You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@cassandra.apache.org by "David Alves (JIRA)" <ji...@apache.org> on 2012/07/17 23:00:41 UTC

[jira] [Comment Edited] (CASSANDRA-1123) Allow tracing query details

    [ https://issues.apache.org/jira/browse/CASSANDRA-1123?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13416363#comment-13416363 ] 

David Alves edited comment on CASSANDRA-1123 at 7/17/12 9:00 PM:
-----------------------------------------------------------------

First patch that implements most of what was suggested, with accompanying test.

Still to define/discuss:
- aaraon original version "replaced" the logger which meant there were already a lot of things being traced. As is this patch is pretty "bare" in terms of trace events in the sense that stuff that goes through CassandraServer gets a new trace session but not much else is traced (even though sessions get propagated across threads and nodes). Maybe we could add events automatically when a session is propagated across stages and across nodes, therefore getting a per-stage and per-node view of how things are executed (I think this could be done rather unintrusively)?

- I haven't added the log to the logger option yet, as I'm not completely sure how useful it is if events are generated per stage/node.


                
      was (Author: dr-alves):
    First patch that implements most of what was suggested, with accompanying test.

Still to define/discuss:
- aaraons "replaced" the logger with meant there were already a lot of things being logged. As is this patch is pretty "bare" in terms of trace events in the sense that stuff that goes through CassandraServer gets a new trace session but not much else is traced (even though session gets propagated across threads and nodes). Maybe we could add events automatically when a session is propagated across stages and across nodes?
- I haven't added the log to the logger option yet, as I'm not completely sure how useful it is if events are generated per stage/node.

                  
> Allow tracing query details
> ---------------------------
>
>                 Key: CASSANDRA-1123
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-1123
>             Project: Cassandra
>          Issue Type: New Feature
>          Components: Core
>            Reporter: Jonathan Ellis
>            Assignee: David Alves
>             Fix For: 1.2
>
>         Attachments: 1123-3.patch.gz, 1123.patch
>
>
> In the spirit of CASSANDRA-511, it would be useful to tracing on queries to see where latency is coming from: how long did row cache lookup take?  key search in the index?  merging the data from the sstables?  etc.
> The main difference vs setting debug logging is that debug logging is too big of a hammer; by turning on the flood of logging for everyone, you actually distort the information you're looking for.  This would be something you could set per-query (or more likely per connection).
> We don't need to be as sophisticated as the techniques discussed in the following papers but they are interesting reading:
> http://research.google.com/pubs/pub36356.html
> http://www.usenix.org/events/osdi04/tech/full_papers/barham/barham_html/
> http://www.usenix.org/event/nsdi07/tech/fonseca.html

--
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