gargvishesh opened a new pull request, #15688:
URL: https://github.com/apache/druid/pull/15688
Adds a set of benchmark queries for measuring the planning time with the IN
operator. Current results indicate that with the recent optimizations, the IN
planning time even with `100000` expressions in the IN clause is just about
`~10s`.
Results
```
Benchmark (inClauseExprCount) (inSubQueryThreshold)
(rowsPerSegment) (schema) Mode Cnt Score Error Units
InBenchmark.queryEqualOrInSql 1 1000000
500000 explicit avgt 5 0.355 ± 0.010 ms/op
InBenchmark.queryEqualOrInSql 1 1000000
500000 auto avgt 5 0.350 ± 0.013 ms/op
InBenchmark.queryEqualOrInSql 10 1000000
500000 explicit avgt 5 0.731 ± 0.105 ms/op
InBenchmark.queryEqualOrInSql 10 1000000
500000 auto avgt 5 0.707 ± 0.013 ms/op
InBenchmark.queryEqualOrInSql 100 1000000
500000 explicit avgt 5 4.699 ± 1.036 ms/op
InBenchmark.queryEqualOrInSql 100 1000000
500000 auto avgt 5 5.133 ± 0.972 ms/op
InBenchmark.queryEqualOrInSql 1000 1000000
500000 explicit avgt 5 54.510 ± 2.140 ms/op
InBenchmark.queryEqualOrInSql 1000 1000000
500000 auto avgt 5 56.576 ± 0.397 ms/op
InBenchmark.queryEqualOrInSql 10000 1000000
500000 explicit avgt 5 843.706 ± 10.657 ms/op
InBenchmark.queryEqualOrInSql 10000 1000000
500000 auto avgt 5 675.669 ± 34.936 ms/op
InBenchmark.queryEqualOrInSql 100000 1000000
500000 explicit avgt 5 9548.689 ± 318.618 ms/op
InBenchmark.queryEqualOrInSql 100000 1000000
500000 auto avgt 5 10056.580 ± 955.134 ms/op
InBenchmark.queryInSql 1 1000000
500000 explicit avgt 5 0.241 ± 0.011 ms/op
InBenchmark.queryInSql 1 1000000
500000 auto avgt 5 0.238 ± 0.002 ms/op
InBenchmark.queryInSql 10 1000000
500000 explicit avgt 5 0.385 ± 0.007 ms/op
InBenchmark.queryInSql 10 1000000
500000 auto avgt 5 0.408 ± 0.003 ms/op
InBenchmark.queryInSql 100 1000000
500000 explicit avgt 5 1.805 ± 0.020 ms/op
InBenchmark.queryInSql 100 1000000
500000 auto avgt 5 1.835 ± 0.023 ms/op
InBenchmark.queryInSql 1000 1000000
500000 explicit avgt 5 17.859 ± 0.780 ms/op
InBenchmark.queryInSql 1000 1000000
500000 auto avgt 5 18.036 ± 0.513 ms/op
InBenchmark.queryInSql 10000 1000000
500000 explicit avgt 5 221.779 ± 16.690 ms/op
InBenchmark.queryInSql 10000 1000000
500000 auto avgt 5 233.813 ± 39.536 ms/op
InBenchmark.queryInSql 100000 1000000
500000 explicit avgt 5 2952.170 ± 95.481 ms/op
InBenchmark.queryInSql 100000 1000000
500000 auto avgt 5 3032.120 ± 170.323 ms/op
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
