Mailing-List: contact common-issues-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Reply-To: common-issues@hadoop.apache.org
Date: Wed, 16 Jan 2013 16:56:13 +0000 (UTC)
From: "Daryn Sharp (JIRA)" <jira@apache.org>
To: common-issues@hadoop.apache.org
Message-ID: <JIRA.12624326.1355770458109.145990.1358355373585@arcas>
In-Reply-To: <JIRA.12624326.1355770458109@arcas>
References: <JIRA.12624326.1355770458109@arcas>
Subject: [jira] [Commented] (HADOOP-9150) Unnecessary DNS resolution
 attempts for logical URIs
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


    [ https://issues.apache.org/jira/browse/HADOOP-9150?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13555198#comment-13555198 ] 

Daryn Sharp commented on HADOOP-9150:
-------------------------------------

Skimming the patch, to reduce adding more methods and complexity, maybe we should consider either of the following:
# Default impl of {{getCanonicalUri()}} just returns {{getUri()}}.  Filesystem like DFS can specifically override {{getCanonicalUri}} to call {{NetUtils.getCanonicalUri}}.  The advantage is that it won't preclude other/future logical filesystems from utilizing a port.
# {{getCanonicalUri()}} continues to call {{NetUtils.getCanonicalUri}}.  Logical filesystems should have a default port of -1 (ie. URI considers this as no port), so perhaps {{NetUtils.getCanonicalUri}} can just return the given uri if there's no default port.

I lean towards #1.
                
> Unnecessary DNS resolution attempts for logical URIs
> ----------------------------------------------------
>
>                 Key: HADOOP-9150
>                 URL: https://issues.apache.org/jira/browse/HADOOP-9150
>             Project: Hadoop Common
>          Issue Type: Bug
>          Components: fs/s3, ha, performance, viewfs
>    Affects Versions: 3.0.0, 2.0.2-alpha
>            Reporter: Todd Lipcon
>            Assignee: Todd Lipcon
>            Priority: Critical
>         Attachments: hadoop-9150.txt, hadoop-9150.txt, hadoop-9150.txt, hadoop-9150.txt, log.txt, tracing-resolver.tgz
>
>
> In the FileSystem code, we accidentally try to DNS-resolve the logical name before it is converted to an actual domain name. In some DNS setups, this can cause a big slowdown - eg in one misconfigured cluster we saw a 2-3x drop in terasort throughput, since every task wasted a lot of time waiting for slow "not found" responses from DNS.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira