After merging your PR, Conbench analyzed the 6 benchmarking runs that have been run so far on merge-commit 2abb3fb.

Benchmarks with performance regressions

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

All benchmark runs analyzed:

• Commit Run on ursa-i9-9960x at 2023-12-22 03:18:24Z
• Commit Run on ec2-m5-4xlarge-us-east-2 at 2023-12-21 23:03:24Z
• Commit Run on ec2-t3-xlarge-us-east-2 at 2023-12-21 23:42:06Z
• Commit Run on arm64-t4g-linux-compute at 2023-12-21 23:53:52Z
• Commit Run on arm64-m6g-linux-compute at 2023-12-22 01:12:11Z
• Commit Run on ursa-thinkcentre-m75q at 2023-12-22 10:55:31Z

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-m6g-linux-compute at 2023-12-22 01:12:11Z
  • BM_ByteStreamSplitDecode_Float_Scalar (C++) with params=65536, source=cpp-micro, suite=parquet-encoding-benchmark
  • ReadUncachedFileAsync (C++) with params=num_cols:8/is_partial:0/real_time, source=cpp-micro, suite=arrow-ipc-read-write-benchmark