After merging your PR, Conbench analyzed the 5 benchmarking runs that have been run so far on merge-commit b30d961.

Benchmarks with performance regressions

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

All benchmark runs analyzed:

• Commit Run on ec2-t3-xlarge-us-east-2 at 2023-10-06 12:26:17Z
• Commit Run on arm64-t4g-linux-compute at 2023-10-06 15:05:48Z
• Commit Run on ec2-m5-4xlarge-us-east-2 at 2023-10-06 15:14:23Z
• Commit Run on arm64-m6g-linux-compute at 2023-10-07 05:48:18Z
• Commit Run on ursa-thinkcentre-m75q at 2023-10-07 22:10:04Z

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 ursa-thinkcentre-m75q at 2023-10-07 22:10:04Z
  • WriteCsvNumericCheckQuote (C++) with params=1, source=cpp-micro, suite=arrow-csv-writer-benchmark
  • BM_ByteStreamSplitEncode_Float_Sse2 (C++) with params=32768, source=cpp-micro, suite=parquet-encoding-benchmark
  • WriteCsvNumericCheckQuote (C++) with params=0, source=cpp-micro, suite=arrow-csv-writer-benchmark
  • setWithWriter (Java) with source=java-micro, suite=arrow.vector.IntBenchmarks
  • WriteCsvNumeric (C++) with params=1, source=cpp-micro, suite=arrow-csv-writer-benchmark
  • WriteCsvNumeric (C++) with params=0, source=cpp-micro, suite=arrow-csv-writer-benchmark