xfs
[Top] [All Lists]

ADD 821124 - Deadlock in extent conversion

To: lord@xxxxxxx
Subject: ADD 821124 - Deadlock in extent conversion
From: pv@xxxxxxxxxxxxx (ananth@xxxxxxxxxxxx)
Date: Fri, 13 Apr 2001 16:08:58 -0700 (PDT)
Cc: linux-xfs@xxxxxxxxxxx
Reply-to: sgi.bugs.xfs@xxxxxxxxxxxxxxxxx
Sender: owner-linux-xfs@xxxxxxxxxxx
Webexec: webpvupdate,pvincident
Webpv: sgigate.sgi.com
View Incident: 
http://co-op.engr.sgi.com/BugWorks/code/bwxquery.cgi?search=Search&wlong=1&view_type=Bug&wi=821124

 Status : closed                       Priority : 2                         
 Assigned Engineer : lord              Submitter : ananth                   
*Modified User : ananth               *Modified User Domain : engr          
*Description :
This problem seen with XFS 1.0 bits on a 64 M, 2CPU system with
1 scsi disk. Tests being run in parallel:

while true; do holes -l 300000000 -b 4099   -i 7 -c 7 /xfs/holes; date; done

and AIM 7, run to crossover.

It took about 3-4 hours to hit this problem, by then
AIM had gone to about 170 processes. In the end,
console became unresponsive ... looking at time-stamps

.....


==========================
ADDITIONAL INFORMATION (ADD)
From: ananth@engr (BugWorks)
Date: Apr 13 2001 04:08:58PM
==========================



Looks like we are not out of the woods yet. Here's
the latest failure. System is not dead yet, since
I know panic tries to sync the file systems, so
there must be a backtrace available soon (back to bta):

-----------
[root@delilah /root]# __alloc_pages: 5-order allocation failed.
kmem_shake( 256): pruning i/dcache @ line #117[16]
__alloc_pages: 5-order allocation failed.
kmem_shake( 273): pruning i/dcache @ line #117[15]
__alloc_pages: 5-order allocation failed.
kmem_shake( 292): pruning i/dcache @ line #117[14]
__alloc_pages: 5-order allocation failed.
kmem_shake( 315): pruning i/dcache @ line #117[13]
__alloc_pages: 5-order allocation failed.
kmem_shake( 341): pruning i/dcache @ line #117[12]
__alloc_pages: 5-order allocation failed.
kmem_shake( 372): pruning i/dcache @ line #117[11]
__alloc_pages: 5-order allocation failed.
kmem_shake( 409): pruning i/dcache @ line #117[10]
__alloc_pages: 5-order allocation failed.
kmem_shake( 455): pruning i/dcache @ line #117[9]
__alloc_pages: 5-order allocation failed.
kmem_shake( 512): pruning i/dcache @ line #117[8]
__alloc_pages: 5-order allocation failed.
kmem_shake( 585): pruning i/dcache @ line #117[7]
__alloc_pages: 5-order allocation failed.
kmem_shake( 682): pruning i/dcache @ line #117[6]
__alloc_pages: 5-order allocation failed.
kmem_shake( 819): pruning i/dcache @ line #117[5]
__alloc_pages: 5-order allocation failed.
kmem_shake(1024): pruning i/dcache @ line #117[4]
__alloc_pages: 5-order allocation failed.
kmem_shake(1365): pruning i/dcache @ line #117[3]
__alloc_pages: 5-order allocation failed.
kmem_shake(2048): pruning i/dcache @ line #117[2]
__alloc_pages: 5-order allocation failed.
kmem_shake(   0): pruning i/dcache @ line #117[1]
__alloc_pages: 5-order allocation failed.
Kernel panic: kmem_alloc: NULL memory on KM_SLEEP request!

Message from syslogd@localhost at Fri Apr 13 14:29:01 2001 ...
localhost kernel: Kernel panic: kmem_alloc: NULL memory on KM_SLEEP request!
------------------

This happened at around load average of 200.

more soon,

ananth.

<Prev in Thread] Current Thread [Next in Thread>