hadoop-mapreduce-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Aaron Kimball (JIRA)" <j...@apache.org>
Subject [jira] Commented: (MAPREDUCE-1231) Distcp is very slow
Date Wed, 25 Nov 2009 19:23:39 GMT

    [ https://issues.apache.org/jira/browse/MAPREDUCE-1231?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12782566#action_12782566

Aaron Kimball commented on MAPREDUCE-1231:

Arun: I agree that using the checksums should be the default if this is the behavior that
users have come to expect.

rsync does its transfer-list generation based on file length and mtime (and, optionally, a
checksum as well with {{-c}}). Checking only on the length feels risky to me. I think that
it would be  much more convincing if {{sameFile()}} included an mtime comparison. This shouldn't
add significant processing overhead, since the same {{getStatus()}} call returns both length
and mtime. (For this to work right, though, you'd need to preserve the mtime on the receiver
OS, which is done with {{-pt}}. So maybe disabling checksum should also recommend the use
of {{-pt}} in a message to the user?) 

And if mtime comparisons were added, that should also be user-ignorable.

> Distcp is very slow
> -------------------
>                 Key: MAPREDUCE-1231
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-1231
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: distcp
>    Affects Versions: 0.20.1
>            Reporter: Jothi Padmanabhan
>            Assignee: Jothi Padmanabhan
>             Fix For: 0.20.2
>         Attachments: mapred-1231-v1.patch, mapred-1231-v2.patch, mapred-1231-y20-v2.patch,
mapred-1231-y20.patch, mapred-1231.patch
> Currently distcp does a checksums check in addition to file length check to decide if
a remote file has to be copied. If the number of files is high (thousands), this checksum
check is proving to be fairly costly leading to a long time before the copy is started.

This message is automatically generated by JIRA.
You can reply to this email to add a comment to the issue online.

View raw message