From 82b212f40059bffd6808c07266a942d444d5558a Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 26 Nov 2012 16:29:45 -0800 Subject: Revert "mm: remove __GFP_NO_KSWAPD" With "mm: vmscan: scale number of pages reclaimed by reclaim/compaction based on failures" reverted, Zdenek Kabelac reported the following Hmm, so it's just took longer to hit the problem and observe kswapd0 spinning on my CPU again - it's not as endless like before - but still it easily eats minutes - it helps to turn off Firefox or TB (memory hungry apps) so kswapd0 stops soon - and restart those apps again. (And I still have like >1GB of cached memory) kswapd0 R running task 0 30 2 0x00000000 Call Trace: preempt_schedule+0x42/0x60 _raw_spin_unlock+0x55/0x60 put_super+0x31/0x40 drop_super+0x22/0x30 prune_super+0x149/0x1b0 shrink_slab+0xba/0x510 The sysrq+m indicates the system has no swap so it'll never reclaim anonymous pages as part of reclaim/compaction. That is one part of the problem but not the root cause as file-backed pages could also be reclaimed. The likely underlying problem is that kswapd is woken up or kept awake for each THP allocation request in the page allocator slow path. If compaction fails for the requesting process then compaction will be deferred for a time and direct reclaim is avoided. However, if there are a storm of THP requests that are simply rejected, it will still be the the case that kswapd is awake for a prolonged period of time as pgdat->kswapd_max_order is updated each time. This is noticed by the main kswapd() loop and it will not call kswapd_try_to_sleep(). Instead it will loopp, shrinking a small number of pages and calling shrink_slab() on each iteration. The temptation is to supply a patch that checks if kswapd was woken for THP and if so ignore pgdat->kswapd_max_order but it'll be a hack and not backed up by proper testing. As 3.7 is very close to release and this is not a bug we should release with, a safer path is to revert "mm: remove __GFP_NO_KSWAPD" for now and revisit it with the view to ironing out the balance_pgdat() logic in general. Signed-off-by: Mel Gorman Cc: Zdenek Kabelac Cc: Seth Jennings Cc: Valdis Kletnieks Cc: Jiri Slaby Cc: Rik van Riel Cc: Robert Jennings Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux/gfp.h') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 02c1c9710be0..d0a79678f169 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -31,6 +31,7 @@ struct vm_area_struct; #define ___GFP_THISNODE 0x40000u #define ___GFP_RECLAIMABLE 0x80000u #define ___GFP_NOTRACK 0x200000u +#define ___GFP_NO_KSWAPD 0x400000u #define ___GFP_OTHER_NODE 0x800000u #define ___GFP_WRITE 0x1000000u @@ -85,6 +86,7 @@ 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) #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 */ @@ -114,7 +116,8 @@ struct vm_area_struct; __GFP_MOVABLE) #define GFP_IOFS (__GFP_IO | __GFP_FS) #define GFP_TRANSHUGE (GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ - __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) + __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \ + __GFP_NO_KSWAPD) #ifdef CONFIG_NUMA #define GFP_THISNODE (__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY) -- cgit v1.2.2 From a50915394f1fc02c2861d3b7ce7014788aa5066e Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 29 Nov 2012 13:54:27 -0800 Subject: revert "Revert "mm: remove __GFP_NO_KSWAPD"" It apepars that this patch was innocent, and we hope that "mm: avoid waking kswapd for THP allocations when compaction is deferred or contended" will fix the final kswapd-spinning cause. Cc: Zdenek Kabelac Cc: Seth Jennings Cc: Valdis Kletnieks Cc: Jiri Slaby Cc: Rik van Riel Cc: Robert Jennings Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'include/linux/gfp.h') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index d0a79678f169..76e1aa206f57 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -30,10 +30,9 @@ struct vm_area_struct; #define ___GFP_HARDWALL 0x20000u #define ___GFP_THISNODE 0x40000u #define ___GFP_RECLAIMABLE 0x80000u -#define ___GFP_NOTRACK 0x200000u -#define ___GFP_NO_KSWAPD 0x400000u -#define ___GFP_OTHER_NODE 0x800000u -#define ___GFP_WRITE 0x1000000u +#define ___GFP_NOTRACK 0x100000u +#define ___GFP_OTHER_NODE 0x200000u +#define ___GFP_WRITE 0x400000u /* * GFP bitmasks.. @@ -86,7 +85,6 @@ 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) #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 */ @@ -96,7 +94,7 @@ struct vm_area_struct; */ #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK) -#define __GFP_BITS_SHIFT 25 /* Room for N __GFP_FOO bits */ +#define __GFP_BITS_SHIFT 23 /* 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 */ @@ -116,8 +114,7 @@ struct vm_area_struct; __GFP_MOVABLE) #define GFP_IOFS (__GFP_IO | __GFP_FS) #define GFP_TRANSHUGE (GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ - __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \ - __GFP_NO_KSWAPD) + __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) #ifdef CONFIG_NUMA #define GFP_THISNODE (__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY) -- cgit v1.2.2 From caf491916b1c1e939a2c7575efb7a77f11fc9bdf Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 10 Dec 2012 10:51:16 -0800 Subject: Revert "revert "Revert "mm: remove __GFP_NO_KSWAPD""" and associated damage This reverts commits a50915394f1fc02c2861d3b7ce7014788aa5066e and d7c3b937bdf45f0b844400b7bf6fd3ed50bac604. This is a revert of a revert of a revert. In addition, it reverts the even older i915 change to stop using the __GFP_NO_KSWAPD flag due to the original commits in linux-next. It turns out that the original patch really was bogus, and that the original revert was the correct thing to do after all. We thought we had fixed the problem, and then reverted the revert, but the problem really is fundamental: waking up kswapd simply isn't the right thing to do, and direct reclaim sometimes simply _is_ the right thing to do. When certain allocations fail, we simply should try some direct reclaim, and if that fails, fail the allocation. That's the right thing to do for THP allocations, which can easily fail, and the GPU allocations want to do that too. So starting kswapd is sometimes simply wrong, and removing the flag that said "don't start kswapd" was a mistake. Let's hope we never revisit this mistake again - and certainly not this many times ;) Acked-by: Mel Gorman Acked-by: Johannes Weiner Cc: Rik van Riel Cc: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux/gfp.h') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 76e1aa206f57..d0a79678f169 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -30,9 +30,10 @@ struct vm_area_struct; #define ___GFP_HARDWALL 0x20000u #define ___GFP_THISNODE 0x40000u #define ___GFP_RECLAIMABLE 0x80000u -#define ___GFP_NOTRACK 0x100000u -#define ___GFP_OTHER_NODE 0x200000u -#define ___GFP_WRITE 0x400000u +#define ___GFP_NOTRACK 0x200000u +#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_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) #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 */ @@ -94,7 +96,7 @@ struct vm_area_struct; */ #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK) -#define __GFP_BITS_SHIFT 23 /* 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 */ @@ -114,7 +116,8 @@ struct vm_area_struct; __GFP_MOVABLE) #define GFP_IOFS (__GFP_IO | __GFP_FS) #define GFP_TRANSHUGE (GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ - __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) + __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \ + __GFP_NO_KSWAPD) #ifdef CONFIG_NUMA #define GFP_THISNODE (__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY) -- cgit v1.2.2