[jira] [Commented] (CASSANDRA-7567) when the commit_log disk for a single node is overwhelmed the entire cluster slows down

2014-07-31 Thread Brandon Williams (JIRA)
[ https://issues.apache.org/jira/browse/CASSANDRA-7567?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14081040#comment-14081040 ] Brandon Williams commented on CASSANDRA-7567: - I applied CASSANDRA-7644

[jira] [Commented] (CASSANDRA-7567) when the commit_log disk for a single node is overwhelmed the entire cluster slows down

2014-07-31 Thread Benedict (JIRA)
[ https://issues.apache.org/jira/browse/CASSANDRA-7567?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14081045#comment-14081045 ] Benedict commented on CASSANDRA-7567: - Which mode of connectivity? smart thrift

[jira] [Commented] (CASSANDRA-7567) when the commit_log disk for a single node is overwhelmed the entire cluster slows down

2014-07-31 Thread Brandon Williams (JIRA)
[ https://issues.apache.org/jira/browse/CASSANDRA-7567?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14081049#comment-14081049 ] Brandon Williams commented on CASSANDRA-7567: - Whichever mode is the

[jira] [Commented] (CASSANDRA-7567) when the commit_log disk for a single node is overwhelmed the entire cluster slows down

2014-07-31 Thread Benedict (JIRA)
[ https://issues.apache.org/jira/browse/CASSANDRA-7567?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14081060#comment-14081060 ] Benedict commented on CASSANDRA-7567: - So Java driver then (cql3 native prepared

[jira] [Commented] (CASSANDRA-7567) when the commit_log disk for a single node is overwhelmed the entire cluster slows down

2014-07-31 Thread Brandon Williams (JIRA)
[ https://issues.apache.org/jira/browse/CASSANDRA-7567?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14081059#comment-14081059 ] Brandon Williams commented on CASSANDRA-7567: - Closing in favor of

[jira] [Commented] (CASSANDRA-7567) when the commit_log disk for a single node is overwhelmed the entire cluster slows down

2014-07-29 Thread Jonathan Ellis (JIRA)
[ https://issues.apache.org/jira/browse/CASSANDRA-7567?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14078393#comment-14078393 ] Jonathan Ellis commented on CASSANDRA-7567: --- Ryan, was your reproduction on

[jira] [Commented] (CASSANDRA-7567) when the commit_log disk for a single node is overwhelmed the entire cluster slows down

2014-07-29 Thread Ryan McGuire (JIRA)
[ https://issues.apache.org/jira/browse/CASSANDRA-7567?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14078401#comment-14078401 ] Ryan McGuire commented on CASSANDRA-7567: - Both do it. All the above results

[jira] [Commented] (CASSANDRA-7567) when the commit_log disk for a single node is overwhelmed the entire cluster slows down

2014-07-29 Thread Benedict (JIRA)
[ https://issues.apache.org/jira/browse/CASSANDRA-7567?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14078424#comment-14078424 ] Benedict commented on CASSANDRA-7567: - Ryan, there's something fishy about those

[jira] [Commented] (CASSANDRA-7567) when the commit_log disk for a single node is overwhelmed the entire cluster slows down

2014-07-29 Thread Ryan McGuire (JIRA)
[ https://issues.apache.org/jira/browse/CASSANDRA-7567?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14078451#comment-14078451 ] Ryan McGuire commented on CASSANDRA-7567: - I'll rerun on both 2.1 and 2.0 and

[jira] [Commented] (CASSANDRA-7567) when the commit_log disk for a single node is overwhelmed the entire cluster slows down

2014-07-29 Thread Ryan McGuire (JIRA)
[ https://issues.apache.org/jira/browse/CASSANDRA-7567?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14078786#comment-14078786 ] Ryan McGuire commented on CASSANDRA-7567: - Sorry for the confusion, I don't

[jira] [Commented] (CASSANDRA-7567) when the commit_log disk for a single node is overwhelmed the entire cluster slows down

2014-07-29 Thread Brandon Williams (JIRA)
[ https://issues.apache.org/jira/browse/CASSANDRA-7567?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14078788#comment-14078788 ] Brandon Williams commented on CASSANDRA-7567: - Half-win then.

[jira] [Commented] (CASSANDRA-7567) when the commit_log disk for a single node is overwhelmed the entire cluster slows down

2014-07-25 Thread Ryan McGuire (JIRA)
[ https://issues.apache.org/jira/browse/CASSANDRA-7567?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14074829#comment-14074829 ] Ryan McGuire commented on CASSANDRA-7567: - {code} cqlsh select activity,

[jira] [Commented] (CASSANDRA-7567) when the commit_log disk for a single node is overwhelmed the entire cluster slows down

2014-07-23 Thread Ryan McGuire (JIRA)
[ https://issues.apache.org/jira/browse/CASSANDRA-7567?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14072373#comment-14072373 ] Ryan McGuire commented on CASSANDRA-7567: - I don't know what it is about 12s

[jira] [Commented] (CASSANDRA-7567) when the commit_log disk for a single node is overwhelmed the entire cluster slows down

2014-07-23 Thread Brandon Williams (JIRA)
[ https://issues.apache.org/jira/browse/CASSANDRA-7567?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14072406#comment-14072406 ] Brandon Williams commented on CASSANDRA-7567: - I ran it a pretty long

[jira] [Commented] (CASSANDRA-7567) when the commit_log disk for a single node is overwhelmed the entire cluster slows down

2014-07-18 Thread Brandon Williams (JIRA)
[ https://issues.apache.org/jira/browse/CASSANDRA-7567?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14066495#comment-14066495 ] Brandon Williams commented on CASSANDRA-7567: - I wasn't able to reproduce

[jira] [Commented] (CASSANDRA-7567) when the commit_log disk for a single node is overwhelmed the entire cluster slows down

2014-07-17 Thread David O'Dell (JIRA)
[ https://issues.apache.org/jira/browse/CASSANDRA-7567?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14065263#comment-14065263 ] David O'Dell commented on CASSANDRA-7567: - BTW the replication_factor = 3 and

[jira] [Commented] (CASSANDRA-7567) when the commit_log disk for a single node is overwhelmed the entire cluster slows down

2014-07-17 Thread Ryan McGuire (JIRA)
[ https://issues.apache.org/jira/browse/CASSANDRA-7567?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14065819#comment-14065819 ] Ryan McGuire commented on CASSANDRA-7567: - I have reproduced this on a 10 node

[jira] [Commented] (CASSANDRA-7567) when the commit_log disk for a single node is overwhelmed the entire cluster slows down

2014-07-17 Thread Ryan McGuire (JIRA)
[ https://issues.apache.org/jira/browse/CASSANDRA-7567?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14065844#comment-14065844 ] Ryan McGuire commented on CASSANDRA-7567: - Forgive my previous armchair