[
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.
