Re: [dm-devel] [RFC] block: fix blk_queue_split() resource exhaustion

On Wed, Jun 22, 2016 at 4:22 PM, Lars Ellenberg wrote: > For a long time, generic_make_request() converts recursion into > iteration by queuing recursive arguments on current->bio_list. > > This is convenient for stacking drivers, > the top-most driver would take the

Re: [dm-devel] 4.4-final: 28 bioset threads on small notebook

On Tue, Feb 23, 2016 at 10:54 PM, Mike Snitzer <snit...@redhat.com> wrote: > On Mon, Feb 22 2016 at 9:55pm -0500, > Ming Lei <ming@canonical.com> wrote: > >> On Tue, Feb 23, 2016 at 6:58 AM, Kent Overstreet >> <kent.overstr...@gmail.com> wrote: >&g

[dm-devel] [PATCH 00/27] block: cleanup direct access on .bi_vcnt & .bi_io_vec

ch two subsystems will be done in the future. Also bio_add_page() is used in floppy, dm-crypt and fs/logfs to avoiding direct access to .bi_vcnt & .bi_io_vec. Thanks, Ming Ming Lei (27): block: bio: introduce 4 helpers for cleanup block: drbd: use bio_get_base_vec() to retrieve the 1st bvec b

Re: [dm-devel] [PATCH 10/12] Limit bio_endio recursion

On Thu, 7 Apr 2016 11:54:49 +0800 Ming Lei <tom.leim...@gmail.com> wrote: > On Mon, Apr 4, 2016 at 1:06 PM, Shaun Tancheff <sh...@tancheff.com> wrote: > > Recursive endio calls can exceed 16k stack. Tested with > > 32k stack and observed: > > > >

Re: [dm-devel] [PATCH 10/12] Limit bio_endio recursion

return chain_bio; > +} > + > /** > * bio_endio - end I/O on a bio > * @bio: bio > @@ -1762,9 +1815,7 @@ void bio_endio(struct bio *bio) > bio_put(bio); > bio = parent; > } else { > - if (bio->bi_

Re: [dm-devel] [RFC] block: fix blk_queue_split() resource exhaustion

On Fri, Jun 24, 2016 at 10:27 PM, Lars Ellenberg <lars.ellenb...@linbit.com> wrote: > On Fri, Jun 24, 2016 at 07:36:57PM +0800, Ming Lei wrote: >> > >> > This is not a theoretical problem. >> > At least int DRBD, and an unfortunately high IO concurrency wrt. the

Re: [dm-devel] [RFC] block: fix blk_queue_split() resource exhaustion

On Mon, Jul 4, 2016 at 4:20 PM, Lars Ellenberg <lars.ellenb...@linbit.com> wrote: > On Sat, Jul 02, 2016 at 06:28:29PM +0800, Ming Lei wrote: >> The idea looks good, but not sure it can cover all cases of >> dm over brbd or brbd over dm and maintaining two lists >&

Re: [dm-devel] [RFC] block: fix blk_queue_split() resource exhaustion

On Wed, Jun 22, 2016 at 4:22 PM, Lars Ellenberg wrote: > For a long time, generic_make_request() converts recursion into > iteration by queuing recursive arguments on current->bio_list. > > This is convenient for stacking drivers, > the top-most driver would take the

Re: [dm-devel] [RFC] block: fix blk_queue_split() resource exhaustion

On Thu, Jul 7, 2016 at 4:03 PM, Lars Ellenberg <lars.ellenb...@linbit.com> wrote: > On Wed, Jul 06, 2016 at 11:57:51PM +0800, Ming Lei wrote: >> > my suggestion >> > >> > generic_make_request(bio_orig) >> > NULL

Re: [dm-devel] [RFC] block: fix blk_queue_split() resource exhaustion

On Fri, Jul 8, 2016 at 6:07 AM, NeilBrown wrote: > On Thu, Jul 07 2016, Lars Ellenberg wrote: > >> On Thu, Jul 07, 2016 at 03:35:48PM +1000, NeilBrown wrote: >>> On Wed, Jun 22 2016, Lars Ellenberg wrote: >>> >>> > For a long time, generic_make_request() converts recursion into

Re: [dm-devel] [RFC] block: fix blk_queue_split() resource exhaustion

On Wed, Jul 6, 2016 at 8:38 PM, Lars Ellenberg <lars.ellenb...@linbit.com> wrote: > On Mon, Jul 04, 2016 at 06:47:29PM +0800, Ming Lei wrote: >> >> One clean solution may be to convert the loop of generic_make_request() >> >> into the following way: >> >&

Re: [dm-devel] v4.9, 4.4-final: 28 bioset threads on small notebook, 36 threads on cellphone

On Tue, Feb 7, 2017 at 10:49 AM, Kent Overstreet wrote: > On Mon, Feb 06, 2017 at 04:47:24PM -0900, Kent Overstreet wrote: >> On Mon, Feb 06, 2017 at 01:53:09PM +0100, Pavel Machek wrote: >> > Still there on v4.9, 36 threads on nokia n900 cellphone. >> > >> > So.. what

Re: [dm-devel] dm-crypt: Fix error with too large bios

On Tue, Aug 30, 2016 at 5:57 AM, Mikulas Patocka <mpato...@redhat.com> wrote: > > > On Mon, 29 Aug 2016, Ming Lei wrote: > >> On Sat, Aug 27, 2016 at 11:09 PM, Mikulas Patocka <mpato...@redhat.com> >> wrote: >> > >> > >> > On Fri,

Re: [dm-devel] dm-crypt: Fix error with too large bios

ss code than reworking bcache to split bios internally. >> > > >> > >BTW. In the device mapper, we have a layer dm-io, that was created to work >> > >around bio size limitations - it accepts unlimited I/O request and splits >> > >it to several bios. When bio si

[dm-devel] [PATCH 07/12] dm: use bvec iterator helpers to implement .get_page and .next_page

Firstly we have mature bvec/bio iterator helper for iterate each page in one bio, not necessary to reinvent a wheel to do that. Secondly the coming multipage bvecs requires this patch. Also add comments about the direct access to bvec table. Signed-off-by: Ming Lei <tom.leim...@gmail.

[dm-devel] [PATCH 01/12] block: bio: pass bvec table to bio_init()

n help to prepare for the following multipage bvec support. Signed-off-by: Ming Lei <tom.leim...@gmail.com> --- block/bio.c | 8 ++-- drivers/block/floppy.c| 3 +-- drivers/md/bcache/io.c| 4 +--- drivers/md/bcache/journal.c | 4 +--- drivers/md/bcach

[dm-devel] [PATCH 06/12] dm: crypt: use bio_add_page()

We have the standard interface to add page to bio, so don't do that in hacking way. Reviewed-by: Christoph Hellwig <h...@lst.de> Signed-off-by: Ming Lei <tom.leim...@gmail.com> --- drivers/md/dm-crypt.c | 8 +--- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/d

[dm-devel] [PATCH 08/12] dm: dm.c: replace 'bio->bi_vcnt == 1' with !bio_multiple_segments

Avoid to access .bi_vcnt directly, because the bio can be splitted from block layer, and .bi_vcnt should never have been used here. Signed-off-by: Ming Lei <tom.leim...@gmail.com> --- drivers/md/dm-rq.c | 7 ++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/md/d

[dm-devel] [PATCH 00/12] block: cleanup direct access to bvec table

to access bio->bi_vcnt. The most special one is to use bvec iterator helpers to implement .get_page/.next_page for dm-io.c One big motivation is to prepare for supporting multipage bvec, but this patchset is one good cleanup too even not for that purpose. Thanks, Ming Ming Lei (12): block:

Re: [dm-devel] [PATCH 08/12] dm: dm.c: replace 'bio->bi_vcnt == 1' with !bio_multiple_segments

On Fri, Nov 11, 2016 at 8:05 PM, Ming Lei <tom.leim...@gmail.com> wrote: > Avoid to access .bi_vcnt directly, because the bio can be > splitted from block layer, and .bi_vcnt should never have > been used here. > > Signed-off-by: Ming Lei <tom.leim...@gmail.com> >

Re: [dm-devel] [PATCH 07/12] dm: use bvec iterator helpers to implement .get_page and .next_page

On Mon, Nov 21, 2016 at 10:49 PM, Mike Snitzer <snit...@redhat.com> wrote: > On Fri, Nov 11 2016 at 7:05am -0500, > Ming Lei <tom.leim...@gmail.com> wrote: > >> Firstly we have mature bvec/bio iterator helper for iterate each >> page in one bio, not ne

Re: [dm-devel] [PATCH 00/60] block: support multipage bvec

help reducing the OK, that is just the 1st part of the patchset. > actual series to a sane size, and it should also help to cut > down the Cc list. > Thanks, Ming Lei -- dm-devel mailing list dm-devel@redhat.com https://www.redhat.com/mailman/listinfo/dm-devel

Re: [dm-devel] [PATCH 09/60] dm: dm.c: replace 'bio->bi_vcnt == 1' with !bio_multiple_segments

On Mon, Oct 31, 2016 at 11:29 PM, Christoph Hellwig <h...@infradead.org> wrote: > On Sat, Oct 29, 2016 at 04:08:08PM +0800, Ming Lei wrote: >> Avoid to access .bi_vcnt directly, because it may be not what >> the driver expected any more after supporting multipage bvec. >

[dm-devel] [PATCH 08/60] dm: use bvec iterator helpers to implement .get_page and .next_page

Firstly we have mature bvec/bio iterator helper for iterate each page in one bio, not necessary to reinvent a wheel to do that. Secondly the coming multipage bvecs requires this patch. Also add comments about the direct access to bvec table. Signed-off-by: Ming Lei <tom.leim...@gmail.

[dm-devel] [PATCH 58/60] dm-crypt: convert to bio_for_each_segment_all_rd()

Signed-off-by: Ming Lei <tom.leim...@gmail.com> --- drivers/md/dm-crypt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 4999c7497f95..ed0f54e51638 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -

[dm-devel] [PATCH 00/60] block: support multipage bvec

33=2 Ming Lei (60): block: bio: introduce bio_init_with_vec_table() block drivers: convert to bio_init_with_vec_table() block: drbd: remove impossible failure handling block: floppy: use bio_add_page() target: avoid to access .bi_vcnt directly bcache: debug: avoid to access .bi_io

[dm-devel] [PATCH 02/60] block drivers: convert to bio_init_with_vec_table()

Signed-off-by: Ming Lei <tom.leim...@gmail.com> --- drivers/block/floppy.c| 3 +-- drivers/md/bcache/io.c| 4 +--- drivers/md/bcache/journal.c | 4 +--- drivers/md/bcache/movinggc.c | 7 +++ drivers/md/bcache/super.c | 13 - drivers/md/bcache/write

[dm-devel] [PATCH 29/60] dm: limit the max bio size as BIO_SP_MAX_SECTORS << SECTOR_SHIFT

For BIO based DM, some targets aren't ready for dealing with bigger incoming bio than 1Mbyte, such as crypt and log write targets. Signed-off-by: Ming Lei <tom.leim...@gmail.com> --- drivers/md/dm.c | 11 ++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/md/

[dm-devel] [PATCH v1 12/54] dm: limit the max bio size as BIO_MAX_PAGES * PAGE_SIZE

For BIO based DM, some targets aren't ready for dealing with bigger incoming bio than 1Mbyte, such as crypt target. Signed-off-by: Ming Lei <tom.leim...@gmail.com> --- drivers/md/dm.c | 11 ++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/md/dm.c b/driv

[dm-devel] [PATCH v1 00/54] block: support multipage bvec

- address comments in V0 [1], http://marc.info/?l=linux-kernel=141680246629547=2 [2], https://patchwork.kernel.org/patch/9451523/ [3], http://marc.info/?t=14773544711=1=2 [4], http://marc.info/?l=linux-mm=147745525801433=2 Ming Lei (54): block: drbd: comment on direct access bvec table

[dm-devel] [PATCH v1 36/54] dm-crypt: don't clear bvec->bv_page in crypt_free_buffer_pages()

The bio is always freed after running crypt_free_buffer_pages(), so it isn't necessary to clear the bv->bv_page. Signed-off-by: Ming Lei <tom.leim...@gmail.com> --- drivers/md/dm-crypt.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-cryp

[dm-devel] [PATCH v1 37/54] dm-crypt: convert to bio_for_each_segment_all_sp()

Signed-off-by: Ming Lei <tom.leim...@gmail.com> --- drivers/md/dm-crypt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 593cdf88bf5f..c6932fb85418 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -

Re: [dm-devel] [PATCH v1 12/54] dm: limit the max bio size as BIO_MAX_PAGES * PAGE_SIZE

On Wed, Jan 4, 2017 at 12:43 AM, Mike Snitzer <snit...@redhat.com> wrote: > On Tue, Dec 27 2016 at 10:56am -0500, > Ming Lei <tom.leim...@gmail.com> wrote: > >> For BIO based DM, some targets aren't ready for dealing with >> bigger incoming bio than 1Mbyte, such

Re: [dm-devel] [PATCH v2] block: trace completion of all bios.

On Thu, Mar 23, 2017 at 05:29:02PM +1100, NeilBrown wrote: > > Currently only dm and md/raid5 bios trigger trace_block_bio_complete(). > Now that we have bio_chain(), it is not possible, in general, for a > driver to know when the bio is really complete. Only bio_endio() > knows that. > > So

Re: [dm-devel] [PATCH v4 6/6] dm rq: Avoid that request processing stalls sporadically

On Wed, Apr 12, 2017 at 06:38:07PM +, Bart Van Assche wrote: > On Wed, 2017-04-12 at 11:42 +0800, Ming Lei wrote: > > On Tue, Apr 11, 2017 at 06:18:36PM +, Bart Van Assche wrote: > > > On Tue, 2017-04-11 at 14:03 -0400, Mike Snitzer wrote: > > > > Rather than

Re: [dm-devel] [PATCH v4 6/6] dm rq: Avoid that request processing stalls sporadically

On Thu, Apr 13, 2017 at 09:59:57AM -0700, Bart Van Assche wrote: > On 04/12/17 19:20, Ming Lei wrote: > > On Wed, Apr 12, 2017 at 06:38:07PM +, Bart Van Assche wrote: > >> If the blk-mq core would always rerun a hardware queue if a block driver > >> returns BLK_MQ_RQ

Re: [dm-devel] [PATCH v4 6/6] dm rq: Avoid that request processing stalls sporadically

On Fri, Apr 14, 2017 at 05:12:50PM +, Bart Van Assche wrote: > On Fri, 2017-04-14 at 09:13 +0800, Ming Lei wrote: > > On Thu, Apr 13, 2017 at 09:59:57AM -0700, Bart Van Assche wrote: > > > On 04/12/17 19:20, Ming Lei wrote: > > > > On Wed, Apr 12, 2017 at 06:

Re: [dm-devel] [PATCH v4 6/6] dm rq: Avoid that request processing stalls sporadically

On Tue, Apr 11, 2017 at 06:18:36PM +, Bart Van Assche wrote: > On Tue, 2017-04-11 at 14:03 -0400, Mike Snitzer wrote: > > Rather than working so hard to use DM code against me, your argument > > should be: "blk-mq drivers X, Y and Z rerun the hw queue; this is a well > > established pattern" >

Re: [dm-devel] [PATCH 10/25] loop: zero-fill bio on the submitting cpu

st, > + .complete = lo_complete_rq, > }; > > static int loop_add(struct loop_device **l, int i) > diff --git a/drivers/block/loop.h b/drivers/block/loop.h > index fb2237c73e61..fecd3f97ef8c 100644 > --- a/drivers/block/loop.h > +++ b/drivers/block/loop.h > @@

[dm-devel] [PATCH 3/6] block: don't call blk_mq_delay_run_hw_queue() in case of BLK_STS_RESOURCE

t;Martin K. Petersen" Cc: linux-s...@vger.kernel.org Signed-off-by: Ming Lei <ming@redhat.com> --- drivers/md/dm-rq.c | 1 - drivers/nvme/host/fc.c | 3 --- drivers/scsi/scsi_lib.c | 4 3 files changed, 8 deletions(-) diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-

Re: [dm-devel] [PATCH 1/1] block: Convert hd_struct in_flight from atomic to percpu

On Fri, Jun 30, 2017 at 2:42 AM, Jens Axboe <ax...@kernel.dk> wrote: > On 06/29/2017 10:00 AM, Jens Axboe wrote: >> On 06/29/2017 09:58 AM, Jens Axboe wrote: >>> On 06/29/2017 02:40 AM, Ming Lei wrote: >>>> On Thu, Jun 29, 2017 at 5:49 AM, Jens Axboe <ax...@k

Re: [dm-devel] [PATCH 1/1] block: Convert hd_struct in_flight from atomic to percpu

On Thu, Jun 29, 2017 at 12:31:05PM -0500, Brian King wrote: > On 06/29/2017 11:25 AM, Ming Lei wrote: > > On Thu, Jun 29, 2017 at 11:58 PM, Jens Axboe <ax...@kernel.dk> wrote: > >> On 06/29/2017 02:40 AM, Ming Lei wrote: > >>> On Thu, Jun 29, 2017 at 5:49 AM

Re: [dm-devel] [PATCH 1/1] block: Convert hd_struct in_flight from atomic to percpu

On Thu, Jun 29, 2017 at 11:58 PM, Jens Axboe <ax...@kernel.dk> wrote: > On 06/29/2017 02:40 AM, Ming Lei wrote: >> On Thu, Jun 29, 2017 at 5:49 AM, Jens Axboe <ax...@kernel.dk> wrote: >>> On 06/28/2017 03:12 PM, Brian King wrote: >>>> This patch converts

Re: [dm-devel] [PATCH 1/1] block: Convert hd_struct in_flight from atomic to percpu

On Sat, Jul 1, 2017 at 10:18 AM, Brian King <brk...@linux.vnet.ibm.com> wrote: > On 06/30/2017 06:26 PM, Jens Axboe wrote: >> On 06/30/2017 05:23 PM, Ming Lei wrote: >>> Hi Bian, >>> >>> On Sat, Jul 1, 2017 at 2:33 AM, Brian King <brk...@linux.vnet.ibm

Re: [dm-devel] [PATCH 1/1] block: Convert hd_struct in_flight from atomic to percpu

l_block devices' is? It means you create 80 null_blk devices? Or you create one null_blk and make its hw queue number as 80 via module parameter of ''submit_queues"? I guess we should focus on multi-queue case since it is the normal way of NVMe. > per null_blk. This is what I saw on this ma

Re: [dm-devel] [PATCH 1/1] block: Convert hd_struct in_flight from atomic to percpu

ounters is the right way to fix it, at least not for the inflight > counter. Yeah, it won't be a issue for non-mq path, and for blk-mq path, maybe we can use some blk-mq knowledge(tagset?) to figure out the 'in_flight' counter. I thought about it before, but never got a perfect solution, and loo

Re: [dm-devel] [PATCH V2 00/20] blk-mq-sched: improve SCSI-MQ performance

On Mon, Aug 07, 2017 at 01:29:41PM -0400, Laurence Oberman wrote: > > > On 08/07/2017 11:27 AM, Bart Van Assche wrote: > > On Mon, 2017-08-07 at 08:48 -0400, Laurence Oberman wrote: > > > I tested this series using Ming's tests as well as my own set of tests > > > typically run against changes

[dm-devel] [v4.13-rc BUG] system lockup when running big buffered write(4M) to IB SRP via mpath

Hi Guys, Laurence and I see a system lockup issue when running concurrent big buffered write(4M bytes) to IB SRP on v4.13-rc3. 1 how to reproduce 1) setup IB_SRR & multi path #./start_opensm.sh #./start_srp.sh # cat start_opensm.sh #!/bin/bash rmmod

Re: [dm-devel] [PATCH 01/10] pktcdvd: remove the call to blk_queue_bounce

On Mon, Jun 19, 2017 at 11:18 PM, Christoph Hellwig <h...@lst.de> wrote: > On Mon, Jun 19, 2017 at 11:13:46PM +0800, Ming Lei wrote: >> On Mon, Jun 19, 2017 at 11:00 PM, Christoph Hellwig <h...@lst.de> wrote: >> > On Mon, Jun 19, 2017 at 10

Re: [dm-devel] [PATCH 01/10] pktcdvd: remove the call to blk_queue_bounce

pd = q->queuedata; > -- > 2.11.0 > blk_queue_make_request() sets bounce for any highmem page for long time, and in theory this patch might cause regression on 32bit arch, when the controller can't handle higmem page really(especially in case of PAE), so we may need to be careful ab

Re: [dm-devel] [PATCH 01/10] pktcdvd: remove the call to blk_queue_bounce

On Mon, Jun 19, 2017 at 11:00 PM, Christoph Hellwig <h...@lst.de> wrote: > On Mon, Jun 19, 2017 at 10:34:36PM +0800, Ming Lei wrote: >> blk_queue_make_request() sets bounce for any highmem page for long time, >> and in theory this patch might cause regression on 32bit arch, w

[dm-devel] [PATCH 0/6] blk-mq: fix & improve queue quiescing

path can break the quiescing. This patch improves this interface via removing stopping queue, then it can be easier to use. Thanks, Ming Ming Lei (6): blk-mq: introduce blk_mq_unquiesce_queue blk-mq: use the introduced blk_mq_unquiesce_queue() blk-mq: fix blk_mq_quiesce_queue blk-mq

[dm-devel] [PATCH 6/6] blk-mq: clarify dispatching won't be blocked by stopping queue

BLK_MQ_S_STOPPED may be not observed in other concurrent I/O paths, we can't guarantee that dispatching won't happen after queue is stopped. So clarify the fact and avoid potential misuse. Signed-off-by: Ming Lei <ming@redhat.com> --- block/blk-mq.c | 10 ++ 1 file chang

[dm-devel] [PATCH 2/6] blk-mq: use the introduced blk_mq_unquiesce_queue()

blk_mq_unquiesce_queue() is used for unquiescing the queue. Signed-off-by: Ming Lei <ming@redhat.com> --- drivers/md/dm-rq.c | 2 +- drivers/nvme/host/core.c | 2 +- drivers/scsi/scsi_lib.c | 5 - 3 files changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/md/dm-

[dm-devel] [PATCH 5/6] blk-mq: don't stop queue for quiescing

cing. Signed-off-by: Ming Lei <ming@redhat.com> --- block/blk-mq.c | 9 ++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index e1fc9ab50c87..900eb91e0ece 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -168,8 +168

[dm-devel] [PATCH 4/6] blk-mq: update comments on blk_mq_quiesce_queue()

dispatched request is freeed - busy dispatched request is requeued, and the STARTED flag is cleared Signed-off-by: Ming Lei <ming@redhat.com> --- block/blk-mq.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index 864709

[dm-devel] [PATCH 6/6] blk-mq: clarify dispatching may not be drained/blocked by stopping queue

BLK_MQ_S_STOPPED may be not observed in other concurrent I/O paths, we can't guarantee that dispatching won't happen after queue is stopped. So clarify the fact and avoid potential misuse. Signed-off-by: Ming Lei <ming@redhat.com> --- block/blk-mq.c | 10 ++ 1 file chang

[dm-devel] [PATCH 3/6] blk-mq: fix blk_mq_quiesce_queue

is introduced and evaluated inside RCU read-side critical sections for fixing the above issues. This patch fixes request use-after-free during canceling requets of NVMe in nvme_dev_disable(). Signed-off-by: Ming Lei <ming@redhat.com> --- block/blk-mq.c

[dm-devel] [PATCH 1/6] blk-mq: introduce blk_mq_unquiesce_queue

Now we use blk_mq_start_stopped_hw_queues() implictely as pair of blk_mq_quiesce_queue(), now we introduce blk_mq_unquiesce_queue() explictely. Also this function is introduced for fixing current quiescing mechanism, which will be done in the following patches. Signed-off-by: Ming Lei <m

Re: [dm-devel] [PATCH 2/6] blk-mq: use the introduced blk_mq_unquiesce_queue()

e system] > > url: > https://github.com/0day-ci/linux/commits/Ming-Lei/blk-mq-introduce-blk_mq_unquiesce_queue/20170526-140138 > base: https://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git > for-next > config: x86_64-randconfig-x019-201721 (attached as .config) >

[dm-devel] [PATCH v2 3/8] blk-mq: use the introduced blk_mq_unquiesce_queue()

blk_mq_unquiesce_queue() is used for unquiescing the queue explicitly, so replace blk_mq_start_stopped_hw_queues() with it. Cc: linux-n...@lists.infradead.org Cc: linux-s...@vger.kernel.org Cc: dm-devel@redhat.com Signed-off-by: Ming Lei <ming@redhat.com> --- drivers/md/dm-rq.c

Re: [dm-devel] [PATCH v2 3/8] blk-mq: use the introduced blk_mq_unquiesce_queue()

On Tue, May 30, 2017 at 12:04:02PM -0700, Eduardo Valentin wrote: > On Sat, May 27, 2017 at 10:21:21PM +0800, Ming Lei wrote: > > blk_mq_unquiesce_queue() is used for unquiescing the > > queue explicitly, so replace blk_mq_start_stopped_hw_queues() > > with it.

Re: [dm-devel] [PATCH v2 3/8] blk-mq: use the introduced blk_mq_unquiesce_queue()

On Tue, May 30, 2017 at 03:12:41PM +, Bart Van Assche wrote: > On Sat, 2017-05-27 at 22:21 +0800, Ming Lei wrote: > > --- a/drivers/scsi/scsi_lib.c > > +++ b/drivers/scsi/scsi_lib.c > > @@ -3030,7 +3030,10 @@ scsi_internal_device_unblock(struct scsi_device > > *s

Re: [dm-devel] [PATCH v3 3/9] blk-mq: use the introduced blk_mq_unquiesce_queue()

On Thu, Jun 01, 2017 at 11:09:00PM +, Bart Van Assche wrote: > On Thu, 2017-06-01 at 08:54 +0800, Ming Lei wrote: > > On Wed, May 31, 2017 at 03:21:41PM +, Bart Van Assche wrote: > > > On Wed, 2017-05-31 at 20:37 +0800, Ming Lei wrote: > > > > diff --git a/dri

Re: [dm-devel] [PATCH v3 3/9] blk-mq: use the introduced blk_mq_unquiesce_queue()

On Wed, May 31, 2017 at 03:21:41PM +, Bart Van Assche wrote: > On Wed, 2017-05-31 at 20:37 +0800, Ming Lei wrote: > > diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c > > index 99e16ac479e3..ffcf05765e2b 100644 > > --- a/drivers/scsi/scsi_lib.c > > ++

[dm-devel] [PATCH v3 3/9] blk-mq: use the introduced blk_mq_unquiesce_queue()

blk_mq_unquiesce_queue() is used for unquiescing the queue explicitly, so replace blk_mq_start_stopped_hw_queues() with it. Cc: linux-n...@lists.infradead.org Cc: linux-s...@vger.kernel.org Cc: dm-devel@redhat.com Signed-off-by: Ming Lei <ming@redhat.com> --- drivers/md/dm-rq.c

[dm-devel] [PATCH v4 05/11] blk-mq: use the introduced blk_mq_unquiesce_queue()

Cc: dm-devel@redhat.com Signed-off-by: Ming Lei <ming@redhat.com> --- drivers/md/dm-rq.c | 2 +- drivers/nvme/host/core.c | 2 +- drivers/scsi/scsi_lib.c | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index b639fa

Re: [dm-devel] [PATCH v2] block: directly insert blk-mq request from blk_insert_cloned_request()

t; } > > +/* > + * Should only be used carefully, when the caller knows we want to > + * bypass a potential IO scheduler on the target device. > + */ > +void blk_mq_request_bypass_insert(struct request *rq) > +{ > + struct blk_mq_ctx *ctx = rq->mq_ctx; > + struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(rq->q, ctx->cpu); > + > + spin_lock(>lock); > + list_add_tail(>queuelist, >dispatch); > + spin_unlock(>lock); > + > + blk_mq_run_hw_queue(hctx, false); > +} > + Hello Jens and Mike, This patch sends flush request to ->dispatch directly too, which changes the previous behaviour, is that OK for dm-rq? -- Ming Lei -- dm-devel mailing list dm-devel@redhat.com https://www.redhat.com/mailman/listinfo/dm-devel

Re: [dm-devel] [PATCH v2] block: directly insert blk-mq request from blk_insert_cloned_request()

On Fri, Sep 15, 2017 at 12:30 AM, Jens Axboe <ax...@kernel.dk> wrote: > On 09/14/2017 09:57 AM, Ming Lei wrote: >> On Tue, Sep 12, 2017 at 5:27 AM, Jens Axboe <ax...@kernel.dk> wrote: >>> On 09/11/2017 03:13 PM, Mike Snitzer wrote: >>>> On Mon, Sep 11

[dm-devel] [PATCH 4/5] block: export blk_update_nr_requests

eturns successfully. This way will make block layer's I/O schedule more effective on dm-rq device. Signed-off-by: Ming Lei <ming@redhat.com> --- block/blk-core.c | 4 +++- block/blk-sysfs.c | 5 + block/blk.h| 2 -- include/linux/blkdev.h | 1 + 4 files changed,

[dm-devel] [PATCH 5/5] dm-mpath: improve I/O schedule

in that coverletter was against the raw lpfc/ib(run after 'multipath -F'), instead of dm-mpath. 5) this patchset itself doesn't depend on the scsi_mq_perf patchset[1] [1] https://marc.info/?t=15043655572=1=2 Signed-off-by: Ming Lei <ming@redhat.com> --- drivers/md/dm-mpath.

[dm-devel] [PATCH 0/5] dm-mpath: improve I/O schedule

mq-deadline, sequential I/O performance is improved a lot, see test result in patch 5's commit log. Any comments are welcome! Thanks, Ming Ming Lei (5): block: don't call blk_mq_delay_run_hw_queue() in case of BLK_STS_RESOURCE dm-mpath: return DM_MAPIO_REQUEUE in case of rq allocat

[dm-devel] [PATCH 2/5] dm-mpath: return DM_MAPIO_REQUEUE in case of rq allocation failure

blk-mq will rerun queue via RESTART after one request is completion, so not necessary to wait random time for requeuing, it should trust blk-mq to do it. Signed-off-by: Ming Lei <ming@redhat.com> --- drivers/md/dm-mpath.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff

[dm-devel] [PATCH 1/5] block: don't call blk_mq_delay_run_hw_queue() in case of BLK_STS_RESOURCE

again. Cc: Mike Snitzer <snit...@redhat.com> Cc: dm-devel@redhat.com Cc: Sagi Grimberg <s...@grimberg.me> Cc: linux-n...@lists.infradead.org Cc: "James E.J. Bottomley" <j...@linux.vnet.ibm.com> Cc: "Martin K. Petersen" <martin.peter...@oracle.com> Cc: li

[dm-devel] [PATCH 0/5] dm-mpath: improve I/O schedule

mq-deadline, sequential I/O performance is improved a lot, see test result in patch 5's commit log. Any comments are welcome! Thanks, Ming Ming Lei (5): block: don't call blk_mq_delay_run_hw_queue() in case of BLK_STS_RESOURCE dm-mpath: return DM_MAPIO_REQUEUE in case of rq allocat

[dm-devel] [PATCH 3/5] dm-mpath: remove annoying message of 'blk_get_request() returned -11'

It is very normal to see allocation failure, so not necessary to dump it and annoy people. Signed-off-by: Ming Lei <ming@redhat.com> --- drivers/md/dm-mpath.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index f5a1088a6e79..f57ad8

Re: [dm-devel] [PATCH 1/5] block: don't call blk_mq_delay_run_hw_queue() in case of BLK_STS_RESOURCE

On Tue, Sep 19, 2017 at 04:49:15PM +, Bart Van Assche wrote: > On Wed, 2017-09-20 at 00:04 +0800, Ming Lei wrote: > > Run queue at end_io is definitely wrong, because blk-mq has SCHED_RESTART > > to do that already. > > Sorry but I disagree. If SCHED_RESTART is set that c

Re: [dm-devel] [PATCH 1/5] block: don't call blk_mq_delay_run_hw_queue() in case of BLK_STS_RESOURCE

Hi Mike, On Tue, Sep 19, 2017 at 07:50:06PM -0400, Mike Snitzer wrote: > On Tue, Sep 19 2017 at 7:25pm -0400, > Bart Van Assche <bart.vanass...@wdc.com> wrote: > > > On Wed, 2017-09-20 at 06:44 +0800, Ming Lei wrote: > > > For this issue, it isn't same between S

Re: [dm-devel] [PATCH 1/5] block: don't call blk_mq_delay_run_hw_queue() in case of BLK_STS_RESOURCE

On Tue, Sep 19, 2017 at 06:42:30PM +, Bart Van Assche wrote: > On Wed, 2017-09-20 at 00:55 +0800, Ming Lei wrote: > > On Wed, Sep 20, 2017 at 12:49 AM, Bart Van Assche > > <bart.vanass...@wdc.com> wrote: > > > On Wed, 2017-09-20 at 00:04 +0800, Ming Lei wrot

Re: [dm-devel] [PATCH 1/5] block: don't call blk_mq_delay_run_hw_queue() in case of BLK_STS_RESOURCE

On Mon, Sep 18, 2017 at 03:18:16PM +, Bart Van Assche wrote: > On Sun, 2017-09-17 at 20:40 +0800, Ming Lei wrote: > > "if no request has completed before the delay has expired" can't be a > > reason to rerun the queue, because the queue can still be busy. > &

Re: [dm-devel] [PATCH] dm-mpath: Improve handling of busy paths

On Thu, Sep 21, 2017 at 03:53:45PM +, Bart Van Assche wrote: > On Thu, 2017-09-21 at 09:41 +0800, Ming Lei wrote: > > On Wed, Sep 20, 2017 at 11:26:09PM +, Bart Van Assche wrote: > > > dm-mpath request submission latency if the underlying driver returns > > >

Re: [dm-devel] [PATCH] dm-mpath: Improve handling of busy paths

On Wed, Sep 20, 2017 at 11:26:09PM +, Bart Van Assche wrote: > On Thu, 2017-09-21 at 06:36 +0800, Ming Lei wrote: > > Actually with GFP_ATOMIC, dispatch in dm-rq can't move on and no request > > will be dequeued from IO scheduler queue if this allocation fails, that > > me

Re: [dm-devel] [PATCH 1/5] block: don't call blk_mq_delay_run_hw_queue() in case of BLK_STS_RESOURCE

On Fri, Sep 15, 2017 at 05:57:31PM +, Bart Van Assche wrote: > On Sat, 2017-09-16 at 00:44 +0800, Ming Lei wrote: > > If .queue_rq() returns BLK_STS_RESOURCE, blk-mq will rerun > > the queue in the three situations: > > > > 1) if BLK_MQ_S_SCHED_RESTART is set > &

Re: [dm-devel] [PATCH 2/5] dm-mpath: return DM_MAPIO_REQUEUE in case of rq allocation failure

On Fri, Sep 15, 2017 at 04:06:55PM -0400, Mike Snitzer wrote: > On Fri, Sep 15 2017 at 1:29pm -0400, > Bart Van Assche <bart.vanass...@wdc.com> wrote: > > > On Sat, 2017-09-16 at 00:44 +0800, Ming Lei wrote: > > > blk-mq will rerun queue via RESTART after one r

Re: [dm-devel] [PATCH 2/5] dm-mpath: return DM_MAPIO_REQUEUE in case of rq allocation failure

On Fri, Sep 15, 2017 at 05:29:53PM +, Bart Van Assche wrote: > On Sat, 2017-09-16 at 00:44 +0800, Ming Lei wrote: > > blk-mq will rerun queue via RESTART after one request is completion, > > so not necessary to wait random time for requeuing, it should trust &

[dm-devel] [PATCH] dm-mpath: return DM_MAPIO_REQUEUE in case of rq allocation failure

. Signed-off-by: Ming Lei <ming@redhat.com> --- drivers/md/dm-mpath.c | 14 +- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 11f273d2f018..0902f7762306 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-m

Re: [dm-devel] [PATCH] dm-mpath: return DM_MAPIO_REQUEUE in case of rq allocation failure

On Fri, Sep 22, 2017 at 03:06:16PM +, Bart Van Assche wrote: > On Fri, 2017-09-22 at 09:35 +0800, Ming Lei wrote: > > + /* > > +* blk-mq's SCHED_RESTART can cover this requeue, so > > +* we needn't to deal with it b

Re: [dm-devel] [PATCH 1/5] block: don't call blk_mq_delay_run_hw_queue() in case of BLK_STS_RESOURCE

On Tue, Sep 19, 2017 at 11:48:23AM -0400, Mike Snitzer wrote: > On Tue, Sep 19 2017 at 1:43am -0400, > Ming Lei <ming@redhat.com> wrote: > > > On Mon, Sep 18, 2017 at 03:18:16PM +, Bart Van Assche wrote: > > > On Sun, 2017-09-17 at 20:40 +0800, Ming Lei wro

Re: [dm-devel] [PATCH 1/5] block: don't call blk_mq_delay_run_hw_queue() in case of BLK_STS_RESOURCE

