Re: [PATCH] [e1000]: Remove unnecessary tx_lock

[jamal <hadi@cyberus.ca>]

On Fri, 2006-04-08 at 11:18 +1000, Herbert Xu wrote:
> On Thu, Aug 03, 2006 at 09:16:04PM -0400, jamal wrote:
> > 
> > and in tg3_tx():
> > 
> >      if likely(stopped) {  
> >        // essentially no lock needed here ....
> >        prune tx ring
> >        if prunned > threshold
> >            wake
> >      } else if not stopped { 
> >           // need a lock here ...
> >          grab ring tx lock irq safe
> >          prune tx ring
> >          release ring tx lock
> >      }
> 
> The problem is that the !stopped case may be the common path for a
> lot of workloads so it'd be good to avoid taking the lock there if
> we can.

True.

Although i cant think of a clever way to do the inverse....
The heuristic i was using to avoid the lock on tx at pruning time was
knowledge that tx was not being entered at all on stop.

cheers,
jamal