slub crashes on dma allocations
in [Kernel]
|
Prev: intel_idle: create a native cpuidle driver for select intel processors
Next: [PATCH 8/8] intel_idle: create a native cpuidle driver for select intel processors
From: Christoph Lameter on 27 May 2010 10:30 So S390 has NUMA and the minalign is allowing very small slabs of 8/16/32 bytes? Try this patch From: Christoph Lameter <cl(a)linux-foundation.org> Subject: SLUB: Allow full duplication of kmalloc array for 390 Seems that S390 is running out of kmalloc caches. Increase the number of kmalloc caches to a safe size. Signed-off-by: Christoph Lameter <cl(a)linux-foundation.org> --- include/linux/slub_def.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) Index: linux-2.6/include/linux/slub_def.h =================================================================== --- linux-2.6.orig/include/linux/slub_def.h 2010-05-27 09:14:16.000000000 -0500 +++ linux-2.6/include/linux/slub_def.h 2010-05-27 09:14:26.000000000 -0500 @@ -140,7 +140,7 @@ struct kmem_cache { #ifdef CONFIG_ZONE_DMA #define SLUB_DMA __GFP_DMA /* Reserve extra caches for potential DMA use */ -#define KMALLOC_CACHES (2 * SLUB_PAGE_SHIFT - 6) +#define KMALLOC_CACHES (2 * SLUB_PAGE_SHIFT) #else /* Disable DMA functionality */ #define SLUB_DMA (__force gfp_t)0 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Heiko Carstens on 27 May 2010 15:10 On Thu, May 27, 2010 at 09:17:17AM -0500, Christoph Lameter wrote: > > So S390 has NUMA and the minalign is allowing very small slabs of 8/16/32 bytes? No NUMA, but minalign is 8. > Try this patch > > From: Christoph Lameter <cl(a)linux-foundation.org> > Subject: SLUB: Allow full duplication of kmalloc array for 390 > > Seems that S390 is running out of kmalloc caches. > > Increase the number of kmalloc caches to a safe size. > > Signed-off-by: Christoph Lameter <cl(a)linux-foundation.org> Yes, that fixes the bug. Thanks! -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Pekka Enberg on 30 May 2010 06:10 Heiko Carstens wrote: > On Thu, May 27, 2010 at 09:17:17AM -0500, Christoph Lameter wrote: >> So S390 has NUMA and the minalign is allowing very small slabs of 8/16/32 bytes? > > No NUMA, but minalign is 8. > >> Try this patch >> >> From: Christoph Lameter <cl(a)linux-foundation.org> >> Subject: SLUB: Allow full duplication of kmalloc array for 390 >> >> Seems that S390 is running out of kmalloc caches. >> >> Increase the number of kmalloc caches to a safe size. >> >> Signed-off-by: Christoph Lameter <cl(a)linux-foundation.org> > > Yes, that fixes the bug. Thanks! We need this for .33 and .34 stable, right? -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Christoph Lameter on 1 Jun 2010 09:50
On Sun, 30 May 2010, Pekka Enberg wrote: > > Yes, that fixes the bug. Thanks! > > We need this for .33 and .34 stable, right? Right. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ |