Temporarily move macOS test on AArch64/ARM64 out of merge queue (ABLD-28 follow-up)

[rdesgroppes]

Motivation

Since #37676 got merged, jobs on macos:ventura-arm64 started queuing for 20+ minutes prior to start - or timing out.

Possible Drawbacks / Trade-offs

This is to be undone once enough macos:ventura-arm64 runners are provisioned, see: https://app.datadoghq.com/s/yB5yjZ/zdt-veh-nzp

[paulcacheux]

thanks !

[agent-platform-auto-pr]

Gitlab CI Configuration Changes

Modified Jobs

tests_macos_gitlab_arm64

  tests_macos_gitlab_arm64:
    after_script:
    - export VAULT_ADDR=https://vault.us1.ddbuild.io
    - vault login -method=aws -no-print
    - 'export PATH="$(pyenv root)/shims:$PATH"
  
      eval "$(pyenv init -)"
  
      eval "$(pyenv virtualenv-init -)"
  
      '
    - "if [ -n \"$PYTHON_VERSION\" ]; then\n  # 1. Use PYTHON_VERSION if set\n  if !\
      \ [[ \"$PYTHON_VERSION\" =~ ^[0-9]+\\.[0-9]+\\.[0-9]+$ ]]; then\n    echo \"Invalid\
      \ Python version format (should be X.Y.Z): $PYTHON_VERSION\" >& 2\n    exit 1\n\
      \  fi\n  if ! [ -d \"$(pyenv root)/versions/$PYTHON_VERSION\" ]; then\n    echo\
      \ \"Python version $PYTHON_VERSION not found. Installing...\"\n    pyenv install\
      \ \"$PYTHON_VERSION\"\n  fi\nelse\n  # 2. Find appropriate python version from\
      \ major version\n  PYTHON_VERSION=\"$(cat .python-version)\"\n  echo \"Find python\
      \ version matching $PYTHON_VERSION\"\n  PYTHON_VERSION_ESCAPED=\"${PYTHON_VERSION//./\\\
      \\.}\"\n  versionmatches=\"$(ls \"$(pyenv root)/versions\" | grep -E \"^${PYTHON_VERSION_ESCAPED}\\\
      \\.[0-9]+$\")\"\n  if [ -n \"$versionmatches\" ]; then\n    # 2.a.\n    echo \"\
      Found already existing python version for $PYTHON_VERSION\"\n  else\n    # 2.b.\n\
      \    echo \"Installing Python $PYTHON_VERSION...\"\n    pyenv install \"$PYTHON_VERSION\"\
      \n    versionmatches=\"$(ls \"$(pyenv root)/versions\" | grep -E \"^${PYTHON_VERSION_ESCAPED}\\\
      \\.[0-9]+$\")\"\n    if [ -z \"$versionmatches\" ]; then\n      echo \"No matching\
      \ Python version found for $PYTHON_VERSION even after installation.\" >& 2\n \
      \     exit 1\n    fi\n  fi\n  # If there are multiple matches, select the latest\
      \ one\n  PYTHON_VERSION=\"$(echo \"$versionmatches\" | sort -V | tail -n 1)\"\n\
      fi\nVENV_NAME=\"datadog-agent-python-$PYTHON_VERSION\"\nVENV_PATH=\"$(pyenv root)/versions/$VENV_NAME\"\
      \n"
    - echo "Using Python $PYTHON_VERSION..."
    - "# Check if the virtual environment directory exists\nif [ ! -d \"$VENV_PATH\"\
      \ ]; then\n  echo \"Creating virtual environment '$VENV_NAME'...\"\n  pyenv virtualenv\
      \ \"$PYTHON_VERSION\" \"$VENV_NAME\"\nelse\n  echo \"Virtual environment '$VENV_NAME'\
      \ already exists. Skipping creation.\"\nfi\n"
    - pyenv activate $VENV_NAME
    - $CI_PROJECT_DIR/tools/ci/junit_upload.sh
    - CODECOV_TOKEN=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $CODECOV token) || exit
      $?; export CODECOV_TOKEN
    - dda inv -- -e coverage.upload-to-codecov $COVERAGE_CACHE_FLAG || true
    artifacts:
      expire_in: 2 weeks
      paths:
      - $TEST_OUTPUT_FILE
      - junit-*.tgz
      reports:
        annotations:
        - $EXTERNAL_LINKS_PATH
        junit:
        - '**/junit-out-*.xml'
      when: always
    before_script:
    - export VAULT_ADDR=https://vault.us1.ddbuild.io
    - vault login -method=aws -no-print
    - export AWS_RETRY_MODE=standard
    - export AWS_RETRY_MAX_ATTEMPTS=5
    - 'eval $(gimme $(cat .go-version))
  
