[ https://issues.apache.org/jira/browse/HBASE-26487?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17454724#comment-17454724 ]
Duo Zhang commented on HBASE-26487: ----------------------------------- I've done the first test, there is no big differences between old and the new implementations on writing performance. I've both run PE 3 times. For the old implementation, the result {noformat} Round 1: latency 158us, qps 31453 Round 2: latency 159us, qps 31353 Round 3: latency 162us, qps 30084 Avg: latency 159.7us, qps 30963.3 {noformat} For the new implementation, the result {noformat} Round 1: latency 150us, qps 33025 Round 2: latency 146us, qps 32949 Round 3: latency 150us, qps 33987 Avg: latency 148.7us, qps 33320.3 {noformat} The difference on latency and qps is about 7%, no very big, and the new implementation is a bit faster > Run some tests to verify the new region replication framework > ------------------------------------------------------------- > > Key: HBASE-26487 > URL: https://issues.apache.org/jira/browse/HBASE-26487 > Project: HBase > Issue Type: Sub-task > Components: integration tests, test > Reporter: Duo Zhang > Assignee: Duo Zhang > Priority: Major > > Make sure there is no big bugs before merging back. -- This message was sent by Atlassian Jira (v8.20.1#820001)