From mboxrd@z Thu Jan 1 00:00:00 1970 From: jamal Subject: Re: [PATCH] sched: Optimize return value of qdisc_restart Date: Thu, 10 May 2007 08:50:37 -0400 Message-ID: <1178801437.4074.37.camel@localhost> References: <1178725965.4058.75.camel@localhost> <20070510115039.GA24439@gondor.apana.org.au> <20070510.045534.90119358.davem@davemloft.net> <1178799661.4074.20.camel@localhost> Reply-To: hadi@cyberus.ca Mime-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 7bit Cc: herbert@gondor.apana.org.au, krkumar2@in.ibm.com, netdev@vger.kernel.org To: David Miller Return-path: Received: from wx-out-0506.google.com ([66.249.82.236]:44969 "EHLO wx-out-0506.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758802AbXEJMum (ORCPT ); Thu, 10 May 2007 08:50:42 -0400 Received: by wx-out-0506.google.com with SMTP id h31so523691wxd for ; Thu, 10 May 2007 05:50:41 -0700 (PDT) In-Reply-To: <1178799661.4074.20.camel@localhost> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org Never mind, I was wrong. qdisc run will be invoked by cpu0; i.e: CPU0 CPU1 + grab qlock | | + find that return code is 0 | enq pkt X + release qdisc running | | + grab qdisc running | ==> outta here | call qdisc_run + release qlock Should have looked at my netconf slides first ;-> cheers, jamal On Thu, 2007-10-05 at 08:21 -0400, jamal wrote: > On Thu, 2007-10-05 at 04:55 -0700, David Miller wrote: > > From: Herbert Xu > > Date: Thu, 10 May 2007 21:50:39 +1000 > > > > > T_SCHED]: Rationalise return value of qdisc_restart > > > > > > The current return value scheme and associated comment was invented > > > back in the 20th century when we still had that tbusy flag. Things > > > have changed quite a bit since then (even Tony Blair is moving on > > > now, not to mention the new French president). > > > > > > All we need to indicate now is whether the caller should continue > > > processing the queue. Therefore it's sufficient if we return 0 if > > > we want to stop and non-zero otherwise. > > > > > > This is based on a patch by Krishna Kumar. > > > > > > Signed-off-by: > > > > Fair enough, patch applied :-) > > Ok, see if this makes sense: > > CPU0 CPU1 (holding qdisc running) > . | > . | > . + grab qlock > . | > . | deq pkt > . + release qlock > . + grab txlock > . | send pkt > . + release txlock > . + grab qlock > has pktX | (NEW: qlen = 0); return 0 instead of -1 > waiting for qlock + release qlock > + grab qlock | > | + find that return code is 0 > | enq pkt X + release qdisc running > | | > + release qlock | ==> outta here > > pkt X is stuck unless some event happens such as a new pkt arrival. > In other words it sits there for an indeterminate period. > > cheers, > jamal