Skip to content

distinct_query_sql benchmark is failing #15213

@Omega359

Description

@Omega359

Describe the bug

Benchmarking custom-measurement-time/distinct_group_by_u64_narrow_limit_10: Warming up for 3.0000 s
Warning: Unable to complete 100 samples in 40.0s. You may wish to increase target time to 43.4s, enable flat sampling, or reduce sample count to 60.
custom-measurement-time/distinct_group_by_u64_narrow_limit_10
                        time:   [8.4231 ms 8.4443 ms 8.4657 ms]
                        change: [-20.783% -17.184% -13.756%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 4 outliers among 100 measurements (4.00%)
  1 (1.00%) low mild
  3 (3.00%) high mild
custom-measurement-time/distinct_group_by_u64_narrow_limit_100
                        time:   [39.834 ms 40.002 ms 40.178 ms]
                        change: [-40.712% -35.158% -29.146%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 3 outliers among 100 measurements (3.00%)
  3 (3.00%) high mild
custom-measurement-time/distinct_group_by_u64_narrow_limit_1000
                        time:   [40.009 ms 40.269 ms 40.549 ms]
                        change: [-32.039% -28.795% -25.608%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 9 outliers among 100 measurements (9.00%)
  8 (8.00%) high mild
  1 (1.00%) high severe
custom-measurement-time/distinct_group_by_u64_narrow_limit_10000
                        time:   [39.870 ms 40.048 ms 40.237 ms]
                        change: [-17.900% -13.292% -8.8751%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 3 outliers among 100 measurements (3.00%)
  3 (3.00%) high mild
custom-measurement-time/group_by_multiple_columns_limit_10
                        time:   [37.690 ms 37.762 ms 37.837 ms]
                        change: [-1.5462% -1.1394% -0.7797%] (p = 0.00 < 0.05)
                        Change within noise threshold.
Found 5 outliers among 100 measurements (5.00%)
  5 (5.00%) high mild

Benchmarking distinct query with 100 partitions and 100000 samples per partition with limit 10: Warming up for 3.0000 s
thread 'tokio-runtime-worker' panicked at datafusion/physical-plan/src/repartition/mod.rs:618:22:
partition not used yet
note: run with `RUST_BACKTRACE=1` environment variable to display a backtrace

To Reproduce

checkout main, run cargo bench -p datafusion --bench distinct_query_sql

Expected behavior

benchmark runs to completion

Additional context

No response

Metadata

Metadata

Assignees

Labels

bugSomething isn't working

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions