From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Return-Path: Message-ID: <1525968713.16630.1.camel@redhat.com> Subject: Re: v4.16-rc1 + dm-mpath + BFQ From: Laurence Oberman To: Bart Van Assche , "paolo.valente@linaro.org" Cc: "ulf.hansson@linaro.org" , "axboe@kernel.dk" , "linux-block@vger.kernel.org" , "snitzer@redhat.com" , "broonie@linaro.org" , "axboe@fb.com" , "linus.walleij@linaro.org" Date: Thu, 10 May 2018 12:11:53 -0400 In-Reply-To: <75617a7d85070b989245e26de21f708c8762c7b7.camel@wdc.com> References: <1518202449.2871.32.camel@wdc.com> <6a1695f4-de6f-a959-5242-9611e148bc11@kernel.dk> <13a55c03-b138-ca8c-0a0a-95c976b4909e@wdc.com> <1FC84680-6482-4FE5-97D0-0F7079C45AA7@linaro.org> <06795609-6ec6-4ae2-f219-3bf7219c11a3@wdc.com> <1518547636.2796.15.camel@wdc.com> <0BF6AC73-69CE-41B5-BDAC-C5249037C83C@linaro.org> <60f48ff1-7c8b-2c10-4560-744d70bccea1@wdc.com> <6C49304C-D506-4719-9365-E7D35BEC9851@linaro.org> <1519868123.2777.28.camel@wdc.com> <10BDC305-A874-477C-9545-5617036C2E91@linaro.org> <2dcb12b92e50a31c55dd3ab0e464cc819432c3d3.camel@wdc.com> <7E372E2C-83A8-4EF4-B52E-E3AC6ED01C74@linaro.org> <6A355080-C9A8-475D-9A35-32850D771ABB@linaro.org> <1525466533.9055.1.camel@redhat.com> <75617a7d85070b989245e26de21f708c8762c7b7.camel@wdc.com> Content-Type: text/plain; charset="UTF-8" Mime-Version: 1.0 List-ID: On Thu, 2018-05-10 at 15:16 +0000, Bart Van Assche wrote: > On Fri, 2018-05-04 at 16:42 -0400, Laurence Oberman wrote: > > I was never able to reproduce Barts original issue using his tree > > and > > actual mlx5/cx4 hardware and ibsrp > > I enabled BFQ with no other special tuning for the moath and > > subpaths. > > I was waiting for him to come back from vacation to check with him. > > (back in the office) > > Hello Laurence, > > What I understood from off-list communication is that you tried to > find > a way to reproduce what I reported without using the srp-test > software. > My understanding is that both Paolo and I can reproduce the reported > issue > with the srp-test software. > > Bart. > > > Hello Bart using your kernel 4.17.0-rc2.bart+ CONFIG_IOSCHED_BFQ=y CONFIG_BFQ_GROUP_IOSCHED=y These are all SRP LUNS 36001405b2b5c6c24c084b6fa4d55da2f dm-27 LIO-ORG ,block-10         size=3.9G features='2 queue_mode mq' hwhandler='0' wp=rw `-+- policy='service-time 0' prio=1 status=active   |- 2:0:0:9  sdap 66:144 active ready running   `- 1:0:0:9  sdaz 67:48  active ready running 36001405b26ebe76dcb94a489f6f245f8 dm-18 LIO-ORG ,block-21         size=3.9G features='2 queue_mode mq' hwhandler='0' wp=rw `-+- policy='service-time 0' prio=1 status=active   |- 2:0:0:20 sdx  65:112 active ready running   `- 1:0:0:20 sdaa 65:160 active ready running [root@ibclient ~]# cd /sys/block [root@ibclient block]# cat /sys/block/dm-18/queue/scheduler mq-deadline kyber [bfq] none [root@ibclient block]# cat /sys/block/sdaa/queue/scheduler mq-deadline kyber [bfq] none [root@ibclient block]# cat /sys/block/sdx/queue/scheduler mq-deadline kyber [bfq] none Not using the test software just exercising the LUNS via my own tests I am unable to get the OOPS I guess something in the srp-test software triggers it then. Doing plenty of IO to 5 mpath devices (1.3Gbytes/sec) #Time     cpu sys inter  ctxsw Free Buff Cach Inac Slab  Map KBRead  Reads KBWrit Writes   KBIn  PktIn  KBOut  PktOut  12:08:32    0   0  1437   1107  88G   5M   1G 902M 300M 178M  1380K    345      0      0      6     74      0       4  Thanks Laurence