[
https://issues.apache.org/jira/browse/CASSANDRA-8193?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14208794#comment-14208794
]
Yuki Morishita commented on CASSANDRA-8193:
-------------------------------------------
Say you have RF of dc1=1, dc2=1, dc3=1, then your
DatacenterAwareRequestCoordinator will send merkle tree requests to all
datacenters at once, which ends up to the same behavior as
ParallelRequestCoordinator.
bq. I think it's more of a performance improvement rather than a new feature.
I gree this is improvement, but at least we need to preserve current behavior.
If you can make this to be an extension, then, in my opinion, it is safe to put
this into 2.0.
> Multi-DC parallel snapshot repair
> ---------------------------------
>
> Key: CASSANDRA-8193
> URL: https://issues.apache.org/jira/browse/CASSANDRA-8193
> Project: Cassandra
> Issue Type: Improvement
> Reporter: Jimmy Mårdell
> Assignee: Jimmy Mårdell
> Priority: Minor
> Fix For: 2.0.12
>
> Attachments: cassandra-2.0-8193-1.txt
>
>
> The current behaviour of snapshot repair is to let one node at a time
> calculate a merkle tree. This is to ensure only one node at a time is doing
> the expensive calculation. The drawback is that it takes even longer time to
> do the merkle tree calculation.
> In a multi-DC setup, I think it would make more sense to have one node in
> each DC calculate the merkle tree at the same time. This would yield a
> significant improvement when you have many data centers.
> I'm not sure how relevant this is in 2.1, but I don't see us upgrading to 2.1
> any time soon. Unless there is an obvious drawback that I'm missing, I'd like
> to implement this in the 2.0 branch.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
