Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-04-06 Thread Ming Lei
On Fri, Apr 06, 2018 at 05:11:53PM +0200, Christian Borntraeger wrote: > > > On 04/06/2018 04:58 PM, Ming Lei wrote: > > On Fri, Apr 06, 2018 at 04:26:49PM +0200, Christian Borntraeger wrote: > >> > >> > >> On 04/06/2018 03:41 PM, Ming Lei wrote: > >>> On Fri, Apr 06, 2018 at 12:19:19PM +0200,

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-04-06 Thread Christian Borntraeger
On 04/06/2018 04:58 PM, Ming Lei wrote: > On Fri, Apr 06, 2018 at 04:26:49PM +0200, Christian Borntraeger wrote: >> >> >> On 04/06/2018 03:41 PM, Ming Lei wrote: >>> On Fri, Apr 06, 2018 at 12:19:19PM +0200, Christian Borntraeger wrote: On 04/06/2018 11:23 AM, Ming Lei wrote:

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-04-06 Thread Ming Lei
On Fri, Apr 06, 2018 at 04:26:49PM +0200, Christian Borntraeger wrote: > > > On 04/06/2018 03:41 PM, Ming Lei wrote: > > On Fri, Apr 06, 2018 at 12:19:19PM +0200, Christian Borntraeger wrote: > >> > >> > >> On 04/06/2018 11:23 AM, Ming Lei wrote: > >>> On Fri, Apr 06, 2018 at 10:51:28AM +0200,

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-04-06 Thread Christian Borntraeger
On 04/06/2018 03:41 PM, Ming Lei wrote: > On Fri, Apr 06, 2018 at 12:19:19PM +0200, Christian Borntraeger wrote: >> >> >> On 04/06/2018 11:23 AM, Ming Lei wrote: >>> On Fri, Apr 06, 2018 at 10:51:28AM +0200, Christian Borntraeger wrote: On 04/06/2018 10:41 AM, Ming Lei wrote:

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-04-06 Thread Ming Lei
On Fri, Apr 06, 2018 at 12:19:19PM +0200, Christian Borntraeger wrote: > > > On 04/06/2018 11:23 AM, Ming Lei wrote: > > On Fri, Apr 06, 2018 at 10:51:28AM +0200, Christian Borntraeger wrote: > >> > >> > >> On 04/06/2018 10:41 AM, Ming Lei wrote: > >>> On Thu, Apr 05, 2018 at 07:39:56PM +0200,

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-04-06 Thread Christian Borntraeger
On 04/06/2018 11:23 AM, Ming Lei wrote: > On Fri, Apr 06, 2018 at 10:51:28AM +0200, Christian Borntraeger wrote: >> >> >> On 04/06/2018 10:41 AM, Ming Lei wrote: >>> On Thu, Apr 05, 2018 at 07:39:56PM +0200, Christian Borntraeger wrote: On 04/05/2018 06:11 PM, Ming Lei wrote:

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-04-06 Thread Christian Borntraeger
On 04/06/2018 11:23 AM, Ming Lei wrote: > On Fri, Apr 06, 2018 at 10:51:28AM +0200, Christian Borntraeger wrote: >> >> >> On 04/06/2018 10:41 AM, Ming Lei wrote: >>> On Thu, Apr 05, 2018 at 07:39:56PM +0200, Christian Borntraeger wrote: On 04/05/2018 06:11 PM, Ming Lei wrote:

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-04-06 Thread Ming Lei
On Fri, Apr 06, 2018 at 10:51:28AM +0200, Christian Borntraeger wrote: > > > On 04/06/2018 10:41 AM, Ming Lei wrote: > > On Thu, Apr 05, 2018 at 07:39:56PM +0200, Christian Borntraeger wrote: > >> > >> > >> On 04/05/2018 06:11 PM, Ming Lei wrote: > > Could you please apply the

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-04-06 Thread Christian Borntraeger
On 04/06/2018 10:51 AM, Christian Borntraeger wrote: > > > On 04/06/2018 10:41 AM, Ming Lei wrote: >> On Thu, Apr 05, 2018 at 07:39:56PM +0200, Christian Borntraeger wrote: >>> >>> >>> On 04/05/2018 06:11 PM, Ming Lei wrote: > > Could you please apply the following patch and provide

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-04-06 Thread Christian Borntraeger
On 04/06/2018 10:41 AM, Ming Lei wrote: > On Thu, Apr 05, 2018 at 07:39:56PM +0200, Christian Borntraeger wrote: >> >> >> On 04/05/2018 06:11 PM, Ming Lei wrote: Could you please apply the following patch and provide the dmesg boot log? >>> >>> And please post out the 'lscpu' log

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-04-06 Thread Ming Lei
On Thu, Apr 05, 2018 at 07:39:56PM +0200, Christian Borntraeger wrote: > > > On 04/05/2018 06:11 PM, Ming Lei wrote: > >> > >> Could you please apply the following patch and provide the dmesg boot log? > > > > And please post out the 'lscpu' log together from the test machine too. > >

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-04-06 Thread Christian Borntraeger
On 04/05/2018 06:05 PM, Ming Lei wrote: [...] > diff --git a/block/blk-mq.c b/block/blk-mq.c > index 90838e998f66..996f8a963026 100644 > --- a/block/blk-mq.c > +++ b/block/blk-mq.c > @@ -1324,9 +1324,18 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx > *hctx) >*/ > if

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-04-05 Thread Christian Borntraeger
On 04/05/2018 07:39 PM, Christian Borntraeger wrote: > > > On 04/05/2018 06:11 PM, Ming Lei wrote: >>> >>> Could you please apply the following patch and provide the dmesg boot log? >> >> And please post out the 'lscpu' log together from the test machine too. > > attached. > > As I said

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-04-05 Thread Christian Borntraeger
On 04/05/2018 06:11 PM, Ming Lei wrote: >> >> Could you please apply the following patch and provide the dmesg boot log? > > And please post out the 'lscpu' log together from the test machine too. attached. As I said before this seems to go way with CONFIG_NR_CPUS=64 or smaller. We have 282

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-04-05 Thread Ming Lei
On Fri, Apr 06, 2018 at 12:05:03AM +0800, Ming Lei wrote: > On Wed, Apr 04, 2018 at 10:18:13AM +0200, Christian Borntraeger wrote: > > > > > > On 03/30/2018 04:53 AM, Ming Lei wrote: > > > On Thu, Mar 29, 2018 at 01:49:29PM +0200, Christian Borntraeger wrote: > > >> > > >> > > >> On 03/29/2018

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-04-05 Thread Ming Lei
On Wed, Apr 04, 2018 at 10:18:13AM +0200, Christian Borntraeger wrote: > > > On 03/30/2018 04:53 AM, Ming Lei wrote: > > On Thu, Mar 29, 2018 at 01:49:29PM +0200, Christian Borntraeger wrote: > >> > >> > >> On 03/29/2018 01:43 PM, Ming Lei wrote: > >>> On Thu, Mar 29, 2018 at 12:49:55PM +0200,

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-04-04 Thread Christian Borntraeger
On 03/30/2018 04:53 AM, Ming Lei wrote: > On Thu, Mar 29, 2018 at 01:49:29PM +0200, Christian Borntraeger wrote: >> >> >> On 03/29/2018 01:43 PM, Ming Lei wrote: >>> On Thu, Mar 29, 2018 at 12:49:55PM +0200, Christian Borntraeger wrote: On 03/29/2018 12:48 PM, Ming Lei wrote:

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-29 Thread Ming Lei
On Thu, Mar 29, 2018 at 01:49:29PM +0200, Christian Borntraeger wrote: > > > On 03/29/2018 01:43 PM, Ming Lei wrote: > > On Thu, Mar 29, 2018 at 12:49:55PM +0200, Christian Borntraeger wrote: > >> > >> > >> On 03/29/2018 12:48 PM, Ming Lei wrote: > >>> On Thu, Mar 29, 2018 at 12:10:11PM +0200,

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-29 Thread Ming Lei
On Thu, Mar 29, 2018 at 12:49:55PM +0200, Christian Borntraeger wrote: > > > On 03/29/2018 12:48 PM, Ming Lei wrote: > > On Thu, Mar 29, 2018 at 12:10:11PM +0200, Christian Borntraeger wrote: > >> > >> > >> On 03/29/2018 11:40 AM, Ming Lei wrote: > >>> On Thu, Mar 29, 2018 at 11:09:08AM +0200,

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-29 Thread Christian Borntraeger
On 03/29/2018 12:48 PM, Ming Lei wrote: > On Thu, Mar 29, 2018 at 12:10:11PM +0200, Christian Borntraeger wrote: >> >> >> On 03/29/2018 11:40 AM, Ming Lei wrote: >>> On Thu, Mar 29, 2018 at 11:09:08AM +0200, Christian Borntraeger wrote: On 03/29/2018 09:23 AM, Christian

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-29 Thread Ming Lei
On Thu, Mar 29, 2018 at 12:10:11PM +0200, Christian Borntraeger wrote: > > > On 03/29/2018 11:40 AM, Ming Lei wrote: > > On Thu, Mar 29, 2018 at 11:09:08AM +0200, Christian Borntraeger wrote: > >> > >> > >> On 03/29/2018 09:23 AM, Christian Borntraeger wrote: > >>> > >>> > >>> On 03/29/2018

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-29 Thread Ming Lei
On Thu, Mar 29, 2018 at 05:52:16PM +0800, Ming Lei wrote: > On Thu, Mar 29, 2018 at 09:23:10AM +0200, Christian Borntraeger wrote: > > > > > > On 03/29/2018 04:00 AM, Ming Lei wrote: > > > On Wed, Mar 28, 2018 at 05:36:53PM +0200, Christian Borntraeger wrote: > > >> > > >> > > >> On 03/28/2018

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-29 Thread Christian Borntraeger
On 03/29/2018 12:11 PM, Christian Borntraeger wrote: > > > On 03/29/2018 11:52 AM, Ming Lei wrote: >> From the debugfs log, hctx0 is mapped to lots of CPU, so it shouldn't be >> unmapped, could you check if it is hctx0 which is unmapped when the >> warning is triggered? If not, what is the

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-29 Thread Christian Borntraeger
On 03/29/2018 11:52 AM, Ming Lei wrote: > From the debugfs log, hctx0 is mapped to lots of CPU, so it shouldn't be > unmapped, could you check if it is hctx0 which is unmapped when the > warning is triggered? If not, what is the unmapped hctx? And you can do > that by adding one extra line: > >

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-29 Thread Christian Borntraeger
On 03/29/2018 11:40 AM, Ming Lei wrote: > On Thu, Mar 29, 2018 at 11:09:08AM +0200, Christian Borntraeger wrote: >> >> >> On 03/29/2018 09:23 AM, Christian Borntraeger wrote: >>> >>> >>> On 03/29/2018 04:00 AM, Ming Lei wrote: On Wed, Mar 28, 2018 at 05:36:53PM +0200, Christian Borntraeger

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-29 Thread Ming Lei
On Thu, Mar 29, 2018 at 09:23:10AM +0200, Christian Borntraeger wrote: > > > On 03/29/2018 04:00 AM, Ming Lei wrote: > > On Wed, Mar 28, 2018 at 05:36:53PM +0200, Christian Borntraeger wrote: > >> > >> > >> On 03/28/2018 05:26 PM, Ming Lei wrote: > >>> Hi Christian, > >>> > >>> On Wed, Mar 28,

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-29 Thread Ming Lei
On Thu, Mar 29, 2018 at 11:09:08AM +0200, Christian Borntraeger wrote: > > > On 03/29/2018 09:23 AM, Christian Borntraeger wrote: > > > > > > On 03/29/2018 04:00 AM, Ming Lei wrote: > >> On Wed, Mar 28, 2018 at 05:36:53PM +0200, Christian Borntraeger wrote: > >>> > >>> > >>> On 03/28/2018

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-29 Thread Christian Borntraeger
On 03/29/2018 09:23 AM, Christian Borntraeger wrote: > > > On 03/29/2018 04:00 AM, Ming Lei wrote: >> On Wed, Mar 28, 2018 at 05:36:53PM +0200, Christian Borntraeger wrote: >>> >>> >>> On 03/28/2018 05:26 PM, Ming Lei wrote: Hi Christian, On Wed, Mar 28, 2018 at 09:45:10AM

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-28 Thread Christian Borntraeger
FWIW, these logs were from a different system (with less disks and cpus). the related log is [4.114191] dasd-eckd.2aa01a: 0.0.3f77: New DASD 3390/0C (CU 3990/01) with 30051 cylinders, 15 heads, 224 sectors [4.114852] dasd-eckd.2aa01a: 0.0.3f74: New DASD 3390/0C (CU 3990/01) with 30051

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-28 Thread Christian Borntraeger
With that patch I now get: [ 40.620619] virbr0: port 1(virbr0-nic) entered disabled state [ 47.418592] run queue from wrong CPU 3, hctx inactive [ 47.418602] CPU: 3 PID: 2153 Comm: kworker/3:1H Tainted: GW 4.16.0-rc7+ #27 [ 47.418604] Hardware name: IBM 2964 NC9 704 (LPAR)

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-28 Thread Christian Borntraeger
On 03/28/2018 05:26 PM, Ming Lei wrote: > Hi Christian, > > On Wed, Mar 28, 2018 at 09:45:10AM +0200, Christian Borntraeger wrote: >> FWIW, this patch does not fix the issue for me: >> >> ostname=? addr=? terminal=? res=success' >> [ 21.454961] WARNING: CPU: 3 PID: 1882 at block/blk-mq.c:1410

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-28 Thread Ming Lei
Hi Christian, On Wed, Mar 28, 2018 at 09:45:10AM +0200, Christian Borntraeger wrote: > FWIW, this patch does not fix the issue for me: > > ostname=? addr=? terminal=? res=success' > [ 21.454961] WARNING: CPU: 3 PID: 1882 at block/blk-mq.c:1410 > __blk_mq_delay_run_hw_queue+0xbe/0xd8 > [

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-28 Thread Jens Axboe
On 3/28/18 8:38 AM, Jens Axboe wrote: > On 3/28/18 1:45 AM, Christian Borntraeger wrote: >> FWIW, this patch does not fix the issue for me: > > Looks like I didn't do the delayed path. How about the below? OK, final version... This is more in line with what I originally suggested. diff --git

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-28 Thread Jens Axboe
On 3/28/18 1:45 AM, Christian Borntraeger wrote: > FWIW, this patch does not fix the issue for me: Looks like I didn't do the delayed path. How about the below? diff --git a/block/blk-mq.c b/block/blk-mq.c index 16e83e6df404..fd663ae1094c 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-28 Thread Christian Borntraeger
FWIW, this patch does not fix the issue for me: ostname=? addr=? terminal=? res=success' [ 21.454961] WARNING: CPU: 3 PID: 1882 at block/blk-mq.c:1410 __blk_mq_delay_run_hw_queue+0xbe/0xd8 [ 21.454968] Modules linked in: scsi_dh_rdac scsi_dh_emc scsi_dh_alua dm_mirror dm_region_hash dm_log

Re: [PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-27 Thread Jens Axboe
On 3/27/18 7:20 PM, Ming Lei wrote: > From commit 20e4d813931961fe ("blk-mq: simplify queue mapping & schedule > with each possisble CPU") on, it should be easier to see unmapped hctx > in some CPU topo, such as, hctx may not be mapped to any CPU. > > This patch avoids the warning in

[PATCH] blk-mq: only run mapped hw queues in blk_mq_run_hw_queues()

2018-03-27 Thread Ming Lei
>From commit 20e4d813931961fe ("blk-mq: simplify queue mapping & schedule with each possisble CPU") on, it should be easier to see unmapped hctx in some CPU topo, such as, hctx may not be mapped to any CPU. This patch avoids the warning in __blk_mq_delay_run_hw_queue() by checking if the hctx is