After merging your PR, Conbench analyzed the 4 benchmarking runs that have been run so far on merge-commit 9cafbb2.

Benchmarks with performance regressions

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

All benchmark runs analyzed:

• Commit Run on arm64-t4g-2xlarge-linux at 2024-09-02 20:57:11Z
• Commit Run on amd64-c6a-4xlarge-linux at 2024-09-02 17:46:04Z
• Commit Run on amd64-m5-4xlarge-linux at 2024-09-02 18:02:35Z
• Commit Run on test-mac-arm at 2024-09-03 00:29:51Z

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 amd64-c6a-4xlarge-linux at 2024-09-02 17:46:04Z

  • BM_RleEncoding (C++) with params=65536/8, source=cpp-micro, suite=parquet-column-io-benchmark
  • BM_RleEncoding (C++) with params=32768/8, source=cpp-micro, suite=parquet-column-io-benchmark
  • BM_RleEncoding (C++) with params=1024/8, source=cpp-micro, suite=parquet-column-io-benchmark
  • BM_RleEncoding (C++) with params=4096/8, source=cpp-micro, suite=parquet-column-io-benchmark

• Commit Run on test-mac-arm at 2024-09-03 00:29:51Z

  • TypeEqualsSimple (C++) with source=cpp-micro, suite=arrow-type-benchmark
  • IntegerParsing (C++) with params=, source=cpp-micro, suite=arrow-value-parsing-benchmark
  • TypeEqualsComplex (C++) with source=cpp-micro, suite=arrow-type-benchmark