[jira] [Commented] (TS-1238) RAM cache hit rate unexpectedly low
[ https://issues.apache.org/jira/browse/TS-1238?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13277202#comment-13277202 ] Bryan Call commented on TS-1238: You can ignore the information about the average object size. That was for disk cache. I don't know what I was thinking at the time... After a couple days the CFLUS is getting about the same cache hit ratio as LRU. In a five minute period it is too hard to tell. Sometimes it is better or worse by ~.1%. It would be nice to have a stat for the number of times that cache fails to get a lock. I would assume there are different locks for RAM and disk cache? Also, it is my understanding that if Traffic Server can't get a lock it will retry a configurable number of times and go to the origin server. It might be nice to have a stat for when this happens too. RAM cache hit rate unexpectedly low --- Key: TS-1238 URL: https://issues.apache.org/jira/browse/TS-1238 Project: Traffic Server Issue Type: Bug Components: Cache Affects Versions: 3.1.3 Reporter: John Plevyak Assignee: John Plevyak Fix For: 3.1.4 Attachments: TS-1238-jp-1.patch The RAM cache is not getting the expected hit rate. Looks like there are a couple issues. -- 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-1238) RAM cache hit rate unexpectedly low
[ https://issues.apache.org/jira/browse/TS-1238?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13276422#comment-13276422 ] John Plevyak commented on TS-1238: -- I think the problem is that the LRU cache doesn't account for its overhead, while the CLFUS cache does which puts it at an unfair disadvantage in terms of relative true memory used per byte allocated. The CLFUS cache is much better behaved when the working set is larger than the RAM cache size and it supports compression. I am going to commit this fix and leave CLFUS as the default and file another bug to fix the accounting for ram in the LRU cache. I think this will make the performance comparable in the best case and better in worse cases. RAM cache hit rate unexpectedly low --- Key: TS-1238 URL: https://issues.apache.org/jira/browse/TS-1238 Project: Traffic Server Issue Type: Bug Components: Cache Affects Versions: 3.1.3 Reporter: John Plevyak Assignee: John Plevyak Fix For: 3.1.4 Attachments: TS-1238-jp-1.patch The RAM cache is not getting the expected hit rate. Looks like there are a couple issues. -- 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-1238) RAM cache hit rate unexpectedly low
[ https://issues.apache.org/jira/browse/TS-1238?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13274771#comment-13274771 ] Bryan Call commented on TS-1238: I am running a patched version of 3.1.3 in production right now. It is busy filling up the ram cache. Since we are already running 3.1.3 in production and using LRU, I thought it would be a better A/B test to patch 3.1.3 instead of using HEAD and introducing more variables. RAM cache hit rate unexpectedly low --- Key: TS-1238 URL: https://issues.apache.org/jira/browse/TS-1238 Project: Traffic Server Issue Type: Bug Components: Cache Affects Versions: 3.1.3 Reporter: John Plevyak Assignee: John Plevyak Fix For: 3.1.4 Attachments: TS-1238-jp-1.patch The RAM cache is not getting the expected hit rate. Looks like there are a couple issues. -- 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-1238) RAM cache hit rate unexpectedly low
[ https://issues.apache.org/jira/browse/TS-1238?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13270768#comment-13270768 ] Leif Hedstrom commented on TS-1238: --- Is this committed and fixed on trunk? Or are we pending more changes? I'm trying to get a handle on 3.1.4 release, so we can get a 3.2 release out soon... RAM cache hit rate unexpectedly low --- Key: TS-1238 URL: https://issues.apache.org/jira/browse/TS-1238 Project: Traffic Server Issue Type: Bug Components: Cache Affects Versions: 3.1.3 Reporter: John Plevyak Assignee: John Plevyak Fix For: 3.1.4 Attachments: TS-1238-jp-1.patch The RAM cache is not getting the expected hit rate. Looks like there are a couple issues. -- 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-1238) RAM cache hit rate unexpectedly low
[ https://issues.apache.org/jira/browse/TS-1238?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13271042#comment-13271042 ] John Plevyak commented on TS-1238: -- It isn't committed. Bryan was going to try it out. It changes one of the defaults (probably for the better) for RAM caching, but I wanted to give him a chance to take a look. I'll see if I can figure it out myself as well. It should be a very safe change. RAM cache hit rate unexpectedly low --- Key: TS-1238 URL: https://issues.apache.org/jira/browse/TS-1238 Project: Traffic Server Issue Type: Bug Components: Cache Affects Versions: 3.1.3 Reporter: John Plevyak Assignee: John Plevyak Fix For: 3.1.4 Attachments: TS-1238-jp-1.patch The RAM cache is not getting the expected hit rate. Looks like there are a couple issues. -- 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-1238) RAM cache hit rate unexpectedly low
[ https://issues.apache.org/jira/browse/TS-1238?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13266717#comment-13266717 ] Bryan Call commented on TS-1238: I will coordinate the testing of the patch, but it might take a couple days. I will shoot for Friday right now looking at my schedule. I had a feeling that it might have to do with the seen filter since it doesn't take effect until the cache is full. It might be nice to have a configuration option on how many hits you need before it is promoted to ram cache. On some workings sets having this configured to 1 might be better. RAM cache hit rate unexpectedly low --- Key: TS-1238 URL: https://issues.apache.org/jira/browse/TS-1238 Project: Traffic Server Issue Type: Bug Components: Cache Affects Versions: 3.1.3 Reporter: John Plevyak Assignee: John Plevyak Fix For: 3.1.4 Attachments: TS-1238-jp-1.patch The RAM cache is not getting the expected hit rate. Looks like there are a couple issues. -- 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