      export GOPATH=$GOROOT
  
      '
    - 'export PATH="$(pyenv root)/shims:$PATH"
  
      eval "$(pyenv init -)"
  
      eval "$(pyenv virtualenv-init -)"
  
      '
    - "if [ -n \"$PYTHON_VERSION\" ]; then\n  # 1. Use PYTHON_VERSION if set\n  if !\
      \ [[ \"$PYTHON_VERSION\" =~ ^[0-9]+\\.[0-9]+\\.[0-9]+$ ]]; then\n    echo \"Invalid\
      \ Python version format (should be X.Y.Z): $PYTHON_VERSION\" >& 2\n    exit 1\n\
      \  fi\n  if ! [ -d \"$(pyenv root)/versions/$PYTHON_VERSION\" ]; then\n    echo\
      \ \"Python version $PYTHON_VERSION not found. Installing...\"\n    pyenv install\
      \ \"$PYTHON_VERSION\"\n  fi\nelse\n  # 2. Find appropriate python version from\
      \ major version\n  PYTHON_VERSION=\"$(cat .python-version)\"\n  echo \"Find python\
      \ version matching $PYTHON_VERSION\"\n  PYTHON_VERSION_ESCAPED=\"${PYTHON_VERSION//./\\\
      \\.}\"\n  versionmatches=\"$(ls \"$(pyenv root)/versions\" | grep -E \"^${PYTHON_VERSION_ESCAPED}\\\
      \\.[0-9]+$\")\"\n  if [ -n \"$versionmatches\" ]; then\n    # 2.a.\n    echo \"\
      Found already existing python version for $PYTHON_VERSION\"\n  else\n    # 2.b.\n\
      \    echo \"Installing Python $PYTHON_VERSION...\"\n    pyenv install \"$PYTHON_VERSION\"\
      \n    versionmatches=\"$(ls \"$(pyenv root)/versions\" | grep -E \"^${PYTHON_VERSION_ESCAPED}\\\
      \\.[0-9]+$\")\"\n    if [ -z \"$versionmatches\" ]; then\n      echo \"No matching\
      \ Python version found for $PYTHON_VERSION even after installation.\" >& 2\n \
      \     exit 1\n    fi\n  fi\n  # If there are multiple matches, select the latest\
      \ one\n  PYTHON_VERSION=\"$(echo \"$versionmatches\" | sort -V | tail -n 1)\"\n\
      fi\nVENV_NAME=\"datadog-agent-python-$PYTHON_VERSION\"\nVENV_PATH=\"$(pyenv root)/versions/$VENV_NAME\"\
      \n"
    - echo "Using Python $PYTHON_VERSION..."
    - "# Check if the virtual environment directory exists\nif [ ! -d \"$VENV_PATH\"\
      \ ]; then\n  echo \"Creating virtual environment '$VENV_NAME'...\"\n  pyenv virtualenv\
      \ \"$PYTHON_VERSION\" \"$VENV_NAME\"\nelse\n  echo \"Virtual environment '$VENV_NAME'\
      \ already exists. Skipping creation.\"\nfi\n"
    - pyenv activate $VENV_NAME
    - python3 -m pip install "git+https://github.com/DataDog/datadog-agent-dev.git@v$(cat
      .dda/version)" --break-system-packages
    - pyenv rehash
    - python3 -m dda self dep sync -f legacy-tasks
    - pyenv rehash
    - DD_API_KEY="$("$CI_PROJECT_DIR"/tools/ci/fetch_secret.sh "$AGENT_API_KEY_ORG2"
      token)" || exit $?; export DD_API_KEY
