2009-05-14 02:56:24 +04:00
|
|
|
#ifndef __ASM_GENERIC_MMAN_COMMON_H
|
|
|
|
|
#define __ASM_GENERIC_MMAN_COMMON_H
|
2006-02-16 02:17:39 +03:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
Author: Michael S. Tsirkin <mst@mellanox.co.il>, Mellanox Technologies Ltd.
|
|
|
|
|
Based on: asm-xxx/mman.h
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#define PROT_READ 0x1 /* page can be read */
|
|
|
|
|
#define PROT_WRITE 0x2 /* page can be written */
|
|
|
|
|
#define PROT_EXEC 0x4 /* page can be executed */
|
|
|
|
|
#define PROT_SEM 0x8 /* page may be used for atomic ops */
|
|
|
|
|
#define PROT_NONE 0x0 /* page can not be accessed */
|
|
|
|
|
#define PROT_GROWSDOWN 0x01000000 /* mprotect flag: extend change to start of growsdown vma */
|
|
|
|
|
#define PROT_GROWSUP 0x02000000 /* mprotect flag: extend change to end of growsup vma */
|
|
|
|
|
|
|
|
|
|
#define MAP_SHARED 0x01 /* Share changes */
|
|
|
|
|
#define MAP_PRIVATE 0x02 /* Changes are private */
|
|
|
|
|
#define MAP_TYPE 0x0f /* Mask for type of mapping */
|
|
|
|
|
#define MAP_FIXED 0x10 /* Interpret addr exactly */
|
|
|
|
|
#define MAP_ANONYMOUS 0x20 /* don't use a file */
|
2009-12-15 05:00:02 +03:00
|
|
|
#ifdef CONFIG_MMAP_ALLOW_UNINITIALIZED
|
|
|
|
|
# define MAP_UNINITIALIZED 0x4000000 /* For anonymous mmap, memory could be uninitialized */
|
|
|
|
|
#else
|
|
|
|
|
# define MAP_UNINITIALIZED 0x0 /* Don't support this flag */
|
|
|
|
|
#endif
|
2006-02-16 02:17:39 +03:00
|
|
|
|
2015-11-06 05:51:39 +03:00
|
|
|
/*
|
|
|
|
|
* Flags for mlock
|
|
|
|
|
*/
|
|
|
|
|
#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */
|
|
|
|
|
|
2006-02-16 02:17:39 +03:00
|
|
|
#define MS_ASYNC 1 /* sync memory asynchronously */
|
|
|
|
|
#define MS_INVALIDATE 2 /* invalidate the caches */
|
|
|
|
|
#define MS_SYNC 4 /* synchronous memory sync */
|
|
|
|
|
|
|
|
|
|
#define MADV_NORMAL 0 /* no further special treatment */
|
|
|
|
|
#define MADV_RANDOM 1 /* expect random page references */
|
|
|
|
|
#define MADV_SEQUENTIAL 2 /* expect sequential page references */
|
|
|
|
|
#define MADV_WILLNEED 3 /* will need these pages */
|
|
|
|
|
#define MADV_DONTNEED 4 /* don't need these pages */
|
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 03:54:53 +03:00
|
|
|
#define MADV_FREE 5 /* free pages only if memory pressure */
|
2006-02-16 02:17:39 +03:00
|
|
|
|
|
|
|
|
/* common parameters: try to keep these consistent across architectures */
|
|
|
|
|
#define MADV_REMOVE 9 /* remove these pages & resources */
|
|
|
|
|
#define MADV_DONTFORK 10 /* don't inherit across fork */
|
|
|
|
|
#define MADV_DOFORK 11 /* do inherit across fork */
|
2009-09-16 13:50:17 +04:00
|
|
|
#define MADV_HWPOISON 100 /* poison a page for testing */
|
2009-12-16 14:20:00 +03:00
|
|
|
#define MADV_SOFT_OFFLINE 101 /* soft offline page for testing */
|
2006-02-16 02:17:39 +03:00
|
|
|
|
2009-09-22 04:01:53 +04:00
|
|
|
#define MADV_MERGEABLE 12 /* KSM may merge identical pages */
|
|
|
|
|
#define MADV_UNMERGEABLE 13 /* KSM may not merge identical pages */
|
|
|
|
|
|
2011-01-14 02:46:31 +03:00
|
|
|
#define MADV_HUGEPAGE 14 /* Worth backing with hugepages */
|
2011-01-14 02:47:17 +03:00
|
|
|
#define MADV_NOHUGEPAGE 15 /* Not worth backing with hugepages */
|
2011-01-14 02:46:31 +03:00
|
|
|
|
2012-03-24 02:02:51 +04:00
|
|
|
#define MADV_DONTDUMP 16 /* Explicity exclude from the core dump,
|
|
|
|
|
overrides the coredump filter bits */
|
2014-04-08 02:37:56 +04:00
|
|
|
#define MADV_DODUMP 17 /* Clear the MADV_DONTDUMP flag */
|
2012-03-24 02:02:51 +04:00
|
|
|
|
2006-02-16 02:17:39 +03:00
|
|
|
/* compatibility flags */
|
|
|
|
|
#define MAP_FILE 0
|
|
|
|
|
|
2012-12-12 04:01:34 +04:00
|
|
|
/*
|
|
|
|
|
* When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
|
|
|
|
|
* This gives us 6 bits, which is enough until someone invents 128 bit address
|
|
|
|
|
* spaces.
|
|
|
|
|
*
|
|
|
|
|
* Assume these are all power of twos.
|
|
|
|
|
* When 0 use the default page size.
|
|
|
|
|
*/
|
|
|
|
|
#define MAP_HUGE_SHIFT 26
|
|
|
|
|
#define MAP_HUGE_MASK 0x3f
|
|
|
|
|
|
2009-05-14 02:56:24 +04:00
|
|
|
#endif /* __ASM_GENERIC_MMAN_COMMON_H */
|
