From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753841AbZDHMJa (ORCPT ); Wed, 8 Apr 2009 08:09:30 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S933387AbZDHMAu (ORCPT ); Wed, 8 Apr 2009 08:00:50 -0400 Received: from brick.kernel.dk ([93.163.65.50]:48931 "EHLO kernel.dk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933401AbZDHMAW (ORCPT ); Wed, 8 Apr 2009 08:00:22 -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, Jens Axboe Subject: [PATCH 08/13] writeback: allow sleepy exit of default writeback task Date: Wed, 8 Apr 2009 14:00:11 +0200 Message-Id: <1239192016-19857-9-git-send-email-jens.axboe@oracle.com> X-Mailer: git-send-email 1.6.2.2.446.gfbdc0 In-Reply-To: <1239192016-19857-1-git-send-email-jens.axboe@oracle.com> References: <1239192016-19857-1-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 | 44 +++++++++++++++++++++++++++++++++++------- include/linux/backing-dev.h | 5 ++++ include/linux/writeback.h | 2 +- 3 files changed, 42 insertions(+), 9 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index bcca7c1..7ed86a0 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -153,9 +153,9 @@ 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. */ -void wb_kupdated(struct bdi_writeback *wb) +long wb_kupdated(struct bdi_writeback *wb) { - long nr_to_write; + long nr_to_write, wrote = 0; struct writeback_control wbc = { .bdi = wb->bdi, .sync_mode = WB_SYNC_NONE, @@ -175,13 +175,16 @@ void wb_kupdated(struct bdi_writeback *wb) wbc.encountered_congestion = 0; wbc.nr_to_write = MAX_WRITEBACK_PAGES; generic_sync_bdi_inodes(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; } -void wb_writeback(struct bdi_writeback *wb) +long wb_writeback(struct bdi_writeback *wb) { struct writeback_control wbc = { .bdi = wb->bdi, @@ -189,7 +192,7 @@ void wb_writeback(struct bdi_writeback *wb) .older_than_this = NULL, .range_cyclic = 1, }; - long nr_pages = wb->nr_pages; + long nr_pages = wb->nr_pages, wrote = 0; for (;;) { unsigned long background_thresh, dirty_thresh; @@ -205,6 +208,7 @@ void wb_writeback(struct bdi_writeback *wb) wbc.pages_skipped = 0; generic_sync_wb_inodes(wb, 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 */ @@ -214,14 +218,18 @@ void wb_writeback(struct bdi_writeback *wb) break; } } + + 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 nr_pages; + /* * We get here in two cases: * @@ -237,11 +245,12 @@ void wb_do_writeback(struct bdi_writeback *wb) * */ if (writeback_acquire(wb)) - wb_kupdated(wb); + nr_pages = wb_kupdated(wb); else - wb_writeback(wb); + nr_pages = wb_writeback(wb); writeback_release(wb); + return nr_pages; } /* @@ -250,6 +259,9 @@ void wb_do_writeback(struct bdi_writeback *wb) */ int bdi_writeback_task(struct bdi_writeback *wb) { + unsigned long last_active = jiffies; + long pages_written; + while (!kthread_should_stop()) { unsigned long wait_jiffies; DEFINE_WAIT(wait); @@ -259,9 +271,25 @@ int bdi_writeback_task(struct bdi_writeback *wb) schedule_timeout(wait_jiffies); try_to_freeze(); - wb_do_writeback(wb); + pages_written = wb_do_writeback(wb); finish_wait(&wb->wait, &wait); + + if (pages_written) + last_active = jiffies; + else { + 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; + } } return 0; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index c596bf6..ce23ec7 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -112,6 +112,11 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi); extern spinlock_t 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 2e08bbd..ddb10dc 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) -- 1.6.2.2.446.gfbdc0