Mailing-List: contact cassandra-commits-help@incubator.apache.org;
 run by ezmlm
Precedence: bulk
Reply-To: cassandra-dev@incubator.apache.org
Message-ID: <1759262941.1258664979651.JavaMail.jira@brutus>
Date: Thu, 19 Nov 2009 21:09:39 +0000 (UTC)
From: "Stu Hood (JIRA)" <jira@apache.org>
To: cassandra-commits@incubator.apache.org
Subject: [jira] Updated: (CASSANDRA-193) Proactive repair
In-Reply-To: <761101744.1242935325628.JavaMail.jira@brutus>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


     [ https://issues.apache.org/jira/browse/CASSANDRA-193?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Stu Hood updated CASSANDRA-193:
-------------------------------

    Attachment: 193-6-inverted-filter.diff

New version of patch 6 to resolve the Cachetable/rendezvous issues I noticed last night.

I don't see any more bugs, but I did some testing with a table containing 10^6 keys, and a Readonly compaction took 2 minutes (!). Hopefully a little bit of profiling will expose the issue quickly, because I can understand that performance like that should prevent merging this patch. I'll try and get a new version out this evening.

> Proactive repair
> ----------------
>
>                 Key: CASSANDRA-193
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-193
>             Project: Cassandra
>          Issue Type: New Feature
>          Components: Core
>            Reporter: Jonathan Ellis
>            Assignee: Stu Hood
>             Fix For: 0.5
>
>         Attachments: 193-1-tree-preparation.diff, 193-1-tree-preparation.diff, 193-2-tree.diff, 193-2-tree.diff, 193-3-aes-preparation.diff, 193-3-aes-preparation.diff, 193-4-aes.diff, 193-4-aes.diff, 193-5-manual-repair.diff, 193-6-inverted-filter.diff, 193-6-inverted-filter.diff, 193-breakdown.txt, mktree-and-binary-tree.png
>
>
> Currently cassandra supports "read repair," i.e., lazy repair when a read is done.  This is better than nothing but is not sufficient for some cases (e.g. catastrophic node failure where you need to rebuild all of a node's data on a new machine).
> Dynamo uses merkle trees here.  This is harder for Cassandra given the CF data model but I suppose we could just hash the serialized CF value.

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