RE: [net-next rfc 1/3] net: avoid high order memory allocation forqueues by using flex array

[Eric Dumazet]

On Wed, 2013-06-19 at 17:06 +0100, David Laight wrote:

> Given the number of places I've seen this code added, why
> not put it in a general helper?

Good luck with that. We had many attempts in the past.

> I also thought that malloc() with GFP_KERNEL would sleep.
> Under what conditions does it fail instead?

For example on 32 bit kernel, LOW memory exhaustion/fragmentation.

vmalloc() has an extra 128MB virtual space (on i386 at least with
standard 3G/1G split)



--
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/