Mailing-List: contact hdfs-issues-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Reply-To: hdfs-issues@hadoop.apache.org
Date: Wed, 15 Jan 2014 17:00:25 +0000 (UTC)
From: "Kihwal Lee (JIRA)" <jira@apache.org>
To: hdfs-issues@hadoop.apache.org
Message-ID: <JIRA.12680353.1384975201906.7171.1389805225524@arcas>
In-Reply-To: <JIRA.12680353.1384975201906@arcas>
References: <JIRA.12680353.1384975201906@arcas>
Subject: [jira] [Commented] (HDFS-5535) Umbrella jira for improved HDFS
 rolling upgrades
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable


    [ https://issues.apache.org/jira/browse/HDFS-5535?page=3Dcom.atlassian.=
jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=3D13872=
269#comment-13872269 ]=20

Kihwal Lee commented on HDFS-5535:
----------------------------------

bq. The total time required to upgrade a cluster MUST not exceed #Nodes_in_=
cluster * 10 seconds.
This is about how fast the upgrade process can go while minimally impacting=
 service and data availability. Please note that this is a requirement for =
the upgrade feature. It does not dictate what users should do.  This requir=
ement exists mainly to help users estimate how soon a cluster can be upgrad=
ed and also force us to guarantee estimates stay valid in the future.

bq. Probably meant to say that old software should be able to support whate=
ver state of the file system left after the upgrade experiment was terminat=
ed?
I know you didn't intended it to be, but this sounds like the requirement i=
s reduced to maintaining file system integrity. It could simply be "Data du=
rability must not be compromised by upgrades or downgrades".

bq. May be it needs to roll edits in some special way to indicate the start=
 of the rolling upgrade?
I believe this came up during discussions, but do not remember the conclusi=
on.  We will clarify this.

bq. What is MTTR?
Mean time to recovery.

bq. Looks like Lite-Decom and =E2=80=9COptimizing DN Restart time=E2=80=9D =
are competing proposals
Yes, indeed. We will do the latter, which will be more in-line with existin=
g tool-driven approaches.  Lite-Decom may be considered in later developmen=
t phases for other use cases(e.g. the case Ming Ma mentioned above), but re=
gular DN rolling upgrade won't depend on it. =20

> Umbrella jira for improved HDFS rolling upgrades
> ------------------------------------------------
>
>                 Key: HDFS-5535
>                 URL: https://issues.apache.org/jira/browse/HDFS-5535
>             Project: Hadoop HDFS
>          Issue Type: New Feature
>          Components: datanode, ha, hdfs-client, namenode
>    Affects Versions: 3.0.0, 2.2.0
>            Reporter: Nathan Roberts
>         Attachments: HDFSRollingUpgradesHighLevelDesign.pdf
>
>
> In order to roll a new HDFS release through a large cluster quickly and s=
afely, a few enhancements are needed in HDFS. An initial High level design =
document will be attached to this jira, and sub-jiras will itemize the indi=
vidual tasks.


--
This message was sent by Atlassian JIRA
(v6.1.5#6160)