cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Nick Bailey (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (CASSANDRA-6696) Partition sstables by token range
Date Fri, 17 Apr 2015 17:47:01 GMT

    [ https://issues.apache.org/jira/browse/CASSANDRA-6696?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14500283#comment-14500283
] 

Nick Bailey commented on CASSANDRA-6696:
----------------------------------------

So I just want to mention on here that the current approach here isn't going to help us much
with CASSANDRA-4756.

If you don't update your compaction strategy, sstables will contain data from many vnodes
so things aren't much different than now. If you do use the new compaction strategy, things
are slightly better in that levels 1 or higher are split per vnode and you could deduplicate
that data, but level 0 won't be so you'll still be forced to overstream anything in level
0.

We may want to revisit a new approach to CASSANDRA-4756, specifically one that isn't compaction
strategy specific.

> Partition sstables by token range
> ---------------------------------
>
>                 Key: CASSANDRA-6696
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-6696
>             Project: Cassandra
>          Issue Type: Improvement
>          Components: Core
>            Reporter: sankalp kohli
>            Assignee: Marcus Eriksson
>              Labels: compaction, correctness, dense-storage, performance
>             Fix For: 3.0
>
>
> In JBOD, when someone gets a bad drive, the bad drive is replaced with a new empty one
and repair is run. 
> This can cause deleted data to come back in some cases. Also this is true for corrupt
stables in which we delete the corrupt stable and run repair. 
> Here is an example:
> Say we have 3 nodes A,B and C and RF=3 and GC grace=10days. 
> row=sankalp col=sankalp is written 20 days back and successfully went to all three nodes.

> Then a delete/tombstone was written successfully for the same row column 15 days back.

> Since this tombstone is more than gc grace, it got compacted in Nodes A and B since it
got compacted with the actual data. So there is no trace of this row column in node A and
B.
> Now in node C, say the original data is in drive1 and tombstone is in drive2. Compaction
has not yet reclaimed the data and tombstone.  
> Drive2 becomes corrupt and was replaced with new empty drive. 
> Due to the replacement, the tombstone in now gone and row=sankalp col=sankalp has come
back to life. 
> Now after replacing the drive we run repair. This data will be propagated to all nodes.

> Note: This is still a problem even if we run repair every gc grace. 
>  



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message