[
https://issues.apache.org/jira/browse/CASSANDRA-7272?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15090687#comment-15090687
]
Jiri Horky commented on CASSANDRA-7272:
---------------------------------------
Just got across this ticket. The comments says this for LCS:
??Make it possible to major compact LCS - write 10 files in L1, 100 files in L2
etc, starting from the lowest token (meaning L1 will not overlap at all with
L2, we need to test this how it works when there is a lot of data on the node)??
This reminds me of ticket CASSANDRA-6284.
I think that by not having full token range the node is responsible for in each
level, you are creating quite a performance problem for further compactions.
With 5 levels, L2 contains some 0.09% of data with 100 sstables, which in this
case, would translate to 0.09% of the token range the node is responsible for.
Now, if there are new writes coming, they are for the entire token range of the
node. So if there are some new sstables in L0, and then in L1, they would need
to be compacted with all the 100 sstables below in L2. The ideal case is 10, so
this creates 10x more IO. The same situation will repeat in further levels.
> Add "Major" Compaction to LCS
> ------------------------------
>
> Key: CASSANDRA-7272
> URL: https://issues.apache.org/jira/browse/CASSANDRA-7272
> Project: Cassandra
> Issue Type: Improvement
> Reporter: T Jake Luciani
> Assignee: Marcus Eriksson
> Priority: Minor
> Labels: compaction, docs-impacting
> Fix For: 2.2.0 beta 1
>
>
> LCS has a number of minor issues (maybe major depending on your perspective).
> LCS is primarily used for wide rows so for instance when you repair data in
> LCS you end up with a copy of an entire repaired row in L0. Over time if you
> repair you end up with multiple copies of a row in L0 - L5. This can make
> predicting disk usage confusing.
> Another issue is cleaning up tombstoned data. If a tombstone lives in level
> 1 and data for the cell lives in level 5 the data will not be reclaimed from
> disk until the tombstone reaches level 5.
> I propose we add a "major" compaction for LCS that forces consolidation of
> data to level 5 to address these.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
