Mailing-List: contact yarn-issues-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Reply-To: yarn-issues@hadoop.apache.org
Date: Thu, 22 Oct 2015 22:35:27 +0000 (UTC)
From: "Wangda Tan (JIRA)" <jira@apache.org>
To: yarn-issues@hadoop.apache.org
Message-ID: <JIRA.12906904.1445466689000.33993.1445553327749@Atlassian.JIRA>
In-Reply-To: <JIRA.12906904.1445466689000@Atlassian.JIRA>
References: <JIRA.12906904.1445466689000@Atlassian.JIRA>
 <JIRA.12906904.1445466689102@arcas>
Subject: [jira] [Commented] (YARN-4287) Capacity Scheduler: Rack Locality
 improvement
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


    [ https://issues.apache.org/jira/browse/YARN-4287?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14970026#comment-14970026 ] 

Wangda Tan commented on YARN-4287:
----------------------------------

Some suggestions
1) RACK_LOCALITY_EXTRA_DELAY -> RACK_LOCALITY_DELAY, same as configuration property name (rack-locality-delay)

2) Do you think if is it a good idea to separate old rack-locality-delay computation (using getLocalityWaitFactor) and new rack-locality-delay config? Now rack-locality-delay = min(old-computed-delay, new-specified-delay), since the getLocalityWaitFactor has some flaws, I think we can make this configurable so user can choose to use specified or computed.

Pseudo code may look like:
{code}
if type is OFF_SWITCH:
  if rack-locality-delay specified:
    delay = rack-locality-delay
  else:
    delay = computed-locality-delay
else if type is RACK_LOCAL:
    delay = min(node-locality-delay, computed-or-specified-rack-locality-delay)
{code}

3)
bq. When we're getting rackLocal assignments, subsequent rackLocal assignments should not be delayed
+1 to the fix, since this is a behavior change, do you think if we need to make this configurable? This change could lead to #node-local container allocation decreasing in some cases.


Thanks,
Wangda

> Capacity Scheduler: Rack Locality improvement
> ---------------------------------------------
>
>                 Key: YARN-4287
>                 URL: https://issues.apache.org/jira/browse/YARN-4287
>             Project: Hadoop YARN
>          Issue Type: Improvement
>          Components: capacityscheduler
>    Affects Versions: 2.7.1
>            Reporter: Nathan Roberts
>            Assignee: Nathan Roberts
>         Attachments: YARN-4287-v2.patch, YARN-4287.patch
>
>
> YARN-4189 does an excellent job describing the issues with the current delay scheduling algorithms within the capacity scheduler. The design proposal also seems like a good direction.
> This jira proposes a simple interim solution to the key issue we've been experiencing on a regular basis:
>  - rackLocal assignments trickle out due to nodeLocalityDelay. This can have significant impact on things like CombineFileInputFormat which targets very specific nodes in its split calculations.
> I'm not sure when YARN-4189 will become reality so I thought a simple interim patch might make sense. The basic idea is simple: 
> 1) Separate delays for rackLocal, and OffSwitch (today there is only 1)
> 2) When we're getting rackLocal assignments, subsequent rackLocal assignments should not be delayed
> Patch will be uploaded shortly. No big deal if the consensus is to go straight to YARN-4189. 


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