[
https://issues.apache.org/jira/browse/HBASE-13082?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
ramkrishna.s.vasudevan updated HBASE-13082:
-------------------------------------------
Attachment: HBASE-13082_1_WIP.patch
Parking a work in progress patch. With my previous patches corrected
most of the test cases. Still few are failing. Looking into them.
The patch introduces a state inside the StoreFile and marks the reader if it is
COMPACTED or NOT_COMPACTED. Every time a scanner uses the storefile we also
increment a ref count. Any scanner getting created will try to check the state
and if the state is COMPACTED then those files will not be used by the scanner
instead only the new file created after compaction will be added. All the
COMPACTED files will be cleared by a background chore service that is
instantiated per store and that will clean up the store files that are in
COMPACTEd state and also that those that has ref count as 0.
> Coarsen StoreScanner locks to RegionScanner
> -------------------------------------------
>
> Key: HBASE-13082
> URL: https://issues.apache.org/jira/browse/HBASE-13082
> Project: HBase
> Issue Type: Bug
> Reporter: Lars Hofhansl
> Assignee: ramkrishna.s.vasudevan
> Attachments: 13082-test.txt, 13082-v2.txt, 13082-v3.txt,
> 13082-v4.txt, 13082.txt, 13082.txt, HBASE-13082_1_WIP.patch, gc.png, gc.png,
> gc.png, hits.png, next.png, next.png
>
>
> Continuing where HBASE-10015 left of.
> We can avoid locking (and memory fencing) inside StoreScanner by deferring to
> the lock already held by the RegionScanner.
> In tests this shows quite a scan improvement and reduced CPU (the fences make
> the cores wait for memory fetches).
> There are some drawbacks too:
> * All calls to RegionScanner need to be remain synchronized
> * Implementors of coprocessors need to be diligent in following the locking
> contract. For example Phoenix does not lock RegionScanner.nextRaw() and
> required in the documentation (not picking on Phoenix, this one is my fault
> as I told them it's OK)
> * possible starving of flushes and compaction with heavy read load.
> RegionScanner operations would keep getting the locks and the
> flushes/compactions would not be able finalize the set of files.
> I'll have a patch soon.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
