- 03 May, 2017 40 commits
-
-
Johannes Weiner authored
The current duplication is a high-maintenance mess, and it's painful to add new items. This increases the size of the event array, but we'll eventually want most of the VM events tracked on a per-cgroup basis anyway. Link: http://lkml.kernel.org/r/20170404220148.28338-2-hannes@cmpxchg.orgSigned-off-by:
Johannes Weiner <hannes@cmpxchg.org> Acked-by:
Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Michal Hocko <mhocko@suse.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Johannes Weiner authored
We only ever count single events, drop the @nr parameter. Rename the function accordingly. Remove low-information kerneldoc. Link: http://lkml.kernel.org/r/20170404220148.28338-1-hannes@cmpxchg.orgSigned-off-by:
Michal Hocko <mhocko@suse.com> Signed-off-by:
-
Johannes Weiner authored
Since commit 59dc76b0 ("mm: vmscan: reduce size of inactive file list") we noticed bigger IO spikes during changes in cache access patterns. The patch in question shrunk the inactive list size to leave more room for the current workingset in the presence of streaming IO. However, workingset transitions that previously happened on the inactive list are now pushed out of memory and incur more refaults to complete. This patch disables active list protection when refaults are being observed. This accelerates workingset transitions, and allows more of the new set to establish itself from memory, without eating into the ability to protect the established workingset during stable periods. The workloads that were measurably affected for us were hit pretty bad by it, with refault/majfault rates doubling and tripling during cache transitions, and the machines sustaining half-hour periods of 100% IO utilization, where they'd previously have sub-minute peaks at 60-90%. Stateful services that handle user data tend to be more conservative with kernel upgrades. As a result we hit most page cache issues with some delay, as was the case here. The severity seemed to warrant a stable tag. Fixes: 59dc76b0 ("mm: vmscan: reduce size of inactive file list") Link: http://lkml.kernel.org/r/20170404220052.27593-1-hannes@cmpxchg.orgSigned-off-by:
-
Anshuman Khandual authored
Commit 091d0d55 ("shm: fix null pointer deref when userspace specifies invalid hugepage size") had replaced MAP_HUGE_MASK with SHM_HUGE_MASK. Though both of them contain the same numeric value of 0x3f, MAP_HUGE_MASK flag sounds more appropriate than the other one in the context. Hence change it back. Link: http://lkml.kernel.org/r/20170404045635.616-1-khandual@linux.vnet.ibm.comSigned-off-by:
Anshuman Khandual <khandual@linux.vnet.ibm.com> Reviewed-by:
Matthew Wilcox <mawilcox@microsoft.com> Acked-by:
Balbir Singh <bsingharora@gmail.com> Acked-by:
-
Michal Hocko authored
Tetsuo has reported that sysrq triggered OOM killer will print a misleading information when no tasks are selected: sysrq: SysRq : Manual OOM execution Out of memory: Kill process 4468 ((agetty)) score 0 or sacrifice child Killed process 4468 ((agetty)) total-vm:43704kB, anon-rss:1760kB, file-rss:0kB, shmem-rss:0kB sysrq: SysRq : Manual OOM execution Out of memory: Kill process 4469 (systemd-cgroups) score 0 or sacrifice child Killed process 4469 (systemd-cgroups) total-vm:10704kB, anon-rss:120kB, file-rss:0kB, shmem-rss:0kB sysrq: SysRq : Manual OOM execution sysrq: OOM request ignored because killer is disabled sysrq: SysRq : Manual OOM execution sysrq: OOM request ignored because killer is disabled sysrq: SysRq : Manual OOM execution sysrq: OOM request ignored because killer is disabled The real reason is that there are no eligible tasks for the OOM killer to select but since commit 7c5f64f8 ("mm: oom: deduplicate victim selection code for memcg and global oom") the semantic of out_of_memory has changed without updating moom_callback. This patch updates moom_callback to tell that no task was eligible which is the case for both oom killer disabled and no eligible tasks. In order to help distinguish first case from the second add printk to both oom_killer_{enable,disable}. This information is useful on its own because it might help debugging potential memory allocation failures. Fixes: 7c5f64f8 ("mm: oom: deduplicate victim selection code for memcg and global oom") Link: http://lkml.kernel.org/r/20170404134705.6361-1-mhocko@kernel.orgSigned-off-by:
Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by:
-
Mike Rapoport authored
Currently, selftest for userfaultfd is compiled three times: for anonymous, shared and hugetlb memory. Let's combine all the cases into a single executable which will have a command line option for selection of the test type. Link: http://lkml.kernel.org/r/1490869741-5913-1-git-send-email-rppt@linux.vnet.ibm.comSigned-off-by:
Mike Rapoport <rppt@linux.vnet.ibm.com> Reviewed-by:
Mike Kravetz <mike.kravetz@oracle.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Shuah Khan <shuah@kernel.org> Signed-off-by:
-
Hao Lee authored
Fix variable name error in comments. No code changes. Link: http://lkml.kernel.org/r/20170403161655.5081-1-haolee.swjtu@gmail.comSigned-off-by:
Hao Lee <haolee.swjtu@gmail.com> Signed-off-by:
-
Tim Chen authored
Add a warning diagnostics to user if we failed to allocate swap slots cache and use it. [akpm@linux-foundation.org: use WARN_ONCE return value, fix grammar in message] Link: http://lkml.kernel.org/r/20170328234827.GA10107@linux.intel.comSigned-off-by:
Tim Chen <tim.c.chen@linux.intel.com> Signed-off-by:
-
Pushkar Jambhlekar authored
It is preferred, and the rest of migrate.h gets it right. Link: http://lkml.kernel.org/r/1490336009-8024-1-git-send-email-pushkar.iit@gmail.comSigned-off-by:
Pushkar Jambhlekar <pushkar.iit@gmail.com> Signed-off-by:
-
Vinayak Menon authored
On SPARSEMEM systems page poisoning is enabled after buddy is up, because of the dependency on page extension init. This causes the pages released by free_all_bootmem not to be poisoned. This either delays or misses the identification of some issues because the pages have to undergo another cycle of alloc-free-alloc for any corruption to be detected. Enable page poisoning early by getting rid of the PAGE_EXT_DEBUG_POISON flag. Since all the free pages will now be poisoned, the flag need not be verified before checking the poison during an alloc. [vinmenon@codeaurora.org: fix Kconfig] Link: http://lkml.kernel.org/r/1490878002-14423-1-git-send-email-vinmenon@codeaurora.org Link: http://lkml.kernel.org/r/1490358246-11001-1-git-send-email-vinmenon@codeaurora.orgSigned-off-by:
Vinayak Menon <vinmenon@codeaurora.org> Acked-by:
Laura Abbott <labbott@redhat.com> Tested-by:
-
Huang Ying authored
Cluster lock is used to protect the swap_cluster_info and corresponding elements in swap_info_struct->swap_map[]. But it is found that now in scan_swap_map_slots(), swap_avail_lock may be acquired when cluster lock is held. This does no good except making the locking more complex and improving the potential locking contention, because the swap_info_struct->lock is used to protect the data structure operated in the code already. Fix this via moving the corresponding operations in scan_swap_map_slots() out of cluster lock. Link: http://lkml.kernel.org/r/20170317064635.12792-3-ying.huang@intel.comSigned-off-by:
"Huang, Ying" <ying.huang@intel.com> Acked-by:
Tim Chen <tim.c.chen@intel.com> Signed-off-by:
-
Huang Ying authored
This is just a cleanup patch, no functionality change. In cluster_list_add_tail(), spin_lock_nested() is used to lock the cluster, while unlock_cluster() is used to unlock the cluster. To improve the code readability, use spin_unlock() directly to unlock the cluster. Link: http://lkml.kernel.org/r/20170317064635.12792-2-ying.huang@intel.comSigned-off-by:
-
Huang Ying authored
Commit cbab0e4e ("swap: avoid read_swap_cache_async() race to deadlock while waiting on discard I/O completion") fixed a deadlock in read_swap_cache_async(). Because at that time, in swap allocation path, a swap entry may be set as SWAP_HAS_CACHE, then wait for discarding to complete before the page for the swap entry is added to the swap cache. But in commit 815c2c54 ("swap: make swap discard async"), the discarding for swap become asynchronous, waiting for discarding to complete will be done before the swap entry is set as SWAP_HAS_CACHE. So the comments in code is incorrect now. This patch fixes the comments. The cond_resched() added in the commit cbab0e4e is not necessary now too. But if we added some sleep in swap allocation path in the future, there may be some hard to debug/reproduce deadlock bug. So it is kept. Link: http://lkml.kernel.org/r/20170317064635.12792-1-ying.huang@intel.comSigned-off-by:
Rafael Aquini <aquini@redhat.com> Cc: Shaohua Li <shli@kernel.org> Signed-off-by:
-
Minchan Kim authored
There is no user for it. Remove it. [minchan@kernel.org: use false instead of SWAP_FAIL] Link: http://lkml.kernel.org/r/20170316053313.GA19241@bbox Link: http://lkml.kernel.org/r/1489555493-14659-11-git-send-email-minchan@kernel.orgSigned-off-by:
Minchan Kim <minchan@kernel.org> Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com> Cc: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Signed-off-by:
-
Minchan Kim authored
rmap_one's return value controls whether rmap_work should contine to scan other ptes or not so it's target for changing to boolean. Return true if the scan should be continued. Otherwise, return false to stop the scanning. This patch makes rmap_one's return value to boolean. Link: http://lkml.kernel.org/r/1489555493-14659-10-git-send-email-minchan@kernel.orgSigned-off-by:
-
Minchan Kim authored
There is no user of the return value from rmap_walk() and friends so this patch makes them void-returning functions. Link: http://lkml.kernel.org/r/1489555493-14659-9-git-send-email-minchan@kernel.orgSigned-off-by:
-
Minchan Kim authored
try_to_unmap() returns SWAP_SUCCESS or SWAP_FAIL so it's suitable for boolean return. This patch changes it. Link: http://lkml.kernel.org/r/1489555493-14659-8-git-send-email-minchan@kernel.orgSigned-off-by:
-
Minchan Kim authored
In 2002, [1] introduced SWAP_AGAIN. At that time, try_to_unmap_one used spin_trylock(&mm->page_table_lock) so it's really easy to contend and fail to hold a lock so SWAP_AGAIN to keep LRU status makes sense. However, now we changed it to mutex-based lock and be able to block without skip pte so there is few of small window to return SWAP_AGAIN so remove SWAP_AGAIN and just return SWAP_FAIL. [1] c48c43e, minimal rmap Link: http://lkml.kernel.org/r/1489555493-14659-7-git-send-email-minchan@kernel.orgSigned-off-by:
-
Minchan Kim authored
ttu doesn't need to return SWAP_MLOCK. Instead, just return SWAP_FAIL because it means the page is not-swappable so it should move to another LRU list(active or unevictable). putback friends will move it to right list depending on the page's LRU flag. Link: http://lkml.kernel.org/r/1489555493-14659-6-git-send-email-minchan@kernel.orgSigned-off-by:
-
Minchan Kim authored
try_to_munlock returns SWAP_MLOCK if the one of VMAs mapped the page has VM_LOCKED flag. In that time, VM set PG_mlocked to the page if the page is not pte-mapped THP which cannot be mlocked, either. With that, __munlock_isolated_page can use PageMlocked to check whether try_to_munlock is successful or not without relying on try_to_munlock's retval. It helps to make try_to_unmap/try_to_unmap_one simple with upcoming patches. [minchan@kernel.org: remove PG_Mlocked VM_BUG_ON check] Link: http://lkml.kernel.org/r/20170411025615.GA6545@bbox Link: http://lkml.kernel.org/r/1489555493-14659-5-git-send-email-minchan@kernel.orgSigned-off-by:
Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by:
Vlastimil Babka <vbabka@suse.cz> Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com> Cc: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Sasha Levin <alexander.levin@verizon.com> Signed-off-by:
-
Minchan Kim authored
If the page is mapped and rescue in try_to_unmap_one, the page_mapcount() of a page cannot be zero, so the page_mapcount check in try_to_unmap is enough to return SWAP_SUCCESS. IOW, SWAP_MLOCK check is redundant so remove it. Link: http://lkml.kernel.org/r/1489555493-14659-4-git-send-email-minchan@kernel.orgSigned-off-by:
-
Minchan Kim authored
If we found lazyfree page is dirty, try_to_unmap_one can just SetPageSwapBakced in there like PG_mlocked page and just return with SWAP_FAIL which is very natural because the page is not swappable right now so that vmscan can activate it. There is no point to introduce new return value SWAP_DIRTY in try_to_unmap at the moment. Link: http://lkml.kernel.org/r/1489555493-14659-3-git-send-email-minchan@kernel.orgSigned-off-by:
Hillf Danton <hillf.zj@alibaba-inc.com> Acked-by:
-
Minchan Kim authored
Nobody uses ret variable. Remove it. Link: http://lkml.kernel.org/r/1489555493-14659-2-git-send-email-minchan@kernel.orgSigned-off-by:
-
Yisheng Xie authored
By reviewing code, I find that when enter do_try_to_free_pages, the may_thrash is always clear, and it will retry shrink zones to tap cgroup's reserves memory by setting may_thrash when the former shrink_zones reclaim nothing. However, when memcg is disabled or on legacy hierarchy, or there do not have any memcg protected by low limit, it should not do this useless retry at all, for we do not have any cgroup's reserves memory to tap, and we have already done hard work but made no progress, which as Michal pointed out in former version, we are trying hard to control the retry logical of page alloctor, and the current additional round of reclaim is just lame. Therefore, to avoid this unneeded retrying and make code more readable, we remove the may_thrash field in scan_control, instead, introduce memcg_low_reclaim and memcg_low_skipped, and only retry when memcg_low_skipped, by setting memcg_low_reclaim. [xieyisheng1@huawei.com: remove may_thrash field, introduce mem_cgroup_reclaim] Link: http://lkml.kernel.org/r/1490191893-5923-1-git-send-email-ysxie@foxmail.com Link: http://lkml.kernel.org/r/1490191893-5923-1-git-send-email-ysxie@foxmail.comSigned-off-by:
Yisheng Xie <xieyisheng1@huawei.com> Acked-by:
Michal Hocko <mhocko@kernel.org> Suggested-by:
Shakeel Butt <shakeelb@google.com> Reviewed-by:
-
Yisheng Xie authored
By reviewing code, I find that if the migrate target is a large free page and we ignore suitable, it may splite large target free page into smaller block which is not good for defrag. So move the ignore block suitable after check large free page. As Vlastimil pointed out in RFC version that this patch is just based on logical analyses which might be better for future-proofing the function and it is most likely won't have any visible effect right now, for direct compaction shouldn't have to be called if there's a >=pageblock_order page already available. Link: http://lkml.kernel.org/r/1489490743-5364-1-git-send-email-xieyisheng1@huawei.comSigned-off-by:
-
Wei Yang authored
The current implementation calculates usemap_size in two steps: * calculate number of bytes to cover these bits * calculate number of "unsigned long" to cover these bytes It would be more clear by: * calculate number of "unsigned long" to cover these bits * multiple it with sizeof(unsigned long) This patch refine usemap_size() a little to make it more easy to understand. Link: http://lkml.kernel.org/r/20170310043713.96871-1-richard.weiyang@gmail.comSigned-off-by:Wei Yang <richard.weiyang@gmail.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by:
-
Johannes Weiner authored
__GFP_NOWARN, which is usually added to avoid warnings from callsites that expect to fail and have fallbacks, currently also suppresses allocation stall warnings. These trigger when an allocation is stuck inside the allocator for 10 seconds or longer. But there is no class of allocations that can get legitimately stuck in the allocator for this long. This always indicates a problem. Always emit stall warnings. Restrict __GFP_NOWARN to alloc failures. Link: http://lkml.kernel.org/r/20170125181150.GA16398@cmpxchg.orgSigned-off-by:
-
Mel Gorman authored
kswapd is woken to reclaim a node based on a failed allocation request from any eligible zone. Once reclaiming in balance_pgdat(), it will continue reclaiming until there is an eligible zone available for the zone it was woken for. kswapd tracks what zone it was recently woken for in pgdat->kswapd_classzone_idx. If it has not been woken recently, this zone will be 0. However, the decision on whether to sleep is made on kswapd_classzone_idx which is 0 without a recent wakeup request and that classzone does not account for lowmem reserves. This allows kswapd to sleep when a low small zone such as ZONE_DMA is balanced for a GFP_DMA request even if a stream of allocations cannot use that zone. While kswapd may be woken again shortly in the near future there are two consequences -- the pgdat bits that control congestion are cleared prematurely and direct reclaim is more likely as kswapd slept prematurely. This patch flips kswapd_classzone_idx to default to MAX_NR_ZONES (an invalid index) when there has been no recent wakeups. If there are no wakeups, it'll decide whether to sleep based on the highest possible zone available (MAX_NR_ZONES - 1). It then becomes critical that the "pgdat balanced" decisions during reclaim and when deciding to sleep are the same. If there is a mismatch, kswapd can stay awake continually trying to balance tiny zones. simoop was used to evaluate it again. Two of the preparation patches regressed the workload so they are included as the second set of results. Otherwise this patch looks artifically excellent 4.11.0-rc1 4.11.0-rc1 4.11.0-rc1 vanilla clear-v2 keepawake-v2 Amean p50-Read 21670074.18 ( 0.00%) 19786774.76 ( 8.69%) 22668332.52 ( -4.61%) Amean p95-Read 25456267.64 ( 0.00%) 24101956.27 ( 5.32%) 26738688.00 ( -5.04%) Amean p99-Read 29369064.73 ( 0.00%) 27691872.71 ( 5.71%) 30991404.52 ( -5.52%) Amean p50-Write 1390.30 ( 0.00%) 1011.91 ( 27.22%) 924.91 ( 33.47%) Amean p95-Write 412901.57 ( 0.00%) 34874.98 ( 91.55%) 1362.62 ( 99.67%) Amean p99-Write 6668722.09 ( 0.00%) 575449.60 ( 91.37%) 16854.04 ( 99.75%) Amean p50-Allocation 78714.31 ( 0.00%) 84246.26 ( -7.03%) 74729.74 ( 5.06%) Amean p95-Allocation 175533.51 ( 0.00%) 400058.43 (-127.91%) 101609.74 ( 42.11%) Amean p99-Allocation 247003.02 ( 0.00%) 10905600.00 (-4315.17%) 125765.57 ( 49.08%) With this patch on top, write and allocation latencies are massively improved. The read latencies are slightly impaired but it's worth noting that this is mostly due to the IO scheduler and not directly related to reclaim. The vmstats are a bit of a mix but the relevant ones are as follows; 4.10.0-rc7 4.10.0-rc7 4.10.0-rc7 mmots-20170209 clear-v1r25keepawake-v1r25 Swap Ins 0 0 0 Swap Outs 0 608 0 Direct pages scanned 6910672 3132699 6357298 Kswapd pages scanned 57036946 82488665 56986286 Kswapd pages reclaimed 55993488 63474329 55939113 Direct pages reclaimed 6905990 2964843 6352115 Kswapd efficiency 98% 76% 98% Kswapd velocity 12494.375 17597.507 12488.065 Direct efficiency 99% 94% 99% Direct velocity 1513.835 668.306 1393.148 Page writes by reclaim 0.000 4410243.000 0.000 Page writes file 0 4409635 0 Page writes anon 0 608 0 Page reclaim immediate 1036792 14175203 1042571 4.11.0-rc1 4.11.0-rc1 4.11.0-rc1 vanilla clear-v2 keepawake-v2 Swap Ins 0 12 0 Swap Outs 0 838 0 Direct pages scanned 6579706 3237270 6256811 Kswapd pages scanned 61853702 79961486 54837791 Kswapd pages reclaimed 60768764 60755788 53849586 Direct pages reclaimed 6579055 2987453 6256151 Kswapd efficiency 98% 75% 98% Page writes by reclaim 0.000 4389496.000 0.000 Page writes file 0 4388658 0 Page writes anon 0 838 0 Page reclaim immediate 1073573 14473009 982507 Swap-outs are equivalent to baseline. Direct reclaim is reduced but not eliminated. It's worth noting that there are two periods of direct reclaim for this workload. The first is when it switches from preparing the files for the actual test itself. It's a lot of file IO followed by a lot of allocs that reclaims heavily for a brief window. While direct reclaim is lower with clear-v2, it is due to kswapd scanning aggressively and trying to reclaim the world which is not the right thing to do. With the patches applied, there is still direct reclaim but the phase change from "creating work files" to starting multiple threads that allocate a lot of anonymous memory faster than kswapd can reclaim. Scanning/reclaim efficiency is restored by this patch. Page writes from reclaim context are back at 0 which is ideal. Pages immediately reclaimed after IO completes is slightly improved but it is expected this will vary slightly. On UMA, there is almost no change so this is not expected to be a universal win. [mgorman@suse.de: fix ->kswapd_classzone_idx initialization] Link: http://lkml.kernel.org/r/20170406174538.5msrznj6nt6qpbx5@suse.de Link: http://lkml.kernel.org/r/20170309075657.25121-4-mgorman@techsingularity.netSigned-off-by:Mel Gorman <mgorman@techsingularity.net> Acked-by:
-
Mel Gorman authored
A pgdat tracks if recent reclaim encountered too many dirty, writeback or congested pages. The flags control whether kswapd writes pages back from reclaim context, tags pages for immediate reclaim when IO completes, whether processes block on wait_iff_congested and whether kswapd blocks when too many pages marked for immediate reclaim are encountered. The state is cleared in a check function with side-effects. With the patch "mm, vmscan: fix zone balance check in prepare_kswapd_sleep", the timing of when the bits get cleared changed. Due to the way the check works, it'll clear the bits if ZONE_DMA is balanced for a GFP_DMA allocation because it does not account for lowmem reserves properly. For the simoop workload, kswapd is not stalling when it should due to the premature clearing, writing pages from reclaim context like crazy and generally being unhelpful. This patch resets the pgdat bits related to page reclaim only when kswapd is going to sleep. The comparison with simoop is then 4.11.0-rc1 4.11.0-rc1 4.11.0-rc1 vanilla fixcheck-v2 clear-v2 Amean p50-Read 21670074.18 ( 0.00%) 20464344.18 ( 5.56%) 19786774.76 ( 8.69%) Amean p95-Read 25456267.64 ( 0.00%) 25721423.64 ( -1.04%) 24101956.27 ( 5.32%) Amean p99-Read 29369064.73 ( 0.00%) 30174230.76 ( -2.74%) 27691872.71 ( 5.71%) Amean p50-Write 1390.30 ( 0.00%) 1395.28 ( -0.36%) 1011.91 ( 27.22%) Amean p95-Write 412901.57 ( 0.00%) 37737.74 ( 90.86%) 34874.98 ( 91.55%) Amean p99-Write 6668722.09 ( 0.00%) 666489.04 ( 90.01%) 575449.60 ( 91.37%) Amean p50-Allocation 78714.31 ( 0.00%) 86286.22 ( -9.62%) 84246.26 ( -7.03%) Amean p95-Allocation 175533.51 ( 0.00%) 351812.27 (-100.42%) 400058.43 (-127.91%) Amean p99-Allocation 247003.02 ( 0.00%) 6291171.56 (-2447.00%) 10905600.00 (-4315.17%) Read latency is improved, write latency is mostly improved but allocation latency is regressed. kswapd is still reclaiming inefficiently, pages are being written back from writeback context and a host of other issues. However, given the change, it needed to be spelled out why the side-effect was moved. Link: http://lkml.kernel.org/r/20170309075657.25121-3-mgorman@techsingularity.netSigned-off-by: -
Shantanu Goel authored
Patch series "Reduce amount of time kswapd sleeps prematurely", v2. The series is unusual in that the first patch fixes one problem and introduces other issues that are noted in the changelog. Patch 2 makes a minor modification that is worth considering on its own but leaves the kernel in a state where it behaves badly. It's not until patch 3 that there is an improvement against baseline. This was mostly motivated by examining Chris Mason's "simoop" benchmark which puts the VM under similar pressure to HADOOP. It has been reported that the benchmark has regressed severely during the last number of releases. While I cannot reproduce all the same problems Chris experienced due to hardware limitations, there was a number of problems on a 2-socket machine with a single disk. simoop latencies 4.11.0-rc1 4.11.0-rc1 vanilla keepawake-v2 Amean p50-Read 21670074.18 ( 0.00%) 22668332.52 ( -4.61%) Amean p95-Read 25456267.64 ( 0.00%) 26738688.00 ( -5.04%) Amean p99-Read 29369064.73 ( 0.00%) 30991404.52 ( -5.52%) Amean p50-Write 1390.30 ( 0.00%) 924.91 ( 33.47%) Amean p95-Write 412901.57 ( 0.00%) 1362.62 ( 99.67%) Amean p99-Write 6668722.09 ( 0.00%) 16854.04 ( 99.75%) Amean p50-Allocation 78714.31 ( 0.00%) 74729.74 ( 5.06%) Amean p95-Allocation 175533.51 ( 0.00%) 101609.74 ( 42.11%) Amean p99-Allocation 247003.02 ( 0.00%) 125765.57 ( 49.08%) These are latencies. Read/write are threads reading fixed-size random blocks from a simulated database. The allocation latency is mmaping and faulting regions of memory. The p50, 95 and p99 reports the worst latencies for 50% of the samples, 95% and 99% respectively. For example, the report indicates that while the test was running 99% of writes completed 99.75% faster. It's worth noting that on a UMA machine that no difference in performance with simoop was observed so milage will vary. It's noted that there is a slight impact to read latencies but it's mostly due to IO scheduler decisions and offset by the large reduction in other latencies. This patch (of 3): The check in prepare_kswapd_sleep needs to match the one in balance_pgdat since the latter will return as soon as any one of the zones in the classzone is above the watermark. This is specially important for higher order allocations since balance_pgdat will typically reset the order to zero relying on compaction to create the higher order pages. Without this patch, prepare_kswapd_sleep fails to wake up kcompactd since the zone balance check fails. It was first reported against 4.9.7 that kswapd is failing to wake up kcompactd due to a mismatch in the zone balance check between balance_pgdat() and prepare_kswapd_sleep(). balance_pgdat() returns as soon as a single zone satisfies the allocation but prepare_kswapd_sleep() requires all zones to do +the same. This causes prepare_kswapd_sleep() to never succeed except in the order == 0 case and consequently, wakeup_kcompactd() is never called. For the machine that originally motivated this patch, the state of compaction from /proc/vmstat looked this way after a day and a half +of uptime: compact_migrate_scanned 240496 compact_free_scanned 76238632 compact_isolated 123472 compact_stall 1791 compact_fail 29 compact_success 1762 compact_daemon_wake 0 After applying the patch and about 10 hours of uptime the state looks like this: compact_migrate_scanned 59927299 compact_free_scanned 2021075136 compact_isolated 640926 compact_stall 4 compact_fail 2 compact_success 2 compact_daemon_wake 5160 Further notes from Mel that motivated him to pick this patch up and resend it; It was observed for the simoop workload (pressures the VM similar to HADOOP) that kswapd was failing to keep ahead of direct reclaim. The investigation noted that there was a need to rationalise kswapd decisions to reclaim with kswapd decisions to sleep. With this patch on a 2-socket box, there was a 49% reduction in direct reclaim scanning. However, the impact otherwise is extremely negative. Kswapd reclaim efficiency dropped from 98% to 76%. simoop has three latency-related metrics for read, write and allocation (an anonymous mmap and fault). 4.11.0-rc1 4.11.0-rc1 vanilla fixcheck-v2 Amean p50-Read 21670074.18 ( 0.00%) 20464344.18 ( 5.56%) Amean p95-Read 25456267.64 ( 0.00%) 25721423.64 ( -1.04%) Amean p99-Read 29369064.73 ( 0.00%) 30174230.76 ( -2.74%) Amean p50-Write 1390.30 ( 0.00%) 1395.28 ( -0.36%) Amean p95-Write 412901.57 ( 0.00%) 37737.74 ( 90.86%) Amean p99-Write 6668722.09 ( 0.00%) 666489.04 ( 90.01%) Amean p50-Allocation 78714.31 ( 0.00%) 86286.22 ( -9.62%) Amean p95-Allocation 175533.51 ( 0.00%) 351812.27 (-100.42%) Amean p99-Allocation 247003.02 ( 0.00%) 6291171.56 (-2447.00%) Of greater concern is that the patch causes swapping and page writes from kswapd context rose from 0 pages to 4189753 pages during the hour the workload ran for. By and large, the patch has very bad behaviour but easily missed as the impact on a UMA machine is negligible. This patch is included with the data in case a bisection leads to this area. This patch is also a pre-requisite for the rest of the series. Link: http://lkml.kernel.org/r/20170309075657.25121-2-mgorman@techsingularity.netSigned-off-by:Shantanu Goel <sgoel01@yahoo.com> Signed-off-by:
-
Minchan Kim authored
With the discussion[1], I found it seems there are every PageFlags functions return bool at this moment so we don't need double negation any more. Although it's not a problem to keep it, it makes future users confused to use double negation for them, too. Remove such possibility. [1] https://marc.info/?l=linux-kernel&m=148881578820434 Frankly sepaking, I like every PageFlags to return bool instead of int. It will make it clear. AFAIR, Chen Gang had tried it but don't know why it was not merged at that time. http://lkml.kernel.org/r/1469336184-1904-1-git-send-email-chengang@emindsoft.com.cn Link: http://lkml.kernel.org/r/1488868597-32222-1-git-send-email-minchan@kernel.orgSigned-off-by:
-
Kees Cook authored
Since commit 3ad38ceb ("x86/mm: Remove CONFIG_DEBUG_NX_TEST"), nothing is using the exported rodata_test_data variable, so drop the export. This additionally updates the pr_fmt to avoid redundant strings and adjusts some whitespace. Link: http://lkml.kernel.org/r/20170307005313.GA85809@beastSigned-off-by:
Kees Cook <keescook@chromium.org> Cc: Jinbum Park <jinb.park7@gmail.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by:
-
Matthew Wilcox authored
The round_up() macro generates a couple of unnecessary instructions in this usage: 48cd: 49 8b 47 50 mov 0x50(%r15),%rax 48d1: 48 83 e8 01 sub $0x1,%rax 48d5: 48 0d ff 0f 00 00 or $0xfff,%rax 48db: 48 83 c0 01 add $0x1,%rax 48df: 48 c1 f8 0c sar $0xc,%rax 48e3: 48 39 c3 cmp %rax,%rbx 48e6: 72 2e jb 4916 <filemap_fault+0x96> If we change round_up() to ((x) + __round_mask(x, y)) & ~__round_mask(x, y) then GCC can see through it and remove the mask (because that would be dead code given the subsequent shift): 48cd: 49 8b 47 50 mov 0x50(%r15),%rax 48d1: 48 05 ff 0f 00 00 add $0xfff,%rax 48d7: 48 c1 e8 0c shr $0xc,%rax 48db: 48 39 c3 cmp %rax,%rbx 48de: 72 2e jb 490e <filemap_fault+0x8e> But that's problematic because we'd evaluate 'y' twice. Converting round_up into an inline function prevents it from being used in other definitions. The easiest thing to do is just change these three usages of round_up to use DIV_ROUND_UP. Also add an unlikely() because GCC's heuristic is wrong in this case. Link: http://lkml.kernel.org/r/20170207192812.5281-1-willy@infradead.orgSigned-off-by: -
Michal Hocko authored
kjournald2 is central to the transaction commit processing. As such any potential allocation from this kernel thread has to be GFP_NOFS. Make sure to mark the whole kernel thread GFP_NOFS by the memalloc_nofs_save. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/20170306131408.9828-8-mhocko@kernel.orgSigned-off-by:
Jan Kara <jack@suse.cz> Reviewed-by:
-
Michal Hocko authored
now that we have memalloc_nofs_{save,restore} api we can mark the whole transaction context as implicitly GFP_NOFS. All allocations will automatically inherit GFP_NOFS this way. This means that we do not have to mark any of those requests with GFP_NOFS and moreover all the ext4_kv[mz]alloc(GFP_NOFS) are also safe now because even the hardcoded GFP_KERNEL allocations deep inside the vmalloc will be NOFS now. [akpm@linux-foundation.org: tweak comments] Link: http://lkml.kernel.org/r/20170306131408.9828-7-mhocko@kernel.orgSigned-off-by: -
Michal Hocko authored
kmem_zalloc_large and _xfs_buf_map_pages use memalloc_noio_{save,restore} API to prevent from reclaim recursion into the fs because vmalloc can invoke unconditional GFP_KERNEL allocations and these functions might be called from the NOFS contexts. The memalloc_noio_save will enforce GFP_NOIO context which is even weaker than GFP_NOFS and that seems to be unnecessary. Let's use memalloc_nofs_{save,restore} instead as it should provide exactly what we need here - implicit GFP_NOFS context. Link: http://lkml.kernel.org/r/20170306131408.9828-6-mhocko@kernel.orgSigned-off-by:Brian Foster <bfoster@redhat.com> Reviewed-by:
Darrick J. Wong <darrick.wong@oracle.com> Acked-by:
-
Michal Hocko authored
GFP_NOFS context is used for the following 5 reasons currently: - to prevent from deadlocks when the lock held by the allocation context would be needed during the memory reclaim - to prevent from stack overflows during the reclaim because the allocation is performed from a deep context already - to prevent lockups when the allocation context depends on other reclaimers to make a forward progress indirectly - just in case because this would be safe from the fs POV - silence lockdep false positives Unfortunately overuse of this allocation context brings some problems to the MM. Memory reclaim is much weaker (especially during heavy FS metadata workloads), OOM killer cannot be invoked because the MM layer doesn't have enough information about how much memory is freeable by the FS layer. In many cases it is far from clear why the weaker context is even used and so it might be used unnecessarily. We would like to get rid of those as much as possible. One way to do that is to use the flag in scopes rather than isolated cases. Such a scope is declared when really necessary, tracked per task and all the allocation requests from within the context will simply inherit the GFP_NOFS semantic. Not only this is easier to understand and maintain because there are much less problematic contexts than specific allocation requests, this also helps code paths where FS layer interacts with other layers (e.g. crypto, security modules, MM etc...) and there is no easy way to convey the allocation context between the layers. Introduce memalloc_nofs_{save,restore} API to control the scope of GFP_NOFS allocation context. This is basically copying memalloc_noio_{save,restore} API we have for other restricted allocation context GFP_NOIO. The PF_MEMALLOC_NOFS flag already exists and it is just an alias for PF_FSTRANS which has been xfs specific until recently. There are no more PF_FSTRANS users anymore so let's just drop it. PF_MEMALLOC_NOFS is now checked in the MM layer and drops __GFP_FS implicitly same as PF_MEMALLOC_NOIO drops __GFP_IO. memalloc_noio_flags is renamed to current_gfp_context because it now cares about both PF_MEMALLOC_NOFS and PF_MEMALLOC_NOIO contexts. Xfs code paths preserve their semantic. kmem_flags_convert() doesn't need to evaluate the flag anymore. This patch shouldn't introduce any functional changes. Let's hope that filesystems will drop direct GFP_NOFS (resp. ~__GFP_FS) usage as much as possible and only use a properly documented memalloc_nofs_{save,restore} checkpoints where they are appropriate. [akpm@linux-foundation.org: fix comment typo, reflow comment] Link: http://lkml.kernel.org/r/20170306131408.9828-5-mhocko@kernel.orgSigned-off-by: -
Michal Hocko authored
xfs has defined PF_FSTRANS to declare a scope GFP_NOFS semantic quite some time ago. We would like to make this concept more generic and use it for other filesystems as well. Let's start by giving the flag a more generic name PF_MEMALLOC_NOFS which is in line with an exiting PF_MEMALLOC_NOIO already used for the same purpose for GFP_NOIO contexts. Replace all PF_FSTRANS usage from the xfs code in the first step before we introduce a full API for it as xfs uses the flag directly anyway. This patch doesn't introduce any functional change. Link: http://lkml.kernel.org/r/20170306131408.9828-4-mhocko@kernel.orgSigned-off-by:
-
Michal Hocko authored
The current implementation of the reclaim lockup detection can lead to false positives and those even happen and usually lead to tweak the code to silence the lockdep by using GFP_NOFS even though the context can use __GFP_FS just fine. See http://lkml.kernel.org/r/20160512080321.GA18496@dastard as an example. ================================= [ INFO: inconsistent lock state ] 4.5.0-rc2+ #4 Tainted: G O --------------------------------- inconsistent {RECLAIM_FS-ON-R} -> {IN-RECLAIM_FS-W} usage. kswapd0/543 [HC0[0]:SC0[0]:HE1:SE1] takes: (&xfs_nondir_ilock_class){++++-+}, at: xfs_ilock+0x177/0x200 [xfs] {RECLAIM_FS-ON-R} state was registered at: mark_held_locks+0x79/0xa0 lockdep_trace_alloc+0xb3/0x100 kmem_cache_alloc+0x33/0x230 kmem_zone_alloc+0x81/0x120 [xfs] xfs_refcountbt_init_cursor+0x3e/0xa0 [xfs] __xfs_refcount_find_shared+0x75/0x580 [xfs] xfs_refcount_find_shared+0x84/0xb0 [xfs] xfs_getbmap+0x608/0x8c0 [xfs] xfs_vn_fiemap+0xab/0xc0 [xfs] do_vfs_ioctl+0x498/0x670 SyS_ioctl+0x79/0x90 entry_SYSCALL_64_fastpath+0x12/0x6f CPU0 ---- lock(&xfs_nondir_ilock_class); <Interrupt> lock(&xfs_nondir_ilock_class); *** DEADLOCK *** 3 locks held by kswapd0/543: stack backtrace: CPU: 0 PID: 543 Comm: kswapd0 Tainted: G O 4.5.0-rc2+ #4 Call Trace: lock_acquire+0xd8/0x1e0 down_write_nested+0x5e/0xc0 xfs_ilock+0x177/0x200 [xfs] xfs_reflink_cancel_cow_range+0x150/0x300 [xfs] xfs_fs_evict_inode+0xdc/0x1e0 [xfs] evict+0xc5/0x190 dispose_list+0x39/0x60 prune_icache_sb+0x4b/0x60 super_cache_scan+0x14f/0x1a0 shrink_slab.part.63.constprop.79+0x1e9/0x4e0 shrink_zone+0x15e/0x170 kswapd+0x4f1/0xa80 kthread+0xf2/0x110 ret_from_fork+0x3f/0x70 To quote Dave: "Ignoring whether reflink should be doing anything or not, that's a "xfs_refcountbt_init_cursor() gets called both outside and inside transactions" lockdep false positive case. The problem here is lockdep has seen this allocation from within a transaction, hence a GFP_NOFS allocation, and now it's seeing it in a GFP_KERNEL context. Also note that we have an active reference to this inode. So, because the reclaim annotations overload the interrupt level detections and it's seen the inode ilock been taken in reclaim ("interrupt") context, this triggers a reclaim context warning where it thinks it is unsafe to do this allocation in GFP_KERNEL context holding the inode ilock..." This sounds like a fundamental problem of the reclaim lock detection. It is really impossible to annotate such a special usecase IMHO unless the reclaim lockup detection is reworked completely. Until then it is much better to provide a way to add "I know what I am doing flag" and mark problematic places. This would prevent from abusing GFP_NOFS flag which has a runtime effect even on configurations which have lockdep disabled. Introduce __GFP_NOLOCKDEP flag which tells the lockdep gfp tracking to skip the current allocation request. While we are at it also make sure that the radix tree doesn't accidentaly override tags stored in the upper part of the gfp_mask. Link: http://lkml.kernel.org/r/20170306131408.9828-3-mhocko@kernel.orgSigned-off-by:
Peter Zijlstra <peterz@infradead.org> Acked-by:
-
Nikolay Borisov authored
Patch series "scope GFP_NOFS api", v5. This patch (of 7): Commit 21caf2fc ("mm: teach mm by current context info to not do I/O during memory allocation") added the memalloc_noio_(save|restore) functions to enable people to modify the MM behavior by disabling I/O during memory allocation. This was further extended in commit 934f3072 ("mm: clear __GFP_FS when PF_MEMALLOC_NOIO is set"). memalloc_noio_* functions prevent allocation paths recursing back into the filesystem without explicitly changing the flags for every allocation site. However, lockdep hasn't been keeping up with the changes and it entirely misses handling the memalloc_noio adjustments. Instead, it is left to the callers of __lockdep_trace_alloc to call the function after they have shaven the respective GFP flags which can lead to false positives: ================================= [ INFO: inconsistent lock state ] 4.10.0-nbor #134 Not tainted --------------------------------- inconsistent {IN-RECLAIM_FS-W} -> {RECLAIM_FS-ON-W} usage. fsstress/3365 [HC0[0]:SC0[0]:HE1:SE1] takes: (&xfs_nondir_ilock_class){++++?.}, at: xfs_ilock+0x141/0x230 {IN-RECLAIM_FS-W} state was registered at: __lock_acquire+0x62a/0x17c0 lock_acquire+0xc5/0x220 down_write_nested+0x4f/0x90 xfs_ilock+0x141/0x230 xfs_reclaim_inode+0x12a/0x320 xfs_reclaim_inodes_ag+0x2c8/0x4e0 xfs_reclaim_inodes_nr+0x33/0x40 xfs_fs_free_cached_objects+0x19/0x20 super_cache_scan+0x191/0x1a0 shrink_slab+0x26f/0x5f0 shrink_node+0xf9/0x2f0 kswapd+0x356/0x920 kthread+0x10c/0x140 ret_from_fork+0x31/0x40 irq event stamp: 173777 hardirqs last enabled at (173777): __local_bh_enable_ip+0x70/0xc0 hardirqs last disabled at (173775): __local_bh_enable_ip+0x37/0xc0 softirqs last enabled at (173776): _xfs_buf_find+0x67a/0xb70 softirqs last disabled at (173774): _xfs_buf_find+0x5db/0xb70 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&xfs_nondir_ilock_class); <Interrupt> lock(&xfs_nondir_ilock_class); *** DEADLOCK *** 4 locks held by fsstress/3365: #0: (sb_writers#10){++++++}, at: mnt_want_write+0x24/0x50 #1: (&sb->s_type->i_mutex_key#12){++++++}, at: vfs_setxattr+0x6f/0xb0 #2: (sb_internal#2){++++++}, at: xfs_trans_alloc+0xfc/0x140 #3: (&xfs_nondir_ilock_class){++++?.}, at: xfs_ilock+0x141/0x230 stack backtrace: CPU: 0 PID: 3365 Comm: fsstress Not tainted 4.10.0-nbor #134 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 Call Trace: kmem_cache_alloc_node_trace+0x3a/0x2c0 vm_map_ram+0x2a1/0x510 _xfs_buf_map_pages+0x77/0x140 xfs_buf_get_map+0x185/0x2a0 xfs_attr_rmtval_set+0x233/0x430 xfs_attr_leaf_addname+0x2d2/0x500 xfs_attr_set+0x214/0x420 xfs_xattr_set+0x59/0xb0 __vfs_setxattr+0x76/0xa0 __vfs_setxattr_noperm+0x5e/0xf0 vfs_setxattr+0xae/0xb0 setxattr+0x15e/0x1a0 path_setxattr+0x8f/0xc0 SyS_lsetxattr+0x11/0x20 entry_SYSCALL_64_fastpath+0x23/0xc6 Let's fix this by making lockdep explicitly do the shaving of respective GFP flags. Fixes: 934f3072 ("mm: clear __GFP_FS when PF_MEMALLOC_NOIO is set") Link: http://lkml.kernel.org/r/20170306131408.9828-2-mhocko@kernel.orgSigned-off-by:
Nikolay Borisov <nborisov@suse.com> Signed-off-by:
-
