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
