From 66f3b8e2e103a0b93b945764d98e9ba46cb926dd Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 2 Sep 2009 09:19:46 +0200 Subject: writeback: move dirty inodes from super_block to backing_dev_info This is a first step at introducing per-bdi flusher threads. We should have no change in behaviour, although sb_has_dirty_inodes() is now ridiculously expensive, as there's no easy way to answer that question. Not a huge problem, since it'll be deleted in subsequent patches. Signed-off-by: Jens Axboe --- mm/backing-dev.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'mm/backing-dev.c') diff --git a/mm/backing-dev.c b/mm/backing-dev.c index c86edd244294..6f163e0f0509 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -22,6 +22,8 @@ struct backing_dev_info default_backing_dev_info = { EXPORT_SYMBOL_GPL(default_backing_dev_info); static struct class *bdi_class; +DEFINE_MUTEX(bdi_lock); +LIST_HEAD(bdi_list); #ifdef CONFIG_DEBUG_FS #include @@ -211,6 +213,10 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, goto exit; } + mutex_lock(&bdi_lock); + list_add_tail(&bdi->bdi_list, &bdi_list); + mutex_unlock(&bdi_lock); + bdi->dev = dev; bdi_debug_register(bdi, dev_name(dev)); @@ -225,9 +231,17 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev) } EXPORT_SYMBOL(bdi_register_dev); +static void bdi_remove_from_list(struct backing_dev_info *bdi) +{ + mutex_lock(&bdi_lock); + list_del(&bdi->bdi_list); + mutex_unlock(&bdi_lock); +} + void bdi_unregister(struct backing_dev_info *bdi) { if (bdi->dev) { + bdi_remove_from_list(bdi); bdi_debug_unregister(bdi); device_unregister(bdi->dev); bdi->dev = NULL; @@ -245,6 +259,10 @@ int bdi_init(struct backing_dev_info *bdi) bdi->min_ratio = 0; bdi->max_ratio = 100; bdi->max_prop_frac = PROP_FRAC_BASE; + INIT_LIST_HEAD(&bdi->bdi_list); + INIT_LIST_HEAD(&bdi->b_io); + INIT_LIST_HEAD(&bdi->b_dirty); + INIT_LIST_HEAD(&bdi->b_more_io); for (i = 0; i < NR_BDI_STAT_ITEMS; i++) { err = percpu_counter_init(&bdi->bdi_stat[i], 0); @@ -259,6 +277,8 @@ int bdi_init(struct backing_dev_info *bdi) err: while (i--) percpu_counter_destroy(&bdi->bdi_stat[i]); + + bdi_remove_from_list(bdi); } return err; @@ -269,6 +289,10 @@ void bdi_destroy(struct backing_dev_info *bdi) { int i; + WARN_ON(!list_empty(&bdi->b_dirty)); + WARN_ON(!list_empty(&bdi->b_io)); + WARN_ON(!list_empty(&bdi->b_more_io)); + bdi_unregister(bdi); for (i = 0; i < NR_BDI_STAT_ITEMS; i++) -- cgit v1.2.2 From 03ba3782e8dcc5b0e1efe440d33084f066e38cae Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 9 Sep 2009 09:08:54 +0200 Subject: writeback: switch to per-bdi threads for flushing data This gets rid of pdflush for bdi writeout and kupdated style cleaning. pdflush writeout suffers from lack of locality and also requires more threads to handle the same workload, since it has to work in a non-blocking fashion against each queue. This also introduces lumpy behaviour and potential request starvation, since pdflush can be starved for queue access if others are accessing it. A sample ffsb workload that does random writes to files is about 8% faster here on a simple SATA drive during the benchmark phase. File layout also seems a LOT more smooth in vmstat: r b swpd free buff cache si so bi bo in cs us sy id wa 0 1 0 608848 2652 375372 0 0 0 71024 604 24 1 10 48 42 0 1 0 549644 2712 433736 0 0 0 60692 505 27 1 8 48 44 1 0 0 476928 2784 505192 0 0 4 29540 553 24 0 9 53 37 0 1 0 457972 2808 524008 0 0 0 54876 331 16 0 4 38 58 0 1 0 366128 2928 614284 0 0 4 92168 710 58 0 13 53 34 0 1 0 295092 3000 684140 0 0 0 62924 572 23 0 9 53 37 0 1 0 236592 3064 741704 0 0 4 58256 523 17 0 8 48 44 0 1 0 165608 3132 811464 0 0 0 57460 560 21 0 8 54 38 0 1 0 102952 3200 873164 0 0 4 74748 540 29 1 10 48 41 0 1 0 48604 3252 926472 0 0 0 53248 469 29 0 7 47 45 where vanilla tends to fluctuate a lot in the creation phase: r b swpd free buff cache si so bi bo in cs us sy id wa 1 1 0 678716 5792 303380 0 0 0 74064 565 50 1 11 52 36 1 0 0 662488 5864 319396 0 0 4 352 302 329 0 2 47 51 0 1 0 599312 5924 381468 0 0 0 78164 516 55 0 9 51 40 0 1 0 519952 6008 459516 0 0 4 78156 622 56 1 11 52 37 1 1 0 436640 6092 541632 0 0 0 82244 622 54 0 11 48 41 0 1 0 436640 6092 541660 0 0 0 8 152 39 0 0 51 49 0 1 0 332224 6200 644252 0 0 4 102800 728 46 1 13 49 36 1 0 0 274492 6260 701056 0 0 4 12328 459 49 0 7 50 43 0 1 0 211220 6324 763356 0 0 0 106940 515 37 1 10 51 39 1 0 0 160412 6376 813468 0 0 0 8224 415 43 0 6 49 45 1 1 0 85980 6452 886556 0 0 4 113516 575 39 1 11 54 34 0 2 0 85968 6452 886620 0 0 0 1640 158 211 0 0 46 54 A 10 disk test with btrfs performs 26% faster with per-bdi flushing. A SSD based writeback test on XFS performs over 20% better as well, with the throughput being very stable around 1GB/sec, where pdflush only manages 750MB/sec and fluctuates wildly while doing so. Random buffered writes to many files behave a lot better as well, as does random mmap'ed writes. A separate thread is added to sync the super blocks. In the long term, adding sync_supers_bdi() functionality could get rid of this thread again. Signed-off-by: Jens Axboe --- mm/backing-dev.c | 341 ++++++++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 323 insertions(+), 18 deletions(-) (limited to 'mm/backing-dev.c') diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 6f163e0f0509..7f3fa79f25c0 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -1,8 +1,11 @@ #include #include +#include +#include #include #include +#include #include #include #include @@ -22,8 +25,18 @@ struct backing_dev_info default_backing_dev_info = { EXPORT_SYMBOL_GPL(default_backing_dev_info); static struct class *bdi_class; -DEFINE_MUTEX(bdi_lock); +DEFINE_SPINLOCK(bdi_lock); LIST_HEAD(bdi_list); +LIST_HEAD(bdi_pending_list); + +static struct task_struct *sync_supers_tsk; +static struct timer_list sync_supers_timer; + +static int bdi_sync_supers(void *); +static void sync_supers_timer_fn(unsigned long); +static void arm_supers_timer(void); + +static void bdi_add_default_flusher_task(struct backing_dev_info *bdi); #ifdef CONFIG_DEBUG_FS #include @@ -187,6 +200,13 @@ static int __init default_bdi_init(void) { int err; + sync_supers_tsk = kthread_run(bdi_sync_supers, NULL, "sync_supers"); + BUG_ON(IS_ERR(sync_supers_tsk)); + + init_timer(&sync_supers_timer); + setup_timer(&sync_supers_timer, sync_supers_timer_fn, 0); + arm_supers_timer(); + err = bdi_init(&default_backing_dev_info); if (!err) bdi_register(&default_backing_dev_info, NULL, "default"); @@ -195,6 +215,242 @@ static int __init default_bdi_init(void) } subsys_initcall(default_bdi_init); +static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi) +{ + memset(wb, 0, sizeof(*wb)); + + wb->bdi = bdi; + wb->last_old_flush = jiffies; + INIT_LIST_HEAD(&wb->b_dirty); + INIT_LIST_HEAD(&wb->b_io); + INIT_LIST_HEAD(&wb->b_more_io); +} + +static void bdi_task_init(struct backing_dev_info *bdi, + struct bdi_writeback *wb) +{ + struct task_struct *tsk = current; + + spin_lock(&bdi->wb_lock); + list_add_tail_rcu(&wb->list, &bdi->wb_list); + spin_unlock(&bdi->wb_lock); + + tsk->flags |= PF_FLUSHER | PF_SWAPWRITE; + set_freezable(); + + /* + * Our parent may run at a different priority, just set us to normal + */ + set_user_nice(tsk, 0); +} + +static int bdi_start_fn(void *ptr) +{ + struct bdi_writeback *wb = ptr; + struct backing_dev_info *bdi = wb->bdi; + int ret; + + /* + * Add us to the active bdi_list + */ + spin_lock(&bdi_lock); + list_add(&bdi->bdi_list, &bdi_list); + spin_unlock(&bdi_lock); + + bdi_task_init(bdi, wb); + + /* + * Clear pending bit and wakeup anybody waiting to tear us down + */ + clear_bit(BDI_pending, &bdi->state); + smp_mb__after_clear_bit(); + wake_up_bit(&bdi->state, BDI_pending); + + ret = bdi_writeback_task(wb); + + /* + * Remove us from the list + */ + spin_lock(&bdi->wb_lock); + list_del_rcu(&wb->list); + spin_unlock(&bdi->wb_lock); + + /* + * Flush any work that raced with us exiting. No new work + * will be added, since this bdi isn't discoverable anymore. + */ + if (!list_empty(&bdi->work_list)) + wb_do_writeback(wb, 1); + + wb->task = NULL; + return ret; +} + +int bdi_has_dirty_io(struct backing_dev_info *bdi) +{ + return wb_has_dirty_io(&bdi->wb); +} + +static void bdi_flush_io(struct backing_dev_info *bdi) +{ + struct writeback_control wbc = { + .bdi = bdi, + .sync_mode = WB_SYNC_NONE, + .older_than_this = NULL, + .range_cyclic = 1, + .nr_to_write = 1024, + }; + + writeback_inodes_wbc(&wbc); +} + +/* + * kupdated() used to do this. We cannot do it from the bdi_forker_task() + * or we risk deadlocking on ->s_umount. The longer term solution would be + * to implement sync_supers_bdi() or similar and simply do it from the + * bdi writeback tasks individually. + */ +static int bdi_sync_supers(void *unused) +{ + set_user_nice(current, 0); + + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + + /* + * Do this periodically, like kupdated() did before. + */ + sync_supers(); + } + + return 0; +} + +static void arm_supers_timer(void) +{ + unsigned long next; + + next = msecs_to_jiffies(dirty_writeback_interval * 10) + jiffies; + mod_timer(&sync_supers_timer, round_jiffies_up(next)); +} + +static void sync_supers_timer_fn(unsigned long unused) +{ + wake_up_process(sync_supers_tsk); + arm_supers_timer(); +} + +static int bdi_forker_task(void *ptr) +{ + struct bdi_writeback *me = ptr; + + bdi_task_init(me->bdi, me); + + for (;;) { + struct backing_dev_info *bdi, *tmp; + struct bdi_writeback *wb; + + /* + * Temporary measure, we want to make sure we don't see + * dirty data on the default backing_dev_info + */ + if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list)) + wb_do_writeback(me, 0); + + spin_lock(&bdi_lock); + + /* + * Check if any existing bdi's have dirty data without + * a thread registered. If so, set that up. + */ + list_for_each_entry_safe(bdi, tmp, &bdi_list, bdi_list) { + if (bdi->wb.task) + continue; + if (list_empty(&bdi->work_list) && + !bdi_has_dirty_io(bdi)) + continue; + + bdi_add_default_flusher_task(bdi); + } + + set_current_state(TASK_INTERRUPTIBLE); + + if (list_empty(&bdi_pending_list)) { + unsigned long wait; + + spin_unlock(&bdi_lock); + wait = msecs_to_jiffies(dirty_writeback_interval * 10); + schedule_timeout(wait); + try_to_freeze(); + continue; + } + + __set_current_state(TASK_RUNNING); + + /* + * This is our real job - check for pending entries in + * bdi_pending_list, and create the tasks that got added + */ + bdi = list_entry(bdi_pending_list.next, struct backing_dev_info, + bdi_list); + list_del_init(&bdi->bdi_list); + spin_unlock(&bdi_lock); + + wb = &bdi->wb; + wb->task = kthread_run(bdi_start_fn, wb, "flush-%s", + dev_name(bdi->dev)); + /* + * If task creation fails, then readd the bdi to + * the pending list and force writeout of the bdi + * from this forker thread. That will free some memory + * and we can try again. + */ + if (IS_ERR(wb->task)) { + wb->task = NULL; + + /* + * Add this 'bdi' to the back, so we get + * a chance to flush other bdi's to free + * memory. + */ + spin_lock(&bdi_lock); + list_add_tail(&bdi->bdi_list, &bdi_pending_list); + spin_unlock(&bdi_lock); + + bdi_flush_io(bdi); + } + } + + return 0; +} + +/* + * Add the default flusher task that gets created for any bdi + * that has dirty data pending writeout + */ +void static bdi_add_default_flusher_task(struct backing_dev_info *bdi) +{ + if (!bdi_cap_writeback_dirty(bdi)) + return; + + /* + * Check with the helper whether to proceed adding a task. Will only + * abort if we two or more simultanous calls to + * bdi_add_default_flusher_task() occured, further additions will block + * waiting for previous additions to finish. + */ + if (!test_and_set_bit(BDI_pending, &bdi->state)) { + list_move_tail(&bdi->bdi_list, &bdi_pending_list); + + /* + * We are now on the pending list, wake up bdi_forker_task() + * to finish the job and add us back to the active bdi_list + */ + wake_up_process(default_backing_dev_info.wb.task); + } +} + int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...) { @@ -213,13 +469,34 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, goto exit; } - mutex_lock(&bdi_lock); + spin_lock(&bdi_lock); list_add_tail(&bdi->bdi_list, &bdi_list); - mutex_unlock(&bdi_lock); + spin_unlock(&bdi_lock); bdi->dev = dev; - bdi_debug_register(bdi, dev_name(dev)); + /* + * Just start the forker thread for our default backing_dev_info, + * and add other bdi's to the list. They will get a thread created + * on-demand when they need it. + */ + if (bdi_cap_flush_forker(bdi)) { + struct bdi_writeback *wb = &bdi->wb; + + wb->task = kthread_run(bdi_forker_task, wb, "bdi-%s", + dev_name(dev)); + if (IS_ERR(wb->task)) { + wb->task = NULL; + ret = -ENOMEM; + + spin_lock(&bdi_lock); + list_del(&bdi->bdi_list); + spin_unlock(&bdi_lock); + goto exit; + } + } + + bdi_debug_register(bdi, dev_name(dev)); exit: return ret; } @@ -231,17 +508,42 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev) } EXPORT_SYMBOL(bdi_register_dev); -static void bdi_remove_from_list(struct backing_dev_info *bdi) +/* + * Remove bdi from the global list and shutdown any threads we have running + */ +static void bdi_wb_shutdown(struct backing_dev_info *bdi) { - mutex_lock(&bdi_lock); + struct bdi_writeback *wb; + + if (!bdi_cap_writeback_dirty(bdi)) + return; + + /* + * If setup is pending, wait for that to complete first + */ + wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait, + TASK_UNINTERRUPTIBLE); + + /* + * Make sure nobody finds us on the bdi_list anymore + */ + spin_lock(&bdi_lock); list_del(&bdi->bdi_list); - mutex_unlock(&bdi_lock); + spin_unlock(&bdi_lock); + + /* + * Finally, kill the kernel threads. We don't need to be RCU + * safe anymore, since the bdi is gone from visibility. + */ + list_for_each_entry(wb, &bdi->wb_list, list) + kthread_stop(wb->task); } void bdi_unregister(struct backing_dev_info *bdi) { if (bdi->dev) { - bdi_remove_from_list(bdi); + if (!bdi_cap_flush_forker(bdi)) + bdi_wb_shutdown(bdi); bdi_debug_unregister(bdi); device_unregister(bdi->dev); bdi->dev = NULL; @@ -251,18 +553,25 @@ EXPORT_SYMBOL(bdi_unregister); int bdi_init(struct backing_dev_info *bdi) { - int i; - int err; + int i, err; bdi->dev = NULL; bdi->min_ratio = 0; bdi->max_ratio = 100; bdi->max_prop_frac = PROP_FRAC_BASE; + spin_lock_init(&bdi->wb_lock); INIT_LIST_HEAD(&bdi->bdi_list); - INIT_LIST_HEAD(&bdi->b_io); - INIT_LIST_HEAD(&bdi->b_dirty); - INIT_LIST_HEAD(&bdi->b_more_io); + INIT_LIST_HEAD(&bdi->wb_list); + INIT_LIST_HEAD(&bdi->work_list); + + bdi_wb_init(&bdi->wb, bdi); + + /* + * Just one thread support for now, hard code mask and count + */ + bdi->wb_mask = 1; + bdi->wb_cnt = 1; for (i = 0; i < NR_BDI_STAT_ITEMS; i++) { err = percpu_counter_init(&bdi->bdi_stat[i], 0); @@ -277,8 +586,6 @@ int bdi_init(struct backing_dev_info *bdi) err: while (i--) percpu_counter_destroy(&bdi->bdi_stat[i]); - - bdi_remove_from_list(bdi); } return err; @@ -289,9 +596,7 @@ void bdi_destroy(struct backing_dev_info *bdi) { int i; - WARN_ON(!list_empty(&bdi->b_dirty)); - WARN_ON(!list_empty(&bdi->b_io)); - WARN_ON(!list_empty(&bdi->b_more_io)); + WARN_ON(bdi_has_dirty_io(bdi)); bdi_unregister(bdi); -- cgit v1.2.2 From f09b00d3e789a88fa6c7c03cedc62cb65c1de0cb Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 25 May 2009 09:08:21 +0200 Subject: writeback: add some debug inode list counters to bdi stats Add some debug entries to be able to inspect the internal state of the writeback details. Signed-off-by: Jens Axboe --- mm/backing-dev.c | 38 ++++++++++++++++++++++++++++++++++---- 1 file changed, 34 insertions(+), 4 deletions(-) (limited to 'mm/backing-dev.c') diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 7f3fa79f25c0..22c45e932e3a 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -52,9 +52,29 @@ static void bdi_debug_init(void) static int bdi_debug_stats_show(struct seq_file *m, void *v) { struct backing_dev_info *bdi = m->private; + struct bdi_writeback *wb; unsigned long background_thresh; unsigned long dirty_thresh; unsigned long bdi_thresh; + unsigned long nr_dirty, nr_io, nr_more_io, nr_wb; + struct inode *inode; + + /* + * inode lock is enough here, the bdi->wb_list is protected by + * RCU on the reader side + */ + nr_wb = nr_dirty = nr_io = nr_more_io = 0; + spin_lock(&inode_lock); + list_for_each_entry(wb, &bdi->wb_list, list) { + nr_wb++; + list_for_each_entry(inode, &wb->b_dirty, i_list) + nr_dirty++; + list_for_each_entry(inode, &wb->b_io, i_list) + nr_io++; + list_for_each_entry(inode, &wb->b_more_io, i_list) + nr_more_io++; + } + spin_unlock(&inode_lock); get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi); @@ -64,12 +84,22 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) "BdiReclaimable: %8lu kB\n" "BdiDirtyThresh: %8lu kB\n" "DirtyThresh: %8lu kB\n" - "BackgroundThresh: %8lu kB\n", + "BackgroundThresh: %8lu kB\n" + "WriteBack threads:%8lu\n" + "b_dirty: %8lu\n" + "b_io: %8lu\n" + "b_more_io: %8lu\n" + "bdi_list: %8u\n" + "state: %8lx\n" + "wb_mask: %8lx\n" + "wb_list: %8u\n" + "wb_cnt: %8u\n", (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)), (unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)), - K(bdi_thresh), - K(dirty_thresh), - K(background_thresh)); + K(bdi_thresh), K(dirty_thresh), + K(background_thresh), nr_wb, nr_dirty, nr_io, nr_more_io, + !list_empty(&bdi->bdi_list), bdi->state, bdi->wb_mask, + !list_empty(&bdi->wb_list), bdi->wb_cnt); #undef K return 0; -- cgit v1.2.2 From d993831fa7ffeb89e994f046f93eeb09ec91df08 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 12 Jun 2009 14:45:52 +0200 Subject: writeback: add name to backing_dev_info This enables us to track who does what and print info. Its main use is catching dirty inodes on the default_backing_dev_info, so we can fix that up. Signed-off-by: Jens Axboe --- mm/backing-dev.c | 1 + 1 file changed, 1 insertion(+) (limited to 'mm/backing-dev.c') diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 22c45e932e3a..5cb32c5b93d8 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -17,6 +17,7 @@ void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page) EXPORT_SYMBOL(default_unplug_io_fn); struct backing_dev_info default_backing_dev_info = { + .name = "default", .ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE, .state = 0, .capabilities = BDI_CAP_MAP_COPY, -- cgit v1.2.2 From 500b067c5e6ceea49cf280a02597b1169320e08c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 9 Sep 2009 09:10:25 +0200 Subject: writeback: check for registered bdi in flusher add and inode dirty Also a debugging aid. We want to catch dirty inodes being added to backing devices that don't do writeback. Signed-off-by: Jens Axboe --- mm/backing-dev.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'mm/backing-dev.c') diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 5cb32c5b93d8..d3ca0dac1111 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -465,6 +465,12 @@ void static bdi_add_default_flusher_task(struct backing_dev_info *bdi) if (!bdi_cap_writeback_dirty(bdi)) return; + if (WARN_ON(!test_bit(BDI_registered, &bdi->state))) { + printk(KERN_ERR "bdi %p/%s is not registered!\n", + bdi, bdi->name); + return; + } + /* * Check with the helper whether to proceed adding a task. Will only * abort if we two or more simultanous calls to @@ -528,6 +534,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, } bdi_debug_register(bdi, dev_name(dev)); + set_bit(BDI_registered, &bdi->state); exit: return ret; } -- cgit v1.2.2 From cfc4ba5365449cb6b5c9f68d755a142f17da1e47 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 14 Sep 2009 13:12:40 +0200 Subject: writeback: use RCU to protect bdi_list Now that bdi_writeback_all() no longer handles integrity writeback, it doesn't have to block anymore. This means that we can switch bdi_list reader side protection to RCU. Signed-off-by: Jens Axboe --- mm/backing-dev.c | 76 ++++++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 55 insertions(+), 21 deletions(-) (limited to 'mm/backing-dev.c') diff --git a/mm/backing-dev.c b/mm/backing-dev.c index d3ca0dac1111..fd93566345b6 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -26,6 +26,12 @@ struct backing_dev_info default_backing_dev_info = { EXPORT_SYMBOL_GPL(default_backing_dev_info); static struct class *bdi_class; + +/* + * bdi_lock protects updates to bdi_list and bdi_pending_list, as well as + * reader side protection for bdi_pending_list. bdi_list has RCU reader side + * locking. + */ DEFINE_SPINLOCK(bdi_lock); LIST_HEAD(bdi_list); LIST_HEAD(bdi_pending_list); @@ -284,9 +290,9 @@ static int bdi_start_fn(void *ptr) /* * Add us to the active bdi_list */ - spin_lock(&bdi_lock); - list_add(&bdi->bdi_list, &bdi_list); - spin_unlock(&bdi_lock); + spin_lock_bh(&bdi_lock); + list_add_rcu(&bdi->bdi_list, &bdi_list); + spin_unlock_bh(&bdi_lock); bdi_task_init(bdi, wb); @@ -389,7 +395,7 @@ static int bdi_forker_task(void *ptr) if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list)) wb_do_writeback(me, 0); - spin_lock(&bdi_lock); + spin_lock_bh(&bdi_lock); /* * Check if any existing bdi's have dirty data without @@ -410,7 +416,7 @@ static int bdi_forker_task(void *ptr) if (list_empty(&bdi_pending_list)) { unsigned long wait; - spin_unlock(&bdi_lock); + spin_unlock_bh(&bdi_lock); wait = msecs_to_jiffies(dirty_writeback_interval * 10); schedule_timeout(wait); try_to_freeze(); @@ -426,7 +432,7 @@ static int bdi_forker_task(void *ptr) bdi = list_entry(bdi_pending_list.next, struct backing_dev_info, bdi_list); list_del_init(&bdi->bdi_list); - spin_unlock(&bdi_lock); + spin_unlock_bh(&bdi_lock); wb = &bdi->wb; wb->task = kthread_run(bdi_start_fn, wb, "flush-%s", @@ -445,9 +451,9 @@ static int bdi_forker_task(void *ptr) * a chance to flush other bdi's to free * memory. */ - spin_lock(&bdi_lock); + spin_lock_bh(&bdi_lock); list_add_tail(&bdi->bdi_list, &bdi_pending_list); - spin_unlock(&bdi_lock); + spin_unlock_bh(&bdi_lock); bdi_flush_io(bdi); } @@ -456,6 +462,24 @@ static int bdi_forker_task(void *ptr) return 0; } +static void bdi_add_to_pending(struct rcu_head *head) +{ + struct backing_dev_info *bdi; + + bdi = container_of(head, struct backing_dev_info, rcu_head); + INIT_LIST_HEAD(&bdi->bdi_list); + + spin_lock(&bdi_lock); + list_add_tail(&bdi->bdi_list, &bdi_pending_list); + spin_unlock(&bdi_lock); + + /* + * We are now on the pending list, wake up bdi_forker_task() + * to finish the job and add us back to the active bdi_list + */ + wake_up_process(default_backing_dev_info.wb.task); +} + /* * Add the default flusher task that gets created for any bdi * that has dirty data pending writeout @@ -478,16 +502,29 @@ void static bdi_add_default_flusher_task(struct backing_dev_info *bdi) * waiting for previous additions to finish. */ if (!test_and_set_bit(BDI_pending, &bdi->state)) { - list_move_tail(&bdi->bdi_list, &bdi_pending_list); + list_del_rcu(&bdi->bdi_list); /* - * We are now on the pending list, wake up bdi_forker_task() - * to finish the job and add us back to the active bdi_list + * We must wait for the current RCU period to end before + * moving to the pending list. So schedule that operation + * from an RCU callback. */ - wake_up_process(default_backing_dev_info.wb.task); + call_rcu(&bdi->rcu_head, bdi_add_to_pending); } } +/* + * Remove bdi from bdi_list, and ensure that it is no longer visible + */ +static void bdi_remove_from_list(struct backing_dev_info *bdi) +{ + spin_lock_bh(&bdi_lock); + list_del_rcu(&bdi->bdi_list); + spin_unlock_bh(&bdi_lock); + + synchronize_rcu(); +} + int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...) { @@ -506,9 +543,9 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, goto exit; } - spin_lock(&bdi_lock); - list_add_tail(&bdi->bdi_list, &bdi_list); - spin_unlock(&bdi_lock); + spin_lock_bh(&bdi_lock); + list_add_tail_rcu(&bdi->bdi_list, &bdi_list); + spin_unlock_bh(&bdi_lock); bdi->dev = dev; @@ -526,9 +563,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, wb->task = NULL; ret = -ENOMEM; - spin_lock(&bdi_lock); - list_del(&bdi->bdi_list); - spin_unlock(&bdi_lock); + bdi_remove_from_list(bdi); goto exit; } } @@ -565,9 +600,7 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi) /* * Make sure nobody finds us on the bdi_list anymore */ - spin_lock(&bdi_lock); - list_del(&bdi->bdi_list); - spin_unlock(&bdi_lock); + bdi_remove_from_list(bdi); /* * Finally, kill the kernel threads. We don't need to be RCU @@ -599,6 +632,7 @@ int bdi_init(struct backing_dev_info *bdi) bdi->max_ratio = 100; bdi->max_prop_frac = PROP_FRAC_BASE; spin_lock_init(&bdi->wb_lock); + INIT_RCU_HEAD(&bdi->rcu_head); INIT_LIST_HEAD(&bdi->bdi_list); INIT_LIST_HEAD(&bdi->wb_list); INIT_LIST_HEAD(&bdi->work_list); -- cgit v1.2.2 From ce5f8e7795195edb6f84f74aa9d72e739df38486 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 14 Sep 2009 12:57:56 +0200 Subject: writeback: splice dirty inode entries to default bdi on bdi_destroy() We cannot safely ensure that the inodes are all gone at this point in time, and we must not destroy this bdi with inodes having off it. So just splice our entries to the default bdi since that one will always persist. Signed-off-by: Jens Axboe --- mm/backing-dev.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'mm/backing-dev.c') diff --git a/mm/backing-dev.c b/mm/backing-dev.c index fd93566345b6..3d3accb1f800 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -668,7 +668,19 @@ void bdi_destroy(struct backing_dev_info *bdi) { int i; - WARN_ON(bdi_has_dirty_io(bdi)); + /* + * Splice our entries to the default_backing_dev_info, if this + * bdi disappears + */ + if (bdi_has_dirty_io(bdi)) { + struct bdi_writeback *dst = &default_backing_dev_info.wb; + + spin_lock(&inode_lock); + list_splice(&bdi->wb.b_dirty, &dst->b_dirty); + list_splice(&bdi->wb.b_io, &dst->b_io); + list_splice(&bdi->wb.b_more_io, &dst->b_more_io); + spin_unlock(&inode_lock); + } bdi_unregister(bdi); -- cgit v1.2.2