From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756537AbZEYHdi (ORCPT ); Mon, 25 May 2009 03:33:38 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753721AbZEYHcS (ORCPT ); Mon, 25 May 2009 03:32:18 -0400 Received: from brick.kernel.dk ([93.163.65.50]:38677 "EHLO kernel.dk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753127AbZEYHbQ (ORCPT ); Mon, 25 May 2009 03:31:16 -0400 From: Jens Axboe To: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org Cc: chris.mason@oracle.com, david@fromorbit.com, hch@infradead.org, akpm@linux-foundation.org, jack@suse.cz, yanmin_zhang@linux.intel.com, Jens Axboe Subject: [PATCH 09/12] writeback: allow sleepy exit of default writeback task Date: Mon, 25 May 2009 09:31:01 +0200 Message-Id: <1243236668-3398-19-git-send-email-jens.axboe@oracle.com> X-Mailer: git-send-email 1.6.3.rc0.1.gf800 In-Reply-To: <1243236668-3398-1-git-send-email-jens.axboe@oracle.com> References: <1243236668-3398-1-git-send-email-jens.axboe@oracle.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Since we do lazy create of default writeback tasks for a bdi, we can allow sleepy exit if it has been completely idle for 5 minutes. Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 52 ++++++++++++++++++++++++++++++++++-------- include/linux/backing-dev.h | 5 ++++ include/linux/writeback.h | 2 +- 3 files changed, 48 insertions(+), 11 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 47f5ace..1292a88 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -247,10 +247,10 @@ int bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb, * older_than_this takes precedence over nr_to_write. So we'll only write back * all dirty pages if they are all attached to "old" mappings. */ -static void wb_kupdated(struct bdi_writeback *wb) +static long wb_kupdated(struct bdi_writeback *wb) { unsigned long oldest_jif; - long nr_to_write; + long nr_to_write, wrote = 0; struct writeback_control wbc = { .bdi = wb->bdi, .sync_mode = WB_SYNC_NONE, @@ -273,10 +273,13 @@ static void wb_kupdated(struct bdi_writeback *wb) wbc.encountered_congestion = 0; wbc.nr_to_write = MAX_WRITEBACK_PAGES; generic_sync_wb_inodes(wb, NULL, &wbc); + wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write; if (wbc.nr_to_write > 0) break; /* All the old data is written */ nr_to_write -= MAX_WRITEBACK_PAGES; } + + return wrote; } static inline bool over_bground_thresh(void) @@ -289,7 +292,7 @@ static inline bool over_bground_thresh(void) global_page_state(NR_UNSTABLE_NFS) >= background_thresh); } -static void __wb_writeback(struct bdi_writeback *wb, long nr_pages, +static long __wb_writeback(struct bdi_writeback *wb, long nr_pages, struct super_block *sb, enum writeback_sync_modes sync_mode) { @@ -299,6 +302,7 @@ static void __wb_writeback(struct bdi_writeback *wb, long nr_pages, .older_than_this = NULL, .range_cyclic = 1, }; + long wrote = 0; for (;;) { if (sync_mode == WB_SYNC_NONE && nr_pages <= 0 && @@ -311,6 +315,7 @@ static void __wb_writeback(struct bdi_writeback *wb, long nr_pages, wbc.pages_skipped = 0; generic_sync_wb_inodes(wb, sb, &wbc); nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; + wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write; /* * If we ran out of stuff to write, bail unless more_io got set */ @@ -320,6 +325,8 @@ static void __wb_writeback(struct bdi_writeback *wb, long nr_pages, break; } } + + return wrote; } /* @@ -345,10 +352,11 @@ static struct bdi_work *get_next_work_item(struct backing_dev_info *bdi, return ret; } -static void wb_writeback(struct bdi_writeback *wb) +static long wb_writeback(struct bdi_writeback *wb) { struct backing_dev_info *bdi = wb->bdi; struct bdi_work *work; + long wrote = 0; while ((work = get_next_work_item(bdi, wb)) != NULL) { struct super_block *sb = bdi_work_sb(work); @@ -356,16 +364,20 @@ static void wb_writeback(struct bdi_writeback *wb) enum writeback_sync_modes sync_mode = work->sync_mode; wb_clear_pending(wb, work); - __wb_writeback(wb, nr_pages, sb, sync_mode); + wrote += __wb_writeback(wb, nr_pages, sb, sync_mode); } + + return wrote; } /* * This will be inlined in bdi_writeback_task() once we get rid of any * dirty inodes on the default_backing_dev_info */ -void wb_do_writeback(struct bdi_writeback *wb) +long wb_do_writeback(struct bdi_writeback *wb) { + long wrote; + /* * We get here in two cases: * @@ -377,9 +389,11 @@ void wb_do_writeback(struct bdi_writeback *wb) * items on the work_list. Process those. */ if (list_empty(&wb->bdi->work_list)) - wb_kupdated(wb); + wrote = wb_kupdated(wb); else - wb_writeback(wb); + wrote = wb_writeback(wb); + + return wrote; } /* @@ -388,12 +402,30 @@ void wb_do_writeback(struct bdi_writeback *wb) */ int bdi_writeback_task(struct bdi_writeback *wb) { + unsigned long last_active = jiffies; + unsigned long wait_jiffies = -1UL; + long pages_written; DEFINE_WAIT(wait); while (!kthread_should_stop()) { - unsigned long wait_jiffies; - wb_do_writeback(wb); + pages_written = wb_do_writeback(wb); + + if (pages_written) + 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 task will get + * recreated automatically. + */ + max_idle = max(5UL * 60 * HZ, wait_jiffies); + if (time_after(jiffies, max_idle + last_active) && + wb_is_default_task(wb)) + break; + } prepare_to_wait(&wb->wait, &wait, TASK_INTERRUPTIBLE); wait_jiffies = msecs_to_jiffies(dirty_writeback_interval * 10); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 72b4797..53e6c8d 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -113,6 +113,11 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi); extern struct mutex bdi_lock; extern struct list_head bdi_list; +static inline int wb_is_default_task(struct bdi_writeback *wb) +{ + return wb == &wb->bdi->wb; +} + static inline int bdi_wblist_needs_lock(struct backing_dev_info *bdi) { return test_bit(BDI_wblist_lock, &bdi->state); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index e414702..30e318b 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -69,7 +69,7 @@ void writeback_inodes(struct writeback_control *wbc); int inode_wait(void *); void sync_inodes_sb(struct super_block *, int wait); void sync_inodes(int wait); -void wb_do_writeback(struct bdi_writeback *wb); +long wb_do_writeback(struct bdi_writeback *wb); /* writeback.h requires fs.h; it, too, is not included from here. */ static inline void wait_on_inode(struct inode *inode) -- 1.6.3.rc0.1.gf800