hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "ramkrishna.s.vasudevan (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (HBASE-13082) Coarsen StoreScanner locks to RegionScanner
Date Tue, 13 Oct 2015 07:11:06 GMT

     [ 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)

Mime
View raw message