You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@qpid.apache.org by "Andy Goldstein (JIRA)" <ji...@apache.org> on 2011/05/26 15:45:51 UTC
[jira] [Created] (QPID-3280) Message throughput suffers in a
cluster when TTL set
Message throughput suffers in a cluster when TTL set
----------------------------------------------------
Key: QPID-3280
URL: https://issues.apache.org/jira/browse/QPID-3280
Project: Qpid
Issue Type: Bug
Components: C++ Broker
Affects Versions: 0.10
Reporter: Andy Goldstein
When sending a large number of messages with nonzero TTLs to a cluster, overall message throughput drops by around 20-30% compared to messages with TTL 0.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
---------------------------------------------------------------------
Apache Qpid - AMQP Messaging Implementation
Project: http://qpid.apache.org
Use/Interact: mailto:dev-subscribe@qpid.apache.org
[jira] [Resolved] (QPID-3280) Message throughput suffers in a
cluster when TTL set
Posted by "Alan Conway (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/QPID-3280?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Alan Conway resolved QPID-3280.
-------------------------------
Resolution: Fixed
Fix Version/s: 0.11
Fixed in revision #1136170
> Message throughput suffers in a cluster when TTL set
> ----------------------------------------------------
>
> Key: QPID-3280
> URL: https://issues.apache.org/jira/browse/QPID-3280
> Project: Qpid
> Issue Type: Bug
> Components: C++ Broker
> Affects Versions: 0.10
> Reporter: Andy Goldstein
> Assignee: Alan Conway
> Fix For: 0.11
>
> Attachments: cluster_ttl.diff
>
>
> When sending a large number of messages with nonzero TTLs to a cluster, overall message throughput drops by around 20-30% compared to messages with TTL 0.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
---------------------------------------------------------------------
Apache Qpid - AMQP Messaging Implementation
Project: http://qpid.apache.org
Use/Interact: mailto:dev-subscribe@qpid.apache.org
[jira] [Commented] (QPID-3280) Message throughput suffers in a
cluster when TTL set
Posted by "Andy Goldstein (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/QPID-3280?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13039708#comment-13039708 ]
Andy Goldstein commented on QPID-3280:
--------------------------------------
Attached potential patch to resolve issue. Added a new "cluster clock" CPG message that the cluster elder fires every so often (default is 10ms, but is configurable). Each node stores and uses the cluster clock when calculating message expiration time or determining if a message has expired. Also moved the QueueCleaner to the cluster timer when the broker is part of a cluster.
> Message throughput suffers in a cluster when TTL set
> ----------------------------------------------------
>
> Key: QPID-3280
> URL: https://issues.apache.org/jira/browse/QPID-3280
> Project: Qpid
> Issue Type: Bug
> Components: C++ Broker
> Affects Versions: 0.10
> Reporter: Andy Goldstein
> Attachments: cluster_ttl.diff
>
>
> When sending a large number of messages with nonzero TTLs to a cluster, overall message throughput drops by around 20-30% compared to messages with TTL 0.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
---------------------------------------------------------------------
Apache Qpid - AMQP Messaging Implementation
Project: http://qpid.apache.org
Use/Interact: mailto:dev-subscribe@qpid.apache.org
[jira] [Updated] (QPID-3280) Message throughput suffers in a
cluster when TTL set
Posted by "Andy Goldstein (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/QPID-3280?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Andy Goldstein updated QPID-3280:
---------------------------------
Attachment: cluster_ttl.diff
Potential patch to resolve issue. Added a new "cluster clock" CPG message that the cluster elder fires every so often (default is 10ms, but is configurable). Each node stores and uses the cluster clock when calculating message expiration time or determining if a message has expired. Also moved the QueueCleaner to the cluster timer when the broker is part of a cluster.
> Message throughput suffers in a cluster when TTL set
> ----------------------------------------------------
>
> Key: QPID-3280
> URL: https://issues.apache.org/jira/browse/QPID-3280
> Project: Qpid
> Issue Type: Bug
> Components: C++ Broker
> Affects Versions: 0.10
> Reporter: Andy Goldstein
> Attachments: cluster_ttl.diff
>
>
> When sending a large number of messages with nonzero TTLs to a cluster, overall message throughput drops by around 20-30% compared to messages with TTL 0.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
---------------------------------------------------------------------
Apache Qpid - AMQP Messaging Implementation
Project: http://qpid.apache.org
Use/Interact: mailto:dev-subscribe@qpid.apache.org
[jira] [Commented] (QPID-3280) Message throughput suffers in a
cluster when TTL set
Posted by "Alan Conway (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/QPID-3280?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13039920#comment-13039920 ]
Alan Conway commented on QPID-3280:
-----------------------------------
Rebased patch on trunk, review on reviewboard https://reviews.apache.org/r/791/
> Message throughput suffers in a cluster when TTL set
> ----------------------------------------------------
>
> Key: QPID-3280
> URL: https://issues.apache.org/jira/browse/QPID-3280
> Project: Qpid
> Issue Type: Bug
> Components: C++ Broker
> Affects Versions: 0.10
> Reporter: Andy Goldstein
> Attachments: cluster_ttl.diff
>
>
> When sending a large number of messages with nonzero TTLs to a cluster, overall message throughput drops by around 20-30% compared to messages with TTL 0.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
---------------------------------------------------------------------
Apache Qpid - AMQP Messaging Implementation
Project: http://qpid.apache.org
Use/Interact: mailto:dev-subscribe@qpid.apache.org
[jira] [Updated] (QPID-3280) Message throughput suffers in a
cluster when TTL set
Posted by "Andy Goldstein (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/QPID-3280?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Andy Goldstein updated QPID-3280:
---------------------------------
Comment: was deleted
(was: Attached potential patch to resolve issue. Added a new "cluster clock" CPG message that the cluster elder fires every so often (default is 10ms, but is configurable). Each node stores and uses the cluster clock when calculating message expiration time or determining if a message has expired. Also moved the QueueCleaner to the cluster timer when the broker is part of a cluster.)
