[jira] [Commented] (CASSANDRA-6496) Endless L0 LCS compactions
[ https://issues.apache.org/jira/browse/CASSANDRA-6496?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13850238#comment-13850238 ] Marcus Eriksson commented on CASSANDRA-6496: i think this might be a duplicate of CASSANDRA-6284 Endless L0 LCS compactions -- Key: CASSANDRA-6496 URL: https://issues.apache.org/jira/browse/CASSANDRA-6496 Project: Cassandra Issue Type: Bug Components: Core Environment: Cassandra 2.0.3, Linux, 6 nodes, 5 disks per node Reporter: Nikolai Grigoriev Attachments: system.log.1.gz, system.log.gz I have first described the problem here: http://stackoverflow.com/questions/20589324/cassandra-2-0-3-endless-compactions-with-no-traffic I think I have really abused my system with the traffic (mix of reads, heavy updates and some deletes). Now after stopping the traffic I see the compactions that are going on endlessly for over 4 days. For a specific CF I have about 4700 sstable data files right now. The compaction estimates are logged as [3312, 4, 0, 0, 0, 0, 0, 0, 0]. sstable_size_in_mb=256. 3214 files are about 256Mb (+/1 few megs), other files are smaller or much smaller than that. No sstables are larger than 256Mb. What I observe is that LCS picks 32 sstables from L0 and compacts them into 32 sstables of approximately the same size. So, what my system is doing for last 4 days (no traffic at all) is compacting groups of 32 sstables into groups of 32 sstables without any changes. Seems like a bug to me regardless of what did I do to get the system into this state... -- This message was sent by Atlassian JIRA (v6.1.4#6159)
[jira] [Commented] (CASSANDRA-6496) Endless L0 LCS compactions
[ https://issues.apache.org/jira/browse/CASSANDRA-6496?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13850381#comment-13850381 ] Nikolai Grigoriev commented on CASSANDRA-6496: -- One thing I forgot to mention about the logs - I have reduced the number of compactors to one when enabling the debugging. Since at that point it was clear that something was wrong I was looking for clarity, not performance :) Endless L0 LCS compactions -- Key: CASSANDRA-6496 URL: https://issues.apache.org/jira/browse/CASSANDRA-6496 Project: Cassandra Issue Type: Bug Components: Core Environment: Cassandra 2.0.3, Linux, 6 nodes, 5 disks per node Reporter: Nikolai Grigoriev Attachments: system.log.1.gz, system.log.gz I have first described the problem here: http://stackoverflow.com/questions/20589324/cassandra-2-0-3-endless-compactions-with-no-traffic I think I have really abused my system with the traffic (mix of reads, heavy updates and some deletes). Now after stopping the traffic I see the compactions that are going on endlessly for over 4 days. For a specific CF I have about 4700 sstable data files right now. The compaction estimates are logged as [3312, 4, 0, 0, 0, 0, 0, 0, 0]. sstable_size_in_mb=256. 3214 files are about 256Mb (+/1 few megs), other files are smaller or much smaller than that. No sstables are larger than 256Mb. What I observe is that LCS picks 32 sstables from L0 and compacts them into 32 sstables of approximately the same size. So, what my system is doing for last 4 days (no traffic at all) is compacting groups of 32 sstables into groups of 32 sstables without any changes. Seems like a bug to me regardless of what did I do to get the system into this state... -- This message was sent by Atlassian JIRA (v6.1.4#6159)
[jira] [Commented] (CASSANDRA-6496) Endless L0 LCS compactions
[ https://issues.apache.org/jira/browse/CASSANDRA-6496?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13850687#comment-13850687 ] Nikolai Grigoriev commented on CASSANDRA-6496: -- Cool! I have got the source tagged 2.0.3, applied the patch, recompiled, restarted the node. Clearly now it compacts the groups of 32 L0 sstables into one large one. I see that it just did one round and created 8Gb sstable from 32 256Mb ones. Thanks a lot for the patch! I will revert the compaction settings to give it enough resources and let it complete its job to see the end results before I restart the test traffic. Endless L0 LCS compactions -- Key: CASSANDRA-6496 URL: https://issues.apache.org/jira/browse/CASSANDRA-6496 Project: Cassandra Issue Type: Bug Components: Core Environment: Cassandra 2.0.3, Linux, 6 nodes, 5 disks per node Reporter: Nikolai Grigoriev Assignee: Jonathan Ellis Labels: compaction Fix For: 2.0.4 Attachments: 6496.txt, system.log.1.gz, system.log.gz I have first described the problem here: http://stackoverflow.com/questions/20589324/cassandra-2-0-3-endless-compactions-with-no-traffic I think I have really abused my system with the traffic (mix of reads, heavy updates and some deletes). Now after stopping the traffic I see the compactions that are going on endlessly for over 4 days. For a specific CF I have about 4700 sstable data files right now. The compaction estimates are logged as [3312, 4, 0, 0, 0, 0, 0, 0, 0]. sstable_size_in_mb=256. 3214 files are about 256Mb (+/1 few megs), other files are smaller or much smaller than that. No sstables are larger than 256Mb. What I observe is that LCS picks 32 sstables from L0 and compacts them into 32 sstables of approximately the same size. So, what my system is doing for last 4 days (no traffic at all) is compacting groups of 32 sstables into groups of 32 sstables without any changes. Seems like a bug to me regardless of what did I do to get the system into this state... -- This message was sent by Atlassian JIRA (v6.1.4#6159)
[jira] [Commented] (CASSANDRA-6496) Endless L0 LCS compactions
[ https://issues.apache.org/jira/browse/CASSANDRA-6496?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13850765#comment-13850765 ] Marcus Eriksson commented on CASSANDRA-6496: [~ngrigoriev] thanks for testing and patch lgtm, +1 Endless L0 LCS compactions -- Key: CASSANDRA-6496 URL: https://issues.apache.org/jira/browse/CASSANDRA-6496 Project: Cassandra Issue Type: Bug Components: Core Environment: Cassandra 2.0.3, Linux, 6 nodes, 5 disks per node Reporter: Nikolai Grigoriev Assignee: Jonathan Ellis Labels: compaction Fix For: 2.0.4 Attachments: 6496.txt, system.log.1.gz, system.log.gz I have first described the problem here: http://stackoverflow.com/questions/20589324/cassandra-2-0-3-endless-compactions-with-no-traffic I think I have really abused my system with the traffic (mix of reads, heavy updates and some deletes). Now after stopping the traffic I see the compactions that are going on endlessly for over 4 days. For a specific CF I have about 4700 sstable data files right now. The compaction estimates are logged as [3312, 4, 0, 0, 0, 0, 0, 0, 0]. sstable_size_in_mb=256. 3214 files are about 256Mb (+/1 few megs), other files are smaller or much smaller than that. No sstables are larger than 256Mb. What I observe is that LCS picks 32 sstables from L0 and compacts them into 32 sstables of approximately the same size. So, what my system is doing for last 4 days (no traffic at all) is compacting groups of 32 sstables into groups of 32 sstables without any changes. Seems like a bug to me regardless of what did I do to get the system into this state... -- This message was sent by Atlassian JIRA (v6.1.4#6159)
[jira] [Commented] (CASSANDRA-6496) Endless L0 LCS compactions
[ https://issues.apache.org/jira/browse/CASSANDRA-6496?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13850048#comment-13850048 ] Jonathan Ellis commented on CASSANDRA-6496: --- Can you enable debug logging in o.a.c.db.compaction and post a log sample? Endless L0 LCS compactions -- Key: CASSANDRA-6496 URL: https://issues.apache.org/jira/browse/CASSANDRA-6496 Project: Cassandra Issue Type: Bug Components: Core Environment: Cassandra 2.0.3, Linux, 6 nodes, 5 disks per node Reporter: Nikolai Grigoriev I have first described the problem here: http://stackoverflow.com/questions/20589324/cassandra-2-0-3-endless-compactions-with-no-traffic I think I have really abused my system with the traffic (mix of reads, heavy updates and some deletes). Now after stopping the traffic I see the compactions that are going on endlessly for over 4 days. For a specific CF I have about 4700 sstable data files right now. The compaction estimates are logged as [3312, 4, 0, 0, 0, 0, 0, 0, 0]. sstable_size_in_mb=256. 3214 files are about 256Mb (+/1 few megs), other files are smaller or much smaller than that. No sstables are larger than 256Mb. What I observe is that LCS picks 32 sstables from L0 and compacts them into 32 sstables of approximately the same size. So, what my system is doing for last 4 days (no traffic at all) is compacting groups of 32 sstables into groups of 32 sstables without any changes. Seems like a bug to me regardless of what did I do to get the system into this state... -- This message was sent by Atlassian JIRA (v6.1.4#6159)