cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Chris Goffinet (JIRA)" <j...@apache.org>
Subject [jira] Commented: (CASSANDRA-883) Hinted Handoff Burning lots of CPU cycles
Date Fri, 12 Mar 2010 18:08:27 GMT

    [ https://issues.apache.org/jira/browse/CASSANDRA-883?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12844594#action_12844594
] 

Chris Goffinet commented on CASSANDRA-883:
------------------------------------------

Name: Hint delivery
State: RUNNABLE
Total blocked: 3,053  Total waited: 111

Stack trace: 
sun.nio.cs.UTF_8.updatePositions(UTF_8.java:59)
sun.nio.cs.UTF_8$Decoder.xflow(UTF_8.java:165)
sun.nio.cs.UTF_8$Decoder.decodeArrayLoop(UTF_8.java:241)
sun.nio.cs.UTF_8$Decoder.decodeLoop(UTF_8.java:305)
java.nio.charset.CharsetDecoder.decode(CharsetDecoder.java:544)
java.lang.StringCoding$StringDecoder.decode(StringCoding.java:140)
java.lang.StringCoding.decode(StringCoding.java:173)
java.lang.String.<init>(String.java:443)
java.lang.String.<init>(String.java:515)
org.apache.cassandra.db.marshal.UTF8Type.compare(UTF8Type.java:32)
org.apache.cassandra.db.marshal.UTF8Type.compare(UTF8Type.java:26)
java.util.concurrent.ConcurrentSkipListMap$ComparableUsingComparator.compareTo(ConcurrentSkipListMap.java:606)
java.util.concurrent.ConcurrentSkipListMap.findPredecessor(ConcurrentSkipListMap.java:685)
java.util.concurrent.ConcurrentSkipListMap.doPut(ConcurrentSkipListMap.java:864)
java.util.concurrent.ConcurrentSkipListMap.putIfAbsent(ConcurrentSkipListMap.java:1893)
org.apache.cassandra.db.ColumnFamily.addColumn(ColumnFamily.java:192)
org.apache.cassandra.db.filter.SliceQueryFilter.collectReducedColumns(SliceQueryFilter.java:133)
org.apache.cassandra.db.filter.QueryFilter.collectCollatedColumns(QueryFilter.java:112)
org.apache.cassandra.db.ColumnFamilyStore.getTopLevelColumns(ColumnFamilyStore.java:813)
org.apache.cassandra.db.ColumnFamilyStore.getColumnFamily(ColumnFamilyStore.java:720)
org.apache.cassandra.db.ColumnFamilyStore.getColumnFamily(ColumnFamilyStore.java:689)
org.apache.cassandra.db.HintedHandOffManager.sendMessage(HintedHandOffManager.java:122)
org.apache.cassandra.db.HintedHandOffManager.deliverAllHints(HintedHandOffManager.java:187)
org.apache.cassandra.db.HintedHandOffManager.access$000(HintedHandOffManager.java:80)
org.apache.cassandra.db.HintedHandOffManager$1.runMayThrow(HintedHandOffManager.java:100)
org.apache.cassandra.utils.WrappedRunnable.run(WrappedRunnable.java:30)
java.lang.Thread.run(Thread.java:619)


> Hinted Handoff Burning lots of CPU cycles
> -----------------------------------------
>
>                 Key: CASSANDRA-883
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-883
>             Project: Cassandra
>          Issue Type: Bug
>    Affects Versions: 0.6
>            Reporter: Chris Goffinet
>
> We've noticed on 2 clusters already, when HH CF gets data, it looks to be looping over
and over again on both HINT DELIVERY and HINTED-HANDOFF-POOL. Both threads in top show over
90% cpu. No nodes have been added/removed lately. I also did a major compaction on HH just
to be sure.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message