Re: [PATCH 0/3] Use one zonelist per node instead of multiplezonelists v2

From: Christoph Lameter
Date: Wed Aug 08 2007 - 19:36:09 EST


On Wed, 8 Aug 2007, Mel Gorman wrote:

>
> > For various policies, the arguments would look like this:
> > Policy start node nodemask
> >
> > default local node cpuset_current_mems_allowed
> >
> > preferred preferred_node cpuset_current_mems_allowed
> >
> > interleave computed node cpuset_current_mems_allowed
> >
> > bind local node policy nodemask [replaces bind
> > zonelist in mempolicy]
> >

GFP_THISNODE could be realized by only setting the desired nodenumber in
the nodemask.

> The last one is the most interesting. Much of the patch in development
> involves deleting the custom node stuff. I've included the patch below if
> you're curious. I wanted to get one-zonelist out first to see if we could
> agree on that before going further with it.

I think we do.

> > Then, just walk the zonelist for the starting node--already ordered by
> > distance--filtering by gfp_zone() and nodemask. Done "right", this
> > should always return memory from the closest allowed node [based on the
> > nodemask argument] to the starting node. And, it would eliminate the
> > custom zonelists for bind policy. Can also eliminate cpuset checks in
> > the allocation loop because that constraint would already be applied to
> > the nodemask argument.
> >
>
> This is what I'm hoping. I haven't looked closely enough to be sure this will
> work but currently I see no reason why it couldn't and it might eliminate
> some of the NUMA-specific paths in the allocator.

Right. But lets first get the general case for the single nodelist
accepted (with the zoneid optimizations?)
-
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/