Bug 174086

Summary:	NFS-Client consumes all memory by putting larg files
Product:	Red Hat Enterprise Linux 4	Reporter:	Falko Pilz <falko.pilz>
Component:	kernel	Assignee:	Steve Dickson <steved>
Status:	CLOSED NOTABUG	QA Contact:	Brian Brock <bbrock>
Severity:	high	Docs Contact:
Priority:	medium
Version:	4.0	CC:	coughlan, jbaron, lwoodman
Target Milestone:	---
Target Release:	---
Hardware:	i386
OS:	Linux
Whiteboard:
Fixed In Version:		Doc Type:	Bug Fix
Doc Text:		Story Points:	---
Clone Of:		Environment:
Last Closed:	2006-11-01 19:50:04 UTC	Type:	---
Regression:	---	Mount Type:	---
Documentation:	---	CRM:
Verified Versions:		Category:	---
oVirt Team:	---	RHEL 7.3 requirements from Atomic Host:
Cloudforms Team:	---	Target Upstream Version:
Embargoed:

Description Falko Pilz 2005-11-24 11:57:22 UTC

From Bugzilla Helper:
User-Agent: Mozilla/5.0 (X11; U; Linux i686; de-DE; rv:1.7.5) Gecko/20041215 Firefox/1.0 Red Hat/1.0-12.EL4

Description of problem:
Our Environment ist this: 
one computer is a RHEL4 AS on 4way Xeon (i386) with 20 GB RAM (here as NFS-Server)
the other is a RHEL 3 AS on S390 (here as NFS-Server)

If we write a file larger than the available memory, the application works until all of the memory is used, than the applikation crashes with an "out of memory" message.
If we copy or move such a file, the crash happens as a kernel panic saying something like that: "no more memory available, no processes to kill"

There isn't at no time any swapping be done.

Version-Release number of selected component (if applicable):
kernel-2.6.9-5ELsmp

How reproducible:
Always

Steps to Reproduce:
1. We have a file nearly 22GB large, if we save, copy or move them on a NFS-mounted directory

Actual Results:  Applikation or kernel crashes

Expected Results:  The move, copy or save should succeed

Additional info:

Comment 1 Steve Dickson 2005-12-09 12:52:32 UTC

Please post a snap shot of the system memory when this happens
by doing a sysrq-M (or echo m > /proc/sysrq-trigger). The output
will be in /var/log/messages.

Also a system backtrace at this point might prove to be useful as
well... Use sysrq-T or 'echo t > /proc/sysrq-trigger" which also
dumps the backtrace in /var/log/messages.

Comment 3 Larry Woodman 2005-12-15 18:40:43 UTC

Please attach the console output that this show_free_areas() prints out just
before the panic:

--------------------------------------------------------------------------
        p = select_bad_process();
                                                                               
                        
        /* Found nothing?!?! Either we hang forever, or we panic. */
        if (!p) {
                show_free_areas();
                panic("Out of memory and no killable processes...\n");
        }
                                                                               
                       
--------------------------------------------------------------------------


Thanks, Larry Woodman

Comment 8 Steve Dickson 2006-11-01 19:50:04 UTC

Being there has not been any outside activity on the bug
since its been open '2005-11-24' I'm going to close this as
not a bug.... please feel free to reopen if this is not the case...