* [patch]block: add plug for blkdev_issue_discard
@ 2012-10-09 1:11 Shaohua Li
2012-10-09 1:56 ` Mike Snitzer
0 siblings, 1 reply; 3+ messages in thread
From: Shaohua Li @ 2012-10-09 1:11 UTC (permalink / raw)
To: axboe; +Cc: linux-kernel
Now discard merge works, add plug for blkdev_issue_discard. This will help
discard request merge especially for raid0 case. In raid0, a big discard
request is split to small requests, and if correct plug is added, such small
requests can be merged in low layer.
Signed-off-by: Shaohua Li <shli@fusionio.com>
---
block/blk-lib.c | 3 +++
1 file changed, 3 insertions(+)
Index: linux/block/blk-lib.c
===================================================================
--- linux.orig/block/blk-lib.c 2012-09-28 15:09:38.655327319 +0800
+++ linux/block/blk-lib.c 2012-10-09 08:45:04.358598888 +0800
@@ -48,6 +48,7 @@ int blkdev_issue_discard(struct block_de
struct bio_batch bb;
struct bio *bio;
int ret = 0;
+ struct blk_plug plug;
if (!q)
return -ENXIO;
@@ -81,6 +82,7 @@ int blkdev_issue_discard(struct block_de
bb.flags = 1 << BIO_UPTODATE;
bb.wait = &wait;
+ blk_start_plug(&plug);
while (nr_sects) {
unsigned int req_sects;
sector_t end_sect;
@@ -117,6 +119,7 @@ int blkdev_issue_discard(struct block_de
atomic_inc(&bb.done);
submit_bio(type, bio);
}
+ blk_finish_plug(&plug);
/* Wait for bios in-flight */
if (!atomic_dec_and_test(&bb.done))
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [patch]block: add plug for blkdev_issue_discard
2012-10-09 1:11 [patch]block: add plug for blkdev_issue_discard Shaohua Li
@ 2012-10-09 1:56 ` Mike Snitzer
2012-10-09 1:59 ` Jens Axboe
0 siblings, 1 reply; 3+ messages in thread
From: Mike Snitzer @ 2012-10-09 1:56 UTC (permalink / raw)
To: Shaohua Li; +Cc: axboe, linux-kernel
On Mon, Oct 8, 2012 at 9:11 PM, Shaohua Li <shli@kernel.org> wrote:
> Now discard merge works, add plug for blkdev_issue_discard. This will help
> discard request merge especially for raid0 case. In raid0, a big discard
> request is split to small requests, and if correct plug is added, such small
> requests can be merged in low layer.
>
> Signed-off-by: Shaohua Li <shli@fusionio.com>
> ---
> block/blk-lib.c | 3 +++
> 1 file changed, 3 insertions(+)
>
> Index: linux/block/blk-lib.c
> ===================================================================
> --- linux.orig/block/blk-lib.c 2012-09-28 15:09:38.655327319 +0800
> +++ linux/block/blk-lib.c 2012-10-09 08:45:04.358598888 +0800
> @@ -48,6 +48,7 @@ int blkdev_issue_discard(struct block_de
> struct bio_batch bb;
> struct bio *bio;
> int ret = 0;
> + struct blk_plug plug;
>
> if (!q)
> return -ENXIO;
> @@ -81,6 +82,7 @@ int blkdev_issue_discard(struct block_de
> bb.flags = 1 << BIO_UPTODATE;
> bb.wait = &wait;
>
> + blk_start_plug(&plug);
> while (nr_sects) {
> unsigned int req_sects;
> sector_t end_sect;
> @@ -117,6 +119,7 @@ int blkdev_issue_discard(struct block_de
> atomic_inc(&bb.done);
> submit_bio(type, bio);
> }
> + blk_finish_plug(&plug);
>
> /* Wait for bios in-flight */
> if (!atomic_dec_and_test(&bb.done))
That plug looks rather coarse-grained. Any adverse affects when mkfs
discards an entire (large) raid0 device? (I suspect not but figured
I'd ask)
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [patch]block: add plug for blkdev_issue_discard
2012-10-09 1:56 ` Mike Snitzer
@ 2012-10-09 1:59 ` Jens Axboe
0 siblings, 0 replies; 3+ messages in thread
From: Jens Axboe @ 2012-10-09 1:59 UTC (permalink / raw)
To: Mike Snitzer; +Cc: Shaohua Li, linux-kernel
On 2012-10-08 19:56, Mike Snitzer wrote:
> On Mon, Oct 8, 2012 at 9:11 PM, Shaohua Li <shli@kernel.org> wrote:
>> Now discard merge works, add plug for blkdev_issue_discard. This will help
>> discard request merge especially for raid0 case. In raid0, a big discard
>> request is split to small requests, and if correct plug is added, such small
>> requests can be merged in low layer.
>>
>> Signed-off-by: Shaohua Li <shli@fusionio.com>
>> ---
>> block/blk-lib.c | 3 +++
>> 1 file changed, 3 insertions(+)
>>
>> Index: linux/block/blk-lib.c
>> ===================================================================
>> --- linux.orig/block/blk-lib.c 2012-09-28 15:09:38.655327319 +0800
>> +++ linux/block/blk-lib.c 2012-10-09 08:45:04.358598888 +0800
>> @@ -48,6 +48,7 @@ int blkdev_issue_discard(struct block_de
>> struct bio_batch bb;
>> struct bio *bio;
>> int ret = 0;
>> + struct blk_plug plug;
>>
>> if (!q)
>> return -ENXIO;
>> @@ -81,6 +82,7 @@ int blkdev_issue_discard(struct block_de
>> bb.flags = 1 << BIO_UPTODATE;
>> bb.wait = &wait;
>>
>> + blk_start_plug(&plug);
>> while (nr_sects) {
>> unsigned int req_sects;
>> sector_t end_sect;
>> @@ -117,6 +119,7 @@ int blkdev_issue_discard(struct block_de
>> atomic_inc(&bb.done);
>> submit_bio(type, bio);
>> }
>> + blk_finish_plug(&plug);
>>
>> /* Wait for bios in-flight */
>> if (!atomic_dec_and_test(&bb.done))
>
> That plug looks rather coarse-grained. Any adverse affects when mkfs
> discards an entire (large) raid0 device? (I suspect not but figured
> I'd ask)
Block core auto-unplugs after a certain depth is reached. So it's better
to make it coarse than try to second guess when to unplug.
--
Jens Axboe
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2012-10-09 2:00 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2012-10-09 1:11 [patch]block: add plug for blkdev_issue_discard Shaohua Li
2012-10-09 1:56 ` Mike Snitzer
2012-10-09 1:59 ` Jens Axboe
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox