@ -549,7 +503,6 @@ impl Storage for PhysicalStorage {
// Update LSNs
self.write_lsn = end_pos;
self.write_record_lsn = end_pos;
self.flush_lsn = end_pos;
self.flush_record_lsn = end_pos;
self.is_truncated_after_restart = true;
Ok(())
@@ -798,6 +751,25 @@ impl WalReader {
}
}
/// Zero block for filling created WAL segments.
const ZERO_BLOCK: &[u8] = &[0u8; XLOG_BLCKSZ];
/// Helper for filling file with zeroes.
async fn write_zeroes(file: &mut File, mut count: usize) -> Result<()> {
fail::fail_point!("sk-write-zeroes", |_| {
info!("write_zeroes hit failpoint");
Err(anyhow::anyhow!("failpoint: sk-write-zeroes"))
});
while count >= XLOG_BLCKSZ {
file.write_all(ZERO_BLOCK).await?;
count -= XLOG_BLCKSZ;
}
file.write_all(&ZERO_BLOCK[0..count]).await?;
file.flush().await?;
Ok(())
}
/// Helper function for opening WAL segment `segno` in `dir`. Returns file and
/// whether it is .partial.
pub(crate) async fn open_wal_file(

View File

@@ -1,7 +1,7 @@
use std::{ffi::CStr, sync::Arc};
use parking_lot::{Mutex, MutexGuard};
use postgres_ffi::v16::wal_generator::{LogicalMessageGenerator, WalGenerator};
use postgres_ffi::v16::wal_generator::WalGenerator;
use utils::lsn::Lsn;
use super::block_storage::BlockStorage;
@@ -18,7 +18,7 @@ impl DiskWalProposer {
internal_available_lsn: Lsn(0),
prev_lsn: Lsn(0),
disk: BlockStorage::new(),
wal_generator: WalGenerator::new(LogicalMessageGenerator::new(c"", &[])),
wal_generator: WalGenerator::new(),
}),
})
}
@@ -36,7 +36,7 @@ pub struct State {
// actual WAL storage
disk: BlockStorage,
// WAL record generator
wal_generator: WalGenerator<LogicalMessageGenerator>,
wal_generator: WalGenerator,
}
impl State {
@@ -64,7 +64,7 @@ impl State {
/// Inserts a logical record in the WAL at the current LSN.
pub fn insert_logical_message(&mut self, prefix: &CStr, msg: &[u8]) {
let (_, record) = self.wal_generator.append_logical_message(prefix, msg);
let record = self.wal_generator.generate_logical_message(prefix, msg);
self.disk.write(self.internal_available_lsn.into(), &record);
self.prev_lsn = self.internal_available_lsn;
self.internal_available_lsn += record.len() as u64;

View File

@@ -3,7 +3,7 @@ use std::{
sync::Arc,
};
use pageserver_api::controller_api::{NodeSchedulingPolicy, ShardSchedulingPolicy};
use pageserver_api::controller_api::NodeSchedulingPolicy;
use utils::{id::NodeId, shard::TenantShardId};
use crate::{
@@ -98,20 +98,6 @@ impl TenantShardDrain {
return None;
}
// Only tenants with a normal (Active) scheduling policy are proactively moved
// around during a node drain. Shards which have been manually configured to a different
// policy are only rescheduled by manual intervention.
match tenant_shard.get_scheduling_policy() {
ShardSchedulingPolicy::Active | ShardSchedulingPolicy::Essential => {
// A migration during drain is classed as 'essential' because it is required to
// uphold our availability goals for the tenant: this shard is elegible for migration.
}
ShardSchedulingPolicy::Pause | ShardSchedulingPolicy::Stop => {
// If we have been asked to avoid rescheduling this shard, then do not migrate it during a drain
return None;
}
}
match scheduler.node_preferred(tenant_shard.intent.get_secondary()) {
Some(node) => Some(node),
None => {

View File

@@ -6721,16 +6721,6 @@ impl Service {
.tenants
.iter_mut()
.filter_map(|(tid, tenant_shard)| {
if !matches!(
tenant_shard.get_scheduling_policy(),
ShardSchedulingPolicy::Active
) {
// Only include tenants in fills if they have a normal (Active) scheduling policy. We
// even exclude Essential, because moving to fill a node is not essential to keeping this
// tenant available.
return None;
}
if tenant_shard.intent.get_secondary().contains(&node_id) {
if let Some(primary) = tenant_shard.intent.get_attached() {
return Some((*primary, *tid));

View File

@@ -45,4 +45,3 @@ class TokenScope(str, Enum):
SAFEKEEPER_DATA = "safekeeperdata"
TENANT = "tenant"
SCRUBBER = "scrubber"
INFRA = "infra"

View File

@@ -80,13 +80,7 @@ class PgBenchRunResult:
):
stdout_lines = stdout.splitlines()
number_of_clients = 0
number_of_threads = 0
number_of_transactions_actually_processed = 0
latency_average = 0.0
latency_stddev = None
tps = 0.0
scale = 0
# we know significant parts of these values from test input
# but to be precise take them from output

View File

@@ -8,7 +8,7 @@ from contextlib import _GeneratorContextManager, contextmanager
# Type-related stuff
from pathlib import Path
from typing import TYPE_CHECKING, final
from typing import TYPE_CHECKING
import pytest
from _pytest.fixtures import FixtureRequest
@@ -70,12 +70,12 @@ class PgCompare(ABC):
@contextmanager
@abstractmethod
def record_pageserver_writes(self, out_name: str) -> Iterator[None]:
def record_pageserver_writes(self, out_name: str):
pass
@contextmanager
@abstractmethod
def record_duration(self, out_name: str) -> Iterator[None]:
def record_duration(self, out_name: str):
pass
@contextmanager
@@ -105,7 +105,6 @@ class PgCompare(ABC):
return results
@final
class NeonCompare(PgCompare):
"""PgCompare interface for the neon stack."""
@@ -207,7 +206,6 @@ class NeonCompare(PgCompare):
return self.zenbenchmark.record_duration(out_name)
@final
class VanillaCompare(PgCompare):
"""PgCompare interface for vanilla postgres."""
@@ -273,7 +271,6 @@ class VanillaCompare(PgCompare):
return self.zenbenchmark.record_duration(out_name)
@final
class RemoteCompare(PgCompare):
"""PgCompare interface for a remote postgres instance."""

View File

@@ -4,14 +4,11 @@ https://python-hyper.org/projects/hyper-h2/en/stable/asyncio-example.html
auth-broker -> local-proxy needs a h2 connection, so we need a h2 server :)
"""
from __future__ import annotations
import asyncio
import collections
import io
import json
from collections.abc import AsyncIterable
from typing import TYPE_CHECKING, final
import pytest_asyncio
from h2.config import H2Configuration
@@ -28,45 +25,34 @@ from h2.events import (
)
from h2.exceptions import ProtocolError, StreamClosedError
from h2.settings import SettingCodes
from typing_extensions import override
if TYPE_CHECKING:
from typing import Any, Optional
RequestData = collections.namedtuple("RequestData", ["headers", "data"])
@final
class H2Server:
def __init__(self, host: str, port: int) -> None:
def __init__(self, host, port) -> None:
self.host = host
self.port = port
@final
class H2Protocol(asyncio.Protocol):
def __init__(self):
config = H2Configuration(client_side=False, header_encoding="utf-8")
self.conn = H2Connection(config=config)
self.transport: Optional[asyncio.Transport] = None
self.stream_data: dict[int, RequestData] = {}
self.flow_control_futures: dict[int, asyncio.Future[Any]] = {}
self.transport = None
self.stream_data = {}
self.flow_control_futures = {}
@override
def connection_made(self, transport: asyncio.BaseTransport):
assert isinstance(transport, asyncio.Transport)
def connection_made(self, transport: asyncio.Transport): # type: ignore[override]
self.transport = transport
self.conn.initiate_connection()
self.transport.write(self.conn.data_to_send())
@override
def connection_lost(self, exc: Optional[Exception]):
def connection_lost(self, _exc):
for future in self.flow_control_futures.values():
future.cancel()
self.flow_control_futures = {}
@override
def data_received(self, data: bytes):
assert self.transport is not None
try:
@@ -91,7 +77,7 @@ class H2Protocol(asyncio.Protocol):
self.window_updated(event.stream_id, event.delta)
elif isinstance(event, RemoteSettingsChanged):
if SettingCodes.INITIAL_WINDOW_SIZE in event.changed_settings:
self.window_updated(0, 0)
self.window_updated(None, 0)
self.transport.write(self.conn.data_to_send())
@@ -137,7 +123,7 @@ class H2Protocol(asyncio.Protocol):
else:
stream_data.data.write(data)
def stream_reset(self, stream_id: int):
def stream_reset(self, stream_id):
"""
A stream reset was sent. Stop sending data.
"""
@@ -145,7 +131,7 @@ class H2Protocol(asyncio.Protocol):
future = self.flow_control_futures.pop(stream_id)
future.cancel()
async def send_data(self, data: bytes, stream_id: int):
async def send_data(self, data, stream_id):
"""
Send data according to the flow control rules.
"""
@@ -175,7 +161,7 @@ class H2Protocol(asyncio.Protocol):
self.transport.write(self.conn.data_to_send())
data = data[chunk_size:]
async def wait_for_flow_control(self, stream_id: int):
async def wait_for_flow_control(self, stream_id):
"""
Waits for a Future that fires when the flow control window is opened.
"""
@@ -183,7 +169,7 @@ class H2Protocol(asyncio.Protocol):
self.flow_control_futures[stream_id] = f
await f
def window_updated(self, stream_id: int, delta):
def window_updated(self, stream_id, delta):
"""
A window update frame was received. Unblock some number of flow control
Futures.

View File

@@ -1782,7 +1782,7 @@ class NeonStorageController(MetricsGetter, LogUtils):
self.request(
"PUT",
f"{self.api}/control/v1/node/{node_id}/drain",
headers=self.headers(TokenScope.INFRA),
headers=self.headers(TokenScope.ADMIN),
)
def cancel_node_drain(self, node_id):
@@ -1790,7 +1790,7 @@ class NeonStorageController(MetricsGetter, LogUtils):
self.request(
"DELETE",
f"{self.api}/control/v1/node/{node_id}/drain",
headers=self.headers(TokenScope.INFRA),
headers=self.headers(TokenScope.ADMIN),
)
def node_fill(self, node_id):
@@ -1798,7 +1798,7 @@ class NeonStorageController(MetricsGetter, LogUtils):
self.request(
"PUT",
f"{self.api}/control/v1/node/{node_id}/fill",
headers=self.headers(TokenScope.INFRA),
headers=self.headers(TokenScope.ADMIN),
)
def cancel_node_fill(self, node_id):
@@ -1806,14 +1806,14 @@ class NeonStorageController(MetricsGetter, LogUtils):
self.request(
"DELETE",
f"{self.api}/control/v1/node/{node_id}/fill",
headers=self.headers(TokenScope.INFRA),
headers=self.headers(TokenScope.ADMIN),
)
def node_status(self, node_id):
response = self.request(
"GET",
f"{self.api}/control/v1/node/{node_id}",
headers=self.headers(TokenScope.INFRA),
headers=self.headers(TokenScope.ADMIN),
)
return response.json()
@@ -1829,7 +1829,7 @@ class NeonStorageController(MetricsGetter, LogUtils):
response = self.request(
"GET",
f"{self.api}/control/v1/node",
headers=self.headers(TokenScope.INFRA),
headers=self.headers(TokenScope.ADMIN),
)
return response.json()
@@ -1857,7 +1857,7 @@ class NeonStorageController(MetricsGetter, LogUtils):
shard_count: Optional[int] = None,
shard_stripe_size: Optional[int] = None,
tenant_config: Optional[dict[Any, Any]] = None,
placement_policy: Optional[Union[dict[Any, Any], str]] = None,
placement_policy: Optional[Union[dict[Any, Any] | str]] = None,
):
"""
Use this rather than pageserver_api() when you need to include shard parameters
@@ -4177,15 +4177,9 @@ class Safekeeper(LogUtils):
return self
def assert_no_errors(self):
not_allowed = [
"manager task finished prematurely",
"error while acquiring WalResidentTimeline guard",
"timeout while acquiring WalResidentTimeline guard",
"invalid xlog page header:",
"WAL record crc mismatch at",
]
for na in not_allowed:
assert not self.log_contains(na)
assert not self.log_contains("manager task finished prematurely")
assert not self.log_contains("error while acquiring WalResidentTimeline guard")
assert not self.log_contains("timeout while acquiring WalResidentTimeline guard")
def append_logical_message(
self, tenant_id: TenantId, timeline_id: TimelineId, request: dict[str, Any]

View File

@@ -316,7 +316,7 @@ class PageserverHttpClient(requests.Session, MetricsGetter):
def tenant_location_conf(
self,
tenant_id: Union[TenantId, TenantShardId],
location_conf: dict[str, Any],
location_conf=dict[str, Any],
flush_ms=None,
lazy: Optional[bool] = None,
):

View File

@@ -56,8 +56,6 @@ def wait_for_upload(
lsn: Lsn,
):
"""waits for local timeline upload up to specified lsn"""
current_lsn = Lsn(0)
for i in range(20):
current_lsn = remote_consistent_lsn(pageserver_http, tenant, timeline)
if current_lsn >= lsn:
@@ -205,8 +203,6 @@ def wait_for_last_record_lsn(
lsn: Lsn,
) -> Lsn:
"""waits for pageserver to catch up to a certain lsn, returns the last observed lsn."""
current_lsn = Lsn(0)
for i in range(1000):
current_lsn = last_record_lsn(pageserver_http, tenant, timeline)
if current_lsn >= lsn:

View File

@@ -112,7 +112,7 @@ def compatibility_snapshot_dir() -> Iterator[Path]:
@pytest.fixture(scope="session")
def compatibility_neon_binpath() -> Iterator[Optional[Path]]:
def compatibility_neon_binpath() -> Optional[Iterator[Path]]:
if os.getenv("REMOTE_ENV"):
return
comp_binpath = None
@@ -133,7 +133,7 @@ def pg_distrib_dir(base_dir: Path) -> Iterator[Path]:
@pytest.fixture(scope="session")
def compatibility_pg_distrib_dir() -> Iterator[Optional[Path]]:
def compatibility_pg_distrib_dir() -> Optional[Iterator[Path]]:
compat_distrib_dir = None
if env_compat_postgres_bin := os.environ.get("COMPATIBILITY_POSTGRES_DISTRIB_DIR"):
compat_distrib_dir = Path(env_compat_postgres_bin).resolve()

View File

@@ -2,13 +2,11 @@ from __future__ import annotations
from contextlib import closing
from io import BufferedReader, RawIOBase
from typing import Optional, final
from typing import Optional
from fixtures.compare_fixtures import PgCompare
from typing_extensions import override
@final
class CopyTestData(RawIOBase):
def __init__(self, rows: int):
self.rows = rows
@@ -16,7 +14,6 @@ class CopyTestData(RawIOBase):
self.linebuf: Optional[bytes] = None
self.ptr = 0
@override
def readable(self):
return True

View File

@@ -1,61 +0,0 @@
from __future__ import annotations
from typing import TYPE_CHECKING, cast
from fixtures.pg_version import PgVersion
if TYPE_CHECKING:
from collections.abc import Sequence
from fixtures.neon_fixtures import NeonEnv
def test_default_locales(neon_simple_env: NeonEnv):
"""
Test that the default locales for compute databases is C.UTF-8.
"""
env = neon_simple_env
endpoint = env.endpoints.create_start("main")
domain_locales = cast(
"Sequence[str]",
endpoint.safe_psql(
"SELECT current_setting('lc_messages') AS lc_messages,"
+ "current_setting('lc_monetary') AS lc_monetary,"
+ "current_setting('lc_numeric') AS lc_numeric,"
+ "current_setting('lc_time') AS lc_time"
)[0],
)
for dl in domain_locales:
assert dl == "C.UTF-8"
# Postgres 15 added the locale providers
if env.pg_version < PgVersion.V15:
results = cast(
"Sequence[str]",
endpoint.safe_psql(
"SELECT datcollate, datctype FROM pg_database WHERE datname = current_database()"
)[0],
)
datcollate = results[0]
datctype = results[1]
else:
results = cast(
"Sequence[str]",
endpoint.safe_psql(
"SELECT datlocprovider, datcollate, datctype FROM pg_database WHERE datname = current_database()"
)[0],
)
datlocprovider = results[0]
datcollate = results[1]
datctype = results[2]
if env.pg_version >= PgVersion.V17:
assert datlocprovider == "b", "The locale provider is not builtin"
else:
assert datlocprovider == "c", "The locale provider is not libc"
assert datcollate == "C.UTF-8"
assert datctype == "C.UTF-8"

