Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754177AbbGXDxB (ORCPT ); Thu, 23 Jul 2015 23:53:01 -0400 Received: from szxga01-in.huawei.com ([58.251.152.64]:55425 "EHLO szxga01-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753337AbbGXDw7 (ORCPT ); Thu, 23 Jul 2015 23:52:59 -0400 Message-ID: <55B1B686.8010006@huawei.com> Date: Fri, 24 Jul 2015 11:52:38 +0800 From: Rui Xiang User-Agent: Mozilla/5.0 (Windows NT 6.1; rv:24.0) Gecko/20100101 Thunderbird/24.4.0 MIME-Version: 1.0 To: CC: , , , Subject: A problem about OX_ID reused by FCoE driver Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 8bit X-Originating-IP: [10.177.22.57] X-CFilter-Loop: Reflected Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1194 Lines: 30 From: Wu Yanjiang Hi all, On a system that was running 3.0.13-0.27-default, a problem that the OX_ID is reused by FCoE driver occurred. Which can be confirmed is that the problem is occurred at initiator side, but the reason how does it happen is unknown. By the trace captured by JDSU protocol analyzer, the initiator initiated a read command about 10 seconds after the virtual link resumed . But about 10ms later, the initiator send ABTS to abort the read command. Then the OX_ID was reused for a new command immediately without abort response from target side and RRQ process. Test environment ： Initiator OS: SLES 11 SP2 (3.0.13-0.27-default) Initiator CNA: INTEL X520-SR2 Test step： 1.INTEL X520-SR2 connect to intel 82599 card in target directly 2.Initiator initiates write and read command to target by FCoE VN2VN protect 3.Disconnect the physical link then reconnect it Any advice is welcome. Thanks. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/