[ https://issues.apache.org/jira/browse/HBASE-8763?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14018385#comment-14018385 ]
stack commented on HBASE-8763: ------------------------------ This patch seems to get us our speed back. Good on one [~jeffreyz] Below do basic 1, 5, 25, and 200 threads test: Here is nopatch, the current master branch: {code} nopatch1.1.txt:2014-06-04 12:11:52,176 INFO [main] wal.HLogPerformanceEvaluation: Summary: threads=1, iterations=1000000, syncInterval=0 took 1224.313s 816.785ops/s nopatch5.1.txt:2014-06-04 12:29:02,864 INFO [main] wal.HLogPerformanceEvaluation: Summary: threads=5, iterations=1000000, syncInterval=0 took 1025.163s 4877.273ops/s nopatch25.1.txt:2014-06-04 12:53:02,973 INFO [main] wal.HLogPerformanceEvaluation: Summary: threads=25, iterations=1000000, syncInterval=0 took 1434.641s 17425.963ops/s nopatch200.1.txt:2014-06-04 13:40:30,333 INFO [main] wal.HLogPerformanceEvaluation: Summary: threads=200, iterations=1000000, syncInterval=0 took 2841.947s 70374.289ops/s {code} Here is w/ patch applied: {code} patch1.1.txt:2014-06-04 14:37:04,973 INFO [main] wal.HLogPerformanceEvaluation: Summary: threads=1, iterations=1000000, syncInterval=0 took 1228.775s 813.819ops/s patch5.1.txt:2014-06-04 14:53:53,623 INFO [main] wal.HLogPerformanceEvaluation: Summary: threads=5, iterations=1000000, syncInterval=0 took 1003.234s 4983.882ops/s patch25.1.txt:2014-06-04 15:17:17,952 INFO [main] wal.HLogPerformanceEvaluation: Summary: threads=25, iterations=1000000, syncInterval=0 took 1398.927s 17870.840ops/s patch200.1.txt:2014-06-04 15:47:36,297 INFO [main] wal.HLogPerformanceEvaluation: Summary: threads=200, iterations=1000000, syncInterval=0 took 1813.013s 110313.609ops/s {code} > [BRAINSTORM] Combine MVCC and SeqId > ----------------------------------- > > Key: HBASE-8763 > URL: https://issues.apache.org/jira/browse/HBASE-8763 > Project: HBase > Issue Type: Improvement > Components: regionserver > Reporter: Enis Soztutar > Assignee: Jeffrey Zhong > Priority: Critical > Attachments: HBase MVCC & LogSeqId Combined.pdf, > hbase-8736-poc.patch, hbase-8763-poc-v1.patch, hbase-8763-v1.patch, > hbase-8763-v2.patch, hbase-8763-v3.patch, hbase-8763-v4.patch, > hbase-8763-v5.1.patch, hbase-8763-v5.patch, hbase-8763_wip1.patch > > > HBASE-8701 and a lot of recent issues include good discussions about mvcc + > seqId semantics. It seems that having mvcc and the seqId complicates the > comparator semantics a lot in regards to flush + WAL replay + compactions + > delete markers and out of order puts. > Thinking more about it I don't think we need a MVCC write number which is > different than the seqId. We can keep the MVCC semantics, read point and > smallest read points intact, but combine mvcc write number and seqId. This > will allow cleaner semantics + implementation + smaller data files. > We can do some brainstorming for 0.98. We still have to verify that this > would be semantically correct, it should be so by my current understanding. -- This message was sent by Atlassian JIRA (v6.2#6252)