You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@trafficserver.apache.org by "Zhao Yongming (JIRA)" <ji...@apache.org> on 2011/08/24 09:31:29 UTC
[jira] [Created] (TS-931) cluster latency too high, about 24ms
cluster latency too high, about 24ms
------------------------------------
Key: TS-931
URL: https://issues.apache.org/jira/browse/TS-931
Project: Traffic Server
Issue Type: Improvement
Components: Clustering
Affects Versions: 3.0.1, 3.1.1
Environment: cluster type 1, content hashing
Reporter: Zhao Yongming
Fix For: 3.1.1
when we enable full clustering, the performance is unacceptable, it add about 24ms per request. we'd expect <10ms latency for each cluster request.
this issue is for weijin :D
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (TS-931) cluster latency too high, about 24ms
Posted by "Leif Hedstrom (Commented) (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/TS-931?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13121052#comment-13121052 ]
Leif Hedstrom commented on TS-931:
----------------------------------
Can this be closed ?
> cluster latency too high, about 24ms
> ------------------------------------
>
> Key: TS-931
> URL: https://issues.apache.org/jira/browse/TS-931
> Project: Traffic Server
> Issue Type: Improvement
> Components: Clustering
> Affects Versions: 3.1.1, 3.0.1
> Environment: cluster type 1, content hashing
> Reporter: Zhao Yongming
> Assignee: weijin
> Fix For: 3.1.1
>
> Attachments: cluster_performance.patch
>
>
> when we enable full clustering, the performance is unacceptable, it add about 24ms per request. we'd expect <10ms latency for each cluster request.
> this issue is for weijin :D
--
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
[jira] [Commented] (TS-931) cluster latency too high, about 24ms
Posted by "weijin (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/TS-931?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13093625#comment-13093625 ]
weijin commented on TS-931:
---------------------------
Base on the current framework, it`s hard to reduce the cluster rt to smaller than 10ms. I will continue to focus on performance issues。
> cluster latency too high, about 24ms
> ------------------------------------
>
> Key: TS-931
> URL: https://issues.apache.org/jira/browse/TS-931
> Project: Traffic Server
> Issue Type: Improvement
> Components: Clustering
> Affects Versions: 3.1.1, 3.0.1
> Environment: cluster type 1, content hashing
> Reporter: Zhao Yongming
> Assignee: weijin
> Fix For: 3.1.1
>
> Attachments: cluster_performance.patch
>
>
> when we enable full clustering, the performance is unacceptable, it add about 24ms per request. we'd expect <10ms latency for each cluster request.
> this issue is for weijin :D
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-931) cluster latency too high, about 24ms
Posted by "weijin (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/TS-931?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
weijin updated TS-931:
----------------------
Attachment: cluster_performance.patch
This patch will reduce the cluster response time. In my test, cluster memory cache hit:
300qps(9.9ms~10.2ms); 600qps(10.5ms~12ms). I did not test the rt under very high pressure.
> cluster latency too high, about 24ms
> ------------------------------------
>
> Key: TS-931
> URL: https://issues.apache.org/jira/browse/TS-931
> Project: Traffic Server
> Issue Type: Improvement
> Components: Clustering
> Affects Versions: 3.1.1, 3.0.1
> Environment: cluster type 1, content hashing
> Reporter: Zhao Yongming
> Assignee: weijin
> Fix For: 3.1.1
>
> Attachments: cluster_performance.patch
>
>
> when we enable full clustering, the performance is unacceptable, it add about 24ms per request. we'd expect <10ms latency for each cluster request.
> this issue is for weijin :D
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Closed] (TS-931) cluster latency too high, about 24ms
Posted by "Zhao Yongming (Closed) (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/TS-931?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Zhao Yongming closed TS-931.
----------------------------
Resolution: Fixed
> cluster latency too high, about 24ms
> ------------------------------------
>
> Key: TS-931
> URL: https://issues.apache.org/jira/browse/TS-931
> Project: Traffic Server
> Issue Type: Improvement
> Components: Clustering
> Affects Versions: 3.1.1, 3.0.1
> Environment: cluster type 1, content hashing
> Reporter: Zhao Yongming
> Assignee: weijin
> Fix For: 3.1.1
>
> Attachments: cluster_performance.patch
>
>
> when we enable full clustering, the performance is unacceptable, it add about 24ms per request. we'd expect <10ms latency for each cluster request.
> this issue is for weijin :D
--
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
[jira] [Assigned] (TS-931) cluster latency too high, about 24ms
Posted by "weijin (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/TS-931?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
weijin reassigned TS-931:
-------------------------
Assignee: weijin
> cluster latency too high, about 24ms
> ------------------------------------
>
> Key: TS-931
> URL: https://issues.apache.org/jira/browse/TS-931
> Project: Traffic Server
> Issue Type: Improvement
> Components: Clustering
> Affects Versions: 3.1.1, 3.0.1
> Environment: cluster type 1, content hashing
> Reporter: Zhao Yongming
> Assignee: weijin
> Fix For: 3.1.1
>
>
> when we enable full clustering, the performance is unacceptable, it add about 24ms per request. we'd expect <10ms latency for each cluster request.
> this issue is for weijin :D
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira