sanastas commented on issue #7676: Add OakIncrementalIndex to Druid URL: https://github.com/apache/incubator-druid/pull/7676#issuecomment-504968841 @b-slim , sure I can provide more details. As I have mentioned we have run Druid's IncrementalIngestionBenchmark (incubator-druid/benchmarks/src/main/java/org/apache/druid/benchmark/indexing/IndexIngestionBenchmark.java) with the data/key generator used there. In order to be more sensitive to data allocation we have increased the number of rows to 3 million (rowsPerSegment=3000000). Experiments compare OakIncrementalIndex implemented with two different memory allocators: OakNativeAllocator and NettyAllocator. Those are the only differences between two Oak implementations. Both allocators allocate from off-heap. The results are presented in the two columns compared in the table I pasted above. The rows in the table represent how many off-heap memory was given to each experiment, for example (-XX:MaxDirectMemorySize=4g). In each experiment 3.8GB are written off-heap. What other details would you like to know?
---------------------------------------------------------------- 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 --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
