* [PATCH V3] block: fix the DISCARD request merge
@ 2018-10-24 3:07 Jianchao Wang
2018-10-24 11:22 ` Christoph Hellwig
2018-10-26 8:05 ` jianchao.wang
0 siblings, 2 replies; 5+ messages in thread
From: Jianchao Wang @ 2018-10-24 3:07 UTC (permalink / raw)
To: axboe; +Cc: martin.petersen, tom.leiming, hch, linux-block, linux-kernel
There are two cases when handle DISCARD merge.
If max_discard_segments == 1, the bios/requests need to be contiguous
to merge. If max_discard_segments > 1, it takes every bio as a range
and different range needn't to be contiguous.
But now, attempt_merge screws this up. It always consider contiguity
for DISCARD for the case max_discard_segments > 1 and cannot merge
contiguous DISCARD for the case max_discard_segments == 1, because
rq_attempt_discard_merge always returns false in this case.
This patch fixes both of the two cases above.
Signed-off-by: Jianchao Wang <jianchao.w.wang@oracle.com>
---
V3:
- Introduce blk_discard_mergable into attempt_merge and
blk_try_merge.
- Some comment changes.
V2:
- Add max_discard_segments > 1 checking in attempt_merge.
- Change patch title and comment.
- Add more comment in attempt_merge
block/blk-merge.c | 34 ++++++++++++++++++++++++----------
1 file changed, 24 insertions(+), 10 deletions(-)
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 42a4674..b258de0 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -714,6 +714,22 @@ static void blk_account_io_merge(struct request *req)
part_stat_unlock();
}
}
+/*
+ * Two cases of handling DISCARD merge:
+ * If max_discard_segments > 1, the driver takes every bio
+ * as a range and send them to controller together. The ranges
+ * needn't to be contiguous.
+ * Otherwise, the bios/requests will be handled as same as
+ * others which should be contiguous.
+ */
+static inline bool blk_discard_mergable(struct request *req)
+{
+ if (req_op(req) == REQ_OP_DISCARD &&
+ queue_max_discard_segments(req->q) > 1)
+ return true;
+ else
+ return false;
+}
/*
* For non-mq, this has to be called with the request spinlock acquired.
@@ -731,12 +747,6 @@ static struct request *attempt_merge(struct request_queue *q,
if (req_op(req) != req_op(next))
return NULL;
- /*
- * not contiguous
- */
- if (blk_rq_pos(req) + blk_rq_sectors(req) != blk_rq_pos(next))
- return NULL;
-
if (rq_data_dir(req) != rq_data_dir(next)
|| req->rq_disk != next->rq_disk
|| req_no_special_merge(next))
@@ -760,11 +770,16 @@ static struct request *attempt_merge(struct request_queue *q,
* counts here. Handle DISCARDs separately, as they
* have separate settings.
*/
- if (req_op(req) == REQ_OP_DISCARD) {
+
+ if (blk_discard_mergable(req)) {
if (!req_attempt_discard_merge(q, req, next))
return NULL;
- } else if (!ll_merge_requests_fn(q, req, next))
+ } else if (blk_rq_pos(req) + blk_rq_sectors(req) == blk_rq_pos(next)) {
+ if (!ll_merge_requests_fn(q, req, next))
+ return NULL;
+ } else {
return NULL;
+ }
/*
* If failfast settings disagree or any of the two is already
@@ -888,8 +903,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
enum elv_merge blk_try_merge(struct request *rq, struct bio *bio)
{
- if (req_op(rq) == REQ_OP_DISCARD &&
- queue_max_discard_segments(rq->q) > 1)
+ if (blk_discard_mergable(rq))
return ELEVATOR_DISCARD_MERGE;
else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector)
return ELEVATOR_BACK_MERGE;
--
2.7.4
^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [PATCH V3] block: fix the DISCARD request merge
2018-10-24 3:07 [PATCH V3] block: fix the DISCARD request merge Jianchao Wang
@ 2018-10-24 11:22 ` Christoph Hellwig
2018-10-26 8:05 ` jianchao.wang
1 sibling, 0 replies; 5+ messages in thread
From: Christoph Hellwig @ 2018-10-24 11:22 UTC (permalink / raw)
To: Jianchao Wang
Cc: axboe, martin.petersen, tom.leiming, hch, linux-block, linux-kernel
> - /*
> - * not contiguous
> - */
> - if (blk_rq_pos(req) + blk_rq_sectors(req) != blk_rq_pos(next))
> - return NULL;
> -
As suggested previously I think we want something like blk_try_merge
and its return values here. Maybe a blk_try_req_merge that takes
requests instead of bios.
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH V3] block: fix the DISCARD request merge
2018-10-24 3:07 [PATCH V3] block: fix the DISCARD request merge Jianchao Wang
2018-10-24 11:22 ` Christoph Hellwig
@ 2018-10-26 8:05 ` jianchao.wang
2018-10-26 8:07 ` Christoph Hellwig
1 sibling, 1 reply; 5+ messages in thread
From: jianchao.wang @ 2018-10-26 8:05 UTC (permalink / raw)
To: axboe; +Cc: martin.petersen, Ming Lei, hch, linux-block, linux-kernel
Would anyone please take a look at this ?
Thanks in advance.
Jianchao
On 10/24/18 11:07 AM, Jianchao Wang wrote:
> There are two cases when handle DISCARD merge.
> If max_discard_segments == 1, the bios/requests need to be contiguous
> to merge. If max_discard_segments > 1, it takes every bio as a range
> and different range needn't to be contiguous.
>
> But now, attempt_merge screws this up. It always consider contiguity
> for DISCARD for the case max_discard_segments > 1 and cannot merge
> contiguous DISCARD for the case max_discard_segments == 1, because
> rq_attempt_discard_merge always returns false in this case.
> This patch fixes both of the two cases above.
>
> Signed-off-by: Jianchao Wang <jianchao.w.wang@oracle.com>
> ---
>
> V3:
> - Introduce blk_discard_mergable into attempt_merge and
> blk_try_merge.
> - Some comment changes.
>
> V2:
> - Add max_discard_segments > 1 checking in attempt_merge.
> - Change patch title and comment.
> - Add more comment in attempt_merge
>
> block/blk-merge.c | 34 ++++++++++++++++++++++++----------
> 1 file changed, 24 insertions(+), 10 deletions(-)
>
> diff --git a/block/blk-merge.c b/block/blk-merge.c
> index 42a4674..b258de0 100644
> --- a/block/blk-merge.c
> +++ b/block/blk-merge.c
> @@ -714,6 +714,22 @@ static void blk_account_io_merge(struct request *req)
> part_stat_unlock();
> }
> }
> +/*
> + * Two cases of handling DISCARD merge:
> + * If max_discard_segments > 1, the driver takes every bio
> + * as a range and send them to controller together. The ranges
> + * needn't to be contiguous.
> + * Otherwise, the bios/requests will be handled as same as
> + * others which should be contiguous.
> + */
> +static inline bool blk_discard_mergable(struct request *req)
> +{
> + if (req_op(req) == REQ_OP_DISCARD &&
> + queue_max_discard_segments(req->q) > 1)
> + return true;
> + else
> + return false;
> +}
>
> /*
> * For non-mq, this has to be called with the request spinlock acquired.
> @@ -731,12 +747,6 @@ static struct request *attempt_merge(struct request_queue *q,
> if (req_op(req) != req_op(next))
> return NULL;
>
> - /*
> - * not contiguous
> - */
> - if (blk_rq_pos(req) + blk_rq_sectors(req) != blk_rq_pos(next))
> - return NULL;
> -
> if (rq_data_dir(req) != rq_data_dir(next)
> || req->rq_disk != next->rq_disk
> || req_no_special_merge(next))
> @@ -760,11 +770,16 @@ static struct request *attempt_merge(struct request_queue *q,
> * counts here. Handle DISCARDs separately, as they
> * have separate settings.
> */
> - if (req_op(req) == REQ_OP_DISCARD) {
> +
> + if (blk_discard_mergable(req)) {
> if (!req_attempt_discard_merge(q, req, next))
> return NULL;
> - } else if (!ll_merge_requests_fn(q, req, next))
> + } else if (blk_rq_pos(req) + blk_rq_sectors(req) == blk_rq_pos(next)) {
> + if (!ll_merge_requests_fn(q, req, next))
> + return NULL;
> + } else {
> return NULL;
> + }
>
> /*
> * If failfast settings disagree or any of the two is already
> @@ -888,8 +903,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
>
> enum elv_merge blk_try_merge(struct request *rq, struct bio *bio)
> {
> - if (req_op(rq) == REQ_OP_DISCARD &&
> - queue_max_discard_segments(rq->q) > 1)
> + if (blk_discard_mergable(rq))
> return ELEVATOR_DISCARD_MERGE;
> else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector)
> return ELEVATOR_BACK_MERGE;
>
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH V3] block: fix the DISCARD request merge
2018-10-26 8:05 ` jianchao.wang
@ 2018-10-26 8:07 ` Christoph Hellwig
2018-10-26 8:22 ` jianchao.wang
0 siblings, 1 reply; 5+ messages in thread
From: Christoph Hellwig @ 2018-10-26 8:07 UTC (permalink / raw)
To: jianchao.wang
Cc: axboe, martin.petersen, Ming Lei, hch, linux-block, linux-kernel
On Fri, Oct 26, 2018 at 04:05:00PM +0800, jianchao.wang wrote:
> Would anyone please take a look at this ?
