You are viewing a plain text version of this content. The canonical link for it is here.

Posted to commits@cassandra.apache.org by "Chris Goffinet (JIRA)" <ji...@apache.org> on 2010/03/14 08:29:27 UTC

[jira] Created: (CASSANDRA-893) Hinted Handoff Paging for Columns

Hinted Handoff Paging for Columns
---------------------------------

                 Key: CASSANDRA-893
                 URL: https://issues.apache.org/jira/browse/CASSANDRA-893
             Project: Cassandra
          Issue Type: Bug
    Affects Versions: 0.6
            Reporter: Chris Goffinet
            Priority: Minor


I noticed this in HHManager:

TODO handle rows that have incrementally grown too large for a single message.)

In CASSANDRA-883 I had noticed a lot of CPU burning cycles. I was unable to figure out until tonight why this was. We had a very very large row (9.2M+ columns). If this row ever got hinted, it was trying to load entire row into memory. 

It might be a good idea to actually add paging support (send target multiple row mutations) so that we don't have read the _entire_ row into memory.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.