[
https://issues.apache.org/jira/browse/HBASE-2405?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12852960#action_12852960
]
stack commented on HBASE-2405:
------------------------------
@Andrew I like two queues idea; liveness queue and background-task queue. We'd
have multiple threads servicing the liveness queue but perhaps the single
worker doing the compactions and splits queue.
@Jon Yes, all should go via compactsplitthread. Lets fix that and make even
manual requests for compactions go this route. Understood about the worry
introducing more parallellism but ain't sure how else to do it if you don't
want to "block the thread processing the message" (even if we redo close so we
dbl-flush, it'll still take the same amount of elapsed time to close, it'll
just be taking writes longer before it puts up the close flag). And good point
that close, open, etc., will come in via callbacks though I envisioned the
callback would just add to the aforementioned queues and then return -- not
wait on close/open to complete.
> Close, split, open of regions in RegionServer are run by a single thread only.
> ------------------------------------------------------------------------------
>
> Key: HBASE-2405
> URL: https://issues.apache.org/jira/browse/HBASE-2405
> Project: Hadoop HBase
> Issue Type: Bug
> Reporter: stack
> Fix For: 0.20.4, 0.21.0
>
>
> JGray and Karthik observed yesterday that a regoin open message arrived at
> the regionserver but that the regionserver worker thread did not get around
> to the actually opening until 45 seconds later (region offline for 45
> seconds). We only run a single Worker thread in a regoinserver processing
> open, close, and splits. In this case, a long running close (or two) held up
> the worker thread. We need to run more than a single worker. A pool of
> workers? Should opens be prioritized?
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
