Return-Path: Received: from userp1040.oracle.com ([156.151.31.81]:23267 "EHLO userp1040.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750759AbcBJVTW convert rfc822-to-8bit (ORCPT ); Wed, 10 Feb 2016 16:19:22 -0500 Content-Type: text/plain; charset=us-ascii Mime-Version: 1.0 (Mac OS X Mail 9.2 \(3112\)) Subject: Re: Kernel crash in Centos 6.6 From: Chuck Lever In-Reply-To: <9eeh3fd9sbcxvpbtxeka4hci.1455121291462@email.android.com> Date: Wed, 10 Feb 2016 16:19:17 -0500 Cc: Linux NFS Mailing List Message-Id: <709CC9F2-40B0-45CB-BBB2-5DFC43A3AEC7@oracle.com> References: <9eeh3fd9sbcxvpbtxeka4hci.1455121291462@email.android.com> To: "fedele.stabile" Sender: linux-nfs-owner@vger.kernel.org List-ID: > On Feb 10, 2016, at 11:21 AM, fedele.stabile wrote: > > No, the client hangs and the only way to gain control is power cycle of client. ... File a bug with your distributor. They should be able to help you with triage steps. > -------- Messaggio originale -------- > Da: Chuck Lever > Data: 10/02/2016 16:28 (GMT+01:00) > A: fedele.stabile@fis.unical.it > Cc: Linux NFS Mailing List > Oggetto: Re: Kernel crash in Centos 6.6 > > Fedele- > > > On Feb 10, 2016, at 7:07 AM, Fedele Stabile wrote: > > > > Hello all, > > I have a kernel crash when I mount an NFS volume using RDMA transport. > > On client and server is installed Centos 6.6 kernel 2.6.32 > > -504.8.1.el6.x86_64 > > I use nfs v4 > > The client hangs if I execute > > mount -t nfs -o rdma ib-server:/data /data > > Server and client are connected throw Infiniband network and Qlogic > > adapters. > > I assume you mean that the mount command hangs, not that > the whole client deadlocks. > > Add "port=20049" to the mount options. > > > -- > Chuck Lever > > > > > -- Chuck Lever