Re: [PATCH v2 6/6] slub: only preallocate cpus_with_slabs ifoffstack

[Christoph Lameter]

On Sun, 23 Oct 2011, Gilad Ben-Yossef wrote:

> We need a cpumask to track cpus with per cpu cache pages
> to know which cpu to whack during flush_all. For
> CONFIG_CPUMASK_OFFSTACK=n we allocate the mask on stack.
> For CONFIG_CPUMASK_OFFSTACK=y we don't want to call kmalloc
> on the flush_all path, so we preallocate per kmem_cache
> on cache creation and use it in flush_all.

I think the on stack alloc should be the default because we can then avoid
the field in kmem_cache and the associated logic with managing the field.
Can we do a GFP_ATOMIC allocation in flush_all()? If the alloc
fails then you can still fallback to send an IPI to all cpus.

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