From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jarek Poplawski Subject: Re: [PATCH take 2] pkt_sched: Fix qdisc_watchdog() vs. dev_deactivate() race Date: Thu, 11 Sep 2008 12:10:10 +0000 Message-ID: <20080911121010.GB5765@ff.dom.local> References: <20080821.005250.117238212.davem@davemloft.net> <20080911.033956.233317469.davem@davemloft.net> <20080911104531.GA21913@gondor.apana.org.au> <20080911.034955.111797743.davem@davemloft.net> <20080911110035.GA22065@gondor.apana.org.au> <20080911115132.GA5765@ff.dom.local> <20080911115449.GA22860@gondor.apana.org.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: David Miller , netdev@vger.kernel.org To: Herbert Xu Return-path: Received: from mail-gx0-f16.google.com ([209.85.217.16]:57703 "EHLO mail-gx0-f16.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752563AbYIKMKT (ORCPT ); Thu, 11 Sep 2008 08:10:19 -0400 Received: by gxk9 with SMTP id 9so16136680gxk.13 for ; Thu, 11 Sep 2008 05:10:17 -0700 (PDT) Content-Disposition: inline In-Reply-To: <20080911115449.GA22860@gondor.apana.org.au> Sender: netdev-owner@vger.kernel.org List-ID: On Thu, Sep 11, 2008 at 09:54:49PM +1000, Herbert Xu wrote: > On Thu, Sep 11, 2008 at 11:51:32AM +0000, Jarek Poplawski wrote: > > > > IMHO, the most reasonable test here is for all tx_queues of a qdisc > > beeing stopped, but since this is quite heavy, probably we need an > > additional qdisc flag for such an occasion. > > Yes we could do that too. Although the head-of-qdisc approach > will eventually lead to the same result. That is, as you pop > things off the head eventually you'll hit a packet that belongs > to the stopped queue and that'll then block the whole qdisc. > > So I don't think there's anything inherently advantageous in > checking all the queues. Yes, but this is only because this current behaviour of blocking all transmit by one stopped tx_queue is wrong (IMHO), and with sch_multiq there should be a real advantage. Cheers, Jarek P.