[
https://issues.apache.org/jira/browse/CASSANDRA-2864?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13063293#comment-13063293
]
Daniel Doubleday commented on CASSANDRA-2864:
---------------------------------------------
Agreed to some extend.
I guess my point is that while I certainly think that the said tasks will help
and in most cases probably mitigate the need for row caching I assume that
there still will be other cases such as relatively small hot data sets with
loads of reads and writes that you would normally put in memcache or such. For
those I think you get more bang.
But we will see. Can always do a shoot-out after the improvements are in.
Also I think that one shared row-cache for all CFs that is only configured with
max size in MB that can do CASSANDRA-1956 (dont cache row but row + filter) and
read through BRAF that skips cache could be worth testing. But this will
probably end in the big 'Would be cool if I hade the time'-box.
> Alternative Row Cache Implementation
> ------------------------------------
>
> Key: CASSANDRA-2864
> URL: https://issues.apache.org/jira/browse/CASSANDRA-2864
> Project: Cassandra
> Issue Type: Improvement
> Components: Core
> Affects Versions: 0.8.1
> Reporter: Daniel Doubleday
> Priority: Minor
> Attachments: rowcache.patch
>
>
> we have been working on an alternative implementation to the existing row
> cache(s)
> We have 2 main goals:
> - Decrease memory -> get more rows in the cache without suffering a huge
> performance penalty
> - Reduce gc pressure
> This sounds a lot like we should be using the new serializing cache in 0.8.
> Unfortunately our workload consists of loads of updates which would
> invalidate the cache all the time.
> The second unfortunate thing is that the idea we came up with doesn't fit the
> new cache provider api...
> It looks like this:
> Like the serializing cache we basically only cache the serialized byte
> buffer. we don't serialize the bloom filter and try to do some other minor
> compression tricks (var ints etc not done yet). The main difference is that
> we don't deserialize but use the normal sstable iterators and filters as in
> the regular uncached case.
> So the read path looks like this:
> return filter.collectCollatedColumns(memtable iter, cached row iter)
> The write path is not affected. It does not update the cache
> During flush we merge all memtable updates with the cached rows.
> The attached patch is based on 0.8 branch r1143352
> It does not replace the existing row cache but sits aside it. Theres
> environment switch to choose the implementation. This way it is easy to
> benchmark performance differences.
> -DuseSSTableCache=true enables the alternative cache. It shares its
> configuration with the standard row cache. So the cache capacity is shared.
> We have duplicated a fair amount of code. First we actually refactored the
> existing sstable filter / reader but than decided to minimize dependencies.
> Also this way it is easy to customize serialization for in memory sstable
> rows.
> We have also experimented a little with compression but since this task at
> this stage is mainly to kick off discussion we wanted to keep things simple.
> But there is certainly room for optimizations.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