> Message throughput suffers in a cluster when TTL set
> ----------------------------------------------------
>
> Key: QPID-3280
> URL: https://issues.apache.org/jira/browse/QPID-3280
> Project: Qpid
> Issue Type: Bug
> Components: C++ Broker
> Affects Versions: 0.10
> Reporter: Andy Goldstein
> Attachments: cluster_ttl.diff
>
>
> When sending a large number of messages with nonzero TTLs to a cluster, overall message throughput drops by around 20-30% compared to messages with TTL 0.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
---------------------------------------------------------------------
Apache Qpid - AMQP Messaging Implementation
Project: http://qpid.apache.org
Use/Interact: mailto:dev-subscribe@qpid.apache.org
[jira] [Assigned] (QPID-3280) Message throughput suffers in a
cluster when TTL set
Posted by "Alan Conway (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/QPID-3280?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Alan Conway reassigned QPID-3280:
---------------------------------
Assignee: Alan Conway
> Message throughput suffers in a cluster when TTL set
> ----------------------------------------------------
>
> Key: QPID-3280
> URL: https://issues.apache.org/jira/browse/QPID-3280
> Project: Qpid
> Issue Type: Bug
> Components: C++ Broker
> Affects Versions: 0.10
> Reporter: Andy Goldstein
> Assignee: Alan Conway
> Attachments: cluster_ttl.diff
>
>
> When sending a large number of messages with nonzero TTLs to a cluster, overall message throughput drops by around 20-30% compared to messages with TTL 0.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
---------------------------------------------------------------------
Apache Qpid - AMQP Messaging Implementation
Project: http://qpid.apache.org
Use/Interact: mailto:dev-subscribe@qpid.apache.org
[jira] [Issue Comment Edited] (QPID-3280) Message throughput
suffers in a cluster when TTL set
Posted by "Alan Conway (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/QPID-3280?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13049998#comment-13049998 ]
Alan Conway edited comment on QPID-3280 at 6/15/11 8:18 PM:
------------------------------------------------------------
Fixed on trunk #1136170
Patch provided by Andy Goldstein
was (Author: aconway):
Fixed on trunk #1136170
> Message throughput suffers in a cluster when TTL set
> ----------------------------------------------------
>
> Key: QPID-3280
> URL: https://issues.apache.org/jira/browse/QPID-3280
> Project: Qpid
> Issue Type: Bug
> Components: C++ Broker
> Affects Versions: 0.10
> Reporter: Andy Goldstein
> Assignee: Alan Conway
> Attachments: cluster_ttl.diff
>
>
> When sending a large number of messages with nonzero TTLs to a cluster, overall message throughput drops by around 20-30% compared to messages with TTL 0.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
---------------------------------------------------------------------
Apache Qpid - AMQP Messaging Implementation
Project: http://qpid.apache.org
Use/Interact: mailto:dev-subscribe@qpid.apache.org
[jira] [Commented] (QPID-3280) Message throughput suffers in a
cluster when TTL set
Posted by "Alan Conway (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/QPID-3280?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13049998#comment-13049998 ]
Alan Conway commented on QPID-3280:
-----------------------------------
Fixed on trunk #1136170
> Message throughput suffers in a cluster when TTL set
> ----------------------------------------------------
>
> Key: QPID-3280
> URL: https://issues.apache.org/jira/browse/QPID-3280
> Project: Qpid
> Issue Type: Bug
> Components: C++ Broker
> Affects Versions: 0.10
> Reporter: Andy Goldstein
> Assignee: Alan Conway
> Attachments: cluster_ttl.diff
>
>
> When sending a large number of messages with nonzero TTLs to a cluster, overall message throughput drops by around 20-30% compared to messages with TTL 0.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
---------------------------------------------------------------------
Apache Qpid - AMQP Messaging Implementation
Project: http://qpid.apache.org
Use/Interact: mailto:dev-subscribe@qpid.apache.org
[jira] [Commented] (QPID-3280) Message throughput suffers in a
cluster when TTL set
Posted by "Alan Conway (Commented) (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/QPID-3280?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13184110#comment-13184110 ]
Alan Conway commented on QPID-3280:
-----------------------------------
As part of this fix, failures regarding "cluster timer task" were also fixed
> Message throughput suffers in a cluster when TTL set
> ----------------------------------------------------
>
> Key: QPID-3280
> URL: https://issues.apache.org/jira/browse/QPID-3280
> Project: Qpid
> Issue Type: Bug
> Components: C++ Broker
> Affects Versions: 0.10
> Reporter: Andy Goldstein
> Assignee: Alan Conway
> Fix For: 0.11
>
> Attachments: cluster_ttl.diff
>
>
> When sending a large number of messages with nonzero TTLs to a cluster, overall message throughput drops by around 20-30% compared to messages with TTL 0.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
---------------------------------------------------------------------
Apache Qpid - AMQP Messaging Implementation
Project: http://qpid.apache.org
Use/Interact: mailto:dev-subscribe@qpid.apache.org