[
https://issues.apache.org/jira/browse/HBASE-13082?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14964005#comment-14964005
]
stack commented on HBASE-13082:
-------------------------------
The one pager is great ([~lhofhansl]!). Nice summary of the issue up top.
Explanation of the approach your fix takes helps.
I am trying to understand the COMPACTED vs NON_COMPACTED state. Is
NON_COMPACTED a freshly-flushed file? Is a COMPACTED file a file that is made
up of N other storefiles and you want to make sure the scan doesn't include
duplicated info -- the compacted file and the compactions inputs?
Or I think you are saying that when a file is COMPACTED, then its content can
be found in another file and so it should not be included in a scan? Should the
state be COMPACTED_AWAY or REPLACED (by file...). Do we need the NON_COMPACTED
state? It is the default. No need to call this state anything (Active?)
How can the following happen? "Now in case of the versioned storefile approach
change, there is a chance that there are reference files which are not yet
archived after compaction because of the change in the store file management."
Where will you write the COMPACTED_AWAY state? In memory or into the file? (I
suppose you can't write it to the file because it is already written)
Doc is great [~ram_krish]
> 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.pdf, HBASE-13082_1_WIP.patch,
> HBASE-13082_2_WIP.patch, HBASE-13082_3.patch, HBASE-13082_4.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)
