From 8c8387ee3f55a38c3388882f1dd72dc526965211 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 5 Nov 2021 13:36:49 -0700 Subject: mm: stop filemap_read() from grabbing a superfluous page Under some circumstances, filemap_read() will allocate sufficient pages to read to the end of the file, call readahead/readpages on them and copy the data over - and then it will allocate another page at the EOF and call readpage on that and then ignore it. This is unnecessary and a waste of time and resources. filemap_read() *does* check for this, but only after it has already done the allocation and I/O. Fix this by checking before calling filemap_get_pages() also. Link: https://lkml.kernel.org/r/163472463105.3126792.7056099385135786492.stgit@warthog.procyon.org.uk Link: https://lore.kernel.org/r/160588481358.3465195.16552616179674485179.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163456863216.2614702.6384850026368833133.stgit@warthog.procyon.org.uk/ Signed-off-by: David Howells Acked-by: Jeff Layton Reviewed-by: Matthew Wilcox (Oracle) Cc: Kent Overstreet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index dae481293b5d95..e50be519f6a484 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2625,6 +2625,9 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, if ((iocb->ki_flags & IOCB_WAITQ) && already_read) iocb->ki_flags |= IOCB_NOWAIT; + if (unlikely(iocb->ki_pos >= i_size_read(inode))) + break; + error = filemap_get_pages(iocb, iter, &pvec); if (error < 0) break; -- cgit 1.2.3-korg From 61d0017e5a32d3b13ba3c7becc83a5a9e53cdbe9 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 5 Nov 2021 13:37:07 -0700 Subject: mm: don't read i_size of inode unless we need it We always go through i_size_read(), and we rarely end up needing it. Push the read to down where we need to check it, which avoids it for most cases. It looks like we can even remove this check entirely, which might be worth pursuing. But at least this takes it out of the hot path. Link: https://lkml.kernel.org/r/6b67981f-57d4-c80e-bc07-6020aa601381@kernel.dk Signed-off-by: Jens Axboe Acked-by: Chris Mason Cc: Josef Bacik Cc: Dave Chinner Cc: Pavel Begunkov Cc: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index e50be519f6a484..ebd68890a8444b 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2740,9 +2740,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; - loff_t size; - size = i_size_read(inode); if (iocb->ki_flags & IOCB_NOWAIT) { if (filemap_range_needs_writeback(mapping, iocb->ki_pos, iocb->ki_pos + count - 1)) @@ -2774,8 +2772,9 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) * the rest of the read. Buffered reads will not work for * DAX files, so don't bother trying. */ - if (retval < 0 || !count || iocb->ki_pos >= size || - IS_DAX(inode)) + if (retval < 0 || !count || IS_DAX(inode)) + return retval; + if (iocb->ki_pos >= i_size_read(inode)) return retval; } -- cgit 1.2.3-korg From d417b49fff3e2f21043c834841e8623a6098741d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 5 Nov 2021 13:37:10 -0700 Subject: mm/filemap.c: remove bogus VM_BUG_ON It is not safe to check page->index without holding the page lock. It can be changed if the page is moved between the swap cache and the page cache for a shmem file, for example. There is a VM_BUG_ON below which checks page->index is correct after taking the page lock. Link: https://lkml.kernel.org/r/20210818144932.940640-1-willy@infradead.org Fixes: 5c211ba29deb ("mm: add and use find_lock_entries") Signed-off-by: Matthew Wilcox (Oracle) Reported-by: Cc: Hugh Dickins Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 1 - 1 file changed, 1 deletion(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index ebd68890a8444b..28c57c2536d0a1 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2093,7 +2093,6 @@ unsigned find_lock_entries(struct address_space *mapping, pgoff_t start, if (!xa_is_value(page)) { if (page->index < start) goto put; - VM_BUG_ON_PAGE(page->index != xas.xa_index, page); if (page->index + thp_nr_pages(page) - 1 > end) goto put; if (!trylock_page(page)) -- cgit 1.2.3-korg From f8ee8909ac818e555ef18b57b0ee4b9fd0478b82 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 5 Nov 2021 13:37:13 -0700 Subject: mm: move more expensive part of XA setup out of mapping check The fast path here is not needing any writeback, yet we spend time setting up the xarray lookup data upfront. Move the part that actually needs to iterate the address space mapping into a separate helper, saving ~30% of the time here. Link: https://lkml.kernel.org/r/49f67983-b802-8929-edab-d807f745c9ca@kernel.dk Signed-off-by: Jens Axboe Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 43 +++++++++++++++++++++++++------------------ 1 file changed, 25 insertions(+), 18 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index 28c57c2536d0a1..938f52702a7aba 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -639,6 +639,30 @@ static bool mapping_needs_writeback(struct address_space *mapping) return mapping->nrpages; } +static bool filemap_range_has_writeback(struct address_space *mapping, + loff_t start_byte, loff_t end_byte) +{ + XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); + pgoff_t max = end_byte >> PAGE_SHIFT; + struct page *page; + + if (end_byte < start_byte) + return false; + + rcu_read_lock(); + xas_for_each(&xas, page, max) { + if (xas_retry(&xas, page)) + continue; + if (xa_is_value(page)) + continue; + if (PageDirty(page) || PageLocked(page) || PageWriteback(page)) + break; + } + rcu_read_unlock(); + return page != NULL; + +} + /** * filemap_range_needs_writeback - check if range potentially needs writeback * @mapping: address space within which to check @@ -656,29 +680,12 @@ static bool mapping_needs_writeback(struct address_space *mapping) bool filemap_range_needs_writeback(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { - XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); - pgoff_t max = end_byte >> PAGE_SHIFT; - struct page *page; - if (!mapping_needs_writeback(mapping)) return false; if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) && !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) return false; - if (end_byte < start_byte) - return false; - - rcu_read_lock(); - xas_for_each(&xas, page, max) { - if (xas_retry(&xas, page)) - continue; - if (xa_is_value(page)) - continue; - if (PageDirty(page) || PageLocked(page) || PageWriteback(page)) - break; - } - rcu_read_unlock(); - return page != NULL; + return filemap_range_has_writeback(mapping, start_byte, end_byte); } EXPORT_SYMBOL_GPL(filemap_range_needs_writeback); -- cgit 1.2.3-korg From 03c4f20454e0231d2cdec4373841a3a25cf4efed Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Fri, 5 Nov 2021 13:38:38 -0700 Subject: mm: introduce pmd_install() helper Patch series "Do some code cleanups related to mm", v3. This patch (of 2): Currently we have three times the same few lines repeated in the code. Deduplicate them by newly introduced pmd_install() helper. Link: https://lkml.kernel.org/r/20210901102722.47686-1-zhengqi.arch@bytedance.com Link: https://lkml.kernel.org/r/20210901102722.47686-2-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng Reviewed-by: David Hildenbrand Reviewed-by: Muchun Song Acked-by: Kirill A. Shutemov Cc: Thomas Gleixner Cc: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Cc: Mika Penttila Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 11 ++--------- mm/internal.h | 1 + mm/memory.c | 34 ++++++++++++++++------------------ 3 files changed, 19 insertions(+), 27 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index 938f52702a7aba..d05f8013a4f0f8 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3211,15 +3211,8 @@ static bool filemap_map_pmd(struct vm_fault *vmf, struct page *page) } } - if (pmd_none(*vmf->pmd)) { - vmf->ptl = pmd_lock(mm, vmf->pmd); - if (likely(pmd_none(*vmf->pmd))) { - mm_inc_nr_ptes(mm); - pmd_populate(mm, vmf->pmd, vmf->prealloc_pte); - vmf->prealloc_pte = NULL; - } - spin_unlock(vmf->ptl); - } + if (pmd_none(*vmf->pmd)) + pmd_install(mm, vmf->pmd, &vmf->prealloc_pte); /* See comment in handle_pte_fault() */ if (pmd_devmap_trans_unstable(vmf->pmd)) { diff --git a/mm/internal.h b/mm/internal.h index cf3cb933eba3f2..6c3e1a9f8c5a6a 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -38,6 +38,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf); void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling); +void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte); static inline bool can_madv_lru_vma(struct vm_area_struct *vma) { diff --git a/mm/memory.c b/mm/memory.c index 48b2e048d2677d..38d63f6d998b18 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -433,9 +433,20 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, } } +void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte) +{ + spinlock_t *ptl = pmd_lock(mm, pmd); + + if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ + mm_inc_nr_ptes(mm); + pmd_populate(mm, pmd, *pte); + *pte = NULL; + } + spin_unlock(ptl); +} + int __pte_alloc(struct mm_struct *mm, pmd_t *pmd) { - spinlock_t *ptl; pgtable_t new = pte_alloc_one(mm); if (!new) return -ENOMEM; @@ -455,13 +466,7 @@ int __pte_alloc(struct mm_struct *mm, pmd_t *pmd) */ smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ - ptl = pmd_lock(mm, pmd); - if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ - mm_inc_nr_ptes(mm); - pmd_populate(mm, pmd, new); - new = NULL; - } - spin_unlock(ptl); + pmd_install(mm, pmd, &new); if (new) pte_free(mm, new); return 0; @@ -4024,17 +4029,10 @@ vm_fault_t finish_fault(struct vm_fault *vmf) return ret; } - if (vmf->prealloc_pte) { - vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); - if (likely(pmd_none(*vmf->pmd))) { - mm_inc_nr_ptes(vma->vm_mm); - pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); - vmf->prealloc_pte = NULL; - } - spin_unlock(vmf->ptl); - } else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) { + if (vmf->prealloc_pte) + pmd_install(vma->vm_mm, vmf->pmd, &vmf->prealloc_pte); + else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) return VM_FAULT_OOM; - } } /* See comment in handle_pte_fault() */ -- cgit 1.2.3-korg From e0f43fa50605f89d45708bce3b94e408ef5c4342 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 5 Nov 2021 13:41:04 -0700 Subject: mm: filemap: coding style cleanup for filemap_map_pmd() Patch series "Solve silent data loss caused by poisoned page cache (shmem/tmpfs)", v5. When discussing the patch that splits page cache THP in order to offline the poisoned page, Noaya mentioned there is a bigger problem [1] that prevents this from working since the page cache page will be truncated if uncorrectable errors happen. By looking this deeper it turns out this approach (truncating poisoned page) may incur silent data loss for all non-readonly filesystems if the page is dirty. It may be worse for in-memory filesystem, e.g. shmem/tmpfs since the data blocks are actually gone. To solve this problem we could keep the poisoned dirty page in page cache then notify the users on any later access, e.g. page fault, read/write, etc. The clean page could be truncated as is since they can be reread from disk later on. The consequence is the filesystems may find poisoned page and manipulate it as healthy page since all the filesystems actually don't check if the page is poisoned or not in all the relevant paths except page fault. In general, we need make the filesystems be aware of poisoned page before we could keep the poisoned page in page cache in order to solve the data loss problem. To make filesystems be aware of poisoned page we should consider: - The page should be not written back: clearing dirty flag could prevent from writeback. - The page should not be dropped (it shows as a clean page) by drop caches or other callers: the refcount pin from hwpoison could prevent from invalidating (called by cache drop, inode cache shrinking, etc), but it doesn't avoid invalidation in DIO path. - The page should be able to get truncated/hole punched/unlinked: it works as it is. - Notify users when the page is accessed, e.g. read/write, page fault and other paths (compression, encryption, etc). The scope of the last one is huge since almost all filesystems need do it once a page is returned from page cache lookup. There are a couple of options to do it: 1. Check hwpoison flag for every path, the most straightforward way. 2. Return NULL for poisoned page from page cache lookup, the most callsites check if NULL is returned, this should have least work I think. But the error handling in filesystems just return -ENOMEM, the error code will incur confusion to the users obviously. 3. To improve #2, we could return error pointer, e.g. ERR_PTR(-EIO), but this will involve significant amount of code change as well since all the paths need check if the pointer is ERR or not just like option #1. I did prototypes for both #1 and #3, but it seems #3 may require more changes than #1. For #3 ERR_PTR will be returned so all the callers need to check the return value otherwise invalid pointer may be dereferenced, but not all callers really care about the content of the page, for example, partial truncate which just sets the truncated range in one page to 0. So for such paths it needs additional modification if ERR_PTR is returned. And if the callers have their own way to handle the problematic pages we need to add a new FGP flag to tell FGP functions to return the pointer to the page. It may happen very rarely, but once it happens the consequence (data corruption) could be very bad and it is very hard to debug. It seems this problem had been slightly discussed before, but seems no action was taken at that time. [2] As the aforementioned investigation, it needs huge amount of work to solve the potential data loss for all filesystems. But it is much easier for in-memory filesystems and such filesystems actually suffer more than others since even the data blocks are gone due to truncating. So this patchset starts from shmem/tmpfs by taking option #1. TODO: * The unpoison has been broken since commit 0ed950d1f281 ("mm,hwpoison: make get_hwpoison_page() call get_any_page()"), and this patch series make refcount check for unpoisoning shmem page fail. * Expand to other filesystems. But I haven't heard feedback from filesystem developers yet. Patch breakdown: Patch #1: cleanup, depended by patch #2 Patch #2: fix THP with hwpoisoned subpage(s) PMD map bug Patch #3: coding style cleanup Patch #4: refactor and preparation. Patch #5: keep the poisoned page in page cache and handle such case for all the paths. Patch #6: the previous patches unblock page cache THP split, so this patch add page cache THP split support. This patch (of 4): A minor cleanup to the indent. Link: https://lkml.kernel.org/r/20211020210755.23964-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20211020210755.23964-4-shy828301@gmail.com Signed-off-by: Yang Shi Reviewed-by: Naoya Horiguchi Cc: Hugh Dickins Cc: Kirill A. Shutemov Cc: Matthew Wilcox Cc: Oscar Salvador Cc: Peter Xu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index d05f8013a4f0f8..6f2c4bd6a571fb 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3203,12 +3203,12 @@ static bool filemap_map_pmd(struct vm_fault *vmf, struct page *page) } if (pmd_none(*vmf->pmd) && PageTransHuge(page)) { - vm_fault_t ret = do_set_pmd(vmf, page); - if (!ret) { - /* The page is mapped successfully, reference consumed. */ - unlock_page(page); - return true; - } + vm_fault_t ret = do_set_pmd(vmf, page); + if (!ret) { + /* The page is mapped successfully, reference consumed. */ + unlock_page(page); + return true; + } } if (pmd_none(*vmf->pmd)) -- cgit 1.2.3-korg From 8cd7c588decf470bf7e14f2be93b709f839a965e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 5 Nov 2021 13:42:25 -0700 Subject: mm/vmscan: throttle reclaim until some writeback completes if congested Patch series "Remove dependency on congestion_wait in mm/", v5. This series that removes all calls to congestion_wait in mm/ and deletes wait_iff_congested. It's not a clever implementation but congestion_wait has been broken for a long time [1]. Even if congestion throttling worked, it was never a great idea. While excessive dirty/writeback pages at the tail of the LRU is one possibility that reclaim may be slow, there is also the problem of too many pages being isolated and reclaim failing for other reasons (elevated references, too many pages isolated, excessive LRU contention etc). This series replaces the "congestion" throttling with 3 different types. - If there are too many dirty/writeback pages, sleep until a timeout or enough pages get cleaned - If too many pages are isolated, sleep until enough isolated pages are either reclaimed or put back on the LRU - If no progress is being made, direct reclaim tasks sleep until another task makes progress with acceptable efficiency. This was initially tested with a mix of workloads that used to trigger corner cases that no longer work. A new test case was created called "stutterp" (pagereclaim-stutterp-noreaders in mmtests) using a freshly created XFS filesystem. Note that it may be necessary to increase the timeout of ssh if executing remotely as ssh itself can get throttled and the connection may timeout. stutterp varies the number of "worker" processes from 4 up to NR_CPUS*4 to check the impact as the number of direct reclaimers increase. It has four types of worker. - One "anon latency" worker creates small mappings with mmap() and times how long it takes to fault the mapping reading it 4K at a time - X file writers which is fio randomly writing X files where the total size of the files add up to the allowed dirty_ratio. fio is allowed to run for a warmup period to allow some file-backed pages to accumulate. The duration of the warmup is based on the best-case linear write speed of the storage. - Y file readers which is fio randomly reading small files - Z anon memory hogs which continually map (100-dirty_ratio)% of memory - Total estimated WSS = (100+dirty_ration) percentage of memory X+Y+Z+1 == NR_WORKERS varying from 4 up to NR_CPUS*4 The intent is to maximise the total WSS with a mix of file and anon memory where some anonymous memory must be swapped and there is a high likelihood of dirty/writeback pages reaching the end of the LRU. The test can be configured to have no background readers to stress dirty/writeback pages. The results below are based on having zero readers. The short summary of the results is that the series works and stalls until some event occurs but the timeouts may need adjustment. The test results are not broken down by patch as the series should be treated as one block that replaces a broken throttling mechanism with a working one. Finally, three machines were tested but I'm reporting the worst set of results. The other two machines had much better latencies for example. First the results of the "anon latency" latency stutterp 5.15.0-rc1 5.15.0-rc1 vanilla mm-reclaimcongest-v5r4 Amean mmap-4 31.4003 ( 0.00%) 2661.0198 (-8374.52%) Amean mmap-7 38.1641 ( 0.00%) 149.2891 (-291.18%) Amean mmap-12 60.0981 ( 0.00%) 187.8105 (-212.51%) Amean mmap-21 161.2699 ( 0.00%) 213.9107 ( -32.64%) Amean mmap-30 174.5589 ( 0.00%) 377.7548 (-116.41%) Amean mmap-48 8106.8160 ( 0.00%) 1070.5616 ( 86.79%) Stddev mmap-4 41.3455 ( 0.00%) 27573.9676 (-66591.66%) Stddev mmap-7 53.5556 ( 0.00%) 4608.5860 (-8505.23%) Stddev mmap-12 171.3897 ( 0.00%) 5559.4542 (-3143.75%) Stddev mmap-21 1506.6752 ( 0.00%) 5746.2507 (-281.39%) Stddev mmap-30 557.5806 ( 0.00%) 7678.1624 (-1277.05%) Stddev mmap-48 61681.5718 ( 0.00%) 14507.2830 ( 76.48%) Max-90 mmap-4 31.4243 ( 0.00%) 83.1457 (-164.59%) Max-90 mmap-7 41.0410 ( 0.00%) 41.0720 ( -0.08%) Max-90 mmap-12 66.5255 ( 0.00%) 53.9073 ( 18.97%) Max-90 mmap-21 146.7479 ( 0.00%) 105.9540 ( 27.80%) Max-90 mmap-30 193.9513 ( 0.00%) 64.3067 ( 66.84%) Max-90 mmap-48 277.9137 ( 0.00%) 591.0594 (-112.68%) Max mmap-4 1913.8009 ( 0.00%) 299623.9695 (-15555.96%) Max mmap-7 2423.9665 ( 0.00%) 204453.1708 (-8334.65%) Max mmap-12 6845.6573 ( 0.00%) 221090.3366 (-3129.64%) Max mmap-21 56278.6508 ( 0.00%) 213877.3496 (-280.03%) Max mmap-30 19716.2990 ( 0.00%) 216287.6229 (-997.00%) Max mmap-48 477923.9400 ( 0.00%) 245414.8238 ( 48.65%) For most thread counts, the time to mmap() is unfortunately increased. In earlier versions of the series, this was lower but a large number of throttling events were reaching their timeout increasing the amount of inefficient scanning of the LRU. There is no prioritisation of reclaim tasks making progress based on each tasks rate of page allocation versus progress of reclaim. The variance is also impacted for high worker counts but in all cases, the differences in latency are not statistically significant due to very large maximum outliers. Max-90 shows that 90% of the stalls are comparable but the Max results show the massive outliers which are increased to to stalling. It is expected that this will be very machine dependant. Due to the test design, reclaim is difficult so allocations stall and there are variances depending on whether THPs can be allocated or not. The amount of memory will affect exactly how bad the corner cases are and how often they trigger. The warmup period calculation is not ideal as it's based on linear writes where as fio is randomly writing multiple files from multiple tasks so the start state of the test is variable. For example, these are the latencies on a single-socket machine that had more memory Amean mmap-4 42.2287 ( 0.00%) 49.6838 * -17.65%* Amean mmap-7 216.4326 ( 0.00%) 47.4451 * 78.08%* Amean mmap-12 2412.0588 ( 0.00%) 51.7497 ( 97.85%) Amean mmap-21 5546.2548 ( 0.00%) 51.8862 ( 99.06%) Amean mmap-30 1085.3121 ( 0.00%) 72.1004 ( 93.36%) The overall system CPU usage and elapsed time is as follows 5.15.0-rc3 5.15.0-rc3 vanilla mm-reclaimcongest-v5r4 Duration User 6989.03 983.42 Duration System 7308.12 799.68 Duration Elapsed 2277.67 2092.98 The patches reduce system CPU usage by 89% as the vanilla kernel is rarely stalling. The high-level /proc/vmstats show 5.15.0-rc1 5.15.0-rc1 vanilla mm-reclaimcongest-v5r2 Ops Direct pages scanned 1056608451.00 503594991.00 Ops Kswapd pages scanned 109795048.00 147289810.00 Ops Kswapd pages reclaimed 63269243.00 31036005.00 Ops Direct pages reclaimed 10803973.00 6328887.00 Ops Kswapd efficiency % 57.62 21.07 Ops Kswapd velocity 48204.98 57572.86 Ops Direct efficiency % 1.02 1.26 Ops Direct velocity 463898.83 196845.97 Kswapd scanned less pages but the detailed pattern is different. The vanilla kernel scans slowly over time where as the patches exhibits burst patterns of scan activity. Direct reclaim scanning is reduced by 52% due to stalling. The pattern for stealing pages is also slightly different. Both kernels exhibit spikes but the vanilla kernel when reclaiming shows pages being reclaimed over a period of time where as the patches tend to reclaim in spikes. The difference is that vanilla is not throttling and instead scanning constantly finding some pages over time where as the patched kernel throttles and reclaims in spikes. Ops Percentage direct scans 90.59 77.37 For direct reclaim, vanilla scanned 90.59% of pages where as with the patches, 77.37% were direct reclaim due to throttling Ops Page writes by reclaim 2613590.00 1687131.00 Page writes from reclaim context are reduced. Ops Page writes anon 2932752.00 1917048.00 And there is less swapping. Ops Page reclaim immediate 996248528.00 107664764.00 The number of pages encountered at the tail of the LRU tagged for immediate reclaim but still dirty/writeback is reduced by 89%. Ops Slabs scanned 164284.00 153608.00 Slab scan activity is similar. ftrace was used to gather stall activity Vanilla ------- 1 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=16000 2 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=12000 8 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=8000 29 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=4000 82394 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=0 The fast majority of wait_iff_congested calls do not stall at all. What is likely happening is that cond_resched() reschedules the task for a short period when the BDI is not registering congestion (which it never will in this test setup). 1 writeback_congestion_wait: usec_timeout=100000 usec_delayed=120000 2 writeback_congestion_wait: usec_timeout=100000 usec_delayed=132000 4 writeback_congestion_wait: usec_timeout=100000 usec_delayed=112000 380 writeback_congestion_wait: usec_timeout=100000 usec_delayed=108000 778 writeback_congestion_wait: usec_timeout=100000 usec_delayed=104000 congestion_wait if called always exceeds the timeout as there is no trigger to wake it up. Bottom line: Vanilla will throttle but it's not effective. Patch series ------------ Kswapd throttle activity was always due to scanning pages tagged for immediate reclaim at the tail of the LRU 1 usec_timeout=100000 usect_delayed=72000 reason=VMSCAN_THROTTLE_WRITEBACK 4 usec_timeout=100000 usect_delayed=20000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=12000 reason=VMSCAN_THROTTLE_WRITEBACK 6 usec_timeout=100000 usect_delayed=16000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=100000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=8000 reason=VMSCAN_THROTTLE_WRITEBACK 94 usec_timeout=100000 usect_delayed=0 reason=VMSCAN_THROTTLE_WRITEBACK 112 usec_timeout=100000 usect_delayed=4000 reason=VMSCAN_THROTTLE_WRITEBACK The majority of events did not stall or stalled for a short period. Roughly 16% of stalls reached the timeout before expiry. For direct reclaim, the number of times stalled for each reason were 6624 reason=VMSCAN_THROTTLE_ISOLATED 93246 reason=VMSCAN_THROTTLE_NOPROGRESS 96934 reason=VMSCAN_THROTTLE_WRITEBACK The most common reason to stall was due to excessive pages tagged for immediate reclaim at the tail of the LRU followed by a failure to make forward. A relatively small number were due to too many pages isolated from the LRU by parallel threads For VMSCAN_THROTTLE_ISOLATED, the breakdown of delays was 9 usec_timeout=20000 usect_delayed=4000 reason=VMSCAN_THROTTLE_ISOLATED 12 usec_timeout=20000 usect_delayed=16000 reason=VMSCAN_THROTTLE_ISOLATED 83 usec_timeout=20000 usect_delayed=20000 reason=VMSCAN_THROTTLE_ISOLATED 6520 usec_timeout=20000 usect_delayed=0 reason=VMSCAN_THROTTLE_ISOLATED Most did not stall at all. A small number reached the timeout. For VMSCAN_THROTTLE_NOPROGRESS, the breakdown of stalls were all over the map 1 usec_timeout=500000 usect_delayed=324000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=332000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=348000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=360000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=228000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=260000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=340000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=364000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=372000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=428000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=460000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=464000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=244000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=252000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=272000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=188000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=268000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=328000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=380000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=392000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=432000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=204000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=220000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=412000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=436000 reason=VMSCAN_THROTTLE_NOPROGRESS 6 usec_timeout=500000 usect_delayed=488000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=212000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=300000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=316000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=472000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=248000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=356000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=456000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=124000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=376000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=484000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=172000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=420000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=452000 reason=VMSCAN_THROTTLE_NOPROGRESS 11 usec_timeout=500000 usect_delayed=256000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=112000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=116000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=144000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=152000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=264000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=384000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=424000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=492000 reason=VMSCAN_THROTTLE_NOPROGRESS 13 usec_timeout=500000 usect_delayed=184000 reason=VMSCAN_THROTTLE_NOPROGRESS 13 usec_timeout=500000 usect_delayed=444000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=308000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=440000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=476000 reason=VMSCAN_THROTTLE_NOPROGRESS 16 usec_timeout=500000 usect_delayed=140000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=232000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=240000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=280000 reason=VMSCAN_THROTTLE_NOPROGRESS 18 usec_timeout=500000 usect_delayed=404000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=148000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=216000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=468000 reason=VMSCAN_THROTTLE_NOPROGRESS 21 usec_timeout=500000 usect_delayed=448000 reason=VMSCAN_THROTTLE_NOPROGRESS 23 usec_timeout=500000 usect_delayed=168000 reason=VMSCAN_THROTTLE_NOPROGRESS 23 usec_timeout=500000 usect_delayed=296000 reason=VMSCAN_THROTTLE_NOPROGRESS 25 usec_timeout=500000 usect_delayed=132000 reason=VMSCAN_THROTTLE_NOPROGRESS 25 usec_timeout=500000 usect_delayed=352000 reason=VMSCAN_THROTTLE_NOPROGRESS 26 usec_timeout=500000 usect_delayed=180000 reason=VMSCAN_THROTTLE_NOPROGRESS 27 usec_timeout=500000 usect_delayed=284000 reason=VMSCAN_THROTTLE_NOPROGRESS 28 usec_timeout=500000 usect_delayed=164000 reason=VMSCAN_THROTTLE_NOPROGRESS 29 usec_timeout=500000 usect_delayed=136000 reason=VMSCAN_THROTTLE_NOPROGRESS 30 usec_timeout=500000 usect_delayed=200000 reason=VMSCAN_THROTTLE_NOPROGRESS 30 usec_timeout=500000 usect_delayed=400000 reason=VMSCAN_THROTTLE_NOPROGRESS 31 usec_timeout=500000 usect_delayed=196000 reason=VMSCAN_THROTTLE_NOPROGRESS 32 usec_timeout=500000 usect_delayed=156000 reason=VMSCAN_THROTTLE_NOPROGRESS 33 usec_timeout=500000 usect_delayed=224000 reason=VMSCAN_THROTTLE_NOPROGRESS 35 usec_timeout=500000 usect_delayed=128000 reason=VMSCAN_THROTTLE_NOPROGRESS 35 usec_timeout=500000 usect_delayed=176000 reason=VMSCAN_THROTTLE_NOPROGRESS 36 usec_timeout=500000 usect_delayed=368000 reason=VMSCAN_THROTTLE_NOPROGRESS 36 usec_timeout=500000 usect_delayed=496000 reason=VMSCAN_THROTTLE_NOPROGRESS 37 usec_timeout=500000 usect_delayed=312000 reason=VMSCAN_THROTTLE_NOPROGRESS 38 usec_timeout=500000 usect_delayed=304000 reason=VMSCAN_THROTTLE_NOPROGRESS 40 usec_timeout=500000 usect_delayed=288000 reason=VMSCAN_THROTTLE_NOPROGRESS 43 usec_timeout=500000 usect_delayed=408000 reason=VMSCAN_THROTTLE_NOPROGRESS 55 usec_timeout=500000 usect_delayed=416000 reason=VMSCAN_THROTTLE_NOPROGRESS 56 usec_timeout=500000 usect_delayed=76000 reason=VMSCAN_THROTTLE_NOPROGRESS 58 usec_timeout=500000 usect_delayed=120000 reason=VMSCAN_THROTTLE_NOPROGRESS 59 usec_timeout=500000 usect_delayed=208000 reason=VMSCAN_THROTTLE_NOPROGRESS 61 usec_timeout=500000 usect_delayed=68000 reason=VMSCAN_THROTTLE_NOPROGRESS 71 usec_timeout=500000 usect_delayed=192000 reason=VMSCAN_THROTTLE_NOPROGRESS 71 usec_timeout=500000 usect_delayed=480000 reason=VMSCAN_THROTTLE_NOPROGRESS 79 usec_timeout=500000 usect_delayed=60000 reason=VMSCAN_THROTTLE_NOPROGRESS 82 usec_timeout=500000 usect_delayed=320000 reason=VMSCAN_THROTTLE_NOPROGRESS 82 usec_timeout=500000 usect_delayed=92000 reason=VMSCAN_THROTTLE_NOPROGRESS 85 usec_timeout=500000 usect_delayed=64000 reason=VMSCAN_THROTTLE_NOPROGRESS 85 usec_timeout=500000 usect_delayed=80000 reason=VMSCAN_THROTTLE_NOPROGRESS 88 usec_timeout=500000 usect_delayed=84000 reason=VMSCAN_THROTTLE_NOPROGRESS 90 usec_timeout=500000 usect_delayed=160000 reason=VMSCAN_THROTTLE_NOPROGRESS 90 usec_timeout=500000 usect_delayed=292000 reason=VMSCAN_THROTTLE_NOPROGRESS 94 usec_timeout=500000 usect_delayed=56000 reason=VMSCAN_THROTTLE_NOPROGRESS 118 usec_timeout=500000 usect_delayed=88000 reason=VMSCAN_THROTTLE_NOPROGRESS 119 usec_timeout=500000 usect_delayed=72000 reason=VMSCAN_THROTTLE_NOPROGRESS 126 usec_timeout=500000 usect_delayed=108000 reason=VMSCAN_THROTTLE_NOPROGRESS 146 usec_timeout=500000 usect_delayed=52000 reason=VMSCAN_THROTTLE_NOPROGRESS 148 usec_timeout=500000 usect_delayed=36000 reason=VMSCAN_THROTTLE_NOPROGRESS 148 usec_timeout=500000 usect_delayed=48000 reason=VMSCAN_THROTTLE_NOPROGRESS 159 usec_timeout=500000 usect_delayed=28000 reason=VMSCAN_THROTTLE_NOPROGRESS 178 usec_timeout=500000 usect_delayed=44000 reason=VMSCAN_THROTTLE_NOPROGRESS 183 usec_timeout=500000 usect_delayed=40000 reason=VMSCAN_THROTTLE_NOPROGRESS 237 usec_timeout=500000 usect_delayed=100000 reason=VMSCAN_THROTTLE_NOPROGRESS 266 usec_timeout=500000 usect_delayed=32000 reason=VMSCAN_THROTTLE_NOPROGRESS 313 usec_timeout=500000 usect_delayed=24000 reason=VMSCAN_THROTTLE_NOPROGRESS 347 usec_timeout=500000 usect_delayed=96000 reason=VMSCAN_THROTTLE_NOPROGRESS 470 usec_timeout=500000 usect_delayed=20000 reason=VMSCAN_THROTTLE_NOPROGRESS 559 usec_timeout=500000 usect_delayed=16000 reason=VMSCAN_THROTTLE_NOPROGRESS 964 usec_timeout=500000 usect_delayed=12000 reason=VMSCAN_THROTTLE_NOPROGRESS 2001 usec_timeout=500000 usect_delayed=104000 reason=VMSCAN_THROTTLE_NOPROGRESS 2447 usec_timeout=500000 usect_delayed=8000 reason=VMSCAN_THROTTLE_NOPROGRESS 7888 usec_timeout=500000 usect_delayed=4000 reason=VMSCAN_THROTTLE_NOPROGRESS 22727 usec_timeout=500000 usect_delayed=0 reason=VMSCAN_THROTTLE_NOPROGRESS 51305 usec_timeout=500000 usect_delayed=500000 reason=VMSCAN_THROTTLE_NOPROGRESS The full timeout is often hit but a large number also do not stall at all. The remainder slept a little allowing other reclaim tasks to make progress. While this timeout could be further increased, it could also negatively impact worst-case behaviour when there is no prioritisation of what task should make progress. For VMSCAN_THROTTLE_WRITEBACK, the breakdown was 1 usec_timeout=100000 usect_delayed=44000 reason=VMSCAN_THROTTLE_WRITEBACK 2 usec_timeout=100000 usect_delayed=76000 reason=VMSCAN_THROTTLE_WRITEBACK 3 usec_timeout=100000 usect_delayed=80000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=48000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=84000 reason=VMSCAN_THROTTLE_WRITEBACK 6 usec_timeout=100000 usect_delayed=72000 reason=VMSCAN_THROTTLE_WRITEBACK 7 usec_timeout=100000 usect_delayed=88000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=56000 reason=VMSCAN_THROTTLE_WRITEBACK 12 usec_timeout=100000 usect_delayed=64000 reason=VMSCAN_THROTTLE_WRITEBACK 16 usec_timeout=100000 usect_delayed=92000 reason=VMSCAN_THROTTLE_WRITEBACK 24 usec_timeout=100000 usect_delayed=68000 reason=VMSCAN_THROTTLE_WRITEBACK 28 usec_timeout=100000 usect_delayed=32000 reason=VMSCAN_THROTTLE_WRITEBACK 30 usec_timeout=100000 usect_delayed=60000 reason=VMSCAN_THROTTLE_WRITEBACK 30 usec_timeout=100000 usect_delayed=96000 reason=VMSCAN_THROTTLE_WRITEBACK 32 usec_timeout=100000 usect_delayed=52000 reason=VMSCAN_THROTTLE_WRITEBACK 42 usec_timeout=100000 usect_delayed=40000 reason=VMSCAN_THROTTLE_WRITEBACK 77 usec_timeout=100000 usect_delayed=28000 reason=VMSCAN_THROTTLE_WRITEBACK 99 usec_timeout=100000 usect_delayed=36000 reason=VMSCAN_THROTTLE_WRITEBACK 137 usec_timeout=100000 usect_delayed=24000 reason=VMSCAN_THROTTLE_WRITEBACK 190 usec_timeout=100000 usect_delayed=20000 reason=VMSCAN_THROTTLE_WRITEBACK 339 usec_timeout=100000 usect_delayed=16000 reason=VMSCAN_THROTTLE_WRITEBACK 518 usec_timeout=100000 usect_delayed=12000 reason=VMSCAN_THROTTLE_WRITEBACK 852 usec_timeout=100000 usect_delayed=8000 reason=VMSCAN_THROTTLE_WRITEBACK 3359 usec_timeout=100000 usect_delayed=4000 reason=VMSCAN_THROTTLE_WRITEBACK 7147 usec_timeout=100000 usect_delayed=0 reason=VMSCAN_THROTTLE_WRITEBACK 83962 usec_timeout=100000 usect_delayed=100000 reason=VMSCAN_THROTTLE_WRITEBACK The majority hit the timeout in direct reclaim context although a sizable number did not stall at all. This is very different to kswapd where only a tiny percentage of stalls due to writeback reached the timeout. Bottom line, the throttling appears to work and the wakeup events may limit worst case stalls. There might be some grounds for adjusting timeouts but it's likely futile as the worst-case scenarios depend on the workload, memory size and the speed of the storage. A better approach to improve the series further would be to prioritise tasks based on their rate of allocation with the caveat that it may be very expensive to track. This patch (of 5): Page reclaim throttles on wait_iff_congested under the following conditions: - kswapd is encountering pages under writeback and marked for immediate reclaim implying that pages are cycling through the LRU faster than pages can be cleaned. - Direct reclaim will stall if all dirty pages are backed by congested inodes. wait_iff_congested is almost completely broken with few exceptions. This patch adds a new node-based workqueue and tracks the number of throttled tasks and pages written back since throttling started. If enough pages belonging to the node are written back then the throttled tasks will wake early. If not, the throttled tasks sleeps until the timeout expires. [neilb@suse.de: Uninterruptible sleep and simpler wakeups] [hdanton@sina.com: Avoid race when reclaim starts] [vbabka@suse.cz: vmstat irq-safe api, clarifications] Link: https://lore.kernel.org/linux-mm/45d8b7a6-8548-65f5-cccf-9f451d4ae3d4@kernel.dk/ [1] Link: https://lkml.kernel.org/r/20211022144651.19914-1-mgorman@techsingularity.net Link: https://lkml.kernel.org/r/20211022144651.19914-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: NeilBrown Cc: "Theodore Ts'o" Cc: Andreas Dilger Cc: "Darrick J . Wong" Cc: Matthew Wilcox Cc: Michal Hocko Cc: Dave Chinner Cc: Rik van Riel Cc: Johannes Weiner Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev.h | 1 - include/linux/mmzone.h | 13 +++++++ include/trace/events/vmscan.h | 34 +++++++++++++++++ include/trace/events/writeback.h | 7 ---- mm/backing-dev.c | 48 ----------------------- mm/filemap.c | 1 + mm/internal.h | 11 ++++++ mm/page_alloc.c | 5 +++ mm/vmscan.c | 82 ++++++++++++++++++++++++++++++++++------ mm/vmstat.c | 1 + 10 files changed, 135 insertions(+), 68 deletions(-) (limited to 'mm/filemap.c') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index ac7f231b88258b..9fb1f0ae273c81 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -154,7 +154,6 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) } long congestion_wait(int sync, long timeout); -long wait_iff_congested(int sync, long timeout); static inline bool mapping_can_writeback(struct address_space *mapping) { diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fb36a29e3aaeb6..5a5e19b90dab37 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -199,6 +199,7 @@ enum node_stat_item { NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ + NR_THROTTLED_WRITTEN, /* NR_WRITTEN while reclaim throttled */ NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_FOLL_PIN_ACQUIRED, /* via: pin_user_page(), gup flag: FOLL_PIN */ NR_FOLL_PIN_RELEASED, /* pages returned via unpin_user_page() */ @@ -272,6 +273,11 @@ enum lru_list { NR_LRU_LISTS }; +enum vmscan_throttle_state { + VMSCAN_THROTTLE_WRITEBACK, + NR_VMSCAN_THROTTLE, +}; + #define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++) #define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++) @@ -841,6 +847,13 @@ typedef struct pglist_data { int node_id; wait_queue_head_t kswapd_wait; wait_queue_head_t pfmemalloc_wait; + + /* workqueues for throttling reclaim for different reasons. */ + wait_queue_head_t reclaim_wait[NR_VMSCAN_THROTTLE]; + + atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */ + unsigned long nr_reclaim_start; /* nr pages written while throttled + * when throttling started. */ struct task_struct *kswapd; /* Protected by mem_hotplug_begin/end() */ int kswapd_order; diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 88faf2400ec253..c317f9fe0d175a 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -27,6 +27,14 @@ {RECLAIM_WB_ASYNC, "RECLAIM_WB_ASYNC"} \ ) : "RECLAIM_WB_NONE" +#define _VMSCAN_THROTTLE_WRITEBACK (1 << VMSCAN_THROTTLE_WRITEBACK) + +#define show_throttle_flags(flags) \ + (flags) ? __print_flags(flags, "|", \ + {_VMSCAN_THROTTLE_WRITEBACK, "VMSCAN_THROTTLE_WRITEBACK"} \ + ) : "VMSCAN_THROTTLE_NONE" + + #define trace_reclaim_flags(file) ( \ (file ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \ (RECLAIM_WB_ASYNC) \ @@ -454,6 +462,32 @@ DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_node_reclaim_end, TP_ARGS(nr_reclaimed) ); +TRACE_EVENT(mm_vmscan_throttled, + + TP_PROTO(int nid, int usec_timeout, int usec_delayed, int reason), + + TP_ARGS(nid, usec_timeout, usec_delayed, reason), + + TP_STRUCT__entry( + __field(int, nid) + __field(int, usec_timeout) + __field(int, usec_delayed) + __field(int, reason) + ), + + TP_fast_assign( + __entry->nid = nid; + __entry->usec_timeout = usec_timeout; + __entry->usec_delayed = usec_delayed; + __entry->reason = 1U << reason; + ), + + TP_printk("nid=%d usec_timeout=%d usect_delayed=%d reason=%s", + __entry->nid, + __entry->usec_timeout, + __entry->usec_delayed, + show_throttle_flags(__entry->reason)) +); #endif /* _TRACE_VMSCAN_H */ /* This part must be outside protection */ diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 840d1ba84cf5cc..3bc759b818974a 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -763,13 +763,6 @@ DEFINE_EVENT(writeback_congest_waited_template, writeback_congestion_wait, TP_ARGS(usec_timeout, usec_delayed) ); -DEFINE_EVENT(writeback_congest_waited_template, writeback_wait_iff_congested, - - TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), - - TP_ARGS(usec_timeout, usec_delayed) -); - DECLARE_EVENT_CLASS(writeback_single_inode_template, TP_PROTO(struct inode *inode, diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 5ccb250898083a..3d2983752e242d 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -1038,51 +1038,3 @@ long congestion_wait(int sync, long timeout) return ret; } EXPORT_SYMBOL(congestion_wait); - -/** - * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a pgdat to complete writes - * @sync: SYNC or ASYNC IO - * @timeout: timeout in jiffies - * - * In the event of a congested backing_dev (any backing_dev) this waits - * for up to @timeout jiffies for either a BDI to exit congestion of the - * given @sync queue or a write to complete. - * - * The return value is 0 if the sleep is for the full timeout. Otherwise, - * it is the number of jiffies that were still remaining when the function - * returned. return_value == timeout implies the function did not sleep. - */ -long wait_iff_congested(int sync, long timeout) -{ - long ret; - unsigned long start = jiffies; - DEFINE_WAIT(wait); - wait_queue_head_t *wqh = &congestion_wqh[sync]; - - /* - * If there is no congestion, yield if necessary instead - * of sleeping on the congestion queue - */ - if (atomic_read(&nr_wb_congested[sync]) == 0) { - cond_resched(); - - /* In case we scheduled, work out time remaining */ - ret = timeout - (jiffies - start); - if (ret < 0) - ret = 0; - - goto out; - } - - /* Sleep until uncongested or a write happens */ - prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); - ret = io_schedule_timeout(timeout); - finish_wait(wqh, &wait); - -out: - trace_writeback_wait_iff_congested(jiffies_to_usecs(timeout), - jiffies_to_usecs(jiffies - start)); - - return ret; -} -EXPORT_SYMBOL(wait_iff_congested); diff --git a/mm/filemap.c b/mm/filemap.c index 6f2c4bd6a571fb..b6140debc2da37 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1612,6 +1612,7 @@ void end_page_writeback(struct page *page) smp_mb__after_atomic(); wake_up_page(page, PG_writeback); + acct_reclaim_writeback(page); put_page(page); } EXPORT_SYMBOL(end_page_writeback); diff --git a/mm/internal.h b/mm/internal.h index 6c3e1a9f8c5a6a..a59b5626f9688b 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -34,6 +34,17 @@ void page_writeback_init(void); +void __acct_reclaim_writeback(pg_data_t *pgdat, struct page *page, + int nr_throttled); +static inline void acct_reclaim_writeback(struct page *page) +{ + pg_data_t *pgdat = page_pgdat(page); + int nr_throttled = atomic_read(&pgdat->nr_writeback_throttled); + + if (nr_throttled) + __acct_reclaim_writeback(pgdat, page, nr_throttled); +} + vm_fault_t do_swap_page(struct vm_fault *vmf); void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 09a0f1c5d5d26b..0f1f1f3532117b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7408,6 +7408,8 @@ static void pgdat_init_kcompactd(struct pglist_data *pgdat) {} static void __meminit pgdat_init_internals(struct pglist_data *pgdat) { + int i; + pgdat_resize_init(pgdat); pgdat_init_split_queue(pgdat); @@ -7416,6 +7418,9 @@ static void __meminit pgdat_init_internals(struct pglist_data *pgdat) init_waitqueue_head(&pgdat->kswapd_wait); init_waitqueue_head(&pgdat->pfmemalloc_wait); + for (i = 0; i < NR_VMSCAN_THROTTLE; i++) + init_waitqueue_head(&pgdat->reclaim_wait[i]); + pgdat_page_ext_init(pgdat); lruvec_init(&pgdat->__lruvec); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 9483dd6af5500e..09beeb55546c8b 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1006,6 +1006,64 @@ static void handle_write_error(struct address_space *mapping, unlock_page(page); } +static void +reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason, + long timeout) +{ + wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason]; + long ret; + DEFINE_WAIT(wait); + + /* + * Do not throttle IO workers, kthreads other than kswapd or + * workqueues. They may be required for reclaim to make + * forward progress (e.g. journalling workqueues or kthreads). + */ + if (!current_is_kswapd() && + current->flags & (PF_IO_WORKER|PF_KTHREAD)) + return; + + if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) { + WRITE_ONCE(pgdat->nr_reclaim_start, + node_page_state(pgdat, NR_THROTTLED_WRITTEN)); + } + + prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); + ret = schedule_timeout(timeout); + finish_wait(wqh, &wait); + atomic_dec(&pgdat->nr_writeback_throttled); + + trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout), + jiffies_to_usecs(timeout - ret), + reason); +} + +/* + * Account for pages written if tasks are throttled waiting on dirty + * pages to clean. If enough pages have been cleaned since throttling + * started then wakeup the throttled tasks. + */ +void __acct_reclaim_writeback(pg_data_t *pgdat, struct page *page, + int nr_throttled) +{ + unsigned long nr_written; + + inc_node_page_state(page, NR_THROTTLED_WRITTEN); + + /* + * This is an inaccurate read as the per-cpu deltas may not + * be synchronised. However, given that the system is + * writeback throttled, it is not worth taking the penalty + * of getting an accurate count. At worst, the throttle + * timeout guarantees forward progress. + */ + nr_written = node_page_state(pgdat, NR_THROTTLED_WRITTEN) - + READ_ONCE(pgdat->nr_reclaim_start); + + if (nr_written > SWAP_CLUSTER_MAX * nr_throttled) + wake_up(&pgdat->reclaim_wait[VMSCAN_THROTTLE_WRITEBACK]); +} + /* possible outcome of pageout() */ typedef enum { /* failed to write page out, page is locked */ @@ -1411,9 +1469,8 @@ static unsigned int shrink_page_list(struct list_head *page_list, /* * The number of dirty pages determines if a node is marked - * reclaim_congested which affects wait_iff_congested. kswapd - * will stall and start writing pages if the tail of the LRU - * is all dirty unqueued pages. + * reclaim_congested. kswapd will stall and start writing + * pages if the tail of the LRU is all dirty unqueued pages. */ page_check_dirty_writeback(page, &dirty, &writeback); if (dirty || writeback) @@ -3179,19 +3236,19 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) * If kswapd scans pages marked for immediate * reclaim and under writeback (nr_immediate), it * implies that pages are cycling through the LRU - * faster than they are written so also forcibly stall. + * faster than they are written so forcibly stall + * until some pages complete writeback. */ if (sc->nr.immediate) - congestion_wait(BLK_RW_ASYNC, HZ/10); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK, HZ/10); } /* - * Tag a node/memcg as congested if all the dirty pages - * scanned were backed by a congested BDI and - * wait_iff_congested will stall. + * Tag a node/memcg as congested if all the dirty pages were marked + * for writeback and immediate reclaim (counted in nr.congested). * * Legacy memcg will stall in page writeback so avoid forcibly - * stalling in wait_iff_congested(). + * stalling in reclaim_throttle(). */ if ((current_is_kswapd() || (cgroup_reclaim(sc) && writeback_throttling_sane(sc))) && @@ -3199,15 +3256,15 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) set_bit(LRUVEC_CONGESTED, &target_lruvec->flags); /* - * Stall direct reclaim for IO completions if underlying BDIs - * and node is congested. Allow kswapd to continue until it + * Stall direct reclaim for IO completions if the lruvec is + * node is congested. Allow kswapd to continue until it * starts encountering unqueued dirty pages or cycling through * the LRU too quickly. */ if (!current_is_kswapd() && current_may_throttle() && !sc->hibernation_mode && test_bit(LRUVEC_CONGESTED, &target_lruvec->flags)) - wait_iff_congested(BLK_RW_ASYNC, HZ/10); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK, HZ/10); if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, sc)) @@ -4285,6 +4342,7 @@ static int kswapd(void *p) WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); + atomic_set(&pgdat->nr_writeback_throttled, 0); for ( ; ; ) { bool ret; diff --git a/mm/vmstat.c b/mm/vmstat.c index ae87c90e0b4e90..0f4643e5324d3a 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1225,6 +1225,7 @@ const char * const vmstat_text[] = { "nr_vmscan_immediate_reclaim", "nr_dirtied", "nr_written", + "nr_throttled_written", "nr_kernel_misc_reclaimable", "nr_foll_pin_acquired", "nr_foll_pin_released", -- cgit 1.2.3-korg