public inbox for netdev@vger.kernel.org 
 help / color / mirror / Atom feed
From: Stephen Hemminger <shemminger@osdl•org>
To: "Eric Lemoine" <eric.lemoine@gmail•com>
Cc: "Benjamin Herrenschmidt" <benh@kernel•crashing.org>,
	"David S. Miller" <davem@davemloft•net>,
	netdev@vger•kernel.org
Subject: Re: [sungem] proposal for a new locking strategy
Date: Mon, 6 Nov 2006 13:49:41 -0800	[thread overview]
Message-ID: <20061106134941.09a7d9bb@freekitty> (raw)
In-Reply-To: <5cac192f0611061310o7b4d267eg37fef6a0cb81bd61@mail.gmail.com>

O
> > > > But the spin is still there, just more complex..
> > > > In qdisc_restart() processing of NETDEV_TX_LOCKED causes:
> > > >         spin_lock(dev->xmit_lock)
> > > >
> > > >         q->requeue()
> > > >         netif_schedule(dev);
> > > >
> > > > SOFTIRQ:
> > > >         net_tx_action()
> > > >         qdisc_run() --> qdisc_restart()
> > > >
> > > > So instead of spinning in tight loop, you end up with a longer code
> > > > path.
> > >
> > > Stephen, sorry for insisting a bit but I'm failing to see how B is
> > > different from C in that respect. With method B, in qdisc_restart(),
> > > if netif_tx_trylock() fails to acquire the lock then we also
> > > requeue(), etc. Same long code path in case of contention.
> > >
> >
> > Method C LLTX causes repeated softirq's which will be slower since the loop
> > requires more instructions than a simple spin loop (Method B).
> 
> What I'm saying above is that Method B also causes repeated tx
> softirqs in case of contention on netif_tx_lock. The code path is :
> netif_tx_trylock() fails -> requeue() -> netif_schedule() ->
> raise_softirq(NET_TX_SOFTIRQ). Am I missing anything?
> 

Never mind, you right.  I think the netif_tx_trylock() there is a bad
idea because of the long route as shown.  Trylock's are usually bad SMP
design anyway. Not sure if it would be possible to change the locking
in qdisc_restart() without causing collateral damage in network drivers.


-- 
Stephen Hemminger <shemminger@osdl•org>

      reply	other threads:[~2006-11-06 21:49 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-11-05 13:00 [sungem] proposal for a new locking strategy Eric Lemoine
2006-11-05 13:05 ` Benjamin Herrenschmidt
2006-11-05 13:17   ` Eric Lemoine
2006-11-05 17:02     ` Stephen Hemminger
2006-11-05 17:28       ` Eric Lemoine
2006-11-05 17:41         ` Stephen Hemminger
2006-11-05 17:52           ` Eric Lemoine
2006-11-05 18:49             ` Stephen Hemminger
2006-11-05 20:11               ` Eric Lemoine
2006-11-06 17:55                 ` Stephen Hemminger
2006-11-06 20:55                   ` Eric Lemoine
2006-11-06 20:57                     ` Stephen Hemminger
2006-11-06 21:10                       ` Eric Lemoine
2006-11-06 21:49                         ` Stephen Hemminger [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20061106134941.09a7d9bb@freekitty \
    --to=shemminger@osdl$(echo .)org \
    --cc=benh@kernel$(echo .)crashing.org \
    --cc=davem@davemloft$(echo .)net \
    --cc=eric.lemoine@gmail$(echo .)com \
    --cc=netdev@vger$(echo .)kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox