thp: _GFP_NO_KSWAPD (32dba98e) · Commits · 戴 / test

Transparent hugepage allocations must be allowed not to invoke kswapd or any other kind of indirect reclaim (especially when the defrag sysfs is control disabled). It's unacceptable to swap out anonymous pages (potentially anonymous transparent hugepages) in order to create new transparent hugepages. This is true for the MADV_HUGEPAGE areas too (swapping out a kvm virtual machine and so having it suffer an unbearable slowdown, so another one with guest physical memory marked MADV_HUGEPAGE can run 30% faster if it is running memory intensive workloads, makes no sense). If a transparent hugepage allocation fails the slowdown is minor and there is total fallback, so kswapd should never be asked to swapout memory to allow the high order allocation to succeed. Signed-off-by:

Andrea Arcangeli <aarcange@redhat.com> Acked-by:

Rik van Riel <riel@redhat.com> Acked-by:

Mel Gorman <mel@csn.ul.ie> Signed-off-by:

Andrew Morton <akpm@linux-foundation.org> Signed-off-by:

Linus Torvalds <torvalds@linux-foundation.org>

include/linux/gfp.h

+4 −1

Original line number	Diff line number	Diff line
		@@ -34,6 +34,7 @@ struct vm_area_struct;
		#else
		#define ___GFP_NOTRACK 0
		#endif
		#define ___GFP_NO_KSWAPD 0x400000u

		/*
		* GFP bitmasks..
		@@ -81,13 +82,15 @@ struct vm_area_struct;
		#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */
		#define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK) /* Don't track with kmemcheck */

		#define __GFP_NO_KSWAPD ((__force gfp_t)___GFP_NO_KSWAPD)

		/*
		* This may seem redundant, but it's a way of annotating false positives vs.
		* allocations that simply cannot be supported (e.g. page tables).
		*/
		#define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK)

		#define __GFP_BITS_SHIFT 22 /* Room for 22 __GFP_FOO bits */
		#define __GFP_BITS_SHIFT 23 /* Room for 23 __GFP_FOO bits */
		#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))

		/* This equals 0, but use constants in case they ever change */

mm/page_alloc.c

+2 −1

Original line number	Diff line number	Diff line
		@@ -2027,6 +2027,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
		goto nopage;

		restart:
		if (!(gfp_mask & __GFP_NO_KSWAPD))
		wake_all_kswapd(order, zonelist, high_zoneidx,
		zone_idx(preferred_zone));

Admin message