[lkml]   [2009]   [Nov]   [10]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [BUGFIX][PATCH] oom-kill: fix NUMA consraint check with nodemask v3
On Wed, 11 Nov 2009, KOSAKI Motohiro wrote:

> Linux doesn't support 1K nodes. (and only SGI huge machine use 512 nodes)

I know for a fact that it does on x86 if you adjust CONFIG_NODES_SHIFT,
I've booted kernels all the way back to 2.6.18 with 1K nodes.

> At least, NODEMASK_ALLOC should make more cleaner interface. current one
> and struct nodemask_scratch are pretty ugly.

I agree, I haven't been a fan of nodemask_scratch because I think its use
case is pretty limited, but I do advocate using NODEMASK_ALLOC() when deep
in the stack. We've made sure that most of the mempolicy code does that
where manipulating nodemasks is common in -mm.

 \ /
  Last update: 2009-11-11 04:31    [W:0.075 / U:2.104 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site