[bug report] NVMe/IB: reset_controller need more than 1min

Yi Zhang yi.zhang at redhat.com
Mon Feb 14 01:47:40 PST 2022


Hi Sagi/Max
Here are more findings with the bisect:

The time for reset operation changed from 3s[1] to 12s[2] after
commit[3], and after commit[4], the reset operation timeout at the
second reset[5], let me know if you need any testing for it, thanks.

[1]
# time nvme reset /dev/nvme0

real 0m3.049s
user 0m0.000s
sys 0m0.006s
[2]
# time nvme reset /dev/nvme0

real 0m12.498s
user 0m0.000s
sys 0m0.006s
[3]
commit 5ec5d3bddc6b912b7de9e3eb6c1f2397faeca2bc (HEAD)
Author: Max Gurtovoy <maxg at mellanox.com>
Date:   Tue May 19 17:05:56 2020 +0300

    nvme-rdma: add metadata/T10-PI support

[4]
commit a70b81bd4d9d2d6c05cfe6ef2a10bccc2e04357a (HEAD)
Author: Hannes Reinecke <hare at suse.de>
Date:   Fri Apr 16 13:46:20 2021 +0200

    nvme: sanitize KATO setting-

[5]
# time nvme reset /dev/nvme0

real 0m12.628s
user 0m0.000s
sys 0m0.006s
# time nvme reset /dev/nvme0

real 1m15.617s
user 0m0.000s
sys 0m0.006s
#dmesg
[ 1866.068377] nvme nvme0: creating 40 I/O queues.
[ 1870.367851] nvme nvme0: mapped 40/0/0 default/read/poll queues.
[ 1870.370949] nvme nvme0: new ctrl: NQN "testnqn", addr 172.31.0.202:4420
[ 1930.981494] nvme nvme0: resetting controller
[ 1939.316131] nvme nvme0: creating 40 I/O queues.
[ 1943.605427] nvme nvme0: mapped 40/0/0 default/read/poll queues.
[ 1953.708327] nvme nvme0: resetting controller
[ 2024.985591] nvme nvme0: I/O 7 QID 0 timeout
[ 2024.990979] nvme nvme0: Property Set error: 881, offset 0x14
[ 2025.031069] nvme nvme0: creating 40 I/O queues.
[ 2029.321798] nvme nvme0: mapped 40/0/0 default/read/poll queues.




More information about the Linux-nvme mailing list