Bug 678153 - System crash with ext4 and heavy load
Summary: System crash with ext4 and heavy load
Keywords:
Status: CLOSED UPSTREAM
Alias: None
Product: Red Hat Enterprise Linux 5
Classification: Red Hat
Component: kernel
Version: 5.5.z
Hardware: x86_64
OS: Linux
unspecified
unspecified
Target Milestone: rc
: ---
Assignee: Red Hat Kernel Manager
QA Contact: Red Hat Kernel QE team
URL:
Whiteboard:
Depends On:
Blocks:
TreeView+ depends on / blocked
 
Reported: 2011-02-16 22:14 UTC by Shad L. Lords
Modified: 2013-02-26 16:56 UTC (History)
1 user (show)

Fixed In Version:
Doc Type: Bug Fix
Doc Text:
Clone Of:
Environment:
Last Closed: 2013-02-26 16:56:09 UTC
Target Upstream Version:

Attachments (Terms of Use)
screen capture of crash (227.94 KB, image/png)
2011-02-16 22:14 UTC, Shad L. Lords 		no flags Details
View All Add an attachment (proposed patch, testcase, etc.)

Description Shad L. Lords 2011-02-16 22:14:25 UTC 
Created attachment 479222 [details]
screen capture of crash

Description of problem:

When running a heavy load (db2 load) against several 1TB ext4 partitions the box will consistently hang/crash.

How reproducible:

6 times over 2 days

Actual results:

See screenshot.

Expected results:

System doesn't crash

Additional info:

When runing the exact same load using xfs instead of ext4 the system has no issues.
Comment 1 Ric Wheeler 2011-02-17 15:01:59 UTC 
Please work with Red Hat support to open a ticket - they can help us collect information that is needed for debugging issues.

Thanks!
Comment 2 Shad L. Lords 2011-02-17 15:30:18 UTC 
Don't have a RHEL support contract and not sure how to contact/work with Red Hat support.  Am willing to do what I can to help you reproduce this as fixing it will benefit all.

This was experienced on a CentOS box.
Comment 3 Ric Wheeler 2011-02-17 16:07:29 UTC 
Red Hat bugzilla is normally used to help our support people work with our customers.

If you don't have a subscription, I think that the best thing would be to have you report issue to the right upstream mailing lists (linux-ext4 in this case).

For those reports, please put in lots of detail - type of machine (cpu type & count, DRAM amount, type of storage) - and the backtrace from the crash.

Thanks!
Note You need to log in before you can comment on or make changes to this bug.