It's unnecessary to SIGKILL a task that is already PF_EXITING and can
actually cause a NULL pointer dereference of the sighand if it has already
been detached. Instead, simply set TIF_MEMDIE so it has access to memory
reserves and can quickly exit as the comment implies.
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
It's possible to livelock the page allocator if a thread has mm->mmap_sem
and fails to make forward progress because the oom killer selects another
thread sharing the same ->mm to kill that cannot exit until the semaphore
is dropped.
The oom killer will not kill multiple tasks at the same time; each oom
killed task must exit before another task may be killed. Thus, if one
thread is holding mm->mmap_sem and cannot allocate memory, all threads
sharing the same ->mm are blocked from exiting as well. In the oom kill
case, that means the thread holding mm->mmap_sem will never free
additional memory since it cannot get access to memory reserves and the
thread that depends on it with access to memory reserves cannot exit
because it cannot acquire the semaphore. Thus, the page allocators
livelocks.
When the oom killer is called and current happens to have a pending
SIGKILL, this patch automatically gives it access to memory reserves and
returns. Upon returning to the page allocator, its allocation will
hopefully succeed so it can quickly exit and free its memory. If not, the
page allocator will fail the allocation if it is not __GFP_NOFAIL.
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When find_lock_task_mm() returns a thread other than p in dump_tasks(),
its name should be displayed instead. This is the thread that will be
targeted by the oom killer, not its mm-less parent.
This also allows us to safely dereference task->comm without needing
get_task_comm().
While we're here, remove the cast on task_cpu(task) as Andrew suggested.
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The comments in dump_tasks() should be updated to be more clear about why
tasks are filtered and how they are filtered by its argument.
An unnecessary comment concerning a check for is_global_init() is removed
since it isn't of importance.
Suggested-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
dump_task() should use find_lock_task_mm() too. It is necessary for
protecting task-exiting race.
dump_tasks() currently filters any task that does not have an attached
->mm since it incorrectly assumes that it must either be in the process of
exiting and has detached its memory or that it's a kernel thread;
multithreaded tasks may actually have subthreads that have a valid ->mm
pointer and thus those threads should actually be displayed. This change
finds those threads, if they exist, and emit their information along with
the rest of the candidate tasks for kill.
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Almost all ->mm == NULL checks in oom_kill.c are wrong.
The current code assumes that the task without ->mm has already released
its memory and ignores the process. However this is not necessarily true
when this process is multithreaded, other live sub-threads can use this
->mm.
- Remove the "if (!p->mm)" check in select_bad_process(), it is
just wrong.
- Add the new helper, find_lock_task_mm(), which finds the live
thread which uses the memory and takes task_lock() to pin ->mm
- change oom_badness() to use this helper instead of just checking
->mm != NULL.
- As David pointed out, select_bad_process() must never choose the
task without ->mm, but no matter what oom_badness() returns the
task can be chosen if nothing else has been found yet.
Change oom_badness() to return int, change it to return -1 if
find_lock_task_mm() fails, and change select_bad_process() to
check points >= 0.
Note! This patch is not enough, we need more changes.
- oom_badness() was fixed, but oom_kill_task() still ignores
the task without ->mm
- oom_forkbomb_penalty() should use find_lock_task_mm() too,
and it also needs other changes to actually find the first
first-descendant children
This will be addressed later.
[kosaki.motohiro@jp.fujitsu.com: use in badness(), __oom_kill_task()]
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
select_bad_process() checks PF_EXITING to detect the task which is going
to release its memory, but the logic is very wrong.
- a single process P with the dead group leader disables
select_bad_process() completely, it will always return
ERR_PTR() while P can live forever
- if the PF_EXITING task has already released its ->mm
it doesn't make sense to expect it is goiing to free
more memory (except task_struct/etc)
Change the code to ignore the PF_EXITING tasks without ->mm.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
select_bad_process() thinks a kernel thread can't have ->mm != NULL, this
is not true due to use_mm().
Change the code to check PF_KTHREAD.
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
KSM reference counts can cause an anon_vma to exist after the processe it
belongs to have already exited. Because the anon_vma lock now lives in
the root anon_vma, we need to ensure that the root anon_vma stays around
until after all the "child" anon_vmas have been freed.
The obvious way to do this is to have a "child" anon_vma take a reference
to the root in anon_vma_fork. When the anon_vma is freed at munmap or
process exit, we drop the refcount in anon_vma_unlink and possibly free
the root anon_vma.
The KSM anon_vma reference count function also needs to be modified to
deal with the possibility of freeing 2 levels of anon_vma. The easiest
way to do this is to break out the KSM magic and make it generic.
When compiling without CONFIG_KSM, this code is compiled out.
Signed-off-by: Rik van Riel <riel@redhat.com>
Tested-by: Larry Woodman <lwoodman@redhat.com>
Acked-by: Larry Woodman <lwoodman@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Tested-by: Dave Young <hidave.darkstar@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Always (and only) lock the root (oldest) anon_vma whenever we do something
in an anon_vma. The recently introduced anon_vma scalability is due to
the rmap code scanning only the VMAs that need to be scanned. Many common
operations still took the anon_vma lock on the root anon_vma, so always
taking that lock is not expected to introduce any scalability issues.
However, always taking the same lock does mean we only need to take one
lock, which means rmap_walk on pages from any anon_vma in the vma is
excluded from occurring during an munmap, expand_stack or other operation
that needs to exclude rmap_walk and similar functions.
Also add the proper locking to vma_adjust.
Signed-off-by: Rik van Riel <riel@redhat.com>
Tested-by: Larry Woodman <lwoodman@redhat.com>
Acked-by: Larry Woodman <lwoodman@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Track the root (oldest) anon_vma in each anon_vma tree. Because we only
take the lock on the root anon_vma, we cannot use the lock on higher-up
anon_vmas to lock anything. This makes it impossible to do an indirect
lookup of the root anon_vma, since the data structures could go away from
under us.
However, a direct pointer is safe because the root anon_vma is always the
last one that gets freed on munmap or exit, by virtue of the same_vma list
order and unlink_anon_vmas walking the list forward.
[akpm@linux-foundation.org: fix typo]
Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Tested-by: Larry Woodman <lwoodman@redhat.com>
Acked-by: Larry Woodman <lwoodman@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Subsitute a direct call of spin_lock(anon_vma->lock) with an inline
function doing exactly the same.
This makes it easier to do the substitution to the root anon_vma lock in a
following patch.
We will deal with the handful of special locks (nested, dec_and_lock, etc)
separately.
Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Tested-by: Larry Woodman <lwoodman@redhat.com>
Acked-by: Larry Woodman <lwoodman@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Rename anon_vma_lock to vma_lock_anon_vma. This matches the naming style
used in page_lock_anon_vma and will come in really handy further down in
this patch series.
Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Tested-by: Larry Woodman <lwoodman@redhat.com>
Acked-by: Larry Woodman <lwoodman@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When a copy-on-write occurs, we take one of two paths in handle_mm_fault:
through handle_pte_fault for normal pages, or through hugetlb_fault for
huge pages.
In the normal page case, we eventually get to do_wp_page and call mmu
notifiers via ptep_clear_flush_notify. There is no callout to the mmmu
notifiers in the huge page case. This patch fixes that.
Signed-off-by: Doug Doan <dougd@cray.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Provide an INIT_MM_CONTEXT intializer macro which can be used to
statically initialize mm_struct:mm_context of init_mm. This way we can
get rid of code which will do the initialization at run time (on s390).
In addition the current code can be found at a place where it is not
expected. So let's have a common initializer which architectures
can use if needed.
This is based on a patch from Suzuki Poulose.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Suzuki Poulose <suzuki@in.ibm.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Use ERR_CAST(x) rather than ERR_PTR(PTR_ERR(x)). The former makes more
clear what is the purpose of the operation, which otherwise looks like a
no-op.
The semantic patch that makes this change is as follows:
(http://coccinelle.lip6.fr/)
// <smpl>
@@
type T;
T x;
identifier f;
@@
T f (...) { <+...
- ERR_PTR(PTR_ERR(x))
+ x
...+> }
@@
expression x;
@@
- ERR_PTR(PTR_ERR(x))
+ ERR_CAST(x)
// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Use memdup_user when user data is immediately copied into the
allocated region.
The semantic patch that makes this change is as follows:
(http://coccinelle.lip6.fr/)
// <smpl>
@@
expression from,to,size,flag;
position p;
identifier l1,l2;
@@
- to = \(kmalloc@p\|kzalloc@p\)(size,flag);
+ to = memdup_user(from,size);
if (
- to==NULL
+ IS_ERR(to)
|| ...) {
<+... when != goto l1;
- -ENOMEM
+ PTR_ERR(to)
...+>
}
- if (copy_from_user(to, from, size) != 0) {
- <+... when != goto l2;
- -EFAULT
- ...+>
- }
// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Make sure we check the truncate constraints early on in ->setattr by adding
those checks to inode_change_ok. Also clean up and document inode_change_ok
to make this obvious.
As a fallout we don't have to call inode_newsize_ok from simple_setsize and
simplify it down to a truncate_setsize which doesn't return an error. This
simplifies a lot of setattr implementations and means we use truncate_setsize
almost everywhere. Get rid of fat_setsize now that it's trivial and mark
ext2_setsize static to make the calling convention obvious.
Keep the inode_newsize_ok in vmtruncate for now as all callers need an
audit for its removal anyway.
Note: setattr code in ecryptfs doesn't call inode_change_ok at all and
needs a deeper audit, but that is left for later.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Make sure we call inode_change_ok before doing any changes in ->setattr,
and make sure to call it even if our fs wants to ignore normal UNIX
permissions, but use the ATTR_FORCE to skip those.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Despite its name it's now a generic implementation of ->setattr, but
rather a helper to copy attributes from a struct iattr to the inode.
Rename it to setattr_copy to reflect this fact.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
This patch fixes alignment of slab objects in case CONFIG_DEBUG_PAGEALLOC is
active.
Before this spot in kmem_cache_create, we have this situation:
- align contains the required alignment of the object
- cachep->obj_offset is 0 or equals align in case of CONFIG_DEBUG_SLAB
- size equals the size of the object, or object plus trailing redzone in case
of CONFIG_DEBUG_SLAB
This spot tries to fill one page per object if the object is in certain size
limits, however setting obj_offset to PAGE_SIZE - size does break the object
alignment since size may not be aligned with the required alignment.
This patch simply adds an ALIGN(size, align) to the equation and fixes the
object size detection accordingly.
This code in drivers/s390/cio/qdio_setup_init has lead to incorrectly aligned
slab objects (sizeof(struct qdio_q) equals 1792):
qdio_q_cache = kmem_cache_create("qdio_q", sizeof(struct qdio_q),
256, 0, NULL);
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
All callers expect a boolean result which is true if the region
overlaps a reserved region. However, the implementation actually
returns -1 if there is no overlap, and a region index (0 based)
if there is.
Make it behave as callers (and common sense) expect.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Fix a bug where a lock is _bh nested within another _bh lock,
but forgets to use the _bh variant for unlock.
Further more, it's not necessary to test _bh locks, the inner lock
can just use spin_lock(). So fix up the bug by making that change.
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
This patch makes sure we first initialize everything and set the BDI_registered
flag, and only after this we add the bdi to 'bdi_list'. Current code adds the
bdi to the list too early, and as a result I the
WARN(!test_bit(BDI_registered, &bdi->state)
in bdi forker is triggered. Also, it is in general good practice to make things
visible only when they are fully initialized.
Also, this patch does few micro clean-ups:
1. Removes the 'exit' label which does not do anything, just returns. This
allows to get rid of few braces and 'ret' variable and make the code smaller.
2. If 'kthread_run()' fails, remove the error code it returns, not hard-coded
'-ENOMEM'. Theoretically, some day 'kthread_run()' can return something
else. Also, in case of failure it is not necessary to set 'bdi->wb.task' to
NULL.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Add 2 new trace points to the periodic write-back wake up case, just like we do
in the 'bdi_queue_work()' function. Namely, introduce:
1. trace_writeback_wake_thread(bdi)
2. trace_writeback_wake_forker_thread(bdi)
The first event is triggered every time we wake up a bdi thread to start
periodic background write-out. The second event is triggered only when the bdi
thread does not exist and should be created by the forker thread.
This patch was suggested by Dave Chinner and Christoph Hellwig.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
The 'setup_timer()' function also calls 'init_timer()', so the extra
'init_timer()' call is not needed. Indeed, 'setup_timer()' is basically
'init_timer()' plus callback function and data pointers initialization.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Whe the first inode for a bdi is marked dirty, we wake up the bdi thread which
should take care of the periodic background write-out. However, the write-out
will actually start only 'dirty_writeback_interval' centisecs later, so we can
delay the wake-up.
This change was requested by Nick Piggin who pointed out that if we delay the
wake-up, we weed out 2 unnecessary contex switches, which matters because
'__mark_inode_dirty()' is a hot-path function.
This patch introduces a new function - 'bdi_wakeup_thread_delayed()', which
sets up a timer to wake-up the bdi thread and returns. So the wake-up is
delayed.
We also delete the timer in bdi threads just before writing-back. And
synchronously delete it when unregistering bdi. At the unregister point the bdi
does not have any users, so no one can arm it again.
Since now we take 'bdi->wb_lock' in the timer, which can execute in softirq
context, we have to use 'spin_lock_bh()' for 'bdi->wb_lock'. This patch makes
this change as well.
This patch also moves the 'bdi_wb_init()' function down in the file to avoid
forward-declaration of 'bdi_wakeup_thread_delayed()'.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Finally, we can get rid of unnecessary wake-ups in bdi threads, which are very
bad for battery-driven devices.
There are two types of activities bdi threads do:
1. process bdi works from the 'bdi->work_list'
2. periodic write-back
So there are 2 sources of wake-up events for bdi threads:
1. 'bdi_queue_work()' - submits bdi works
2. '__mark_inode_dirty()' - adds dirty I/O to bdi's
The former already has bdi wake-up code. The latter does not, and this patch
adds it.
'__mark_inode_dirty()' is hot-path function, but this patch adds another
'spin_lock(&bdi->wb_lock)' there. However, it is taken only in rare cases when
the bdi has no dirty inodes. So adding this spinlock should be fine and should
not affect performance.
This patch makes sure bdi threads and the forker thread do not wake-up if there
is nothing to do. The forker thread will nevertheless wake up at least every
5 min. to check whether it has to kill a bdi thread. This can also be optimized,
but is not worth it.
This patch also tidies up the warning about unregistered bid, and turns it from
an ugly crocodile to a simple 'WARN()' statement.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Currently, bdi threads can decide to exit if there were no useful activities
for 5 minutes. However, this causes nasty races: we can easily oops in the
'bdi_queue_work()' if the bdi thread decides to exit while we are waking it up.
And even if we do not oops, but the bdi tread exits immediately after we wake
it up, we'd lose the wake-up event and have an unnecessary delay (up to 5 secs)
in the bdi work processing.
This patch makes the forker thread to be the central place which not only
creates bdi threads, but also kills them if they were inactive long enough.
This better design-wise.
Another reason why this change was done is to prepare for the further changes
which will prevent the bdi threads from waking up every 5 sec and wasting
power. Indeed, when the task does not wake up periodically anymore, it won't be
able to exit either.
This patch also moves the the 'wake_up_bit()' call from the bdi thread to the
forker thread as well. So now the forker thread sets the BDI_pending bit, then
forks the task or kills it, then clears the bit and wakes up the waiting
process.
The only process which may wain on the bit is 'bdi_wb_shutdown()'. This
function was changed as well - now it first removes the bdi from the
'bdi_list', then waits on the 'BDI_pending' bit. Once it wakes up, it is
guaranteed that the forker thread won't race with it, because the bdi is not
visible. Note, the forker thread sets the 'BDI_pending' bit under the
'bdi->wb_lock' which is essential for proper serialization.
And additionally, when we change 'bdi->wb.task', we now take the
'bdi->work_lock', to make sure that we do not lose wake-ups which we otherwise
would when raced with, say, 'bdi_queue_work()'.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
This patch re-structures the bdi forker a little:
1. Add 'bdi_cap_flush_forker(bdi)' condition check to the bdi loop. The reason
for this is that the forker thread can start _before_ the 'BDI_registered'
flag is set (see 'bdi_register()'), so the WARN() statement will fire for
the default bdi. I observed this warning at boot-up.
2. Introduce an enum 'action' and use "switch" statement in the outer loop.
This is a preparation to the further patch which will teach the forker
thread killing bdi threads, so we'll have another case in the "switch"
statement. This change was suggested by Christoph Hellwig.
This patch is just a small step towards the coming change where the forker
thread will kill the bdi threads. It should simplify reviewing the following
changes, which would otherwise be larger.
This patch also amends comments a little.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
The forker thread removes bdis from 'bdi_list' before forking the bdi thread.
But this is wrong for at least 2 reasons.
Reason #1: if we temporary remove a bdi from the list, we may miss works which
would otherwise be given to us.
Reason #2: this is racy; indeed, 'bdi_wb_shutdown()' expects that bdis are
always in the 'bdi_list' (see 'bdi_remove_from_list()'), and when
it races with the forker thread, it can shut down the bdi thread
at the same time as the forker creates it.
This patch makes sure the forker thread never removes bdis from 'bdi_list'
(which was suggested by Christoph Hellwig).
In order to make sure that we do not race with 'bdi_wb_shutdown()', we have to
hold the 'bdi_lock' while walking the 'bdi_list' and setting the 'BDI_pending'
flag.
NOTE! The error path is interesting. Currently, when we fail to create a bdi
thread, we move the bdi to the tail of 'bdi_list'. But if we never remove the
bdi from the list, we cannot move it to the tail either, because then we can
mess up the RCU readers which walk the list. And also, we'll have the race
described above in "Reason #2".
But I not think that adding to the tail is any important so I just do not do
that.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
This patch simplifies bdi code a little by removing the 'pending_list' which is
redundant. Indeed, currently the forker thread ('bdi_forker_thread()') is
working like this:
1. In a loop, fetch all bdi's which have works but have no writeback thread and
move them to the 'pending_list'.
2. If the list is empty, sleep for 5 sec.
3. Otherwise, take one bdi from the list, fork the writeback thread for this
bdi, and repeat the loop.
IOW, it first moves everything to the 'pending_list', then process only one
element, and so on. This patch simplifies the algorithm, which is now as
follows.
1. Find the first bdi which has a work and remove it from the global list of
bdi's (bdi_list).
2. If there was not such bdi, sleep 5 sec.
3. Fork the writeback thread for this bdi and repeat the loop.
IOW, now we find the first bdi to process, process it, and so on. This is
simpler and involves less lists.
The bonus now is that we can get rid of a couple of functions, as well as
remove complications which involve 'rcu_call()' and 'bdi->rcu_head'.
This patch also makes sure we use 'list_add_tail_rcu()', instead of plain
'list_add_tail()', but this piece of code is going to be removed in the next
patch anyway.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Currently, if someone submits jobs for the default bdi, we can lose wake-up
events. E.g., this can happen if 'bdi_queue_work()' is called when
'bdi_forker_thread()' is executing code after 'wb_do_writeback(me, 0)', but
before 'set_current_state(TASK_INTERRUPTIBLE)'.
This situation is unlikely, and the result is not very severe - we'll just
delay the execution of the work, but this is still not very nice.
This patch fixes the issue by checking whether the default bdi has works before
the forker thread goes sleep.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Currently the forker thread can lose wake-ups which may lead to unnecessary
delays in processing bdi works. E.g., consider the following scenario.
1. 'bdi_forker_thread()' walks the 'bdi_list', finds out there is nothing to
do, and is about to finish the loop.
2. A bdi thread decides to exit because it was inactive for long time.
3. 'bdi_queue_work()' adds a work to the bdi which just exited, so it wakes up
the forker thread.
4. but 'bdi_forker_thread()' executes 'set_current_state(TASK_INTERRUPTIBLE)'
and goes sleep. We lose a wake-up.
Losing the wake-up is not fatal, but this means that the bdi work processing
will be delayed by up to 5 sec. This race is theoretical, I never hit it, but
it is worth fixing.
The fix is to execute 'set_current_state(TASK_INTERRUPTIBLE)' _before_ walking
'bdi_list', not after.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
This patch fixes a very unlikely race condition on the bdi forker thread error
path: when bdi thread creation fails, 'bdi->wb.task' may contain the error code
for a short period of time. If at the same time someone submits a work to this
bdi, we can end up with an oops 'bdi_queue_work()' while executing
'wake_up_process(wb->task)'.
This patch fixes the issue by introducing a temporary variable 'task' and
storing the possible error code there, so that 'wb->task' would never take
erroneous values.
Note, this race is very unlikely and I never hit it, so it is theoretical, but
nevertheless worth fixing.
This patch also merges 2 comments which were previously separate.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
The write-back code mixes words "thread" and "task" for the same things. This
is not a big deal, but still an inconsistency.
hch: a convention I tend to use and I've seen in various places
is to always use _task for the storage of the task_struct pointer,
and thread everywhere else. This especially helps with having
foo_thread for the actual thread and foo_task for a global
variable keeping the task_struct pointer
This patch renames:
* 'bdi_add_default_flusher_task()' -> 'bdi_add_default_flusher_thread()'
* 'bdi_forker_task()' -> 'bdi_forker_thread()'
because bdi threads are 'bdi_writeback_thread()', so these names are more
consistent.
This patch also amends commentaries and makes them refer the forker and bdi
threads as "thread", not "task".
Also, while on it, make 'bdi_add_default_flusher_thread()' declaration use
'static void' instead of 'void static' and make checkpatch.pl happy.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Add a trace event to the ->writepage loop in write_cache_pages to give
visibility into how the ->writepage call is changing variables within the
writeback control structure. Of most interest is how wbc->nr_to_write changes
from call to call, especially with filesystems that write multiple pages
in ->writepage.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Tracing high level background writeback events is good, but it doesn't
give the entire picture. Add visibility into write throttling to catch IO
dispatched by foreground throttling of processing dirtying lots of pages.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Trace queue/sched/exec parts of the writeback loop. This provides
insight into when and why flusher threads are scheduled to run. e.g
a sync invocation leaves traces like:
sync-[...]: writeback_queue: bdi 8:0: sb_dev 8:1 nr_pages=7712 sync_mode=0 kupdate=0 range_cyclic=0 background=0
flush-8:0-[...]: writeback_exec: bdi 8:0: sb_dev 8:1 nr_pages=7712 sync_mode=0 kupdate=0 range_cyclic=0 background=0
This also lays the foundation for adding more writeback tracing to
provide deeper insight into the whole writeback path.
The original tracing code is from Jens Axboe, though this version is
a rewrite as a result of the code being traced changing
significantly.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Move all code for the writeback thread into fs/fs-writeback.c instead of
splitting it over two functions in two files.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
The wb_list member of struct backing_device_info always has exactly one
element. Just use the direct bdi->wb pointer instead and simplify some
code.
Also remove bdi_task_init which is now trivial to prepare for the next
patch.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Remove the current bio flags and reuse the request flags for the bio, too.
This allows to more easily trace the type of I/O from the filesystem
down to the block driver. There were two flags in the bio that were
missing in the requests: BIO_RW_UNPLUG and BIO_RW_AHEAD. Also I've
renamed two request flags that had a superflous RW in them.
Note that the flags are in bio.h despite having the REQ_ name - as
blkdev.h includes bio.h that is the only way to go for now.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/slab-2.6:
slub: Allow removal of slab caches during boot
Revert "slub: Allow removal of slab caches during boot"
slub numa: Fix rare allocation from unexpected node
slab: use deferable timers for its periodic housekeeping
slub: Use kmem_cache flags to detect if slab is in debugging mode.
slub: Allow removal of slab caches during boot
slub: Check kasprintf results in kmem_cache_init()
SLUB: Constants need UL
slub: Use a constant for a unspecified node.
SLOB: Free objects to their own list
slab: fix caller tracking on !CONFIG_DEBUG_SLAB && CONFIG_TRACING
* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86: Ioremap: fix wrong physical address handling in PAT code
x86, tlb: Clean up and correct used type
x86, iomap: Fix wrong page aligned size calculation in ioremapping code
x86, mm: Create symbolic index into address_markers array
x86, ioremap: Fix normal ram range check
x86, ioremap: Fix incorrect physical address handling in PAE mode
x86-64, mm: Initialize VDSO earlier on 64 bits
x86, kmmio/mmiotrace: Fix double free of kmmio_fault_pages
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (162 commits)
tracing/kprobes: unregister_trace_probe needs to be called under mutex
perf: expose event__process function
perf events: Fix mmap offset determination
perf, powerpc: fsl_emb: Restore setting perf_sample_data.period
perf, powerpc: Convert the FSL driver to use local64_t
perf tools: Don't keep unreferenced maps when unmaps are detected
perf session: Invalidate last_match when removing threads from rb_tree
perf session: Free the ref_reloc_sym memory at the right place
x86,mmiotrace: Add support for tracing STOS instruction
perf, sched migration: Librarize task states and event headers helpers
perf, sched migration: Librarize the GUI class
perf, sched migration: Make the GUI class client agnostic
perf, sched migration: Make it vertically scrollable
perf, sched migration: Parameterize cpu height and spacing
perf, sched migration: Fix key bindings
perf, sched migration: Ignore unhandled task states
perf, sched migration: Handle ignored migrate out events
perf: New migration tool overview
tracing: Drop cpparg() macro
perf: Use tracepoint_synchronize_unregister() to flush any pending tracepoint call
...
Fix up trivial conflicts in Makefile and drivers/cpufreq/cpufreq.c
* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
Revert "net: Make accesses to ->br_port safe for sparse RCU"
mce: convert to rcu_dereference_index_check()
net: Make accesses to ->br_port safe for sparse RCU
vfs: add fs.h to define struct file
lockdep: Add an in_workqueue_context() lockdep-based test function
rcu: add __rcu API for later sparse checking
rcu: add an rcu_dereference_index_check()
tree/tiny rcu: Add debug RCU head objects
mm: remove all rcu head initializations
fs: remove all rcu head initializations, except on_stack initializations
powerpc: remove all rcu head initializations
* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jwessel/linux-2.6-kgdb:
debug_core,kdb: fix crash when arch does not have single step
kgdb,x86: use macro HBP_NUM to replace magic number 4
kgdb,mips: remove unused kgdb_cpu_doing_single_step operations
mm,kdb,kgdb: Add a debug reference for the kdb kmap usage
KGDB: Remove set but unused newPC
ftrace,kdb: Allow dumping a specific cpu's buffer with ftdump
ftrace,kdb: Extend kdb to be able to dump the ftrace buffer
kgdb,powerpc: Replace hardcoded offset by BREAK_INSTR_SIZE
arm,kgdb: Add ability to trap into debugger on notify_die
gdbstub: do not directly use dbg_reg_def[] in gdb_cmd_reg_set()
gdbstub: Implement gdbserial 'p' and 'P' packets
kgdb,arm: Individual register get/set for arm
kgdb,mips: Individual register get/set for mips
kgdb,x86: Individual register get/set for x86
kgdb,kdb: individual register set and and get API
gdbstub: Optimize kgdb's "thread:" response for the gdb serial protocol
kgdb: remove custom hex_to_bin()implementation
The kdb kmap should never get used outside of the kernel debugger
exception context.
Signed-off-by: Jason Wessel<jason.wessel@windriver.com>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Ingo Molnar <mingo@elte.hu>
CC: linux-mm@kvack.org
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu:
percpu: allow limited allocation before slab is online
percpu: make @dyn_size always mean min dyn_size in first chunk init functions
Serialize kmem_cache_create and kmem_cache_destroy using the slub_lock. Only
possible after the use of the slub_lock during dynamic dma creation has been
removed.
Then make sure that the setup of the slab sysfs entries does not race
with kmem_cache_create and kmem_cache destroy.
If a slab cache is removed before we have setup sysfs then simply skip over
the sysfs handling.
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Roland Dreier <rdreier@cisco.com>
Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
is_hwpoison_address accesses the page table, so the caller must hold
current->mm->mmap_sem in read mode. So fix its usage in hva_to_pfn of
kvm accordingly.
Comment is_hwpoison_address to remind other users.
Reported-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
In common cases, guest SRAO MCE will cause corresponding poisoned page
be un-mapped and SIGBUS be sent to QEMU-KVM, then QEMU-KVM will relay
the MCE to guest OS.
But it is reported that if the poisoned page is accessed in guest
after unmapping and before MCE is relayed to guest OS, userspace will
be killed.
The reason is as follows. Because poisoned page has been un-mapped,
guest access will cause guest exit and kvm_mmu_page_fault will be
called. kvm_mmu_page_fault can not get the poisoned page for fault
address, so kernel and user space MMIO processing is tried in turn. In
user MMIO processing, poisoned page is accessed again, then userspace
is killed by force_sig_info.
To fix the bug, kvm_mmu_page_fault send HWPOISON signal to QEMU-KVM
and do not try kernel and user space MMIO processing for poisoned
page.
[xiao: fix warning introduced by avi]
Reported-by: Max Asbock <masbock@linux.vnet.ibm.com>
Signed-off-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Debian's ia64 autobuilders have been seeing kernel freeze or reboot
when running the gdb testsuite (Debian bug 588574): dannf bisected to
2.6.32 62eede62da "mm: ZERO_PAGE without
PTE_SPECIAL"; and reproduced it with gdb's gcore on a simple target.
I'd missed updating the gate_vma handling in __get_user_pages(): that
happens to use vm_normal_page() (nowadays failing on the zero page),
yet reported success even when it failed to get a page - boom when
access_process_vm() tried to copy that to its intermediate buffer.
Fix this, resisting cleanups: in particular, leave it for now reporting
success when not asked to get any pages - very probably safe to change,
but let's not risk it without testing exposure.
Why did ia64 crash with 16kB pages, but succeed with 64kB pages?
Because setup_gate() pads each 64kB of its gate area with zero pages.
Reported-by: Andreas Barth <aba@not.so.argh.org>
Bisected-by: dann frazier <dannf@debian.org>
Signed-off-by: Hugh Dickins <hughd@google.com>
Tested-by: dann frazier <dannf@dannf.org>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The network developers have seen sporadic allocations resulting in objects
coming from unexpected NUMA nodes despite asking for objects from a
specific node.
This is due to get_partial() calling get_any_partial() if partial
slabs are exhausted for a node even if a node was specified and therefore
one would expect allocations only from the specified node.
get_any_partial() sporadically may return a slab from a foreign
node to gradually reduce the size of partial lists on remote nodes
and thereby reduce total memory use for a slab cache.
The behavior is controlled by the remote_defrag_ratio of each cache.
Strictly speaking this is permitted behavior since __GFP_THISNODE was
not specified for the allocation but it is certain surprising.
This patch makes sure that the remote defrag behavior only occurs
if no node was specified.
Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
Add a flag to force lazy_max_pages() to zero to prevent any outstanding
mapped pages. We'll need this for Xen.
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Nick Piggin <npiggin@suse.de>
We need lock_page_nosync() here because we have no reference to the
mapping when taking the page lock.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Reviewed-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
slab has a "once every 2 second" timer for its housekeeping.
As the number of logical processors is growing, its more and more
common that this 2 second timer becomes the primary wakeup source.
This patch turns this housekeeping timer into a deferable timer,
which means that the timer does not interrupt idle, but just runs
at the next event that wakes the cpu up.
The impact is that the timer likely runs a bit later, but during the
delay no code is running so there's not all that much reason for
a difference in housekeeping to occur because of this delay.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
The description and parameters of the kmemleak API weren't obvious. This
patch adds comments clarifying the API usage.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Introduce a new DEBUG_KMEMLEAK_DEFAULT_OFF config parameter that allows
kmemleak to be disabled by default, but enabled on the command line
via: kmemleak=on. Although a reboot is required to turn it on, its still
useful to not require a re-compile.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
There may be situations when an object is freed using a pointer inside
the memory block. Kmemleak should show more information to help with
debugging.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
With commits 08677214 and 59be5a8e, alloc_bootmem()/free_bootmem() and
friends use the early_res functions for memory management when
NO_BOOTMEM is enabled. This patch adds the kmemleak calls in the
corresponding code paths for bootmem allocations.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Acked-by: Yinghai Lu <yinghai@kernel.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: stable@kernel.org
The pointer to the page_cgroup table allocated in
init_section_page_cgroup() is stored in section->page_cgroup as (base -
pfn). Since this value does not point to the beginning or inside the
allocated memory block, kmemleak reports a false positive.
This was reported in bugzilla.kernel.org as #16297.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Reported-by: Adrien Dessemond <adrien.dessemond@gmail.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Andrew Morton <akpm@linux-foundation.org>
The current shrinker implementation requires the registered callback
to have global state to work from. This makes it difficult to shrink
caches that are not global (e.g. per-filesystem caches). Pass the shrinker
structure to the callback so that users can embed the shrinker structure
in the context the shrinker needs to operate on and get back to it in the
callback via container_of().
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
* 'kmemleak' of git://git.kernel.org/pub/scm/linux/kernel/git/cmarinas/linux-2.6-cm:
kmemleak: Add support for NO_BOOTMEM configurations
kmemleak: Annotate false positive in init_section_page_cgroup()
The cacheline with the flags is reachable from the hot paths after the
percpu allocator changes went in. So there is no need anymore to put a
flag into each slab page. Get rid of the SlubDebug flag and use
the flags in kmem_cache instead.
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
If a slab cache is removed before we have setup sysfs then simply skip over
the sysfs handling.
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Roland Dreier <rdreier@cisco.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
Small allocations may fail during slab bringup which is fatal. Add a BUG_ON()
so that we fail immediately rather than failing later during sysfs
processing.
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
UL suffix is missing in some constants. Conform to how slab.h uses constants.
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
kmalloc_node() and friends can be passed a constant -1 to indicate
that no choice was made for the node from which the object needs to
come.
Use NUMA_NO_NODE instead of -1.
CC: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
SLOB has alloced smaller objects from their own list in reduce overall external
fragmentation and increase repeatability, free to their own list also.
This is /proc/meminfo result in my test machine:
without this patch:
===
MemTotal: 1030720 kB
MemFree: 750012 kB
Buffers: 15496 kB
Cached: 160396 kB
SwapCached: 0 kB
Active: 105024 kB
Inactive: 145604 kB
Active(anon): 74816 kB
Inactive(anon): 2180 kB
Active(file): 30208 kB
Inactive(file): 143424 kB
Unevictable: 16 kB
....
with this patch:
===
MemTotal: 1030720 kB
MemFree: 751908 kB
Buffers: 15492 kB
Cached: 160280 kB
SwapCached: 0 kB
Active: 102720 kB
Inactive: 146140 kB
Active(anon): 73168 kB
Inactive(anon): 2180 kB
Active(file): 29552 kB
Inactive(file): 143960 kB
Unevictable: 16 kB
...
The result shows an improvement of 1 MB!
And when I tested it on a embeded system with 64 MB, I found this path is never
called during kernel bootup.
Acked-by: Matt Mackall <mpm@selenic.com>
Signed-off-by: Bob Liu <lliubbo@gmail.com>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
via following scripts
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/lmb/memblock/g' \
-e 's/LMB/MEMBLOCK/g' \
$FILES
for N in $(find . -name lmb.[ch]); do
M=$(echo $N | sed 's/lmb/memblock/g')
mv $N $M
done
and remove some wrong change like lmbench and dlmb etc.
also move memblock.c from lib/ to mm/
Suggested-by: Ingo Molnar <mingo@elte.hu>
Acked-by: "H. Peter Anvin" <hpa@zytor.com>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Current x86 ioremap() doesn't handle physical address higher than
32-bit properly in X86_32 PAE mode. When physical address higher than
32-bit is passed to ioremap(), higher 32-bits in physical address is
cleared wrongly. Due to this bug, ioremap() can map wrong address to
linear address space.
In my case, 64-bit MMIO region was assigned to a PCI device (ioat
device) on my system. Because of the ioremap()'s bug, wrong physical
address (instead of MMIO region) was mapped to linear address space.
Because of this, loading ioatdma driver caused unexpected behavior
(kernel panic, kernel hangup, ...).
Signed-off-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
LKML-Reference: <4C1AE680.7090408@jp.fujitsu.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
* 'for-linus' of git://git.kernel.dk/linux-2.6-block:
writeback: simplify the write back thread queue
writeback: split writeback_inodes_wb
writeback: remove writeback_inodes_wbc
fs-writeback: fix kernel-doc warnings
splice: check f_mode for seekable file
splice: direct_splice_actor() should not use pos in sd
First remove items from work_list as soon as we start working on them. This
means we don't have to track any pending or visited state and can get
rid of all the RCU magic freeing the work items - we can simply free
them once the operation has finished. Second use a real completion for
tracking synchronous requests - if the caller sets the completion pointer
we complete it, otherwise use it as a boolean indicator that we can free
the work item directly. Third unify struct wb_writeback_args and struct
bdi_work into a single data structure, wb_writeback_work. Previous we
set all parameters into a struct wb_writeback_args, copied it into
struct bdi_work, copied it again on the stack to use it there. Instead
of just allocate one structure dynamically or on the stack and use it
all the way through the stack.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
This was just an odd wrapper around writeback_inodes_wb. Removing this
also allows to get rid of the bdi member of struct writeback_control
which was rather out of place there.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Conflicts:
fs/fs-writeback.c
Merge reason: Resolve the conflict
Note, i picked the version from Linus's tree, which effectively reverts
the fs-writeback.c bits of:
b97181f: fs: remove all rcu head initializations, except on_stack initializations
As the upstream changes to this file changed this code heavily and the
first attempt to resolve the conflict resulted in a non-booting kernel.
It's safer to re-try this portion of the commit cleanly.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
My patch to "Factor out duplicate put/frees in mpol_shared_policy_init()
to a common return path"; and Dan Carpenter's fix thereto both left a
dangling reference to the incoming tmpfs superblock mempolicy structure.
A similar leak was introduced earlier when the nodemask was moved offstack
to the scratch area despite the note in the comment block regarding the
incoming ref.
Move the remaining 'put of the incoming "mpol" to the common exit path to
drop the reference.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Dan Carpenter <error27@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
OOM-waitqueue should be waken up when oom_disable is canceled. This is a
fix for 3c11ecf448 ("memcg: oom kill disable and oom status").
How to test:
Create a cgroup A...
1. set memory.limit and memory.memsw.limit to be small value
2. echo 1 > /cgroup/A/memory.oom_control, this disables oom-kill.
3. run a program which must cause OOM.
A program executed in 3 will sleep by oom_waiqueue in memcg. Then, how to
wake it up is problem.
1. echo 0 > /cgroup/A/memory.oom_control (enable OOM-killer)
2. echo big mem > /cgroup/A/memory.memsw.limit_in_bytes(allow more swap)
etc..
Without the patch, a task in slept can not be waken up.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'for-linus' of git://git.kernel.dk/linux-2.6-block:
block: Don't count_vm_events for discard bio in submit_bio.
cfq: fix recursive call in cfq_blkiocg_update_completion_stats()
cfq-iosched: Fixed boot warning with BLK_CGROUP=y and CFQ_GROUP_IOSCHED=n
cfq: Don't allow queue merges for queues that have no process references
block: fix DISCARD_BARRIER requests
cciss: set SCSI max cmd len to 16, as default is wrong
cpqarray: fix two more wrong section type
cpqarray: fix wrong __init type on pci probe function
drbd: Fixed a race between disk-attach and unexpected state changes
writeback: fix pin_sb_for_writeback
writeback: add missing requeue_io in writeback_inodes_wb
writeback: simplify and split bdi_start_writeback
writeback: simplify wakeup_flusher_threads
writeback: fix writeback_inodes_wb from writeback_inodes_sb
writeback: enforce s_umount locking in writeback_inodes_sb
writeback: queue work on stack in writeback_inodes_sb
writeback: fix writeback completion notifications
This patch updates percpu allocator such that it can serve limited
amount of allocation before slab comes online. This is primarily to
allow slab to depend on working percpu allocator.
Two parameters, PERCPU_DYNAMIC_EARLY_SIZE and SLOTS, determine how
much memory space and allocation map slots are reserved. If this
reserved area is exhausted, WARN_ON_ONCE() will trigger and allocation
will fail till slab comes online.
The following changes are made to implement early alloc.
* pcpu_mem_alloc() now checks slab_is_available()
* Chunks are allocated using pcpu_mem_alloc()
* Init paths make sure ai->dyn_size is at least as large as
PERCPU_DYNAMIC_EARLY_SIZE.
* Initial alloc maps are allocated in __initdata and copied to
kmalloc'd areas once slab is online.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Christoph Lameter <cl@linux-foundation.org>
In pcpu_build_alloc_info() and pcpu_embed_first_chunk(), @dyn_size was
ssize_t, -1 meant auto-size, 0 forced 0 and positive meant minimum
size. There's no use case for forcing 0 and the upcoming early alloc
support always requires non-zero dynamic size. Make @dyn_size always
mean minimum dyn_size.
While at it, make pcpu_build_alloc_info() static which doesn't have
any external caller as suggested by David Rientjes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: David Rientjes <rientjes@google.com>
per_cpu_ptr_to_phys() determines whether the passed in @addr belongs
to the first_chunk or not by just matching the address against the
address range of the base unit (unit0, used by cpu0). When an adress
from another cpu was passed in, it will always determine that the
address doesn't belong to the first chunk even when it does. This
makes the function return a bogus physical address which may lead to
crash.
This problem was discovered by Cliff Wickman while investigating a
crash during kdump on a SGI UV system.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Cliff Wickman <cpw@sgi.com>
Tested-by: Cliff Wickman <cpw@sgi.com>
Cc: stable@kernel.org
Fix the following two trivial bugs in pcpu_build_alloc_info()
* we should memset group_cnt to 0 by size of group_cnt, not size of
group_map (both are of the same size, so the bug isn't dangerous)
* we can delete useless variable group_cnt_max.
Signed-off-by: Pavel V. Panteleev <pp_84@mail.ru>
Signed-off-by: Tejun Heo <tj@kernel.org>
Remove all rcu head inits. We don't care about the RCU head state before passing
it to call_rcu() anyway. Only leave the "on_stack" variants so debugobjects can
keep track of objects on stack.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
bdi_start_writeback now never gets a superblock passed, so we can just remove
that case. And to further untangle the code and flatten the call stack
split it into two trivial helpers for it's two callers.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
We have been resisting new ftrace plugins and removing existing
ones, and kmemtrace has been superseded by kmem trace events
and perf-kmem, so we remove it.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Acked-by: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
[ remove kmemtrace from the makefile, handle slob too ]
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Add the capacility to track data mmap()s. This can be used together
with PERF_SAMPLE_ADDR for data profiling.
Signed-off-by: Anton Blanchard <anton@samba.org>
[Updated code for stable perf ABI]
Signed-off-by: Eric B Munson <ebmunson@us.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <1274193049-25997-1-git-send-email-ebmunson@us.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
sync can currently take a really long time if a concurrent writer is
extending a file. The problem is that the dirty pages on the address
space grow in the same direction as write_cache_pages scans, so if
the writer keeps ahead of writeback, the writeback will not
terminate until the writer stops adding dirty pages.
For a data integrity sync, we only need to write the pages dirty at
the time we start the writeback, so we can stop scanning once we get
to the page that was at the end of the file at the time the scan
started.
This will prevent operations like copying a large file preventing
sync from completing as it will not write back pages that were
dirtied after the sync was started. This does not impact the
existing integrity guarantees, as any dirty page (old or new)
within the EOF range at the start of the scan will still be
captured.
This patch will not prevent sync from blocking on large writes into
holes. That requires more complex intervention while this patch only
addresses the common append-case of this sync holdoff.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
If a filesystem writes more than one page in ->writepage, write_cache_pages
fails to notice this and continues to attempt writeback when wbc->nr_to_write
has gone negative - this trace was captured from XFS:
wbc_writeback_start: towrt=1024
wbc_writepage: towrt=1024
wbc_writepage: towrt=0
wbc_writepage: towrt=-1
wbc_writepage: towrt=-5
wbc_writepage: towrt=-21
wbc_writepage: towrt=-85
This has adverse effects on filesystem writeback behaviour. write_cache_pages()
needs to terminate after a certain number of pages are written, not after a
certain number of calls to ->writepage are made. This is a regression
introduced by 17bc6c30cf ("vfs: Add
no_nrwrite_index_update writeback control flag"), but cannot be reverted
directly due to subsequent bug fixes that have gone in on top of it.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:
Minix: Clean up left over label
fix truncate inode time modification breakage
fix setattr error handling in sysfs, configfs
fcntl: return -EFAULT if copy_to_user fails
wrong type for 'magic' argument in simple_fill_super()
fix the deadlock in qib_fs
mqueue doesn't need make_bad_inode()
* 'for-linus' of git://git.kernel.dk/linux-2.6-block: (27 commits)
block: make blk_init_free_list and elevator_init idempotent
block: avoid unconditionally freeing previously allocated request_queue
pipe: change /proc/sys/fs/pipe-max-pages to byte sized interface
pipe: change the privilege required for growing a pipe beyond system max
pipe: adjust minimum pipe size to 1 page
block: disable preemption before using sched_clock()
cciss: call BUG() earlier
Preparing 8.3.8rc2
drbd: Reduce verbosity
drbd: use drbd specific ratelimit instead of global printk_ratelimit
drbd: fix hang on local read errors while disconnected
drbd: Removed the now empty w_io_error() function
drbd: removed duplicated #includes
drbd: improve usage of MSG_MORE
drbd: need to set socket bufsize early to take effect
drbd: improve network latency, TCP_QUICKACK
drbd: Revert "drbd: Create new current UUID as late as possible"
brd: support discard
Revert "writeback: fix WB_SYNC_NONE writeback from umount"
Revert "writeback: ensure that WB_SYNC_NONE writeback with sb pinned is sync"
...
Greg Thelen reported recent Johannes's stack diet patch makes kernel hang.
His test is following.
mount -t cgroup none /cgroups -o memory
mkdir /cgroups/cg1
echo $$ > /cgroups/cg1/tasks
dd bs=1024 count=1024 if=/dev/null of=/data/foo
echo $$ > /cgroups/tasks
echo 1 > /cgroups/cg1/memory.force_empty
Actually, This OOM hard to try logic have been corrupted since following
two years old patch.
commit a41f24ea9f
Author: Nishanth Aravamudan <nacc@us.ibm.com>
Date: Tue Apr 29 00:58:25 2008 -0700
page allocator: smarter retry of costly-order allocations
Original intention was "return success if the system have shrinkable zones
though priority==0 reclaim was failure". But the above patch changed to
"return nr_reclaimed if .....". Oh, That forgot nr_reclaimed may be 0 if
priority==0 reclaim failure.
And Johannes's patch 0aeb2339e5 ("vmscan: remove all_unreclaimable scan
control") made it more corrupt. Originally, priority==0 reclaim failure
on memcg return 0, but this patch changed to return 1. It totally
confused memcg.
This patch fixes it completely.
Reported-by: Greg Thelen <gthelen@google.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Tested-by: Greg Thelen <gthelen@google.com>
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mtime and ctime should be changed only if the file size has actually
changed. Patches changing ext2 and tmpfs from vmtruncate to new truncate
sequence has caused regressions where they always update timestamps.
There is some strange cases in POSIX where truncate(2) must not update
times unless the size has acutally changed, see 6e656be89.
This area is all still rather buggy in different ways in a lot of
filesystems and needs a cleanup and audit (ideally the vfs will provide
a simple attribute or call to direct all filesystems exactly which
attributes to change). But coming up with the best solution will take a
while and is not appropriate for rc anyway.
So fix recent regression for now.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
This reverts commit e913fc825d.
We are investigating a hang associated with the WB_SYNC_NONE changes,
so revert them for now.
Conflicts:
fs/fs-writeback.c
mm/page-writeback.c
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
* 'slub/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/slab-2.6:
SLUB: Allow full duplication of kmalloc array for 390
slub: move kmem_cache_node into it's own cacheline
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse:
mm: export generic_pipe_buf_*() to modules
fuse: support splice() reading from fuse device
fuse: allow splice to move pages
mm: export remove_from_page_cache() to modules
mm: export lru_cache_add_*() to modules
fuse: support splice() writing to fuse device
fuse: get page reference for readpages
fuse: use get_user_pages_fast()
fuse: remove unneeded variable
Introduce a new truncate calling sequence into fs/mm subsystems. Rather than
setattr > vmtruncate > truncate, have filesystems call their truncate sequence
from ->setattr if filesystem specific operations are required. vmtruncate is
deprecated, and truncate_pagecache and inode_newsize_ok helpers introduced
previously should be used.
simple_setattr is introduced for simple in-ram filesystems to implement
the new truncate sequence. Eventually all filesystems should be converted
to implement a setattr, and the default code in notify_change should go
away.
simple_setsize is also introduced to perform just the ATTR_SIZE portion
of simple_setattr (ie. changing i_size and trimming pagecache).
To implement the new truncate sequence:
- filesystem specific manipulations (eg freeing blocks) must be done in
the setattr method rather than ->truncate.
- vmtruncate can not be used by core code to trim blocks past i_size in
the event of write failure after allocation, so this must be performed
in the fs code.
- convert usage of helpers block_write_begin, nobh_write_begin,
cont_write_begin, and *blockdev_direct_IO* to use _newtrunc postfixed
variants. These avoid calling vmtruncate to trim blocks (see previous).
- inode_setattr should not be used. generic_setattr is a new function
to be used to copy simple attributes into the generic inode.
- make use of the better opportunity to handle errors with the new sequence.
Big problem with the previous calling sequence: the filesystem is not called
until i_size has already changed. This means it is not allowed to fail the
call, and also it does not know what the previous i_size was. Also, generic
code calling vmtruncate to truncate allocated blocks in case of error had
no good way to return a meaningful error (or, for example, atomically handle
block deallocation).
Cc: Christoph Hellwig <hch@lst.de>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
We don't name our generic fsync implementations very well currently.
The no-op implementation for in-memory filesystems currently is called
simple_sync_file which doesn't make too much sense to start with,
the the generic one for simple filesystems is called simple_fsync
which can lead to some confusion.
This patch renames the generic file fsync method to generic_file_fsync
to match the other generic_file_* routines it is supposed to be used
with, and the no-op implementation to noop_fsync to make it obvious
what to expect. In addition add some documentation for both methods.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
* git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable: (27 commits)
Btrfs: add more error checking to btrfs_dirty_inode
Btrfs: allow unaligned DIO
Btrfs: drop verbose enospc printk
Btrfs: Fix block generation verification race
Btrfs: fix preallocation and nodatacow checks in O_DIRECT
Btrfs: avoid ENOSPC errors in btrfs_dirty_inode
Btrfs: move O_DIRECT space reservation to btrfs_direct_IO
Btrfs: rework O_DIRECT enospc handling
Btrfs: use async helpers for DIO write checksumming
Btrfs: don't walk around with task->state != TASK_RUNNING
Btrfs: do aio_write instead of write
Btrfs: add basic DIO read/write support
direct-io: do not merge logically non-contiguous requests
direct-io: add a hook for the fs to provide its own submit_bio function
fs: allow short direct-io reads to be completed via buffered IO
Btrfs: Metadata ENOSPC handling for balance
Btrfs: Pre-allocate space for data relocation
Btrfs: Metadata ENOSPC handling for tree log
Btrfs: Metadata reservation for orphan inodes
Btrfs: Introduce global metadata reservation
...
Example usage of generic "numa_mem_id()":
The mainline slab code, since ~ 2.6.19, does not handle memoryless nodes
well. Specifically, the "fast path"--____cache_alloc()--will never
succeed as slab doesn't cache offnode object on the per cpu queues, and
for memoryless nodes, all memory will be "off node" relative to
numa_node_id(). This adds significant overhead to all kmem cache
allocations, incurring a significant regression relative to earlier
kernels [from before slab.c was reorganized].
This patch uses the generic topology function "numa_mem_id()" to return
the "effective local memory node" for the calling context. This is the
first node in the local node's generic fallback zonelist-- the same node
that "local" mempolicy-based allocations would use. This lets slab cache
these "local" allocations and avoid fallback/refill on every allocation.
N.B.: Slab will need to handle node and memory hotplug events that could
change the value returned by numa_mem_id() for any given node if recent
changes to address memory hotplug don't already address this. E.g., flush
all per cpu slab queues before rebuilding the zonelists while the
"machine" is held in the stopped state.
Performance impact on "hackbench 400 process 200"
2.6.34-rc3-mmotm-100405-1609 no-patch this-patch
ia64 no memoryless nodes [avg of 10]: 11.713 11.637 ~0.65 diff
ia64 cpus all on memless nodes [10]: 228.259 26.484 ~8.6x speedup
The slowdown of the patched kernel from ~12 sec to ~28 seconds when
configured with memoryless nodes is the result of all cpus allocating from
a single node's mm pagepool. The cache lines of the single node are
distributed/interleaved over the memory of the real physical nodes, but
the zone lock, list heads, ... of the single node with memory still each
live in a single cache line that is accessed from all processors.
x86_64 [8x6 AMD] [avg of 40]: 2.883 2.845
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Nick Piggin <npiggin@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Eric Whitney <eric.whitney@hp.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Introduce numa_mem_id(), based on generic percpu variable infrastructure
to track "nearest node with memory" for archs that support memoryless
nodes.
Define API in <linux/topology.h> when CONFIG_HAVE_MEMORYLESS_NODES
defined, else stubs. Architectures will define HAVE_MEMORYLESS_NODES
if/when they support them.
Archs can override definitions of:
numa_mem_id() - returns node number of "local memory" node
set_numa_mem() - initialize [this cpus'] per cpu variable 'numa_mem'
cpu_to_mem() - return numa_mem for specified cpu; may be used as lvalue
Generic initialization of 'numa_mem' occurs in __build_all_zonelists().
This will initialize the boot cpu at boot time, and all cpus on change of
numa_zonelist_order, or when node or memory hot-plug requires zonelist
rebuild. Archs that support memoryless nodes will need to initialize
'numa_mem' for secondary cpus as they're brought on-line.
[akpm@linux-foundation.org: fix build]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Nick Piggin <npiggin@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Eric Whitney <eric.whitney@hp.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Rework the generic version of the numa_node_id() function to use the new
generic percpu variable infrastructure.
Guard the new implementation with a new config option:
CONFIG_USE_PERCPU_NUMA_NODE_ID.
Archs which support this new implemention will default this option to 'y'
when NUMA is configured. This config option could be removed if/when all
archs switch over to the generic percpu implementation of numa_node_id().
Arch support involves:
1) converting any existing per cpu variable implementations to use
this implementation. x86_64 is an instance of such an arch.
2) archs that don't use a per cpu variable for numa_node_id() will
need to initialize the new per cpu variable "numa_node" as cpus
are brought on-line. ia64 is an example.
3) Defining USE_PERCPU_NUMA_NODE_ID in arch dependent Kconfig--e.g.,
when NUMA is configured. This is required because I have
retained the old implementation by default to allow archs to
be modified incrementally, as desired.
Subsequent patches will convert x86_64 and ia64 to use this implemenation.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Nick Piggin <npiggin@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Eric Whitney <eric.whitney@hp.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
By the previous modification, the cpu notifier can return encapsulate
errno value. This converts the cpu notifiers for slab.
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We have observed several workloads running on multi-node systems where
memory is assigned unevenly across the nodes in the system. There are
numerous reasons for this but one is the round-robin rotor in
cpuset_mem_spread_node().
For example, a simple test that writes a multi-page file will allocate
pages on nodes 0 2 4 6 ... Odd nodes are skipped. (Sometimes it
allocates on odd nodes & skips even nodes).
An example is shown below. The program "lfile" writes a file consisting
of 10 pages. The program then mmaps the file & uses get_mempolicy(...,
MPOL_F_NODE) to determine the nodes where the file pages were allocated.
The output is shown below:
# ./lfile
allocated on nodes: 2 4 6 0 1 2 6 0 2
There is a single rotor that is used for allocating both file pages & slab
pages. Writing the file allocates both a data page & a slab page
(buffer_head). This advances the RR rotor 2 nodes for each page
allocated.
A quick confirmation seems to confirm this is the cause of the uneven
allocation:
# echo 0 >/dev/cpuset/memory_spread_slab
# ./lfile
allocated on nodes: 6 7 8 9 0 1 2 3 4 5
This patch introduces a second rotor that is used for slab allocations.
Signed-off-by: Jack Steiner <steiner@sgi.com>
Acked-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Paul Menage <menage@google.com>
Cc: Jack Steiner <steiner@sgi.com>
Cc: Robin Holt <holt@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Introduce struct mem_cgroup_thresholds. It helps to reduce number of
checks of thresholds type (memory or mem+swap).
[akpm@linux-foundation.org: repair comment]
Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Phil Carmody <ext-phil.2.carmody@nokia.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Paul Menage <menage@google.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Since we are unable to handle an error returned by
cftype.unregister_event() properly, let's make the callback
void-returning.
mem_cgroup_unregister_event() has been rewritten to be a "never fail"
function. On mem_cgroup_usage_register_event() we save old buffer for
thresholds array and reuse it in mem_cgroup_usage_unregister_event() to
avoid allocation.
Signed-off-by: Kirill A. Shutemov <kirill@shutemov.name>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Phil Carmody <ext-phil.2.carmody@nokia.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Paul Menage <menage@google.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
FILE_MAPPED per memcg of migrated file cache is not properly updated,
because our hook in page_add_file_rmap() can't know to which memcg
FILE_MAPPED should be counted.
Basically, this patch is for fixing the bug but includes some big changes
to fix up other messes.
Now, at migrating mapped file, events happen in following sequence.
1. allocate a new page.
2. get memcg of an old page.
3. charge ageinst a new page before migration. But at this point,
no changes to new page's page_cgroup, no commit for the charge.
(IOW, PCG_USED bit is not set.)
4. page migration replaces radix-tree, old-page and new-page.
5. page migration remaps the new page if the old page was mapped.
6. Here, the new page is unlocked.
7. memcg commits the charge for newpage, Mark the new page's page_cgroup
as PCG_USED.
Because "commit" happens after page-remap, we can count FILE_MAPPED
at "5", because we should avoid to trust page_cgroup->mem_cgroup.
if PCG_USED bit is unset.
(Note: memcg's LRU removal code does that but LRU-isolation logic is used
for helping it. When we overwrite page_cgroup->mem_cgroup, page_cgroup is
not on LRU or page_cgroup->mem_cgroup is NULL.)
We can lose file_mapped accounting information at 5 because FILE_MAPPED
is updated only when mapcount changes 0->1. So we should catch it.
BTW, historically, above implemntation comes from migration-failure
of anonymous page. Because we charge both of old page and new page
with mapcount=0, we can't catch
- the page is really freed before remap.
- migration fails but it's freed before remap
or .....corner cases.
New migration sequence with memcg is:
1. allocate a new page.
2. mark PageCgroupMigration to the old page.
3. charge against a new page onto the old page's memcg. (here, new page's pc
is marked as PageCgroupUsed.)
4. page migration replaces radix-tree, page table, etc...
5. At remapping, new page's page_cgroup is now makrked as "USED"
We can catch 0->1 event and FILE_MAPPED will be properly updated.
And we can catch SWAPOUT event after unlock this and freeing this
page by unmap() can be caught.
7. Clear PageCgroupMigration of the old page.
So, FILE_MAPPED will be correctly updated.
Then, for what MIGRATION flag is ?
Without it, at migration failure, we may have to charge old page again
because it may be fully unmapped. "charge" means that we have to dive into
memory reclaim or something complated. So, it's better to avoid
charge it again. Before this patch, __commit_charge() was working for
both of the old/new page and fixed up all. But this technique has some
racy condtion around FILE_MAPPED and SWAPOUT etc...
Now, the kernel use MIGRATION flag and don't uncharge old page until
the end of migration.
I hope this change will make memcg's page migration much simpler. This
page migration has caused several troubles. Worth to add a flag for
simplification.
Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Only an out of memory error will cause ret to be set.
Signed-off-by: Phil Carmody <ext-phil.2.carmody@nokia.com>
Acked-by: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The bottom 4 hunks are atomically changing memory to which there are no
aliases as it's freshly allocated, so there's no need to use atomic
operations.
The other hunks are just atomic_read and atomic_set, and do not involve
any read-modify-write. The use of atomic_{read,set} doesn't prevent a
read/write or write/write race, so if a race were possible (I'm not saying
one is), then it would still be there even with atomic_set.
See:
http://digitalvampire.org/blog/index.php/2007/05/13/atomic-cargo-cults/
Signed-off-by: Phil Carmody <ext-phil.2.carmody@nokia.com>
Acked-by: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
It's pointless to try to kill current if select_bad_process() did not find
an eligible task to kill in mem_cgroup_out_of_memory() since it's
guaranteed that current is a member of the memcg that is oom and it is, by
definition, unkillable.
Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch adds support for moving charge of file pages, which include
normal file, tmpfs file and swaps of tmpfs file. It's enabled by setting
bit 1 of <target cgroup>/memory.move_charge_at_immigrate.
Unlike the case of anonymous pages, file pages(and swaps) in the range
mmapped by the task will be moved even if the task hasn't done page fault,
i.e. they might not be the task's "RSS", but other task's "RSS" that maps
the same file. And mapcount of the page is ignored(the page can be moved
even if page_mapcount(page) > 1). So, conditions that the page/swap
should be met to be moved is that it must be in the range mmapped by the
target task and it must be charged to the old cgroup.
[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: fix warning]
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch cleans up move charge code by:
- define functions to handle pte for each types, and make
is_target_pte_for_mc() cleaner.
- instead of checking the MOVE_CHARGE_TYPE_ANON bit, define a function
that checks the bit.
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This adds a feature to disable oom-killer for memcg, if disabled, of
course, tasks under memcg will stop.
But now, we have oom-notifier for memcg. And the world around memcg is
not under out-of-memory. memcg's out-of-memory just shows memcg hits
limit. Then, administrator or management daemon can recover the situation
by
- kill some process
- enlarge limit, add more swap.
- migrate some tasks
- remove file cache on tmps (difficult ?)
Unlike oom-killer, you can take enough information before killing tasks.
(by gcore, or, ps etc.)
[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Considering containers or other resource management softwares in userland,
event notification of OOM in memcg should be implemented. Now, memcg has
"threshold" notifier which uses eventfd, we can make use of it for oom
notification.
This patch adds oom notification eventfd callback for memcg. The usage is
very similar to threshold notifier, but control file is memory.oom_control
and no arguments other than eventfd is required.
% cgroup_event_notifier /cgroup/A/memory.oom_control dummy
(About cgroup_event_notifier, see Documentation/cgroup/)
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: David Rientjes <rientjes@google.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
memcg's oom waitqueue is a system-wide wait_queue (for handling
hierarchy.) So, it's better to add custom wake function and do filtering
in wake up path.
This patch adds a filtering feature for waking up oom-waiters. Hierarchy
is properly handled.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
I/O errors can happen due to temporary failures, like multipath
errors or losing network contact with the iSCSI server. Because
of that, the VM will retry readpage on the page.
However, do_generic_file_read does not clear PG_error. This
causes the system to be unable to actually use the data in the
page cache page, even if the subsequent readpage completes
successfully!
The function filemap_fault has had a ClearPageError before
readpage forever. This patch simply adds the same to
do_generic_file_read.
Signed-off-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Larry Woodman <lwoodman@redhat.com>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Slightly rearrange the logic that determines capabilities and vm_flags.
Disable BDI_CAP_MAP_DIRECT in all cases if the device can't support the
protections. Allow private readonly mappings of readonly backing devices.
Signed-off-by: Bernd Schmidt <bernds_cb1@t-online.de>
Signed-off-by: Mike Frysinger <vapier@gentoo.org>
Acked-by: David McCullough <davidm@snapgear.com>
Acked-by: Greg Ungerer <gerg@uclinux.org>
Acked-by: Paul Mundt <lethal@linux-sh.org>
Acked-by: David Howells <dhowells@redhat.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>
The original code called mpol_put(new) while "new" was an ERR_PTR.
Signed-off-by: Dan Carpenter <error27@gmail.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add global mutex zonelists_mutex to fix the possible race:
CPU0 CPU1 CPU2
(1) zone->present_pages += online_pages;
(2) build_all_zonelists();
(3) alloc_page();
(4) free_page();
(5) build_all_zonelists();
(6) __build_all_zonelists();
(7) zone->pageset = alloc_percpu();
In step (3,4), zone->pageset still points to boot_pageset, so bad
things may happen if 2+ nodes are in this state. Even if only 1 node
is accessing the boot_pageset, (3) may still consume too much memory
to fail the memory allocations in step (7).
Besides, atomic operation ensures alloc_percpu() in step (7) will never fail
since there is a new fresh memory block added in step(6).
[haicheng.li@linux.intel.com: hold zonelists_mutex when build_all_zonelists]
Signed-off-by: Haicheng Li <haicheng.li@linux.intel.com>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Reviewed-by: Andi Kleen <andi.kleen@intel.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
For each new populated zone of hotadded node, need to update its pagesets
with dynamically allocated per_cpu_pageset struct for all possible CPUs:
1) Detach zone->pageset from the shared boot_pageset
at end of __build_all_zonelists().
2) Use mutex to protect zone->pageset when it's still
shared in onlined_pages()
Otherwises, multiple zones of different nodes would share same boot strapping
boot_pageset for same CPU, which will finally cause below kernel panic:
------------[ cut here ]------------
kernel BUG at mm/page_alloc.c:1239!
invalid opcode: 0000 [#1] SMP
...
Call Trace:
[<ffffffff811300c1>] __alloc_pages_nodemask+0x131/0x7b0
[<ffffffff81162e67>] alloc_pages_current+0x87/0xd0
[<ffffffff81128407>] __page_cache_alloc+0x67/0x70
[<ffffffff811325f0>] __do_page_cache_readahead+0x120/0x260
[<ffffffff81132751>] ra_submit+0x21/0x30
[<ffffffff811329c6>] ondemand_readahead+0x166/0x2c0
[<ffffffff81132ba0>] page_cache_async_readahead+0x80/0xa0
[<ffffffff8112a0e4>] generic_file_aio_read+0x364/0x670
[<ffffffff81266cfa>] nfs_file_read+0xca/0x130
[<ffffffff8117b20a>] do_sync_read+0xfa/0x140
[<ffffffff8117bf75>] vfs_read+0xb5/0x1a0
[<ffffffff8117c151>] sys_read+0x51/0x80
[<ffffffff8103c032>] system_call_fastpath+0x16/0x1b
RIP [<ffffffff8112ff13>] get_page_from_freelist+0x883/0x900
RSP <ffff88000d1e78a8>
---[ end trace 4bda28328b9990db ]
[akpm@linux-foundation.org: merge fix]
Signed-off-by: Haicheng Li <haicheng.li@linux.intel.com>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Reviewed-by: Andi Kleen <andi.kleen@intel.com>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
No behavior change here.
Move some of setup_per_cpu_pageset() code into a new function
setup_zone_pageset() that will be useful for memory hotplug.
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Haicheng Li <haicheng.li@linux.intel.com>
Reviewed-by: Andi Kleen <andi.kleen@intel.com>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In f4112de6b6 ("mm: introduce
debug_kmap_atomic") I said that debug_kmap_atomic() needs
CONFIG_TRACE_IRQFLAGS_SUPPORT.
It was wrong. (I thought irqs_disabled() is only available when the
architecture has CONFIG_TRACE_IRQFLAGS_SUPPORT)
Remove the #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT check to enable
kmap_atomic() debugging for the architectures which do not have
CONFIG_TRACE_IRQFLAGS_SUPPORT.
Reported-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Enable users to online CPUs even if the CPUs belongs to a numa node which
doesn't have onlined local memory.
The zonlists(pg_data_t.node_zonelists[]) of a numa node are created either
in system boot/init period, or at the time of local memory online. For a
numa node without onlined local memory, its zonelists are not initialized
at present. As a result, any memory allocation operations executed by
CPUs within this node will fail. In fact, an out-of-memory error is
triggered when attempt to online CPUs before memory comes to online.
This patch tries to create zonelists for such numa nodes, so that the
memory allocation for this node can be fallback'ed to other nodes.
[akpm@linux-foundation.org: remove unneeded export]
[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: minskey guo<chaohong.guo@intel.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
For now, we have global isolation vs. memory control group isolation, do
not allow the reclaim entry function to set an arbitrary page isolation
callback, we do not need that flexibility.
And since we already pass around the group descriptor for the memory
control group isolation case, just use it to decide which one of the two
isolator functions to use.
The decisions can be merged into nearby branches, so no extra cost there.
In fact, we save the indirect calls.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This scan control is abused to communicate a return value from
shrink_zones(). Write this idiomatically and remove the knob.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
If vmscan is under lumpy reclaim mode, it have to ignore referenced bit
for making contenious free pages. but current page_check_references()
doesn't.
Fix it.
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
get_scan_ratio() calculates percentage and if the percentage is < 1%, it
will round percentage down to 0% and cause we completely ignore scanning
anon/file pages to reclaim memory even the total anon/file pages are very
big.
To avoid underflow, we don't use percentage, instead we directly calculate
how many pages should be scaned. In this way, we should get several
scanned pages for < 1% percent.
This has some benefits:
1. increase our calculation precision
2. making our scan more smoothly. Without this, if percent[x] is
underflow, shrink_zone() doesn't scan any pages and suddenly it scans
all pages when priority is zero. With this, even priority isn't zero,
shrink_zone() gets chance to scan some pages.
Note, this patch doesn't really change logics, but just increase
precision. For system with a lot of memory, this might slightly changes
behavior. For example, in a sequential file read workload, without the
patch, we don't swap any anon pages. With it, if anon memory size is
bigger than 16G, we will see one anon page swapped. The 16G is calculated
as PAGE_SIZE * priority(4096) * (fp/ap). fp/ap is assumed to be 1024
which is common in this workload. So the impact sounds not a big deal.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Rik van Riel <riel@redhat.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>
Use mm->task_size instead of TASK_SIZE to ensure that the entire user
address space is migrated. mm->task_size is independent of the calling
task context. TASK SIZE may be dependant on the address space size of the
calling process. Usage of TASK_SIZE can lead to partial address space
migration if the calling process was 32 bit and the migrating process was
64 bit.
Here is the test script used on 64 system with a 32 bit echo process:
mount -t cgroup none /cgroup -o cpuset
cd /cgroup
mkdir 0
echo 1 > 0/cpuset.cpus
echo 0 > 0/cpuset.mems
echo 1 > 0/cpuset.memory_migrate
mkdir 1
echo 1 > 1/cpuset.cpus
echo 1 > 1/cpuset.mems
echo 1 > 1/cpuset.memory_migrate
echo $$ > 0/tasks
64_bit_process &
pid=$!
echo $pid > 1/tasks # This does not migrate all process pages without
# this patch. If 64 bit echo is used or this patch is
# applied, then the full address space of $pid is
# migrated.
To check memory migration, I watched:
grep MemUsed /sys/devices/system/node/node*/meminfo
Signed-off-by: Greg Thelen <gthelen@google.com>
Acked-by: Christoph Lameter <cl@linux-foundation.org>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The fragmentation index may indicate that a failure is due to external
fragmentation but after a compaction run completes, it is still possible
for an allocation to fail. There are two obvious reasons as to why
o Page migration cannot move all pages so fragmentation remains
o A suitable page may exist but watermarks are not met
In the event of compaction followed by an allocation failure, this patch
defers further compaction in the zone (1 << compact_defer_shift) times.
If the next compaction attempt also fails, compact_defer_shift is
increased up to a maximum of 6. If compaction succeeds, the defer
counters are reset again.
The zone that is deferred is the first zone in the zonelist - i.e. the
preferred zone. To defer compaction in the other zones, the information
would need to be stored in the zonelist or implemented similar to the
zonelist_cache. This would impact the fast-paths and is not justified at
this time.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The kernel applies some heuristics when deciding if memory should be
compacted or reclaimed to satisfy a high-order allocation. One of these
is based on the fragmentation. If the index is below 500, memory will not
be compacted. This choice is arbitrary and not based on data. To help
optimise the system and set a sensible default for this value, this patch
adds a sysctl extfrag_threshold. The kernel will only compact memory if
the fragmentation index is above the extfrag_threshold.
[randy.dunlap@oracle.com: Fix build errors when proc fs is not configured]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Ordinarily when a high-order allocation fails, direct reclaim is entered
to free pages to satisfy the allocation. With this patch, it is
determined if an allocation failed due to external fragmentation instead
of low memory and if so, the calling process will compact until a suitable
page is freed. Compaction by moving pages in memory is considerably
cheaper than paging out to disk and works where there are locked pages or
no swap. If compaction fails to free a page of a suitable size, then
reclaim will still occur.
Direct compaction returns as soon as possible. As each block is
compacted, it is checked if a suitable page has been freed and if so, it
returns.
[akpm@linux-foundation.org: Fix build errors]
[aarcange@redhat.com: fix count_vm_event preempt in memory compaction direct reclaim]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add a per-node sysfs file called compact. When the file is written to,
each zone in that node is compacted. The intention that this would be
used by something like a job scheduler in a batch system before a job
starts so that the job can allocate the maximum number of hugepages
without significant start-up cost.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add a proc file /proc/sys/vm/compact_memory. When an arbitrary value is
written to the file, all zones are compacted. The expected user of such a
trigger is a job scheduler that prepares the system before the target
application runs.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch is the core of a mechanism which compacts memory in a zone by
relocating movable pages towards the end of the zone.
A single compaction run involves a migration scanner and a free scanner.
Both scanners operate on pageblock-sized areas in the zone. The migration
scanner starts at the bottom of the zone and searches for all movable
pages within each area, isolating them onto a private list called
migratelist. The free scanner starts at the top of the zone and searches
for suitable areas and consumes the free pages within making them
available for the migration scanner. The pages isolated for migration are
then migrated to the newly isolated free pages.
[aarcange@redhat.com: Fix unsafe optimisation]
[mel@csn.ul.ie: do not schedule work on other CPUs for compaction]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The fragmentation fragmentation index, is only meaningful if an allocation
would fail and indicates what the failure is due to. A value of -1 such
as in many of the examples above states that the allocation would succeed.
If it would fail, the value is between 0 and 1. A value tending towards
0 implies the allocation failed due to a lack of memory. A value tending
towards 1 implies it failed due to external fragmentation.
For the most part, the huge page size will be the size of interest but not
necessarily so it is exported on a per-order and per-zo basis via
/sys/kernel/debug/extfrag/extfrag_index
> cat /sys/kernel/debug/extfrag/extfrag_index
Node 0, zone DMA -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.00
Node 0, zone Normal -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 0.954
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The unusable free space index measures how much of the available free
memory cannot be used to satisfy an allocation of a given size and is a
value between 0 and 1. The higher the value, the more of free memory is
unusable and by implication, the worse the external fragmentation is. For
the most part, the huge page size will be the size of interest but not
necessarily so it is exported on a per-order and per-zone basis via
/sys/kernel/debug/extfrag/unusable_index.
> cat /sys/kernel/debug/extfrag/unusable_index
Node 0, zone DMA 0.000 0.000 0.000 0.001 0.005 0.013 0.021 0.037 0.037 0.101 0.230
Node 0, zone Normal 0.000 0.000 0.000 0.001 0.002 0.002 0.005 0.015 0.028 0.028 0.054
[akpm@linux-foundation.org: Fix allnoconfig]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Page migration requires rmap to be able to find all ptes mapping a page
at all times, otherwise the migration entry can be instantiated, but it
is possible to leave one behind if the second rmap_walk fails to find
the page. If this page is later faulted, migration_entry_to_page() will
call BUG because the page is locked indicating the page was migrated by
the migration PTE not cleaned up. For example
kernel BUG at include/linux/swapops.h:105!
invalid opcode: 0000 [#1] PREEMPT SMP
...
Call Trace:
[<ffffffff810e951a>] handle_mm_fault+0x3f8/0x76a
[<ffffffff8130c7a2>] do_page_fault+0x44a/0x46e
[<ffffffff813099b5>] page_fault+0x25/0x30
[<ffffffff8114de33>] load_elf_binary+0x152a/0x192b
[<ffffffff8111329b>] search_binary_handler+0x173/0x313
[<ffffffff81114896>] do_execve+0x219/0x30a
[<ffffffff8100a5c6>] sys_execve+0x43/0x5e
[<ffffffff8100320a>] stub_execve+0x6a/0xc0
RIP [<ffffffff811094ff>] migration_entry_wait+0xc1/0x129
There is a race between shift_arg_pages and migration that triggers this
bug. A temporary stack is setup during exec and later moved. If
migration moves a page in the temporary stack and the VMA is then removed
before migration completes, the migration PTE may not be found leading to
a BUG when the stack is faulted.
This patch causes pages within the temporary stack during exec to be
skipped by migration. It does this by marking the VMA covering the
temporary stack with an otherwise impossible combination of VMA flags.
These flags are cleared when the temporary stack is moved to its final
location.
[kamezawa.hiroyu@jp.fujitsu.com: idea for having migration skip temporary stacks]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
CONFIG_MIGRATION currently depends on CONFIG_NUMA or on the architecture
being able to hot-remove memory. The main users of page migration such as
sys_move_pages(), sys_migrate_pages() and cpuset process migration are
only beneficial on NUMA so it makes sense.
As memory compaction will operate within a zone and is useful on both NUMA
and non-NUMA systems, this patch allows CONFIG_MIGRATION to be set if the
user selects CONFIG_COMPACTION as an option.
[akpm@linux-foundation.org: Depend on CONFIG_HUGETLB_PAGE]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
PageAnon pages that are unmapped may or may not have an anon_vma so are
not currently migrated. However, a swap cache page can be migrated and
fits this description. This patch identifies page swap caches and allows
them to be migrated but ensures that no attempt to made to remap the pages
would would potentially try to access an already freed anon_vma.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
rmap_walk_anon() was triggering errors in memory compaction that look like
use-after-free errors. The problem is that between the page being
isolated from the LRU and rcu_read_lock() being taken, the mapcount of the
page dropped to 0 and the anon_vma gets freed. This can happen during
memory compaction if pages being migrated belong to a process that exits
before migration completes. Hence, the use-after-free race looks like
1. Page isolated for migration
2. Process exits
3. page_mapcount(page) drops to zero so anon_vma was no longer reliable
4. unmap_and_move() takes the rcu_lock but the anon_vma is already garbage
4. call try_to_unmap, looks up tha anon_vma and "locks" it but the lock
is garbage.
This patch checks the mapcount after the rcu lock is taken. If the
mapcount is zero, the anon_vma is assumed to be freed and no further
action is taken.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
For clarity of review, KSM and page migration have separate refcounts on
the anon_vma. While clear, this is a waste of memory. This patch gets
KSM and page migration to share their toys in a spirit of harmony.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patchset is a memory compaction mechanism that reduces external
fragmentation memory by moving GFP_MOVABLE pages to a fewer number of
pageblocks. The term "compaction" was chosen as there are is a number of
mechanisms that are not mutually exclusive that can be used to defragment
memory. For example, lumpy reclaim is a form of defragmentation as was
slub "defragmentation" (really a form of targeted reclaim). Hence, this
is called "compaction" to distinguish it from other forms of
defragmentation.
In this implementation, a full compaction run involves two scanners
operating within a zone - a migration and a free scanner. The migration
scanner starts at the beginning of a zone and finds all movable pages
within one pageblock_nr_pages-sized area and isolates them on a
migratepages list. The free scanner begins at the end of the zone and
searches on a per-area basis for enough free pages to migrate all the
pages on the migratepages list. As each area is respectively migrated or
exhausted of free pages, the scanners are advanced one area. A compaction
run completes within a zone when the two scanners meet.
This method is a bit primitive but is easy to understand and greater
sophistication would require maintenance of counters on a per-pageblock
basis. This would have a big impact on allocator fast-paths to improve
compaction which is a poor trade-off.
It also does not try relocate virtually contiguous pages to be physically
contiguous. However, assuming transparent hugepages were in use, a
hypothetical khugepaged might reuse compaction code to isolate free pages,
split them and relocate userspace pages for promotion.
Memory compaction can be triggered in one of three ways. It may be
triggered explicitly by writing any value to /proc/sys/vm/compact_memory
and compacting all of memory. It can be triggered on a per-node basis by
writing any value to /sys/devices/system/node/nodeN/compact where N is the
node ID to be compacted. When a process fails to allocate a high-order
page, it may compact memory in an attempt to satisfy the allocation
instead of entering direct reclaim. Explicit compaction does not finish
until the two scanners meet and direct compaction ends if a suitable page
becomes available that would meet watermarks.
The series is in 14 patches. The first three are not "core" to the series
but are important pre-requisites.
Patch 1 reference counts anon_vma for rmap_walk_anon(). Without this
patch, it's possible to use anon_vma after free if the caller is
not holding a VMA or mmap_sem for the pages in question. While
there should be no existing user that causes this problem,
it's a requirement for memory compaction to be stable. The patch
is at the start of the series for bisection reasons.
Patch 2 merges the KSM and migrate counts. It could be merged with patch 1
but would be slightly harder to review.
Patch 3 skips over unmapped anon pages during migration as there are no
guarantees about the anon_vma existing. There is a window between
when a page was isolated and migration started during which anon_vma
could disappear.
Patch 4 notes that PageSwapCache pages can still be migrated even if they
are unmapped.
Patch 5 allows CONFIG_MIGRATION to be set without CONFIG_NUMA
Patch 6 exports a "unusable free space index" via debugfs. It's
a measure of external fragmentation that takes the size of the
allocation request into account. It can also be calculated from
userspace so can be dropped if requested
Patch 7 exports a "fragmentation index" which only has meaning when an
allocation request fails. It determines if an allocation failure
would be due to a lack of memory or external fragmentation.
Patch 8 moves the definition for LRU isolation modes for use by compaction
Patch 9 is the compaction mechanism although it's unreachable at this point
Patch 10 adds a means of compacting all of memory with a proc trgger
Patch 11 adds a means of compacting a specific node with a sysfs trigger
Patch 12 adds "direct compaction" before "direct reclaim" if it is
determined there is a good chance of success.
Patch 13 adds a sysctl that allows tuning of the threshold at which the
kernel will compact or direct reclaim
Patch 14 temporarily disables compaction if an allocation failure occurs
after compaction.
Testing of compaction was in three stages. For the test, debugging,
preempt, the sleep watchdog and lockdep were all enabled but nothing nasty
popped out. min_free_kbytes was tuned as recommended by hugeadm to help
fragmentation avoidance and high-order allocations. It was tested on X86,
X86-64 and PPC64.
Ths first test represents one of the easiest cases that can be faced for
lumpy reclaim or memory compaction.
1. Machine freshly booted and configured for hugepage usage with
a) hugeadm --create-global-mounts
b) hugeadm --pool-pages-max DEFAULT:8G
c) hugeadm --set-recommended-min_free_kbytes
d) hugeadm --set-recommended-shmmax
The min_free_kbytes here is important. Anti-fragmentation works best
when pageblocks don't mix. hugeadm knows how to calculate a value that
will significantly reduce the worst of external-fragmentation-related
events as reported by the mm_page_alloc_extfrag tracepoint.
2. Load up memory
a) Start updatedb
b) Create in parallel a X files of pagesize*128 in size. Wait
until files are created. By parallel, I mean that 4096 instances
of dd were launched, one after the other using &. The crude
objective being to mix filesystem metadata allocations with
the buffer cache.
c) Delete every second file so that pageblocks are likely to
have holes
d) kill updatedb if it's still running
At this point, the system is quiet, memory is full but it's full with
clean filesystem metadata and clean buffer cache that is unmapped.
This is readily migrated or discarded so you'd expect lumpy reclaim
to have no significant advantage over compaction but this is at
the POC stage.
3. In increments, attempt to allocate 5% of memory as hugepages.
Measure how long it took, how successful it was, how many
direct reclaims took place and how how many compactions. Note
the compaction figures might not fully add up as compactions
can take place for orders other than the hugepage size
X86 vanilla compaction
Final page count 913 916 (attempted 1002)
pages reclaimed 68296 9791
X86-64 vanilla compaction
Final page count: 901 902 (attempted 1002)
Total pages reclaimed: 112599 53234
PPC64 vanilla compaction
Final page count: 93 94 (attempted 110)
Total pages reclaimed: 103216 61838
There was not a dramatic improvement in success rates but it wouldn't be
expected in this case either. What was important is that fewer pages were
reclaimed in all cases reducing the amount of IO required to satisfy a
huge page allocation.
The second tests were all performance related - kernbench, netperf, iozone
and sysbench. None showed anything too remarkable.
The last test was a high-order allocation stress test. Many kernel
compiles are started to fill memory with a pressured mix of unmovable and
movable allocations. During this, an attempt is made to allocate 90% of
memory as huge pages - one at a time with small delays between attempts to
avoid flooding the IO queue.
vanilla compaction
Percentage of request allocated X86 98 99
Percentage of request allocated X86-64 95 98
Percentage of request allocated PPC64 55 70
This patch:
rmap_walk_anon() does not use page_lock_anon_vma() for looking up and
locking an anon_vma and it does not appear to have sufficient locking to
ensure the anon_vma does not disappear from under it.
This patch copies an approach used by KSM to take a reference on the
anon_vma while pages are being migrated. This should prevent rmap_walk()
running into nasty surprises later because anon_vma has been freed.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
There are two types of zonelist ordering methodologies:
- node order, preferring allocations on a node to stay local to and
- zone order, preferring allocations come from a higher zone to avoid
allocating in lowmem zones even though they may not be local.
The ordering technique used by the kernel is configurable on the command
line, but also has some logic to determine what the default should be.
This logic currently lacks knowledge of systems where a node may only have
lowmem. For such systems, it is necessary to use node order so that
GFP_KERNEL allocations may be satisfied by nodes consisting of only
lowmem.
If zone order is used, GFP_KERNEL allocations to such nodes are actually
allocated on a node with local affinity that includes ZONE_NORMAL.
This change defaults to node zonelist ordering if any node lacks
ZONE_NORMAL.
To force zone order, append 'numa_zonelist_order=zone' to the kernel
command line.
Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Do page table walks with the well-known nested loops we use in several
other places already.
This avoids doing full page table walks after every pte range and also
allows to handle unmapped areas bigger than one pte range in one go.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Instead of passing a start address and a number of pages into the helper
functions, convert them to use a start and an end address.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Split out functions to handle hugetlb ranges, pte ranges and unmapped
ranges, to improve readability but also to prepare the file structure for
nested page table walks.
No semantic changes intended.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This fixes some minor issues that bugged me while going over the code:
o adjust argument order of do_mincore() to match the syscall
o simplify range length calculation
o drop superfluous shift in huge tlb calculation, address is page aligned
o drop dead nr_huge calculation
o check pte_none() before pte_present()
o comment and whitespace fixes
No semantic changes intended.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Before applying this patch, cpuset updates task->mems_allowed and
mempolicy by setting all new bits in the nodemask first, and clearing all
old unallowed bits later. But in the way, the allocator may find that
there is no node to alloc memory.
The reason is that cpuset rebinds the task's mempolicy, it cleans the
nodes which the allocater can alloc pages on, for example:
(mpol: mempolicy)
task1 task1's mpol task2
alloc page 1
alloc on node0? NO 1
1 change mems from 1 to 0
1 rebind task1's mpol
0-1 set new bits
0 clear disallowed bits
alloc on node1? NO 0
...
can't alloc page
goto oom
This patch fixes this problem by expanding the nodes range first(set newly
allowed bits) and shrink it lazily(clear newly disallowed bits). So we
use a variable to tell the write-side task that read-side task is reading
nodemask, and the write-side task clears newly disallowed nodes after
read-side task ends the current memory allocation.
[akpm@linux-foundation.org: fix spello]
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Paul Menage <menage@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Ravikiran Thirumalai <kiran@scalex86.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Nick Piggin reported that the allocator may see an empty nodemask when
changing cpuset's mems[1]. It happens only on the kernel that do not do
atomic nodemask_t stores. (MAX_NUMNODES > BITS_PER_LONG)
But I found that there is also a problem on the kernel that can do atomic
nodemask_t stores. The problem is that the allocator can't find a node to
alloc page when changing cpuset's mems though there is a lot of free
memory. The reason is like this:
(mpol: mempolicy)
task1 task1's mpol task2
alloc page 1
alloc on node0? NO 1
1 change mems from 1 to 0
1 rebind task1's mpol
0-1 set new bits
0 clear disallowed bits
alloc on node1? NO 0
...
can't alloc page
goto oom
I can use the attached program reproduce it by the following step:
# mkdir /dev/cpuset
# mount -t cpuset cpuset /dev/cpuset
# mkdir /dev/cpuset/1
# echo `cat /dev/cpuset/cpus` > /dev/cpuset/1/cpus
# echo `cat /dev/cpuset/mems` > /dev/cpuset/1/mems
# echo $$ > /dev/cpuset/1/tasks
# numactl --membind=`cat /dev/cpuset/mems` ./cpuset_mem_hog <nr_tasks> &
<nr_tasks> = max(nr_cpus - 1, 1)
# killall -s SIGUSR1 cpuset_mem_hog
# ./change_mems.sh
several hours later, oom will happen though there is a lot of free memory.
This patchset fixes this problem by expanding the nodes range first(set
newly allowed bits) and shrink it lazily(clear newly disallowed bits). So
we use a variable to tell the write-side task that read-side task is
reading nodemask, and the write-side task clears newly disallowed nodes
after read-side task ends the current memory allocation.
This patch:
In order to fix no node to alloc memory, when we want to update mempolicy
and mems_allowed, we expand the set of nodes first (set all the newly
nodes) and shrink the set of nodes lazily(clean disallowed nodes), But the
mempolicy's rebind functions may breaks the expanding.
So we restructure the mempolicy's rebind functions and split the rebind
work to two steps, just like the update of cpuset's mems: The 1st step:
expand the set of the mempolicy's nodes. The 2nd step: shrink the set of
the mempolicy's nodes. It is used when there is no real lock to protect
the mempolicy in the read-side. Otherwise we can do rebind work at once.
In order to implement it, we define
enum mpol_rebind_step {
MPOL_REBIND_ONCE,
MPOL_REBIND_STEP1,
MPOL_REBIND_STEP2,
MPOL_REBIND_NSTEP,
};
If the mempolicy needn't be updated by two steps, we can pass
MPOL_REBIND_ONCE to the rebind functions. Or we can pass
MPOL_REBIND_STEP1 to do the first step of the rebind work and pass
MPOL_REBIND_STEP2 to do the second step work.
Besides that, it maybe long time between these two step and we have to
release the lock that protects mempolicy and mems_allowed. If we hold the
lock once again, we must check whether the current mempolicy is under the
rebinding (the first step has been done) or not, because the task may
alloc a new mempolicy when we don't hold the lock. So we defined the
following flag to identify it:
#define MPOL_F_REBINDING (1 << 2)
The new functions will be used in the next patch.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Paul Menage <menage@google.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Ravikiran Thirumalai <kiran@scalex86.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Factor out duplicate put/frees in mpol_shared_policy_init() to a common
return path.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Ravikiran Thirumalai <kiran@scalex86.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Rename 'policy_types[]' to 'policy_modes[]' to better match the array
contents.
Use designated intializer syntax for policy_modes[].
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Ravikiran Thirumalai <kiran@scalex86.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We don't really need the extra variable 'i' in mpol_parse_str(). The only
use is as the the loop variable. Then, it's assigned to 'mode'. Just use
mode, and loose the 'uninitialized_var()' macro.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Ravikiran Thirumalai <kiran@scalex86.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
No need to call mpol_set_nodemask() when we have no context for the
mempolicy. This can occur when we're parsing a tmpfs 'mpol' mount option.
Just save the raw nodemask in the mempolicy's w.user_nodemask member for
use when a tmpfs/shmem file is created. mpol_shared_policy_init() will
"contextualize" the policy for the new file based on the creating task's
context.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Ravikiran Thirumalai <kiran@scalex86.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Lee's patch "mempolicy: use MPOL_PREFERRED for system-wide default policy"
has made the MPOL_DEFAULT only used in the memory policy APIs. So, no
need to check in __mpol_equal also. Also get rid of mpol_match_intent()
and move its logic directly into __mpol_equal().
Signed-off-by: Bob Liu <lliubbo@gmail.com>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In policy_zonelist() mode MPOL_INTERLEAVE shouldn't happen, so fall
through to BUG() instead of break to return. I also fixed the comment.
Signed-off-by: Bob Liu <lliubbo@gmail.com>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1. In funtion is_valid_nodemask(), varibable k will be inited to 0 in
the following loop, needn't init to policy_zone anymore.
2. (MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES) has already defined
to MPOL_MODE_FLAGS in mempolicy.h.
Signed-off-by: Bob Liu <lliubbo@gmail.com>
Acked-by: David Rientjes <rientjes@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
putback_lru_page() never can fail. So it doesn't matter count of "the
number of pages put back".
In addition, users of this functions don't use return value.
Let's remove unnecessary code.
Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
prep_new_page() will call set_page_private(page, 0) to initialise the
page, so the code is redundant.
Signed-off-by: Huang Shijie <shijie8@gmail.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Acked-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In order to reduce fragmentation, this patch classifies freed pages in two
groups according to their probability of being part of a high order merge.
Pages belonging to a compound whose next-highest buddy is free are more
likely to be part of a high order merge in the near future, so they will
be added at the tail of the freelist. The remaining pages are put at the
front of the freelist.
In this way, the pages that are more likely to cause a big merge are kept
free longer. Consequently there is a tendency to aggregate the
long-living allocations on a subset of the compounds, reducing the
fragmentation.
This heuristic was tested on three machines, x86, x86-64 and ppc64 with
3GB of RAM in each machine. The tests were kernbench, netperf, sysbench
and STREAM for performance and a high-order stress test for huge page
allocations.
KernBench X86
Elapsed mean 374.77 ( 0.00%) 375.10 (-0.09%)
User mean 649.53 ( 0.00%) 650.44 (-0.14%)
System mean 54.75 ( 0.00%) 54.18 ( 1.05%)
CPU mean 187.75 ( 0.00%) 187.25 ( 0.27%)
KernBench X86-64
Elapsed mean 94.45 ( 0.00%) 94.01 ( 0.47%)
User mean 323.27 ( 0.00%) 322.66 ( 0.19%)
System mean 36.71 ( 0.00%) 36.50 ( 0.57%)
CPU mean 380.75 ( 0.00%) 381.75 (-0.26%)
KernBench PPC64
Elapsed mean 173.45 ( 0.00%) 173.74 (-0.17%)
User mean 587.99 ( 0.00%) 587.95 ( 0.01%)
System mean 60.60 ( 0.00%) 60.57 ( 0.05%)
CPU mean 373.50 ( 0.00%) 372.75 ( 0.20%)
Nothing notable for kernbench.
NetPerf UDP X86
64 42.68 ( 0.00%) 42.77 ( 0.21%)
128 85.62 ( 0.00%) 85.32 (-0.35%)
256 170.01 ( 0.00%) 168.76 (-0.74%)
1024 655.68 ( 0.00%) 652.33 (-0.51%)
2048 1262.39 ( 0.00%) 1248.61 (-1.10%)
3312 1958.41 ( 0.00%) 1944.61 (-0.71%)
4096 2345.63 ( 0.00%) 2318.83 (-1.16%)
8192 4132.90 ( 0.00%) 4089.50 (-1.06%)
16384 6770.88 ( 0.00%) 6642.05 (-1.94%)*
NetPerf UDP X86-64
64 148.82 ( 0.00%) 154.92 ( 3.94%)
128 298.96 ( 0.00%) 312.95 ( 4.47%)
256 583.67 ( 0.00%) 626.39 ( 6.82%)
1024 2293.18 ( 0.00%) 2371.10 ( 3.29%)
2048 4274.16 ( 0.00%) 4396.83 ( 2.79%)
3312 6356.94 ( 0.00%) 6571.35 ( 3.26%)
4096 7422.68 ( 0.00%) 7635.42 ( 2.79%)*
8192 12114.81 ( 0.00%)* 12346.88 ( 1.88%)
16384 17022.28 ( 0.00%)* 17033.19 ( 0.06%)*
1.64% 2.73%
NetPerf UDP PPC64
64 49.98 ( 0.00%) 50.25 ( 0.54%)
128 98.66 ( 0.00%) 100.95 ( 2.27%)
256 197.33 ( 0.00%) 191.03 (-3.30%)
1024 761.98 ( 0.00%) 785.07 ( 2.94%)
2048 1493.50 ( 0.00%) 1510.85 ( 1.15%)
3312 2303.95 ( 0.00%) 2271.72 (-1.42%)
4096 2774.56 ( 0.00%) 2773.06 (-0.05%)
8192 4918.31 ( 0.00%) 4793.59 (-2.60%)
16384 7497.98 ( 0.00%) 7749.52 ( 3.25%)
The tests are run to have confidence limits within 1%. Results marked
with a * were not confident although in this case, it's only outside by
small amounts. Even with some results that were not confident, the
netperf UDP results were generally positive.
NetPerf TCP X86
64 652.25 ( 0.00%)* 648.12 (-0.64%)*
23.80% 22.82%
128 1229.98 ( 0.00%)* 1220.56 (-0.77%)*
21.03% 18.90%
256 2105.88 ( 0.00%) 1872.03 (-12.49%)*
1.00% 16.46%
1024 3476.46 ( 0.00%)* 3548.28 ( 2.02%)*
13.37% 11.39%
2048 4023.44 ( 0.00%)* 4231.45 ( 4.92%)*
9.76% 12.48%
3312 4348.88 ( 0.00%)* 4396.96 ( 1.09%)*
6.49% 8.75%
4096 4726.56 ( 0.00%)* 4877.71 ( 3.10%)*
9.85% 8.50%
8192 4732.28 ( 0.00%)* 5777.77 (18.10%)*
9.13% 13.04%
16384 5543.05 ( 0.00%)* 5906.24 ( 6.15%)*
7.73% 8.68%
NETPERF TCP X86-64
netperf-tcp-vanilla-netperf netperf-tcp
tcp-vanilla pgalloc-delay
64 1895.87 ( 0.00%)* 1775.07 (-6.81%)*
5.79% 4.78%
128 3571.03 ( 0.00%)* 3342.20 (-6.85%)*
3.68% 6.06%
256 5097.21 ( 0.00%)* 4859.43 (-4.89%)*
3.02% 2.10%
1024 8919.10 ( 0.00%)* 8892.49 (-0.30%)*
5.89% 6.55%
2048 10255.46 ( 0.00%)* 10449.39 ( 1.86%)*
7.08% 7.44%
3312 10839.90 ( 0.00%)* 10740.15 (-0.93%)*
6.87% 7.33%
4096 10814.84 ( 0.00%)* 10766.97 (-0.44%)*
6.86% 8.18%
8192 11606.89 ( 0.00%)* 11189.28 (-3.73%)*
7.49% 5.55%
16384 12554.88 ( 0.00%)* 12361.22 (-1.57%)*
7.36% 6.49%
NETPERF TCP PPC64
netperf-tcp-vanilla-netperf netperf-tcp
tcp-vanilla pgalloc-delay
64 594.17 ( 0.00%) 596.04 ( 0.31%)*
1.00% 2.29%
128 1064.87 ( 0.00%)* 1074.77 ( 0.92%)*
1.30% 1.40%
256 1852.46 ( 0.00%)* 1856.95 ( 0.24%)
1.25% 1.00%
1024 3839.46 ( 0.00%)* 3813.05 (-0.69%)
1.02% 1.00%
2048 4885.04 ( 0.00%)* 4881.97 (-0.06%)*
1.15% 1.04%
3312 5506.90 ( 0.00%) 5459.72 (-0.86%)
4096 6449.19 ( 0.00%) 6345.46 (-1.63%)
8192 7501.17 ( 0.00%) 7508.79 ( 0.10%)
16384 9618.65 ( 0.00%) 9490.10 (-1.35%)
There was a distinct lack of confidence in the X86* figures so I included
what the devation was where the results were not confident. Many of the
results, whether gains or losses were within the standard deviation so no
solid conclusion can be reached on performance impact. Looking at the
figures, only the X86-64 ones look suspicious with a few losses that were
outside the noise. However, the results were so unstable that without
knowing why they vary so much, a solid conclusion cannot be reached.
SYSBENCH X86
sysbench-vanilla pgalloc-delay
1 7722.85 ( 0.00%) 7756.79 ( 0.44%)
2 14901.11 ( 0.00%) 13683.44 (-8.90%)
3 15171.71 ( 0.00%) 14888.25 (-1.90%)
4 14966.98 ( 0.00%) 15029.67 ( 0.42%)
5 14370.47 ( 0.00%) 14865.00 ( 3.33%)
6 14870.33 ( 0.00%) 14845.57 (-0.17%)
7 14429.45 ( 0.00%) 14520.85 ( 0.63%)
8 14354.35 ( 0.00%) 14362.31 ( 0.06%)
SYSBENCH X86-64
1 17448.70 ( 0.00%) 17484.41 ( 0.20%)
2 34276.39 ( 0.00%) 34251.00 (-0.07%)
3 50805.25 ( 0.00%) 50854.80 ( 0.10%)
4 66667.10 ( 0.00%) 66174.69 (-0.74%)
5 66003.91 ( 0.00%) 65685.25 (-0.49%)
6 64981.90 ( 0.00%) 65125.60 ( 0.22%)
7 64933.16 ( 0.00%) 64379.23 (-0.86%)
8 63353.30 ( 0.00%) 63281.22 (-0.11%)
9 63511.84 ( 0.00%) 63570.37 ( 0.09%)
10 62708.27 ( 0.00%) 63166.25 ( 0.73%)
11 62092.81 ( 0.00%) 61787.75 (-0.49%)
12 61330.11 ( 0.00%) 61036.34 (-0.48%)
13 61438.37 ( 0.00%) 61994.47 ( 0.90%)
14 62304.48 ( 0.00%) 62064.90 (-0.39%)
15 63296.48 ( 0.00%) 62875.16 (-0.67%)
16 63951.76 ( 0.00%) 63769.09 (-0.29%)
SYSBENCH PPC64
-sysbench-pgalloc-delay-sysbench
sysbench-vanilla pgalloc-delay
1 7645.08 ( 0.00%) 7467.43 (-2.38%)
2 14856.67 ( 0.00%) 14558.73 (-2.05%)
3 21952.31 ( 0.00%) 21683.64 (-1.24%)
4 27946.09 ( 0.00%) 28623.29 ( 2.37%)
5 28045.11 ( 0.00%) 28143.69 ( 0.35%)
6 27477.10 ( 0.00%) 27337.45 (-0.51%)
7 26489.17 ( 0.00%) 26590.06 ( 0.38%)
8 26642.91 ( 0.00%) 25274.33 (-5.41%)
9 25137.27 ( 0.00%) 24810.06 (-1.32%)
10 24451.99 ( 0.00%) 24275.85 (-0.73%)
11 23262.20 ( 0.00%) 23674.88 ( 1.74%)
12 24234.81 ( 0.00%) 23640.89 (-2.51%)
13 24577.75 ( 0.00%) 24433.50 (-0.59%)
14 25640.19 ( 0.00%) 25116.52 (-2.08%)
15 26188.84 ( 0.00%) 26181.36 (-0.03%)
16 26782.37 ( 0.00%) 26255.99 (-2.00%)
Again, there is little to conclude here. While there are a few losses,
the results vary by +/- 8% in some cases. They are the results of most
concern as there are some large losses but it's also within the variance
typically seen between kernel releases.
The STREAM results varied so little and are so verbose that I didn't
include them here.
The final test stressed how many huge pages can be allocated. The
absolute number of huge pages allocated are the same with or without the
page. However, the "unusability free space index" which is a measure of
external fragmentation was slightly lower (lower is better) throughout the
lifetime of the system. I also measured the latency of how long it took
to successfully allocate a huge page. The latency was slightly lower and
on X86 and PPC64, more huge pages were allocated almost immediately from
the free lists. The improvement is slight but there.
[mel@csn.ul.ie: Tested, reworked for less branches]
[czoccolo@gmail.com: fix oops by checking pfn_valid_within()]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Corrado Zoccolo <czoccolo@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Shaohua Li reported parallel file copy on tmpfs can lead to OOM killer.
This is regression of caused by commit 9ff473b9a7 ("vmscan: evict
streaming IO first"). Wow, It is 2 years old patch!
Currently, tmpfs file cache is inserted active list at first. This means
that the insertion doesn't only increase numbers of pages in anon LRU, but
it also reduces anon scanning ratio. Therefore, vmscan will get totally
confused. It scans almost only file LRU even though the system has plenty
unused tmpfs pages.
Historically, lru_cache_add_active_anon() was used for two reasons.
1) Intend to priotize shmem page rather than regular file cache.
2) Intend to avoid reclaim priority inversion of used once pages.
But we've lost both motivation because (1) Now we have separate anon and
file LRU list. then, to insert active list doesn't help such priotize.
(2) In past, one pte access bit will cause page activation. then to
insert inactive list with pte access bit mean higher priority than to
insert active list. Its priority inversion may lead to uninteded lru
chun. but it was already solved by commit 645747462 (vmscan: detect
mapped file pages used only once). (Thanks Hannes, you are great!)
Thus, now we can use lru_cache_add_anon() instead.
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reported-by: Shaohua Li <shaohua.li@intel.com>
Reviewed-by: Wu Fengguang <fengguang.wu@intel.com>
Reviewed-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Henrique de Moraes Holschuh <hmh@hmh.eng.br>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This is similar to what already happens in the write case. If we have a short
read while doing O_DIRECT, instead of just returning, fallthrough and try to
read the rest via buffered IO. BTRFS needs this because if we encounter a
compressed or inline extent during DIO, we need to fallback on buffered. If the
extent is compressed we need to read the entire thing into memory and
de-compress it into the users pages. I have tested this with fsx and everything
works great. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch is meant to improve the performance of SLUB by moving the local
kmem_cache_node lock into it's own cacheline separate from kmem_cache.
This is accomplished by simply removing the local_node when NUMA is enabled.
On my system with 2 nodes I saw around a 5% performance increase w/
hackbench times dropping from 6.2 seconds to 5.9 seconds on average. I
suspect the performance gain would increase as the number of nodes
increases, but I do not have the data to currently back that up.
Bugzilla-Reference: http://bugzilla.kernel.org/show_bug.cgi?id=15713
Cc: <stable@kernel.org>
Reported-by: Alex Shi <alex.shi@intel.com>
Tested-by: Alex Shi <alex.shi@intel.com>
Acked-by: Yanmin Zhang <yanmin_zhang@linux.intel.com>
Acked-by: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
The alloc_slab_page() in SLUB uses alloc_pages() if node is '-1'. This means
that node validity check in alloc_pages_node is unnecessary and we can use
alloc_pages_exact_node() to avoid comparison and branch as commit
6484eb3e2a ("page allocator: do not check NUMA node ID when the caller
knows the node is valid") did for the page allocator.
Cc: Christoph Lameter <cl@linux-foundation.org>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
commit 94b528d (kmemtrace: SLUB hooks for caller-tracking functions)
missed tracing kmalloc_large_node in __kmalloc_node_track_caller. We
should trace it same as __kmalloc_node.
Acked-by: David Rientjes <rientjes@google.com>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Xiaotian Feng <dfeng@redhat.com>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
I discovered that we can overflow stack if CONFIG_SLUB_DEBUG=y and use slabs
with many objects, since list_slab_objects() and process_slab() use
DECLARE_BITMAP(map, page->objects).
With 65535 bits, we use 8192 bytes of stack ...
Switch these allocations to dynamic allocations.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (69 commits)
fix handling of offsets in cris eeprom.c, get rid of fake on-stack files
get rid of home-grown mutex in cris eeprom.c
switch ecryptfs_write() to struct inode *, kill on-stack fake files
switch ecryptfs_get_locked_page() to struct inode *
simplify access to ecryptfs inodes in ->readpage() and friends
AFS: Don't put struct file on the stack
Ban ecryptfs over ecryptfs
logfs: replace inode uid,gid,mode initialization with helper function
ufs: replace inode uid,gid,mode initialization with helper function
udf: replace inode uid,gid,mode init with helper
ubifs: replace inode uid,gid,mode initialization with helper function
sysv: replace inode uid,gid,mode initialization with helper function
reiserfs: replace inode uid,gid,mode initialization with helper function
ramfs: replace inode uid,gid,mode initialization with helper function
omfs: replace inode uid,gid,mode initialization with helper function
bfs: replace inode uid,gid,mode initialization with helper function
ocfs2: replace inode uid,gid,mode initialization with helper function
nilfs2: replace inode uid,gid,mode initialization with helper function
minix: replace inode uid,gid,mode init with helper
ext4: replace inode uid,gid,mode init with helper
...
Trivial conflict in fs/fs-writeback.c (mark bitfields unsigned)
- seems what ramfs_get_inode is only locally, make it static.
[AV: the hell it is; it's used by shmem, so shmem needed conversion too
and no, that function can't be made static]
Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Now that the last user passing a NULL file pointer is gone we can remove
the redundant dentry argument and associated hacks inside vfs_fsynmc_range.
The next step will be removig the dentry argument from ->fsync, but given
the luck with the last round of method prototype changes I'd rather
defer this until after the main merge window.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
The entries in xattr handler table should be immutable (ie const)
like other operation tables.
Later patches convert common filesystems. Uncoverted filesystems
will still work, but will generate a compiler warning.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
* git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging-2.6: (577 commits)
Staging: ramzswap: Handler for swap slot free callback
swap: Add swap slot free callback to block_device_operations
swap: Add flag to identify block swap devices
Staging: vt6655: use ETH_FRAME_LEN macro instead of custom one
Staging: vt6655: use ETH_DATA_LEN macro instead of custom one
Staging: vt6655: use ETH_FCS_LEN macro instead of custom one
Staging: vt6656: use ETH_HLEN macro instead of custom one
Staging: comedi: quatech_daqp_cs.c Replace eos semaphore with a completion.
Staging: dt3155v4l: remove private memory allocator
Staging: crystalhd: Remove typedefs from driver
Staging: winbond: Fix for pointer name format issue in mds.c
Staging: vt6656: removed custom UCHAR/USHORT/UINT/ULONG/ULONGLONG typedefs
Staging: vt6656: removed custom CHAR/SHORT/INT/LONG typedefs
Staging: comedi: Altered the way printk is used in 8255.c
staging: iio: adis16350 and similar IMU driver
Staging: iio: max1363 Fix two bugs in single_channel_from_ring
Staging: iio: adis16220 extract bin_attribute structures from state
Staging: iio: adis16220 vibration sensor driver
Staging: comedi: Kconfig dependancy fixes
Staging: comedi: fix up build error from last Kconfig changes
...
Conflicts:
drivers/staging/arlan/arlan-main.c
drivers/staging/comedi/drivers/cb_das16_cs.c
drivers/staging/cx25821/cx25821-alsa.c
drivers/staging/dt3155/dt3155_drv.c
drivers/staging/hv/hv.c
drivers/staging/netwave/netwave_cs.c
drivers/staging/wavelan/wavelan.c
drivers/staging/wavelan/wavelan_cs.c
drivers/staging/wlags49_h2/wl_cs.c
This required a bit of hand merging due to the conflicts
that happened in the later .34-rc releases, as well as
some staging driver changing coming in through other trees
(v4l and pcmcia).
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
When CONFIG_BLOCK isn't enabled:
mm/page-writeback.c: In function 'laptop_mode_timer_fn':
mm/page-writeback.c:708: error: dereferencing pointer to incomplete type
mm/page-writeback.c:709: error: dereferencing pointer to incomplete type
Fix this by essentially eliminating the laptop sync handlers when
CONFIG_BLOCK isn't set, as most are only used from the block layer code.
The exception is laptop_sync_completion() which is used from sys_sync(),
make that an empty declaration in that case.
Reported-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Commit 69b62d01 fixed up most of the places where we would enter
busy schedule() spins when disabling the periodic background
writeback. This fixes up the sb timer so that it doesn't get
hammered on with the delay disabled, and ensures that it gets
rearmed if needed when /proc/sys/vm/dirty_writeback_centisecs
gets modified.
bdi_forker_task() also needs to check for !dirty_writeback_centisecs
and use schedule() appropriately, fix that up too.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial: (44 commits)
vlynq: make whole Kconfig-menu dependant on architecture
add descriptive comment for TIF_MEMDIE task flag declaration.
EEPROM: max6875: Header file cleanup
EEPROM: 93cx6: Header file cleanup
EEPROM: Header file cleanup
agp: use NULL instead of 0 when pointer is needed
rtc-v3020: make bitfield unsigned
PCI: make bitfield unsigned
jbd2: use NULL instead of 0 when pointer is needed
cciss: fix shadows sparse warning
doc: inode uses a mutex instead of a semaphore.
uml: i386: Avoid redefinition of NR_syscalls
fix "seperate" typos in comments
cocbalt_lcdfb: correct sections
doc: Change urls for sparse
Powerpc: wii: Fix typo in comment
i2o: cleanup some exit paths
Documentation/: it's -> its where appropriate
UML: Fix compiler warning due to missing task_struct declaration
UML: add kernel.h include to signal.c
...
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu:
ia64: add sparse annotation to __ia64_per_cpu_var()
percpu: implement kernel memory based chunk allocation
percpu: move vmalloc based chunk management into percpu-vm.c
percpu: misc preparations for nommu support
percpu: reorganize chunk creation and destruction
percpu: factor out pcpu_addr_in_first/reserved_chunk() and update per_cpu_ptr_to_phys()
