hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Francis Liu (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-15156) Support first assignment of split daughters to non-parent RS
Date Wed, 03 Feb 2016 03:20:39 GMT

    [ https://issues.apache.org/jira/browse/HBASE-15156?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15129708#comment-15129708
] 

Francis Liu commented on HBASE-15156:
-------------------------------------

Thanks for the review [~stack] some responses:

{quote}
We assign daughters to the same node as parent because this way we can get the data back on
line more promptly.
{quote}
What was the reason it was faster? In terms of assigment overhead I don't think there's much
difference in zkless land since everything has to go through the master now before becoming
visible.

{quote}
On patch, seems fine for branch-1. Should update doc on method to say sna and snb are optional
on splitRegion.
{quote}
Will do.

{quote}
On patch, seems fine for branch-1. Should update doc on method to say sna and snb are optional
on splitRegion.
{quote}
What would need to be done to get it into trunk?

{quote}
public static final String ASSIGN_DAUGHTERS_AFTER_SPLIT =
"hbase.split.unassign";
{quote}
will fix.

{quote}
Could you group the two clausees that get invoked when shouldAssignAfterSplit == true ?
{quote}
will do.

{quote}
What region is being offlined here: regionOffline(hri, State.SPLIT); .. the parent?
{quote}
Yup parent. 

{quote}
Why not have this assign happen in the call to onRegionSplit?
{quote}
Because it's just a waste of RPC. We already do something similar if the RS performing the
split dies, so this is not unprecendent. 

{quote}
!services.getConfiguration().getBoolean(HConstants.ASSIGN_DAUGHTERS_AFTER_SPLIT, false)) {
{quote}
Will consolidate. we can actually take this a step further and embed in the response to reportRegionInTransition()
call to master wether the RS should online the daughter regions. This way we need only the
config set on the master minimizes config errors?





> Support first assignment of split daughters to non-parent RS
> ------------------------------------------------------------
>
>                 Key: HBASE-15156
>                 URL: https://issues.apache.org/jira/browse/HBASE-15156
>             Project: HBase
>          Issue Type: New Feature
>            Reporter: Francis Liu
>            Assignee: Francis Liu
>         Attachments: HBASE-15156.patch
>
>
> On region split, the region's daughter is always opened by the same region server hosting
the parent region. In some cases this is not ideal:
> This feature was mainly needed for favored nodes to allow for more freedom when selecting
favored nodes for daughter regions. ie The daughter doesn't have to always select the regionserver
hosting the split as a favored node which should allow for better favored node distribution.
> Though this feature is actually useful in cases where region splits occur much more often
than the balancer is run. It also is a bit more efficient as the major compaction that occurs
after daughter assignment does not go to waste (ie cancelled half-way, loss of locality due
to move, etc). We actually run it this way in some of our clusters even without favored nodes
enabled. Hence I am supplying a patch which is independent of favored nodes.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message