diff --git a/.github/actionlint.yml b/.github/actionlint.yml index b7e0be761a..3142a36fa0 100644 --- a/.github/actionlint.yml +++ b/.github/actionlint.yml @@ -7,6 +7,7 @@ self-hosted-runner: - small-metal - small-arm64 - unit-perf + - unit-perf-aws-arm - us-east-2 config-variables: - AWS_ECR_REGION diff --git a/.github/workflows/build_and_test.yml b/.github/workflows/build_and_test.yml index 456c7b8c92..0ceaa96fb0 100644 --- a/.github/workflows/build_and_test.yml +++ b/.github/workflows/build_and_test.yml @@ -306,14 +306,14 @@ jobs: statuses: write contents: write pull-requests: write - runs-on: [ self-hosted, unit-perf ] + runs-on: [ self-hosted, unit-perf-aws-arm ] container: image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm credentials: username: ${{ github.actor }} password: ${{ secrets.GITHUB_TOKEN }} # for changed limits, see comments on `options:` earlier in this file - options: --init --shm-size=512mb --ulimit memlock=67108864:67108864 + options: --init --shm-size=512mb --ulimit memlock=67108864:67108864 --ulimit nofile=65536:65536 --security-opt seccomp=unconfined strategy: fail-fast: false matrix: diff --git a/.github/workflows/periodic_pagebench.yml b/.github/workflows/periodic_pagebench.yml index 317db94052..728a6d4956 100644 --- a/.github/workflows/periodic_pagebench.yml +++ b/.github/workflows/periodic_pagebench.yml @@ -1,4 +1,4 @@ -name: Periodic pagebench performance test on unit-perf hetzner runner +name: Periodic pagebench performance test on unit-perf-aws-arm runners on: schedule: @@ -40,7 +40,7 @@ jobs: statuses: write contents: write pull-requests: write - runs-on: [ self-hosted, unit-perf ] + runs-on: [ self-hosted, unit-perf-aws-arm ] container: image: ghcr.io/neondatabase/build-tools:pinned-bookworm credentials: diff --git a/.github/workflows/proxy-benchmark.yml b/.github/workflows/proxy-benchmark.yml index 3a98ad4e8e..0ae93ce295 100644 --- a/.github/workflows/proxy-benchmark.yml +++ b/.github/workflows/proxy-benchmark.yml @@ -1,4 +1,4 @@ -name: Periodic proxy performance test on unit-perf hetzner runner +name: Periodic proxy performance test on unit-perf-aws-arm runners on: push: # TODO: remove after testing @@ -32,7 +32,7 @@ jobs: statuses: write contents: write pull-requests: write - runs-on: [self-hosted, unit-perf] + runs-on: [self-hosted, unit-perf-aws-arm] timeout-minutes: 60 # 1h timeout container: image: ghcr.io/neondatabase/build-tools:pinned-bookworm diff --git a/test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py b/test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py index 41696bf887..68bfa81b25 100644 --- a/test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py +++ b/test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py @@ -55,9 +55,10 @@ def test_pageserver_characterize_throughput_with_n_tenants( @pytest.mark.parametrize("duration", [20 * 60]) @pytest.mark.parametrize("pgbench_scale", [get_scale_for_db(2048)]) # we use 1 client to characterize latencies, and 64 clients to characterize throughput/scalability -# we use 64 clients because typically for a high number of connections we recommend the connection pooler -# which by default uses 64 connections -@pytest.mark.parametrize("n_clients", [1, 64]) +# we use 8 clients because we see a latency knee around 6-8 clients on im4gn.2xlarge instance type, +# which we use for this periodic test - at a cpu utilization of around 70 % - which is considered +# a good utilization for pageserver. +@pytest.mark.parametrize("n_clients", [1, 8]) @pytest.mark.parametrize("n_tenants", [1]) @pytest.mark.timeout(2400) def test_pageserver_characterize_latencies_with_1_client_and_throughput_with_many_clients_one_tenant(