On Sun, 11 Nov 2007, Mel Gorman wrote: > If MPOL_BIND is in effect, the allocation will be filtered based on the > current allowed nodemask. If they specify THISNODE and the specified > node or current node is not in the mask, I would expect the allocation > to fail. Is that unexpected to anybody? Currently GFP_THISNODE with MPOL_BIND results an allocation on the first node. - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
- References:
- [PATCH 0/6] Use one zonelist per node instead of multiple zonelists v9
- From: Mel Gorman <[email protected]>
- [PATCH 6/6] Use one zonelist that is filtered by nodemask
- From: Mel Gorman <[email protected]>
- Re: [PATCH 6/6] Use one zonelist that is filtered by nodemask
- From: Christoph Lameter <[email protected]>
- Re: [PATCH 6/6] Use one zonelist that is filtered by nodemask
- From: [email protected] (Mel Gorman)
- Re: [PATCH 6/6] Use one zonelist that is filtered by nodemask
- From: Nishanth Aravamudan <[email protected]>
- Re: [PATCH 6/6] Use one zonelist that is filtered by nodemask
- From: Lee Schermerhorn <[email protected]>
- Re: [PATCH 6/6] Use one zonelist that is filtered by nodemask
- From: Christoph Lameter <[email protected]>
- Re: [PATCH 6/6] Use one zonelist that is filtered by nodemask
- From: [email protected] (Mel Gorman)
- [PATCH 0/6] Use one zonelist per node instead of multiple zonelists v9
- Prev by Date: Re: snd_hda_intel 2.6.24-rc2 bug: interrupts don't always work on Lenovo X60s
- Next by Date: Re: [patch] x86: fix taking DNA during 64bit sigreturn
- Previous by thread: Re: [PATCH 6/6] Use one zonelist that is filtered by nodemask
- Next by thread: Re: [PATCH 6/6] Use one zonelist that is filtered by nodemask
- Index(es):
 |