You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@bookkeeper.apache.org by GitBox <gi...@apache.org> on 2022/06/06 17:12:07 UTC

[GitHub] [bookkeeper] merlimat commented on pull request #3264: Update datasketches version from 0.8.3 to 3.2.0

merlimat commented on PR #3264:
URL: https://github.com/apache/bookkeeper/pull/3264#issuecomment-1147682083

   @Shoothzj Just did a quick test. There are 4 bytes per each recorded sample with the new Datasketches. It would be good to understand why that is the case and if there's any way to configure DataSketches to avoid that.
   
   ```
   DataSketches 0.8.3
   Benchmark                                                           (statsProvider)   Mode  Cnt     Score     Error   Units
   StatsLoggerBenchmark.recordLatency                                       Prometheus  thrpt    3    15.203 ±   2.787  ops/us
   StatsLoggerBenchmark.recordLatency:·gc.alloc.rate                        Prometheus  thrpt    3     0.023 ±   0.368  MB/sec
   StatsLoggerBenchmark.recordLatency:·gc.alloc.rate.norm                   Prometheus  thrpt    3     0.002 ±   0.027    B/op
   StatsLoggerBenchmark.recordLatency:·gc.churn.G1_Eden_Space               Prometheus  thrpt    3     1.603 ±  50.660  MB/sec
   StatsLoggerBenchmark.recordLatency:·gc.churn.G1_Eden_Space.norm          Prometheus  thrpt    3     0.116 ±   3.650    B/op
   StatsLoggerBenchmark.recordLatency:·gc.count                             Prometheus  thrpt    3     1.000            counts
   StatsLoggerBenchmark.recordLatency:·gc.time                              Prometheus  thrpt    3     2.000                ms
   StatsLoggerBenchmark.recordLatency:·stack                                Prometheus  thrpt            NaN               ---
   
   
   DataSketches 3.2.0
   Benchmark                                                           (statsProvider)   Mode  Cnt     Score     Error   Units
   StatsLoggerBenchmark.recordLatency                                       Prometheus  thrpt    3    15.965 ±   9.438  ops/us
   StatsLoggerBenchmark.recordLatency:·gc.alloc.rate                        Prometheus  thrpt    3    63.314 ±  35.780  MB/sec
   StatsLoggerBenchmark.recordLatency:·gc.alloc.rate.norm                   Prometheus  thrpt    3     4.377 ±   0.023    B/op
   StatsLoggerBenchmark.recordLatency:·gc.churn.G1_Eden_Space               Prometheus  thrpt    3    57.793 ±   4.866  MB/sec
   StatsLoggerBenchmark.recordLatency:·gc.churn.G1_Eden_Space.norm          Prometheus  thrpt    3     3.998 ±   2.456    B/op
   StatsLoggerBenchmark.recordLatency:·gc.count                             Prometheus  thrpt    3     3.000            counts
   StatsLoggerBenchmark.recordLatency:·gc.time                              Prometheus  thrpt    3     4.000                ms
   StatsLoggerBenchmark.recordLatency:·stack                                Prometheus  thrpt            NaN               ---
   ```


-- 
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: issues-unsubscribe@bookkeeper.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org