From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id BDE69C7618E for ; Mon, 24 Apr 2023 05:11:52 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230495AbjDXFLu (ORCPT ); Mon, 24 Apr 2023 01:11:50 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:35156 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229476AbjDXFLt (ORCPT ); Mon, 24 Apr 2023 01:11:49 -0400 Received: from verein.lst.de (verein.lst.de [213.95.11.211]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 63E8C30EC for ; Sun, 23 Apr 2023 22:11:48 -0700 (PDT) Received: by verein.lst.de (Postfix, from userid 2407) id 9B40B67373; Mon, 24 Apr 2023 07:11:44 +0200 (CEST) Date: Mon, 24 Apr 2023 07:11:44 +0200 From: Christoph Hellwig To: Max Gurtovoy Cc: martin.petersen@oracle.com, hch@lst.de, sagi@grimberg.me, linux-nvme@lists.infradead.org, kbusch@kernel.org, axboe@kernel.dk, linux-block@vger.kernel.org, oren@nvidia.com, oevron@nvidia.com, israelr@nvidia.com Subject: Re: [PATCH v1 0/2] Fix failover to non integrity NVMe path Message-ID: <20230424051144.GA9288@lst.de> References: <20230423141330.40437-1-mgurtovoy@nvidia.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20230423141330.40437-1-mgurtovoy@nvidia.com> User-Agent: Mutt/1.5.17 (2007-11-01) Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org On Sun, Apr 23, 2023 at 05:13:28PM +0300, Max Gurtovoy wrote: > Hi Christoph/Sagi/Martin, > > We're encountered a crash while testing failover between NVMeF/RDMA > paths to a target that expose a namespace with metadata. The scenario is > the following: > Configure one initiator/host path on PI offload capable port (e.g ConnectX-5 > device) and configure second initiator/host path on non PI offload capable > port (e.g ConnectX-3). Hmm. I suspect the right thing to do here is to just fail the second connect.