[
https://issues.apache.org/jira/browse/CASSANDRA-2901?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Jonathan Ellis updated CASSANDRA-2901:
--------------------------------------
Description:
Moved from CASSANDRA-1876:
There are five stages: read, deserialize, merge, serialize, and write. We
probably want to continue doing read+deserialize and serialize+write together,
or you waste a lot copying to/from buffers.
So, what I would suggest is: one thread per input sstable doing read +
deserialize (a row at a time). A thread pool (one per core?) merging
corresponding rows from each input sstable. One thread doing serialize +
writing the output (this has to wait for the merge threads to complete
in-order, obviously). This should take us from being CPU bound on SSDs (since
only one core is compacting) to being I/O bound.
This will require roughly 2x the memory, to allow the reader threads to work
ahead of the merge stage. (I.e. for each input sstable you will have up to one
row in a queue waiting to be merged, and the reader thread working on the
next.) Seems quite reasonable on that front. You'll also want a small queue
size for the serialize-merged-rows executor.
Multithreaded compaction should be either on or off. It doesn't make sense to
try to do things halfway (by doing the reads with a
threadpool whose size you can grow/shrink, for instance): we still have
compaction threads tuned to low priority, by default, so the impact on the rest
of the system won't be very different. Nor do we expect to have so many input
sstables that we lose a lot in context switching between reader threads.
IMO it's acceptable to punt completely on rows that are larger than memory, and
fall back to the old non-parallel code there. I don't see any sane way to
parallelize large-row compactions.
was:
Moved from CASSANDRA-1876:
There are five stages: read, deserialize, merge, serialize, and write. We
probably want to continue doing read+deserialize and serialize+write together,
or you waste a lot copying to/from buffers.
So, what I would suggest is: one thread per input sstable doing read +
deserialize (a row at a time). One thread merging corresponding rows from each
input sstable. One thread doing serialize + writing the output. This should
give us between 2x and 3x speedup (depending how much doing the merge on
another thread than write saves us).
This will require roughly 2x the memory, to allow the reader threads to work
ahead of the merge stage. (I.e. for each input sstable you will have up to one
row in a queue waiting to be merged, and the reader thread working on the
next.) Seems quite reasonable on that front.
Multithreaded compaction should be either on or off. It doesn't make sense to
try to do things halfway (by doing the reads with a
threadpool whose size you can grow/shrink, for instance): we still have
compaction threads tuned to low priority, by default, so the impact on the rest
of the system won't be very different. Nor do we expect to have so many input
sstables that we lose a lot in context switching between reader threads. (If
this is a concern, we already have a tunable to limit the number of sstables
merged at a time in a single CF.)
IMO it's acceptable to punt completely on rows that are larger than memory, and
fall back to the old non-parallel code there. I don't see any sane way to
parallelize large-row compactions.
> Allow taking advantage of multiple cores while compacting a single CF
> ---------------------------------------------------------------------
>
> Key: CASSANDRA-2901
> URL: https://issues.apache.org/jira/browse/CASSANDRA-2901
> Project: Cassandra
> Issue Type: Improvement
> Components: Core
> Reporter: Jonathan Ellis
> Priority: Minor
> Fix For: 0.8.2
>
>
> Moved from CASSANDRA-1876:
> There are five stages: read, deserialize, merge, serialize, and write. We
> probably want to continue doing read+deserialize and serialize+write
> together, or you waste a lot copying to/from buffers.
> So, what I would suggest is: one thread per input sstable doing read +
> deserialize (a row at a time). A thread pool (one per core?) merging
> corresponding rows from each input sstable. One thread doing serialize +
> writing the output (this has to wait for the merge threads to complete
> in-order, obviously). This should take us from being CPU bound on SSDs (since
> only one core is compacting) to being I/O bound.
> This will require roughly 2x the memory, to allow the reader threads to work
> ahead of the merge stage. (I.e. for each input sstable you will have up to
> one row in a queue waiting to be merged, and the reader thread working on the
> next.) Seems quite reasonable on that front. You'll also want a small queue
> size for the serialize-merged-rows executor.
> Multithreaded compaction should be either on or off. It doesn't make sense to
> try to do things halfway (by doing the reads with a
> threadpool whose size you can grow/shrink, for instance): we still have
> compaction threads tuned to low priority, by default, so the impact on the
> rest of the system won't be very different. Nor do we expect to have so many
> input sstables that we lose a lot in context switching between reader threads.
> IMO it's acceptable to punt completely on rows that are larger than memory,
> and fall back to the old non-parallel code there. I don't see any sane way to
> parallelize large-row compactions.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
