Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752982Ab0GYLcJ (ORCPT ); Sun, 25 Jul 2010 07:32:09 -0400 Received: from smtp.nokia.com ([192.100.105.134]:43493 "EHLO mgw-mx09.nokia.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752637Ab0GYL3e (ORCPT ); Sun, 25 Jul 2010 07:29:34 -0400 From: Artem Bityutskiy To: Jens Axboe Cc: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org Subject: [PATCHv6 10/15] writeback: move bdi threads exiting logic to the forker thread Date: Sun, 25 Jul 2010 14:29:20 +0300 Message-Id: <1280057365-10297-11-git-send-email-dedekind1@gmail.com> X-Mailer: git-send-email 1.7.1.1 In-Reply-To: <1280057365-10297-1-git-send-email-dedekind1@gmail.com> References: <1280057365-10297-1-git-send-email-dedekind1@gmail.com> X-OriginalArrivalTime: 25 Jul 2010 11:29:28.0985 (UTC) FILETIME=[A4F2E890:01CB2BEC] X-Nokia-AV: Clean Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 8505 Lines: 282 From: Artem Bityutskiy Currently, bdi threads can decide to exit if there were no useful activities for 5 minutes. However, this causes nasty races: we can easily oops in the 'bdi_queue_work()' if the bdi thread decides to exit while we are waking it up. And even if we do not oops, but the bdi tread exits immediately after we wake it up, we'd lose the wake-up event and have an unnecessary delay (up to 5 secs) in the bdi work processing. This patch makes the forker thread to be the central place which not only creates bdi threads, but also kills them if they were inactive long enough. This better design-wise. Another reason why this change was done is to prepare for the further changes which will prevent the bdi threads from waking up every 5 sec and wasting power. Indeed, when the task does not wake up periodically anymore, it won't be able to exit either. This patch also moves the the 'wake_up_bit()' call from the bdi thread to the forker thread as well. So now the forker thread sets the BDI_pending bit, then forks the task or kills it, then clears the bit and wakes up the waiting process. The only process which may wain on the bit is 'bdi_wb_shutdown()'. This function was changed as well - now it first removes the bdi from the 'bdi_list', then waits on the 'BDI_pending' bit. Once it wakes up, it is guaranteed that the forker thread won't race with it, because the bdi is not visible. Note, the forker thread sets the 'BDI_pending' bit under the 'bdi->wb_lock' which is essential for proper serialization. And additionally, when we change 'bdi->wb.task', we now take the 'bdi->work_lock', to make sure that we do not lose wake-ups which we otherwise would when raced with, say, 'bdi_queue_work()'. Signed-off-by: Artem Bityutskiy Reviewed-by: Christoph Hellwig --- fs/fs-writeback.c | 54 +++++++++-------------------------------- mm/backing-dev.c | 69 ++++++++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 70 insertions(+), 53 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 53e1028..b9e5ba0 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -78,21 +78,17 @@ static void bdi_queue_work(struct backing_dev_info *bdi, spin_lock(&bdi->wb_lock); list_add_tail(&work->list, &bdi->work_list); - spin_unlock(&bdi->wb_lock); - - /* - * If the default thread isn't there, make sure we add it. When - * it gets created and wakes up, we'll run this work. - */ - if (unlikely(!bdi->wb.task)) { + if (bdi->wb.task) { + wake_up_process(bdi->wb.task); + } else { + /* + * The bdi thread isn't there, wake up the forker thread which + * will create and run it. + */ trace_writeback_nothread(bdi, work); wake_up_process(default_backing_dev_info.wb.task); - } else { - struct bdi_writeback *wb = &bdi->wb; - - if (wb->task) - wake_up_process(wb->task); } + spin_unlock(&bdi->wb_lock); } static void @@ -800,7 +796,6 @@ int bdi_writeback_thread(void *data) { struct bdi_writeback *wb = data; struct backing_dev_info *bdi = wb->bdi; - unsigned long wait_jiffies = -1UL; long pages_written; current->flags |= PF_FLUSHER | PF_SWAPWRITE; @@ -812,13 +807,6 @@ int bdi_writeback_thread(void *data) */ set_user_nice(current, 0); - /* - * 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); - trace_writeback_thread_start(bdi); while (!kthread_should_stop()) { @@ -828,18 +816,6 @@ int bdi_writeback_thread(void *data) if (pages_written) wb->last_active = jiffies; - else if (wait_jiffies != -1UL) { - unsigned long max_idle; - - /* - * Longest period of inactivity that we tolerate. If we - * see dirty data again later, the thread will get - * recreated automatically. - */ - max_idle = max(5UL * 60 * HZ, wait_jiffies); - if (time_after(jiffies, max_idle + wb->last_active)) - break; - } set_current_state(TASK_INTERRUPTIBLE); if (!list_empty(&bdi->work_list)) { @@ -847,21 +823,15 @@ int bdi_writeback_thread(void *data) continue; } - if (dirty_writeback_interval) { - wait_jiffies = msecs_to_jiffies(dirty_writeback_interval * 10); - schedule_timeout(wait_jiffies); - } else + if (dirty_writeback_interval) + schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10)); + else schedule(); try_to_freeze(); } - wb->task = NULL; - - /* - * Flush any work that raced with us exiting. No new work - * will be added, since this bdi isn't discoverable anymore. - */ + /* Flush any work that raced with us exiting */ if (!list_empty(&bdi->work_list)) wb_do_writeback(wb, 1); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index e104e32..9c1c199 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -316,6 +316,18 @@ static void sync_supers_timer_fn(unsigned long unused) bdi_arm_supers_timer(); } +/* + * Calculate the longest interval (jiffies) bdi threads are allowed to be + * inactive. + */ +static unsigned long bdi_longest_inactive(void) +{ + unsigned long interval; + + interval = msecs_to_jiffies(dirty_writeback_interval * 10); + return max(5UL * 60 * HZ, interval); +} + static int bdi_forker_thread(void *ptr) { struct bdi_writeback *me = ptr; @@ -329,11 +341,12 @@ static int bdi_forker_thread(void *ptr) set_user_nice(current, 0); for (;;) { - struct task_struct *task; + struct task_struct *task = NULL; struct backing_dev_info *bdi; enum { NO_ACTION, /* Nothing to do */ FORK_THREAD, /* Fork bdi thread */ + KILL_THREAD, /* Kill inactive bdi thread */ } action = NO_ACTION; /* @@ -346,10 +359,6 @@ static int bdi_forker_thread(void *ptr) spin_lock_bh(&bdi_lock); set_current_state(TASK_INTERRUPTIBLE); - /* - * Check if any existing bdi's have dirty data without - * a thread registered. If so, set that up. - */ list_for_each_entry(bdi, &bdi_list, bdi_list) { bool have_dirty_io; @@ -376,6 +385,25 @@ static int bdi_forker_thread(void *ptr) action = FORK_THREAD; break; } + + spin_lock(&bdi->wb_lock); + /* + * If there is no work to do and the bdi thread was + * inactive long enough - kill it. The wb_lock is taken + * to make sure no-one adds more work to this bdi and + * wakes the bdi thread up. + */ + if (bdi->wb.task && !have_dirty_io && + time_after(jiffies, bdi->wb.last_active + + bdi_longest_inactive())) { + task = bdi->wb.task; + bdi->wb.task = NULL; + spin_unlock(&bdi->wb_lock); + set_bit(BDI_pending, &bdi->state); + action = KILL_THREAD; + break; + } + spin_unlock(&bdi->wb_lock); } spin_unlock_bh(&bdi_lock); @@ -394,8 +422,20 @@ static int bdi_forker_thread(void *ptr) * the bdi from the thread. */ bdi_flush_io(bdi); - } else + } else { + /* + * The spinlock makes sure we do not lose + * wake-ups when racing with 'bdi_queue_work()'. + */ + spin_lock(&bdi->wb_lock); bdi->wb.task = task; + spin_unlock(&bdi->wb_lock); + } + break; + + case KILL_THREAD: + __set_current_state(TASK_RUNNING); + kthread_stop(task); break; case NO_ACTION: @@ -407,6 +447,13 @@ static int bdi_forker_thread(void *ptr) /* Back to the main loop */ continue; } + + /* + * 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); } return 0; @@ -490,15 +537,15 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi) return; /* - * If setup is pending, wait for that to complete first + * Make sure nobody finds us on the bdi_list anymore */ - wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait, - TASK_UNINTERRUPTIBLE); + bdi_remove_from_list(bdi); /* - * Make sure nobody finds us on the bdi_list anymore + * If setup is pending, wait for that to complete first */ - bdi_remove_from_list(bdi); + wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait, + TASK_UNINTERRUPTIBLE); /* * Finally, kill the kernel thread. We don't need to be RCU -- 1.7.1.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/