From mboxrd@z Thu Jan 1 00:00:00 1970 From: Mike Christie Subject: Re: [PATCH 12/16] BNX2I: Added feature to silently drop NOPOUT request Date: Fri, 19 Nov 2010 23:07:32 -0600 Message-ID: <4CE75794.2050508@cs.wisc.edu> References: <1289430297-30221-13-git-send-email-eddie.wai@broadcom.com> <4CE4A030.7080004@cs.wisc.edu> <1290108358.6191.124.camel@ltirv-waie-lx1> <4CE584C6.7070300@cs.wisc.edu> <4CE586D6.3060803@cs.wisc.edu> <1290117557.6191.136.camel@ltirv-waie-lx1> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from sabe.cs.wisc.edu ([128.105.6.20]:39527 "EHLO sabe.cs.wisc.edu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932708Ab0KTE7h (ORCPT ); Fri, 19 Nov 2010 23:59:37 -0500 In-Reply-To: <1290117557.6191.136.camel@ltirv-waie-lx1> Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: open-iscsi@googlegroups.com Cc: Eddie Wai , Eddie Wai , James Bottomley , linux-scsi , Michael Chan , Anil Veerabhadrappa , Benjamin Li On 11/18/2010 03:59 PM, Eddie Wai wrote: > As for the NOPOUT requests, since the NOPOUT send request failed, the > last_ping jiffies count would not get updated. Then the > iscsi_check_transport_timeouts callback will just keeps getting called > and stalling the system. > > Perhaps a better way to do this is to allow the last_ping jiffies to be > updated but use a different ping_timeout value for failed nopout ping > conditions. > If this is a hard error then we can just have xmit_task return a error, and then have iscsi_send_nopout call iscsi_conn_failure for the driver. Is there any issue with starting the eh process at this time? Would the quicker swing around to ep_disconnect and ep_connect cause problems?