From mboxrd@z Thu Jan 1 00:00:00 1970 From: Yang Yingliang Subject: Re: [PATCH] bonding: set correct tx_queue_len for bond_dev Date: Tue, 30 Jul 2013 17:24:54 +0800 Message-ID: <51F78666.3050801@huawei.com> References: <51F7694A.1060703@huawei.com> <20130730.003403.299786235452826263.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit Cc: , , To: David Miller Return-path: Received: from szxga01-in.huawei.com ([119.145.14.64]:58561 "EHLO szxga01-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754680Ab3G3JZL (ORCPT ); Tue, 30 Jul 2013 05:25:11 -0400 In-Reply-To: <20130730.003403.299786235452826263.davem@davemloft.net> Sender: netdev-owner@vger.kernel.org List-ID: On 2013/7/30 15:34, David Miller wrote: > From: Yang Yingliang > Date: Tue, 30 Jul 2013 15:20:42 +0800 > >> With htb, sch->limit is set from bond_dev->tx_queue_len which >> is initialized to 0 in bond_setup. > > This is intentional, software devices should not queue TX > packets. This makes software devices with htb qdisc can hold only one packet, others are dropped. Maybe sch->limit's default value which is 1 is too small. Instead of this patch, I'll send another patch to fix this value for fixing this issue. > > You can only use the packet scheduler with hardware devices. > >