I did take a look and reply to it..
>
> Thanks in advance.
> Jianchao
>
> On 10/24/18 11:07 AM, Jianchao Wang wrote:
> > There are two cases when handle DISCARD merge.
> > If max_discard_segments == 1, the bios/requests need to be contiguous
> > to merge. If max_discard_segments > 1, it takes every bio as a range
> > and different range needn't to be contiguous.
> >
> > But now, attempt_merge screws this up. It always consider contiguity
> > for DISCARD for the case max_discard_segments > 1 and cannot merge
> > contiguous DISCARD for the case max_discard_segments == 1, because
> > rq_attempt_discard_merge always returns false in this case.
> > This patch fixes both of the two cases above.
> >
> > Signed-off-by: Jianchao Wang <jianchao.w.wang@oracle.com>
> > ---
> >
> > V3:
> > - Introduce blk_discard_mergable into attempt_merge and
> > blk_try_merge.
> > - Some comment changes.
> >
> > V2:
> > - Add max_discard_segments > 1 checking in attempt_merge.
> > - Change patch title and comment.
> > - Add more comment in attempt_merge
> >
> > block/blk-merge.c | 34 ++++++++++++++++++++++++----------
> > 1 file changed, 24 insertions(+), 10 deletions(-)
> >
> > diff --git a/block/blk-merge.c b/block/blk-merge.c
> > index 42a4674..b258de0 100644
> > --- a/block/blk-merge.c
> > +++ b/block/blk-merge.c
> > @@ -714,6 +714,22 @@ static void blk_account_io_merge(struct request *req)
> > part_stat_unlock();
> > }
> > }
> > +/*
> > + * Two cases of handling DISCARD merge:
> > + * If max_discard_segments > 1, the driver takes every bio
> > + * as a range and send them to controller together. The ranges
> > + * needn't to be contiguous.
> > + * Otherwise, the bios/requests will be handled as same as
> > + * others which should be contiguous.
> > + */
> > +static inline bool blk_discard_mergable(struct request *req)
> > +{
> > + if (req_op(req) == REQ_OP_DISCARD &&
> > + queue_max_discard_segments(req->q) > 1)
> > + return true;
> > + else
> > + return false;
> > +}
> >
> > /*
> > * For non-mq, this has to be called with the request spinlock acquired.
> > @@ -731,12 +747,6 @@ static struct request *attempt_merge(struct request_queue *q,
> > if (req_op(req) != req_op(next))
> > return NULL;
> >
> > - /*
> > - * not contiguous
> > - */
> > - if (blk_rq_pos(req) + blk_rq_sectors(req) != blk_rq_pos(next))
> > - return NULL;
> > -
> > if (rq_data_dir(req) != rq_data_dir(next)
> > || req->rq_disk != next->rq_disk
> > || req_no_special_merge(next))
> > @@ -760,11 +770,16 @@ static struct request *attempt_merge(struct request_queue *q,
> > * counts here. Handle DISCARDs separately, as they
> > * have separate settings.
> > */
> > - if (req_op(req) == REQ_OP_DISCARD) {
> > +
> > + if (blk_discard_mergable(req)) {
> > if (!req_attempt_discard_merge(q, req, next))
> > return NULL;
> > - } else if (!ll_merge_requests_fn(q, req, next))
> > + } else if (blk_rq_pos(req) + blk_rq_sectors(req) == blk_rq_pos(next)) {
> > + if (!ll_merge_requests_fn(q, req, next))
> > + return NULL;
> > + } else {
> > return NULL;
> > + }
> >
> > /*
> > * If failfast settings disagree or any of the two is already
> > @@ -888,8 +903,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
> >
> > enum elv_merge blk_try_merge(struct request *rq, struct bio *bio)
> > {
> > - if (req_op(rq) == REQ_OP_DISCARD &&
> > - queue_max_discard_segments(rq->q) > 1)
> > + if (blk_discard_mergable(rq))
> > return ELEVATOR_DISCARD_MERGE;
> > else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector)
> > return ELEVATOR_BACK_MERGE;
> >
---end quoted text---
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH V3] block: fix the DISCARD request merge
2018-10-26 8:07 ` Christoph Hellwig
@ 2018-10-26 8:22 ` jianchao.wang
0 siblings, 0 replies; 5+ messages in thread
From: jianchao.wang @ 2018-10-26 8:22 UTC (permalink / raw)
To: Christoph Hellwig
Cc: axboe, martin.petersen, Ming Lei, linux-block, linux-kernel
On 10/26/18 4:07 PM, Christoph Hellwig wrote:
> On Fri, Oct 26, 2018 at 04:05:00PM +0800, jianchao.wang wrote:
>> Would anyone please take a look at this ?
>
> I did take a look and reply to it..
Oh sorry, I missed it in my email client.
