fix the typo

## Problem

- Benchmark periodic pagebench had inconsistent benchmarking results
even when run with the same commit hash.
Hypothesis is this was due to running on dedicated but virtualized EC
instance with varying CPU frequency.

- the dedicated instance type used for the benchmark is quite "old" and
we increasingly get `An error occurred (InsufficientInstanceCapacity)
when calling the StartInstances operation (reached max retries: 2):
Insufficient capacity.`

- periodic pagebench uses a snapshot of pageserver timelines to have the
same layer structure in each run and get consistent performance.
Re-creating the snapshot was a painful manual process (see
https://github.com/neondatabase/cloud/issues/27051 and
https://github.com/neondatabase/cloud/issues/27653)

## Summary of changes

- Run the periodic pagebench on a custom hetzner GitHub runner with
large nvme disk and governor set to defined perf profile
- provide a manual dispatch option for the workflow that allows to
create a new snapshot
- keep the manual dispatch option to specify a commit hash useful for
bi-secting regressions
- always use the newest created snapshot (S3 bucket uses date suffix in
S3 key, example
`s3://neon-github-public-dev/performance/pagebench/shared-snapshots-2025-05-17/`
- `--ignore`
`test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py`
in regular benchmarks run for each commit
- improve perf copying snapshot by using `cp` subprocess instead of
traversing tree in python


## Example runs with code in this PR:
- run which creates new snapshot
https://github.com/neondatabase/neon/actions/runs/15083408849/job/42402986376#step:19:55
- run which uses latest snapshot
-
https://github.com/neondatabase/neon/actions/runs/15084907676/job/42406240745#step:11:65

.github/workflows/build_and_test.yml

@@ -314,7 +314,8 @@ jobs:
           test_selection: performance
           run_in_parallel: false
           save_perf_report: ${{ github.ref_name == 'main' }}
-          extra_params: --splits 5 --group ${{ matrix.pytest_split_group }}
+          # test_pageserver_max_throughput_getpage_at_latest_lsn is run in separate workflow periodic_pagebench.yml because it needs snapshots
+          extra_params: --splits 5 --group ${{ matrix.pytest_split_group }} --ignore=test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py
           benchmark_durations: ${{ needs.get-benchmarks-durations.outputs.json }}
           pg_version: v16
           aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}

.github/workflows/periodic_pagebench.yml

@@ -1,4 +1,4 @@
-name: Periodic pagebench performance test on dedicated EC2 machine in eu-central-1 region
+name: Periodic pagebench performance test on unit-perf hetzner runner
 
 on:
   schedule:
@@ -8,7 +8,7 @@ on:
     #        │   │ ┌───────────── day of the month (1 - 31)
     #        │   │ │ ┌───────────── month (1 - 12 or JAN-DEC)
     #        │   │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
-    - cron: '0 */3 * * *' # Runs every 3 hours
+    - cron: '0 */4 * * *' # Runs every 4 hours
   workflow_dispatch: # Allows manual triggering of the workflow
     inputs:
       commit_hash:
@@ -16,6 +16,11 @@ on:
         description: 'The long neon repo commit hash for the system under test (pageserver) to be tested.'
         required: false
         default: ''
+      recreate_snapshots:
+        type: boolean
+        description: 'Recreate snapshots - !!!WARNING!!! We should only recreate snapshots if the previous ones are no longer compatible. Otherwise benchmarking results are not comparable across runs.'
+        required: false
+        default: false
 
 defaults:
   run:
@@ -29,13 +34,13 @@ permissions:
   contents: read
 
 jobs:
-  trigger_bench_on_ec2_machine_in_eu_central_1:
+  run_periodic_pagebench_test:
     permissions:
       id-token: write # aws-actions/configure-aws-credentials
       statuses: write
       contents: write
       pull-requests: write
-    runs-on: [ self-hosted, small ]
+    runs-on: [ self-hosted, unit-perf ]
     container:
       image: ghcr.io/neondatabase/build-tools:pinned-bookworm
       credentials:
@@ -44,10 +49,13 @@ jobs:
       options: --init
     timeout-minutes: 360  # Set the timeout to 6 hours
     env:
-      API_KEY: ${{ secrets.PERIODIC_PAGEBENCH_EC2_RUNNER_API_KEY }}
       RUN_ID: ${{ github.run_id }}
-      AWS_DEFAULT_REGION : "eu-central-1"
-      AWS_INSTANCE_ID : "i-02a59a3bf86bc7e74"
+      DEFAULT_PG_VERSION: 16
+      BUILD_TYPE: release
+      RUST_BACKTRACE: 1
+      # NEON_ENV_BUILDER_USE_OVERLAYFS_FOR_SNAPSHOTS: 1 - doesn't work without root in container
+      S3_BUCKET: neon-github-public-dev
+      PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
     steps:
     # we don't need the neon source code because we run everything remotely
     # however we still need the local github actions to run the allure step below
@@ -56,99 +64,194 @@ jobs:
       with:
         egress-policy: audit
 
-    - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+    - name: Set up the environment which depends on $RUNNER_TEMP on nvme drive
+      id: set-env
+      shell: bash -euxo pipefail {0}
+      run: |
+        {
+          echo "NEON_DIR=${RUNNER_TEMP}/neon"
+          echo "NEON_BIN=${RUNNER_TEMP}/neon/bin"
+          echo "POSTGRES_DISTRIB_DIR=${RUNNER_TEMP}/neon/pg_install"
+          echo "LD_LIBRARY_PATH=${RUNNER_TEMP}/neon/pg_install/v${DEFAULT_PG_VERSION}/lib"
+          echo "BACKUP_DIR=${RUNNER_TEMP}/instance_store/saved_snapshots"
+          echo "TEST_OUTPUT=${RUNNER_TEMP}/neon/test_output"
+          echo "PERF_REPORT_DIR=${RUNNER_TEMP}/neon/test_output/perf-report-local"
+          echo "ALLURE_DIR=${RUNNER_TEMP}/neon/test_output/allure-results"
+          echo "ALLURE_RESULTS_DIR=${RUNNER_TEMP}/neon/test_output/allure-results/results"
+        } >> "$GITHUB_ENV"
 
-    - name: Show my own (github runner) external IP address - usefull for IP allowlisting
-      run: curl https://ifconfig.me
+        echo "allure_results_dir=${RUNNER_TEMP}/neon/test_output/allure-results/results" >> "$GITHUB_OUTPUT"
 
-    - name: Assume AWS OIDC role that allows to manage (start/stop/describe... EC machine)
-      uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
+    - uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
       with:
         aws-region: eu-central-1
-        role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN }}
-        role-duration-seconds: 3600
-
-    - name: Start EC2 instance and wait for the instance to boot up
-      run: |
-        aws ec2 start-instances --instance-ids $AWS_INSTANCE_ID
-        aws ec2 wait instance-running --instance-ids $AWS_INSTANCE_ID
-        sleep 60 # sleep some time to allow cloudinit and our API server to start up
-
-    - name: Determine public IP of the EC2 instance and set env variable EC2_MACHINE_URL_US
-      run: |
-        public_ip=$(aws ec2 describe-instances --instance-ids $AWS_INSTANCE_ID --query 'Reservations[*].Instances[*].PublicIpAddress' --output text)
-        echo "Public IP of the EC2 instance: $public_ip"
-        echo "EC2_MACHINE_URL_US=https://${public_ip}:8443" >> $GITHUB_ENV
-
+        role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
+        role-duration-seconds: 18000 # max 5 hours (needed in case commit hash is still being built)
     - name: Determine commit hash
+      id: commit_hash
+      shell: bash -euxo pipefail {0}
       env:
         INPUT_COMMIT_HASH: ${{ github.event.inputs.commit_hash }}
       run: |
-        if [ -z "$INPUT_COMMIT_HASH" ]; then
-          echo "COMMIT_HASH=$(curl -s https://api.github.com/repos/neondatabase/neon/commits/main | jq -r '.sha')" >> $GITHUB_ENV
+        if [[ -z "${INPUT_COMMIT_HASH}" ]]; then
+          COMMIT_HASH=$(curl -s https://api.github.com/repos/neondatabase/neon/commits/main | jq -r '.sha')
+          echo "COMMIT_HASH=$COMMIT_HASH" >> $GITHUB_ENV
+          echo "commit_hash=$COMMIT_HASH" >> "$GITHUB_OUTPUT"
           echo "COMMIT_HASH_TYPE=latest" >> $GITHUB_ENV
         else
-          echo "COMMIT_HASH=$INPUT_COMMIT_HASH" >> $GITHUB_ENV
+          COMMIT_HASH="${INPUT_COMMIT_HASH}"
+          echo "COMMIT_HASH=$COMMIT_HASH" >> $GITHUB_ENV
+          echo "commit_hash=$COMMIT_HASH" >> "$GITHUB_OUTPUT"
           echo "COMMIT_HASH_TYPE=manual" >> $GITHUB_ENV
         fi
+    - name: Checkout the neon repository at given commit hash
+      uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      with:
+        ref: ${{ steps.commit_hash.outputs.commit_hash }}
 
-    - name: Start Bench with run_id
+    # does not reuse ./.github/actions/download because we need to download the artifact for the given commit hash
+    # example artifact
+    # s3://neon-github-public-dev/artifacts/48b870bc078bd2c450eb7b468e743b9c118549bf/15036827400/1/neon-Linux-X64-release-artifact.tar.zst /instance_store/artifacts/neon-Linux-release-artifact.tar.zst
+    - name: Determine artifact S3_KEY for given commit hash and download and extract artifact
+      id: artifact_prefix
+      shell: bash -euxo pipefail {0}
+      env:
+        ARCHIVE: ${{ runner.temp }}/downloads/neon-${{ runner.os }}-${{ runner.arch }}-release-artifact.tar.zst
+        COMMIT_HASH: ${{ env.COMMIT_HASH }}
+        COMMIT_HASH_TYPE: ${{ env.COMMIT_HASH_TYPE }}
       run: |
-        curl -k -X 'POST' \
-        "${EC2_MACHINE_URL_US}/start_test/${GITHUB_RUN_ID}" \
-        -H 'accept: application/json' \
-        -H 'Content-Type: application/json' \
-        -H "Authorization: Bearer $API_KEY" \
-        -d "{\"neonRepoCommitHash\": \"${COMMIT_HASH}\", \"neonRepoCommitHashType\": \"${COMMIT_HASH_TYPE}\"}"
+        attempt=0
+        max_attempts=24 # 5 minutes * 24 = 2 hours
 
-    - name: Poll Test Status
-      id: poll_step
-      run: |
-        status=""
-        while [[ "$status" != "failure" && "$status" != "success" ]]; do
-          response=$(curl -k -X 'GET' \
-          "${EC2_MACHINE_URL_US}/test_status/${GITHUB_RUN_ID}" \
-          -H 'accept: application/json' \
-          -H "Authorization: Bearer $API_KEY")
-          echo "Response: $response"
-          set +x
-          status=$(echo $response | jq -r '.status')
-          echo "Test status: $status"
-          if [[ "$status" == "failure" ]]; then
-            echo "Test failed"
-            exit 1 # Fail the job step if status is failure
-          elif [[ "$status" == "success" || "$status" == "null" ]]; then
+        while [[ $attempt -lt $max_attempts ]]; do
+          # the following command will fail until the artifacts are available ...
+          S3_KEY=$(aws s3api list-objects-v2 --bucket "$S3_BUCKET" --prefix "artifacts/$COMMIT_HASH/" \
+            | jq -r '.Contents[]?.Key' \
+            | grep "neon-${{ runner.os }}-${{ runner.arch }}-release-artifact.tar.zst" \
+            | sort --version-sort \
+            | tail -1) || true # ... thus ignore errors from the command
+          if [[ -n "${S3_KEY}" ]]; then
+            echo "Artifact found: $S3_KEY"
+            echo "S3_KEY=$S3_KEY" >> $GITHUB_ENV
             break
-          elif [[ "$status" == "too_many_runs" ]]; then
-            echo "Too many runs already running"
-            echo "too_many_runs=true" >> "$GITHUB_OUTPUT"
-            exit 1
           fi
-
-          sleep 60 # Poll every 60 seconds
+          
+          # Increment attempt counter and sleep for 5 minutes
+          attempt=$((attempt + 1))
+          echo "Attempt $attempt of $max_attempts to find artifacts in S3 bucket s3://$S3_BUCKET/artifacts/$COMMIT_HASH failed. Retrying in 5 minutes..."
+          sleep 300 # Sleep for 5 minutes
         done
 
-    - name: Retrieve Test Logs
-      if: always() && steps.poll_step.outputs.too_many_runs != 'true'
-      run: |
-        curl -k -X 'GET' \
-        "${EC2_MACHINE_URL_US}/test_log/${GITHUB_RUN_ID}" \
-        -H 'accept: application/gzip' \
-        -H "Authorization: Bearer $API_KEY" \
-        --output "test_log_${GITHUB_RUN_ID}.gz"
+        if [[ -z "${S3_KEY}" ]]; then
+          echo "Error: artifact not found in S3 bucket s3://$S3_BUCKET/artifacts/$COMMIT_HASH" after 2 hours
+        else
+          mkdir -p $(dirname $ARCHIVE)
+          time aws s3 cp --only-show-errors s3://$S3_BUCKET/${S3_KEY} ${ARCHIVE}
+          mkdir -p ${NEON_DIR}
+          time tar -xf ${ARCHIVE} -C ${NEON_DIR}
+          rm -f ${ARCHIVE}
+        fi
 
-    - name: Unzip Test Log and Print it into this job's log
-      if: always() && steps.poll_step.outputs.too_many_runs != 'true'
+    - name: Download snapshots from S3
+      if: ${{ github.event_name != 'workflow_dispatch' || github.event.inputs.recreate_snapshots == 'false' || github.event.inputs.recreate_snapshots == '' }}
+      id: download_snapshots
+      shell: bash -euxo pipefail {0}
       run: |
-        gzip -d "test_log_${GITHUB_RUN_ID}.gz"
-        cat "test_log_${GITHUB_RUN_ID}"
+        # Download the snapshots from S3
+        mkdir -p ${TEST_OUTPUT}
+        mkdir -p $BACKUP_DIR
+        cd $BACKUP_DIR
+        mkdir parts
+        cd parts
+        PART=$(aws s3api list-objects-v2 --bucket $S3_BUCKET --prefix performance/pagebench/ \
+          | jq -r '.Contents[]?.Key' \
+          | grep -E 'shared-snapshots-[0-9]{4}-[0-9]{2}-[0-9]{2}' \
+          | sort \
+          | tail -1)
+        echo "Latest PART: $PART"
+        if [[ -z "$PART" ]]; then
+          echo "ERROR: No matching S3 key found" >&2
+          exit 1
+        fi
+        S3_KEY=$(dirname $PART)
+        time aws s3 cp --only-show-errors --recursive s3://${S3_BUCKET}/$S3_KEY/ .
+        cd $TEST_OUTPUT
+        time cat $BACKUP_DIR/parts/* | zstdcat | tar --extract --preserve-permissions
+        rm -rf ${BACKUP_DIR}
+
+    - name: Cache poetry deps
+      uses: actions/cache@v4
+      with:
+        path: ~/.cache/pypoetry/virtualenvs
+        key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
+
+    - name: Install Python deps
+      shell: bash -euxo pipefail {0}
+      run: ./scripts/pysync
+
+    # we need high number of open files for pagebench
+    - name: show ulimits
+      shell: bash -euxo pipefail {0}
+      run: |
+        ulimit -a
+
+    - name: Run pagebench testcase
+      shell: bash -euxo pipefail {0}
+      env:
+        CI: false  # need to override this env variable set by github to enforce using snapshots
+      run: |
+        export PLATFORM=hetzner-unit-perf-${COMMIT_HASH_TYPE}
+        # report the commit hash of the neon repository in the revision of the test results
+        export GITHUB_SHA=${COMMIT_HASH}
+        rm -rf ${PERF_REPORT_DIR}
+        rm -rf ${ALLURE_RESULTS_DIR}
+        mkdir -p ${PERF_REPORT_DIR}
+        mkdir -p ${ALLURE_RESULTS_DIR}
+        PARAMS="--alluredir=${ALLURE_RESULTS_DIR} --tb=short --verbose -rA"
+        EXTRA_PARAMS="--out-dir ${PERF_REPORT_DIR} --durations-path $TEST_OUTPUT/benchmark_durations.json"
+        # run only two selected tests
+        # environment set by parent:
+        # RUST_BACKTRACE=1 DEFAULT_PG_VERSION=16 BUILD_TYPE=release
+        ./scripts/pytest ${PARAMS} test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py::test_pageserver_characterize_throughput_with_n_tenants ${EXTRA_PARAMS}
+        ./scripts/pytest ${PARAMS} test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py::test_pageserver_characterize_latencies_with_1_client_and_throughput_with_many_clients_one_tenant ${EXTRA_PARAMS}
+
+    - name: upload the performance metrics to the Neon performance database which is used by grafana dashboards to display the results
+      shell: bash -euxo pipefail {0}
+      run: |
+        export REPORT_FROM="$PERF_REPORT_DIR"
+        export GITHUB_SHA=${COMMIT_HASH}
+        time ./scripts/generate_and_push_perf_report.sh
+
+    - name: Upload test results
+      if: ${{ !cancelled() }}
+      uses: ./.github/actions/allure-report-store
+      with:
+        report-dir:  ${{ steps.set-env.outputs.allure_results_dir }}
+        unique-key: ${{ env.BUILD_TYPE }}-${{ env.DEFAULT_PG_VERSION }}-${{ runner.arch }}
+        aws-oidc-role-arn:  ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
     - name: Create Allure report
+      id: create-allure-report
       if: ${{ !cancelled() }}
       uses: ./.github/actions/allure-report-generate
       with:
         aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
 
+    - name: Upload snapshots
+      if: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.recreate_snapshots != 'false' && github.event.inputs.recreate_snapshots != '' }}
+      id: upload_snapshots
+      shell: bash -euxo pipefail {0}
+      run: |
+        mkdir -p $BACKUP_DIR
+        cd $TEST_OUTPUT
+        tar --create --preserve-permissions --file - shared-snapshots | zstd -o $BACKUP_DIR/shared_snapshots.tar.zst
+        cd $BACKUP_DIR
+        mkdir parts
+        split -b 1G shared_snapshots.tar.zst ./parts/shared_snapshots.tar.zst.part.
+        SNAPSHOT_DATE=$(date +%F)  # YYYY-MM-DD
+        cd parts
+        time aws s3 cp --recursive . s3://${S3_BUCKET}/performance/pagebench/shared-snapshots-${SNAPSHOT_DATE}/
+
     - name: Post to a Slack channel
       if: ${{ github.event.schedule && failure() }}
       uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
@@ -157,26 +260,22 @@ jobs:
         slack-message: "Periodic pagebench testing on dedicated hardware: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
       env:
         SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
-
+        
     - name: Cleanup Test Resources
       if: always()
+      shell: bash -euxo pipefail {0}
+      env:
+        ARCHIVE: ${{ runner.temp }}/downloads/neon-${{ runner.os }}-${{ runner.arch }}-release-artifact.tar.zst
       run: |
-        curl -k -X 'POST' \
-        "${EC2_MACHINE_URL_US}/cleanup_test/${GITHUB_RUN_ID}" \
-        -H 'accept: application/json' \
-        -H "Authorization: Bearer $API_KEY" \
-        -d ''
+        # Cleanup the test resources
+        if [[ -d "${BACKUP_DIR}" ]]; then
+          rm -rf ${BACKUP_DIR}
+        fi
+        if [[ -d "${TEST_OUTPUT}" ]]; then
+          rm -rf ${TEST_OUTPUT}
+        fi
+        if [[ -d "${NEON_DIR}" ]]; then
+          rm -rf ${NEON_DIR}
+        fi
+        rm -rf $(dirname $ARCHIVE)
 
-    - name: Assume AWS OIDC role that allows to manage (start/stop/describe... EC machine)
-      if: always() && steps.poll_step.outputs.too_many_runs != 'true'
-      uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
-      with:
-        aws-region: eu-central-1
-        role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN }}
-        role-duration-seconds: 3600
-
-    - name: Stop EC2 instance and wait for the instance to be stopped
-      if: always() && steps.poll_step.outputs.too_many_runs != 'true'
-      run: |
-        aws ec2 stop-instances --instance-ids $AWS_INSTANCE_ID
-        aws ec2 wait instance-stopped --instance-ids $AWS_INSTANCE_ID

Cargo.lock

@@ -1276,7 +1276,7 @@ version = "0.1.0"
 dependencies = [
  "anyhow",
  "chrono",
- "indexmap 2.0.1",
+ "indexmap 2.9.0",
  "jsonwebtoken",
  "regex",
  "remote_storage",
@@ -1308,7 +1308,7 @@ dependencies = [
  "flate2",
  "futures",
  "http 1.1.0",
- "indexmap 2.0.1",
+ "indexmap 2.9.0",
  "itertools 0.10.5",
  "jsonwebtoken",
  "metrics",
@@ -2597,7 +2597,7 @@ dependencies = [
  "futures-sink",
  "futures-util",
  "http 0.2.9",
- "indexmap 2.0.1",
+ "indexmap 2.9.0",
  "slab",
  "tokio",
  "tokio-util",
@@ -2616,7 +2616,7 @@ dependencies = [
  "futures-sink",
  "futures-util",
  "http 1.1.0",
- "indexmap 2.0.1",
+ "indexmap 2.9.0",
  "slab",
  "tokio",
  "tokio-util",
@@ -2863,14 +2863,14 @@ dependencies = [
  "pprof",
  "regex",
  "routerify",
- "rustls 0.23.18",
+ "rustls 0.23.27",
  "rustls-pemfile 2.1.1",
  "serde",
  "serde_json",
  "serde_path_to_error",
  "thiserror 1.0.69",
  "tokio",
- "tokio-rustls 0.26.0",
+ "tokio-rustls 0.26.2",
  "tokio-stream",
  "tokio-util",
  "tracing",
@@ -3200,12 +3200,12 @@ dependencies = [
 
 [[package]]
 name = "indexmap"
-version = "2.0.1"
+version = "2.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ad227c3af19d4914570ad36d30409928b75967c298feb9ea1969db3a610bb14e"
+checksum = "cea70ddb795996207ad57735b50c5982d8844f38ba9ee5f1aedcfb708a2aa11e"
 dependencies = [
  "equivalent",
- "hashbrown 0.14.5",
+ "hashbrown 0.15.2",
  "serde",
 ]
 
@@ -3228,7 +3228,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "232929e1d75fe899576a3d5c7416ad0d88dbfbb3c3d6aa00873a7408a50ddb88"
 dependencies = [
  "ahash",
- "indexmap 2.0.1",
+ "indexmap 2.9.0",
  "is-terminal",
  "itoa",
  "log",
@@ -3251,7 +3251,7 @@ dependencies = [
  "crossbeam-utils",
  "dashmap 6.1.0",
  "env_logger",
- "indexmap 2.0.1",
+ "indexmap 2.9.0",
  "itoa",
  "log",
  "num-format",
@@ -4112,7 +4112,7 @@ dependencies = [
  "opentelemetry-http",
  "opentelemetry-proto",
  "opentelemetry_sdk",
- "prost 0.13.3",
+ "prost 0.13.5",
  "reqwest",
  "thiserror 1.0.69",
 ]
@@ -4125,8 +4125,8 @@ checksum = "a6e05acbfada5ec79023c85368af14abd0b307c015e9064d249b2a950ef459a6"
 dependencies = [
  "opentelemetry",
  "opentelemetry_sdk",
- "prost 0.13.3",
- "tonic",
+ "prost 0.13.5",
+ "tonic 0.12.3",
 ]
 
 [[package]]
@@ -4339,7 +4339,7 @@ dependencies = [
  "reqwest",
  "rpds",
  "rstest",
- "rustls 0.23.18",
+ "rustls 0.23.27",
  "scopeguard",
  "send-future",
  "serde",
@@ -4358,7 +4358,7 @@ dependencies = [
  "tokio-epoll-uring",
  "tokio-io-timeout",
  "tokio-postgres",
- "tokio-rustls 0.26.0",
+ "tokio-rustls 0.26.2",
  "tokio-stream",
  "tokio-tar",
  "tokio-util",
@@ -4455,8 +4455,8 @@ dependencies = [
 name = "pageserver_page_api"
 version = "0.1.0"
 dependencies = [
- "prost 0.13.3",
- "tonic",
+ "prost 0.13.5",
+ "tonic 0.13.1",
  "tonic-build",
  "workspace_hack",
 ]
@@ -4837,14 +4837,14 @@ dependencies = [
  "bytes",
  "once_cell",
  "pq_proto",
- "rustls 0.23.18",
+ "rustls 0.23.27",
  "rustls-pemfile 2.1.1",
  "serde",
  "thiserror 1.0.69",
  "tokio",
  "tokio-postgres",
  "tokio-postgres-rustls",
- "tokio-rustls 0.26.0",
+ "tokio-rustls 0.26.2",
  "tokio-util",
  "tracing",
 ]
@@ -4951,7 +4951,7 @@ dependencies = [
  "inferno 0.12.0",
  "num",
  "paste",
- "prost 0.13.3",
+ "prost 0.13.5",
 ]
 
 [[package]]
@@ -5056,12 +5056,12 @@ dependencies = [
 
 [[package]]
 name = "prost"
-version = "0.13.3"
+version = "0.13.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7b0487d90e047de87f984913713b85c601c05609aad5b0df4b4573fbf69aa13f"
+checksum = "2796faa41db3ec313a31f7624d9286acf277b52de526150b7e69f3debf891ee5"
 dependencies = [
  "bytes",
- "prost-derive 0.13.3",
+ "prost-derive 0.13.5",
 ]
 
 [[package]]
@@ -5099,7 +5099,7 @@ dependencies = [
  "once_cell",
  "petgraph",
  "prettyplease",
- "prost 0.13.3",
+ "prost 0.13.5",
  "prost-types 0.13.3",
  "regex",
  "syn 2.0.100",
@@ -5121,9 +5121,9 @@ dependencies = [
 
 [[package]]
 name = "prost-derive"
-version = "0.13.3"
+version = "0.13.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e9552f850d5f0964a4e4d0bf306459ac29323ddfbae05e35a7c0d35cb0803cc5"
+checksum = "8a56d757972c98b346a9b766e3f02746cde6dd1cd1d1d563472929fdd74bec4d"
 dependencies = [
  "anyhow",
  "itertools 0.12.1",
@@ -5147,7 +5147,7 @@ version = "0.13.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4759aa0d3a6232fb8dbdb97b61de2c20047c68aca932c7ed76da9d788508d670"
 dependencies = [
- "prost 0.13.3",
+ "prost 0.13.5",
 ]
 
 [[package]]
@@ -5195,7 +5195,7 @@ dependencies = [
  "hyper 0.14.30",
  "hyper 1.4.1",
  "hyper-util",
- "indexmap 2.0.1",
+ "indexmap 2.9.0",
  "ipnet",
  "itertools 0.10.5",
  "itoa",
@@ -5229,7 +5229,7 @@ dependencies = [
  "rsa",
  "rstest",
  "rustc-hash 1.1.0",
- "rustls 0.23.18",
+ "rustls 0.23.27",
  "rustls-native-certs 0.8.0",
  "rustls-pemfile 2.1.1",
  "scopeguard",
@@ -5248,7 +5248,7 @@ dependencies = [
  "tokio",
  "tokio-postgres",
  "tokio-postgres2",
- "tokio-rustls 0.26.0",
+ "tokio-rustls 0.26.2",
  "tokio-tungstenite 0.21.0",
  "tokio-util",
  "tracing",
@@ -5472,13 +5472,13 @@ dependencies = [
  "num-bigint",
  "percent-encoding",
  "pin-project-lite",
- "rustls 0.23.18",
+ "rustls 0.23.27",
  "rustls-native-certs 0.8.0",
  "ryu",
  "sha1_smol",
  "socket2",
  "tokio",
- "tokio-rustls 0.26.0",
+ "tokio-rustls 0.26.2",
  "tokio-util",
  "url",
 ]
@@ -5926,15 +5926,15 @@ dependencies = [
 
