linux.git/mm/vmstat.c, branch v4.6-rc2

thp, vmstats: count deferred split events

2016-03-17T22:09:34+00:00

Count how many times we put a THP in split queue.  Currently, it happens
on partial unmap of a THP.

Rapidly growing value can indicate that an application behaves
unfriendly wrt THP: often fault in huge page and then unmap part of it.
This leads to unnecessary memory fragmentation and the application may
require tuning.

The event also can help with debugging kernel [mis-]behaviour.

Signed-off-by: Kirill A. Shutemov 
Cc: Andrea Arcangeli 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm, compaction: introduce kcompactd

2016-03-17T22:09:34+00:00

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 
Cc: Andrea Arcangeli 
Cc: "Kirill A. Shutemov" 
Cc: Rik van Riel 
Cc: Joonsoo Kim 
Cc: Mel Gorman 
Cc: David Rientjes 
Cc: Michal Hocko 
Cc: Johannes Weiner 
Signed-off-by: Arnd Bergmann 
Signed-off-by: Paul Gortmaker 
Cc: Hugh Dickins 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm, page_owner: convert page_owner_inited to static key

2016-03-15T23:55:16+00:00

CONFIG_PAGE_OWNER attempts to impose negligible runtime overhead when
enabled during compilation, but not actually enabled during runtime by
boot param page_owner=on.  This overhead can be further reduced using
the static key mechanism, which this patch does.

Signed-off-by: Vlastimil Babka 
Acked-by: Michal Hocko 
Cc: Joonsoo Kim 
Cc: Minchan Kim 
Cc: Sasha Levin 
Cc: "Kirill A. Shutemov" 
Cc: Mel Gorman 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm, page_owner: print migratetype of page and pageblock, symbolic flags

2016-03-15T23:55:16+00:00

The information in /sys/kernel/debug/page_owner includes the migratetype
of the pageblock the page belongs to.  This is also checked against the
page's migratetype (as declared by gfp_flags during its allocation), and
the page is reported as Fallback if its migratetype differs from the
pageblock's one.  t This is somewhat misleading because in fact fallback
allocation is not the only reason why these two can differ.  It also
doesn't direcly provide the page's migratetype, although it's possible
to derive that from the gfp_flags.

It's arguably better to print both page and pageblock's migratetype and
leave the interpretation to the consumer than to suggest fallback
allocation as the only possible reason.  While at it, we can print the
migratetypes as string the same way as /proc/pagetypeinfo does, as some
of the numeric values depend on kernel configuration.  For that, this
patch moves the migratetype_names array from #ifdef CONFIG_PROC_FS part
of mm/vmstat.c to mm/page_alloc.c and exports it.

With the new format strings for flags, we can now also provide symbolic
page and gfp flags in the /sys/kernel/debug/page_owner file.  This
replaces the positional printing of page flags as single letters, which
might have looked nicer, but was limited to a subset of flags, and
required the user to remember the letters.

Example page_owner entry after the patch:

  Page allocated via order 0, mask 0x24213ca(GFP_HIGHUSER_MOVABLE|__GFP_COLD|__GFP_NOWARN|__GFP_NORETRY)
  PFN 520 type Movable Block 1 type Movable Flags 0xfffff8001006c(referenced|uptodate|lru|active|mappedtodisk)
   [] __alloc_pages_nodemask+0x134/0x230
   [] alloc_pages_current+0x88/0x120
   [] __page_cache_alloc+0xe6/0x120
   [] __do_page_cache_readahead+0xdc/0x240
   [] ondemand_readahead+0x135/0x260
   [] page_cache_sync_readahead+0x31/0x50
   [] generic_file_read_iter+0x453/0x760
   [] __vfs_read+0xa7/0xd0

Signed-off-by: Vlastimil Babka 
Acked-by: Michal Hocko 
Cc: Joonsoo Kim 
Cc: Minchan Kim 
Cc: Sasha Levin 
Cc: "Kirill A. Shutemov" 
Cc: Mel Gorman 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

vmstat: make vmstat_update deferrable

2016-02-06T02:10:40+00:00

Commit 0eb77e988032 ("vmstat: make vmstat_updater deferrable again and
shut down on idle") made vmstat_shepherd deferrable.  vmstat_update
itself is still useing standard timer which might interrupt idle task.
This is possible because "mm, vmstat: make quiet_vmstat lighter" removed
cancel_delayed_work from the quiet_vmstat.