    - DD_APP_KEY="$("$CI_PROJECT_DIR"/tools/ci/fetch_secret.sh "$AGENT_APP_KEY_ORG2"
      token)" || exit $?; export DD_APP_KEY
    - "if [ \"$CI_COMMIT_BRANCH\" = \"main\" ] || [[ \"$CI_COMMIT_BRANCH\" =~ ^[0-9]+\\\
      .[0-9]+\\.(x|[0-9]+)$ ]]; then\n  dda inv -- -e macos.report-versions -l all ||\
      \ true\nfi\n"
    - "if [ \"$((RANDOM%20))\" -eq 0 ]; then\n  echo Trying to remove inactive versions\n\
      \  dda inv -- -e macos.remove-inactive-versions -l python -t \"$PYTHON_VERSION\"\
      \ || true\n  dda inv -- -e macos.remove-inactive-versions -l go -t \"$(cat .go-version)\"\
      \ || true\nfi\n"
    - dda inv -- -e rtloader.make
    - dda inv -- -e rtloader.install
    - dda inv -- -e install-tools
    needs:
    - go_deps
    - go_tools_deps
    rules:
+   - if: $CI_COMMIT_BRANCH =~ /^mq-working-branch-/
+     when: never
    - if: $RUN_UNIT_TESTS == "off"
      when: never
    - if: $CI_COMMIT_BRANCH == "main"
      variables:
        COVERAGE_CACHE_FLAG: --push-coverage-cache
        FAST_TESTS: 'false'
    - if: $CI_COMMIT_BRANCH =~ /^[0-9]+\.[0-9]+\.x$/
      variables:
        COVERAGE_CACHE_FLAG: ''
        FAST_TESTS: 'false'
    - if: $CI_COMMIT_TAG != null
      variables:
        COVERAGE_CACHE_FLAG: ''
        FAST_TESTS: 'false'
    - if: $CI_PIPELINE_SOURCE == "trigger" || $CI_PIPELINE_SOURCE == "pipeline"
      variables:
        COVERAGE_CACHE_FLAG: ''
        FAST_TESTS: 'false'
    - if: $RUN_UNIT_TESTS == "on"
      variables:
        COVERAGE_CACHE_FLAG: ''
        FAST_TESTS: 'false'
    - variables:
        COVERAGE_CACHE_FLAG: --pull-coverage-cache
        FAST_TESTS: 'true'
    script:
    - mkdir -p $GOPATH/pkg/mod/cache && tar xJf modcache.tar.xz -C $GOPATH/pkg/mod/cache
      || exit 101
    - rm -f modcache.tar.xz
    - mkdir -p $GOPATH/pkg/mod/cache && tar xJf modcache_tools.tar.xz -C $GOPATH/pkg/mod/cache
      || exit 101
    - rm -f modcache_tools.tar.xz
    - dda inv -- -e gitlab.generate-ci-visibility-links --output=$EXTERNAL_LINKS_PATH
    - FAST_TESTS_FLAG=""
    - if [[ "$FAST_TESTS" == "true" ]]; then FAST_TESTS_FLAG="--only-impacted-packages";
      fi
    - dda inv -- -e test --rerun-fails=2 --race --profile --cpus 12 --result-json $TEST_OUTPUT_FILE
      --junit-tar "junit-${CI_JOB_NAME}.tgz" $FAST_TESTS_FLAG --test-washer --coverage
    - dda inv -- -e invoke-unit-tests
    stage: source_test
    tags:
    - macos:ventura-arm64
    - specific:true
    variables:
      FLAKY_PATTERNS_CONFIG: $CI_PROJECT_DIR/flaky-patterns-runtime.yaml
      TEST_OUTPUT_FILE: test_output.json

Changes Summary

Removed	Modified	Added	Renamed
0	1	0	0

ℹ️ Diff available in the job log.