 [[package]]
 name = "rustls"
-version = "0.23.18"
+version = "0.23.27"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9c9cc1d47e243d655ace55ed38201c19ae02c148ae56412ab8750e8f0166ab7f"
+checksum = "730944ca083c1c233a75c09f199e973ca499344a2b7ba9e755c457e86fb4a321"
 dependencies = [
  "log",
  "once_cell",
  "ring",
  "rustls-pki-types",
- "rustls-webpki 0.102.8",
+ "rustls-webpki 0.103.3",
  "subtle",
  "zeroize",
 ]
@@ -6023,6 +6023,17 @@ dependencies = [
  "untrusted",
 ]
 
+[[package]]
+name = "rustls-webpki"
+version = "0.103.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e4a72fe2bcf7a6ac6fd7d0b9e5cb68aeb7d4c0a0271730218b3e92d43b4eb435"
+dependencies = [
+ "ring",
+ "rustls-pki-types",
+ "untrusted",
+]
+
 [[package]]
 name = "rustversion"
 version = "1.0.12"
@@ -6074,7 +6085,7 @@ dependencies = [
  "regex",
  "remote_storage",
  "reqwest",
- "rustls 0.23.18",
+ "rustls 0.23.27",
  "safekeeper_api",
  "safekeeper_client",
  "scopeguard",
@@ -6091,7 +6102,7 @@ dependencies = [
  "tokio",
  "tokio-io-timeout",
  "tokio-postgres",
- "tokio-rustls 0.26.0",
+ "tokio-rustls 0.26.2",
  "tokio-stream",
  "tokio-tar",
  "tokio-util",
@@ -6263,7 +6274,7 @@ checksum = "255914a8e53822abd946e2ce8baa41d4cded6b8e938913b7f7b9da5b7ab44335"
 dependencies = [
  "httpdate",
  "reqwest",
- "rustls 0.23.18",
+ "rustls 0.23.27",
  "sentry-backtrace",
  "sentry-contexts",
  "sentry-core",
@@ -6692,11 +6703,11 @@ dependencies = [
  "metrics",
  "once_cell",
  "parking_lot 0.12.1",
- "prost 0.13.3",
- "rustls 0.23.18",
+ "prost 0.13.5",
+ "rustls 0.23.27",
  "tokio",
- "tokio-rustls 0.26.0",
- "tonic",
+ "tokio-rustls 0.26.2",
+ "tonic 0.13.1",
  "tonic-build",
  "tracing",
  "utils",
@@ -6738,7 +6749,7 @@ dependencies = [
  "regex",
  "reqwest",
  "routerify",
- "rustls 0.23.18",
+ "rustls 0.23.27",
  "rustls-native-certs 0.8.0",
  "safekeeper_api",
  "safekeeper_client",
@@ -6753,7 +6764,7 @@ dependencies = [
  "tokio",
  "tokio-postgres",
  "tokio-postgres-rustls",
- "tokio-rustls 0.26.0",
+ "tokio-rustls 0.26.2",
  "tokio-util",
  "tracing",
  "utils",
@@ -6791,7 +6802,7 @@ dependencies = [
  "postgres_ffi",
  "remote_storage",
  "reqwest",
- "rustls 0.23.18",
+ "rustls 0.23.27",
  "rustls-native-certs 0.8.0",
  "serde",
  "serde_json",
@@ -7325,10 +7336,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "04fb792ccd6bbcd4bba408eb8a292f70fc4a3589e5d793626f45190e6454b6ab"
 dependencies = [
  "ring",
- "rustls 0.23.18",
+ "rustls 0.23.27",
  "tokio",
  "tokio-postgres",
- "tokio-rustls 0.26.0",
+ "tokio-rustls 0.26.2",
  "x509-certificate",
 ]
 
@@ -7372,12 +7383,11 @@ dependencies = [
 
 [[package]]
 name = "tokio-rustls"
-version = "0.26.0"
+version = "0.26.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0c7bc40d0e5a97695bb96e27995cd3a08538541b0a846f65bba7a359f36700d4"
+checksum = "8e727b36a1a0e8b74c376ac2211e40c2c8af09fb4013c60d910495810f008e9b"
 dependencies = [
- "rustls 0.23.18",
- "rustls-pki-types",
+ "rustls 0.23.27",
  "tokio",
 ]
 
@@ -7475,7 +7485,7 @@ version = "0.22.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f21c7aaf97f1bd9ca9d4f9e73b0a6c74bd5afef56f2bc931943a6e1c37e04e38"
 dependencies = [
- "indexmap 2.0.1",
+ "indexmap 2.9.0",
  "serde",
  "serde_spanned",
  "toml_datetime",
@@ -7487,6 +7497,27 @@ name = "tonic"
 version = "0.12.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "877c5b330756d856ffcc4553ab34a5684481ade925ecc54bcd1bf02b1d0d4d52"
+dependencies = [
+ "async-trait",
+ "base64 0.22.1",
+ "bytes",
+ "http 1.1.0",
+ "http-body 1.0.0",
+ "http-body-util",
+ "percent-encoding",
+ "pin-project",
+ "prost 0.13.5",
+ "tokio-stream",
+ "tower-layer",
+ "tower-service",
+ "tracing",
+]
+
+[[package]]
+name = "tonic"
+version = "0.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7e581ba15a835f4d9ea06c55ab1bd4dce26fc53752c69a04aac00703bfb49ba9"
 dependencies = [
  "async-trait",
  "base64 0.22.1",
@@ -7499,13 +7530,12 @@ dependencies = [
  "hyper-util",
  "percent-encoding",
  "pin-project",
- "prost 0.13.3",
+ "prost 0.13.5",
  "rustls-native-certs 0.8.0",
- "rustls-pemfile 2.1.1",
  "tokio",
- "tokio-rustls 0.26.0",
+ "tokio-rustls 0.26.2",
  "tokio-stream",
- "tower 0.4.13",
+ "tower 0.5.2",
  "tower-layer",
  "tower-service",
  "tracing",
@@ -7513,9 +7543,9 @@ dependencies = [
 
 [[package]]
 name = "tonic-build"
-version = "0.12.3"
+version = "0.13.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9557ce109ea773b399c9b9e5dca39294110b74f1f342cb347a80d1fce8c26a11"
+checksum = "eac6f67be712d12f0b41328db3137e0d0757645d8904b4cb7d51cd9c2279e847"
 dependencies = [
  "prettyplease",
  "proc-macro2",
@@ -7533,16 +7563,11 @@ checksum = "b8fa9be0de6cf49e536ce1851f987bd21a43b771b09473c3549a6c853db37c1c"
 dependencies = [
  "futures-core",
  "futures-util",
- "indexmap 1.9.3",
  "pin-project",
  "pin-project-lite",
- "rand 0.8.5",
- "slab",
  "tokio",
- "tokio-util",
  "tower-layer",
  "tower-service",
- "tracing",
 ]
 
