On Thu, Jan 19, 2006 at 05:49:20PM -0800, Andrew Morton wrote:
> Dave Jones <[email protected]> wrote:
> >
> > The Fedora user in the bug report
> > https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=175173
> > who on x86-64 with 5GB saw zone_dma exhausted saw a similar result,
> > delays the kill, but it does still happen.
>
> Again, that person's ZONE_DMA has *zero* pages on the LRU. Something has
> consumed all of the piddling little zone for kernel data structures. It is
> a true oom.
>
> We need to work out who is using all this ZONE_DMA memory and make them
> stop it.
It reminds me, we had a similar problem in the 2.4.x kernel with
many SCSI hosts loaded - that caused scsi_malloc (which uses DMA)
to consume a lot of DMA memory and trigger the OOM. I know that code
was much rewritten for 2.6.x, through DMA allocations in the SCSI
subsystem (regardless of drivers) still exist here and there.
--
Dan Aloni
[email protected], [email protected], [email protected], [email protected]
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
[Index of Archives]
[Kernel Newbies]
[Netfilter]
[Bugtraq]
[Photo]
[Stuff]
[Gimp]
[Yosemite News]
[MIPS Linux]
[ARM Linux]
[Linux Security]
[Linux RAID]
[Video 4 Linux]
[Linux for the blind]
[Linux Resources]
