diff --git a/.github/workflows/bench.yml b/.github/workflows/bench.yml index 6a46e9120c..d3482f22e0 100644 --- a/.github/workflows/bench.yml +++ b/.github/workflows/bench.yml @@ -245,6 +245,12 @@ jobs: continue-on-error: true run: | set -o pipefail + # The t-test compares a run with the last 30 runs of its branch, not + # all history. Without a window, a correct step change (#445's + # predicate_pushdown, #476's checkpoint and wal_replay fixtures) kept + # alerting for weeks; with 30, a lasting change alerts on about five + # runs (enough for the two-in-a-row issue below), then becomes the + # baseline. # A branch other than main starts from main's history and thresholds. start_point=() if [ "$BENCH_REF" != main ]; then @@ -258,6 +264,7 @@ jobs: --testbed ubuntu-latest \ --threshold-measure latency \ --threshold-test t_test \ + --threshold-max-sample-size 30 \ --threshold-upper-boundary ${{ matrix.threshold }} \ --err \ --adapter rust_criterion \