cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Sylvain Lebresne (Commented) (JIRA)" <>
Subject [jira] [Commented] (CASSANDRA-3721) Staggering repair
Date Tue, 24 Jan 2012 16:52:41 GMT


Sylvain Lebresne commented on CASSANDRA-3721:

What I suggest for now is to separate the snapshotting parts from this patch (we can even
spawn a new ticket) because it changes the network protocol, so if we don't get it for 1.1,
we'll kind of have to wait for 1.2 with our current rule of not changing the protocol version
during a major cycle. I won't have time to look at the rest for the 1.1 freeze, but we can
get it for 1.1.1. 
> Staggering repair
> -----------------
>                 Key: CASSANDRA-3721
>                 URL:
>             Project: Cassandra
>          Issue Type: Improvement
>          Components: Core
>    Affects Versions: 1.1
>            Reporter: Vijay
>            Assignee: Vijay
>            Priority: Minor
>             Fix For: 1.1
>         Attachments: 0001-staggering-repair-with-snapshot.patch
> Currently repair runs on all the nodes at once and causing the range of data to be hot
(higher latency on reads).
> Sequence:
> 1) Send a repair request to all of the nodes so we can hold the references of the SSTables
(point at which repair was initiated)
> 2) Send Validation on one node at a time (once completed will release references).
> 3) Hold the reference of the tree in the requesting node and once everything is complete
start diff.
> We can also serialize the streaming part not more than 1 node is involved in the streaming.

This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators:!default.jspa
For more information on JIRA, see:


View raw message