From a756cf5908530e8b40bdf569eb48b40139e8d7fd Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 10 Jan 2012 15:07:49 -0800 Subject: mm: try to distribute dirty pages fairly across zones The maximum number of dirty pages that exist in the system at any time is determined by a number of pages considered dirtyable and a user-configured percentage of those, or an absolute number in bytes. This number of dirtyable pages is the sum of memory provided by all the zones in the system minus their lowmem reserves and high watermarks, so that the system can retain a healthy number of free pages without having to reclaim dirty pages. But there is a flaw in that we have a zoned page allocator which does not care about the global state but rather the state of individual memory zones. And right now there is nothing that prevents one zone from filling up with dirty pages while other zones are spared, which frequently leads to situations where kswapd, in order to restore the watermark of free pages, does indeed have to write pages from that zone's LRU list. This can interfere so badly with IO from the flusher threads that major filesystems (btrfs, xfs, ext4) mostly ignore write requests from reclaim already, taking away the VM's only possibility to keep such a zone balanced, aside from hoping the flushers will soon clean pages from that zone. Enter per-zone dirty limits. They are to a zone's dirtyable memory what the global limit is to the global amount of dirtyable memory, and try to make sure that no single zone receives more than its fair share of the globally allowed dirty pages in the first place. As the number of pages considered dirtyable excludes the zones' lowmem reserves and high watermarks, the maximum number of dirty pages in a zone is such that the zone can always be balanced without requiring page cleaning. As this is a placement decision in the page allocator and pages are dirtied only after the allocation, this patch allows allocators to pass __GFP_WRITE when they know in advance that the page will be written to and become dirty soon. The page allocator will then attempt to allocate from the first zone of the zonelist - which on NUMA is determined by the task's NUMA memory policy - that has not exceeded its dirty limit. At first glance, it would appear that the diversion to lower zones can increase pressure on them, but this is not the case. With a full high zone, allocations will be diverted to lower zones eventually, so it is more of a shift in timing of the lower zone allocations. Workloads that previously could fit their dirty pages completely in the higher zone may be forced to allocate from lower zones, but the amount of pages that "spill over" are limited themselves by the lower zones' dirty constraints, and thus unlikely to become a problem. For now, the problem of unfair dirty page distribution remains for NUMA configurations where the zones allowed for allocation are in sum not big enough to trigger the global dirty limits, wake up the flusher threads and remedy the situation. Because of this, an allocation that could not succeed on any of the considered zones is allowed to ignore the dirty limits before going into direct reclaim or even failing the allocation, until a future patch changes the global dirty throttling and flusher thread activation so that they take individual zone states into account. Test results 15M DMA + 3246M DMA32 + 504 Normal = 3765M memory 40% dirty ratio 16G USB thumb drive 10 runs of dd if=/dev/zero of=disk/zeroes bs=32k count=$((10 << 15)) seconds nr_vmscan_write (stddev) min| median| max xfs vanilla: 549.747( 3.492) 0.000| 0.000| 0.000 patched: 550.996( 3.802) 0.000| 0.000| 0.000 fuse-ntfs vanilla: 1183.094(53.178) 54349.000| 59341.000| 65163.000 patched: 558.049(17.914) 0.000| 0.000| 43.000 btrfs vanilla: 573.679(14.015) 156657.000| 460178.000| 606926.000 patched: 563.365(11.368) 0.000| 0.000| 1362.000 ext4 vanilla: 561.197(15.782) 0.000|2725438.000|4143837.000 patched: 568.806(17.496) 0.000| 0.000| 0.000 Signed-off-by: Johannes Weiner Reviewed-by: Minchan Kim Acked-by: Mel Gorman Reviewed-by: Michal Hocko Tested-by: Wu Fengguang Cc: KAMEZAWA Hiroyuki Cc: Christoph Hellwig Cc: Dave Chinner Cc: Jan Kara Cc: Shaohua Li Cc: Rik van Riel Cc: Chris Mason Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux/gfp.h') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 66f172fdf5f..581e74b7df9 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -36,6 +36,7 @@ struct vm_area_struct; #endif #define ___GFP_NO_KSWAPD 0x400000u #define ___GFP_OTHER_NODE 0x800000u +#define ___GFP_WRITE 0x1000000u /* * GFP bitmasks.. @@ -85,6 +86,7 @@ struct vm_area_struct; #define __GFP_NO_KSWAPD ((__force gfp_t)___GFP_NO_KSWAPD) #define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */ +#define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) /* Allocator intends to dirty page */ /* * This may seem redundant, but it's a way of annotating false positives vs. @@ -92,7 +94,7 @@ struct vm_area_struct; */ #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK) -#define __GFP_BITS_SHIFT 24 /* Room for N __GFP_FOO bits */ +#define __GFP_BITS_SHIFT 25 /* Room for N __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 */ -- cgit v1.2.3