[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <OF30FBF3A7.542644C5-ON6525768F.004B51CE-6525768F.004B9690@in.ibm.com>
Date: Thu, 17 Dec 2009 19:26:50 +0530
From: Krishna Kumar2 <krkumar2@...ibm.com>
To: Herbert Xu <herbert@...dor.apana.org.au>
Cc: davem@...emloft.net, mst@...hat.com, netdev@...r.kernel.org,
Rusty Russell <rusty@...tcorp.com.au>,
Sridhar Samudrala <sri@...ibm.com>
Subject: Re: [RFC PATCH] Regression in linux 2.6.32 virtio_net seen with vhost-net
Herbert Xu <herbert@...dor.apana.org.au> wrote on 12/17/2009 07:10:53 PM:
> > Since dequeue_skb finds the first skb that was cached in gso_skb,
> > handles the stopped txq and returns NULL for all subsequent skbs.
> > And qdisc_restart bails out immediately. Only the first skb will
> > get requeue'd, and no more skbs are taken out of the queue -
> > either dequeue or gso_skb, till the driver restarts the queue.
>
> But dev_requeue_skb immediately reschedules a new TX softirq
> so this will keep going until the hardware wakes up the queue.
>
> That is, we have an infinite loop consuming CPU that could otherwise
> be spent doing useful work, such as generating new packets.
Except that dev_requeue_skb is never called again till the device is
restarted and stopped. It is called once per stop, and after this,
dequeue_skb never returns a skb, hence no more requeue's.
Thanks,
- KK
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists