2011-05-27 07:25:24 +08:00
|
|
|
#ifndef VM_EVENT_ITEM_H_INCLUDED
|
|
|
|
|
#define VM_EVENT_ITEM_H_INCLUDED
|
|
|
|
|
|
|
|
|
|
#ifdef CONFIG_ZONE_DMA
|
|
|
|
|
#define DMA_ZONE(xx) xx##_DMA,
|
|
|
|
|
#else
|
|
|
|
|
#define DMA_ZONE(xx)
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#ifdef CONFIG_ZONE_DMA32
|
|
|
|
|
#define DMA32_ZONE(xx) xx##_DMA32,
|
|
|
|
|
#else
|
|
|
|
|
#define DMA32_ZONE(xx)
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#ifdef CONFIG_HIGHMEM
|
2015-11-06 10:48:50 +08:00
|
|
|
#define HIGHMEM_ZONE(xx) xx##_HIGH,
|
2011-05-27 07:25:24 +08:00
|
|
|
#else
|
|
|
|
|
#define HIGHMEM_ZONE(xx)
|
|
|
|
|
#endif
|
|
|
|
|
|
2015-11-06 10:48:50 +08:00
|
|
|
#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL, HIGHMEM_ZONE(xx) xx##_MOVABLE
|
2011-05-27 07:25:24 +08:00
|
|
|
|
|
|
|
|
enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
|
|
|
|
|
FOR_ALL_ZONES(PGALLOC),
|
|
|
|
|
PGFREE, PGACTIVATE, PGDEACTIVATE,
|
|
|
|
|
PGFAULT, PGMAJFAULT,
|
mm: support madvise(MADV_FREE)
Linux doesn't have an ability to free pages lazy while other OS already
have been supported that named by madvise(MADV_FREE).
The gain is clear that kernel can discard freed pages rather than
swapping out or OOM if memory pressure happens.
Without memory pressure, freed pages would be reused by userspace
without another additional overhead(ex, page fault + allocation +
zeroing).
Jason Evans said:
: Facebook has been using MAP_UNINITIALIZED
: (https://lkml.org/lkml/2012/1/18/308) in some of its applications for
: several years, but there are operational costs to maintaining this
: out-of-tree in our kernel and in jemalloc, and we are anxious to retire it
: in favor of MADV_FREE. When we first enabled MAP_UNINITIALIZED it
: increased throughput for much of our workload by ~5%, and although the
: benefit has decreased using newer hardware and kernels, there is still
: enough benefit that we cannot reasonably retire it without a replacement.
:
: Aside from Facebook operations, there are numerous broadly used
: applications that would benefit from MADV_FREE. The ones that immediately
: come to mind are redis, varnish, and MariaDB. I don't have much insight
: into Android internals and development process, but I would hope to see
: MADV_FREE support eventually end up there as well to benefit applications
: linked with the integrated jemalloc.
:
: jemalloc will use MADV_FREE once it becomes available in the Linux kernel.
: In fact, jemalloc already uses MADV_FREE or equivalent everywhere it's
: available: *BSD, OS X, Windows, and Solaris -- every platform except Linux
: (and AIX, but I'm not sure it even compiles on AIX). The lack of
: MADV_FREE on Linux forced me down a long series of increasingly
: sophisticated heuristics for madvise() volume reduction, and even so this
: remains a common performance issue for people using jemalloc on Linux.
: Please integrate MADV_FREE; many people will benefit substantially.
How it works:
When madvise syscall is called, VM clears dirty bit of ptes of the
range. If memory pressure happens, VM checks dirty bit of page table
and if it found still "clean", it means it's a "lazyfree pages" so VM
could discard the page instead of swapping out. Once there was store
operation for the page before VM peek a page to reclaim, dirty bit is
set so VM can swap out the page instead of discarding.
One thing we should notice is that basically, MADV_FREE relies on dirty
bit in page table entry to decide whether VM allows to discard the page
or not. IOW, if page table entry includes marked dirty bit, VM
shouldn't discard the page.
However, as a example, if swap-in by read fault happens, page table
entry doesn't have dirty bit so MADV_FREE could discard the page
wrongly.
For avoiding the problem, MADV_FREE did more checks with PageDirty and
PageSwapCache. It worked out because swapped-in page lives on swap
cache and since it is evicted from the swap cache, the page has PG_dirty
flag. So both page flags check effectively prevent wrong discarding by
MADV_FREE.
However, a problem in above logic is that swapped-in page has PG_dirty
still after they are removed from swap cache so VM cannot consider the
page as freeable any more even if madvise_free is called in future.
Look at below example for detail.
ptr = malloc();
memset(ptr);
..
..
.. heavy memory pressure so all of pages are swapped out
..
..
var = *ptr; -> a page swapped-in and could be removed from
swapcache. Then, page table doesn't mark
dirty bit and page descriptor includes PG_dirty
..
..
madvise_free(ptr); -> It doesn't clear PG_dirty of the page.
..
..
..
.. heavy memory pressure again.
.. In this time, VM cannot discard the page because the page
.. has *PG_dirty*
To solve the problem, this patch clears PG_dirty if only the page is
owned exclusively by current process when madvise is called because
PG_dirty represents ptes's dirtiness in several processes so we could
clear it only if we own it exclusively.
Firstly, heavy users would be general allocators(ex, jemalloc, tcmalloc
and hope glibc supports it) and jemalloc/tcmalloc already have supported
the feature for other OS(ex, FreeBSD)
barrios@blaptop:~/benchmark/ebizzy$ lscpu
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
CPU(s): 12
On-line CPU(s) list: 0-11
Thread(s) per core: 1
Core(s) per socket: 1
Socket(s): 12
NUMA node(s): 1
Vendor ID: GenuineIntel
CPU family: 6
Model: 2
Stepping: 3
CPU MHz: 3200.185
BogoMIPS: 6400.53
Virtualization: VT-x
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 32K
L1i cache: 32K
L2 cache: 4096K
NUMA node0 CPU(s): 0-11
ebizzy benchmark(./ebizzy -S 10 -n 512)
Higher avg is better.
vanilla-jemalloc MADV_free-jemalloc
1 thread
records: 10 records: 10
avg: 2961.90 avg: 12069.70
std: 71.96(2.43%) std: 186.68(1.55%)
max: 3070.00 max: 12385.00
min: 2796.00 min: 11746.00
2 thread
records: 10 records: 10
avg: 5020.00 avg: 17827.00
std: 264.87(5.28%) std: 358.52(2.01%)
max: 5244.00 max: 18760.00
min: 4251.00 min: 17382.00
4 thread
records: 10 records: 10
avg: 8988.80 avg: 27930.80
std: 1175.33(13.08%) std: 3317.33(11.88%)
max: 9508.00 max: 30879.00
min: 5477.00 min: 21024.00
8 thread
records: 10 records: 10
avg: 13036.50 avg: 33739.40
std: 170.67(1.31%) std: 5146.22(15.25%)
max: 13371.00 max: 40572.00
min: 12785.00 min: 24088.00
16 thread
records: 10 records: 10
avg: 11092.40 avg: 31424.20
std: 710.60(6.41%) std: 3763.89(11.98%)
max: 12446.00 max: 36635.00
min: 9949.00 min: 25669.00
32 thread
records: 10 records: 10
avg: 11067.00 avg: 34495.80
std: 971.06(8.77%) std: 2721.36(7.89%)
max: 12010.00 max: 38598.00
min: 9002.00 min: 30636.00
In summary, MADV_FREE is about much faster than MADV_DONTNEED.
This patch (of 12):
Add core MADV_FREE implementation.
[akpm@linux-foundation.org: small cleanups]
Signed-off-by: Minchan Kim <minchan@kernel.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Mika Penttil <mika.penttila@nextfour.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Jason Evans <je@fb.com>
Cc: Daniel Micay <danielmicay@gmail.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Shaohua Li <shli@kernel.org>
Cc: <yalin.wang2010@gmail.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: "James E.J. Bottomley" <jejb@parisc-linux.org>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: "Shaohua Li" <shli@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chen Gang <gang.chen.5i5j@gmail.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Darrick J. Wong <darrick.wong@oracle.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Helge Deller <deller@gmx.de>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Roland Dreier <roland@kernel.org>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Shaohua Li <shli@kernel.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-16 08:54:53 +08:00
|
|
|
PGLAZYFREED,
|
2011-05-27 07:25:24 +08:00
|
|
|
FOR_ALL_ZONES(PGREFILL),
|
2012-04-26 07:01:48 +08:00
|
|
|
FOR_ALL_ZONES(PGSTEAL_KSWAPD),
|
|
|
|
|
FOR_ALL_ZONES(PGSTEAL_DIRECT),
|
2011-05-27 07:25:24 +08:00
|
|
|
FOR_ALL_ZONES(PGSCAN_KSWAPD),
|
|
|
|
|
FOR_ALL_ZONES(PGSCAN_DIRECT),
|
2012-08-01 07:44:39 +08:00
|
|
|
PGSCAN_DIRECT_THROTTLE,
|
2011-05-27 07:25:24 +08:00
|
|
|
#ifdef CONFIG_NUMA
|
|
|
|
|
PGSCAN_ZONE_RECLAIM_FAILED,
|
|
|
|
|
#endif
|
2012-04-26 07:01:48 +08:00
|
|
|
PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL,
|
2011-05-27 07:25:24 +08:00
|
|
|
KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
|
|
|
|
|
PAGEOUTRUN, ALLOCSTALL, PGROTATED,
|
2014-04-04 05:48:19 +08:00
|
|
|
DROP_PAGECACHE, DROP_SLAB,
|
2012-11-02 22:52:48 +08:00
|
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
|
|
|
NUMA_PTE_UPDATES,
|
2013-11-13 07:08:32 +08:00
|
|
|
NUMA_HUGE_PTE_UPDATES,
|
2012-11-02 22:52:48 +08:00
|
|
|
NUMA_HINT_FAULTS,
|
|
|
|
|
NUMA_HINT_FAULTS_LOCAL,
|
|
|
|
|
NUMA_PAGE_MIGRATE,
|
|
|
|
|
#endif
|
2012-10-19 17:46:20 +08:00
|
|
|
#ifdef CONFIG_MIGRATION
|
|
|
|
|
PGMIGRATE_SUCCESS, PGMIGRATE_FAIL,
|
|
|
|
|
#endif
|
2011-05-27 07:25:24 +08:00
|
|
|
#ifdef CONFIG_COMPACTION
|
2012-10-19 19:00:10 +08:00
|
|
|
COMPACTMIGRATE_SCANNED, COMPACTFREE_SCANNED,
|
|
|
|
|
COMPACTISOLATED,
|
2011-05-27 07:25:24 +08:00
|
|
|
COMPACTSTALL, COMPACTFAIL, COMPACTSUCCESS,
|
mm, compaction: introduce kcompactd
Memory compaction can be currently performed in several contexts:
- kswapd balancing a zone after a high-order allocation failure
- direct compaction to satisfy a high-order allocation, including THP
page fault attemps
- khugepaged trying to collapse a hugepage
- manually from /proc
The purpose of compaction is two-fold. The obvious purpose is to
satisfy a (pending or future) high-order allocation, and is easy to
evaluate. The other purpose is to keep overal memory fragmentation low
and help the anti-fragmentation mechanism. The success wrt the latter
purpose is more
The current situation wrt the purposes has a few drawbacks:
- compaction is invoked only when a high-order page or hugepage is not
available (or manually). This might be too late for the purposes of
keeping memory fragmentation low.
- direct compaction increases latency of allocations. Again, it would
be better if compaction was performed asynchronously to keep
fragmentation low, before the allocation itself comes.
- (a special case of the previous) the cost of compaction during THP
page faults can easily offset the benefits of THP.
- kswapd compaction appears to be complex, fragile and not working in
some scenarios. It could also end up compacting for a high-order
allocation request when it should be reclaiming memory for a later
order-0 request.
To improve the situation, we should be able to benefit from an
equivalent of kswapd, but for compaction - i.e. a background thread
which responds to fragmentation and the need for high-order allocations
(including hugepages) somewhat proactively.
One possibility is to extend the responsibilities of kswapd, which could
however complicate its design too much. It should be better to let
kswapd handle reclaim, as order-0 allocations are often more critical
than high-order ones.
Another possibility is to extend khugepaged, but this kthread is a
single instance and tied to THP configs.
This patch goes with the option of a new set of per-node kthreads called
kcompactd, and lays the foundations, without introducing any new
tunables. The lifecycle mimics kswapd kthreads, including the memory
hotplug hooks.
For compaction, kcompactd uses the standard compaction_suitable() and
ompact_finished() criteria and the deferred compaction functionality.
Unlike direct compaction, it uses only sync compaction, as there's no
allocation latency to minimize.
This patch doesn't yet add a call to wakeup_kcompactd. The kswapd
compact/reclaim loop for high-order pages will be replaced by waking up
kcompactd in the next patch with the description of what's wrong with
the old approach.
Waking up of the kcompactd threads is also tied to kswapd activity and
follows these rules:
- we don't want to affect any fastpaths, so wake up kcompactd only from
the slowpath, as it's done for kswapd
- if kswapd is doing reclaim, it's more important than compaction, so
don't invoke kcompactd until kswapd goes to sleep
- the target order used for kswapd is passed to kcompactd
Future possible future uses for kcompactd include the ability to wake up
kcompactd on demand in special situations, such as when hugepages are
not available (currently not done due to __GFP_NO_KSWAPD) or when a
fragmentation event (i.e. __rmqueue_fallback()) occurs. It's also
possible to perform periodic compaction with kcompactd.
[arnd@arndb.de: fix build errors with kcompactd]
[paul.gortmaker@windriver.com: don't use modular references for non modular code]
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: David Rientjes <rientjes@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-18 05:18:08 +08:00
|
|
|
KCOMPACTD_WAKE,
|
2011-05-27 07:25:24 +08:00
|
|
|
#endif
|
|
|
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
|
|
|
|
HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL,
|
|
|
|
|
#endif
|
|
|
|
|
UNEVICTABLE_PGCULLED, /* culled to noreclaim list */
|
|
|
|
|
UNEVICTABLE_PGSCANNED, /* scanned for reclaimability */
|
|
|
|
|
UNEVICTABLE_PGRESCUED, /* rescued from noreclaim list */
|
|
|
|
|
UNEVICTABLE_PGMLOCKED,
|
|
|
|
|
UNEVICTABLE_PGMUNLOCKED,
|
|
|
|
|
UNEVICTABLE_PGCLEARED, /* on COW, page truncate */
|
|
|
|
|
UNEVICTABLE_PGSTRANDED, /* unable to isolate on unlock */
|
|
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
|
|
|
THP_FAULT_ALLOC,
|
|
|
|
|
THP_FAULT_FALLBACK,
|
|
|
|
|
THP_COLLAPSE_ALLOC,
|
|
|
|
|
THP_COLLAPSE_ALLOC_FAILED,
|
2016-07-27 06:25:31 +08:00
|
|
|
THP_FILE_ALLOC,
|
|
|
|
|
THP_FILE_MAPPED,
|
2016-01-16 08:52:46 +08:00
|
|
|
THP_SPLIT_PAGE,
|
|
|
|
|
THP_SPLIT_PAGE_FAILED,
|
2016-03-18 05:18:45 +08:00
|
|
|
THP_DEFERRED_SPLIT_PAGE,
|
2016-01-16 08:52:46 +08:00
|
|
|
THP_SPLIT_PMD,
|
2012-12-13 05:51:09 +08:00
|
|
|
THP_ZERO_PAGE_ALLOC,
|
|
|
|
|
THP_ZERO_PAGE_ALLOC_FAILED,
|
2011-05-27 07:25:24 +08:00
|
|
|
#endif
|
2014-10-10 06:29:32 +08:00
|
|
|
#ifdef CONFIG_MEMORY_BALLOON
|
|
|
|
|
BALLOON_INFLATE,
|
|
|
|
|
BALLOON_DEFLATE,
|
|
|
|
|
#ifdef CONFIG_BALLOON_COMPACTION
|
|
|
|
|
BALLOON_MIGRATE,
|
|
|
|
|
#endif
|
|
|
|
|
#endif
|
2014-01-22 06:33:16 +08:00
|
|
|
#ifdef CONFIG_DEBUG_TLBFLUSH
|
2013-09-12 05:20:24 +08:00
|
|
|
#ifdef CONFIG_SMP
|
2013-09-12 05:20:23 +08:00
|
|
|
NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */
|
|
|
|
|
NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */
|
2014-01-22 06:33:16 +08:00
|
|
|
#endif /* CONFIG_SMP */
|
2013-09-12 05:20:23 +08:00
|
|
|
NR_TLB_LOCAL_FLUSH_ALL,
|
|
|
|
|
NR_TLB_LOCAL_FLUSH_ONE,
|
2014-01-22 06:33:16 +08:00
|
|
|
#endif /* CONFIG_DEBUG_TLBFLUSH */
|
2014-06-05 07:06:46 +08:00
|
|
|
#ifdef CONFIG_DEBUG_VM_VMACACHE
|
|
|
|
|
VMACACHE_FIND_CALLS,
|
|
|
|
|
VMACACHE_FIND_HITS,
|
2014-12-13 08:56:10 +08:00
|
|
|
VMACACHE_FULL_FLUSHES,
|
2014-06-05 07:06:46 +08:00
|
|
|
#endif
|
2011-05-27 07:25:24 +08:00
|
|
|
NR_VM_EVENT_ITEMS
|
|
|
|
|
};
|
|
|
|
|
|
2016-07-27 06:25:31 +08:00
|
|
|
#ifndef CONFIG_TRANSPARENT_HUGEPAGE
|
|
|
|
|
#define THP_FILE_ALLOC ({ BUILD_BUG(); 0; })
|
|
|
|
|
#define THP_FILE_MAPPED ({ BUILD_BUG(); 0; })
|
|
|
|
|
#endif
|
|
|
|
|
|
2011-05-27 07:25:24 +08:00
|
|
|
#endif /* VM_EVENT_ITEM_H_INCLUDED */
|