Le mardi 03 janvier 2012 à 14:37 +0100, Eric Dumazet a écrit :
> Le mardi 03 janvier 2012 à 14:31 +0100, Eric Dumazet a écrit :
> > Le mardi 03 janvier 2012 à 12:01 +0000, David Laight a écrit :
> > > > if (acct) {
> > > > - spin_lock_bh(&ct->lock);
> > > > - acct[CTINFO2DIR(ctinfo)].packets++;
> > > > - acct[CTINFO2DIR(ctinfo)].bytes += skb->len;
> > > > - spin_unlock_bh(&ct->lock);
> > > > + atomic64_inc(&acct[CTINFO2DIR(ctinfo)].packets);
> > > > + atomic64_add(skb->len,
> > > &acct[CTINFO2DIR(ctinfo)].bytes);
> > > > }
> > >
> > > On a 32bit arch the two atomic64 operations require a locked
> > > bus cycle each. The spin_unlock_bh() may not need one - so
> > > the code may now be slower (modulo lock contention etc).
> > >
> > > Probably worth caching &acct[CTINFO2DIR(ctinfo)] in a local,
> > > the compiler probably can't do it itself.
> >
> > You're mistaken.
> >
> > Compile a UP kernel and check yourself before doing such claims.
> >
> >
>
> Oops sorry, I misread your mail, I thought you were speaking of UP
> kernel.
>
I got confused because your argument applies to 64bit platform as well
(two atomic ops instead of one in spin_lock_bh())
As a matter of fact, atomic64_[inc|add]() use two locked operations on
32bit.
Plus this code (atomic64_xxx_cx8()) seems very buggy since 2.6.35
kernels ... Oh well...
--
To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
