- 01 Aug, 2012 37 commits
-
-
David Rientjes authored
commit 89e8a244 upstream. Stable note: Not tracked in Bugzilla. [get|put]_mems_allowed() is extremely expensive and severely impacted page allocator performance. This is part of a series of patches that reduce page allocator overhead. {get,put}_mems_allowed() exist so that general kernel code may locklessly access a task's set of allowable nodes without having the chance that a concurrent write will cause the nodemask to be empty on configurations where MAX_NUMNODES > BITS_PER_LONG. This could incur a significant delay, however, especially in low memory conditions because the page allocator is blocking and reclaim requires get_mems_allowed() itself. It is not atypical to see writes to cpuset.mems take over 2 seconds to complete, for example. In low memory conditions, this is problematic because it's one of the most imporant times to change cpuset.mems in the first place! The only way a task's set of allowable nodes may change is through cpusets by writing to cpuset.mems and when attaching a task to a generic code is not reading the nodemask with get_mems_allowed() at the same time, and then clearing all the old nodes. This prevents the possibility that a reader will see an empty nodemask at the same time the writer is storing a new nodemask. If at least one node remains unchanged, though, it's possible to simply set all new nodes and then clear all the old nodes. Changing a task's nodemask is protected by cgroup_mutex so it's guaranteed that two threads are not changing the same task's nodemask at the same time, so the nodemask is guaranteed to be stored before another thread changes it and determines whether a node remains set or not. Signed-off-by:
David Rientjes <rientjes@google.com> Cc: Miao Xie <miaox@cn.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Paul Menage <paul@paulmenage.org> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by:
Mel Gorman <mgorman@suse.de> Signed-off-by:
Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-
Johannes Weiner authored
commit b95a2f2d upstream - WARNING: this is a substitute patch. Stable note: Not tracked in Bugzilla. This is a partial backport of an upstream commit addressing a completely different issue that accidentally contained an important fix. The workload this patch helps was memcached when IO is started in the background. memcached should stay resident but without this patch it gets swapped. Sometimes this manifests as a drop in throughput but mostly it was observed through /proc/vmstat. Commit [246e87a9: memcg: fix get_scan_count() for small targets] was meant to fix a problem whereby small scan targets on memcg were ignored causing priority to raise too sharply. It forced scanning to take place if the target was small, memcg or kswapd. From the time it was introduced it caused excessive reclaim by kswapd with workloads being pushed to swap that previously would have stayed resident. This was accidentally fixed in commit [b95a2f2d: mm: vmscan: convert global reclaim to per-memcg LRU lists] by making it harder for kswapd to force scan small targets but that patchset is not suitable for backporting. This was later changed again by commit [90126375: mm/vmscan: push lruvec pointer into get_scan_count()] into a format that looks like it would be a straight-forward backport but there is a subtle difference due to the use of lruvecs. The impact of the accidental fix is to make it harder for kswapd to force scan small targets by taking zone->all_unreclaimable into account. This patch is the closest equivalent available based on what is backported. Signed-off-by:
-
Hugh Dickins authored
commit 043bcbe5 upstream. Stable note: Not tracked in Bugzilla. There were reports of shared mapped pages being unfairly reclaimed in comparison to older kernels. This is being addressed over time. Even though the subject refers to lumpy reclaim, it impacts compaction as well. Lumpy reclaim does well to stop at a PageAnon when there's no swap, but better is to stop at any PageSwapBacked, which includes shmem/tmpfs too. Signed-off-by:
Hugh Dickins <hughd@google.com> Reviewed-by:
KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by:
Minchan Kim <minchan@kernel.org> Signed-off-by:
-
Minchan Kim authored
commit 86cfd3a4 upstream. Stable note: Not tracked in Bugzilla. This patch reduces kswapd CPU usage on swapless systems with high anonymous memory usage. It's pointless to continue reclaiming when we have no swap space and lots of anon pages in the inactive list. Without this patch, it is possible when swap is disabled to continue trying to reclaim when there are only anonymous pages in the system even though that will not make any progress. Signed-off-by:
Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <jweiner@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by:
-
Konstantin Khlebnikov authored
commit c909e993 upstream. Stable note: Not tracked in Bugzilla. There were reports of shared mapped pages being unfairly reclaimed in comparison to older kernels. This is being addressed over time. Logic added in commit 8cab4754 ("vmscan: make mapped executable pages the first class citizen") was noticeably weakened in commit 64574746 ("vmscan: detect mapped file pages used only once"). Currently these pages can become "first class citizens" only after second usage. After this patch page_check_references() will activate they after first usage, and executable code gets yet better chance to stay in memory. Signed-off-by:
Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by:
-
Konstantin Khlebnikov authored
commit 34dbc67a upstream. Stable note: Not tracked in Bugzilla. There were reports of shared mapped pages being unfairly reclaimed in comparison to older kernels. This is being addressed over time. The specific workload being addressed here in described in paragraph four and while paragraph five says it did not help performance as such, it made a difference to major page faults. I'm aware of at least one bug for a large vendor that was due to increased major faults. Commit 64574746 ("vmscan: detect mapped file pages used only once") greatly decreases lifetime of single-used mapped file pages. Unfortunately it also decreases life time of all shared mapped file pages. Because after commit bf3f3bc5 ("mm: don't mark_page_accessed in fault path") page-fault handler does not mark page active or even referenced. Thus page_check_references() activates file page only if it was used twice while it stays in inactive list, meanwhile it activates anon pages after first access. Inactive list can be small enough, this way reclaimer can accidentally throw away any widely used page if it wasn't used twice in short period. After this patch page_check_references() also activate file mapped page at first inactive list scan if this page is already used multiple times via several ptes. I found this while trying to fix degragation in rhel6 (~2.6.32) from rhel5 (~2.6.18). There a complete mess with >100 web/mail/spam/ftp containers, they share all their files but there a lot of anonymous pages: ~500mb shared file mapped memory and 15-20Gb non-shared anonymous memory. In this situation major-pagefaults are very costly, because all containers share the same page. In my load kernel created a disproportionate pressure on the file memory, compared with the anonymous, they equaled only if I raise swappiness up to 150 =) These patches actually wasn't helped a lot in my problem, but I saw noticable (10-20 times) reduce in count and average time of major-pagefault in file-mapped areas. Actually both patches are fixes for commit v2.6.33-5448-g64574746, because it was aimed at one scenario (singly used pages), but it breaks the logic in other scenarios (shared and/or executable pages) Signed-off-by:
