hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Lars Hofhansl (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (HBASE-13082) Coarsen StoreScanner locks to RegionScanner
Date Sun, 08 Mar 2015 06:16:39 GMT

     [ https://issues.apache.org/jira/browse/HBASE-13082?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Lars Hofhansl updated HBASE-13082:
----------------------------------
    Attachment: 13082-v3.txt

This one does pass TestAtomicOperation. But see how nasty it is.
Coprocessors now have to take care of setting the lock, if they don't everything is going
to work until a scanner interleaves with a flush/compaction. That one could get an NPE, or
if the wrong lock was set, wrong data could silently be returned.
(Although it *is* clear from the StoreScanner's constructor that the lock needs to be passed).

> 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: Lars Hofhansl
>             Fix For: 2.0.0, 1.1.0
>
>         Attachments: 13082-test.txt, 13082-v2.txt, 13082-v3.txt, 13082.txt, 13082.txt,
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