cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Jeff Griffith (JIRA)" <>
Subject [jira] [Updated] (CASSANDRA-10515) Commit logs back up with move to 2.1.10
Date Thu, 15 Oct 2015 23:56:08 GMT


Jeff Griffith updated CASSANDRA-10515:
    Attachment: RUN3tpstats.jpg

[~tjake] I monitored live for a few hours to capture the behavior. See RUN3tpstats.jpg in
the attachments:

Overview is:
Monitoring threads began to block before the memtable flushing did.
Memtable flushing seemed to be progressing slowly and then post flushing operations began
to pile up. The primary things blocked were:
1. MemtableFlushWriter/handleNotif
2. CompactionExec/getNextBGTask
3. ServiceThread/getEstimatedRemTask

Those three blocked and never came unblocked so assume (?) the locker never completed:

"CompactionExecutor:18" #1462 daemon prio=1 os_prio=4 tid=0x00007fd961410000 nid=0x728b runnable
   java.lang.Thread.State: RUNNABLE
        at org.apache.cassandra.dht.Bounds.contains(
        at org.apache.cassandra.dht.Bounds.intersects(
        at org.apache.cassandra.db.compaction.LeveledManifest.overlapping(
        at org.apache.cassandra.db.compaction.LeveledManifest.overlapping(
        at org.apache.cassandra.db.compaction.LeveledManifest.getCandidatesFor(
        at org.apache.cassandra.db.compaction.LeveledManifest.getCompactionCandidates(
        - locked <0x00000004a8bc5038> (a org.apache.cassandra.db.compaction.LeveledManifest)
        at org.apache.cassandra.db.compaction.LeveledCompactionStrategy.getMaximalTask(
        at org.apache.cassandra.db.compaction.LeveledCompactionStrategy.getNextBackgroundTask(
        - locked <0x00000004a8af17d0> (a org.apache.cassandra.db.compaction.LeveledCompactionStrategy)
        at org.apache.cassandra.db.compaction.WrappingCompactionStrategy.getNextBackgroundTask(
        - locked <0x00000004a894df10> (a org.apache.cassandra.db.compaction.WrappingCompactionStrategy)
        at org.apache.cassandra.db.compaction.CompactionManager$
        at java.util.concurrent.Executors$
        at java.util.concurrent.ThreadPoolExecutor.runWorker(
        at java.util.concurrent.ThreadPoolExecutor$

> Commit logs back up with move to 2.1.10
> ---------------------------------------
>                 Key: CASSANDRA-10515
>                 URL:
>             Project: Cassandra
>          Issue Type: Bug
>          Components: Core
>         Environment: redhat 6.5, cassandra 2.1.10
>            Reporter: Jeff Griffith
>            Assignee: Branimir Lambov
>            Priority: Critical
>              Labels: commitlog, triage
>         Attachments: CommitLogProblem.jpg, CommitLogSize.jpg, RUN3tpstats.jpg, stacktrace.txt,
> After upgrading from cassandra 2.0.x to 2.1.10, we began seeing problems where some nodes
break the 12G commit log max we configured and go as high as 65G or more before it restarts.
Once it reaches the state of more than 12G commit log files, "nodetool compactionstats" hangs.
Eventually C* restarts without errors (not sure yet whether it is crashing but I'm checking
into it) and the cleanup occurs and the commit logs shrink back down again. Here is the nodetool
compactionstats immediately after restart.
> {code}
> jgriffith@prod1xc1.c2.bf1:~$ ndc
> pending tasks: 2185
>    compaction type   keyspace                          table     completed          total
   unit   progress
>         Compaction   SyncCore                          *cf1*   61251208033   170643574558
  bytes     35.89%
>         Compaction   SyncCore                          *cf2*   19262483904    19266079916
  bytes     99.98%
>         Compaction   SyncCore                          *cf3*    6592197093     6592316682
  bytes    100.00%
>         Compaction   SyncCore                          *cf4*    3411039555     3411039557
  bytes    100.00%
>         Compaction   SyncCore                          *cf5*    2879241009     2879487621
  bytes     99.99%
>         Compaction   SyncCore                          *cf6*   21252493623    21252635196
  bytes    100.00%
>         Compaction   SyncCore                          *cf7*   81009853587    81009854438
  bytes    100.00%
>         Compaction   SyncCore                          *cf8*    3005734580     3005768582
  bytes    100.00%
> Active compaction remaining time :        n/a
> {code}
> I was also doing periodic "nodetool tpstats" which were working but not being logged
in system.log on the StatusLogger thread until after the compaction started working again.

This message was sent by Atlassian JIRA

View raw message