[jira] [Commented] (HBASE-15470) Add a setting for Priority queue length
[ https://issues.apache.org/jira/browse/HBASE-15470?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15215495#comment-15215495 ] Anoop Sam John commented on HBASE-15470: Added new config 'hbase.ipc.server.priority.max.callqueue.length'. Mind adding a release notes? > Add a setting for Priority queue length > --- > > Key: HBASE-15470 > URL: https://issues.apache.org/jira/browse/HBASE-15470 > Project: HBase > Issue Type: Improvement > Components: IPC/RPC, Region Assignment >Affects Versions: 1.2.0 >Reporter: Elliott Clark >Assignee: Elliott Clark > Fix For: 2.0.0, 1.3.0 > > Attachments: HBASE-15470.patch > > > Meta can have very different request rates than any other region. We > shouldn't use the same call queue length. > For example: > If a normal request takes 100ms ( long scan or large get ) > but a call to meta is all in memory so it takes < 1ms > So a call queue length of 100 represents multiple seconds of work for normal > requests, but less than a second for meta. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (HBASE-15470) Add a setting for Priority queue length
[ https://issues.apache.org/jira/browse/HBASE-15470?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15199129#comment-15199129 ] Hudson commented on HBASE-15470: ABORTED: Integrated in HBase-1.3 #606 (See [https://builds.apache.org/job/HBase-1.3/606/]) HBASE-15470 Add a setting for Priority queue length (eclark: rev 9c13e0daffcf489f91755b1f93aff0fa23b51aff) * hbase-server/src/main/java/org/apache/hadoop/hbase/ipc/FifoRpcScheduler.java * hbase-server/src/main/java/org/apache/hadoop/hbase/ipc/RpcExecutor.java * hbase-server/src/main/java/org/apache/hadoop/hbase/ipc/SimpleRpcScheduler.java * hbase-server/src/main/java/org/apache/hadoop/hbase/ipc/RpcScheduler.java > Add a setting for Priority queue length > --- > > Key: HBASE-15470 > URL: https://issues.apache.org/jira/browse/HBASE-15470 > Project: HBase > Issue Type: Improvement > Components: IPC/RPC, Region Assignment >Affects Versions: 1.2.0 >Reporter: Elliott Clark >Assignee: Elliott Clark > Fix For: 2.0.0, 1.3.0 > > Attachments: HBASE-15470.patch > > > Meta can have very different request rates than any other region. We > shouldn't use the same call queue length. > For example: > If a normal request takes 100ms ( long scan or large get ) > but a call to meta is all in memory so it takes < 1ms > So a call queue length of 100 represents multiple seconds of work for normal > requests, but less than a second for meta. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (HBASE-15470) Add a setting for Priority queue length
[ https://issues.apache.org/jira/browse/HBASE-15470?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15198825#comment-15198825 ] Hudson commented on HBASE-15470: SUCCESS: Integrated in HBase-1.3-IT #557 (See [https://builds.apache.org/job/HBase-1.3-IT/557/]) HBASE-15470 Add a setting for Priority queue length (eclark: rev f1bb26c2235e231c6326cd5c78932f492844b8aa) * hbase-server/src/main/java/org/apache/hadoop/hbase/ipc/RpcScheduler.java * hbase-server/src/main/java/org/apache/hadoop/hbase/ipc/RpcExecutor.java * hbase-server/src/main/java/org/apache/hadoop/hbase/ipc/FifoRpcScheduler.java * hbase-server/src/main/java/org/apache/hadoop/hbase/ipc/SimpleRpcScheduler.java > Add a setting for Priority queue length > --- > > Key: HBASE-15470 > URL: https://issues.apache.org/jira/browse/HBASE-15470 > Project: HBase > Issue Type: Improvement > Components: IPC/RPC, Region Assignment >Affects Versions: 1.2.0 >Reporter: Elliott Clark >Assignee: Elliott Clark > Fix For: 2.0.0, 1.3.0 > > Attachments: HBASE-15470.patch > > > Meta can have very different request rates than any other region. We > shouldn't use the same call queue length. > For example: > If a normal request takes 100ms ( long scan or large get ) > but a call to meta is all in memory so it takes < 1ms > So a call queue length of 100 represents multiple seconds of work for normal > requests, but less than a second for meta. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (HBASE-15470) Add a setting for Priority queue length
[ https://issues.apache.org/jira/browse/HBASE-15470?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15198806#comment-15198806 ] Hudson commented on HBASE-15470: FAILURE: Integrated in HBase-1.4 #24 (See [https://builds.apache.org/job/HBase-1.4/24/]) HBASE-15470 Add a setting for Priority queue length (eclark: rev f1bb26c2235e231c6326cd5c78932f492844b8aa) * hbase-server/src/main/java/org/apache/hadoop/hbase/ipc/RpcScheduler.java * hbase-server/src/main/java/org/apache/hadoop/hbase/ipc/RpcExecutor.java * hbase-server/src/main/java/org/apache/hadoop/hbase/ipc/SimpleRpcScheduler.java * hbase-server/src/main/java/org/apache/hadoop/hbase/ipc/FifoRpcScheduler.java > Add a setting for Priority queue length > --- > > Key: HBASE-15470 > URL: https://issues.apache.org/jira/browse/HBASE-15470 > Project: HBase > Issue Type: Improvement > Components: IPC/RPC, Region Assignment >Affects Versions: 1.2.0 >Reporter: Elliott Clark >Assignee: Elliott Clark > Fix For: 2.0.0, 1.3.0 > > Attachments: HBASE-15470.patch > > > Meta can have very different request rates than any other region. We > shouldn't use the same call queue length. > For example: > If a normal request takes 100ms ( long scan or large get ) > but a call to meta is all in memory so it takes < 1ms > So a call queue length of 100 represents multiple seconds of work for normal > requests, but less than a second for meta. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (HBASE-15470) Add a setting for Priority queue length
[ https://issues.apache.org/jira/browse/HBASE-15470?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15198801#comment-15198801 ] Hudson commented on HBASE-15470: FAILURE: Integrated in HBase-Trunk_matrix #782 (See [https://builds.apache.org/job/HBase-Trunk_matrix/782/]) HBASE-15470 Add a setting for Priority queue length (eclark: rev ac1a7a4a78966826d755a21faa007f9ae03f2cd0) * hbase-server/src/main/java/org/apache/hadoop/hbase/ipc/RpcExecutor.java * hbase-server/src/main/java/org/apache/hadoop/hbase/ipc/RpcScheduler.java * hbase-server/src/main/java/org/apache/hadoop/hbase/ipc/FifoRpcScheduler.java * hbase-server/src/main/java/org/apache/hadoop/hbase/ipc/SimpleRpcScheduler.java > Add a setting for Priority queue length > --- > > Key: HBASE-15470 > URL: https://issues.apache.org/jira/browse/HBASE-15470 > Project: HBase > Issue Type: Improvement > Components: IPC/RPC, Region Assignment >Affects Versions: 1.2.0 >Reporter: Elliott Clark >Assignee: Elliott Clark > Fix For: 2.0.0, 1.3.0 > > Attachments: HBASE-15470.patch > > > Meta can have very different request rates than any other region. We > shouldn't use the same call queue length. > For example: > If a normal request takes 100ms ( long scan or large get ) > but a call to meta is all in memory so it takes < 1ms > So a call queue length of 100 represents multiple seconds of work for normal > requests, but less than a second for meta. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (HBASE-15470) Add a setting for Priority queue length
[ https://issues.apache.org/jira/browse/HBASE-15470?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15198432#comment-15198432 ] Mikhail Antonov commented on HBASE-15470: - +1 > Add a setting for Priority queue length > --- > > Key: HBASE-15470 > URL: https://issues.apache.org/jira/browse/HBASE-15470 > Project: HBase > Issue Type: Improvement > Components: IPC/RPC, Region Assignment >Affects Versions: 1.2.0 >Reporter: Elliott Clark >Assignee: Elliott Clark > Fix For: 2.0.0, 1.3.0 > > Attachments: HBASE-15470.patch > > > Meta can have very different request rates than any other region. We > shouldn't use the same call queue length. > For example: > If a normal request takes 100ms ( long scan or large get ) > but a call to meta is all in memory so it takes < 1ms > So a call queue length of 100 represents multiple seconds of work for normal > requests, but less than a second for meta. -- This message was sent by Atlassian JIRA (v6.3.4#6332)