Got it from the https://lkml.org/lkml/2018/10/24/491
And we could also have a blk_merge_req_ok there. :)
Thanks
Jianchao
>
>>
>> Thanks in advance.
>> Jianchao
>>
>> On 10/24/18 11:07 AM, Jianchao Wang wrote:
>>> There are two cases when handle DISCARD merge.
>>> If max_discard_segments == 1, the bios/requests need to be contiguous
>>> to merge. If max_discard_segments > 1, it takes every bio as a range
>>> and different range needn't to be contiguous.
>>>
>>> But now, attempt_merge screws this up. It always consider contiguity
>>> for DISCARD for the case max_discard_segments > 1 and cannot merge
>>> contiguous DISCARD for the case max_discard_segments == 1, because
>>> rq_attempt_discard_merge always returns false in this case.
>>> This patch fixes both of the two cases above.
>>>
>>> Signed-off-by: Jianchao Wang <jianchao.w.wang@oracle.com>
>>> ---
>>>
>>> V3:
>>> - Introduce blk_discard_mergable into attempt_merge and
>>> blk_try_merge.
>>> - Some comment changes.
>>>
>>> V2:
>>> - Add max_discard_segments > 1 checking in attempt_merge.
>>> - Change patch title and comment.
>>> - Add more comment in attempt_merge
>>>
>>> block/blk-merge.c | 34 ++++++++++++++++++++++++----------
>>> 1 file changed, 24 insertions(+), 10 deletions(-)
>>>
>>> diff --git a/block/blk-merge.c b/block/blk-merge.c
>>> index 42a4674..b258de0 100644
>>> --- a/block/blk-merge.c
>>> +++ b/block/blk-merge.c
>>> @@ -714,6 +714,22 @@ static void blk_account_io_merge(struct request *req)
>>> part_stat_unlock();
>>> }
>>> }
>>> +/*
>>> + * Two cases of handling DISCARD merge:
>>> + * If max_discard_segments > 1, the driver takes every bio
>>> + * as a range and send them to controller together. The ranges
>>> + * needn't to be contiguous.
>>> + * Otherwise, the bios/requests will be handled as same as
>>> + * others which should be contiguous.
>>> + */
>>> +static inline bool blk_discard_mergable(struct request *req)
>>> +{
>>> + if (req_op(req) == REQ_OP_DISCARD &&
>>> + queue_max_discard_segments(req->q) > 1)
>>> + return true;
>>> + else
>>> + return false;
>>> +}
>>>
>>> /*
>>> * For non-mq, this has to be called with the request spinlock acquired.
>>> @@ -731,12 +747,6 @@ static struct request *attempt_merge(struct request_queue *q,
>>> if (req_op(req) != req_op(next))
>>> return NULL;
>>>
>>> - /*
>>> - * not contiguous
>>> - */
>>> - if (blk_rq_pos(req) + blk_rq_sectors(req) != blk_rq_pos(next))
>>> - return NULL;
>>> -
>>> if (rq_data_dir(req) != rq_data_dir(next)
>>> || req->rq_disk != next->rq_disk
>>> || req_no_special_merge(next))
>>> @@ -760,11 +770,16 @@ static struct request *attempt_merge(struct request_queue *q,
>>> * counts here. Handle DISCARDs separately, as they
>>> * have separate settings.
>>> */
>>> - if (req_op(req) == REQ_OP_DISCARD) {
>>> +
>>> + if (blk_discard_mergable(req)) {
>>> if (!req_attempt_discard_merge(q, req, next))
>>> return NULL;
>>> - } else if (!ll_merge_requests_fn(q, req, next))
>>> + } else if (blk_rq_pos(req) + blk_rq_sectors(req) == blk_rq_pos(next)) {
>>> + if (!ll_merge_requests_fn(q, req, next))
>>> + return NULL;
>>> + } else {
>>> return NULL;
>>> + }
>>>
>>> /*
>>> * If failfast settings disagree or any of the two is already
>>> @@ -888,8 +903,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
>>>
>>> enum elv_merge blk_try_merge(struct request *rq, struct bio *bio)
>>> {
>>> - if (req_op(rq) == REQ_OP_DISCARD &&
>>> - queue_max_discard_segments(rq->q) > 1)
>>> + if (blk_discard_mergable(rq))
>>> return ELEVATOR_DISCARD_MERGE;
>>> else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector)
>>> return ELEVATOR_BACK_MERGE;
>>>
> ---end quoted text---
>
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2018-10-26 8:23 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-10-24 3:07 [PATCH V3] block: fix the DISCARD request merge Jianchao Wang
2018-10-24 11:22 ` Christoph Hellwig
2018-10-26 8:05 ` jianchao.wang
2018-10-26 8:07 ` Christoph Hellwig
2018-10-26 8:22 ` jianchao.wang
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).