View File

@@ -656,7 +656,6 @@ def test_upgrade_generationless_local_file_paths(
workload.write_rows(1000)
attached_pageserver = env.get_tenant_pageserver(tenant_id)
assert attached_pageserver is not None
secondary_pageserver = list([ps for ps in env.pageservers if ps.id != attached_pageserver.id])[
0
]

View File

@@ -1,50 +0,0 @@
from __future__ import annotations
import time
from fixtures.neon_fixtures import NeonEnv, logical_replication_sync
def test_physical_and_logical_replication(neon_simple_env: NeonEnv, vanilla_pg):
env = neon_simple_env
n_records = 100000
primary = env.endpoints.create_start(
branch_name="main",
endpoint_id="primary",
config_lines=["min_wal_size=32MB", "max_wal_size=64MB"],
)
p_con = primary.connect()
p_cur = p_con.cursor()
p_cur.execute("CREATE TABLE t(pk bigint primary key, payload text default repeat('?',200))")
p_cur.execute("create publication pub1 for table t")
# start subscriber to primary
vanilla_pg.start()
vanilla_pg.safe_psql("CREATE TABLE t(pk bigint primary key, payload text)")
connstr = primary.connstr().replace("'", "''")
vanilla_pg.safe_psql(f"create subscription sub1 connection '{connstr}' publication pub1")
time.sleep(1)
secondary = env.endpoints.new_replica_start(
origin=primary,
endpoint_id="secondary",
config_lines=["min_wal_size=32MB", "max_wal_size=64MB"],
)
s_con = secondary.connect()
s_cur = s_con.cursor()
for pk in range(n_records):
p_cur.execute("insert into t (pk) values (%s)", (pk,))
s_cur.execute("select count(*) from t")
assert s_cur.fetchall()[0][0] == n_records
logical_replication_sync(vanilla_pg, primary)
assert vanilla_pg.safe_psql("select count(*) from t")[0][0] == n_records
# Check that LR slot is not copied to replica
s_cur.execute("select count(*) from pg_replication_slots")
assert s_cur.fetchall()[0][0] == 0

View File

@@ -37,7 +37,7 @@ async def test_websockets(static_proxy: NeonProxy):
startup_message.extend(b"\0")
length = (4 + len(startup_message)).to_bytes(4, byteorder="big")
await websocket.send([length, bytes(startup_message)])
await websocket.send([length, startup_message])
startup_response = await websocket.recv()
assert isinstance(startup_response, bytes)

View File

@@ -1,22 +1,19 @@
from __future__ import annotations
import time
from typing import Union
import pytest
from fixtures.common_types import Lsn, TenantId, TenantShardId, TimelineId
from fixtures.common_types import Lsn
from fixtures.log_helper import log
from fixtures.neon_fixtures import (
Endpoint,
LogCursor,
NeonEnv,
NeonEnvBuilder,
last_flush_lsn_upload,
tenant_get_shards,
)
from fixtures.pageserver.http import PageserverHttpClient
from fixtures.pageserver.utils import wait_for_last_record_lsn
from fixtures.utils import query_scalar, wait_until
from fixtures.utils import query_scalar
#
@@ -172,63 +169,23 @@ def test_readonly_node_gc(neon_env_builder: NeonEnvBuilder):
)
return last_flush_lsn
def get_layers_protected_by_lease(
ps_http: PageserverHttpClient,
tenant_id: Union[TenantId, TenantShardId],
timeline_id: TimelineId,
lease_lsn: Lsn,
) -> set[str]:
"""Get all layers whose start_lsn is less than or equal to the lease lsn."""
layer_map_info = ps_http.layer_map_info(tenant_id, timeline_id)
return set(
x.layer_file_name
for x in layer_map_info.historic_layers
if Lsn(x.lsn_start) <= lease_lsn
)
def trigger_gc_and_select(
env: NeonEnv,
ep_static: Endpoint,
lease_lsn: Lsn,
ctx: str,
offset: None | LogCursor = None,
) -> LogCursor:
def trigger_gc_and_select(env: NeonEnv, ep_static: Endpoint, ctx: str):
"""
Trigger GC manually on all pageservers. Then run an `SELECT` query.
"""
for shard, ps in tenant_get_shards(env, env.initial_tenant):
client = ps.http_client()
layers_guarded_before_gc = get_layers_protected_by_lease(
client, shard, env.initial_timeline, lease_lsn=lsn
)
gc_result = client.timeline_gc(shard, env.initial_timeline, 0)
layers_guarded_after_gc = get_layers_protected_by_lease(
client, shard, env.initial_timeline, lease_lsn=lsn
)
# Note: cannot assert on `layers_removed` here because it could be layers
# not guarded by the lease. Instead, use layer map dump.
assert layers_guarded_before_gc.issubset(
layers_guarded_after_gc
), "Layers guarded by lease before GC should not be removed"
# not guarded by the lease. Rely on successful execution of the query instead.
log.info(f"{gc_result=}")
# wait for lease renewal before running query.
_, offset = wait_until(
20,
0.5,
lambda: ep_static.assert_log_contains(
"lsn_lease_bg_task.*Request succeeded", offset=offset
),
)
with ep_static.cursor() as cur:
# Following query should succeed if pages are properly guarded by leases.
cur.execute("SELECT count(*) FROM t0")
assert cur.fetchone() == (ROW_COUNT,)
log.info(f"`SELECT` query succeed after GC, {ctx=}")
return offset
# Insert some records on main branch
with env.endpoints.create_start("main") as ep_main:
@@ -256,9 +213,7 @@ def test_readonly_node_gc(neon_env_builder: NeonEnvBuilder):
generate_updates_on_main(env, ep_main, 3, end=100)
offset = trigger_gc_and_select(
env, ep_static, lease_lsn=lsn, ctx="Before pageservers restart"
)
trigger_gc_and_select(env, ep_static, ctx="Before pageservers restart")
# Trigger Pageserver restarts
for ps in env.pageservers:
@@ -267,13 +222,7 @@ def test_readonly_node_gc(neon_env_builder: NeonEnvBuilder):
time.sleep(LSN_LEASE_LENGTH / 2)
ps.start()
trigger_gc_and_select(
env,
ep_static,
lease_lsn=lsn,
ctx="After pageservers restart",
offset=offset,
)
trigger_gc_and_select(env, ep_static, ctx="After pageservers restart")
# Reconfigure pageservers
env.pageservers[0].stop()
@@ -282,13 +231,7 @@ def test_readonly_node_gc(neon_env_builder: NeonEnvBuilder):
)
env.storage_controller.reconcile_until_idle()
trigger_gc_and_select(
env,
ep_static,
lease_lsn=lsn,
ctx="After putting pageserver 0 offline",
offset=offset,
)
trigger_gc_and_select(env, ep_static, ctx="After putting pageserver 0 offline")
# Do some update so we can increment latest_gc_cutoff
generate_updates_on_main(env, ep_main, i, end=100)

View File

@@ -256,7 +256,6 @@ def test_sharding_split_compaction(
# Cleanup part 1: while layers are still in PITR window, we should only drop layers that are fully redundant
for shard in shards:
ps = env.get_tenant_pageserver(shard)
assert ps is not None
# Invoke compaction: this should drop any layers that don't overlap with the shard's key stripes
detail_before = ps.http_client().timeline_detail(shard, timeline_id)

View File

@@ -1237,7 +1237,6 @@ def test_storage_controller_tenant_deletion(
# Assert attachments all have local content
for shard_id in shard_ids:
pageserver = env.get_tenant_pageserver(shard_id)
assert pageserver is not None
assert pageserver.tenant_dir(shard_id).exists()
# Assert all shards have some content in remote storage
@@ -2746,7 +2745,6 @@ def test_storage_controller_validate_during_migration(neon_env_builder: NeonEnvB
# Upload but don't compact
origin_pageserver = env.get_tenant_pageserver(tenant_id)
assert origin_pageserver is not None
dest_ps_id = [p.id for p in env.pageservers if p.id != origin_pageserver.id][0]
origin_pageserver.http_client().timeline_checkpoint(
tenant_id, timeline_id, wait_until_uploaded=True, compact=False

View File

@@ -245,7 +245,6 @@ def test_scrubber_physical_gc_ancestors(
workload.write_rows(100, upload=False)
for shard in shards:
ps = env.get_tenant_pageserver(shard)
assert ps is not None
log.info(f"Waiting for shard {shard} on pageserver {ps.id}")
ps.http_client().timeline_checkpoint(
shard, timeline_id, compact=False, wait_until_uploaded=True
@@ -271,7 +270,6 @@ def test_scrubber_physical_gc_ancestors(
workload.churn_rows(100)
for shard in shards:
ps = env.get_tenant_pageserver(shard)
assert ps is not None
ps.http_client().timeline_compact(shard, timeline_id, force_image_layer_creation=True)
ps.http_client().timeline_gc(shard, timeline_id, 0)
@@ -338,15 +336,12 @@ def test_scrubber_physical_gc_timeline_deletion(neon_env_builder: NeonEnvBuilder
# Issue a deletion queue flush so that the parent shard can't leave behind layers
# that will look like unexpected garbage to the scrubber
ps = env.get_tenant_pageserver(tenant_id)
assert ps is not None
ps.http_client().deletion_queue_flush(execute=True)
env.get_tenant_pageserver(tenant_id).http_client().deletion_queue_flush(execute=True)
new_shard_count = 4
shards = env.storage_controller.tenant_shard_split(tenant_id, shard_count=new_shard_count)
for shard in shards:
ps = env.get_tenant_pageserver(shard)
assert ps is not None
log.info(f"Waiting for shard {shard} on pageserver {ps.id}")
ps.http_client().timeline_checkpoint(
shard, timeline_id, compact=False, wait_until_uploaded=True

View File

@@ -315,7 +315,6 @@ def test_single_branch_get_tenant_size_grows(
tenant_id: TenantId,
timeline_id: TimelineId,
) -> tuple[Lsn, int]:
size = 0
consistent = False
size_debug = None
@@ -361,7 +360,7 @@ def test_single_branch_get_tenant_size_grows(
collected_responses.append(("CREATE", current_lsn, size))
batch_size = 100
prev_size = 0
for i in range(3):
with endpoint.cursor() as cur:
cur.execute(

View File

@@ -146,7 +146,6 @@ def test_threshold_based_eviction(
out += [f" {remote} {layer.layer_file_name}"]
return "\n".join(out)
stable_for: float = 0
observation_window = 8 * eviction_threshold
consider_stable_when_no_change_for_seconds = 3 * eviction_threshold
poll_interval = eviction_threshold / 3

View File

@@ -16,7 +16,6 @@ from fixtures.neon_fixtures import (
NeonEnvBuilder,
PgBin,
flush_ep_to_pageserver,
last_flush_lsn_upload,
wait_for_last_flush_lsn,
)
from fixtures.pageserver.http import HistoricLayerInfo, PageserverApiException
@@ -577,49 +576,27 @@ def test_compaction_induced_by_detaches_in_history(
assert_pageserver_backups_equal(fullbackup_before, fullbackup_after, set())
@pytest.mark.parametrize("shards_initial_after", [(1, 1), (2, 2), (1, 4)])
@pytest.mark.parametrize("sharded", [True, False])
def test_timeline_ancestor_detach_idempotent_success(
neon_env_builder: NeonEnvBuilder, shards_initial_after: tuple[int, int]
neon_env_builder: NeonEnvBuilder, sharded: bool
):
shards_initial = shards_initial_after[0]
shards_after = shards_initial_after[1]
shards = 2 if sharded else 1
neon_env_builder.num_pageservers = shards_after
env = neon_env_builder.init_start(
initial_tenant_shard_count=shards_initial if shards_initial > 1 else None,
initial_tenant_conf={
# small checkpointing and compaction targets to ensure we generate many upload operations
"checkpoint_distance": 512 * 1024,
"compaction_threshold": 1,
"compaction_target_size": 512 * 1024,
# disable background compaction and GC. We invoke it manually when we want it to happen.
"gc_period": "0s",
"compaction_period": "0s",
},
)
neon_env_builder.num_pageservers = shards
env = neon_env_builder.init_start(initial_tenant_shard_count=shards if sharded else None)
pageservers = dict((int(p.id), p) for p in env.pageservers)
for ps in pageservers.values():
ps.allowed_errors.extend(SHUTDOWN_ALLOWED_ERRORS)
if shards_after > 1:
if sharded:
# FIXME: should this be in the neon_env_builder.init_start?
env.storage_controller.reconcile_until_idle()
client = env.storage_controller.pageserver_api()
else:
client = env.pageserver.http_client()
# Write some data so that we have some layers to copy
with env.endpoints.create_start("main", tenant_id=env.initial_tenant) as endpoint:
endpoint.safe_psql_many(
[
"CREATE TABLE foo(key serial primary key, t text default 'data_content')",
"INSERT INTO foo SELECT FROM generate_series(1,1024)",
]
)
last_flush_lsn_upload(env, endpoint, env.initial_tenant, env.initial_timeline)
first_branch = env.create_branch("first_branch")
_ = env.create_branch("second_branch", ancestor_branch_name="first_branch")
@@ -630,12 +607,6 @@ def test_timeline_ancestor_detach_idempotent_success(
reparented1 = env.create_branch("first_reparented", ancestor_branch_name="main")
reparented2 = env.create_branch("second_reparented", ancestor_branch_name="main")
if shards_after > shards_initial:
# Do a shard split
# This is a reproducer for https://github.com/neondatabase/neon/issues/9667
env.storage_controller.tenant_shard_split(env.initial_tenant, shards_after)
env.storage_controller.reconcile_until_idle()
first_reparenting_response = client.detach_ancestor(env.initial_tenant, first_branch)
assert set(first_reparenting_response) == {reparented1, reparented2}

View File

@@ -1506,10 +1506,15 @@ class SafekeeperEnv:
port=port.http,
auth_token=None,
)
safekeeper_process = start_in_background(
cmd, safekeeper_dir, "safekeeper.log", safekeeper_client.check_status
)
return safekeeper_process
try:
safekeeper_process = start_in_background(
cmd, safekeeper_dir, "safekeeper.log", safekeeper_client.check_status
)
return safekeeper_process
except Exception as e:
log.error(e)
safekeeper_process.kill()
raise Exception(f"Failed to start safekepeer as {cmd}, reason: {e}") from e
def get_safekeeper_connstrs(self):
assert self.safekeepers is not None, "safekeepers are not initialized"

View File

@@ -602,7 +602,7 @@ async def run_segment_init_failure(env: NeonEnv):
sk = env.safekeepers[0]
sk_http = sk.http_client()
sk_http.configure_failpoints([("sk-zero-segment", "return")])
sk_http.configure_failpoints([("sk-write-zeroes", "return")])
conn = await ep.connect_async()
ep.safe_psql("select pg_switch_wal()") # jump to the segment boundary
# next insertion should hang until failpoint is disabled.

View File

@@ -64,7 +64,6 @@ def test_wal_restore(
),
str(data_dir),
str(port),
env.pg_version,
]
)
restored.start()
@@ -128,7 +127,6 @@ def test_wal_restore_initdb(
),
str(data_dir),
str(port),
env.pg_version,
]
)
restored.start()

View File

@@ -64,7 +64,7 @@ rand = { version = "0.8", features = ["small_rng"] }
regex = { version = "1" }
regex-automata = { version = "0.4", default-features = false, features = ["dfa-onepass", "hybrid", "meta", "nfa-backtrack", "perf-inline", "perf-literal", "unicode"] }
regex-syntax = { version = "0.8" }
reqwest = { version = "0.12", default-features = false, features = ["blocking", "json", "rustls-tls", "rustls-tls-native-roots", "stream"] }
reqwest = { version = "0.12", default-features = false, features = ["blocking", "json", "rustls-tls", "stream"] }
rustls = { version = "0.23", default-features = false, features = ["logging", "ring", "std", "tls12"] }
scopeguard = { version = "1" }
serde = { version = "1", features = ["alloc", "derive"] }