From af6a311384bce6c88e15c80ab22ab051a918b4eb Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Mon, 3 Oct 2011 20:46:17 -0600 Subject: writeback: add bg_threshold parameter to __bdi_update_bandwidth() No behavior change. Signed-off-by: Wu Fengguang --- fs/fs-writeback.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 04cf3b91e50..28076562ada 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -675,7 +675,7 @@ static inline bool over_bground_thresh(void) static void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time) { - __bdi_update_bandwidth(wb->bdi, 0, 0, 0, 0, start_time); + __bdi_update_bandwidth(wb->bdi, 0, 0, 0, 0, 0, start_time); } /* -- cgit v1.2.3 From b00949aa2df9970a912bf060bc95e99da356881c Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Thu, 18 Nov 2010 14:38:33 -0600 Subject: writeback: per-bdi background threshold One thing puzzled me is that in JBOD case, the per-disk writeout performance is smaller than the corresponding single-disk case even when they have comparable bdi_thresh. Tracing shows find that in single disk case, bdi_writeback is always kept high while in JBOD case, it could drop low from time to time and correspondingly bdi_reclaimable could sometimes rush high. The fix is to watch bdi_reclaimable and kick background writeback as soon as it goes high. This resembles the global background threshold but in per-bdi manner. The trick is, as long as bdi_reclaimable does not go high, bdi_writeback naturally won't go low because bdi_reclaimable+bdi_writeback ~= bdi_thresh. With less fluctuated writeback pages, JBOD performance is observed to increase noticeably in various cases. vmstat:nr_written values before/after patch: 3.1.0-rc4-wo-underrun+ 3.1.0-rc4-bgthresh3+ ------------------------ ------------------------ 125596480 +25.9% 158179363 JBOD-10HDD-16G/ext4-100dd-1M-24p-16384M-20:10-X 61790815 +110.4% 130032231 JBOD-10HDD-16G/ext4-10dd-1M-24p-16384M-20:10-X 58853546 -0.1% 58823828 JBOD-10HDD-16G/ext4-1dd-1M-24p-16384M-20:10-X 110159811 +24.7% 137355377 JBOD-10HDD-16G/xfs-100dd-1M-24p-16384M-20:10-X 69544762 +10.8% 77080047 JBOD-10HDD-16G/xfs-10dd-1M-24p-16384M-20:10-X 50644862 +0.5% 50890006 JBOD-10HDD-16G/xfs-1dd-1M-24p-16384M-20:10-X 42677090 +28.0% 54643527 JBOD-10HDD-thresh=100M/ext4-100dd-1M-24p-16384M-100M:10-X 47491324 +13.3% 53785605 JBOD-10HDD-thresh=100M/ext4-10dd-1M-24p-16384M-100M:10-X 52548986 +0.9% 53001031 JBOD-10HDD-thresh=100M/ext4-1dd-1M-24p-16384M-100M:10-X 26783091 +36.8% 36650248 JBOD-10HDD-thresh=100M/xfs-100dd-1M-24p-16384M-100M:10-X 35526347 +14.0% 40492312 JBOD-10HDD-thresh=100M/xfs-10dd-1M-24p-16384M-100M:10-X 44670723 -1.1% 44177606 JBOD-10HDD-thresh=100M/xfs-1dd-1M-24p-16384M-100M:10-X 127996037 +22.4% 156719990 JBOD-10HDD-thresh=2G/ext4-100dd-1M-24p-16384M-2048M:10-X 57518856 +3.8% 59677625 JBOD-10HDD-thresh=2G/ext4-10dd-1M-24p-16384M-2048M:10-X 51919909 +12.2% 58269894 JBOD-10HDD-thresh=2G/ext4-1dd-1M-24p-16384M-2048M:10-X 86410514 +79.0% 154660433 JBOD-10HDD-thresh=2G/xfs-100dd-1M-24p-16384M-2048M:10-X 40132519 +38.6% 55617893 JBOD-10HDD-thresh=2G/xfs-10dd-1M-24p-16384M-2048M:10-X 48423248 +7.5% 52042927 JBOD-10HDD-thresh=2G/xfs-1dd-1M-24p-16384M-2048M:10-X 206041046 +44.1% 296846536 JBOD-10HDD-thresh=4G/xfs-100dd-1M-24p-16384M-4096M:10-X 72312903 -19.4% 58272885 JBOD-10HDD-thresh=4G/xfs-10dd-1M-24p-16384M-4096M:10-X 50635672 -0.5% 50384787 JBOD-10HDD-thresh=4G/xfs-1dd-1M-24p-16384M-4096M:10-X 68308534 +115.7% 147324758 JBOD-10HDD-thresh=800M/ext4-100dd-1M-24p-16384M-800M:10-X 57882933 +14.5% 66269621 JBOD-10HDD-thresh=800M/ext4-10dd-1M-24p-16384M-800M:10-X 52183472 +12.8% 58855181 JBOD-10HDD-thresh=800M/ext4-1dd-1M-24p-16384M-800M:10-X 53788956 +94.2% 104460352 JBOD-10HDD-thresh=800M/xfs-100dd-1M-24p-16384M-800M:10-X 44493342 +35.5% 60298210 JBOD-10HDD-thresh=800M/xfs-10dd-1M-24p-16384M-800M:10-X 42641209 +18.9% 50681038 JBOD-10HDD-thresh=800M/xfs-1dd-1M-24p-16384M-800M:10-X Signed-off-by: Wu Fengguang --- fs/fs-writeback.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 28076562ada..6401cd76f10 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -658,14 +658,21 @@ long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages) return nr_pages - work.nr_pages; } -static inline bool over_bground_thresh(void) +static bool over_bground_thresh(struct backing_dev_info *bdi) { unsigned long background_thresh, dirty_thresh; global_dirty_limits(&background_thresh, &dirty_thresh); - return (global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS) > background_thresh); + if (global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS) > background_thresh) + return true; + + if (bdi_stat(bdi, BDI_RECLAIMABLE) > + bdi_dirty_limit(bdi, background_thresh)) + return true; + + return false; } /* @@ -727,7 +734,7 @@ static long wb_writeback(struct bdi_writeback *wb, * For background writeout, stop when we are below the * background dirty threshold */ - if (work->for_background && !over_bground_thresh()) + if (work->for_background && !over_bground_thresh(wb->bdi)) break; if (work->for_kupdate) { @@ -811,7 +818,7 @@ static unsigned long get_nr_dirty_pages(void) static long wb_check_background_flush(struct bdi_writeback *wb) { - if (over_bground_thresh()) { + if (over_bground_thresh(wb->bdi)) { struct wb_writeback_work work = { .nr_pages = LONG_MAX, -- cgit v1.2.3 From ad4e38dd6a33bb3a4882c487d7abe621e583b982 Mon Sep 17 00:00:00 2001 From: Curt Wohlgemuth Date: Fri, 7 Oct 2011 21:51:56 -0600 Subject: writeback: send work item to queue_io, move_expired_inodes Instead of sending ->older_than_this to queue_io() and move_expired_inodes(), send the entire wb_writeback_work structure. There are other fields of a work item that are useful in these routines and in tracepoints. Acked-by: Jan Kara Signed-off-by: Curt Wohlgemuth Signed-off-by: Wu Fengguang --- fs/fs-writeback.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'fs') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 6401cd76f10..c5102969360 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -251,7 +251,7 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t) */ static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, - unsigned long *older_than_this) + struct wb_writeback_work *work) { LIST_HEAD(tmp); struct list_head *pos, *node; @@ -262,8 +262,8 @@ static int move_expired_inodes(struct list_head *delaying_queue, while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); - if (older_than_this && - inode_dirtied_after(inode, *older_than_this)) + if (work->older_than_this && + inode_dirtied_after(inode, *work->older_than_this)) break; if (sb && sb != inode->i_sb) do_sb_sort = 1; @@ -302,13 +302,13 @@ out: * | * +--> dequeue for IO */ -static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this) +static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work) { int moved; assert_spin_locked(&wb->list_lock); list_splice_init(&wb->b_more_io, &wb->b_io); - moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this); - trace_writeback_queue_io(wb, older_than_this, moved); + moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, work); + trace_writeback_queue_io(wb, work, moved); } static int write_inode(struct inode *inode, struct writeback_control *wbc) @@ -651,7 +651,7 @@ long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages) spin_lock(&wb->list_lock); if (list_empty(&wb->b_io)) - queue_io(wb, NULL); + queue_io(wb, &work); __writeback_inodes_wb(wb, &work); spin_unlock(&wb->list_lock); @@ -745,7 +745,7 @@ static long wb_writeback(struct bdi_writeback *wb, trace_writeback_start(wb->bdi, work); if (list_empty(&wb->b_io)) - queue_io(wb, work->older_than_this); + queue_io(wb, work); if (work->sb) progress = writeback_sb_inodes(work->sb, wb, work); else -- cgit v1.2.3 From 0e175a1835ffc979e55787774e58ec79e41957d7 Mon Sep 17 00:00:00 2001 From: Curt Wohlgemuth Date: Fri, 7 Oct 2011 21:54:10 -0600 Subject: writeback: Add a 'reason' to wb_writeback_work This creates a new 'reason' field in a wb_writeback_work structure, which unambiguously identifies who initiates writeback activity. A 'wb_reason' enumeration has been added to writeback.h, to enumerate the possible reasons. The 'writeback_work_class' and tracepoint event class and 'writeback_queue_io' tracepoints are updated to include the symbolic 'reason' in all trace events. And the 'writeback_inodes_sbXXX' family of routines has had a wb_stats parameter added to them, so callers can specify why writeback is being started. Acked-by: Jan Kara Signed-off-by: Curt Wohlgemuth Signed-off-by: Wu Fengguang --- fs/btrfs/extent-tree.c | 3 ++- fs/buffer.c | 2 +- fs/ext4/inode.c | 2 +- fs/fs-writeback.c | 49 ++++++++++++++++++++++++++++++++++++------------- fs/quota/quota.c | 2 +- fs/sync.c | 4 ++-- fs/ubifs/budget.c | 2 +- 7 files changed, 44 insertions(+), 20 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index f5be06a2462..c9ee0e18bbd 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3340,7 +3340,8 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans, smp_mb(); nr_pages = min_t(unsigned long, nr_pages, root->fs_info->delalloc_bytes >> PAGE_CACHE_SHIFT); - writeback_inodes_sb_nr_if_idle(root->fs_info->sb, nr_pages); + writeback_inodes_sb_nr_if_idle(root->fs_info->sb, nr_pages, + WB_REASON_FS_FREE_SPACE); spin_lock(&space_info->lock); if (reserved > space_info->bytes_reserved) diff --git a/fs/buffer.c b/fs/buffer.c index 1a80b048ade..f5dcee6c4cf 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -285,7 +285,7 @@ static void free_more_memory(void) struct zone *zone; int nid; - wakeup_flusher_threads(1024); + wakeup_flusher_threads(1024, WB_REASON_FREE_MORE_MEM); yield(); for_each_online_node(nid) { diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 986e2388f03..7fa73a3b212 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2241,7 +2241,7 @@ static int ext4_nonda_switch(struct super_block *sb) * start pushing delalloc when 1/2 of free blocks are dirty. */ if (free_blocks < 2 * dirty_blocks) - writeback_inodes_sb_if_idle(sb); + writeback_inodes_sb_if_idle(sb, WB_REASON_FS_FREE_SPACE); return 0; } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index c5102969360..73c3992b2bb 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -41,11 +41,23 @@ struct wb_writeback_work { unsigned int for_kupdate:1; unsigned int range_cyclic:1; unsigned int for_background:1; + enum wb_reason reason; /* why was writeback initiated? */ struct list_head list; /* pending work list */ struct completion *done; /* set if the caller waits */ }; +const char *wb_reason_name[] = { + [WB_REASON_BACKGROUND] = "background", + [WB_REASON_TRY_TO_FREE_PAGES] = "try_to_free_pages", + [WB_REASON_SYNC] = "sync", + [WB_REASON_PERIODIC] = "periodic", + [WB_REASON_LAPTOP_TIMER] = "laptop_timer", + [WB_REASON_FREE_MORE_MEM] = "free_more_memory", + [WB_REASON_FS_FREE_SPACE] = "fs_free_space", + [WB_REASON_FORKER_THREAD] = "forker_thread" +}; + /* * Include the creation of the trace points after defining the * wb_writeback_work structure so that the definition remains local to this @@ -115,7 +127,7 @@ static void bdi_queue_work(struct backing_dev_info *bdi, static void __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, - bool range_cyclic) + bool range_cyclic, enum wb_reason reason) { struct wb_writeback_work *work; @@ -135,6 +147,7 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, work->sync_mode = WB_SYNC_NONE; work->nr_pages = nr_pages; work->range_cyclic = range_cyclic; + work->reason = reason; bdi_queue_work(bdi, work); } @@ -150,9 +163,10 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, * completion. Caller need not hold sb s_umount semaphore. * */ -void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages) +void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, + enum wb_reason reason) { - __bdi_start_writeback(bdi, nr_pages, true); + __bdi_start_writeback(bdi, nr_pages, true, reason); } /** @@ -641,12 +655,14 @@ static long __writeback_inodes_wb(struct bdi_writeback *wb, return wrote; } -long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages) +long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, + enum wb_reason reason) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, + .reason = reason, }; spin_lock(&wb->list_lock); @@ -825,6 +841,7 @@ static long wb_check_background_flush(struct bdi_writeback *wb) .sync_mode = WB_SYNC_NONE, .for_background = 1, .range_cyclic = 1, + .reason = WB_REASON_BACKGROUND, }; return wb_writeback(wb, &work); @@ -858,6 +875,7 