Some benchmarks had errors
After merging your PR, Conbench analyzed the 6 benchmarking runs that have been run so far on merge-commit f7dc37f.
Benchmarks with errors
These are errors that were caught while running the benchmarks. You can click each link to go to the Conbench entry for that benchmark, which might have more information about what the error was.
- Commit Run on
ursa-i9-9960x
at 2024-02-10 12:20:04Z
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 2024-02-10 12:20:04Z - Commit Run on
arm64-m6g-linux-compute
at 2024-02-10 14:27:45Z - Commit Run on
ec2-m5-4xlarge-us-east-2
at 2024-02-10 12:49:51Z - Commit Run on
arm64-t4g-linux-compute
at 2024-02-10 14:40:31Z - Commit Run on
ec2-t3-xlarge-us-east-2
at 2024-02-10 12:24:57Z - Commit Run on
ursa-thinkcentre-m75q
at 2024-02-10 13:10:44Z
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-linux-compute
at 2024-02-10 14:40:31ZErrorSchemeNoErrorNoInline
(C++) with source=cpp-micro, suite=arrow-type-benchmarkErrorSchemeBoolNoInline
(C++) with source=cpp-micro, suite=arrow-type-benchmarkSchemaEqualsWithMetadata
(C++) with source=cpp-micro, suite=arrow-type-benchmarkErrorSchemeNoError
(C++) with source=cpp-micro, suite=arrow-type-benchmarkErrorSchemeExceptionNoInline
(C++) with source=cpp-micro, suite=arrow-type-benchmark
-
Commit Run on
ursa-thinkcentre-m75q
at 2024-02-10 13:10:44ZThreadPoolSpawn
(C++) with params=threads:8/task_cost:10000/real_time, source=cpp-micro, suite=arrow-thread-pool-benchmarkShortVectorInsertAtEnd
(C++) with params=<STATIC_VECTOR(int)>, source=cpp-micro, suite=arrow-small-vector-benchmarkThreadPoolSpawn
(C++) with params=threads:8/task_cost:100000/real_time, source=cpp-micro, suite=arrow-thread-pool-benchmark
Details
This report was generated using the lookback z-score method with a z-score threshold of 30.0.