nvme/rdma initiator stuck on reboot

Steve Wise swise at opengridcomputing.com
Wed Aug 17 08:13:23 PDT 2016


> 
> Can this be related due to the fact that we use a signle-threaded
> workqueue for delete/reset/reconnect? (delete cancel_sync the active
> reconnect work...)
> 
> Does this untested patch help?

That seems to do it!


> --
> diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
> index 8d2875b4c56d..78a47c17fb01 100644
> --- a/drivers/nvme/host/rdma.c
> +++ b/drivers/nvme/host/rdma.c
> @@ -1997,7 +1997,7 @@ static struct nvmf_transport_ops
> nvme_rdma_transport = {
> 
>   static int __init nvme_rdma_init_module(void)
>   {
> -       nvme_rdma_wq = create_workqueue("nvme_rdma_wq");
> +       nvme_rdma_wq = alloc_workqueue("nvme_rdma_wq", 0, 0);
>          if (!nvme_rdma_wq)
>                  return -ENOMEM;
> --




More information about the Linux-nvme mailing list