You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Test SPDK NVMe-oF target with Software Roce. While increasing the queue depth, we always have the following issue while calling ibv_poll_cq:
nvmf_tgt.c: 255:spdk_nvmf_startup: NOTICE: Acceptor running on core 0 on socket 0
rdma.c:1707:spdk_nvmf_rdma_qpair_poll: ERROR: CQ error on CQ 0x1a69230, Request 0x27695128 (12): transport retry counter exceeded
The text was updated successfully, but these errors were encountered:
I was setting up SPDK NVMe-OF with softRoCE on linux kernel 4.15.0.
I am not able to discover the nvme target from another linux client.
However, I can see that its getting discovered on nvme target ie using same initiator as the target
very well.
Used the following conf
======snip====
NQN nqn.2016-06.io.spdk:cnode2
Listen RDMA 192.168.106.163:4420
AllowAnyHost Yes
Host nqn.2016-06.io.spdk:init
SN SPDK00000000000002
Namespace Malloc0
Namespace Malloc1
Namespace AIO0
Namespace AIO1
===snip
Error am getting at the client side is
root@amit-VirtualBox:/RCoE/targets/nvme-cli# ./nvme discover -t rdma -a 192.168.106.163 -s 4420
Failed to write to /dev/nvme-fabrics: Connection reset by peer
But request did not reach the nvme target as I had started it in debug mode.
Any help would be appreciated.
Test SPDK NVMe-oF target with Software Roce. While increasing the queue depth, we always have the following issue while calling ibv_poll_cq:
nvmf_tgt.c: 255:spdk_nvmf_startup: NOTICE: Acceptor running on core 0 on socket 0
rdma.c:1707:spdk_nvmf_rdma_qpair_poll: ERROR: CQ error on CQ 0x1a69230, Request 0x27695128 (12): transport retry counter exceeded
The text was updated successfully, but these errors were encountered: