[ https://issues.apache.org/jira/browse/HBASE-20411?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16452640#comment-16452640 ]
stack commented on HBASE-20411: ------------------------------- I tried the patch [~huaxiang] and it just seems to slow things down like my one does. Let me come back here after we figure the root for why we going slower than hbase1.... I think your patch is more promising than mine but we should commit a melding of the two since my version avoids locking altogether where it not needed. This also has been showing up on occasion: the synchronize on blockSignal in MemStoreFlusher: org.apache.hadoop.hbase.regionserver.MemStoreFlusher.reclaimMemStoreMemory(MemStoreFlusher.java:72 For investigation later.... seems like the blockSignal synchronize not needed after your patch goes in. Thanks. > Ameliorate MutableSegment synchronize > ------------------------------------- > > Key: HBASE-20411 > URL: https://issues.apache.org/jira/browse/HBASE-20411 > Project: HBase > Issue Type: Bug > Reporter: stack > Priority: Major > Attachments: 2.load.patched.17704.lock.svg, > 2.load.patched.2.17704.lock.svg, 2.more.patch.12010.lock.svg, 41901.lock.svg, > HBASE-20411-atomiclong-longadder.patch, HBASE-20411.branch-2.0.001.patch, > HBASE-20411.branch-2.0.002.patch, HBASE-20411.branch-2.0.003.patch, > HBASE-20411.branch-2.0.004.patch, HBASE-20411.branch-2.0.005.patch, > HBASE-20411.branch-2.0.006.patch, HBASE-20411.branch-2.0.007.patch > > > This item is migrated from HBASE-20236 so it gets dedicated issue. > Let me upload evidence that has this synchronize as a stake in our write-time > perf. I'll migrate the patch I posted with updates that come of comments > posted by [~mdrob] on the HBASE-20236 issue. -- This message was sent by Atlassian JIRA (v7.6.3#76005)