Re: Pb of __alloc_pages

Marcelo Tosatti (marcelo@conectiva.com.br)
Mon, 11 Jun 2001 22:33:38 -0300 (BRT)


On Mon, 11 Jun 2001, Didier CONTIS wrote:

> -----BEGIN PGP SIGNED MESSAGE-----
> Hash: SHA1
>
> I am building a Beowulf cluster using Dell PowerEdge 1400SC
> (2x800Mhz, 1GB of ram, 9GB Ultra160) and using kernel 2.4.5
>
> I several of my nodes I am getting the following errors:
>
> Jun 10 00:19:32 grendel16 kernel: __alloc_pages: 0-order allocation
> failed.
> Jun 10 00:19:32 grendel16 last message repeated 12 times
> Jun 10 00:19:36 grendel16 kernel: ed.
> Jun 10 00:19:36 grendel16 kernel: __alloc_pages: 0-order allocation
> failed.
> Jun 10 00:19:55 grendel16 last message repeated 363 times
> Jun 10 00:23:32 grendel16 kernel: VFS: file-max limit 8192 reached
>
> Below is the output of cat /proc/slabinfo
>
> I was wondering if someone could help me debug this one.
>
> Thanks in advance for any help,

Could you please try 2.4.6pre1 or higher?

Since you seem to have an IO intensive workload (right?), pre1 should
throttle those IO allocations and avoid the extreme memory shortage.

Thanks

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/