[jira] [Commented] (CASSANDRA-2045) Simplify HH to decrease read load when nodes come back

["Edward Capriolo (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/CASSANDRA-2045?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13025978#comment-13025978 ] 

Edward Capriolo commented on CASSANDRA-2045:
--------------------------------------------

I wanted to suggest two ideas.

* Commit Log 
Store it in commit log format
Stream the commit log to the awoken host
let the awoken host worry about replay throttling

* store hints in a separate physical column family. Still have hinted pointers
when finding data for the "pointer" the Read has to read through the much smaller hinted handoff table, rather then the actual data table. This

* store hints in separate physical column family (IE write twice)
Then stream the files to the awoken node.


> Simplify HH to decrease read load when nodes come back
> ------------------------------------------------------
>
>                 Key: CASSANDRA-2045
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-2045
>             Project: Cassandra
>          Issue Type: Improvement
>            Reporter: Chris Goffinet
>             Fix For: 1.0
>
>
> Currently when HH is enabled, hints are stored, and when a node comes back, we begin sending that node data. We do a lookup on the local node for the row to send. To help reduce read load (if a node is offline for long period of time) we should store the data we want forward the node locally instead. We wouldn't have to do any lookups, just take byte[] and send to the destination.

--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira