memcg_oom_mutex is used to protect memcg OOM path and eventfd interface
for oom_control. None of the critical sections which it protects sleep
(eventfd_signal works from atomic context and the rest are simple linked
list resp. oom_lock atomic operations).
Mutex is also too heavyweight for those code paths because it triggers a
lot of scheduling. It also makes makes convoying effects more visible
when we have a big number of oom killing because we take the lock
mutliple times during mem_cgroup_handle_oom so we have multiple places
where many processes can sleep.
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Cc: Balbir Singh <bsingharora@gmail.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>
Commit 867578cb ("memcg: fix oom kill behavior") introduced a oom_lock
counter which is incremented by mem_cgroup_oom_lock when we are about to
handle memcg OOM situation. mem_cgroup_handle_oom falls back to a sleep
if oom_lock > 1 to prevent from multiple oom kills at the same time.
The counter is then decremented by mem_cgroup_oom_unlock called from the
same function.
This works correctly but it can lead to serious starvations when we have
many processes triggering OOM and many CPUs available for them (I have
tested with 16 CPUs).
Consider a process (call it A) which gets the oom_lock (the first one
that got to mem_cgroup_handle_oom and grabbed memcg_oom_mutex) and other
processes that are blocked on the mutex. While A releases the mutex and
calls mem_cgroup_out_of_memory others will wake up (one after another)
and increase the counter and fall into sleep (memcg_oom_waitq).
Once A finishes mem_cgroup_out_of_memory it takes the mutex again and
decreases oom_lock and wakes other tasks (if releasing memory by
somebody else - e.g. killed process - hasn't done it yet).
A testcase would look like:
Assume malloc XXX is a program allocating XXX Megabytes of memory
which touches all allocated pages in a tight loop
# swapoff SWAP_DEVICE
# cgcreate -g memory:A
# cgset -r memory.oom_control=0 A
# cgset -r memory.limit_in_bytes= 200M
# for i in `seq 100`
# do
# cgexec -g memory:A malloc 10 &
# done
The main problem here is that all processes still race for the mutex and
there is no guarantee that we will get counter back to 0 for those that
got back to mem_cgroup_handle_oom. In the end the whole convoy
in/decreases the counter but we do not get to 1 that would enable
killing so nothing useful can be done. The time is basically unbounded
because it highly depends on scheduling and ordering on mutex (I have
seen this taking hours...).
This patch replaces the counter by a simple {un}lock semantic. As
mem_cgroup_oom_{un}lock works on the a subtree of a hierarchy we have to
make sure that nobody else races with us which is guaranteed by the
memcg_oom_mutex.
We have to be careful while locking subtrees because we can encounter a
subtree which is already locked: hierarchy:
A
/ \
B \
/\ \
C D E
B - C - D tree might be already locked. While we want to enable locking
E subtree because OOM situations cannot influence each other we
definitely do not want to allow locking A.
Therefore we have to refuse lock if any subtree is already locked and
clear up the lock for all nodes that have been set up to the failure
point.
On the other hand we have to make sure that the rest of the world will
recognize that a group is under OOM even though it doesn't have a lock.
Therefore we have to introduce under_oom variable which is incremented
and decremented for the whole subtree when we enter resp. leave
mem_cgroup_handle_oom. under_oom, unlike oom_lock, doesn't need be
updated under memcg_oom_mutex because its users only check a single
group and they use atomic operations for that.
This can be checked easily by the following test case:
# cgcreate -g memory:A
# cgset -r memory.use_hierarchy=1 A
# cgset -r memory.oom_control=1 A
# cgset -r memory.limit_in_bytes= 100M
# cgset -r memory.memsw.limit_in_bytes= 100M
# cgcreate -g memory:A/B
# cgset -r memory.oom_control=1 A/B
# cgset -r memory.limit_in_bytes=20M
# cgset -r memory.memsw.limit_in_bytes=20M
# cgexec -g memory:A/B malloc 30 & #->this will be blocked by OOM of group B
# cgexec -g memory:A malloc 80 & #->this will be blocked by OOM of group A
While B gets oom_lock A will not get it. Both of them go into sleep and
wait for an external action. We can make the limit higher for A to
enforce waking it up
# cgset -r memory.memsw.limit_in_bytes=300M A
# cgset -r memory.limit_in_bytes=300M A
malloc in A has to wake up even though it doesn't have oom_lock.
Finally, the unlock path is very easy because we always unlock only the
subtree we have locked previously while we always decrement under_oom.
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In mm/memcontrol.c, there are many lru stat functions as..
mem_cgroup_zone_nr_lru_pages
mem_cgroup_node_nr_file_lru_pages
mem_cgroup_nr_file_lru_pages
mem_cgroup_node_nr_anon_lru_pages
mem_cgroup_nr_anon_lru_pages
mem_cgroup_node_nr_unevictable_lru_pages
mem_cgroup_nr_unevictable_lru_pages
mem_cgroup_node_nr_lru_pages
mem_cgroup_nr_lru_pages
mem_cgroup_get_local_zonestat
Some of them are under #ifdef MAX_NUMNODES >1 and others are not.
This seems bad. This patch consolidates all functions into
mem_cgroup_zone_nr_lru_pages()
mem_cgroup_node_nr_lru_pages()
mem_cgroup_nr_lru_pages()
For these functions, "which LRU?" information is passed by a mask.
example:
mem_cgroup_nr_lru_pages(mem, BIT(LRU_ACTIVE_ANON))
And I added some macro as ALL_LRU, ALL_LRU_FILE, ALL_LRU_ANON.
example:
mem_cgroup_nr_lru_pages(mem, ALL_LRU)
BTW, considering layout of NUMA memory placement of counters, this patch seems
to be better.
Now, when we gather all LRU information, we scan in following orer
for_each_lru -> for_each_node -> for_each_zone.
This means we'll touch cache lines in different node in turn.
After patch, we'll scan
for_each_node -> for_each_zone -> for_each_lru(mask)
Then, we'll gather information in the same cacheline at once.
[akpm@linux-foundation.org: fix warnigns, build error]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Ying Han <yinghan@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Each memory cgroup has a 'swappiness' value which can be accessed by
get_swappiness(memcg). The major user is try_to_free_mem_cgroup_pages()
and swappiness is passed by argument. It's propagated by scan_control.
get_swappiness() is a static function but some planned updates will need
to get swappiness from files other than memcontrol.c This patch exports
get_swappiness() as mem_cgroup_swappiness(). With this, we can remove the
argument of swapiness from try_to_free... and drop swappiness from
scan_control. only memcg uses it.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Ying Han <yinghan@google.com>
Cc: Shaohua Li <shaohua.li@intel.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>
* Merge akpm patch series: (122 commits)
drivers/connector/cn_proc.c: remove unused local
Documentation/SubmitChecklist: add RCU debug config options
reiserfs: use hweight_long()
reiserfs: use proper little-endian bitops
pnpacpi: register disabled resources
drivers/rtc/rtc-tegra.c: properly initialize spinlock
drivers/rtc/rtc-twl.c: check return value of twl_rtc_write_u8() in twl_rtc_set_time()
drivers/rtc: add support for Qualcomm PMIC8xxx RTC
drivers/rtc/rtc-s3c.c: support clock gating
drivers/rtc/rtc-mpc5121.c: add support for RTC on MPC5200
init: skip calibration delay if previously done
misc/eeprom: add eeprom access driver for digsy_mtc board
misc/eeprom: add driver for microwire 93xx46 EEPROMs
checkpatch.pl: update $logFunctions
checkpatch: make utf-8 test --strict
checkpatch.pl: add ability to ignore various messages
checkpatch: add a "prefer __aligned" check
checkpatch: validate signature styles and To: and Cc: lines
checkpatch: add __rcu as a sparse modifier
checkpatch: suggest using min_t or max_t
...
Did this as a merge because of (trivial) conflicts in
- Documentation/feature-removal-schedule.txt
- arch/xtensa/include/asm/uaccess.h
that were just easier to fix up in the merge than in the patch series.
devres uses the pointer value as key after it's freed, which is safe but
triggers spurious use-after-free warnings on some static analysis tools.
Rearrange code to avoid such warnings.
Signed-off-by: Maxin B. John <maxin.john@gmail.com>
Reviewed-by: Rolf Eike Beer <eike-kernel@sf-tec.de>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
NR_WRITTEN is now accounted at block IO enqueue time, which is not very
accurate as to common understanding. This moves NR_WRITTEN accounting to
the IO completion time and makes it more consistent with BDI_WRITTEN,
which is used for bandwidth estimation.
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Cc: Michael Rubin <mrubin@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
shmem_unuse_inode() and shmem_writepage() contain a little code to cope
with pages inserted independently into the filecache, probably by a
filesystem stacked on top of tmpfs, then fed to its ->readpage() or
->writepage().
Unionfs was indeed experimenting with working in that way three years ago,
but I find no current examples: nowadays the stacking filesystems use vfs
interfaces to the lower filesystem.
It's now illegal: remove most of that code, adding some WARN_ON_ONCEs.
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Erez Zadok <ezk@fsl.cs.sunysb.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We can now simplify shmem_getpage_gfp(): there is no longer a dilemma of
filepage passed in via shmem_readpage(), then swappage found, which must
then be copied over to it.
Although at first it's tempting to replace the **pagep arg by returning
struct page *, that makes a mess of IS_ERR_OR_NULL(page)s in all the
callers, so leave as is.
Insert BUG_ON(!PageUptodate) when we find and lock page: some of the
complication came from uninitialized pages inserted into filecache prior
to readpage; but now we're in control, and only release pagelock on
filecache once it's uptodate (if an error occurs in reading back from
swap, the page remains in swapcache, never moved to filecache).
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The prealloc_page handling in shmem_getpage_gfp() is unnecessarily
complicated: first simplify that before going on to filepage/swappage.
That's right, don't report ENOMEM when the preallocation fails: we may or
may not need the page. But simply report ENOMEM once we find we do need
it, instead of dropping lock, repeating allocation, unwinding on failure
etc. And leave the out label on the fast path, don't goto.
Fix something that looks like a bug but turns out not to be: set
PageSwapBacked on prealloc_page before its mem_cgroup_cache_charge(), as
the removed case was doing. That's important before adding to LRU
(determines which LRU the page goes on), and does affect which path it
takes through memcontrol.c, but in the end MEM_CGROUP_CHANGE_TYPE_ SHMEM
is handled no differently from CACHE.
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Shaohua Li <shaohua.li@intel.com>
Cc: "Zhang, Yanmin" <yanmin.zhang@intel.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Remove that pernicious shmem_readpage() at last: the things we needed it
for (splice, loop, sendfile, i915 GEM) are now fully taken care of by
shmem_file_splice_read() and shmem_read_mapping_page_gfp().
This removal clears the way for a simpler shmem_getpage_gfp(), since page
is never passed in; but leave most of that cleanup until after.
sys_readahead() and sys_fadvise(POSIX_FADV_WILLNEED) will now EINVAL,
instead of unexpectedly trying to read ahead on tmpfs: if that proves to
be an issue for someone, then we can either arrange for them to return
success instead, or try to implement async readahead on tmpfs.
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Make shmem_getpage() a wrapper, passing mapping_gfp_mask() down to
shmem_getpage_gfp(), which in turn passes gfp down to shmem_swp_alloc().
Change shmem_read_mapping_page_gfp() to use shmem_getpage_gfp() in the
CONFIG_SHMEM case; but leave tiny !SHMEM using read_cache_page_gfp().
Add a BUG_ON() in case anyone happens to call this on a non-shmem mapping;
though we might later want to let that case route to read_cache_page_gfp().
It annoys me to have these two almost-redundant args, gfp and fault_type:
I can't find a better way; but initialize fault_type only in shmem_fault().
Note that before, read_cache_page_gfp() was allocating i915_gem's pages
with __GFP_NORETRY as intended; but the corresponding swap vector pages
got allocated without it, leaving a small possibility of OOM.
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Tidy up shmem_file_splice_read():
Remove readahead: okay, we could implement shmem readahead on swap,
but have never done so before, swap being the slow exceptional path.
Use shmem_getpage() instead of find_or_create_page() plus ->readpage().
Remove several comments: sorry, I found them more distracting than
helpful, and this will not be the reference version of splice_read().
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Copy __generic_file_splice_read() and generic_file_splice_read() from
fs/splice.c to shmem_file_splice_read() in mm/shmem.c. Make
page_cache_pipe_buf_ops and spd_release_page() accessible to it.
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Jens Axboe <jaxboe@fusionio.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
I haven't reproduced it myself but the fail scenario is that on such
machines (notably ARM and some embedded powerpc), if you manage to hit
that futex path on a writable page whose dirty bit has gone from the PTE,
you'll livelock inside the kernel from what I can tell.
It will go in a loop of trying the atomic access, failing, trying gup to
"fix it up", getting succcess from gup, go back to the atomic access,
failing again because dirty wasn't fixed etc...
So I think you essentially hang in the kernel.
The scenario is probably rare'ish because affected architecture are
embedded and tend to not swap much (if at all) so we probably rarely hit
the case where dirty is missing or young is missing, but I think Shan has
a piece of SW that can reliably reproduce it using a shared writable
mapping & fork or something like that.
On archs who use SW tracking of dirty & young, a page without dirty is
effectively mapped read-only and a page without young unaccessible in the
PTE.
Additionally, some architectures might lazily flush the TLB when relaxing
write protection (by doing only a local flush), and expect a fault to
invalidate the stale entry if it's still present on another processor.
The futex code assumes that if the "in_atomic()" access -EFAULT's, it can
"fix it up" by causing get_user_pages() which would then be equivalent to
taking the fault.
However that isn't the case. get_user_pages() will not call
handle_mm_fault() in the case where the PTE seems to have the right
permissions, regardless of the dirty and young state. It will eventually
update those bits ... in the struct page, but not in the PTE.
Additionally, it will not handle the lazy TLB flushing that can be
required by some architectures in the fault case.
Basically, gup is the wrong interface for the job. The patch provides a
more appropriate one which boils down to just calling handle_mm_fault()
since what we are trying to do is simulate a real page fault.
The futex code currently attempts to write to user memory within a
pagefault disabled section, and if that fails, tries to fix it up using
get_user_pages().
This doesn't work on archs where the dirty and young bits are maintained
by software, since they will gate access permission in the TLB, and will
not be updated by gup().
In addition, there's an expectation on some archs that a spurious write
fault triggers a local TLB flush, and that is missing from the picture as
well.
I decided that adding those "features" to gup() would be too much for this
already too complex function, and instead added a new simpler
fixup_user_fault() which is essentially a wrapper around handle_mm_fault()
which the futex code can call.
[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: fix some nits Darren saw, fiddle comment layout]
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Reported-by: Shan Hai <haishan.bai@gmail.com>
Tested-by: Shan Hai <haishan.bai@gmail.com>
Cc: David Laight <David.Laight@ACULAB.COM>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Darren Hart <darren.hart@intel.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
radix_tree_tagged() is lockless - it reads from a member of the raid-tree
root node. It does not require any protection.
Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
With zone_reclaim_mode enabled, it's possible for zones to be considered
full in the zonelist_cache so they are skipped in the future. If the
process enters direct reclaim, the ZLC may still consider zones to be full
even after reclaiming pages. Reconsider all zones for allocation if
direct reclaim returns successfully.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
There have been a small number of complaints about significant stalls
while copying large amounts of data on NUMA machines reported on a
distribution bugzilla. In these cases, zone_reclaim was enabled by
default due to large NUMA distances. In general, the complaints have not
been about the workload itself unless it was a file server (in which case
the recommendation was disable zone_reclaim).
The stalls are mostly due to significant amounts of time spent scanning
the preferred zone for pages to free. After a failure, it might fallback
to another node (as zonelists are often node-ordered rather than
zone-ordered) but stall quickly again when the next allocation attempt
occurs. In bad cases, each page allocated results in a full scan of the
preferred zone.
Patch 1 checks the preferred zone for recent allocation failure
which is particularly important if zone_reclaim has failed
recently. This avoids rescanning the zone in the near future and
instead falling back to another node. This may hurt node locality
in some cases but a failure to zone_reclaim is more expensive than
a remote access.
Patch 2 clears the zlc information after direct reclaim.
Otherwise, zone_reclaim can mark zones full, direct reclaim can
reclaim enough pages but the zone is still not considered for
allocation.
This was tested on a 24-thread 2-node x86_64 machine. The tests were
focused on large amounts of IO. All tests were bound to the CPUs on
node-0 to avoid disturbances due to processes being scheduled on different
nodes. The kernels tested are
3.0-rc6-vanilla Vanilla 3.0-rc6
zlcfirst Patch 1 applied
zlcreconsider Patches 1+2 applied
FS-Mark
./fs_mark -d /tmp/fsmark-10813 -D 100 -N 5000 -n 208 -L 35 -t 24 -S0 -s 524288
fsmark-3.0-rc6 3.0-rc6 3.0-rc6
vanilla zlcfirs zlcreconsider
Files/s min 54.90 ( 0.00%) 49.80 (-10.24%) 49.10 (-11.81%)
Files/s mean 100.11 ( 0.00%) 135.17 (25.94%) 146.93 (31.87%)
Files/s stddev 57.51 ( 0.00%) 138.97 (58.62%) 158.69 (63.76%)
Files/s max 361.10 ( 0.00%) 834.40 (56.72%) 802.40 (55.00%)
Overhead min 76704.00 ( 0.00%) 76501.00 ( 0.27%) 77784.00 (-1.39%)
Overhead mean 1485356.51 ( 0.00%) 1035797.83 (43.40%) 1594680.26 (-6.86%)
Overhead stddev 1848122.53 ( 0.00%) 881489.88 (109.66%) 1772354.90 ( 4.27%)
Overhead max 7989060.00 ( 0.00%) 3369118.00 (137.13%) 10135324.00 (-21.18%)
MMTests Statistics: duration
User/Sys Time Running Test (seconds) 501.49 493.91 499.93
Total Elapsed Time (seconds) 2451.57 2257.48 2215.92
MMTests Statistics: vmstat
Page Ins 46268 63840 66008
Page Outs 90821596 90671128 88043732
Swap Ins 0 0 0
Swap Outs 0 0 0
Direct pages scanned 13091697 8966863 8971790
Kswapd pages scanned 0 1830011 1831116
Kswapd pages reclaimed 0 1829068 1829930
Direct pages reclaimed 13037777 8956828 8648314
Kswapd efficiency 100% 99% 99%
Kswapd velocity 0.000 810.643 826.346
Direct efficiency 99% 99% 96%
Direct velocity 5340.128 3972.068 4048.788
Percentage direct scans 100% 83% 83%
Page writes by reclaim 0 3 0
Slabs scanned 796672 720640 720256
Direct inode steals 7422667 7160012 7088638
Kswapd inode steals 0 1736840 2021238
Test completes far faster with a large increase in the number of files
created per second. Standard deviation is high as a small number of
iterations were much higher than the mean. The number of pages scanned by
zone_reclaim is reduced and kswapd is used for more work.
LARGE DD
3.0-rc6 3.0-rc6 3.0-rc6
vanilla zlcfirst zlcreconsider
download tar 59 ( 0.00%) 59 ( 0.00%) 55 ( 7.27%)
dd source files 527 ( 0.00%) 296 (78.04%) 320 (64.69%)
delete source 36 ( 0.00%) 19 (89.47%) 20 (80.00%)
MMTests Statistics: duration
User/Sys Time Running Test (seconds) 125.03 118.98 122.01
Total Elapsed Time (seconds) 624.56 375.02 398.06
MMTests Statistics: vmstat
Page Ins 3594216 439368 407032
Page Outs 23380832 23380488 23377444
Swap Ins 0 0 0
Swap Outs 0 436 287
Direct pages scanned 17482342 69315973 82864918
Kswapd pages scanned 0 519123 575425
Kswapd pages reclaimed 0 466501 522487
Direct pages reclaimed 5858054 2732949 2712547
Kswapd efficiency 100% 89% 90%
Kswapd velocity 0.000 1384.254 1445.574
Direct efficiency 33% 3% 3%
Direct velocity 27991.453 184832.737 208171.929
Percentage direct scans 100% 99% 99%
Page writes by reclaim 0 5082 13917
Slabs scanned 17280 29952 35328
Direct inode steals 115257 1431122 332201
Kswapd inode steals 0 0 979532
This test downloads a large tarfile and copies it with dd a number of
times - similar to the most recent bug report I've dealt with. Time to
completion is reduced. The number of pages scanned directly is still
disturbingly high with a low efficiency but this is likely due to the
number of dirty pages encountered. The figures could probably be improved
with more work around how kswapd is used and how dirty pages are handled
but that is separate work and this result is significant on its own.
Streaming Mapped Writer
MMTests Statistics: duration
User/Sys Time Running Test (seconds) 124.47 111.67 112.64
Total Elapsed Time (seconds) 2138.14 1816.30 1867.56
MMTests Statistics: vmstat
Page Ins 90760 89124 89516
Page Outs 121028340 120199524 120736696
Swap Ins 0 86 55
Swap Outs 0 0 0
Direct pages scanned 114989363 96461439 96330619
Kswapd pages scanned 56430948 56965763 57075875
Kswapd pages reclaimed 27743219 27752044 27766606
Direct pages reclaimed 49777 46884 36655
Kswapd efficiency 49% 48% 48%
Kswapd velocity 26392.541 31363.631 30561.736
Direct efficiency 0% 0% 0%
Direct velocity 53780.091 53108.759 51581.004
Percentage direct scans 67% 62% 62%
Page writes by reclaim 385 122 1513
Slabs scanned 43008 39040 42112
Direct inode steals 0 10 8
Kswapd inode steals 733 534 477
This test just creates a large file mapping and writes to it linearly.
Time to completion is again reduced.
The gains are mostly down to two things. In many cases, there is less
scanning as zone_reclaim simply gives up faster due to recent failures.
The second reason is that memory is used more efficiently. Instead of
scanning the preferred zone every time, the allocator falls back to
another zone and uses it instead improving overall memory utilisation.
This patch: initialise ZLC for first zone eligible for zone_reclaim.
The zonelist cache (ZLC) is used among other things to record if
zone_reclaim() failed for a particular zone recently. The intention is to
avoid a high cost scanning extremely long zonelists or scanning within the
zone uselessly.
Currently the zonelist cache is setup only after the first zone has been
considered and zone_reclaim() has been called. The objective was to avoid
a costly setup but zone_reclaim is itself quite expensive. If it is
failing regularly such as the first eligible zone having mostly mapped
pages, the cost in scanning and allocation stalls is far higher than the
ZLC initialisation step.
This patch initialises ZLC before the first eligible zone calls
zone_reclaim(). Once initialised, it is checked whether the zone failed
zone_reclaim recently. If it has, the zone is skipped. As the first zone
is now being checked, additional care has to be taken about zones marked
full. A zone can be marked "full" because it should not have enough
unmapped pages for zone_reclaim but this is excessive as direct reclaim or
kswapd may succeed where zone_reclaim fails. Only mark zones "full" after
zone_reclaim fails if it failed to reclaim enough pages after scanning.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Currently we are keeping faulted page locked throughout whole __do_fault
call (except for page_mkwrite code path) after calling file system's fault
code. If we do early COW, we allocate a new page which has to be charged
for a memcg (mem_cgroup_newpage_charge).
This function, however, might block for unbounded amount of time if memcg
oom killer is disabled or fork-bomb is running because the only way out of
the OOM situation is either an external event or OOM-situation fix.
In the end we are keeping the faulted page locked and blocking other
processes from faulting it in which is not good at all because we are
basically punishing potentially an unrelated process for OOM condition in
a different group (I have seen stuck system because of ld-2.11.1.so being
locked).
We can do test easily.
% cgcreate -g memory:A
% cgset -r memory.limit_in_bytes=64M A
% cgset -r memory.memsw.limit_in_bytes=64M A
% cd kernel_dir; cgexec -g memory:A make -j
Then, the whole system will live-locked until you kill 'make -j'
by hands (or push reboot...) This is because some important page in a
a shared library are locked.
Considering again, the new page is not necessary to be allocated
with lock_page() held. And usual page allocation may dive into
long memory reclaim loop with holding lock_page() and can cause
very long latency.
There are 3 ways.
1. do allocation/charge before lock_page()
Pros. - simple and can handle page allocation in the same manner.
This will reduce holding time of lock_page() in general.
Cons. - we do page allocation even if ->fault() returns error.
2. do charge after unlock_page(). Even if charge fails, it's just OOM.
Pros. - no impact to non-memcg path.
Cons. - implemenation requires special cares of LRU and we need to modify
page_add_new_anon_rmap()...
3. do unlock->charge->lock again method.
Pros. - no impact to non-memcg path.
Cons. - This may kill LOCK_PAGE_RETRY optimization. We need to release
lock and get it again...
This patch moves "charge" and memory allocation for COW page
before lock_page(). Then, we can avoid scanning LRU with holding
a lock on a page and latency under lock_page() will be reduced.
Then, above livelock disappears.
[akpm@linux-foundation.org: fix code layout]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reported-by: Lutz Vieweg <lvml@5t9.de>
Original-idea-by: Michal Hocko <mhocko@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Ying Han <yinghan@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
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>
2.6.36's 7e496299d4 ("tmpfs: make tmpfs scalable with percpu_counter for
used blocks") to make tmpfs scalable with percpu_counter used
inode->i_lock in place of sbinfo->stat_lock around i_blocks updates; but
that was adverse to scalability, and unnecessary, since info->lock is
already held there in the fast paths.
Remove those uses of i_lock, and add info->lock in the three error paths
where it's then needed across shmem_free_blocks(). It's not actually
needed across shmem_unacct_blocks(), but they're so often paired that it
looks wrong to split them apart.
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
truncate_inode_pages_range()'s final loop has a nice pincer property,
bringing start and end together, squeezing out the last pages. But the
range handling missed out on that, just sliding up the range, perhaps
letting pages come in behind it. Add one more test to give it the same
pincer effect.
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Make the pagevec_lookup loops in truncate_inode_pages_range(),
invalidate_mapping_pages() and invalidate_inode_pages2_range() more
consistent with each other.
They were relying upon page->index of an unlocked page, but apologizing
for it: accept it, embrace it, add comments and WARN_ONs, and simplify the
index handling.
invalidate_inode_pages2_range() had special handling for a wrapped
page->index + 1 = 0 case; but MAX_LFS_FILESIZE doesn't let us anywhere
near there, and a corrupt page->index in the radix_tree could cause more
trouble than that would catch. Remove that wrapped handling.
invalidate_inode_pages2_range() uses min() to limit the pagevec_lookup
when near the end of the range: copy that into the other two, although
it's less useful than you might think (it limits the use of the buffer,
rather than the indices looked up).
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Use consistent variable names in truncate_pagecache(), truncate_setsize(),
vmtruncate() and vmtruncate_range().
unmap_mapping_range() and vmtruncate_range() have mismatched interfaces:
don't change either, but make the vmtruncates more precise about what they
expect unmap_mapping_range() to do.
vmtruncate_range() is currently called only with page-aligned start and
end+1: can handle unaligned start, but unaligned end+1 would hit BUG_ON in
truncate_inode_pages_range() (lacks partial clearing of the end page).
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The often-NULL data arg to read_cache_page() and read_mapping_page()
functions is misdescribed as "destination for read data": no, it's the
first arg to the filler function, often struct file * to ->readpage().
Satisfy checkpatch.pl on those filler prototypes, and tidy up the
declarations in linux/pagemap.h.
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
- shmem pages are not immediately available, but they are not
potentially available either, even if we swap them out, they will just
relocate from memory into swap, total amount of immediate and
potentially available memory is not going to be affected, so we
shouldn't count them as potentially free in the first place.
- nr_free_pages() is not an expensive operation anymore, there is no
need to split the decision making in two halves and repeat code.
Signed-off-by: Dmitry Fink <dmitry.fink@palm.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Acked-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
RED_INACTIVE is a slab thing, and reusing it for memblock was
inappropriate, because memblock is dealing with phys_addr_t's which have a
Kconfigurable sizeof().
Create a new poison type for this application. Fixes the sparse warning
warning: cast truncates bits from constant value (9f911029d74e35b becomes 9d74e35b)
Reported-by: H Hartley Sweeten <hartleys@visionengravers.com>
Tested-by: H Hartley Sweeten <hartleys@visionengravers.com>
Acked-by: Pekka Enberg <penberg@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The badness() function in the oom killer was renamed to oom_badness() in
a63d83f427 ("oom: badness heuristic rewrite") since it is a globally
exported function for clarity.
The prototype for the old function still existed in linux/oom.h, so remove
it. There are no existing users.
Also fixes documentation and comment references to badness() and adjusts
them accordingly.
Signed-off-by: David Rientjes <rientjes@google.com>
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>
ZAP_BLOCK_SIZE became unused in the preemptible-mmu_gather work ("mm:
Remove i_mmap_lock lockbreak"). So zap it.
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fix coding style issues flagged by checkpatch.pl
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Acked-by: Eric B Munson <emunson@mgebm.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The lock is released first thing in all three branches. Simplify this by
unconditionally releasing lock and remove else clause which was only there
to be sure lock was released.
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Johannes Weiner <jweiner@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit a539f3533b ("mm: add SECTION_ALIGN_UP() and
SECTION_ALIGN_DOWN() macro") introduced the SECTION_ALIGN_UP() and
SECTION_ALIGN_DOWN() macros. Use those macros to increase code
readability.
Signed-off-by: Daniel Kiper <dkiper@net-space.pl>
Acked-by: David Rientjes <rientjes@google.com>
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>
In commit a2c8990aed ("memsw: remove noswapaccount kernel parameter"),
Michal forgot to remove some left pieces of noswapaccount in the tree,
this patch removes them all.
Signed-off-by: WANG Cong <xiyou.wangcong@gmail.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Originally, walk_hugetlb_range() didn't require a caller take any lock.
But commit d33b9f45bd ("mm: hugetlb: fix hugepage memory leak in
walk_page_range") changed its rule. Because it added find_vma() call in
walk_hugetlb_range().
Any locking-rule change commit should write a doc too.
[akpm@linux-foundation.org: clarify comment]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Hiroyuki Kamezawa <kamezawa.hiroyuki@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Currently, walk_page_range() calls find_vma() every page table for walk
iteration. but it's completely unnecessary if walk->hugetlb_entry is
unused. And we don't have to assume find_vma() is a lightweight
operation. So this patch checks the walk->hugetlb_entry and avoids the
find_vma() call if possible.
This patch also makes some cleanups. 1) remove ugly uninitialized_var()
and 2) #ifdef in function body.
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Hiroyuki Kamezawa <kamezawa.hiroyuki@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The doc of find_vma() says,
/* Look up the first VMA which satisfies addr < vm_end, NULL if none. */
struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
{
(snip)
Thus, caller should confirm whether the returned vma matches a desired one.
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Hiroyuki Kamezawa <kamezawa.hiroyuki@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
global_faults and last_aging are only used in grab_swap_token(). Move
them into grab_swap_token().
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
http://www.cs.wm.edu/~sjiang/token.pdf is now dead. Replace it with an
alive alternative.
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: 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 patch contains online_page_callback and apropriate functions for
registering/unregistering online page callbacks. It allows to do some
machine specific tasks during online page stage which is required to
implement memory hotplug in virtual machines. Currently this patch is
required by latest memory hotplug support for Xen balloon driver patch
which will be posted soon.
Additionally, originial online_page() function was splited into
following functions doing "atomic" operations:
- __online_page_set_limits() - set new limits for memory management code,
- __online_page_increment_counters() - increment totalram_pages and totalhigh_pages,
- __online_page_free() - free page to allocator.
It was done to:
- not duplicate existing code,
- ease hotplug code devolpment by usage of well defined interface,
- avoid stupid bugs which are unavoidable when the same code
(by design) is developed in many places.
[akpm@linux-foundation.org: use explicit indirect-call syntax]
Signed-off-by: Daniel Kiper <dkiper@net-space.pl>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Vito said:
: The system has many usb disks coming and going day to day, with their
: respective bdi's having min_ratio set to 1 when inserted. It works for
: some time until eventually min_ratio can no longer be set, even when the
: active set of bdi's seen in /sys/class/bdi/*/min_ratio doesn't add up to
: anywhere near 100.
:
: This then leads to an unrelated starvation problem caused by write-heavy
: fuse mounts being used atop the usb disks, a problem the min_ratio setting
: at the underlying devices bdi effectively prevents.
Fix this leakage by resetting the bdi min_ratio when unregistering the
BDI.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Reported-by: Vito Caputo <lkml@pengaru.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
These uses are read-only and in a subsequent patch I have a const struct
page in my hand...
[akpm@linux-foundation.org: fix warnings in lowmem_page_address()]
Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Michel Lespinasse <walken@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This is needed on HIGHMEM systems - we don't always have a virtual
address so store the physical address and map it in as needed.
[akpm@linux-foundation.org: cleanup]
Signed-off-by: Becky Bruce <beckyb@kernel.crashing.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial: (43 commits)
fs: Merge split strings
treewide: fix potentially dangerous trailing ';' in #defined values/expressions
uwb: Fix misspelling of neighbourhood in comment
net, netfilter: Remove redundant goto in ebt_ulog_packet
trivial: don't touch files that are removed in the staging tree
lib/vsprintf: replace link to Draft by final RFC number
doc: Kconfig: `to be' -> `be'
doc: Kconfig: Typo: square -> squared
doc: Konfig: Documentation/power/{pm => apm-acpi}.txt
drivers/net: static should be at beginning of declaration
drivers/media: static should be at beginning of declaration
drivers/i2c: static should be at beginning of declaration
XTENSA: static should be at beginning of declaration
SH: static should be at beginning of declaration
MIPS: static should be at beginning of declaration
ARM: static should be at beginning of declaration
rcu: treewide: Do not use rcu_read_lock_held when calling rcu_dereference_check
Update my e-mail address
PCIe ASPM: forcedly -> forcibly
gma500: push through device driver tree
...
Fix up trivial conflicts:
- arch/arm/mach-ep93xx/dma-m2p.c (deleted)
- drivers/gpio/gpio-ep93xx.c (renamed and context nearby)
- drivers/net/r8169.c (just context changes)
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:
fs: take the ACL checks to common code
bury posix_acl_..._masq() variants
kill boilerplates around posix_acl_create_masq()
generic_acl: no need to clone acl just to push it to set_cached_acl()
kill boilerplate around posix_acl_chmod_masq()
reiserfs: cache negative ACLs for v1 stat format
xfs: cache negative ACLs if there is no attribute fork
9p: do no return 0 from ->check_acl without actually checking
vfs: move ACL cache lookup into generic code
CIFS: Fix oops while mounting with prefixpath
xfs: Fix wrong return value of xfs_file_aio_write
fix devtmpfs race
caam: don't pass bogus S_IFCHR to debugfs_create_...()
get rid of create_proc_entry() abuses - proc_mkdir() is there for purpose
asus-wmi: ->is_visible() can't return negative
fix jffs2 ACLs on big-endian with 16bit mode_t
9p: close ACL leaks
ocfs2_init_acl(): fix a leak
VFS : mount lock scalability for internal mounts
Replace the ->check_acl method with a ->get_acl method that simply reads an
ACL from disk after having a cache miss. This means we can replace the ACL
checking boilerplate code with a single implementation in namei.c.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
We need to branch to the debug code for the first object if we allocate
a new slab otherwise the first object will be marked wrongly as inactive.
Tested-by: Rabin Vincent <rabin@rab.in>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
* 'for-3.1/core' of git://git.kernel.dk/linux-block: (24 commits)
block: strict rq_affinity
backing-dev: use synchronize_rcu_expedited instead of synchronize_rcu
block: fix patch import error in max_discard_sectors check
block: reorder request_queue to remove 64 bit alignment padding
CFQ: add think time check for group
CFQ: add think time check for service tree
CFQ: move think time check variables to a separate struct
fixlet: Remove fs_excl from struct task.
cfq: Remove special treatment for metadata rqs.
block: document blk_plug list access
block: avoid building too big plug list
compat_ioctl: fix make headers_check regression
block: eliminate potential for infinite loop in blkdev_issue_discard
compat_ioctl: fix warning caused by qemu
block: flush MEDIA_CHANGE from drivers on close(2)
blk-throttle: Make total_nr_queued unsigned
block: Add __attribute__((format(printf...) and fix fallout
fs/partitions/check.c: make local symbols static
block:remove some spare spaces in genhd.c
block:fix the comment error in blkdev.h
...
On x86 a page without a mapper is by definition not referenced / old.
The s390 architecture keeps the reference bit in the storage key and
the current code will check the storage key for page without a mapper.
This leads to an interesting effect: the first time an s390 system
needs to write pages to swap it only finds referenced pages. This
causes a lot of pages to get added and written to the swap device.
To avoid this behaviour change page_referenced to query the storage
key only if there is a mapper of the page.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
We set bdi->dirty_exceeded (and thus ratelimiting code starts to
call balance_dirty_pages() every 8 pages) when a per-bdi limit is
exceeded or global limit is exceeded. But per-bdi limit also depends
on the task. Thus different tasks reach the limit on that bdi at
different levels of dirty pages. The result is that with current code
bdi->dirty_exceeded ping-ponged between 1 and 0 depending on which task
just got into balance_dirty_pages().
We fix the issue by clearing bdi->dirty_exceeded only when per-bdi amount
of dirty pages drops below the threshold (7/8 * bdi_dirty_limit) where task
limits already do not have any influence.
Impact: The end result is, the dirty pages are kept more tightly under
control, with the average number slightly lowered than before. This
reduces the risk to throttle light dirtiers and hence more responsive.
However it may add overheads by enforcing balance_dirty_pages() calls
on every 8 pages when there are 2+ heavy dirtiers.
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Christoph Hellwig <hch@infradead.org>
CC: Dave Chinner <david@fromorbit.com>
CC: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
backing-dev: use synchronize_rcu_expedited instead of synchronize_rcu
synchronize_rcu sleeps several timer ticks. synchronize_rcu_expedited is
much faster.
With 100Hz timer frequency, when we remove 10000 block devices with
"dmsetup remove_all" command, it takes 27 minutes. With this patch,
removing 10000 block devices takes only 15 seconds.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (107 commits)
vfs: use ERR_CAST for err-ptr tossing in lookup_instantiate_filp
isofs: Remove global fs lock
jffs2: fix IN_DELETE_SELF on overwriting rename() killing a directory
fix IN_DELETE_SELF on overwriting rename() on ramfs et.al.
mm/truncate.c: fix build for CONFIG_BLOCK not enabled
fs:update the NOTE of the file_operations structure
Remove dead code in dget_parent()
AFS: Fix silly characters in a comment
switch d_add_ci() to d_splice_alias() in "found negative" case as well
simplify gfs2_lookup()
jfs_lookup(): don't bother with . or ..
get rid of useless dget_parent() in btrfs rename() and link()
get rid of useless dget_parent() in fs/btrfs/ioctl.c
fs: push i_mutex and filemap_write_and_wait down into ->fsync() handlers
drivers: fix up various ->llseek() implementations
fs: handle SEEK_HOLE/SEEK_DATA properly in all fs's that define their own llseek
Ext4: handle SEEK_HOLE/SEEK_DATA generically
Btrfs: implement our own ->llseek
fs: add SEEK_HOLE and SEEK_DATA flags
reiserfs: make reiserfs default to barrier=flush
...
Fix up trivial conflicts in fs/xfs/linux-2.6/xfs_super.c due to the new
shrinker callout for the inode cache, that clashed with the xfs code to
start the periodic workers later.
* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
rcu: Fix wrong check in list_splice_init_rcu()
net,rcu: Convert call_rcu(xt_rateest_free_rcu) to kfree_rcu()
sysctl,rcu: Convert call_rcu(free_head) to kfree
vmalloc,rcu: Convert call_rcu(rcu_free_vb) to kfree_rcu()
vmalloc,rcu: Convert call_rcu(rcu_free_va) to kfree_rcu()
ipc,rcu: Convert call_rcu(ipc_immediate_free) to kfree_rcu()
ipc,rcu: Convert call_rcu(free_un) to kfree_rcu()
security,rcu: Convert call_rcu(sel_netport_free) to kfree_rcu()
security,rcu: Convert call_rcu(sel_netnode_free) to kfree_rcu()
ia64,rcu: Convert call_rcu(sn_irq_info_free) to kfree_rcu()
block,rcu: Convert call_rcu(disk_free_ptbl_rcu_cb) to kfree_rcu()
scsi,rcu: Convert call_rcu(fc_rport_free_rcu) to kfree_rcu()
audit_tree,rcu: Convert call_rcu(__put_tree) to kfree_rcu()
security,rcu: Convert call_rcu(whitelist_item_free) to kfree_rcu()
md,rcu: Convert call_rcu(free_conf) to kfree_rcu()
* 'ptrace' of git://git.kernel.org/pub/scm/linux/kernel/git/oleg/misc: (39 commits)
ptrace: do_wait(traced_leader_killed_by_mt_exec) can block forever
ptrace: fix ptrace_signal() && STOP_DEQUEUED interaction
connector: add an event for monitoring process tracers
ptrace: dont send SIGSTOP on auto-attach if PT_SEIZED
ptrace: mv send-SIGSTOP from do_fork() to ptrace_init_task()
ptrace_init_task: initialize child->jobctl explicitly
has_stopped_jobs: s/task_is_stopped/SIGNAL_STOP_STOPPED/
ptrace: make former thread ID available via PTRACE_GETEVENTMSG after PTRACE_EVENT_EXEC stop
ptrace: wait_consider_task: s/same_thread_group/ptrace_reparented/
ptrace: kill real_parent_is_ptracer() in in favor of ptrace_reparented()
ptrace: ptrace_reparented() should check same_thread_group()
redefine thread_group_leader() as exit_signal >= 0
do not change dead_task->exit_signal
kill task_detached()
reparent_leader: check EXIT_DEAD instead of task_detached()
make do_notify_parent() __must_check, update the callers
__ptrace_detach: avoid task_detached(), check do_notify_parent()
kill tracehook_notify_death()
make do_notify_parent() return bool
ptrace: s/tracehook_tracer_task()/ptrace_parent()/
...
In commit c225150b "slab: fix DEBUG_SLAB build",
"if ((unsigned long)objp & (ARCH_SLAB_MINALIGN-1))" is always true if
ARCH_SLAB_MINALIGN == 0. Do not print warning if ARCH_SLAB_MINALIGN == 0.
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
All these are instances of
#define NAME value;
or
#define NAME(params_opt) value;
These of course fail to build when used in contexts like
if(foo $OP NAME)
while(bar $OP NAME)
and may silently generate the wrong code in contexts such as
foo = NAME + 1; /* foo = value; + 1; */
bar = NAME - 1; /* bar = value; - 1; */
baz = NAME & quux; /* baz = value; & quux; */
Reported on comp.lang.c,
Message-ID: <ab0d55fe-25e5-482b-811e-c475aa6065c3@c29g2000yqd.googlegroups.com>
Initial analysis of the dangers provided by Keith Thompson in that thread.
There are many more instances of more complicated macros having unnecessary
trailing semicolons, but this pile seems to be all of the cases of simple
values suffering from the problem. (Thus things that are likely to be found
in one of the contexts above, more complicated ones aren't.)
Signed-off-by: Phil Carmody <ext-phil.2.carmody@nokia.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Moving the event counter into the dynamically allocated 'struc seq_file'
allows poll() support without the need to allocate its own tracking
structure.
All current users are switched over to use the new counter.
Requested-by: Andrew Morton akpm@linux-foundation.org
Acked-by: NeilBrown <neilb@suse.de>
Tested-by: Lucas De Marchi lucas.demarchi@profusion.mobi
Signed-off-by: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
i_alloc_sem is a rather special rw_semaphore. It's the last one that may
be released by a non-owner, and it's write side is always mirrored by
real exclusion. It's intended use it to wait for all pending direct I/O
requests to finish before starting a truncate.
Replace it with a hand-grown construct:
- exclusion for truncates is already guaranteed by i_mutex, so it can
simply fall way
- the reader side is replaced by an i_dio_count member in struct inode
that counts the number of pending direct I/O requests. Truncate can't
proceed as long as it's non-zero
- when i_dio_count reaches non-zero we wake up a pending truncate using
wake_up_bit on a new bit in i_flags
- new references to i_dio_count can't appear while we are waiting for
it to read zero because the direct I/O count always needs i_mutex
(or an equivalent like XFS's i_iolock) for starting a new operation.
This scheme is much simpler, and saves the space of a spinlock_t and a
struct list_head in struct inode (typically 160 bits on a non-debug 64-bit
system).
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
The rcu callback rcu_free_vb() just calls a kfree(),
so we use kfree_rcu() instead of the call_rcu(rcu_free_vb).
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: David Rientjes <rientjes@google.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
The rcu callback rcu_free_va() just calls a kfree(),
so we use kfree_rcu() instead of the call_rcu(rcu_free_va).
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: David Rientjes <rientjes@google.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Reduce high order allocations for some setups.
(NR_CPUS=4096 -> we need 64KB per kmem_cache struct)
We now allocate exact needed size (using nr_cpu_ids and nr_node_ids)
This also makes code a bit smaller on x86_64, since some field offsets
are less than the 127 limit :
Before patch :
# size mm/slab.o
text data bss dec hex filename
22605 361665 32 384302 5dd2e mm/slab.o
After patch :
# size mm/slab.o
text data bss dec hex filename
22349 353473 8224 384046 5dc2e mm/slab.o
CC: Andrew Morton <akpm@linux-foundation.org>
Reported-by: Konstantin Khlebnikov <khlebnikov@openvz.org>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
For shrinkers that have their own cond_resched* calls, having
shrink_slab break the work down into small batches is not
paticularly efficient. Add a custom batchsize field to the struct
shrinker so that shrinkers can use a larger batch size if they
desire.
A value of zero (uninitialised) means "use the default", so
behaviour is unchanged by this patch.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
When a shrinker returns -1 to shrink_slab() to indicate it cannot do
any work given the current memory reclaim requirements, it adds the
entire total_scan count to shrinker->nr. The idea ehind this is that
whenteh shrinker is next called and can do work, it will do the work
of the previously aborted shrinker call as well.
However, if a filesystem is doing lots of allocation with GFP_NOFS
set, then we get many, many more aborts from the shrinkers than we
do successful calls. The result is that shrinker->nr winds up to
it's maximum permissible value (twice the current cache size) and
then when the next shrinker call that can do work is issued, it
has enough scan count built up to free the entire cache twice over.
This manifests itself in the cache going from full to empty in a
matter of seconds, even when only a small part of the cache is
needed to be emptied to free sufficient memory.
Under metadata intensive workloads on ext4 and XFS, I'm seeing the
VFS caches increase memory consumption up to 75% of memory (no page
cache pressure) over a period of 30-60s, and then the shrinker
empties them down to zero in the space of 2-3s. This cycle repeats
over and over again, with the shrinker completely trashing the inode
and dentry caches every minute or so the workload continues.
This behaviour was made obvious by the shrink_slab tracepoints added
earlier in the series, and made worse by the patch that corrected
the concurrent accounting of shrinker->nr.
To avoid this problem, stop repeated small increments of the total
scan value from winding shrinker->nr up to a value that can cause
the entire cache to be freed. We still need to allow it to wind up,
so use the delta as the "large scan" threshold check - if the delta
is more than a quarter of the entire cache size, then it is a large
scan and allowed to cause lots of windup because we are clearly
needing to free lots of memory.
If it isn't a large scan then limit the total scan to half the size
of the cache so that windup never increases to consume the whole
cache. Reducing the total scan limit further does not allow enough
wind-up to maintain the current levels of performance, whilst a
higher threshold does not prevent the windup from freeing the entire
cache under sustained workloads.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
shrink_slab() allows shrinkers to be called in parallel so the
struct shrinker can be updated concurrently. It does not provide any
exclusio for such updates, so we can get the shrinker->nr value
increasing or decreasing incorrectly.
As a result, when a shrinker repeatedly returns a value of -1 (e.g.
a VFS shrinker called w/ GFP_NOFS), the shrinker->nr goes haywire,
sometimes updating with the scan count that wasn't used, sometimes
losing it altogether. Worse is when a shrinker does work and that
update is lost due to racy updates, which means the shrinker will do
the work again!
Fix this by making the total_scan calculations independent of
shrinker->nr, and making the shrinker->nr updates atomic w.r.t. to
other updates via cmpxchg loops.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
It is impossible to understand what the shrinkers are actually doing
without instrumenting the code, so add a some tracepoints to allow
insight to be gained.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
I'm running a workload which triggers a lot of swap in a machine with 4
nodes. After I kill the workload, I found a kswapd livelock. Sometimes
kswapd3 or kswapd2 are keeping running and I can't access filesystem,
but most memory is free.
This looks like a regression since commit 08951e5459 ("mm: vmscan:
correct check for kswapd sleeping in sleeping_prematurely").
Node 2 and 3 have only ZONE_NORMAL, but balance_pgdat() will return 0
for classzone_idx. The reason is end_zone in balance_pgdat() is 0 by
default, if all zones have watermark ok, end_zone will keep 0.
Later sleeping_prematurely() always returns true. Because this is an
order 3 wakeup, and if classzone_idx is 0, both balanced_pages and
present_pages in pgdat_balanced() are 0. We add a special case here.
If a zone has no page, we think it's balanced. This fixes the livelock.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fix CONFIG_SLAB=y CONFIG_DEBUG_SLAB=y build error and warnings.
Now that ARCH_SLAB_MINALIGN defaults to __alignof__(unsigned long long),
it is always defined (when slab.h included), but cannot be used in #if:
mm/slab.c: In function `cache_alloc_debugcheck_after':
mm/slab.c:3156:5: warning: "__alignof__" is not defined
mm/slab.c:3156:5: error: missing binary operator before token "("
make[1]: *** [mm/slab.o] Error 1
So just remove the #if and #endif lines, but then 64-bit build warns:
mm/slab.c: In function `cache_alloc_debugcheck_after':
mm/slab.c:3156:6: warning: cast from pointer to integer of different size
mm/slab.c:3158:10: warning: format `%d' expects type `int', but argument
3 has type `long unsigned int'
Fix those with casts, whatever the actual type of ARCH_SLAB_MINALIGN.
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
Split cmpxchg_double_slab into two functions. One for the case where we know that
interrupts are disabled (and therefore the fallback does not need to disable
interrupts) and one for the other cases where fallback will also disable interrupts.
This fixes the issue that __slab_free called cmpxchg_double_slab in some scenarios
without disabling interrupts.
Tested-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
SPARSEMEM w/o VMEMMAP and DISCONTIGMEM, both used only on 32bit, use
sections array to map pfn to nid which is limited in granularity. If
NUMA nodes are laid out such that the mapping cannot be accurate, boot
will fail triggering BUG_ON() in mminit_verify_page_links().
On 32bit, it's 512MiB w/ PAE and SPARSEMEM. This seems to have been
granular enough until commit 2706a0bf7b (x86, NUMA: Enable
CONFIG_AMD_NUMA on 32bit too). Apparently, there is a machine which
aligns NUMA nodes to 128MiB and has only AMD NUMA but not SRAT. This
led to the following BUG_ON().
On node 0 totalpages: 2096615
DMA zone: 32 pages used for memmap
DMA zone: 0 pages reserved
DMA zone: 3927 pages, LIFO batch:0
Normal zone: 1740 pages used for memmap
Normal zone: 220978 pages, LIFO batch:31
HighMem zone: 16405 pages used for memmap
HighMem zone: 1853533 pages, LIFO batch:31
BUG: Int 6: CR2 (null)
EDI (null) ESI 00000002 EBP 00000002 ESP c1543ecc
EBX f2400000 EDX 00000006 ECX (null) EAX 00000001
err (null) EIP c16209aa CS 00000060 flg 00010002
Stack: f2400000 00220000 f7200800 c1620613 00220000 01000000 04400000 00238000
(null) f7200000 00000002 f7200b58 f7200800 c1620929 000375fe (null)
f7200b80 c16395f0 00200a02 f7200a80 (null) 000375fe 00000002 (null)
Pid: 0, comm: swapper Not tainted 2.6.39-rc5-00181-g2706a0b #17
Call Trace:
[<c136b1e5>] ? early_fault+0x2e/0x2e
[<c16209aa>] ? mminit_verify_page_links+0x12/0x42
[<c1620613>] ? memmap_init_zone+0xaf/0x10c
[<c1620929>] ? free_area_init_node+0x2b9/0x2e3
[<c1607e99>] ? free_area_init_nodes+0x3f2/0x451
[<c1601d80>] ? paging_init+0x112/0x118
[<c15f578d>] ? setup_arch+0x791/0x82f
[<c15f43d9>] ? start_kernel+0x6a/0x257
This patch implements node_map_pfn_alignment() which determines
maximum internode alignment and update numa_register_memblks() to
reject NUMA configuration if alignment exceeds the pfn -> nid mapping
granularity of the memory model as determined by PAGES_PER_SECTION.
This makes the problematic machine boot w/ flatmem by rejecting the
NUMA config and provides protection against crazy NUMA configurations.
Signed-off-by: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20110712074534.GB2872@htj.dyndns.org
LKML-Reference: <20110628174613.GP478@escobedo.osrc.amd.com>
Reported-and-Tested-by: Hans Rosenfeld <hans.rosenfeld@amd.com>
Cc: Conny Seidel <conny.seidel@amd.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Add trace event balance_dirty_state for showing the global dirty page
counts and thresholds at each global_dirty_limits() invocation. This
will cover the callers throttle_vm_writeout(), over_bground_thresh()
and each balance_dirty_pages() loop.
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
The max-pause limit helps to keep the sleep time inside
balance_dirty_pages() within MAX_PAUSE=200ms. The 200ms max sleep means
per task rate limit of 8pages/200ms=160KB/s when dirty exceeded, which
normally is enough to stop dirtiers from continue pushing the dirty
pages high, unless there are a sufficient large number of slow dirtiers
(eg. 500 tasks doing 160KB/s will still sum up to 80MB/s, exceeding the
write bandwidth of a slow disk and hence accumulating more and more dirty
pages).
The pass-good limit helps to let go of the good bdi's in the presence of
a blocked bdi (ie. NFS server not responding) or slow USB disk which for
some reason build up a large number of initial dirty pages that refuse
to go away anytime soon.
For example, given two bdi's A and B and the initial state
bdi_thresh_A = dirty_thresh / 2
bdi_thresh_B = dirty_thresh / 2
bdi_dirty_A = dirty_thresh / 2
bdi_dirty_B = dirty_thresh / 2
Then A get blocked, after a dozen seconds
bdi_thresh_A = 0
bdi_thresh_B = dirty_thresh
bdi_dirty_A = dirty_thresh / 2
bdi_dirty_B = dirty_thresh / 2
The (bdi_dirty_B < bdi_thresh_B) test is now useless and the dirty pages
will be effectively throttled by condition (nr_dirty < dirty_thresh).
This has two problems:
(1) we lose the protections for light dirtiers
(2) balance_dirty_pages() effectively becomes IO-less because the
(bdi_nr_reclaimable > bdi_thresh) test won't be true. This is good
for IO, but balance_dirty_pages() loses an important way to break
out of the loop which leads to more spread out throttle delays.
DIRTY_PASSGOOD_AREA can eliminate the above issues. The only problem is,
DIRTY_PASSGOOD_AREA needs to be defined as 2 to fully cover the above
example while this patch uses the more conservative value 8 so as not to
surprise people with too many dirty pages than expected.
The max-pause limit won't noticeably impact the speed dirty pages are
knocked down when there is a sudden drop of global/bdi dirty thresholds.
Because the heavy dirties will be throttled below 160KB/s which is slow
enough. It does help to avoid long dirty throttle delays and especially
will make light dirtiers more responsive.
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
The start of a heavy weight application (ie. KVM) may instantly knock
down determine_dirtyable_memory() if the swap is not enabled or full.
global_dirty_limits() and bdi_dirty_limit() will in turn get global/bdi
dirty thresholds that are _much_ lower than the global/bdi dirty pages.
balance_dirty_pages() will then heavily throttle all dirtiers including
the light ones, until the dirty pages drop below the new dirty thresholds.
During this _deep_ dirty-exceeded state, the system may appear rather
unresponsive to the users.
About "deep" dirty-exceeded: task_dirty_limit() assigns 1/8 lower dirty
threshold to heavy dirtiers than light ones, and the dirty pages will
be throttled around the heavy dirtiers' dirty threshold and reasonably
below the light dirtiers' dirty threshold. In this state, only the heavy
dirtiers will be throttled and the dirty pages are carefully controlled
to not exceed the light dirtiers' dirty threshold. However if the
threshold itself suddenly drops below the number of dirty pages, the
light dirtiers will get heavily throttled.
So introduce global_dirty_limit for tracking the global dirty threshold
with policies
- follow downwards slowly
- follow up in one shot
global_dirty_limit can effectively mask out the impact of sudden drop of
dirtyable memory. It will be used in the next patch for two new type of
dirty limits. Note that the new dirty limits are not going to avoid
throttling the light dirtiers, but could limit their sleep time to 200ms.
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Introduce
nr_dirty = NR_FILE_DIRTY + NR_WRITEBACK + NR_UNSTABLE_NFS
in order to simplify many tests in the following patches.
balance_dirty_pages() will eventually care only about the dirty sums
besides nr_writeback.
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Add a "BdiWriteBandwidth" entry and indent others in /debug/bdi/*/stats.
btw, increase digital field width to 10, for keeping the possibly
huge BdiWritten number aligned at least for desktop systems.
Impact: this could break user space tools if they are dumb enough to
depend on the number of white spaces.
CC: Theodore Ts'o <tytso@mit.edu>
CC: Jan Kara <jack@suse.cz>
CC: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
The estimation value will start from 100MB/s and adapt to the real
bandwidth in seconds.
It tries to update the bandwidth only when disk is fully utilized.
Any inactive period of more than one second will be skipped.
The estimated bandwidth will be reflecting how fast the device can
writeout when _fully utilized_, and won't drop to 0 when it goes idle.
The value will remain constant at disk idle time. At busy write time, if
not considering fluctuations, it will also remain high unless be knocked
down by possible concurrent reads that compete for the disk time and
bandwidth with async writes.
The estimation is not done purely in the flusher because there is no
guarantee for write_cache_pages() to return timely to update bandwidth.
The bdi->avg_write_bandwidth smoothing is very effective for filtering
out sudden spikes, however may be a little biased in long term.
The overheads are low because the bdi bandwidth update only occurs at
200ms intervals.
The 200ms update interval is suitable, because it's not possible to get
the real bandwidth for the instance at all, due to large fluctuations.
The NFS commits can be as large as seconds worth of data. One XFS
completion may be as large as half second worth of data if we are going
to increase the write chunk to half second worth of data. In ext4,
fluctuations with time period of around 5 seconds is observed. And there
is another pattern of irregular periods of up to 20 seconds on SSD tests.
That's why we are not only doing the estimation at 200ms intervals, but
also averaging them over a period of 3 seconds and then go further to do
another level of smoothing in avg_write_bandwidth.
CC: Li Shaohua <shaohua.li@intel.com>
CC: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Introduce the BDI_WRITTEN counter. It will be used for estimating the
bdi's write bandwidth.
Peter Zijlstra <a.p.zijlstra@chello.nl>:
Move BDI_WRITTEN accounting into __bdi_writeout_inc().
This will cover and fix fuse, which only calls bdi_writeout_inc().
CC: Michael Rubin <mrubin@google.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Pass struct wb_writeback_work all the way down to writeback_sb_inodes(),
and initialize the struct writeback_control there.
struct writeback_control is basically designed to control writeback of a
single file, but we keep abuse it for writing multiple files in
writeback_sb_inodes() and its callers.
It immediately clean things up, e.g. suddenly wbc.nr_to_write vs
work->nr_pages starts to make sense, and instead of saving and restoring
pages_skipped in writeback_sb_inodes it can always start with a clean
zero value.
It also makes a neat IO pattern change: large dirty files are now
written in the full 4MB writeback chunk size, rather than whatever
remained quota in wbc->nr_to_write.
Acked-by: Jan Kara <jack@suse.cz>
Proposed-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
remap_pfn_range() means map physical address pfn<<PAGE_SHIFT to user addr.
For nommu arch it's implemented by vma->vm_start = pfn << PAGE_SHIFT which
is wrong acroding the original meaning of this function. And some driver
developer using remap_pfn_range() with correct parameter will get
unexpected result because vm_start is changed. It should be implementd
like addr = pfn << PAGE_SHIFT but which is meanless on nommu arch, this
patch just make it simply return.
Parameter name and setting of vma->vm_flags also be fixed.
Signed-off-by: Bob Liu <lliubbo@gmail.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: David Howells <dhowells@redhat.com>
Acked-by: Greg Ungerer <gerg@uclinux.org>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Bob Liu <lliubbo@gmail.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
commit 889976dbcb ("memcg: reclaim memory from nodes in round-robin
order") adds an numa node round-robin for memcg. But the information is
updated once per 10sec.
This patch changes the update trigger from jiffies to memcg's event count.
After this patch, numa scan information will be updated when we see 1024
events of pagein/pageout under a memcg.
[akpm@linux-foundation.org: attempt to repair code layout]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Ying Han <yinghan@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
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>
Now, in mem_cgroup_hierarchical_reclaim(), mem_cgroup_local_usage() is
used for checking whether the memcg contains reclaimable pages or not. If
no pages in it, the routine skips it.
But, mem_cgroup_local_usage() contains Unevictable pages and cannot handle
"noswap" condition correctly. This doesn't work on a swapless system.
This patch adds test_mem_cgroup_reclaimable() and replaces
mem_cgroup_local_usage(). test_mem_cgroup_reclaimable() see LRU counter
and returns correct answer to the caller. And this new function has
"noswap" argument and can see only FILE LRU if necessary.
[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: fix kerneldoc layout]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Ying Han <yinghan@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
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>
__tlb_remove_page() switches to a new batch page, but still checks space
in the old batch. This check always fails, and causes a forced tlb flush.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
During allocator-intensive workloads, kswapd will be woken frequently
causing free memory to oscillate between the high and min watermark. This
is expected behaviour. Unfortunately, if the highest zone is small, a
problem occurs.
When balance_pgdat() returns, it may be at a lower classzone_idx than it
started because the highest zone was unreclaimable. Before checking if it
should go to sleep though, it checks pgdat->classzone_idx which when there
is no other activity will be MAX_NR_ZONES-1. It interprets this as it has
been woken up while reclaiming, skips scheduling and reclaims again. As
there is no useful reclaim work to do, it enters into a loop of shrinking
slab consuming loads of CPU until the highest zone becomes reclaimable for
a long period of time.
There are two problems here. 1) If the returned classzone or order is
lower, it'll continue reclaiming without scheduling. 2) if the highest
zone was marked unreclaimable but balance_pgdat() returns immediately at
DEF_PRIORITY, the new lower classzone is not communicated back to kswapd()
for sleeping.
This patch does two things that are related. If the end_zone is
unreclaimable, this information is communicated back. Second, if the
classzone or order was reduced due to failing to reclaim, new information
is not read from pgdat and instead an attempt is made to go to sleep. Due
to this, it is also necessary that pgdat->classzone_idx be initialised
each time to pgdat->nr_zones - 1 to avoid re-reads being interpreted as
wakeups.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Andrew Lutomirski <luto@mit.edu>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When deciding if kswapd is sleeping prematurely, the classzone is taken
into account but this is different to what balance_pgdat() and the
allocator are doing. Specifically, the DMA zone will be checked based on
the classzone used when waking kswapd which could be for a GFP_KERNEL or
GFP_HIGHMEM request. The lowmem reserve limit kicks in, the watermark is
not met and kswapd thinks it's sleeping prematurely keeping kswapd awake in
error.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Andrew Lutomirski <luto@mit.edu>
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: Johannes Weiner <hannes@cmpxchg.org>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
During allocator-intensive workloads, kswapd will be woken frequently
causing free memory to oscillate between the high and min watermark. This
is expected behaviour.
When kswapd applies pressure to zones during node balancing, it checks if
the zone is above a high+balance_gap threshold. If it is, it does not
apply pressure but it unconditionally shrinks slab on a global basis which
is excessive. In the event kswapd is being kept awake due to a high small
unreclaimable zone, it skips zone shrinking but still calls shrink_slab().
Once pressure has been applied, the check for zone being unreclaimable is
being made before the check is made if all_unreclaimable should be set.
This miss of unreclaimable can cause has_under_min_watermark_zone to be
set due to an unreclaimable zone preventing kswapd backing off on
congestion_wait().
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Andrew Lutomirski <luto@mit.edu>
Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
During allocator-intensive workloads, kswapd will be woken frequently
causing free memory to oscillate between the high and min watermark. This
is expected behaviour. Unfortunately, if the highest zone is small, a
problem occurs.
This seems to happen most with recent sandybridge laptops but it's
probably a co-incidence as some of these laptops just happen to have a
small Normal zone. The reproduction case is almost always during copying
large files that kswapd pegs at 100% CPU until the file is deleted or
cache is dropped.
The problem is mostly down to sleeping_prematurely() keeping kswapd awake
when the highest zone is small and unreclaimable and compounded by the
fact we shrink slabs even when not shrinking zones causing a lot of time
to be spent in shrinkers and a lot of memory to be reclaimed.
Patch 1 corrects sleeping_prematurely to check the zones matching
the classzone_idx instead of all zones.
Patch 2 avoids shrinking slab when we are not shrinking a zone.
Patch 3 notes that sleeping_prematurely is checking lower zones against
a high classzone which is not what allocators or balance_pgdat()
is doing leading to an artifical belief that kswapd should be
still awake.
Patch 4 notes that when balance_pgdat() gives up on a high zone that the
decision is not communicated to sleeping_prematurely()
This problem affects 2.6.38.8 for certain and is expected to affect 2.6.39
and 3.0-rc4 as well. If accepted, they need to go to -stable to be picked
up by distros and this series is against 3.0-rc4. I've cc'd people that
reported similar problems recently to see if they still suffer from the
problem and if this fixes it.
This patch: correct the check for kswapd sleeping in sleeping_prematurely()
During allocator-intensive workloads, kswapd will be woken frequently
causing free memory to oscillate between the high and min watermark. This
is expected behaviour.
A problem occurs if the highest zone is small. balance_pgdat() only
considers unreclaimable zones when priority is DEF_PRIORITY but
sleeping_prematurely considers all zones. It's possible for this sequence
to occur
1. kswapd wakes up and enters balance_pgdat()
2. At DEF_PRIORITY, marks highest zone unreclaimable
3. At DEF_PRIORITY-1, ignores highest zone setting end_zone
4. At DEF_PRIORITY-1, calls shrink_slab freeing memory from
highest zone, clearing all_unreclaimable. Highest zone
is still unbalanced
5. kswapd returns and calls sleeping_prematurely
6. sleeping_prematurely looks at *all* zones, not just the ones
being considered by balance_pgdat. The highest small zone
has all_unreclaimable cleared but the zone is not
balanced. all_zones_ok is false so kswapd stays awake
This patch corrects the behaviour of sleeping_prematurely to check the
zones balance_pgdat() checked.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Pádraig Brady <P@draigBrady.com>
Tested-by: Andrew Lutomirski <luto@mit.edu>
Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This fixes the following build breakage commit d6543e3 ("slub: Enable backtrace
for create/delete points"):
CC mm/slub.o
mm/slub.c: In function ‘set_track’:
mm/slub.c:428: error: storage size of ‘trace’ isn’t known
mm/slub.c:435: error: implicit declaration of function ‘save_stack_trace’
mm/slub.c:428: warning: unused variable ‘trace’
make[1]: *** [mm/slub.o] Error 1
make: *** [mm/slub.o] Error 2
Signed-off-by: Pekka Enberg <penberg@kernel.org>
slub checks for poison one byte by one, which is highly inefficient
and shows up frequently as a highest cpu-eater in perf top.
Joining reads gives nice speedup:
(Compiling some project with different options)
make -j12 make clean
slub_debug disabled: 1m 27s 1.2 s
slub_debug enabled: 1m 46s 7.6 s
slub_debug enabled + this patch: 1m 33s 3.2 s
check_bytes still shows up high, but not always at the top.
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Matt Mackall <mpm@selenic.com>
Cc: linux-mm@kvack.org
Signed-off-by: Pekka Enberg <penberg@kernel.org>
This is for tracking down suspect memory usage.
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
load_freelist is now only branched to only if there are objects available.
So no need to check the object variable for NULL.
Signed-off-by: Pekka Enberg <penberg@kernel.org>
Make deactivation occur implicitly while checking out the current freelist.
This avoids one cmpxchg operation on a slab that is now fully in use.
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
Slub reloads the per cpu slab if the page does not satisfy the NUMA condition. Track
those reloads since doing so has a performance impact.
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
We can avoid deactivate slab in special cases if we do the
deactivation of slabs in each code flow that leads to new_slab.
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
Disabling interrupts can be avoided now. However, list operation still require
disabling interrupts since allocations can occur from interrupt
contexts and there is no way to perform atomic list operations.
The acquition of the list_lock therefore has to disable interrupts as well.
Dropping interrupt handling significantly simplifies the slowpath.
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
We will be calling free_debug_processing with interrupts disabled
in some case when the later patches are applied. Some of the
functions called by free_debug_processing expect interrupts to be
off.
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
Locking slabs is no longer necesary if the arch supports cmpxchg operations
and if no debuggin features are used on a slab. If the arch does not support
cmpxchg then we fallback to use the slab lock to do a cmpxchg like operation.
The patch also changes the lock order. Slab locks are subsumed to the node lock
now. With that approach slab_trylocking is no longer necessary.
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
