iemejia commented on issue #11055: [BEAM-9436] Improve GBK in spark structured streaming runner URL: https://github.com/apache/beam/pull/11055#issuecomment-605875941 > > > I think you missed this comment 8 days ago: #11055 (comment) > > > > > > Once again, I saw your results (and even mentioned them in my previous comment) but I asked for more details since it was not clear what kind of tests have been running and, before, we usually provided Nexmark results in such kind of optimisations. > > My bad, the results comment was not clear enough: when the PR contained the jenkins scripts of the load tests it was clear but now that I have separated them in a different PR, it is no more clear: the test that I ran was `GroupByKeyLoadTest` and the CL: > `-Xms12g -Xmx20g -Prunner=":runners:spark" -PloadTest.mainClass="org.apache.beam.sdk.loadtests.GroupByKeyLoadTest" -PloadTest.args="--fanout=1 --iterations=1 --streaming=false --runner=SparkStructuredStreamingRunner --sourceOptions={\"numRecords\":200000,\"keySizeBytes\":100000,\"valueSizeBytes\":100000}"` @echauchot. Can you please share the exact command line needed to run the load tests (to reproduce it and for future reference). Thanks.
---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
