[jira] [Updated] (CASSANDRA-16782) Improve the way we pick sstables for STCS-in-L0 and in TWCS 'current' window
[ https://issues.apache.org/jira/browse/CASSANDRA-16782?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Branimir Lambov updated CASSANDRA-16782: Status: Review In Progress (was: Patch Available) > Improve the way we pick sstables for STCS-in-L0 and in TWCS 'current' window > > > Key: CASSANDRA-16782 > URL: https://issues.apache.org/jira/browse/CASSANDRA-16782 > Project: Cassandra > Issue Type: Improvement > Components: Local/Compaction/LCS, Local/Compaction/TWCS >Reporter: Marcus Eriksson >Assignee: Marcus Eriksson >Priority: Normal > Fix For: 4.x > > > The goal when being behind in L0 should always be to get the number of > sstables down to a reasonable level as soon as possible. Currently it is > common that we run compactions on the large sstables but leave thousands of > tiny sstables behind. -- 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
[jira] [Updated] (CASSANDRA-16782) Improve the way we pick sstables for STCS-in-L0 and in TWCS 'current' window
[ https://issues.apache.org/jira/browse/CASSANDRA-16782?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Branimir Lambov updated CASSANDRA-16782: Reviewers: Aleksei Zotov, Branimir Lambov > Improve the way we pick sstables for STCS-in-L0 and in TWCS 'current' window > > > Key: CASSANDRA-16782 > URL: https://issues.apache.org/jira/browse/CASSANDRA-16782 > Project: Cassandra > Issue Type: Improvement > Components: Local/Compaction/LCS, Local/Compaction/TWCS >Reporter: Marcus Eriksson >Assignee: Marcus Eriksson >Priority: Normal > Fix For: 4.x > > > The goal when being behind in L0 should always be to get the number of > sstables down to a reasonable level as soon as possible. Currently it is > common that we run compactions on the large sstables but leave thousands of > tiny sstables behind. -- 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
[jira] [Updated] (CASSANDRA-16782) Improve the way we pick sstables for STCS-in-L0 and in TWCS 'current' window
[ https://issues.apache.org/jira/browse/CASSANDRA-16782?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Marcus Eriksson updated CASSANDRA-16782: Fix Version/s: (was: 4.0.x) > Improve the way we pick sstables for STCS-in-L0 and in TWCS 'current' window > > > Key: CASSANDRA-16782 > URL: https://issues.apache.org/jira/browse/CASSANDRA-16782 > Project: Cassandra > Issue Type: Improvement > Components: Local/Compaction/LCS, Local/Compaction/TWCS >Reporter: Marcus Eriksson >Assignee: Marcus Eriksson >Priority: Normal > Fix For: 4.x > > > The goal when being behind in L0 should always be to get the number of > sstables down to a reasonable level as soon as possible. Currently it is > common that we run compactions on the large sstables but leave thousands of > tiny sstables behind. -- 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
[jira] [Updated] (CASSANDRA-16782) Improve the way we pick sstables for STCS-in-L0 and in TWCS 'current' window
[ https://issues.apache.org/jira/browse/CASSANDRA-16782?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Marcus Eriksson updated CASSANDRA-16782: Fix Version/s: 4.0.x > Improve the way we pick sstables for STCS-in-L0 and in TWCS 'current' window > > > Key: CASSANDRA-16782 > URL: https://issues.apache.org/jira/browse/CASSANDRA-16782 > Project: Cassandra > Issue Type: Improvement > Components: Local/Compaction/LCS, Local/Compaction/TWCS >Reporter: Marcus Eriksson >Assignee: Marcus Eriksson >Priority: Normal > Fix For: 4.0.x, 4.x > > > The goal when being behind in L0 should always be to get the number of > sstables down to a reasonable level as soon as possible. Currently it is > common that we run compactions on the large sstables but leave thousands of > tiny sstables behind. -- 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
[jira] [Updated] (CASSANDRA-16782) Improve the way we pick sstables for STCS-in-L0 and in TWCS 'current' window
[ https://issues.apache.org/jira/browse/CASSANDRA-16782?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Marcus Eriksson updated CASSANDRA-16782: Test and Documentation Plan: cci run Status: Patch Available (was: Open) This patch collects smallest sstables until the total size is 1GB or we reach 1000 sstables (both configurable), and compacts them together. Once we can't do any compactions like that (say the 4 smallest sstables size is > 1GB) we start doing L0 -> L1 compactions instead, this avoids creating huge sstables in L0. With TWCS we take the same approach, but once we can't do any more compactions like that we do regular STCS [https://github.com/krummas/cassandra/commits/marcuse/16782] [https://app.circleci.com/pipelines/github/krummas/cassandra?branch=marcuse%2F16782] > Improve the way we pick sstables for STCS-in-L0 and in TWCS 'current' window > > > Key: CASSANDRA-16782 > URL: https://issues.apache.org/jira/browse/CASSANDRA-16782 > Project: Cassandra > Issue Type: Improvement > Components: Local/Compaction/LCS, Local/Compaction/TWCS >Reporter: Marcus Eriksson >Assignee: Marcus Eriksson >Priority: Normal > Fix For: 4.x > > > The goal when being behind in L0 should always be to get the number of > sstables down to a reasonable level as soon as possible. Currently it is > common that we run compactions on the large sstables but leave thousands of > tiny sstables behind. -- 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
[jira] [Updated] (CASSANDRA-16782) Improve the way we pick sstables for STCS-in-L0 and in TWCS 'current' window
[ https://issues.apache.org/jira/browse/CASSANDRA-16782?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Marcus Eriksson updated CASSANDRA-16782: Change Category: Operability Complexity: Normal Component/s: Local/Compaction/TWCS Local/Compaction/LCS Fix Version/s: 4.x Status: Open (was: Triage Needed) > Improve the way we pick sstables for STCS-in-L0 and in TWCS 'current' window > > > Key: CASSANDRA-16782 > URL: https://issues.apache.org/jira/browse/CASSANDRA-16782 > Project: Cassandra > Issue Type: Improvement > Components: Local/Compaction/LCS, Local/Compaction/TWCS >Reporter: Marcus Eriksson >Assignee: Marcus Eriksson >Priority: Normal > Fix For: 4.x > > > The goal when being behind in L0 should always be to get the number of > sstables down to a reasonable level as soon as possible. Currently it is > common that we run compactions on the large sstables but leave thousands of > tiny sstables behind. -- 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