On Tue, Aug 1, 2023 at 7:28 PM Yi Zhang <yi.zhang@xxxxxxxxxx> wrote: > > Hello > > I found random nvme/047 failure on linux-block/for-next when I do > stress blktests nvme/tcp nvme/047 test: I tried to add one "sleep 0.05" after connecting that can workaround this issue. > > Kernel config: https://pastebin.com/6i3sZWAx > ============================================0 > nvme/047 (test different queue types for fabric transports) [failed] > runtime 71.129s ... 7.096s > --- tests/nvme/047.out 2023-07-16 23:04:30.052101710 -0400 > +++ /root/blktests/results/nodev/nvme/047.out.bad 2023-07-19 > 09:17:35.949908134 -0400 > @@ -1,2 +1,198 @@ > Running nvme/047 > +fio: looks like your file system does not support direct=1/buffered=0 > +fio: looks like your file system does not support direct=1/buffered=0 > +fio: looks like your file system does not support direct=1/buffered=0 > +fio: looks like your file system does not support direct=1/buffered=0 > +fio: destination does not support O_DIRECT > +fio: destination does not support O_DIRECT > ... > (Run 'diff -u tests/nvme/047.out > /root/blktests/results/nodev/nvme/047.out.bad' to see the entire diff) > > After some investigating, I found it was due to the /dev/nvme0n1 node > couldn't be created in time which lead to the following fio failing. > + nvme connect -t tcp -a 127.0.0.1 -s 4420 -n blktests-subsystem-1 > --hostnqn=nqn.2014-08.org.nvmexpress:uuid:0f01fb42-9f7f-4856-b0b3-51e60b8de349 > --hostid=0f01fb42-9f7f-4856-b0b3-51e60b8de349 --nr-write-queues=1 > + ls -l /dev/nvme0 /dev/nvme-fabrics > crw-------. 1 root root 234, 0 Aug 1 05:50 /dev/nvme0 > crw-------. 1 root root 10, 122 Aug 1 05:50 /dev/nvme-fabrics > + '[' '!' -b /dev/nvme0n1 ']' > + echo '/dev/nvme0n1 node still not created' > dmesg: > [ 1840.413396] loop0: detected capacity change from 0 to 10485760 > [ 1840.934379] nvmet: adding nsid 1 to subsystem blktests-subsystem-1 > [ 1841.018766] nvmet_tcp: enabling port 0 (127.0.0.1:4420) > [ 1846.782615] nvmet: creating nvm controller 1 for subsystem > blktests-subsystem-1 for NQN > nqn.2014-08.org.nvmexpress:uuid:0f01fb42-9f7f-4856-b0b3-51e60b8de349. > [ 1846.808392] nvme nvme0: creating 33 I/O queues. > [ 1846.874298] nvme nvme0: mapped 1/32/0 default/read/poll queues. > [ 1846.945334] nvme nvme0: new ctrl: NQN "blktests-subsystem-1", addr > 127.0.0.1:4420 > > BTW, I also found after disabling nvme_core.multipath, seems this > issue cannot be reproduced. > > -- > Best Regards, > Yi Zhang -- Best Regards, Yi Zhang
