From 499d05ecf990a7a7bbf9e0a273f9969f8ec69efc Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 16 Nov 2011 19:34:48 +0800 Subject: mm: Make task in balance_dirty_pages() killable There is no reason why task in balance_dirty_pages() shouldn't be killable and it helps in recovering from some error conditions (like when filesystem goes in error state and cannot accept writeback anymore but we still want to kill processes using it to be able to unmount it). There will be follow up patches to further abort the generic_perform_write() and other filesystem write loops, to avoid large write + SIGKILL combination exceeding the dirty limit and possibly strange OOM. Reported-by: Kazuya Mio Tested-by: Kazuya Mio Reviewed-by: Neil Brown Reviewed-by: KOSAKI Motohiro Signed-off-by: Jan Kara Signed-off-by: Wu Fengguang --- mm/page-writeback.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'mm/page-writeback.c') diff --git a/mm/page-writeback.c b/mm/page-writeback.c index a3278f005230..79c34419fadd 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1133,7 +1133,7 @@ pause: pages_dirtied, pause, start_time); - __set_current_state(TASK_UNINTERRUPTIBLE); + __set_current_state(TASK_KILLABLE); io_schedule_timeout(pause); dirty_thresh = hard_dirty_limit(dirty_thresh); @@ -1145,6 +1145,9 @@ pause: */ if (nr_dirty < dirty_thresh) break; + + if (fatal_signal_pending(current)) + break; } if (!dirty_exceeded && bdi->dirty_exceeded) -- cgit v1.2.3 From 1df647197c5b8aacaeb58592cba9a1df322c9000 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Sun, 13 Nov 2011 19:47:32 -0600 Subject: writeback: hard throttle 1000+ dd on a slow USB stick The sleep based balance_dirty_pages() can pause at most MAX_PAUSE=200ms on every 1 4KB-page, which means it cannot throttle a task under 4KB/200ms=20KB/s. So when there are more than 512 dd writing to a 10MB/s USB stick, its bdi dirty pages could grow out of control. Even if we can increase MAX_PAUSE, the minimal (task_ratelimit = 1) means a limit of 4KB/s. They can eventually be safeguarded by the global limit check (nr_dirty < dirty_thresh). However if someone is also writing to an HDD at the same time, it'll get poor HDD write performance. We at least want to maintain good write performance for other devices when one device is attacked by some "massive parallel" workload, or suffers from slow write bandwidth, or somehow get stalled due to some error condition (eg. NFS server not responding). For a stalled device, we need to completely block its dirtiers, too, before its bdi dirty pages grow all the way up to the global limit and leave no space for the other functional devices. So change the loop exit condition to /* * Always enforce global dirty limit; also enforce bdi dirty limit * if the normal max_pause sleeps cannot keep things under control. */ if (nr_dirty < dirty_thresh && (bdi_dirty < bdi_thresh || bdi->dirty_ratelimit > 1)) break; which can be further simplified to if (task_ratelimit) break; Signed-off-by: Wu Fengguang --- mm/page-writeback.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'mm/page-writeback.c') diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 79c34419fadd..e7cb5ff6e53d 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1136,14 +1136,11 @@ pause: __set_current_state(TASK_KILLABLE); io_schedule_timeout(pause); - dirty_thresh = hard_dirty_limit(dirty_thresh); /* - * max-pause area. If dirty exceeded but still within this - * area, no need to sleep for more than 200ms: (a) 8 pages per - * 200ms is typically more than enough to curb heavy dirtiers; - * (b) the pause time limit makes the dirtiers more responsive. + * This is typically equal to (nr_dirty < dirty_thresh) and can + * also keep "1000+ dd on a slow USB stick" under control. */ - if (nr_dirty < dirty_thresh) + if (task_ratelimit) break; if (fatal_signal_pending(current)) -- cgit v1.2.3 From 468e6a20afaccb67e2a7d7f60d301f90e1c6f301 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Wed, 7 Sep 2011 10:41:32 -0600 Subject: writeback: remove vm_dirties and task->dirties They are not used any more. Signed-off-by: Wu Fengguang --- include/linux/init_task.h | 1 - include/linux/sched.h | 1 - kernel/fork.c | 5 ----- mm/page-writeback.c | 9 --------- 4 files changed, 16 deletions(-) (limited to 'mm/page-writeback.c') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 08ffab01e76c..94b1e356c02a 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -184,7 +184,6 @@ extern struct cred init_cred; [PIDTYPE_SID] = INIT_PID_LINK(PIDTYPE_SID), \ }, \ .thread_group = LIST_HEAD_INIT(tsk.thread_group), \ - .dirties = INIT_PROP_LOCAL_SINGLE(dirties), \ INIT_IDS \ INIT_PERF_EVENTS(tsk) \ INIT_TRACE_IRQFLAGS \ diff --git a/include/linux/sched.h b/include/linux/sched.h index 68daf4f27e2c..1c4f3e9b9bc5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1521,7 +1521,6 @@ struct task_struct { #ifdef CONFIG_FAULT_INJECTION int make_it_fail; #endif - struct prop_local_single dirties; /* * when (nr_dirtied >= nr_dirtied_pause), it's time to call * balance_dirty_pages() for some dirty throttling pause diff --git a/kernel/fork.c b/kernel/fork.c index ba0d17261329..da4a6a10d088 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -162,7 +162,6 @@ static void account_kernel_stack(struct thread_info *ti, int account) void free_task(struct task_struct *tsk) { - prop_local_destroy_single(&tsk->dirties); account_kernel_stack(tsk->stack, -1); free_thread_info(tsk->stack); rt_mutex_debug_task_free(tsk); @@ -274,10 +273,6 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) tsk->stack = ti; - err = prop_local_init_single(&tsk->dirties); - if (err) - goto out; - setup_thread_stack(tsk, orig); clear_user_return_notifier(tsk); clear_tsk_need_resched(tsk); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index e7cb5ff6e53d..71252486bc6f 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -128,7 +128,6 @@ unsigned long global_dirty_limit; * */ static struct prop_descriptor vm_completions; -static struct prop_descriptor vm_dirties; /* * couple the period to the dirty_ratio: @@ -154,7 +153,6 @@ static void update_completion_period(void) { int shift = calc_period_shift(); prop_change_shift(&vm_completions, shift); - prop_change_shift(&vm_dirties, shift); writeback_set_ratelimit(); } @@ -235,11 +233,6 @@ void bdi_writeout_inc(struct backing_dev_info *bdi) } EXPORT_SYMBOL_GPL(bdi_writeout_inc); -void task_dirty_inc(struct task_struct *tsk) -{ - prop_inc_single(&vm_dirties, &tsk->dirties); -} - /* * Obtain an accurate fraction of the BDI's portion. */ @@ -1395,7 +1388,6 @@ void __init page_writeback_init(void) shift = calc_period_shift(); prop_descriptor_init(&vm_completions, shift); - prop_descriptor_init(&vm_dirties, shift); } /** @@ -1724,7 +1716,6 @@ void account_page_dirtied(struct page *page, struct address_space *mapping) __inc_zone_page_state(page, NR_DIRTIED); __inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE); __inc_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED); - task_dirty_inc(current); task_io_account_write(PAGE_CACHE_SIZE); } } -- cgit v1.2.3 From aed21ad28b1323b2807faea019e5ac388a7bc837 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Wed, 23 Nov 2011 11:44:41 -0600 Subject: writeback: comment on the bdi dirty threshold We do "floating proportions" to let active devices to grow its target share of dirty pages and stalled/inactive devices to decrease its target share over time. It works well except in the case of "an inactive disk suddenly goes busy", where the initial target share may be too small. To mitigate this, bdi_position_ratio() has the below line to raise a small bdi_thresh when it's safe to do so, so that the disk be feed with enough dirty pages for efficient IO and in turn fast rampup of bdi_thresh: bdi_thresh = max(bdi_thresh, (limit - dirty) / 8); balance_dirty_pages() normally does negative feedback control which adjusts ratelimit to balance the bdi dirty pages around the target. In some extreme cases when that is not enough, it will have to block the tasks completely until the bdi dirty pages drop below bdi_thresh. Acked-by: Jan Kara Acked-by: Peter Zijlstra Signed-off-by: Wu Fengguang --- mm/page-writeback.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'mm/page-writeback.c') diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 71252486bc6f..155efca4c123 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -411,8 +411,13 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) * * Returns @bdi's dirty limit in pages. The term "dirty" in the context of * dirty balancing includes all PG_dirty, PG_writeback and NFS unstable pages. - * And the "limit" in the name is not seriously taken as hard limit in - * balance_dirty_pages(). + * + * Note that balance_dirty_pages() will only seriously take it as a hard limit + * when sleeping max_pause per page is not enough to keep the dirty pages under + * control. For example, when the device is completely stalled due to some error + * conditions, or when there are 1000 dd tasks writing to a slow 10MB/s USB key. + * In the other normal situations, it acts more gently by throttling the tasks + * more (rather than completely block them) when the bdi dirty pages go high. * * It allocates high/low dirty limits to fast/slow devices, in order to prevent * - starving fast devices @@ -594,6 +599,13 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi, */ if (unlikely(bdi_thresh > thresh)) bdi_thresh = thresh; + /* + * It's very possible that bdi_thresh is close to 0 not because the + * device is slow, but that it has remained inactive for long time. + * Honour such devices a reasonable good (hopefully IO efficient) + * threshold, so that the occasional writes won't be blocked and active + * writes can rampup the threshold quickly. + */ bdi_thresh = max(bdi_thresh, (limit - dirty) / 8); /* * scale global setpoint to bdi's: -- cgit v1.2.3 From c5c6343c4d75f9d3226e05a72e7861e967fc8099 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Fri, 2 Dec 2011 10:21:33 -0600 Subject: writeback: permit through good bdi even when global dirty exceeded On a system with 1 local mount and 1 NFS mount, if the NFS server becomes not responding when dd to the NFS mount, the NFS dirty pages may exceed the global dirty limit and _every_ task involving writing will be blocked. The whole system appears unresponsive. The workaround is to permit through the bdi's that only has a small number of dirty pages. The number chosen (bdi_stat_error pages) is not enough to enable the local disk to run in optimal throughput, however is enough to make the system responsive on a broken NFS mount. The user can then kill the dirtiers on the NFS mount and increase the global dirty limit to bring up the local disk's throughput. It risks allowing dirty pages to grow much larger than the global dirty limit when there are 1000+ mounts, however that's very unlikely to happen, especially in low memory profiles. Signed-off-by: Wu Fengguang --- mm/page-writeback.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'mm/page-writeback.c') diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 155efca4c123..17403e3a7c89 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1148,6 +1148,19 @@ pause: if (task_ratelimit) break; + /* + * In the case of an unresponding NFS server and the NFS dirty + * pages exceeds dirty_thresh, give the other good bdi's a pipe + * to go through, so that tasks on them still remain responsive. + * + * In theory 1 page is enough to keep the comsumer-producer + * pipe going: the flusher cleans 1 page => the task dirties 1 + * more page. However bdi_dirty has accounting errors. So use + * the larger and more IO friendly bdi_stat_error. + */ + if (bdi_dirty <= bdi_stat_error(bdi)) + break; + if (fatal_signal_pending(current)) break; } -- cgit v1.2.3 From 82e230a07de3812a5e87a27979f033dad59172e3 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Fri, 2 Dec 2011 18:21:51 -0600 Subject: writeback: set max_pause to lowest value on zero bdi_dirty Some trace shows lots of bdi_dirty=0 lines where it's actually some small value if w/o the accounting errors in the per-cpu bdi stats. In this case the max pause time should really be set to the smallest (non-zero) value to avoid IO queue underrun and improve throughput. Signed-off-by: Wu Fengguang --- mm/page-writeback.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'mm/page-writeback.c') diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 17403e3a7c89..50f08241f981 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -989,8 +989,7 @@ static unsigned long bdi_max_pause(struct backing_dev_info *bdi, * * 8 serves as the safety ratio. */ - if (bdi_dirty) - t = min(t, bdi_dirty * HZ / (8 * bw + 1)); + t = min(t, bdi_dirty * HZ / (8 * bw + 1)); /* * The pause time will be settled within range (max_pause/4, max_pause). -- cgit v1.2.3