On Wed, Sep 20, 2017 at 12:49 AM, Bart Van Assche <bart.vanass...@wdc.com> wrote: > On Wed, 2017-09-20 at 00:04 +0800, Ming Lei wrote: >> Run queue at end_io is definitely wrong, because blk-mq has SCHED_RESTART >> to do that already. > > Sorry but I disagree. If SCHED

Re: [dm-devel] [PATCH 1/5] block: don't call blk_mq_delay_run_hw_queue() in case of BLK_STS_RESOURCE

On Tue, Sep 19, 2017 at 11:56:03AM -0400, Mike Snitzer wrote: > On Tue, Sep 19 2017 at 11:36am -0400, > Bart Van Assche <bart.vanass...@wdc.com> wrote: > > > On Tue, 2017-09-19 at 13:43 +0800, Ming Lei wrote: > > > On Mon, Sep 18, 2017 at 03:18:16PM +, Bart Va

Re: [dm-devel] [PATCH 2/5] dm-mpath: return DM_MAPIO_REQUEUE in case of rq allocation failure

On Tue, Sep 19, 2017 at 10:41:30AM -0400, Mike Snitzer wrote: > On Sun, Sep 17 2017 at 9:23am -0400, > Ming Lei <ming@redhat.com> wrote: > > > On Fri, Sep 15, 2017 at 04:06:55PM -0400, Mike Snitzer wrote: > > > On Fri, Sep 15 2017 at 1:29pm -0400, >

Re: [dm-devel] [PATCH V5 00/14] blk-mq-sched: improve sequential I/O performance(part 1)

Hi John, On Mon, Oct 09, 2017 at 01:09:22PM +0100, John Garry wrote: > On 30/09/2017 11:27, Ming Lei wrote: > > Hi Jens, > > > > In Red Hat internal storage test wrt. blk-mq scheduler, we > > found that I/O performance is much bad with mq-deadline, especially >

Re: [dm-devel] [PATCH V5 00/14] blk-mq-sched: improve sequential I/O performance(part 1)

On Tue, Oct 10, 2017 at 01:24:52PM +0100, John Garry wrote: > On 10/10/2017 02:46, Ming Lei wrote: > > > > > > I tested this series for the SAS controller on HiSilicon hip07 > > > > > > platform as I > > > > > > am interested in enabling

Re: [dm-devel] [PATCH V6 4/5] blk-mq-sched: improve dispatching from sw queue

On Tue, Oct 10, 2017 at 11:23:45AM -0700, Omar Sandoval wrote: > On Mon, Oct 09, 2017 at 07:24:23PM +0800, Ming Lei wrote: > > SCSI devices use host-wide tagset, and the shared driver tag space is > > often quite big. Meantime there is also queue depth for each lun( > >

[dm-devel] [PATCH V5 7/7] blk-mq-sched: don't dequeue request until all in ->dispatch are flushed

;bart.vanass...@wdc.com> Tested-by: Oleksandr Natalenko <oleksa...@natalenko.name> Tested-by: Tom Nguyen <tom81...@gmail.com> Tested-by: Paolo Valente <paolo.vale...@linaro.org> Signed-off-by: Ming Lei <ming@redhat.com> --- block/blk-mq-debugf

[dm-devel] [PATCH V5 00/14] blk-mq-sched: improve sequential I/O performance(part 1)

- hold ctx->lock when clearing ctx busy bit as suggested by Bart Ming Lei (7): blk-mq: issue rq directly in blk_mq_request_bypass_insert() blk-mq-sched: fix scheduler bad performance sbitmap: introduce __sbitmap_for_each_set() blk-mq: introduce blk_mq_dequeue_from_ctx() bl

[dm-devel] [PATCH V5 4/8] block: move actual bio merge code into __elv_merge

So that we can reuse __elv_merge() to merge bio into requests from sw queue in the following patches. No functional change. Tested-by: Oleksandr Natalenko <oleksa...@natalenko.name> Tested-by: Tom Nguyen <tom81...@gmail.com> Tested-by: Paolo Valente <paolo.vale...@linaro.org> S

[dm-devel] [PATCH V5 6/8] block: introduce .last_merge and .hash to blk_mq_ctx

Prepare for supporting bio merge to sw queue if no blk-mq io scheduler is taken. Tested-by: Oleksandr Natalenko <oleksa...@natalenko.name> Tested-by: Tom Nguyen <tom81...@gmail.com> Tested-by: Paolo Valente <paolo.vale...@linaro.org> Signed-off-by: Ming Lei <ming@redha

[dm-devel] [PATCH V5 1/8] blk-mq-sched: introduce blk_mq_sched_queue_depth()

dr Natalenko <oleksa...@natalenko.name> Tested-by: Tom Nguyen <tom81...@gmail.com> Tested-by: Paolo Valente <paolo.vale...@linaro.org> Signed-off-by: Ming Lei <ming@redhat.com> --- block/blk-mq-sched.c | 8 +--- block/blk-mq-sched.h | 11 +++ 2 files ch

[dm-devel] [PATCH 4/5] dm-mpath: cache ti->clone during requeue

During requeue, block layer won't change the request any more, such as no merge, so we can cache ti->clone and let .clone_and_map_rq check if the cache can be hit. Signed-off-by: Ming Lei <ming@redhat.com> --- drivers/md/dm-mpath.c | 31 --- drivers/m

  1   2   3   4   5   6   7   >