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb) .sync_mode = WB_SYNC_NONE, .for_kupdate = 1, .range_cyclic = 1, + .reason = WB_REASON_PERIODIC, }; return wb_writeback(wb, &work); @@ -976,7 +994,7 @@ int bdi_writeback_thread(void *data) * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back * the whole world. */ -void wakeup_flusher_threads(long nr_pages) +void wakeup_flusher_threads(long nr_pages, enum wb_reason reason) { struct backing_dev_info *bdi; @@ -989,7 +1007,7 @@ void wakeup_flusher_threads(long nr_pages) list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { if (!bdi_has_dirty_io(bdi)) continue; - __bdi_start_writeback(bdi, nr_pages, false); + __bdi_start_writeback(bdi, nr_pages, false, reason); } rcu_read_unlock(); } @@ -1210,7 +1228,9 @@ static void wait_sb_inodes(struct super_block *sb) * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ -void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr) +void writeback_inodes_sb_nr(struct super_block *sb, + unsigned long nr, + enum wb_reason reason) { DECLARE_COMPLETION_ONSTACK(done); struct wb_writeback_work work = { @@ -1219,6 +1239,7 @@ void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr) .tagged_writepages = 1, .done = &done, .nr_pages = nr, + .reason = reason, }; WARN_ON(!rwsem_is_locked(&sb->s_umount)); @@ -1235,9 +1256,9 @@ EXPORT_SYMBOL(writeback_inodes_sb_nr); * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ -void writeback_inodes_sb(struct super_block *sb) +void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { - return writeback_inodes_sb_nr(sb, get_nr_dirty_pages()); + return writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); } EXPORT_SYMBOL(writeback_inodes_sb); @@ -1248,11 +1269,11 @@ EXPORT_SYMBOL(writeback_inodes_sb); * Invoke writeback_inodes_sb if no writeback is currently underway. * Returns 1 if writeback was started, 0 if not. */ -int writeback_inodes_sb_if_idle(struct super_block *sb) +int writeback_inodes_sb_if_idle(struct super_block *sb, enum wb_reason reason) { if (!writeback_in_progress(sb->s_bdi)) { down_read(&sb->s_umount); - writeback_inodes_sb(sb); + writeback_inodes_sb(sb, reason); up_read(&sb->s_umount); return 1; } else @@ -1269,11 +1290,12 @@ EXPORT_SYMBOL(writeback_inodes_sb_if_idle); * Returns 1 if writeback was started, 0 if not. */ int writeback_inodes_sb_nr_if_idle(struct super_block *sb, - unsigned long nr) + unsigned long nr, + enum wb_reason reason) { if (!writeback_in_progress(sb->s_bdi)) { down_read(&sb->s_umount); - writeback_inodes_sb_nr(sb, nr); + writeback_inodes_sb_nr(sb, nr, reason); up_read(&sb->s_umount); return 1; } else @@ -1297,6 +1319,7 @@ void sync_inodes_sb(struct super_block *sb) .nr_pages = LONG_MAX, .range_cyclic = 0, .done = &done, + .reason = WB_REASON_SYNC, }; WARN_ON(!rwsem_is_locked(&sb->s_umount)); diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 10b6be3ca28..4bae57fc603 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -286,7 +286,7 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, /* caller already holds s_umount */ if (sb->s_flags & MS_RDONLY) return -EROFS; - writeback_inodes_sb(sb); + writeback_inodes_sb(sb, WB_REASON_SYNC); return 0; default: return -EINVAL; diff --git a/fs/sync.c b/fs/sync.c index c98a7477edf..101b8ef901d 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -43,7 +43,7 @@ static int __sync_filesystem(struct super_block *sb, int wait) if (wait) sync_inodes_sb(sb); else - writeback_inodes_sb(sb); + writeback_inodes_sb(sb, WB_REASON_SYNC); if (sb->s_op->sync_fs) sb->s_op->sync_fs(sb, wait); @@ -98,7 +98,7 @@ static void sync_filesystems(int wait) */ SYSCALL_DEFINE0(sync) { - wakeup_flusher_threads(0); + wakeup_flusher_threads(0, WB_REASON_SYNC); sync_filesystems(0); sync_filesystems(1); if (unlikely(laptop_mode)) diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c index 315de66e52b..bc4f94b2870 100644 --- a/fs/ubifs/budget.c +++ b/fs/ubifs/budget.c @@ -63,7 +63,7 @@ static void shrink_liability(struct ubifs_info *c, int nr_to_write) { down_read(&c->vfs_sb->s_umount); - writeback_inodes_sb(c->vfs_sb); + writeback_inodes_sb(c->vfs_sb, WB_REASON_FS_FREE_SPACE); up_read(&c->vfs_sb->s_umount); } -- cgit v1.2.3