 [[package]]
@@ -7553,9 +7578,12 @@ checksum = "d039ad9159c98b70ecfd540b2573b97f7f52c3e8d9f8ad57a24b916a536975f9"
 dependencies = [
  "futures-core",
  "futures-util",
+ "indexmap 2.9.0",
  "pin-project-lite",
+ "slab",
  "sync_wrapper 1.0.1",
  "tokio",
+ "tokio-util",
  "tower-layer",
  "tower-service",
  "tracing",
@@ -7883,7 +7911,7 @@ dependencies = [
  "base64 0.22.1",
  "log",
  "once_cell",
- "rustls 0.23.18",
+ "rustls 0.23.27",
  "rustls-pki-types",
  "url",
  "webpki-roots",
@@ -8078,7 +8106,7 @@ dependencies = [
  "pageserver_api",
  "postgres_ffi",
  "pprof",
- "prost 0.13.3",
+ "prost 0.13.5",
  "remote_storage",
  "serde",
  "serde_json",
@@ -8534,8 +8562,7 @@ dependencies = [
  "hyper 0.14.30",
  "hyper 1.4.1",
  "hyper-util",
- "indexmap 1.9.3",
- "indexmap 2.0.1",
+ "indexmap 2.9.0",
  "itertools 0.12.1",
  "lazy_static",
  "libc",
@@ -8557,16 +8584,16 @@ dependencies = [
  "percent-encoding",
  "prettyplease",
  "proc-macro2",
- "prost 0.13.3",
+ "prost 0.13.5",
  "quote",
  "rand 0.8.5",
  "regex",
  "regex-automata 0.4.3",
  "regex-syntax 0.8.2",
  "reqwest",
- "rustls 0.23.18",
+ "rustls 0.23.27",
  "rustls-pki-types",
- "rustls-webpki 0.102.8",
+ "rustls-webpki 0.103.3",
  "scopeguard",
  "sec1 0.7.3",
  "serde",
@@ -8584,12 +8611,11 @@ dependencies = [
  "time",
  "time-macros",
  "tokio",
- "tokio-rustls 0.26.0",
+ "tokio-rustls 0.26.2",
  "tokio-stream",
  "tokio-util",
  "toml_edit",
- "tonic",
- "tower 0.4.13",
+ "tower 0.5.2",
  "tracing",
  "tracing-core",
  "tracing-log",

Cargo.toml

@@ -149,7 +149,7 @@ pin-project-lite = "0.2"
 pprof = { version = "0.14", features = ["criterion", "flamegraph", "frame-pointer", "prost-codec"] }
 procfs = "0.16"
 prometheus = {version = "0.13", default-features=false, features = ["process"]} # removes protobuf dependency
-prost = "0.13"
+prost = "0.13.5"
 rand = "0.8"
 redis = { version = "0.29.2", features = ["tokio-rustls-comp", "keep-alive"] }
 regex = "1.10.2"
@@ -199,7 +199,7 @@ tokio-tar = "0.3"
 tokio-util = { version = "0.7.10", features = ["io", "rt"] }
 toml = "0.8"
 toml_edit = "0.22"
-tonic = {version = "0.12.3", default-features = false, features = ["channel", "tls", "tls-roots"]}
+tonic = { version = "0.13.1", default-features = false, features = ["channel", "codegen", "prost", "tls-ring", "tls-native-roots"] }
 tower = { version = "0.5.2", default-features = false }
 tower-http = { version = "0.6.2", features = ["auth", "request-id", "trace"] }
 
@@ -280,7 +280,7 @@ criterion = "0.5.1"
 rcgen = "0.13"
 rstest = "0.18"
 camino-tempfile = "1.0.2"
-tonic-build = "0.12"
+tonic-build = "0.13.1"
 
 [patch.crates-io]
 

compute/compute-node.Dockerfile

@@ -582,6 +582,38 @@ RUN make -j $(getconf _NPROCESSORS_ONLN) && \
     make -j $(getconf _NPROCESSORS_ONLN) install && \
     echo 'trusted = true' >> /usr/local/pgsql/share/extension/hypopg.control
 
+#########################################################################################
+#
+# Layer "online_advisor-build"
+# compile online_advisor extension
+#
+#########################################################################################
+FROM build-deps AS online_advisor-src
+ARG PG_VERSION
+
+# online_advisor supports all Postgres version starting from PG14, but prior to PG17 has to be included in preload_shared_libraries
+# last release 1.0 - May 15, 2025
+WORKDIR /ext-src
+RUN case "${PG_VERSION:?}" in \
+    "v17") \
+        ;; \
+    *) \
+        echo "skipping the version of online_advistor for $PG_VERSION" && exit 0 \
+        ;; \
+    esac && \
+	wget https://github.com/knizhnik/online_advisor/archive/refs/tags/1.0.tar.gz -O online_advisor.tar.gz && \
+    echo "059b7d9e5a90013a58bdd22e9505b88406ce05790675eb2d8434e5b215652d54 online_advisor.tar.gz" | sha256sum --check && \
+    mkdir online_advisor-src && cd online_advisor-src && tar xzf ../online_advisor.tar.gz --strip-components=1 -C .
+
+FROM pg-build AS online_advisor-build
+COPY --from=online_advisor-src /ext-src/ /ext-src/
+WORKDIR /ext-src/
+RUN if [ -d online_advisor-src ]; then \
+	    cd online_advisor-src && \
+        make -j install && \
+        echo 'trusted = true' >> /usr/local/pgsql/share/extension/online_advisor.control; \
+    fi
+
 #########################################################################################
 #
 # Layer "pg_hashids-build"
@@ -1648,6 +1680,7 @@ COPY --from=pg_jsonschema-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=pg_graphql-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=pg_tiktoken-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=hypopg-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=online_advisor-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=pg_hashids-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=rum-build /usr/local/pgsql/ /usr/local/pgsql/
 COPY --from=pgtap-build /usr/local/pgsql/ /usr/local/pgsql/
@@ -1823,6 +1856,7 @@ COPY --from=pgjwt-src /ext-src/ /ext-src/
 COPY --from=pg_graphql-src /ext-src/ /ext-src/
 #COPY --from=pg_tiktoken-src /ext-src/ /ext-src/
 COPY --from=hypopg-src /ext-src/ /ext-src/
+COPY --from=online_advisor-src /ext-src/ /ext-src/
 COPY --from=pg_hashids-src /ext-src/ /ext-src/
 COPY --from=rum-src /ext-src/ /ext-src/
 COPY --from=pgtap-src /ext-src/ /ext-src/
@@ -1848,6 +1882,7 @@ COPY --from=pg_partman-src /ext-src/ /ext-src/
 #COPY --from=pg_mooncake-src /ext-src/ /ext-src/
 COPY --from=pg_repack-src /ext-src/ /ext-src/
 COPY --from=pg_repack-build /usr/local/pgsql/ /usr/local/pgsql/
+COPY --from=pg_duckdb-src /ext-src/ /ext-src/
 COPY compute/patches/pg_repack.patch /ext-src
 RUN cd /ext-src/pg_repack-src && patch -p1 </ext-src/pg_repack.patch && rm -f /ext-src/pg_repack.patch
 

