Bug 960591 - IO errors due to transport endpoint not connected when one of the servers go down in replicate pair
Summary: IO errors due to transport endpoint not connected when one of the servers go ...
Keywords:
Status: CLOSED DUPLICATE of bug 961275
Alias: None
Product: Red Hat Gluster Storage
Classification: Red Hat Storage
Component: glusterfs
Version: 2.1
Hardware: Unspecified
OS: Unspecified
unspecified
unspecified
Target Milestone: ---
: ---
Assignee: Amar Tumballi
QA Contact: Sudhir D
URL:
Whiteboard:
Depends On:
Blocks:
TreeView+ depends on / blocked
 
Reported: 2013-05-07 12:57 UTC by Sachidananda Urs
Modified: 2013-12-19 00:09 UTC (History)
3 users (show)

Fixed In Version:
Doc Type: Bug Fix
Doc Text:
Clone Of:
Environment:
Last Closed: 2013-05-10 06:47:35 UTC
Embargoed:

Attachments (Terms of Use)
Client logs (12.12 KB, application/x-bzip)
2013-05-07 12:57 UTC, Sachidananda Urs 		no flags Details
View All

Description Sachidananda Urs 2013-05-07 12:57:11 UTC 
Created attachment 744720 [details]
Client logs

Description of problem:

After some intense IO on the mount point, bring down one of the servers. IO errors are seen on the client. Lookup/readdir works fine, but cp fails. Attached client logs.


Version-Release number of selected component (if applicable):

glusterfs 3.4.0.3rhs built on May  3 2013 08:27:13

How reproducible:

Always.

Steps to Reproduce:
1. Run 20-30 parallel kernel compiles.
2. Run 20-30 parallel kernel extracts
3. cp -r a few gb to data
4. Bring down one of the servers (pull the plug)
Comment 2 Sachidananda Urs 2013-05-10 06:47:35 UTC 

*** This bug has been marked as a duplicate of bug 961275 ***
Note You need to log in before you can comment on or make changes to this bug.