Pekka Enberg <penberg@kernel.org> Acked-by:
Minchan Kim <minchan.kim@gmail.com> Reviewed-by:
KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Shaohua Li <shaohua.li@intel.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by:
-
Mel Gorman authored
commit 0cee34fd upstream. Stable note: Not tracked on Bugzilla. THP and compaction was found to aggressively reclaim pages and stall systems under different situations that was addressed piecemeal over time. If compaction can proceed for a given zone, shrink_zones() does not reclaim any more pages from it. After commit [e0c23279: vmscan: abort reclaim/compaction if compaction can proceed], do_try_to_free_pages() tries to finish as soon as possible once one zone can compact. This was intended to prevent slabs being shrunk unnecessarily but there are side-effects. One is that a small zone that is ready for compaction will abort reclaim even if the chances of successfully allocating a THP from that zone is small. It also means that reclaim can return too early even though sc->nr_to_reclaim pages were not reclaimed. This partially reverts the commit until it is proven that slabs are really being shrunk unnecessarily but preserves the check to return 1 to avoid OOM if reclaim was aborted prematurely. [aarcange@redhat.com: This patch replaces a revert from Andrea] Signed-off-by:
-
Mel Gorman authored
commit 7335084d upstream. Stable note: Not tracked in Bugzilla. This patch makes later patches easier to apply but otherwise has little to justify it. The problem it fixes was never observed but the source of the theoretical problem did not exist for very long. During direct reclaim it is possible that reclaim will be aborted so that compaction can be attempted to satisfy a high-order allocation. If this decision is made before any pages are reclaimed, it is possible that 0 is returned to the page allocator potentially triggering an OOM. This has not been observed but it is a possibility so this patch addresses it. Signed-off-by:
-
Mel Gorman authored
commit fe4b1b24 upstream. Stable note: Not tracked on Bugzilla. THP and compaction was found to aggressively reclaim pages and stall systems under different situations that was addressed piecemeal over time. This patch addresses a problem where the fix regressed THP allocation success rates. In commit e0887c19 ("vmscan: limit direct reclaim for higher order allocations"), Rik noted that reclaim was too aggressive when THP was enabled. In his initial patch he used the number of free pages to decide if reclaim should abort for compaction. My feedback was that reclaim and compaction should be using the same logic when deciding if reclaim should be aborted. Unfortunately, this had the effect of reducing THP success rates when the workload included something like streaming reads that continually allocated pages. The window during which compaction could run and return a THP was too small. This patch combines Rik's two patches together. compaction_suitable() is still used to decide if reclaim should be aborted to allow compaction is used. However, it will also ensure that there is a reasonable buffer of free pages available. This improves upon the THP allocation success rates but bounds the number of pages that are freed for compaction. Signed-off-by:
-
Mel Gorman authored
commit a6bc32b8 upstream. Stable note: Not tracked in Buzilla. This was part of a series that reduced interactivity stalls experienced when THP was enabled. These stalls were particularly noticable when copying data to a USB stick but the experiences for users varied a lot. This patch adds a lightweight sync migrate operation MIGRATE_SYNC_LIGHT mode that avoids writing back pages to backing storage. Async compaction maps to MIGRATE_ASYNC while sync compaction maps to MIGRATE_SYNC_LIGHT. For other migrate_pages users such as memory hotplug, MIGRATE_SYNC is used. This avoids sync compaction stalling for an excessive length of time, particularly when copying files to a USB stick where there might be a large number of dirty pages backed by a filesystem that does not support ->writepages. [aarcange@redhat.com: This patch is heavily based on Andrea's work] [akpm@linux-foundation.org: fix fs/nfs/write.c build] [akpm@linux-foundation.org: fix fs/btrfs/disk-io.c build] Signed-off-by:
-
Alex Shi authored
commit f0dfcde0 upstream. Stable note: Fixes https://bugzilla.redhat.com/show_bug.cgi?id=712019. This patch reduces kswapd CPU usage. There 2 places to read pgdat in kswapd. One is return from a successful balance, another is waked up from kswapd sleeping. The new_order and new_classzone_idx represent the balance input order and classzone_idx. But current new_order and new_classzone_idx are not assigned after kswapd_try_to_sleep(), that will cause a bug in the following scenario. 1: after a successful balance, kswapd goes to sleep, and new_order = 0; new_classzone_idx = __MAX_NR_ZONES - 1; 2: kswapd waked up with order = 3 and classzone_idx = ZONE_NORMAL 3: in the balance_pgdat() running, a new balance wakeup happened with order = 5, and classzone_idx = ZONE_NORMAL 4: the first wakeup(order = 3) finished successufly, return order = 3 but, the new_order is still 0, so, this balancing will be treated as a failed balance. And then the second tighter balancing will be missed. So, to avoid the above problem, the new_order and new_classzone_idx need to be assigned for later successful comparison. Signed-off-by:
Alex Shi <alex.shi@intel.com> Acked-by:
Pádraig Brady <P@draigBrady.com> Signed-off-by:
-
Alex Shi authored
commit d2ebd0f6 upstream. Stable note: Fixes https://bugzilla.redhat.com/show_bug.cgi?id=712019. This patch reduces kswapd CPU usage. In commit 215ddd66 ("mm: vmscan: only read new_classzone_idx from pgdat when reclaiming successfully") , Mel Gorman said kswapd is better to sleep after a unsuccessful balancing if there is tighter reclaim request pending in the balancing. But in the following scenario, kswapd do something that is not matched our expectation. The patch fixes this issue. 1, Read pgdat request A (classzone_idx, order = 3) 2, balance_pgdat() 3, During pgdat, a new pgdat request B (classzone_idx, order = 5) is placed 4, balance_pgdat() returns but failed since returned order = 0 5, pgdat of request A assigned to balance_pgdat(), and do balancing again. While the expectation behavior of kswapd should try to sleep. Signed-off-by:
Tim Chen <tim.c.chen@linux.intel.com> Acked-by:
-
Mel Gorman authored
commit c8244935 upstream. Stable note: Not tracked in Bugzilla. A fix aimed at preserving page aging information by reducing LRU list churning had the side-effect of reducing THP allocation success rates. This was part of a series to restore the success rates while preserving the reclaim fix. Commit 39deaf85 ("mm: compaction: make isolate_lru_page() filter-aware") noted that compaction does not migrate dirty or writeback pages and that is was meaningless to pick the page and re-add it to the LRU list. This had to be partially reverted because some dirty pages can be migrated by compaction without blocking. This patch updates "mm: compaction: make isolate_lru_page" by skipping over pages that migration has no possibility of migrating to minimise LRU disruption. Signed-off-by:
-
Mel Gorman authored
commit 66199712 upstream. Stable note: Not tracked in Buzilla. This was part of a series that reduced interactivity stalls experienced when THP was enabled. If compaction is deferred, direct reclaim is used to try to free enough pages for the allocation to succeed. For small high-orders, this has a reasonable chance of success. However, if the caller has specified __GFP_NO_KSWAPD to limit the disruption to the system, it makes more sense to fail the allocation rather than stall the caller in direct reclaim. This patch skips direct reclaim if compaction is deferred and the caller specifies __GFP_NO_KSWAPD. Async compaction only considers a subset of pages so it is possible for compaction to be deferred prematurely and not enter direct reclaim even in cases where it should. To compensate for this, this patch also defers compaction only if sync compaction failed. Signed-off-by:
-
Mel Gorman authored
commit b969c4ab upstream. Stable note: Not tracked in Bugzilla. A fix aimed at preserving page aging information by reducing LRU list churning had the side-effect of reducing THP allocation success rates. This was part of a series to restore the success rates while preserving the reclaim fix. Asynchronous compaction is used when allocating transparent hugepages to avoid blocking for long periods of time. Due to reports of stalling, there was a debate on disabling synchronous compaction but this severely impacted allocation success rates. Part of the reason was that many dirty pages are skipped in asynchronous compaction by the following check; if (PageDirty(page) && !sync && mapping->a_ops->migratepage != migrate_page) rc = -EBUSY; This skips over all mapping aops using buffer_migrate_page() even though it is possible to migrate some of these pages without blocking. This patch updates the ->migratepage callback with a "sync" parameter. It is the responsibility of the callback to fail gracefully if migration would block. Signed-off-by:
-
Mel Gorman authored
commit a77ebd33 upstream. Stable note: Not tracked in Bugzilla. A fix aimed at preserving page aging information by reducing LRU list churning had the side-effect of reducing THP allocation success rates. This was part of a series to restore the success rates while preserving the reclaim fix. Short summary: There are severe stalls when a USB stick using VFAT is used with THP enabled that are reduced by this series. If you are experiencing this problem, please test and report back and considering I have seen complaints from openSUSE and Fedora users on this as well as a few private mails, I'm guessing it's a widespread issue. This is a new type of USB-related stall because it is due to synchronous compaction writing where as in the past the big problem was dirty pages reaching the end of the LRU and being written by reclaim. Am cc'ing Andrew this time and this series would replace mm-do-not-stall-in-synchronous-compaction-for-thp-allocations.patch. I'm also cc'ing Dave Jones as he might have merged that patch to Fedora for wider testing and ideally it would be reverted and replaced by this series. That said, the later patches could really do with some review. If this series is not the answer then a new direction needs to be discussed because as it is, the stalls are unacceptable as the results in this leader show. For testers that try backporting this to 3.1, it won't work because there is a non-obvious dependency on not writing back pages in direct reclaim so you need those patches too. Changelog since V5 o Rebase to 3.2-rc5 o Tidy up the changelogs a bit Changelog since V4 o Added reviewed-bys, credited Andrea properly for sync-light o Allow dirty pages without mappings to be considered for migration o Bound the number of pages freed for compaction o Isolate PageReclaim pages on their own LRU list This is against 3.2-rc5 and follows on from discussions on "mm: Do not stall in synchronous compaction for THP allocations" and "[RFC PATCH 0/5] Reduce compaction-related stalls". Initially, the proposed patch eliminated stalls due to compaction which sometimes resulted in user-visible interactivity problems on browsers by simply never using sync compaction. The downside was that THP success allocation rates were lower because dirty pages were not being migrated as reported by Andrea. His approach at fixing this was nacked on the grounds that it reverted fixes from Rik merged that reduced the amount of pages reclaimed as it severely impacted his workloads performance. This series attempts to reconcile the requirements of maximising THP usage, without stalling in a user-visible fashion due to compaction or cheating by reclaiming an excessive number of pages. Patch 1 partially reverts commit 39deaf85 to allow migration to isolate dirty pages. This is because migration can move some dirty pages without blocking. Patch 2 notes that the /proc/sys/vm/compact_memory handler is not using synchronous compaction when it should be. This is unrelated to the reported stalls but is worth fixing. Patch 3 checks if we isolated a compound page during lumpy scan and account for it properly. For the most part, this affects tracing so it's unrelated to the stalls but worth fixing. Patch 4 notes that it is possible to abort reclaim early for compaction and return 0 to the page allocator potentially entering the "may oom" path. This has not been observed in practice but the rest of the series potentially makes it easier to happen. Patch 5 adds a sync parameter to the migratepage callback and gives the callback responsibility for migrating the page without blocking if sync==false. For example, fallback_migrate_page will not call writepage if sync==false. This increases the number of pages that can be handled by asynchronous compaction thereby reducing stalls. Patch 6 restores filter-awareness to isolate_lru_page for migration. In practice, it means that pages under writeback and pages without a ->migratepage callback will not be isolated for migration. Patch 7 avoids calling direct reclaim if compaction is deferred but makes sure that compaction is only deferred if sync compaction was used. Patch 8 introduces a sync-light migration mechanism that sync compaction uses. The objective is to allow some stalls but to not call ->writepage which can lead to significant user-visible stalls. Patch 9 notes that while we want to abort reclaim ASAP to allow compation to go ahead that we leave a very small window of opportunity for compaction to run. This patch allows more pages to be freed by reclaim but bounds the number to a reasonable level based on the high watermark on each zone. Patch 10 allows slabs to be shrunk even after compaction_ready() is true for one zone. This is to avoid a problem whereby a single small zone can abort reclaim even though no pages have been reclaimed and no suitably large zone is in a usable state. Patch 11 fixes a problem with the rate of page scanning. As reclaim is rarely stalling on pages under writeback it means that scan rates are very high. This is particularly true for direct reclaim which is not calling writepage. The vmstat figures implied that much of this was busy work with PageReclaim pages marked for immediate reclaim. This patch is a prototype that moves these pages to their own LRU list. This has been tested and other than 2 USB keys getting trashed, nothing horrible fell out. That said, I am a bit unhappy with the rescue logic in patch 11 but did not find a better way around it. It does significantly reduce scan rates and System CPU time indicating it is the right direction to take. What is of critical importance is that stalls due to compaction are massively reduced even though sync compaction was still allowed. Testing from people complaining about stalls copying to USBs with THP enabled are particularly welcome. The following tests all involve THP usage and USB keys in some way. Each test follows this type of pattern 1. Read from some fast fast storage, be it raw device or file. Each time the copy finishes, start again until the test ends 2. Write a large file to a filesystem on a USB stick. Each time the copy finishes, start again until the test ends 3. When memory is low, start an alloc process that creates a mapping the size of physical memory to stress THP allocation. This is the "real" part of the test and the part that is meant to trigger stalls when THP is enabled. Copying continues in the background. 4. Record the CPU usage and time to execute of the alloc process 5. Record the number of THP allocs and fallbacks as well as the number of THP pages in use a the end of the test just before alloc exited 6. Run the test 5 times to get an idea of variability 7. Between each run, sync is run and caches dropped and the test waits until nr_dirty is a small number to avoid interference or caching between iterations that would skew the figures. The individual tests were then writebackCPDeviceBasevfat Disable THP, read from a raw device (sda), vfat on USB stick writebackCPDeviceBaseext4 Disable THP, read from a raw device (sda), ext4 on USB stick writebackCPDevicevfat THP enabled, read from a raw device (sda), vfat on USB stick writebackCPDeviceext4 THP enabled, read from a raw device (sda), ext4 on USB stick writebackCPFilevfat THP enabled, read from a file on fast storage and USB, both vfat writebackCPFileext4 THP enabled, read from a file on fast storage and USB, both ext4 The kernels tested were 3.1 3.1 vanilla 3.2-rc5 freemore Patches 1-10 immediate Patches 1-11 andrea The 8 patches Andrea posted as a basis of comparison The results are very long unfortunately. I'll start with the case where we are not using THP at all writebackCPDeviceBasevfat 3.1.0-vanilla rc5-vanilla freemore-v6r1 isolate-v6r1 andrea-v2r1 System Time 1.28 ( 0.00%) 54.49 (-4143.46%) 48.63 (-3687.69%) 4.69 ( -265.11%) 51.88 (-3940.81%) +/- 0.06 ( 0.00%) 2.45 (-4305.55%) 4.75 (-8430.57%) 7.46 (-13282.76%) 4.76 (-8440.70%) User Time 0.09 ( 0.00%) 0.05 ( 40.91%) 0.06 ( 29.55%) 0.07 ( 15.91%) 0.06 ( 27.27%) +/- 0.02 ( 0.00%) 0.01 ( 45.39%) 0.02 ( 25.07%) 0.00 ( 77.06%) 0.01 ( 52.24%) Elapsed Time 110.27 ( 0.00%) 56.38 ( 48.87%) 49.95 ( 54.70%) 11.77 ( 89.33%) 53.43 ( 51.54%) +/- 7.33 ( 0.00%) 3.77 ( 48.61%) 4.94 ( 32.63%) 6.71 ( 8.50%) 4.76 ( 35.03%) THP Active 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) +/- 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) Fault Alloc 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) +/- 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) Fault Fallback 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) +/- 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) The THP figures are obviously all 0 because THP was enabled. The main thing to watch is the elapsed times and how they compare to times when THP is enabled later. It's also important to note that elapsed time is improved by this series as System CPu time is much reduced. writebackCPDevicevfat 3.1.0-vanilla rc5-vanilla freemore-v6r1 isolate-v6r1 andrea-v2r1 System Time 1.22 ( 0.00%) 13.89 (-1040.72%) 46.40 (-3709.20%) 4.44 ( -264.37%) 47.37 (-3789.33%) +/- 0.06 ( 0.00%) 22.82 (-37635.56%) 3.84 (-6249.44%) 6.48 (-10618.92%) 6.60 (-10818.53%) User Time 0.06 ( 0.00%) 0.06 ( -6.90%) 0.05 ( 17.24%) 0.05 ( 13.79%) 0.04 ( 31.03%) +/- 0.01 ( 0.00%) 0.01 ( 33.33%) 0.01 ( 33.33%) 0.01 ( 39.14%) 0.01 ( 25.46%) Elapsed Time 10445.54 ( 0.00%) 2249.92 ( 78.46%) 70.06 ( 99.33%) 16.59 ( 99.84%) 472.43 ( 95.48%) +/- 643.98 ( 0.00%) 811.62 ( -26.03%) 10.02 ( 98.44%) 7.03 ( 98.91%) 59.99 ( 90.68%) THP Active 15.60 ( 0.00%) 35.20 ( 225.64%) 65.00 ( 416.67%) 70.80 ( 453.85%) 62.20 ( 398.72%) +/- 18.48 ( 0.00%) 51.29 ( 277.59%) 15.99 ( 86.52%) 37.91 ( 205.18%) 22.02 ( 119.18%) Fault Alloc 121.80 ( 0.00%) 76.60 ( 62.89%) 155.40 ( 127.59%) 181.20 ( 148.77%) 286.60 ( 235.30%) +/- 73.51 ( 0.00%) 61.11 ( 83.12%) 34.89 ( 47.46%) 31.88 ( 43.36%) 68.13 ( 92.68%) Fault Fallback 881.20 ( 0.00%) 926.60 ( -5.15%) 847.60 ( 3.81%) 822.00 ( 6.72%) 716.60 ( 18.68%) +/- 73.51 ( 0.00%) 61.26 ( 16.67%) 34.89 ( 52.54%) 31.65 ( 56.94%) 67.75 ( 7.84%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 3540.88 1945.37 716.04 64.97 1937.03 Total Elapsed Time (seconds) 52417.33 11425.90 501.02 230.95 2520.28 The first thing to note is the "Elapsed Time" for the vanilla kernels of 2249 seconds versus 56 with THP disabled which might explain the reports of USB stalls with THP enabled. Applying the patches brings performance in line with THP-disabled performance while isolating pages for immediate reclaim from the LRU cuts down System CPU time. The "Fault Alloc" success rate figures are also improved. The vanilla kernel only managed to allocate 76.6 pages on average over the course of 5 iterations where as applying the series allocated 181.20 on average albeit it is well within variance. It's worth noting that applies the series at least descreases the amount of variance which implies an improvement. Andrea's series had a higher success rate for THP allocations but at a severe cost to elapsed time which is still better than vanilla but still much worse than disabling THP altogether. One can bring my series close to Andrea's by removing this check /* * If compaction is deferred for high-order allocations, it is because * sync compaction recently failed. In this is the case and the caller * has requested the system not be heavily disrupted, fail the * allocation now instead of entering direct reclaim */ if (deferred_compaction && (gfp_mask & __GFP_NO_KSWAPD)) goto nopage; I didn't include a patch that removed the above check because hurting overall performance to improve the THP figure is not what the average user wants. It's something to consider though if someone really wants to maximise THP usage no matter what it does to the workload initially. This is summary of vmstat figures from the same test. 3.1.0-vanilla rc5-vanilla freemore-v6r1 isolate-v6r1 andrea-v2r1 Page Ins 3257266139 1111844061 17263623 10901575 161423219 Page Outs 81054922 30364312 3626530 3657687 8753730 Swap Ins 3294 2851 6560 4964 4592 Swap Outs 390073 528094 620197 790912 698285 Direct pages scanned 1077581700 3024951463 1764930052 115140570 5901188831 Kswapd pages scanned 34826043 7112868 2131265 1686942 1893966 Kswapd pages reclaimed 28950067 4911036 1246044 966475 1497726 Direct pages reclaimed 805148398 280167837 3623473 2215044 40809360 Kswapd efficiency 83% 69% 58% 57% 79% Kswapd velocity 664.399 622.521 4253.852 7304.360 751.490 Direct efficiency 74% 9% 0% 1% 0% Direct velocity 20557.737 264745.137 3522673.849 498551.938 2341481.435 Percentage direct scans 96% 99% 99% 98% 99% Page writes by reclaim 722646 529174 620319 791018 699198 Page writes file 332573 1080 122 106 913 Page writes anon 390073 528094 620197 790912 698285 Page reclaim immediate 0 2552514720 1635858848 111281140 5478375032 Page rescued immediate 0 0 0 87848 0 Slabs scanned 23552 23552 9216 8192 9216 Direct inode steals 231 0 0 0 0 Kswapd inode steals 0 0 0 0 0 Kswapd skipped wait 28076 786 0 61 6 THP fault alloc 609 383 753 906 1433 THP collapse alloc 12 6 0 0 6 THP splits 536 211 456 593 1136 THP fault fallback 4406 4633 4263 4110 3583 THP collapse fail 120 127 0 0 4 Compaction stalls 1810 728 623 779 3200 Compaction success 196 53 60 80 123 Compaction failures 1614 675 563 699 3077 Compaction pages moved 193158 53545 243185 333457 226688 Compaction move failure 9952 9396 16424 23676 45070 The main things to look at are 1. Page In/out figures are much reduced by the series. 2. Direct page scanning is incredibly high (264745.137 pages scanned per second on the vanilla kernel) but isolating PageReclaim pages on their own list reduces the number of pages scanned significantly. 3. The fact that "Page rescued immediate" is a positive number implies that we sometimes race removing pages from the LRU_IMMEDIATE list that need to be put back on a normal LRU but it happens only for 0.07% of the pages marked for immediate reclaim. writebackCPDeviceext4 3.1.0-vanilla rc5-vanilla freemore-v6r1 isolate-v6r1 andrea-v2r1 System Time 1.51 ( 0.00%) 1.77 ( -17.66%) 1.46 ( 2.92%) 1.15 ( 23.77%) 1.89 ( -25.63%) +/- 0.27 ( 0.00%) 0.67 ( -148.52%) 0.33 ( -22.76%) 0.30 ( -11.15%) 0.19 ( 30.16%) User Time 0.03 ( 0.00%) 0.04 ( -37.50%) 0.05 ( -62.50%) 0.07 ( -112.50%) 0.04 ( -18.75%) +/- 0.01 ( 0.00%) 0.02 ( -146.64%) 0.02 ( -97.91%) 0.02 ( -75.59%) 0.02 ( -63.30%) Elapsed Time 124.93 ( 0.00%) 114.49 ( 8.36%) 96.77 ( 22.55%) 27.48 ( 78.00%) 205.70 ( -64.65%) +/- 20.20 ( 0.00%) 74.39 ( -268.34%) 59.88 ( -196.48%) 7.72 ( 61.79%) 25.03 ( -23.95%) THP Active 161.80 ( 0.00%) 83.60 ( 51.67%) 141.20 ( 87.27%) 84.60 ( 52.29%) 82.60 ( 51.05%) +/- 71.95 ( 0.00%) 43.80 ( 60.88%) 26.91 ( 37.40%) 59.02 ( 82.03%) 52.13 ( 72.45%) Fault Alloc 471.40 ( 0.00%) 228.60 ( 48.49%) 282.20 ( 59.86%) 225.20 ( 47.77%) 388.40 ( 82.39%) +/- 88.07 ( 0.00%) 87.42 ( 99.26%) 73.79 ( 83.78%) 109.62 ( 124.47%) 82.62 ( 93.81%) Fault Fallback 531.60 ( 0.00%) 774.60 ( -45.71%) 720.80 ( -35.59%) 777.80 ( -46.31%) 614.80 ( -15.65%) +/- 88.07 ( 0.00%) 87.26 ( 0.92%) 73.79 ( 16.22%) 109.62 ( -24.47%) 82.29 ( 6.56%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 50.22 33.76 30.65 24.14 128.45 Total Elapsed Time (seconds) 1113.73 1132.19 1029.45 759.49 1707.26 Similar test but the USB stick is using ext4 instead of vfat. As ext4 does not use writepage for migration, the large stalls due to compaction when THP is enabled are not observed. Still, isolating PageReclaim pages on their own list helped completion time largely by reducing the number of pages scanned by direct reclaim although time spend in congestion_wait could also be a factor. Again, Andrea's series had far higher success rates for THP allocation at the cost of elapsed time. I didn't look too closely but a quick look at the vmstat figures tells me kswapd reclaimed 8 times more pages than the patch series and direct reclaim reclaimed roughly three times as many pages. It follows that if memory is aggressively reclaimed, there will be more available for THP. writebackCPFilevfat 3.1.0-vanilla rc5-vanilla freemore-v6r1 isolate-v6r1 andrea-v2r1 System Time 1.76 ( 0.00%) 29.10 (-1555.52%) 46.01 (-2517.18%) 4.79 ( -172.35%) 54.89 (-3022.53%) +/- 0.14 ( 0.00%) 25.61 (-18185.17%) 2.15 (-1434.83%) 6.60 (-4610.03%) 9.75 (-6863.76%) User Time 0.05 ( 0.00%) 0.07 ( -45.83%) 0.05 ( -4.17%) 0.06 ( -29.17%) 0.06 ( -16.67%) +/- 0.02 ( 0.00%) 0.02 ( 20.11%) 0.02 ( -3.14%) 0.01 ( 31.58%) 0.01 ( 47.41%) Elapsed Time 22520.79 ( 0.00%) 1082.85 ( 95.19%) 73.30 ( 99.67%) 32.43 ( 99.86%) 291.84 ( 98.70%) +/- 7277.23 ( 0.00%) 706.29 ( 90.29%) 19.05 ( 99.74%) 17.05 ( 99.77%) 125.55 ( 98.27%) THP Active 83.80 ( 0.00%) 12.80 ( 15.27%) 15.60 ( 18.62%) 13.00 ( 15.51%) 0.80 ( 0.95%) +/- 66.81 ( 0.00%) 20.19 ( 30.22%) 5.92 ( 8.86%) 15.06 ( 22.54%) 1.17 ( 1.75%) Fault Alloc 171.00 ( 0.00%) 67.80 ( 39.65%) 97.40 ( 56.96%) 125.60 ( 73.45%) 133.00 ( 77.78%) +/- 82.91 ( 0.00%) 30.69 ( 37.02%) 53.91 ( 65.02%) 55.05 ( 66.40%) 21.19 ( 25.56%) Fault Fallback 832.00 ( 0.00%) 935.20 ( -12.40%) 906.00 ( -8.89%) 877.40 ( -5.46%) 870.20 ( -4.59%) +/- 82.91 ( 0.00%) 30.69 ( 62.98%) 54.01 ( 34.86%) 55.05 ( 33.60%) 20.91 ( 74.78%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 7229.81 928.42 704.52 80.68 1330.76 Total Elapsed Time (seconds) 112849.04 5618.69 571.11 360.54 1664.28 In this case, the test is reading/writing only from filesystems but as it's vfat, it's slow due to calling writepage during compaction. Little to observe really - the time to complete the test goes way down with the series applied and THP allocation success rates go up in comparison to 3.2-rc5. The success rates are lower than 3.1.0 but the elapsed time for that kernel is abysmal so it is not really a sensible comparison. As before, Andrea's series allocates more THPs at the cost of overall performance. writebackCPFileext4 3.1.0-vanilla rc5-vanilla freemore-v6r1 isolate-v6r1 andrea-v2r1 System Time 1.51 ( 0.00%) 1.77 ( -17.66%) 1.46 ( 2.92%) 1.15 ( 23.77%) 1.89 ( -25.63%) +/- 0.27 ( 0.00%) 0.67 ( -148.52%) 0.33 ( -22.76%) 0.30 ( -11.15%) 0.19 ( 30.16%) User Time 0.03 ( 0.00%) 0.04 ( -37.50%) 0.05 ( -62.50%) 0.07 ( -112.50%) 0.04 ( -18.75%) +/- 0.01 ( 0.00%) 0.02 ( -146.64%) 0.02 ( -97.91%) 0.02 ( -75.59%) 0.02 ( -63.30%) Elapsed Time 124.93 ( 0.00%) 114.49 ( 8.36%) 96.77 ( 22.55%) 27.48 ( 78.00%) 205.70 ( -64.65%) +/- 20.20 ( 0.00%) 74.39 ( -268.34%) 59.88 ( -196.48%) 7.72 ( 61.79%) 25.03 ( -23.95%) THP Active 161.80 ( 0.00%) 83.60 ( 51.67%) 141.20 ( 87.27%) 84.60 ( 52.29%) 82.60 ( 51.05%) +/- 71.95 ( 0.00%) 43.80 ( 60.88%) 26.91 ( 37.40%) 59.02 ( 82.03%) 52.13 ( 72.45%) Fault Alloc 471.40 ( 0.00%) 228.60 ( 48.49%) 282.20 ( 59.86%) 225.20 ( 47.77%) 388.40 ( 82.39%) +/- 88.07 ( 0.00%) 87.42 ( 99.26%) 73.79 ( 83.78%) 109.62 ( 124.47%) 82.62 ( 93.81%) Fault Fallback 531.60 ( 0.00%) 774.60 ( -45.71%) 720.80 ( -35.59%) 777.80 ( -46.31%) 614.80 ( -15.65%) +/- 88.07 ( 0.00%) 87.26 ( 0.92%) 73.79 ( 16.22%) 109.62 ( -24.47%) 82.29 ( 6.56%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 50.22 33.76 30.65 24.14 128.45 Total Elapsed Time (seconds) 1113.73 1132.19 1029.45 759.49 1707.26 Same type of story - elapsed times go down. In this case, allocation success rates are roughtly the same. As before, Andrea's has higher success rates but takes a lot longer. Overall the series does reduce latencies and while the tests are inherency racy as alloc competes with the cp processes, the variability was included. The THP allocation rates are not as high as they could be but that is because we would have to be more aggressive about reclaim and compaction impacting overall performance. This patch: Commit 39deaf85 ("mm: compaction: make isolate_lru_page() filter-aware") noted that compaction does not migrate dirty or writeback pages and that is was meaningless to pick the page and re-add it to the LRU list. What was missed during review is that asynchronous migration moves dirty pages if their ->migratepage callback is migrate_page() because these can be moved without blocking. This potentially impacted hugepage allocation success rates by a factor depending on how many dirty pages are in the system. This patch partially reverts 39deaf85 to allow migration to isolate dirty pages again. This increases how much compaction disrupts the LRU but that is addressed later in the series. Signed-off-by:
Andrea Arcangeli <aarcange@redhat.com> Reviewed-by:
-
Minchan Kim authored
commit 0dabec93 upstream. Stable note: Not tracked in Bugzilla. This patch makes later patches easier to apply but has no other impact. unmap_and_move() is one a big messy function. Clean it up. Signed-off-by:
-
Minchan Kim authored
commit f80c0673 upstream. Stable note: Not tracked in Bugzilla. THP and compaction disrupt the LRU list leading to poor reclaim decisions which has a variable performance impact. In __zone_reclaim case, we don't want to shrink mapped page. Nonetheless, we have isolated mapped page and re-add it into LRU's head. It's unnecessary CPU overhead and makes LRU churning. Of course, when we isolate the page, the page might be mapped but when we try to migrate the page, the page would be not mapped. So it could be migrated. But race is rare and although it happens, it's no big deal. Signed-off-by:
Johannes Weiner <hannes@cmpxchg.org> Reviewed-by:
Michal Hocko <mhocko@suse.cz> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by:
-
Minchan Kim authored
commit 39deaf85 upstream. Stable note: Not tracked in Bugzilla. THP and compaction disrupt the LRU list leading to poor reclaim decisions which has a variable performance impact. In async mode, compaction doesn't migrate dirty or writeback pages. So, it's meaningless to pick the page and re-add it to lru list. Of course, when we isolate the page in compaction, the page might be dirty or writeback but when we try to migrate the page, the page would be not dirty, writeback. So it could be migrated. But it's very unlikely as isolate and migration cycle is much faster than writeout. So, this patch helps cpu overhead and prevent unnecessary LRU churning. Signed-off-by:
-
Minchan Kim authored
commit 4356f21d upstream. Stable note: Not tracked in Bugzilla. This patch makes later patches easier to apply but has no other impact. Change ISOLATE_XXX macro with bitwise isolate_mode_t type. Normally, macro isn't recommended as it's type-unsafe and making debugging harder as symbol cannot be passed throught to the debugger. Quote from Johannes " Hmm, it would probably be cleaner to fully convert the isolation mode into independent flags. INACTIVE, ACTIVE, BOTH is currently a tri-state among flags, which is a bit ugly." This patch moves isolate mode from swap.h to mmzone.h by memcontrol.h Signed-off-by:
-
Minchan Kim authored
commit b9e84ac1 upstream. Stable note: Not tracked in Bugzilla. This patch makes later patches easier to apply but has no other impact. acct_isolated of compaction uses page_lru_base_type which returns only base type of LRU list so it never returns LRU_ACTIVE_ANON or LRU_ACTIVE_FILE. In addtion, cc->nr_[anon|file] is used in only acct_isolated so it doesn't have fields in conpact_control. This patch removes fields from compact_control and makes clear function of acct_issolated which counts the number of anon|file pages isolated. Signed-off-by:
-
Mel Gorman authored
commit e0c23279 upstream. Stable note: Not tracked on Bugzilla. THP and compaction was found to aggressively reclaim pages and stall systems under different situations that was addressed piecemeal over time. If compaction can proceed, shrink_zones() stops doing any work but its callers still call shrink_slab() which raises the priority and potentially sleeps. This is unnecessary and wasteful so this patch aborts direct reclaim/compaction entirely if compaction can proceed. Signed-off-by:
Johannes Weiner <jweiner@redhat.com> Cc: Josh Boyer <jwboyer@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by:
-
Rik van Riel authored
commit e0887c19 upstream. Stable note: Not tracked on Bugzilla. THP and compaction was found to aggressively reclaim pages and stall systems under different situations that was addressed piecemeal over time. Paragraph 3 of this changelog is the motivation for this patch. When suffering from memory fragmentation due to unfreeable pages, THP page faults will repeatedly try to compact memory. Due to the unfreeable pages, compaction fails. Needless to say, at that point page reclaim also fails to create free contiguous 2MB areas. However, that doesn't stop the current code from trying, over and over again, and freeing a minimum of 4MB (2UL << sc->order pages) at every single invocation. This resulted in my 12GB system having 2-3GB free memory, a corresponding amount of used swap and very sluggish response times. This can be avoided by having the direct reclaim code not reclaim from zones that already have plenty of free memory available for compaction. If compaction still fails due to unmovable memory, doing additional reclaim will only hurt the system, not help. [jweiner@redhat.com: change comment to explain the order check] Signed-off-by:
-
Dave Chinner authored
commit 3567b59a upstream. Stable note: Not tracked in Bugzilla. This patch reduces excessive reclaim of slab objects reducing the amount of information that has to be brought back in from disk. The third and fourth paragram in the series describes the impact. 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> Signed-off-by:
-
Dave Chinner authored
commit acf92b48 upstream. Stable note: Not tracked in Bugzilla. This patch reduces excessive reclaim of slab objects reducing the amount of information that has to be brought back in from disk. 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 authored
commit 09576073 upstream. Stable note: This patch makes later patches easier to apply but otherwise has little to justify it. It is a diagnostic patch that was part of a series addressing excessive slab shrinking after GFP_NOFS failures. There is detailed information on the series' motivation at https://lkml.org/lkml/2011/6/2/42 . 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:
-
Shaohua Li authored
commit 439423f6 upstream. Stable note: Not tracked in Bugzilla. kswapd is responsible for clearing ZONE_CONGESTED after it balances a zone and this patch fixes a bug where that was failing to happen. Without this patch, processes can stall in wait_iff_congested unnecessarily. For users, this can look like an interactivity stall but some workloads would see it as sudden drop in throughput. ZONE_CONGESTED is only cleared in kswapd, but pages can be freed in any task. It's possible ZONE_CONGESTED isn't cleared in some cases: 1. the zone is already balanced just entering balance_pgdat() for order-0 because concurrent tasks free memory. In this case, later check will skip the zone as it's balanced so the flag isn't cleared. 2. high order balance fallbacks to order-0. quote from Mel: At the end of balance_pgdat(), kswapd uses the following logic; If reclaiming at high order { for each zone { if all_unreclaimable skip if watermark is not met order = 0 loop again /* watermark is met */ clear congested } } i.e. it clears ZONE_CONGESTED if it the zone is balanced. if not, it restarts balancing at order-0. However, if the higher zones are balanced for order-0, kswapd will miss clearing ZONE_CONGESTED as that only happens after a zone is shrunk. This can mean that wait_iff_congested() stalls unnecessarily. This patch makes kswapd clear ZONE_CONGESTED during its initial highmem->dma scan for zones that are already balanced. Signed-off-by:
Shaohua Li <shaohua.li@intel.com> Acked-by:
-
Johannes Weiner authored
commit a4d3e9e7 upstream. Stable note: Not tracked in Bugzilla. This patch augments an earlier commit that avoids scanning priority being artificially raised. The older fix was particularly important for small memcgs to avoid calling wait_iff_congested() unnecessarily. Without swap, anonymous pages are not scanned. As such, they should not count when considering force-scanning a small target if there is no swap. Otherwise, targets are not force-scanned even when their effective scan number is zero and the other conditions--kswapd/memcg--apply. This fixes 246e87a9 ("memcg: fix get_scan_count() for small targets"). [akpm@linux-foundation.org: fix comment] Signed-off-by:
Mel Gorman <mel@csn.ul.ie> Signed-off-by:
-
Mel Gorman authored
commit 938929f1 upstream. Stable note: Fixes https://bugzilla.novell.com/show_bug.cgi?id=726210 . Large machines with 1TB or more of RAM take a long time to boot without this patch and may spew out soft lockup warnings. When min_free_kbytes is updated, some pageblocks are marked MIGRATE_RESERVE. Ordinarily, this work is unnoticable as it happens early in boot but on large machines with 1TB of memory, this has been reported to delay boot times, probably due to the NUMA distances involved. The bulk of the work is due to calling calling pageblock_is_reserved() an unnecessary amount of times and accessing far more struct page metadata than is necessary. This patch significantly reduces the amount of work done by setup_zone_migrate_reserve() improving boot times on 1TB machines. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by:
-
Mel Gorman authored
commit 2bbcb878 upstream. Stable note: Fixes https://bugzilla.novell.com/show_bug.cgi?id=721039 . Without the patch, memory hot-add can fail for kernel configurations that do not set CONFIG_SPARSEMEM_VMEMMAP. (Resending as I am not seeing it in -next so maybe it got lost) mm: memory hotplug: Check if pages are correctly reserved on a per-section basis It is expected that memory being brought online is PageReserved similar to what happens when the page allocator is being brought up. Memory is onlined in "memory blocks" which consist of one or more sections. Unfortunately, the code that verifies PageReserved is currently assuming that the memmap backing all these pages is virtually contiguous which is only the case when CONFIG_SPARSEMEM_VMEMMAP is set. As a result, memory hot-add is failing on those configurations with the message; kernel: section number XXX page number 256 not reserved, was it already online? This patch updates the PageReserved check to lookup struct page once per section to guarantee the correct struct page is being checked. [Check pages within sections properly: rientjes@google.com] [original patch by: nfont@linux.vnet.ibm.com] Signed-off-by:
Nathan Fontenot <nfont@linux.vnet.ibm.com> Signed-off-by:
Greg Kroah-Hartman <gregkh@suse.de>
-
Dimitri Sivanich authored
commit a1cb2c60 upstream. Stable note: Not tracked on Bugzilla. This patch is known to make a big difference to tmpfs performance on larger machines. This was found to adversely affect tmpfs I/O performance. Tests run on a 640 cpu UV system. With 120 threads doing parallel writes, each to different tmpfs mounts: No patch: ~300 MB/sec With vm_stat alignment: ~430 MB/sec Signed-off-by:
Dimitri Sivanich <sivanich@sgi.com> Acked-by:
Christoph Lameter <cl@gentwo.org> Acked-by:
-
Mikulas Patocka authored
commit 751f188d upstream. This patch fixes a crash when a discard request is sent during mirror recovery. Firstly, some background. Generally, the following sequence happens during mirror synchronization: - function do_recovery is called - do_recovery calls dm_rh_recovery_prepare - dm_rh_recovery_prepare uses a semaphore to limit the number simultaneously recovered regions (by default the semaphore value is 1, so only one region at a time is recovered) - dm_rh_recovery_prepare calls __rh_recovery_prepare, __rh_recovery_prepare asks the log driver for the next region to recover. Then, it sets the region state to DM_RH_RECOVERING. If there are no pending I/Os on this region, the region is added to quiesced_regions list. If there are pending I/Os, the region is not added to any list. It is added to the quiesced_regions list later (by dm_rh_dec function) when all I/Os finish. - when the region is on quiesced_regions list, there are no I/Os in flight on this region. The region is popped from the list in dm_rh_recovery_start function. Then, a kcopyd job is started in the recover function. - when the kcopyd job finishes, recovery_complete is called. It calls dm_rh_recovery_end. dm_rh_recovery_end adds the region to recovered_regions or failed_recovered_regions list (depending on whether the copy operation was successful or not). The above mechanism assumes that if the region is in DM_RH_RECOVERING state, no new I/Os are started on this region. When I/O is started, dm_rh_inc_pending is called, which increases reg->pending count. When I/O is finished, dm_rh_dec is called. It decreases reg->pending count. If the count is zero and the region was in DM_RH_RECOVERING state, dm_rh_dec adds it to the quiesced_regions list. Consequently, if we call dm_rh_inc_pending/dm_rh_dec while the region is in DM_RH_RECOVERING state, it could be added to quiesced_regions list multiple times or it could be added to this list when kcopyd is copying data (it is assumed that the region is not on any list while kcopyd does its jobs). This results in memory corruption and crash. There already exist bypasses for REQ_FLUSH requests: REQ_FLUSH requests do not belong to any region, so they are always added to the sync list in do_writes. dm_rh_inc_pending does not increase count for REQ_FLUSH requests. In mirror_end_io, dm_rh_dec is never called for REQ_FLUSH requests. These bypasses avoid the crash possibility described above. These bypasses were improperly implemented for REQ_DISCARD when the mirror target gained discard support in commit 5fc2ffea (dm raid1: support discard). In do_writes, REQ_DISCARD requests is always added to the sync queue and immediately dispatched (even if the region is in DM_RH_RECOVERING). However, dm_rh_inc and dm_rh_dec is called for REQ_DISCARD resusts. So it violates the rule that no I/Os are started on DM_RH_RECOVERING regions, and causes the list corruption described above. This patch changes it so that REQ_DISCARD requests follow the same path as REQ_FLUSH. This avoids the crash. Reference: https://bugzilla.redhat.com/837607Signed-off-by:
Mikulas Patocka <mpatocka@redhat.com> Signed-off-by:
Alasdair G Kergon <agk@redhat.com> Signed-off-by:
-
Artem Bityutskiy authored
commit c6727932 upstream. UBIFS has a feature called "empty space fix-up" which is a quirk to work-around limitations of dumb flasher programs. Namely, of those flashers that are unable to skip NAND pages full of 0xFFs while flashing, resulting in empty space at the end of half-filled eraseblocks to be unusable for UBIFS. This feature is relatively new (introduced in v3.0). The fix-up routine (fixup_free_space()) is executed only once at the very first mount if the superblock has the 'space_fixup' flag set (can be done with -F option of mkfs.ubifs). It basically reads all the UBIFS data and metadata and writes it back to the same LEB. The routine assumes the image is pristine and does not have anything in the journal. There was a bug in 'fixup_free_space()' where it fixed up the log incorrectly. All but one LEB of the log of a pristine file-system are empty. And one contains just a commit start node. And 'fixup_free_space()' just unmapped this LEB, which resulted in wiping the commit start node. As a result, some users were unable to mount the file-system next time with the following symptom: UBIFS error (pid 1): replay_log_leb: first log node at LEB 3:0 is not CS node UBIFS error (pid 1): replay_log_leb: log error detected while replaying the log at LEB 3:0 The root-cause of this bug was that 'fixup_free_space()' wrongly assumed that the beginning of empty space in the log head (c->lhead_offs) was known on mount. However, it is not the case - it was always 0. UBIFS does not store in it the master node and finds out by scanning the log on every mount. The fix is simple - just pass commit start node size instead of 0 to 'fixup_leb()'. Signed-off-by:
Artem Bityutskiy <Artem.Bityutskiy@linux.intel.com> Reported-by:
Iwo Mergler <Iwo.Mergler@netcommwireless.com> Tested-by:
James Nute <newten82@gmail.com> Signed-off-by:
-
David Daney authored
commit 7b1c0d26 upstream. Improper alignment can lead to unbootable systems and/or random crashes. [ralf@linux-mips.org: This is a lond standing bug since 6eb10bc9 (kernel.org) rsp. c422a10917f75fd19fa7fe070aaaa23e384dae6f (lmo) [MIPS: Clean up linker script using new linker script macros.] so dates back to 2.6.32.] Signed-off-by:
David Daney <david.daney@cavium.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/3881/Signed-off-by:
Ralf Baechle <ralf@linux-mips.org> Signed-off-by:
-
Aaditya Kumar authored
commit 1c7e7f6c upstream. Offlining memory may block forever, waiting for kswapd() to wake up because kswapd() does not check the event kthread->should_stop before sleeping. The proper pattern, from Documentation/memory-barriers.txt, is: --- waker --- event_indicated = 1; wake_up_process(event_daemon); --- sleeper --- for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (event_indicated) break; schedule(); } set_current_state() may be wrapped by: prepare_to_wait(); In the kswapd() case, event_indicated is kthread->should_stop. === offlining memory (waker) === kswapd_stop() kthread_stop() kthread->should_stop = 1 wake_up_process() wait_for_completion() === kswapd_try_to_sleep (sleeper) === kswapd_try_to_sleep() prepare_to_wait() . . schedule() . . finish_wait() The schedule() needs to be protected by a test of kthread->should_stop, which is wrapped by kthread_should_stop(). Reproducer: Do heavy file I/O in background. Do a memory offline/online in a tight loop Signed-off-by:
Aaditya Kumar <aaditya.kumar@ap.sony.com> Acked-by:
-
John Stultz authored
commit 6b1859db upstream. In commit 6b43ae8a, I introduced a bug that kept the STA_INS or STA_DEL bit from being cleared from time_status via adjtimex() without forcing STA_PLL first. Usually once the STA_INS is set, it isn't cleared until the leap second is applied, so its unlikely this affected anyone. However during testing I noticed it took some effort to cancel a leap second once STA_INS was set. Signed-off-by:
John Stultz <johnstul@us.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Richard Cochran <richardcochran@gmail.com> Cc: Prarit Bhargava <prarit@redhat.com> Link: http://lkml.kernel.org/r/1342156917-25092-2-git-send-email-john.stultz@linaro.orgSigned-off-by:
Thomas Gleixner <tglx@linutronix.de> Signed-off-by:
-
Jeff Layton authored
commit cd60042c upstream. When we get back a FIND_FIRST/NEXT result, we have some info about the dentry that we use to instantiate a new inode. We were ignoring and discarding that info when we had an existing dentry in the cache. Fix this by updating the inode in place when we find an existing dentry and the uniqueid is the same. Reported-and-Tested-by:
Andrew Bartlett <abartlet@samba.org> Reported-by:
Bill Robertson <bill_robertson@debortoli.com.au> Reported-by:
Dion Edwards <dion_edwards@debortoli.com.au> Signed-off-by:
Jeff Layton <jlayton@redhat.com> Signed-off-by:
Steve French <smfrench@gmail.com> Signed-off-by:
-
- 19 Jul, 2012 3 commits
-
-
Greg Kroah-Hartman authored
-
Thomas Gleixner authored
This is a backport of 3e997130 The leap second rework unearthed another issue of inconsistent data. On timekeeping_resume() the timekeeper data is updated, but nothing calls timekeeping_update(), so now the update code in the timer interrupt sees stale values. This has been the case before those changes, but then the timer interrupt was using stale data as well so this went unnoticed for quite some time. Add the missing update call, so all the data is consistent everywhere. Reported-by:
Andreas Schwab <schwab@linux-m68k.org> Reported-and-tested-by:
"Rafael J. Wysocki" <rjw@sisk.pl> Reported-and-tested-by:
Martin Steigerwald <Martin@lichtvoll.de> Cc: John Stultz <johnstul@us.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>, Cc: Prarit Bhargava <prarit@redhat.com> Signed-off-by:
-
John Stultz authored
This is a backport of 5baefd6d The update of the hrtimer base offsets on all cpus cannot be made atomically from the timekeeper.lock held and interrupt disabled region as smp function calls are not allowed there. clock_was_set(), which enforces the update on all cpus, is called either from preemptible process context in case of do_settimeofday() or from the softirq context when the offset modification happened in the timer interrupt itself due to a leap second. In both cases there is a race window for an hrtimer interrupt between dropping timekeeper lock, enabling interrupts and clock_was_set() issuing the updates. Any interrupt which arrives in that window will see the new time but operate on stale offsets. So we need to make sure that an hrtimer interrupt always sees a consistent state of time and offsets. ktime_get_update_offsets() allows us to get the current monotonic time and update the per cpu hrtimer base offsets from hrtimer_interrupt() to capture a consistent state of monotonic time and the offsets. The function replaces the existing ktime_get() calls in hrtimer_interrupt(). The overhead of the new function vs. ktime_get() is minimal as it just adds two store operations. This ensures that any changes to realtime or boottime offsets are noticed and stored into the per-cpu hrtimer base structures, prior to any hrtimer expiration and guarantees that timers are not expired early. Signed-off-by:
Ingo Molnar <mingo@kernel.org> Acked-by:
Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by:
Prarit Bhargava <prarit@redhat.com> Link: http://lkml.kernel.org/r/1341960205-56738-8-git-send-email-johnstul@us.ibm.comSigned-off-by:
-