compute_tools/src/rsyslog.rs

@@ -27,6 +27,40 @@ fn get_rsyslog_pid() -> Option<String> {
     }
 }
 
+fn wait_for_rsyslog_pid() -> Result<String, anyhow::Error> {
+    const MAX_WAIT: Duration = Duration::from_secs(5);
+    const INITIAL_SLEEP: Duration = Duration::from_millis(2);
+
+    let mut sleep_duration = INITIAL_SLEEP;
+    let start = std::time::Instant::now();
+    let mut attempts = 1;
+
+    for attempt in 1.. {
+        attempts = attempt;
+        match get_rsyslog_pid() {
+            Some(pid) => return Ok(pid),
+            None => {
+                if start.elapsed() >= MAX_WAIT {
+                    break;
+                }
+                info!(
+                    "rsyslogd is not running, attempt {}. Sleeping for {} ms",
+                    attempt,
+                    sleep_duration.as_millis()
+                );
+                std::thread::sleep(sleep_duration);
+                sleep_duration *= 2;
+            }
+        }
+    }
+
+    Err(anyhow::anyhow!(
+        "rsyslogd is not running after waiting for {} seconds and {} attempts",
+        attempts,
+        start.elapsed().as_secs()
+    ))
+}
+
 // Restart rsyslogd to apply the new configuration.
 // This is necessary, because there is no other way to reload the rsyslog configuration.
 //
@@ -36,14 +70,14 @@ fn get_rsyslog_pid() -> Option<String> {
 // TODO: test it properly
 //
 fn restart_rsyslog() -> Result<()> {
-    let old_pid = get_rsyslog_pid().context("rsyslogd is not running")?;
-    info!("rsyslogd is running with pid: {}, restart it", old_pid);
-
     // kill it to restart
     let _ = Command::new("pkill")
         .arg("rsyslogd")
         .output()
-        .context("Failed to stop rsyslogd")?;
+        .context("Failed to restart rsyslogd")?;
+
+    // ensure rsyslogd is running
+    wait_for_rsyslog_pid()?;
 
     Ok(())
 }
@@ -131,15 +165,11 @@ pub fn configure_postgres_logs_export(conf: PostgresLogsRsyslogConfig) -> Result
         return Ok(());
     }
 
-    // When new config is empty we can simply remove the configuration file.
+    // Nothing to configure
     if new_config.is_empty() {
-        info!("removing rsyslog config file: {}", POSTGRES_LOGS_CONF_PATH);
-        match std::fs::remove_file(POSTGRES_LOGS_CONF_PATH) {
-            Ok(_) => {}
-            Err(err) if err.kind() == ErrorKind::NotFound => {}
-            Err(err) => return Err(err.into()),
-        }
-        restart_rsyslog()?;
+        // When the configuration is removed, PostgreSQL will stop sending data
+        // to the files watched by rsyslog, so restarting rsyslog is more effort
+        // than just ignoring this change.
         return Ok(());
     }
 

pgxn/neon/communicator.c

@@ -717,7 +717,7 @@ prefetch_read(PrefetchRequest *slot)
 	Assert(slot->status == PRFS_REQUESTED);
 	Assert(slot->response == NULL);
 	Assert(slot->my_ring_index == MyPState->ring_receive);
-	Assert(readpage_reentrant_guard);
+	Assert(readpage_reentrant_guard || AmPrewarmWorker);
 
 	if (slot->status != PRFS_REQUESTED ||
 		slot->response != NULL ||
@@ -800,7 +800,7 @@ communicator_prefetch_receive(BufferTag tag)
 	PrfHashEntry *entry;
 	PrefetchRequest hashkey;
 
-	Assert(readpage_reentrant_guard);
+	Assert(readpage_reentrant_guard || AmPrewarmWorker); /* do not pump prefetch state in prewarm worker */
 	hashkey.buftag = tag;
 	entry = prfh_lookup(MyPState->prf_hash, &hashkey);
 	if (entry != NULL && prefetch_wait_for(entry->slot->my_ring_index))
@@ -2450,6 +2450,7 @@ void
 communicator_reconfigure_timeout_if_needed(void)
 {
 	bool	needs_set = MyPState->ring_receive != MyPState->ring_unused &&
+						!AmPrewarmWorker && /* do not pump prefetch state in prewarm worker */
 						readahead_getpage_pull_timeout_ms > 0;
 
 	if (needs_set != timeout_set)

pgxn/neon/file_cache.c

@@ -201,6 +201,8 @@ static shmem_request_hook_type prev_shmem_request_hook;
 bool lfc_store_prefetch_result;
 bool lfc_prewarm_update_ws_estimation;
 
+bool AmPrewarmWorker;
+
 #define LFC_ENABLED() (lfc_ctl->limit != 0)
 
 /*
@@ -845,6 +847,8 @@ lfc_prewarm_main(Datum main_arg)
 	PrewarmWorkerState* ws;
 	uint32 worker_id = DatumGetInt32(main_arg);
 
+	AmPrewarmWorker = true;
+
 	pqsignal(SIGTERM, die);
 	BackgroundWorkerUnblockSignals();
 

pgxn/neon/neon.h

@@ -23,6 +23,8 @@ extern int	wal_acceptor_connection_timeout;
 extern int	readahead_getpage_pull_timeout_ms;
 extern bool	disable_wal_prev_lsn_checks;
 
+extern bool AmPrewarmWorker;
+
 #if PG_MAJORVERSION_NUM >= 17
 extern uint32		WAIT_EVENT_NEON_LFC_MAINTENANCE;
 extern uint32		WAIT_EVENT_NEON_LFC_READ;

scripts/benchmark_durations.py

@@ -32,12 +32,6 @@ BENCHMARKS_DURATION_QUERY = """
 # the total duration varies from 8 to 40 minutes.
 # We use some pre-collected durations as a fallback to have a better distribution.
 FALLBACK_DURATION = {
-    "test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py::test_pageserver_max_throughput_getpage_at_latest_lsn[1-13-30]": 400.15,
-    "test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py::test_pageserver_max_throughput_getpage_at_latest_lsn[1-6-30]": 372.521,
-    "test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py::test_pageserver_max_throughput_getpage_at_latest_lsn[10-13-30]": 420.017,
-    "test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py::test_pageserver_max_throughput_getpage_at_latest_lsn[10-6-30]": 373.769,
-    "test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py::test_pageserver_max_throughput_getpage_at_latest_lsn[100-13-30]": 678.742,
-    "test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py::test_pageserver_max_throughput_getpage_at_latest_lsn[100-6-30]": 512.135,
     "test_runner/performance/test_branch_creation.py::test_branch_creation_heavy_write[20]": 58.036,
     "test_runner/performance/test_branch_creation.py::test_branch_creation_many_relations": 22.104,
     "test_runner/performance/test_branch_creation.py::test_branch_creation_many[1024]": 126.073,

storage_broker/src/bin/storage_broker.rs

@@ -17,12 +17,14 @@ use std::pin::Pin;
 use std::sync::Arc;
 use std::time::Duration;
 
