VM: killing process - How to identify the problem

VM: killing process - How to identify the problem

[Mudeem Siddiqui]

Hi all, 

I have linux 2.4.25 on a mips processor. Other than my application, the
other processes that are running on the system are udhcpd, dhcpd,
mini_dns etc. The applicaiton is quite memory intensive, it has
allocated 5 MB of a buffer which acts as a queue and the applicaiton
queues and de-queues packets in the queue at frequents intervals. The
memory for this buffer is allocated just once when the application
starts at the time of boot. So I would assume that there would be quite
a lot of paging going on. 

The issue is that randomly the application gets killed, there is no
segmnetation fault or anything and if I look at /var/log/messages I see
quite a lot of 

__alloc_pages: 0-order allocation failed 
__alloc_pages: 0-order allocation failed 
__alloc_pages: 0-order allocation failed 


and then 

VM: killing process 

I have read that the application can be killed if the kernel is not able
to service the paging request or oom-killer can also kill the process.
How can I confirm that one of these is happening? I want to identify the
root cause of the application crash before experimenting like increasing
the swap space or even disable the oom-killer (i don't know if that
would be a good idea though). Any suggestions 

Thanks 
Mudeem 

Re: VM: killing process - How to identify the problem

[Jiri Slaby]

On 05/20/2008 11:10 PM, Mudeem Siddiqui wrote:
> Hi all, 
> 
> I have linux 2.4.25 on a mips processor. Other than my application, the

Just curious, is is a typo?

> other processes that are running on the system are udhcpd, dhcpd,
> mini_dns etc. The applicaiton is quite memory intensive, it has
> allocated 5 MB of a buffer which acts as a queue and the applicaiton
> queues and de-queues packets in the queue at frequents intervals. The
> memory for this buffer is allocated just once when the application
> starts at the time of boot. So I would assume that there would be quite
> a lot of paging going on. 
> 
> The issue is that randomly the application gets killed, there is no
> segmnetation fault or anything and if I look at /var/log/messages I see
> quite a lot of 
> 
> __alloc_pages: 0-order allocation failed 
> __alloc_pages: 0-order allocation failed 
> __alloc_pages: 0-order allocation failed 
> 
> 
> and then 
> 
> VM: killing process 

Caused by out of memory, a page fault couldn't be serviced due to memory 
exhaustion. See arch/mips/mm/fault.c.

RE: VM: killing process - How to identify the problem

[Mudeem Siddiqui]

>Just curious, is is a typo?

I would say is is is a typo :)

>> 
>> __alloc_pages: 0-order allocation failed
>> __alloc_pages: 0-order allocation failed
>> __alloc_pages: 0-order allocation failed
>> 
>> 
>> and then 
>> 
>> VM: killing process 

>Caused by out of memory, a page fault couldn't be serviced due to
memory 
>exhaustion. See arch/mips/mm/fault.c.

Can this condition arise due to some other reason other than memory
leak. E.g the way the paging is being done etc because the application
calls malloc only once when it starts. I have been struggling with this
for quite a while, how would you recommend I should try to solve this?

Thanks