Change vmstat_work to use DEFERRABLE_WORK to prevent from pointless
wakeups from the idle context.

Acked-by: Christoph Lameter 
Signed-off-by: Michal Hocko 
Cc: Mike Galbraith 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm, vmstat: make quiet_vmstat lighter

2016-02-06T02:10:40+00:00

Mike has reported a considerable overhead of refresh_cpu_vm_stats from
the idle entry during pipe test:

    12.89%  [kernel]       [k] refresh_cpu_vm_stats.isra.12
     4.75%  [kernel]       [k] __schedule
     4.70%  [kernel]       [k] mutex_unlock
     3.14%  [kernel]       [k] __switch_to

This is caused by commit 0eb77e988032 ("vmstat: make vmstat_updater
deferrable again and shut down on idle") which has placed quiet_vmstat
into cpu_idle_loop.  The main reason here seems to be that the idle
entry has to get over all zones and perform atomic operations for each
vmstat entry even though there might be no per cpu diffs.  This is a
pointless overhead for _each_ idle entry.

Make sure that quiet_vmstat is as light as possible.

First of all it doesn't make any sense to do any local sync if the
current cpu is already set in oncpu_stat_off because vmstat_update puts
itself there only if there is nothing to do.

Then we can check need_update which should be a cheap way to check for
potential per-cpu diffs and only then do refresh_cpu_vm_stats.

The original patch also did cancel_delayed_work which we are not doing
here.  There are two reasons for that.  Firstly cancel_delayed_work from
idle context will blow up on RT kernels (reported by Mike):

  CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.5.0-rt3 #7
  Hardware name: MEDION MS-7848/MS-7848, BIOS M7848W08.20C 09/23/2013
  Call Trace:
    dump_stack+0x49/0x67
    ___might_sleep+0xf5/0x180
    rt_spin_lock+0x20/0x50
    try_to_grab_pending+0x69/0x240
    cancel_delayed_work+0x26/0xe0
    quiet_vmstat+0x75/0xa0
    cpu_idle_loop+0x38/0x3e0
    cpu_startup_entry+0x13/0x20
    start_secondary+0x114/0x140

And secondly, even on !RT kernels it might add some non trivial overhead
which is not necessary.  Even if the vmstat worker wakes up and preempts
idle then it will be most likely a single shot noop because the stats
were already synced and so it would end up on the oncpu_stat_off anyway.
We just need to teach both vmstat_shepherd and vmstat_update to stop
scheduling the worker if there is nothing to do.

[mgalbraith@suse.de: cancel pending work of the cpu_stat_off CPU]
Signed-off-by: Michal Hocko 
Reported-by: Mike Galbraith 
Acked-by: Christoph Lameter 
Signed-off-by: Mike Galbraith 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

vmstat: Remove BUG_ON from vmstat_update

2016-01-24T16:55:52+00:00

If we detect that there is nothing to do just set the flag and do not
check if it was already set before.  Races really do not matter.  If the
flag is set by any code then the shepherd will start dealing with the
situation and reenable the vmstat workers when necessary again.

Since commit 0eb77e988032 ("vmstat: make vmstat_updater deferrable again
and shut down on idle") quiet_vmstat might update cpu_stat_off and mark
a particular cpu to be handled by vmstat_shepherd.  This might trigger a
VM_BUG_ON in vmstat_update because the work item might have been
sleeping during the idle period and see the cpu_stat_off updated after
the wake up.  The VM_BUG_ON is therefore misleading and no more
appropriate.  Moreover it doesn't really suite any protection from real
bugs because vmstat_shepherd will simply reschedule the vmstat_work
anytime it sees a particular cpu set or vmstat_update would do the same
from the worker context directly.  Even when the two would race the
result wouldn't be incorrect as the counters update is fully idempotent.

Reported-by: Sasha Levin 
Signed-off-by: Christoph Lameter 
Acked-by: Michal Hocko 
Cc: Johannes Weiner 
Cc: Tetsuo Handa 
Cc: Andrew Morton 
Signed-off-by: Linus Torvalds

mm: support madvise(MADV_FREE)

2016-01-16T01:56:32+00:00

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 
Acked-by: Michal Hocko 
Acked-by: Hugh Dickins 
Cc: Mika Penttil 
Cc: Michael Kerrisk 
Cc: Johannes Weiner 
Cc: Rik van Riel 
Cc: Mel Gorman 
Cc: KOSAKI Motohiro 
Cc: Jason Evans 
Cc: Daniel Micay 
Cc: "Kirill A. Shutemov" 
Cc: Shaohua Li 
Cc: 
Cc: Andy Lutomirski 
Cc: "James E.J. Bottomley" 
Cc: "Kirill A. Shutemov" 
Cc: "Shaohua Li" 
Cc: Andrea Arcangeli 
Cc: Arnd Bergmann 
Cc: Benjamin Herrenschmidt 
Cc: Catalin Marinas 
Cc: Chen Gang 
Cc: Chris Zankel 
Cc: Darrick J. Wong 
Cc: David S. Miller 
Cc: Helge Deller 
Cc: Ivan Kokshaysky 
Cc: Matt Turner 
Cc: Max Filippov 
Cc: Ralf Baechle 
Cc: Richard Henderson 
Cc: Roland Dreier 
Cc: Russell King 
Cc: Shaohua Li 
Cc: Will Deacon 
Cc: Wu Fengguang 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm, vmstats: new THP splitting event

2016-01-16T01:56:32+00:00

The patch replaces THP_SPLIT with tree events: THP_SPLIT_PAGE,
THP_SPLIT_PAGE_FAILED and THP_SPLIT_PMD.  It reflects the fact that we
are going to be able split PMD without the compound page and that
split_huge_page() can fail.

Signed-off-by: Kirill A.  Shutemov 
Acked-by: Christoph Lameter 
Tested-by: Sasha Levin 
Tested-by: Aneesh Kumar K.V 
Acked-by: Jerome Marchand 
Acked-by: Vlastimil Babka 
Cc: Andrea Arcangeli 
Cc: Hugh Dickins 
Cc: Dave Hansen 
Cc: Mel Gorman 
Cc: Rik van Riel 
Cc: Naoya Horiguchi 
Cc: Steve Capper 
Cc: Johannes Weiner 
Cc: Michal Hocko 
Cc: David Rientjes 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

vmstat: make vmstat_updater deferrable again and shut down on idle

2016-01-15T00:00:49+00:00

Currently the vmstat updater is not deferrable as a result of commit
ba4877b9ca51 ("vmstat: do not use deferrable delayed work for
vmstat_update").  This in turn can cause multiple interruptions of the
applications because the vmstat updater may run at

Make vmstate_update deferrable again and provide a function that folds
the differentials when the processor is going to idle mode thus
addressing the issue of the above commit in a clean way.

Note that the shepherd thread will continue scanning the differentials
from another processor and will reenable the vmstat workers if it
detects any changes.

Fixes: ba4877b9ca51 ("vmstat: do not use deferrable delayed work for vmstat_update")
Signed-off-by: Christoph Lameter 
Cc: Michal Hocko 
Cc: Johannes Weiner 
Cc: Tetsuo Handa 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds