After merging your PR, Conbench analyzed the 4 benchmarking runs that have been run so far on merge-commit 7df396e.

Benchmarks with performance regressions

There were 0 possible performance regressions, according to the lookback z-score method.

All benchmark runs analyzed:

• Commit Run on amd64-c6a-4xlarge-linux at 2025-04-04 03:30:55Z
• Commit Run on arm64-t4g-2xlarge-linux at 2025-04-04 04:57:24Z
• Commit Run on amd64-m5-4xlarge-linux at 2025-04-04 08:23:53Z
• Commit Run on test-mac-arm at 2025-04-04 03:58:35Z

Unstable benchmarks with performance regressions

The following benchmark results indicate a possible performance regression, but are known to sometimes produce false positives when applying the lookback z-score analysis.

• Commit Run on arm64-t4g-2xlarge-linux at 2025-04-04 04:57:24Z

  • FilterInt64FilterWithNulls (C++) with params=1048576/13, source=cpp-micro, suite=arrow-compute-vector-selection-benchmark
  • ConstructFromShortStdVector (C++) with params=<SMALL_VECTOR(std::string)>, source=cpp-micro, suite=arrow-small-vector-benchmark

• Commit Run on amd64-m5-4xlarge-linux at 2025-04-04 08:23:53Z

  • ShortVectorPushBack (C++) with params=<STD_VECTOR(int)>, source=cpp-micro, suite=arrow-small-vector-benchmark
  • ShortVectorInsert (C++) with params=<STD_VECTOR(int)>, source=cpp-micro, suite=arrow-small-vector-benchmark
  • LongVectorInsertAtEnd (C++) with params=<STD_VECTOR(int)>, source=cpp-micro, suite=arrow-small-vector-benchmark
  • ShortVectorInsertAtEnd (C++) with params=<STD_VECTOR(int)>, source=cpp-micro, suite=arrow-small-vector-benchmark