From: Daniel Phillips <phillips@phunq.net>
To: Jens Axboe <jens.axboe@oracle.com>
Cc: linux-kernel@vger.kernel.org,
Andrew Morton <akpm@linux-foundation.org>,
Peter Zijlstra <peterz@infradead.org>
Subject: Re: [RFC] [PATCH] A clean approach to writeout throttling
Date: Mon, 10 Dec 2007 03:33:20 -0800 [thread overview]
Message-ID: <200712100333.20934.phillips@phunq.net> (raw)
In-Reply-To: <20071210104749.GC5008@kernel.dk>
[-- Attachment #1: Type: text/plain, Size: 152 bytes --]
On Monday 10 December 2007 02:47, Jens Axboe wrote:
> ...the warning on request_queue_t...
There you go, Jens, service with a smile.
Regards,
Daniel
[-- Attachment #2: bio.throttle-2.6.24-rc3-mm --]
[-- Type: text/x-diff, Size: 3912 bytes --]
--- 2.6.24-rc3-mm.clean/block/ll_rw_blk.c 2007-12-04 14:45:25.000000000 -0800
+++ 2.6.24-rc3-mm/block/ll_rw_blk.c 2007-12-10 03:27:42.000000000 -0800
@@ -3210,7 +3210,7 @@ static inline int bio_check_eod(struct b
*/
static inline void __generic_make_request(struct bio *bio)
{
- struct request_queue *q;
+ struct request_queue *q = bdev_get_queue(bio->bi_bdev);
sector_t old_sector;
int ret, nr_sectors = bio_sectors(bio);
dev_t old_dev;
@@ -3221,6 +3221,13 @@ static inline void __generic_make_reques
if (bio_check_eod(bio, nr_sectors))
goto end_io;
+ if (q && q->metric && !bio->bi_queue) {
+ int need = bio->bi_throttle = q->metric(bio);
+ bio->bi_queue = q;
+ /* FIXME: potential race if atomic_sub is called in the middle of condition check */
+ wait_event_interruptible(q->throttle_wait, atomic_read(&q->available) >= need);
+ atomic_sub(need, &q->available);
+ }
/*
* Resolve the mapping until finished. (drivers are
* still free to implement/resolve their own stacking
@@ -3234,7 +3241,6 @@ static inline void __generic_make_reques
do {
char b[BDEVNAME_SIZE];
- q = bdev_get_queue(bio->bi_bdev);
if (!q) {
printk(KERN_ERR
"generic_make_request: Trying to access "
--- 2.6.24-rc3-mm.clean/drivers/md/dm.c 2007-12-04 14:46:04.000000000 -0800
+++ 2.6.24-rc3-mm/drivers/md/dm.c 2007-12-04 23:31:41.000000000 -0800
@@ -889,6 +889,11 @@ static int dm_any_congested(void *conges
return r;
}
+static unsigned dm_metric(struct bio *bio)
+{
+ return bio->bi_vcnt;
+}
+
/*-----------------------------------------------------------------
* An IDR is used to keep track of allocated minor numbers.
*---------------------------------------------------------------*/
@@ -967,6 +972,7 @@ out:
static struct block_device_operations dm_blk_dops;
+#define DEFAULT_THROTTLE_CAPACITY 1000
/*
* Allocate and initialise a blank device with a given minor.
*/
@@ -1009,6 +1015,11 @@ static struct mapped_device *alloc_dev(i
goto bad1_free_minor;
md->queue->queuedata = md;
+ md->queue->metric = dm_metric;
+ /* A dm device constructor may change the throttle capacity */
+ atomic_set(&md->queue->available, md->queue->capacity = DEFAULT_THROTTLE_CAPACITY);
+ init_waitqueue_head(&md->queue->throttle_wait);
+
md->queue->backing_dev_info.congested_fn = dm_any_congested;
md->queue->backing_dev_info.congested_data = md;
blk_queue_make_request(md->queue, dm_request);
--- 2.6.24-rc3-mm.clean/fs/bio.c 2007-12-04 14:38:47.000000000 -0800
+++ 2.6.24-rc3-mm/fs/bio.c 2007-12-04 23:31:41.000000000 -0800
@@ -1007,6 +1007,13 @@ void bio_endio(struct bio *bio, int erro
else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
error = -EIO;
+ if (bio->bi_throttle) {
+ struct request_queue *q = bio->bi_queue;
+ bio->bi_throttle = 0; /* or detect multiple endio and err? */
+ atomic_add(bio->bi_throttle, &q->available);
+ wake_up(&q->throttle_wait);
+ }
+
if (bio->bi_end_io)
bio->bi_end_io(bio, error);
}
--- 2.6.24-rc3-mm.clean/include/linux/bio.h 2007-12-04 14:39:31.000000000 -0800
+++ 2.6.24-rc3-mm/include/linux/bio.h 2007-12-04 23:31:41.000000000 -0800
@@ -111,6 +111,9 @@ struct bio {
bio_end_io_t *bi_end_io;
atomic_t bi_cnt; /* pin count */
+ struct request_queue *bi_queue; /* for throttling */
+ unsigned bi_throttle; /* throttle metric */
+
void *bi_private;
bio_destructor_t *bi_destructor; /* destructor */
--- 2.6.24-rc3-mm.clean/include/linux/blkdev.h 2007-12-04 14:47:18.000000000 -0800
+++ 2.6.24-rc3-mm/include/linux/blkdev.h 2007-12-04 23:31:41.000000000 -0800
@@ -383,6 +383,10 @@ struct request_queue
struct work_struct unplug_work;
struct backing_dev_info backing_dev_info;
+ unsigned (*metric)(struct bio *bio); /* bio throttle metric */
+ wait_queue_head_t throttle_wait;
+ atomic_t available;
+ unsigned capacity;
/*
* The queue owner gets to use this for whatever they like.
next prev parent reply other threads:[~2007-12-10 11:33 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-12-06 0:03 [RFC] [PATCH] A clean approach to writeout throttling Daniel Phillips
2007-12-06 1:24 ` Andrew Morton
2007-12-06 6:21 ` Daniel Phillips
2007-12-06 7:31 ` Andrew Morton
2007-12-06 9:48 ` Daniel Phillips
2007-12-06 11:55 ` Andrew Morton
2007-12-06 15:52 ` Rik van Riel
2007-12-06 17:34 ` Andrew Morton
2007-12-06 17:48 ` Rik van Riel
2007-12-06 20:04 ` Daniel Phillips
2007-12-06 20:27 ` Andrew Morton
2007-12-06 21:27 ` Daniel Phillips
2007-12-06 21:53 ` Bill Davidsen
2007-12-07 0:04 ` Daniel Phillips
2007-12-07 0:29 ` Andrew Morton
2007-12-07 7:13 ` Daniel Phillips
2007-12-10 9:20 ` Daniel Phillips
2007-12-10 10:47 ` Jens Axboe
2007-12-10 11:23 ` [RFC] [PATCH] A clean aEvgeniy pproach " Daniel Phillips
2007-12-10 11:41 ` Jens Axboe
2007-12-10 12:13 ` Daniel Phillips
2007-12-10 12:16 ` Jens Axboe
2007-12-10 12:27 ` Daniel Phillips
2007-12-10 12:32 ` Jens Axboe
2007-12-10 13:04 ` Daniel Phillips
2007-12-10 13:19 ` Jens Axboe
2007-12-10 13:26 ` Daniel Phillips
2007-12-10 13:30 ` Jens Axboe
2007-12-10 13:43 ` Daniel Phillips
2007-12-10 13:53 ` Jens Axboe
2007-12-10 14:17 ` Daniel Phillips
2007-12-11 13:15 ` Jens Axboe
2007-12-11 19:38 ` Daniel Phillips
2007-12-11 20:01 ` Jens Axboe
2007-12-11 20:11 ` Daniel Phillips
2007-12-11 20:07 ` Daniel Phillips
2007-12-10 11:33 ` Daniel Phillips [this message]
2007-12-10 21:31 ` [RFC] [PATCH] A clean approach " Jonathan Corbet
2007-12-10 22:06 ` Pekka Enberg
2007-12-11 4:21 ` Daniel Phillips
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=200712100333.20934.phillips@phunq.net \
--to=phillips@phunq.net \
--cc=akpm@linux-foundation.org \
--cc=jens.axboe@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=peterz@infradead.org \
/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).