From: Jens Axboe <jens.axboe@oracle.com>
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, richard@rsk.demon.co.uk,
damien.wyart@free.fr, fweisbec@gmail.com, Alan.Brunelle@hp.com,
Jens Axboe <jens.axboe@oracle.com>
Subject: [PATCH 06/10] writeback: allow sleepy exit of default writeback task
Date: Wed, 17 Jun 2009 13:07:18 +0200 [thread overview]
Message-ID: <1245236842-3141-7-git-send-email-jens.axboe@oracle.com> (raw)
In-Reply-To: <1245236842-3141-1-git-send-email-jens.axboe@oracle.com>
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 <jens.axboe@oracle.com>
---
fs/fs-writeback.c | 54 ++++++++++++++++++++++++++++++++++--------
include/linux/backing-dev.h | 5 ++++
include/linux/writeback.h | 2 +-
3 files changed, 49 insertions(+), 12 deletions(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 38a1cdf..61b8a91 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -284,10 +284,10 @@ void 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,
@@ -308,10 +308,13 @@ 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)
@@ -324,7 +327,7 @@ 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)
{
@@ -334,6 +337,7 @@ 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 &&
@@ -346,6 +350,7 @@ 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
*/
@@ -355,6 +360,8 @@ static void __wb_writeback(struct bdi_writeback *wb, long nr_pages,
break;
}
}
+
+ return wrote;
}
/*
@@ -383,10 +390,11 @@ static struct bdi_work *get_next_work_item(struct backing_dev_info *bdi,
/*
* Retrieve work items and do the writeback they describe
*/
-static void wb_writeback(struct bdi_writeback *wb, int force_wait)
+static long wb_writeback(struct bdi_writeback *wb, int force_wait)
{
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);
@@ -408,7 +416,7 @@ static void wb_writeback(struct bdi_writeback *wb, int force_wait)
if (sync_mode == WB_SYNC_NONE)
wb_clear_pending(wb, work);
- __wb_writeback(wb, nr_pages, sb, sync_mode);
+ wrote += __wb_writeback(wb, nr_pages, sb, sync_mode);
/*
* This is a data integrity writeback, so only do the
@@ -417,14 +425,18 @@ static void wb_writeback(struct bdi_writeback *wb, int force_wait)
if (sync_mode == WB_SYNC_ALL)
wb_clear_pending(wb, work);
}
+
+ 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, int force_wait)
+long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
{
+ long wrote;
+
/*
* We get here in two cases:
*
@@ -436,9 +448,11 @@ void wb_do_writeback(struct bdi_writeback *wb, int force_wait)
* 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, force_wait);
+ wrote = wb_writeback(wb, force_wait);
+
+ return wrote;
}
/*
@@ -447,10 +461,28 @@ void wb_do_writeback(struct bdi_writeback *wb, int force_wait)
*/
int bdi_writeback_task(struct bdi_writeback *wb)
{
+ unsigned long last_active = jiffies;
+ unsigned long wait_jiffies = -1UL;
+ long pages_written;
+
while (!kthread_should_stop()) {
- unsigned long wait_jiffies;
+ pages_written = wb_do_writeback(wb, 0);
+
+ if (pages_written)
+ last_active = jiffies;
+ else if (wait_jiffies != -1UL) {
+ unsigned long max_idle;
- wb_do_writeback(wb, 0);
+ /*
+ * 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;
+ }
wait_jiffies = msecs_to_jiffies(dirty_writeback_interval * 10);
set_current_state(TASK_INTERRUPTIBLE);
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index f7e4c6a..0bc9dbb 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -111,6 +111,11 @@ 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 588a449..e070b91 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -68,7 +68,7 @@ struct writeback_control {
void writeback_inodes(struct writeback_control *wbc);
int inode_wait(void *);
void sync_inodes_sb(struct super_block *, int wait);
-void wb_do_writeback(struct bdi_writeback *wb, int force_wait);
+long wb_do_writeback(struct bdi_writeback *wb, int force_wait);
/* 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
next prev parent reply other threads:[~2009-06-17 11:07 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-06-17 11:07 [PATCH 0/10] Per-bdi writeback flusher threads v11 Jens Axboe
2009-06-17 11:07 ` [PATCH 01/10] writeback: move dirty inodes from super_block to backing_dev_info Jens Axboe
2009-06-17 11:07 ` [PATCH 02/10] writeback: switch to per-bdi threads for flushing data Jens Axboe
2009-06-17 11:07 ` [PATCH 03/10] writeback: get rid of pdflush completely Jens Axboe
2009-06-17 11:07 ` [PATCH 04/10] writeback: separate the flushing state/task from the bdi Jens Axboe
2009-06-17 11:07 ` [PATCH 05/10] writeback: support > 1 flusher thread per bdi Jens Axboe
2009-06-17 11:07 ` Jens Axboe [this message]
2009-06-17 11:07 ` [PATCH 07/10] writeback: add some debug inode list counters to bdi stats Jens Axboe
2009-06-17 11:07 ` [PATCH 08/10] writeback: add name to backing_dev_info Jens Axboe
2009-06-17 11:07 ` [PATCH 09/10] writeback: check for registered bdi in flusher add and inode dirty Jens Axboe
2009-06-17 11:07 ` [PATCH 10/10] writeback: use spin_trylock() in bdi_writeback_all() for WB_SYNC_NONE Jens Axboe
2009-06-17 12:18 ` 2.6.30 backport (Was "Re: [PATCH 0/10] Per-bdi writeback flusher threads v11") Jens Axboe
-- strict thread matches above, loose matches on Subject: below --
2009-06-25 10:41 [PATCH 0/10] Per-bdi writeback flusher threads v12 Jens Axboe
2009-06-25 10:41 ` [PATCH 06/10] writeback: allow sleepy exit of default writeback task Jens Axboe
2009-08-31 12:14 [PATCH 0/10] Per-bdi writeback flusher threads v14 Jens Axboe
2009-08-31 12:14 ` [PATCH 06/10] writeback: allow sleepy exit of default writeback task Jens Axboe
2009-08-31 13:02 ` Christoph Hellwig
2009-08-31 17:32 ` Jens Axboe
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1245236842-3141-7-git-send-email-jens.axboe@oracle.com \
--to=jens.axboe@oracle.com \
--cc=Alan.Brunelle@hp.com \
--cc=akpm@linux-foundation.org \
--cc=chris.mason@oracle.com \
--cc=damien.wyart@free.fr \
--cc=david@fromorbit.com \
--cc=fweisbec@gmail.com \
--cc=hch@infradead.org \
--cc=jack@suse.cz \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=richard@rsk.demon.co.uk \
--cc=yanmin_zhang@linux.intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).