From 9d823e8f6b1b7b39f952d7d1795f29162143a433 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Sat, 11 Jun 2011 18:10:12 -0600 Subject: writeback: per task dirty rate limit Add two fields to task_struct. 1) account dirtied pages in the individual tasks, for accuracy 2) per-task balance_dirty_pages() call intervals, for flexibility The balance_dirty_pages() call interval (ie. nr_dirtied_pause) will scale near-sqrt to the safety gap between dirty pages and threshold. The main problem of per-task nr_dirtied is, if 1k+ tasks start dirtying pages at exactly the same time, each task will be assigned a large initial nr_dirtied_pause, so that the dirty threshold will be exceeded long before each task reached its nr_dirtied_pause and hence call balance_dirty_pages(). The solution is to watch for the number of pages dirtied on each CPU in between the calls into balance_dirty_pages(). If it exceeds ratelimit_pages (3% dirty threshold), force call balance_dirty_pages() for a chance to set bdi->dirty_exceeded. In normal situations, this safeguarding condition is not expected to trigger at all. On the sqrt in dirty_poll_interval(): It will serve as an initial guess when dirty pages are still in the freerun area. When dirty pages are floating inside the dirty control scope [freerun, limit], a followup patch will use some refined dirty poll interval to get the desired pause time. thresh-dirty (MB) sqrt 1 16 2 22 4 32 8 45 16 64 32 90 64 128 128 181 256 256 512 362 1024 512 The above table means, given 1MB (or 1GB) gap and the dd tasks polling balance_dirty_pages() on every 16 (or 512) pages, the dirty limit won't be exceeded as long as there are less than 16 (or 512) concurrent dd's. So sqrt naturally leads to less overheads and more safe concurrent tasks for large memory servers, which have large (thresh-freerun) gaps. peter: keep the per-CPU ratelimit for safeguarding the 1k+ tasks case CC: Peter Zijlstra Reviewed-by: Andrea Righi Signed-off-by: Wu Fengguang --- kernel/fork.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 8e6b6f4fb272..cc0815df99f2 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1302,6 +1302,9 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->pdeath_signal = 0; p->exit_state = 0; + p->nr_dirtied = 0; + p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10); + /* * Ok, make it visible to the rest of the system. * We dont wake it up yet. -- cgit v1.2.2 From c9f01245b6a7d77d17deaa71af10f6aca14fa24e Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 31 Oct 2011 17:07:15 -0700 Subject: oom: remove oom_disable_count This removes mm->oom_disable_count entirely since it's unnecessary and currently buggy. The counter was intended to be per-process but it's currently decremented in the exit path for each thread that exits, causing it to underflow. The count was originally intended to prevent oom killing threads that share memory with threads that cannot be killed since it doesn't lead to future memory freeing. The counter could be fixed to represent all threads sharing the same mm, but it's better to remove the count since: - it is possible that the OOM_DISABLE thread sharing memory with the victim is waiting on that thread to exit and will actually cause future memory freeing, and - there is no guarantee that a thread is disabled from oom killing just because another thread sharing its mm is oom disabled. Signed-off-by: David Rientjes Reported-by: Oleg Nesterov Reviewed-by: Oleg Nesterov Cc: Ying Han Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 8e6b6f4fb272..70d76191afb9 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -501,7 +501,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) mm->cached_hole_size = ~0UL; mm_init_aio(mm); mm_init_owner(mm, p); - atomic_set(&mm->oom_disable_count, 0); if (likely(!mm_alloc_pgd(mm))) { mm->def_flags = 0; @@ -816,8 +815,6 @@ good_mm: /* Initializing for Swap token stuff */ mm->token_priority = 0; mm->last_interval = 0; - if (tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) - atomic_inc(&mm->oom_disable_count); tsk->mm = mm; tsk->active_mm = mm; @@ -1391,13 +1388,8 @@ bad_fork_cleanup_io: bad_fork_cleanup_namespaces: exit_task_namespaces(p); bad_fork_cleanup_mm: - if (p->mm) { - task_lock(p); - if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) - atomic_dec(&p->mm->oom_disable_count); - task_unlock(p); + if (p->mm) mmput(p->mm); - } bad_fork_cleanup_signal: if (!(clone_flags & CLONE_THREAD)) free_signal_struct(p->signal); -- cgit v1.2.2 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 --- kernel/fork.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'kernel/fork.c') 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); -- cgit v1.2.2