Re: [PATCH V2 1/2] mm/vmscan: restore sc->gfp_mask after promoting it to __GFP_HIGHMEM

2014-02-14 Thread Rik van Riel
On 02/14/2014 01:41 AM, Weijie Yang wrote: > We promote sc->gfp_mask to __GFP_HIGHMEM to forcibly scan highmem if > there are too many buffer_heads pinning highmem. see: cc715d99e5 > > This patch restores sc->gfp_mask to its caller original value after > finishing the scan job, to avoid the

Re: [PATCH V2 1/2] mm/vmscan: restore sc->gfp_mask after promoting it to __GFP_HIGHMEM

2014-02-14 Thread Mel Gorman
On Fri, Feb 14, 2014 at 02:41:33PM +0800, Weijie Yang wrote: > We promote sc->gfp_mask to __GFP_HIGHMEM to forcibly scan highmem if > there are too many buffer_heads pinning highmem. see: cc715d99e5 > > This patch restores sc->gfp_mask to its caller original value after > finishing the scan job,

Re: [PATCH V2 1/2] mm/vmscan: restore sc-gfp_mask after promoting it to __GFP_HIGHMEM

2014-02-14 Thread Mel Gorman
On Fri, Feb 14, 2014 at 02:41:33PM +0800, Weijie Yang wrote: We promote sc-gfp_mask to __GFP_HIGHMEM to forcibly scan highmem if there are too many buffer_heads pinning highmem. see: cc715d99e5 This patch restores sc-gfp_mask to its caller original value after finishing the scan job, to

Re: [PATCH V2 1/2] mm/vmscan: restore sc-gfp_mask after promoting it to __GFP_HIGHMEM

2014-02-14 Thread Rik van Riel
On 02/14/2014 01:41 AM, Weijie Yang wrote: We promote sc-gfp_mask to __GFP_HIGHMEM to forcibly scan highmem if there are too many buffer_heads pinning highmem. see: cc715d99e5 This patch restores sc-gfp_mask to its caller original value after finishing the scan job, to avoid the impact on