hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Brian Bockelman (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HADOOP-4775) FUSE crashes reliably on 0.19.0
Date Wed, 10 Dec 2008 20:34:44 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-4775?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12655347#action_12655347
] 

Brian Bockelman commented on HADOOP-4775:
-----------------------------------------

After increasing the memory in LIBHDFS_OPTS, fuse_dfs no longer completely deadlocks.  Instead,
it continues to use 100-200% CPU and 1-1.5GB memory, but still processes new requests.

It seems that something (maybe an error handling routine?) is causing an infinite loop which
caused the deadlocks.

Brian

> FUSE crashes reliably on 0.19.0
> -------------------------------
>
>                 Key: HADOOP-4775
>                 URL: https://issues.apache.org/jira/browse/HADOOP-4775
>             Project: Hadoop Core
>          Issue Type: Bug
>          Components: contrib/fuse-dfs
>            Reporter: Brian Bockelman
>            Priority: Critical
>         Attachments: fuse_lotsofmem_bt.txt, fuse_lotsofmem_pmap.txt
>
>
> Every morning I come in and find many nodes which have developed the dreaded "Transport
endpoint not connected" error overnight.  This has only started after the 0.19.0 upgrade.

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


Mime
View raw message