+use bytes::Bytes;
 use camino::Utf8PathBuf;
 use clap::{Parser, command};
 use futures::future::OptionFuture;
 use futures_core::Stream;
 use futures_util::StreamExt;
-use http_body_util::Full;
+use http_body_util::combinators::BoxBody;
+use http_body_util::{Empty, Full};
 use http_utils::tls_certs::ReloadingCertificateResolver;
 use hyper::body::Incoming;
 use hyper::header::CONTENT_TYPE;
@@ -46,7 +48,6 @@ use tokio::net::TcpListener;
 use tokio::sync::broadcast;
 use tokio::sync::broadcast::error::RecvError;
 use tokio::time;
-use tonic::body::{self, BoxBody, empty_body};
 use tonic::codegen::Service;
 use tonic::{Code, Request, Response, Status};
 use tracing::*;
@@ -634,7 +635,7 @@ impl BrokerService for Broker {
 // We serve only metrics and healthcheck through http1.
 async fn http1_handler(
     req: hyper::Request<Incoming>,
-) -> Result<hyper::Response<BoxBody>, Infallible> {
+) -> Result<hyper::Response<BoxBody<Bytes, Infallible>>, Infallible> {
     let resp = match (req.method(), req.uri().path()) {
         (&Method::GET, "/metrics") => {
             let mut buffer = vec![];
@@ -645,16 +646,16 @@ async fn http1_handler(
             hyper::Response::builder()
                 .status(StatusCode::OK)
                 .header(CONTENT_TYPE, encoder.format_type())
-                .body(body::boxed(Full::new(bytes::Bytes::from(buffer))))
+                .body(BoxBody::new(Full::new(Bytes::from(buffer))))
                 .unwrap()
         }
         (&Method::GET, "/status") => hyper::Response::builder()
             .status(StatusCode::OK)
-            .body(empty_body())
+            .body(BoxBody::new(Empty::new()))
             .unwrap(),
         _ => hyper::Response::builder()
             .status(StatusCode::NOT_FOUND)
-            .body(empty_body())
+            .body(BoxBody::new(Empty::new()))
             .unwrap(),
     };
     Ok(resp)

test_runner/fixtures/neon_fixtures.py

@@ -682,7 +682,7 @@ class NeonEnvBuilder:
                 log.info(
                     f"Copying pageserver tenants directory {tenants_from_dir} to {tenants_to_dir}"
                 )
-                shutil.copytree(tenants_from_dir, tenants_to_dir)
+                subprocess.run(["cp", "-a", tenants_from_dir, tenants_to_dir], check=True)
             else:
                 log.info(
                     f"Creating overlayfs mount of pageserver tenants directory {tenants_from_dir} to {tenants_to_dir}"
@@ -698,8 +698,9 @@ class NeonEnvBuilder:
         shutil.rmtree(self.repo_dir / "local_fs_remote_storage", ignore_errors=True)
         if self.test_overlay_dir is None:
             log.info("Copying local_fs_remote_storage directory from snapshot")
-            shutil.copytree(
-                repo_dir / "local_fs_remote_storage", self.repo_dir / "local_fs_remote_storage"
+            subprocess.run(
+                ["cp", "-a", f"{repo_dir / 'local_fs_remote_storage'}", f"{self.repo_dir}"],
+                check=True,
             )
         else:
             log.info("Creating overlayfs mount of local_fs_remote_storage directory from snapshot")

test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py

@@ -14,7 +14,7 @@ from fixtures.neon_fixtures import (
     PgBin,
     wait_for_last_flush_lsn,
 )
-from fixtures.utils import get_scale_for_db, humantime_to_ms, skip_on_ci
+from fixtures.utils import get_scale_for_db, humantime_to_ms
 
 from performance.pageserver.util import setup_pageserver_with_tenants
 
@@ -36,9 +36,6 @@ if TYPE_CHECKING:
 @pytest.mark.parametrize("pgbench_scale", [get_scale_for_db(200)])
 @pytest.mark.parametrize("n_tenants", [500])
 @pytest.mark.timeout(10000)
-@skip_on_ci(
-    "This test needs lot of resources and should run on dedicated HW, not in github action runners as part of CI"
-)
 def test_pageserver_characterize_throughput_with_n_tenants(
     neon_env_builder: NeonEnvBuilder,
     zenbenchmark: NeonBenchmarker,
@@ -63,9 +60,6 @@ def test_pageserver_characterize_throughput_with_n_tenants(
 @pytest.mark.parametrize("n_clients", [1, 64])
 @pytest.mark.parametrize("n_tenants", [1])
 @pytest.mark.timeout(2400)
-@skip_on_ci(
-    "This test needs lot of resources and should run on dedicated HW, not in github action runners as part of CI"
-)
 def test_pageserver_characterize_latencies_with_1_client_and_throughput_with_many_clients_one_tenant(
     neon_env_builder: NeonEnvBuilder,
     zenbenchmark: NeonBenchmarker,

workspace_hack/Cargo.toml

@@ -53,8 +53,7 @@ hmac = { version = "0.12", default-features = false, features = ["reset"] }
 hyper-582f2526e08bb6a0 = { package = "hyper", version = "0.14", features = ["client", "http1", "http2", "runtime", "server", "stream"] }
 hyper-dff4ba8e3ae991db = { package = "hyper", version = "1", features = ["full"] }
 hyper-util = { version = "0.1", features = ["client-legacy", "http1", "http2", "server", "service"] }
-indexmap-dff4ba8e3ae991db = { package = "indexmap", version = "1", default-features = false, features = ["std"] }
-indexmap-f595c2ba2a3f28df = { package = "indexmap", version = "2", features = ["serde"] }
+indexmap = { version = "2", features = ["serde"] }
 itertools = { version = "0.12" }
 lazy_static = { version = "1", default-features = false, features = ["spin_no_std"] }
 libc = { version = "0.2", features = ["extra_traits", "use_std"] }
@@ -82,7 +81,7 @@ regex-syntax = { version = "0.8" }
 reqwest = { version = "0.12", default-features = false, features = ["blocking", "json", "rustls-tls", "rustls-tls-native-roots", "stream"] }
 rustls = { version = "0.23", default-features = false, features = ["logging", "ring", "std", "tls12"] }
 rustls-pki-types = { version = "1", features = ["std"] }
-rustls-webpki = { version = "0.102", default-features = false, features = ["ring", "std"] }
+rustls-webpki = { version = "0.103", default-features = false, features = ["ring", "std"] }
 scopeguard = { version = "1" }
 sec1 = { version = "0.7", features = ["pem", "serde", "std", "subtle"] }
 serde = { version = "1", features = ["alloc", "derive"] }
@@ -102,8 +101,7 @@ tokio-rustls = { version = "0.26", default-features = false, features = ["loggin
 tokio-stream = { version = "0.1" }
 tokio-util = { version = "0.7", features = ["codec", "compat", "io", "rt"] }
 toml_edit = { version = "0.22", features = ["serde"] }
-tonic = { version = "0.12", default-features = false, features = ["codegen", "prost", "tls-roots"] }
-tower = { version = "0.4", default-features = false, features = ["balance", "buffer", "limit", "util"] }
+tower = { version = "0.5", default-features = false, features = ["balance", "buffer", "limit", "log"] }
 tracing = { version = "0.1", features = ["log"] }
 tracing-core = { version = "0.1" }
 tracing-log = { version = "0.2" }
@@ -125,8 +123,7 @@ either = { version = "1" }
 getrandom = { version = "0.2", default-features = false, features = ["std"] }
 half = { version = "2", default-features = false, features = ["num-traits"] }
 hashbrown = { version = "0.14", features = ["raw"] }
-indexmap-dff4ba8e3ae991db = { package = "indexmap", version = "1", default-features = false, features = ["std"] }
-indexmap-f595c2ba2a3f28df = { package = "indexmap", version = "2", features = ["serde"] }
+indexmap = { version = "2", features = ["serde"] }
 itertools = { version = "0.12" }
 libc = { version = "0.2", features = ["extra_traits", "use_std"] }
 log = { version = "0.4", default-features = false, features = ["std"] }