[cit-pr-commenter]

Regression Detector

Regression Detector Results

Metrics dashboard
Target profiles
Run ID: d7b61939-f210-4cf6-bcd6-9830f4fca221

Baseline: a980511
Comparison: 1752068
Diff

Optimization Goals: ✅ No significant changes detected

Experiments ignored for regressions

Regressions in experiments with settings containing erratic: true are ignored.

perf	experiment	goal	Δ mean %	Δ mean % CI	trials	links
➖	docker_containers_cpu	% cpu utilization	+2.19	[-0.95, +5.33]	1	Logs

Fine details of change detection per experiment

perf	experiment	goal	Δ mean %	Δ mean % CI	trials	links
➖	quality_gate_logs	% cpu utilization	+4.04	[+1.20, +6.88]	1	Logs bounds checks dashboard
➖	docker_containers_cpu	% cpu utilization	+2.19	[-0.95, +5.33]	1	Logs
➖	quality_gate_metrics_logs	memory utilization	+2.06	[+1.67, +2.46]	1	Logs bounds checks dashboard
➖	otlp_ingest_metrics	memory utilization	+0.36	[+0.21, +0.50]	1	Logs
➖	docker_containers_memory	memory utilization	+0.20	[+0.13, +0.26]	1	Logs
➖	file_to_blackhole_500ms_latency	egress throughput	+0.13	[-0.50, +0.76]	1	Logs
➖	file_to_blackhole_100ms_latency	egress throughput	+0.05	[-0.56, +0.67]	1	Logs
➖	file_to_blackhole_1000ms_latency	egress throughput	+0.04	[-0.58, +0.66]	1	Logs
➖	file_to_blackhole_0ms_latency	egress throughput	-0.00	[-0.58, +0.57]	1	Logs
➖	tcp_dd_logs_filter_exclude	ingress throughput	-0.00	[-0.02, +0.02]	1	Logs
➖	uds_dogstatsd_to_api	ingress throughput	-0.00	[-0.30, +0.29]	1	Logs
➖	quality_gate_idle_all_features	memory utilization	-0.03	[-0.07, +0.00]	1	Logs bounds checks dashboard
➖	ddot_logs	memory utilization	-0.08	[-0.17, +0.02]	1	Logs
➖	file_tree	memory utilization	-0.08	[-0.12, -0.04]	1	Logs
➖	quality_gate_idle	memory utilization	-0.27	[-0.34, -0.19]	1	Logs bounds checks dashboard
➖	uds_dogstatsd_20mb_12k_contexts_20_senders	memory utilization	-0.31	[-0.35, -0.27]	1	Logs
➖	tcp_syslog_to_blackhole	ingress throughput	-0.31	[-0.37, -0.25]	1	Logs
➖	otlp_ingest_logs	memory utilization	-0.31	[-0.43, -0.19]	1	Logs
➖	ddot_metrics	memory utilization	-0.35	[-0.46, -0.23]	1	Logs

Bounds Checks: ✅ Passed

perf	experiment	bounds_check_name	replicates_passed	links
✅	docker_containers_cpu	simple_check_run	10/10
✅	docker_containers_memory	memory_usage	10/10
✅	docker_containers_memory	simple_check_run	10/10
✅	file_to_blackhole_0ms_latency	lost_bytes	10/10
✅	file_to_blackhole_0ms_latency	memory_usage	10/10
✅	file_to_blackhole_1000ms_latency	memory_usage	10/10
✅	file_to_blackhole_100ms_latency	lost_bytes	10/10
✅	file_to_blackhole_100ms_latency	memory_usage	10/10
✅	file_to_blackhole_500ms_latency	lost_bytes	10/10
✅	file_to_blackhole_500ms_latency	memory_usage	10/10
✅	quality_gate_idle	intake_connections	10/10	bounds checks dashboard
✅	quality_gate_idle	memory_usage	10/10	bounds checks dashboard
✅	quality_gate_idle_all_features	intake_connections	10/10	bounds checks dashboard
✅	quality_gate_idle_all_features	memory_usage	10/10	bounds checks dashboard
✅	quality_gate_logs	intake_connections	10/10	bounds checks dashboard
✅	quality_gate_logs	lost_bytes	10/10	bounds checks dashboard
✅	quality_gate_logs	memory_usage	10/10	bounds checks dashboard
✅	quality_gate_metrics_logs	cpu_usage	10/10	bounds checks dashboard
✅	quality_gate_metrics_logs	intake_connections	10/10	bounds checks dashboard
✅	quality_gate_metrics_logs	lost_bytes	10/10	bounds checks dashboard
✅	quality_gate_metrics_logs	memory_usage	10/10	bounds checks dashboard

Explanation

Confidence level: 90.00%
Effect size tolerance: |Δ mean %| ≥ 5.00%

Performance changes are noted in the perf column of each table:

• ✅ = significantly better comparison variant performance
• ❌ = significantly worse comparison variant performance
• ➖ = no significant change in performance

A regression test is an A/B test of target performance in a repeatable rig, where "performance" is measured as "comparison variant minus baseline variant" for an optimization goal (e.g., ingress throughput). Due to intrinsic variability in measuring that goal, we can only estimate its mean value for each experiment; we report uncertainty in that value as a 90.00% confidence interval denoted "Δ mean % CI".

For each experiment, we decide whether a change in performance is a "regression" -- a change worth investigating further -- if all of the following criteria are true:

1. Its estimated |Δ mean %| ≥ 5.00%, indicating the change is big enough to merit a closer look.

2. Its 90.00% confidence interval "Δ mean % CI" does not contain zero, indicating that if our statistical model is accurate, there is at least a 90.00% chance there is a difference in performance between baseline and comparison variants.

3. Its configuration does not mark it "erratic".

CI Pass/Fail Decision

✅ Passed. All Quality Gates passed.

• quality_gate_logs, bounds check lost_bytes: 10/10 replicas passed. Gate passed.
• quality_gate_logs, bounds check memory_usage: 10/10 replicas passed. Gate passed.
• quality_gate_logs, bounds check intake_connections: 10/10 replicas passed. Gate passed.
• quality_gate_idle, bounds check intake_connections: 10/10 replicas passed. Gate passed.
• quality_gate_idle, bounds check memory_usage: 10/10 replicas passed. Gate passed.
• quality_gate_metrics_logs, bounds check memory_usage: 10/10 replicas passed. Gate passed.
• quality_gate_metrics_logs, bounds check intake_connections: 10/10 replicas passed. Gate passed.
• quality_gate_metrics_logs, bounds check cpu_usage: 10/10 replicas passed. Gate passed.
• quality_gate_metrics_logs, bounds check lost_bytes: 10/10 replicas passed. Gate passed.
• quality_gate_idle_all_features, bounds check memory_usage: 10/10 replicas passed. Gate passed.
• quality_gate_idle_all_features, bounds check intake_connections: 10/10 replicas passed. Gate passed.

[agent-platform-auto-pr]

Static quality checks

✅ Please find below the results from static quality gates
Comparison made with ancestor 124e8e9

Successful checks

Info

	Quality gate	Delta	On disk size (MiB)	Delta	On wire size (MiB)
✅	agent_deb_amd64	$${0}$$	$${704.71}$$ < $${704.84}$$	$${-0.03}$$	$${177.87}$$ < $${178.58}$$
✅	agent_deb_amd64_fips	$${0}$$	$${702.96}$$ < $${703.09}$$	$${-0.03}$$	$${177.33}$$ < $${178.12}$$
✅	agent_heroku_amd64	$${0}$$	$${354.62}$$ < $${355.37}$$	$${+0}$$	$${94.86}$$ < $${95.72}$$
✅	agent_msi	$${0}$$	$${979.37}$$ < $${979.61}$$	$${+0.01}$$	$${148.65}$$ < $${149.31}$$
✅	agent_rpm_amd64	$${0}$$	$${704.69}$$ < $${704.83}$$	$${+0.02}$$	$${179.58}$$ < $${180.22}$$
✅	agent_rpm_amd64_fips	$${0}$$	$${702.95}$$ < $${703.08}$$	$${-0.04}$$	$${179.15}$$ < $${179.85}$$
✅	agent_rpm_arm64	$${0}$$	$${694.5}$$ < $${694.74}$$	$${+0.01}$$	$${163.29}$$ < $${163.96}$$
✅	agent_rpm_arm64_fips	$${0}$$	$${692.81}$$ < $${693.05}$$	$${-0.03}$$	$${162.2}$$ < $${163.0}$$
✅	agent_suse_amd64	$${0}$$	$${704.69}$$ < $${704.83}$$	$${+0.02}$$	$${179.58}$$ < $${180.22}$$
✅	agent_suse_amd64_fips	$${0}$$	$${702.95}$$ < $${703.08}$$	$${-0.04}$$	$${179.15}$$ < $${179.85}$$
✅	agent_suse_arm64	$${0}$$	$${694.5}$$ < $${694.74}$$	$${+0.01}$$	$${163.29}$$ < $${163.96}$$
✅	agent_suse_arm64_fips	$${0}$$	$${692.81}$$ < $${693.05}$$	$${-0.03}$$	$${162.2}$$ < $${163.0}$$
✅	docker_agent_amd64	$${+0}$$	$${788.45}$$ < $${788.65}$$	$${+0}$$	$${271.36}$$ < $${272.01}$$
✅	docker_agent_arm64	$${-0}$$	$${801.77}$$ < $${802.0}$$	$${+0}$$	$${258.99}$$ < $${259.7}$$
✅	docker_agent_jmx_amd64	$${-0}$$	$${979.7}$$ < $${979.84}$$	$${-0}$$	$${340.38}$$ < $${340.95}$$
✅	docker_agent_jmx_arm64	$${-0}$$	$${981.61}$$ < $${981.8}$$	$${+0}$$	$${323.99}$$ < $${324.65}$$
✅	docker_cluster_agent_amd64	$${0}$$	$${213.91}$$ < $${214.5}$$	$${-0}$$	$${72.72}$$ < $${73.51}$$
✅	docker_cluster_agent_arm64	$${0}$$	$${229.75}$$ < $${230.33}$$	$${-0}$$	$${68.97}$$ < $${69.77}$$
✅	docker_cws_instrumentation_amd64	$${0}$$	$${7.07}$$ < $${7.12}$$	$${+0}$$	$${2.95}$$ < $${3.29}$$
✅	docker_cws_instrumentation_arm64	$${-0}$$	$${6.69}$$ < $${6.92}$$	$${-0}$$	$${2.7}$$ < $${3.07}$$
✅	docker_dogstatsd_amd64	$${0}$$	$${38.55}$$ < $${39.57}$$	$${+0}$$	$${14.88}$$ < $${15.76}$$
✅	docker_dogstatsd_arm64	$${0}$$	$${37.23}$$ < $${38.2}$$	$${-0}$$	$${14.33}$$ < $${14.83}$$
✅	dogstatsd_deb_amd64	$${0}$$	$${29.79}$$ < $${31.4}$$	$${-0}$$	$${7.85}$$ < $${8.95}$$
✅	dogstatsd_deb_arm64	$${0}$$	$${28.39}$$ < $${29.97}$$	$${-0}$$	$${6.81}$$ < $${7.89}$$
✅	dogstatsd_rpm_amd64	$${0}$$	$${29.79}$$ < $${31.4}$$	$${+0}$$	$${7.86}$$ < $${8.96}$$
✅	dogstatsd_suse_amd64	$${0}$$	$${29.79}$$ < $${31.4}$$	$${+0}$$	$${7.86}$$ < $${8.96}$$
✅	iot_agent_deb_amd64	$${0}$$	$${54.06}$$ < $${54.55}$$	$${-0}$$	$${13.62}$$ < $${14.45}$$
✅	iot_agent_deb_arm64	$${0}$$	$${51.38}$$ < $${51.9}$$	$${+0}$$	$${11.79}$$ < $${12.63}$$
✅	iot_agent_deb_armhf	$${0}$$	$${50.9}$$ < $${51.42}$$	$${+0.03}$$	$${11.9}$$ < $${12.74}$$
✅	iot_agent_rpm_amd64	$${0}$$	$${54.06}$$ < $${54.55}$$	$${-0}$$	$${13.65}$$ < $${14.47}$$
✅	iot_agent_rpm_arm64	$${0}$$	$${51.38}$$ < $${51.91}$$	$${+0}$$	$${11.81}$$ < $${12.65}$$
✅	iot_agent_suse_amd64	$${0}$$	$${54.06}$$ < $${54.55}$$	$${-0}$$	$${13.65}$$ < $${14.47}$$

[chouetz]

Can you put this rule on top, as the first match is the most important

[rdesgroppes]

Thanks, @chouetz, I took your comment into consideration when moving the workaround from the build to the test job.