Mailing-List: contact common-issues-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Date: Thu, 9 Jun 2016 15:30:21 +0000 (UTC)
From: "Steve Loughran (JIRA)" <jira@apache.org>
To: common-issues@hadoop.apache.org
Message-ID: <JIRA.12946546.1457012319000.40535.1465486221594@Atlassian.JIRA>
In-Reply-To: <JIRA.12946546.1457012319000@Atlassian.JIRA>
References: <JIRA.12946546.1457012319000@Atlassian.JIRA> <JIRA.12946546.1457012319991@arcas>
Subject: [jira] [Commented] (HADOOP-12878) Impersonate hosts in s3a for
 better data locality handling
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable
archived-at: Thu, 09 Jun 2016 15:30:23 -0000


    [ https://issues.apache.org/jira/browse/HADOOP-12878?page=3Dcom.atlassi=
an.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=3D15=
322700#comment-15322700 ]=20

Steve Loughran commented on HADOOP-12878:
-----------------------------------------

"*" is certainly something that is used in resource requests...I'd don't se=
e it being used in any filesystem block location status calls. I suspect th=
at any long-lived application will be doing hostname matching on the blocks=
 that come back for locality =E2=80=94and may not work with a "*" (it's not=
 a hostname after all), or not treat it that well.

Assuming the hostname was configurable: you'd give it a list, it'd return a=
 random subset of them, people could experiment with "*" and "offsite.examp=
le.org" to see what worked well.

> Impersonate hosts in s3a for better data locality handling
> ----------------------------------------------------------
>
>                 Key: HADOOP-12878
>                 URL: https://issues.apache.org/jira/browse/HADOOP-12878
>             Project: Hadoop Common
>          Issue Type: Sub-task
>          Components: fs/s3
>    Affects Versions: 2.8.0
>            Reporter: Thomas Demoor
>            Assignee: Thomas Demoor
>
> Currently, {{localhost}} is passed as locality for each block, causing al=
l blocks involved in job to initially target the same node (RM), before bei=
ng moved by the scheduler (to a rack-local node). This reduces parallelism =
for jobs (with short-lived mappers).=20
> We should mimic Azures implementation: a config setting {{fs.s3a.block.lo=
cation.impersonatedhost}} where the user can enter the list of hostnames in=
 the cluster to return to {{getFileBlockLocations}}.=20
> Possible optimization: for larger systems, it might be better to return N=
 (5?) random hostnames to prevent passing a huge array (the downstream code=
 assumes size =3D O(3)).


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

---------------------------------------------------------------------
To unsubscribe, e-mail: common-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: common-issues-help@hadoop.apache.org