[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1279806988-14100-13-git-send-email-dedekind1@gmail.com>
Date: Thu, 22 Jul 2010 16:56:26 +0300
From: Artem Bityutskiy <dedekind1@...il.com>
To: Jens Axboe <axboe@...nel.dk>
Cc: linux-fsdevel@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: [PATCHv3 12/14] writeback: optimize periodic bdi thread wakeups
From: Artem Bityutskiy <Artem.Bityutskiy@...ia.com>
Whe the first inode for a bdi is marked dirty, we wake up the bdi thread which
should take care of the periodic background write-out. However, the write-out
will actually start only 'dirty_writeback_interval' centisecs later, so we can
delay the wake-up.
This change was requested by Nick Piggin who pointed out that if we delay the
wake-up, we weed out 2 unnecessary contex switches, which matters because
'__mark_inode_dirty()' is a hot-path function.
This patch introduces a new function - 'bdi_wakeup_thread_delayed()', which
sets up a timer to wake-up the bdi thread and returns. So the wake-up is
delayed.
We also delete the timer in bdi threads just before writing-back.
This patch also moves the 'bdi_wb_init()' function down in the file to avoid
forward-declaration of 'bdi_wakeup_thread_delayed()'.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@...ia.com>
---
fs/fs-writeback.c | 28 +++++--------------
include/linux/backing-dev.h | 2 +
mm/backing-dev.c | 64 +++++++++++++++++++++++++++++++++++--------
3 files changed, 61 insertions(+), 33 deletions(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 6477782..d8d0a21 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -817,6 +817,12 @@ int bdi_writeback_thread(void *data)
trace_writeback_thread_start(bdi);
while (!kthread_should_stop()) {
+ /*
+ * Remove own delayed wake-up timer, since we are already awake
+ * and we'll take care of the preriodic write-back.
+ */
+ del_timer(&wb->wakeup_timer);
+
pages_written = wb_do_writeback(wb, 0);
trace_writeback_pages_written(pages_written);
@@ -875,26 +881,6 @@ void wakeup_flusher_threads(long nr_pages)
rcu_read_unlock();
}
-/*
- * This function is used when the first inode for this bdi is marked dirty. It
- * wakes-up the corresponding bdi thread which should then take care of the
- * periodic background write-out of dirty inodes.
- */
-static void wakeup_bdi_thread(struct backing_dev_info *bdi)
-{
- spin_lock(&bdi->wb_lock);
- if (bdi->wb.task)
- wake_up_process(bdi->wb.task);
- else
- /*
- * When bdi tasks are inactive for long time, they are killed.
- * In this case we have to wake-up the forker thread which
- * should create and run the bdi thread.
- */
- wake_up_process(default_backing_dev_info.wb.task);
- spin_unlock(&bdi->wb_lock);
-}
-
static noinline void block_dump___mark_inode_dirty(struct inode *inode)
{
if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
@@ -1026,7 +1012,7 @@ out:
spin_unlock(&inode_lock);
if (wakeup_bdi)
- wakeup_bdi_thread(bdi);
+ bdi_wakeup_thread_delayed(bdi);
}
EXPORT_SYMBOL(__mark_inode_dirty);
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 71b6223..7628219 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -52,6 +52,7 @@ struct bdi_writeback {
unsigned long last_active; /* last time bdi thread was active */
struct task_struct *task; /* writeback thread */
+ struct timer_list wakeup_timer; /* used for delayed bdi thread wakeup */
struct list_head b_dirty; /* dirty inodes */
struct list_head b_io; /* parked for writeback */
struct list_head b_more_io; /* parked for more writeback */
@@ -105,6 +106,7 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi);
int bdi_writeback_thread(void *data);
int bdi_has_dirty_io(struct backing_dev_info *bdi);
void bdi_arm_supers_timer(void);
+void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi);
extern spinlock_t bdi_lock;
extern struct list_head bdi_list;
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index ef880d9..cba2255 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -248,17 +248,6 @@ static int __init default_bdi_init(void)
}
subsys_initcall(default_bdi_init);
-static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
-{
- memset(wb, 0, sizeof(*wb));
-
- wb->bdi = bdi;
- wb->last_old_flush = jiffies;
- INIT_LIST_HEAD(&wb->b_dirty);
- INIT_LIST_HEAD(&wb->b_io);
- INIT_LIST_HEAD(&wb->b_more_io);
-}
-
int bdi_has_dirty_io(struct backing_dev_info *bdi)
{
return wb_has_dirty_io(&bdi->wb);
@@ -316,6 +305,43 @@ static void sync_supers_timer_fn(unsigned long unused)
bdi_arm_supers_timer();
}
+static void wakeup_timer_fn(unsigned long data)
+{
+ struct backing_dev_info *bdi = (struct backing_dev_info *)data;
+
+ spin_lock(&bdi->wb_lock);
+ if (bdi->wb.task) {
+ wake_up_process(bdi->wb.task);
+ } else {
+ /*
+ * When bdi tasks are inactive for long time, they are killed.
+ * In this case we have to wake-up the forker thread which
+ * should create and run the bdi thread.
+ */
+ wake_up_process(default_backing_dev_info.wb.task);
+ }
+ spin_unlock(&bdi->wb_lock);
+}
+
+/*
+ * This function is used when the first inode for this bdi is marked dirty. It
+ * wakes-up the corresponding bdi thread which should then take care of the
+ * periodic background write-out of dirty inodes. Since the write-out would
+ * starts only 'dirty_writeback_interval' centisecs from now anyway, we just
+ * set up a timer which wakes the bdi thread up later.
+ *
+ * Note, we wouldn't bother setting up the timer, but this function is on the
+ * fast-path (used by '__mark_inode_dirty()'), so we save few context switches
+ * by delaying the wake-up.
+ */
+void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi)
+{
+ unsigned long timeout;
+
+ timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
+ mod_timer(&bdi->wb.wakeup_timer, jiffies + timeout);
+}
+
/*
* Calculate the longest interval (jiffies) bdi threads are allowed to be
* inactive.
@@ -349,8 +375,10 @@ static int bdi_forker_thread(void *ptr)
* Temporary measure, we want to make sure we don't see
* dirty data on the default backing_dev_info
*/
- if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list))
+ if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list)) {
+ del_timer(&me->wakeup_timer);
wb_do_writeback(me, 0);
+ }
spin_lock_bh(&bdi_lock);
set_current_state(TASK_INTERRUPTIBLE);
@@ -577,6 +605,18 @@ void bdi_unregister(struct backing_dev_info *bdi)
}
EXPORT_SYMBOL(bdi_unregister);
+static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
+{
+ memset(wb, 0, sizeof(*wb));
+
+ wb->bdi = bdi;
+ wb->last_old_flush = jiffies;
+ INIT_LIST_HEAD(&wb->b_dirty);
+ INIT_LIST_HEAD(&wb->b_io);
+ INIT_LIST_HEAD(&wb->b_more_io);
+ setup_timer(&wb->wakeup_timer, wakeup_timer_fn, (unsigned long)bdi);
+}
+
int bdi_init(struct backing_dev_info *bdi)
{
int i, err;
--
1.7.1.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists