Re: [PATCH 06/19] Check only once if the zonelist is suitable forthe allocation

From: Christoph Lameter
Date: Tue Feb 24 2009 - 12:33:30 EST

Next message: Christoph Lameter: "Re: [PATCH 08/19] Simplify the check on whether cpusets are a factoror not"
Previous message: Ian Abbott: "[PATCH] [UIO] Take offset into account when determining number ofpages that can be mapped"
In reply to: Mel Gorman: "[PATCH 06/19] Check only once if the zonelist is suitable for the allocation"
Next in thread: Mel Gorman: "[PATCH 07/19] Break up the allocator entry point into fast and slow paths"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

On Tue, 24 Feb 2009, Mel Gorman wrote:

> It is possible with __GFP_THISNODE that no zones are suitable. This
> patch makes sure the check is only made once.

GFP_THISNODE is only a performance factor if SLAB is the slab allocator.
The restart logic in __alloc_pages_internal() is mainly used by OOM
processing.

But the patch looks okay regardless...

Reviewed-by: Christoph Lameter <cl@xxxxxxxxxxxxxxxxxxxx>
--
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/

Next message: Christoph Lameter: "Re: [PATCH 08/19] Simplify the check on whether cpusets are a factoror not"
Previous message: Ian Abbott: "[PATCH] [UIO] Take offset into account when determining number ofpages that can be mapped"
In reply to: Mel Gorman: "[PATCH 06/19] Check only once if the zonelist is suitable for the allocation"
Next in thread: Mel Gorman: "[PATCH 07/19] Break up the allocator entry point into fast and slow paths"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]