Thanks for your patience. Conbench analyzed the 4 benchmarking runs that have been run so far on PR commit caeec86.

Benchmarks with performance regressions

There were 3 possible performance regressions, according to the lookback z-score method.

Benchmarks with regressions:

• Pull Request Run on arm64-t4g-2xlarge-linux at 2025-09-16 11:08:20Z

  • ChunkedArrayRankInt64Narrow (C++) with params=65536/100/tiebreaker:2, source=cpp-micro, suite=arrow-compute-vector-sort-benchmark
  • CompressedInputStreamZeroCopyBufferReturnedByCallee (C++) with params=Compression::LZ4_FRAME/num_bytes:1048576/batch_size:1048576, source=cpp-micro, suite=arrow-io-compressed-benchmark

• Pull Request Run on amd64-m5-4xlarge-linux at 2025-09-16 11:00:12Z

  • GrouperWithMultiTypes (C++) with params="{utf8}"/4096/2, source=cpp-micro, suite=arrow-compute-grouper-benchmark

All benchmark runs analyzed:

• Pull Request Run on arm64-t4g-2xlarge-linux at 2025-09-16 11:08:20Z
• Pull Request Run on amd64-m5-4xlarge-linux at 2025-09-16 11:00:12Z
• Pull Request Run on amd64-c6a-4xlarge-linux at 2025-09-16 10:46:19Z
• Pull Request Run on test-mac-arm at 2025-09-16 11:11:20Z