[ https://issues.apache.org/jira/browse/CASSANDRA-15657?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17100447#comment-17100447 ]
ZhaoYang edited comment on CASSANDRA-15657 at 5/6/20, 4:32 AM: --------------------------------------------------------------- [~e.dimitrova] Thanks for the report. This patch allows ZCS for size-tiered compaction which is used by the test and the test log showed that the file is indeed received via ZCS... {code:java} INFO [CompactionExecutor:2] 2020-05-06 12:28:10,848 PendingRepairManager.java:446 - Obsoleting transient repaired ssatblesDEBUG [CompactionExecutor:2] 2020-05-06 12:28:10,852 PendingRepairManager.java:144 - Removing compaction strategy for pending repair fc89be70-8f51-11ea-8232-f78d8bc3c1f4 on ks.tblINFO [NonPeriodicTasks:1] 2020-05-06 12:28:10,855 SSTable.java:111 - Deleting sstable: /private/var/folders/w0/m4svxry56h56g_42mx0rwbcr0000gn/T/dtest-9fybyxp7/test/node2/data0/ks/tbl-f26130408f5111ea8232f78d8bc3c1f4/na-1-big {code} Transient replica repair is removing the received file and it's doing it faster on ZCS sstable than non-ZCS sstable. was (Author: jasonstack): [~e.dimitrova] Thanks for the report. This patch allows ZCS for size-tiered compaction which is used by the test and the test log showed that the file is indeed received via ZCS...Probably some lifecycle issue that the received sstable isn't added to ColumnFamilyStore. > Improve zero-copy-streaming containment check by using file sections > -------------------------------------------------------------------- > > Key: CASSANDRA-15657 > URL: https://issues.apache.org/jira/browse/CASSANDRA-15657 > Project: Cassandra > Issue Type: Improvement > Components: Legacy/Streaming and Messaging > Reporter: ZhaoYang > Assignee: ZhaoYang > Priority: Normal > Fix For: 4.0 > > > Currently zero copy streaming is only enabled for leveled-compaction strategy > and it checks if all keys in the sstables are included in the transferred > ranges. > This is very inefficient. The containment check can be improved by checking > if transferred sections (the transferred file positions) cover entire sstable. > I also enabled ZCS for all compaction strategies since the new containment > check is very fast.. -- This message was sent by Atlassian Jira (v8.3.4#803005) --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org For additional commands, e-mail: commits-h...@cassandra.apache.org