Re: [Bug #30572] 2.6.38-rc7, OOM behaviour?

[David Rientjes]

On Sun, 27 Mar 2011, Rafael J. Wysocki wrote:

> This message has been generated automatically as a part of a summary report
> of recent regressions.
> 
> The following bug entry is on the current list of known regressions
> from 2.6.37.  Please verify if it still should be listed and let the tracking team
> know (either way).
> 
> 
> Bug-Entry	: http://bugzilla.kernel.org/show_bug.cgi?id=30572
> Subject		: 2.6.38-rc7, OOM behaviour?
> Submitter	: Mathias BurÃn <mathias.buren@xxxxxxxxx>
> Date		: 2011-03-02 19:33 (26 days old)
> Message-ID	: <AANLkTine5sru_JsK1LmRVa9fwxjPsaDdZUTFPCBi6A+c@xxxxxxxxxxxxxx>
> References	: http://marc.info/?l=linux-kernel&m=129909440018096&w=2
> 

The log that was presented in the References link is a normal oom killer 
log and would be typical if you exhausted 1GB of swap space.  It correctly 
kills the chrome process in the log provided, but other relevant portions 
seem to have been snipped for futher diagnosis.

Mathias, could you please provide the entire oom killer output, 
specifically the last time it was invoked (search for "invoked 
oom\-killer" and paste everything after the last occurrence)?