From mboxrd@z Thu Jan 1 00:00:00 1970 From: sagi@grimberg.me (Sagi Grimberg) Date: Thu, 19 Oct 2017 12:44:13 +0300 Subject: nvmeof rdma regression issue on 4.14.0-rc1 (or maybe mlx4?) In-Reply-To: <0561ed58-7104-d8b6-1709-ea181ac493f5@redhat.com> References: <1735134433.8514119.1505997532669.JavaMail.zimbra@redhat.com> <1215229914.8516804.1505998051674.JavaMail.zimbra@redhat.com> <20170921144421.GA15285@infradead.org> <47493aa0-4cad-721b-4ea2-c3b2293340aa@grimberg.me> <20170924103426.GB25094@mtr-leonro.local> <4d0e27f2-99e4-ffc7-18a5-e5757c27dad4@redhat.com> <4faccebf-7fcf-58b9-1605-82ee9acc652b@grimberg.me> <729c512f-55ff-25e4-6dd9-8b4dcc31bb8d@grimberg.me> <6d639dd4-9366-2ecf-b49e-751c7a167528@grimberg.me> <64135330-a62d-87b8-c805-6b52fd40bf81@redhat.com> <62eea88b-caa4-5799-3d8f-8d8789879aa8@grimberg.me> <0561ed58-7104-d8b6-1709-ea181ac493f5@redhat.com> Message-ID: <0069d38b-efb7-0d41-ff0f-2087572cb22f@grimberg.me> > Hi Sagi > With this patch, no such error log found on host side, Awsome. that's the culprit... > but I found there > is no nvme0n1 device node even get "nvme nvme0: Successfully > reconnected" on host. That is expected because you did not persist a namespace UUID which caused the kernel to generate a random one. That confused the host as it got the same namespace ID with a different UUID. Can you please set a uuid when you rerun the test?