Re: [PATCH 1/8] drivers/random: Cache align ip_random better

[Matt Mackall]

On Wed, 2011-03-16 at 20:26 +0100, Eric Dumazet wrote:
> > I think this alignment exists to minimize the number of cacheline
> > bounces on SMP as this can be a pretty hot structure in the network
> > stack. It could probably benefit from a per-cpu treatment.
> > 
> 
> Well, this is a mostly read area of memory, dirtied every 5 minutes.
> 
> Compare this to 'jiffies' for example ;)
> 
> What could be done is to embed 'ip_cnt' inside ip_keydata[0] for
> example, to avoid wasting a cache line for one bit ;)
> 
> 
> c1606c40 b ip_cnt
> <hole>
> c1606c80 b ip_keydata

Yeah. I actually think we're due for rethinking this entire process. It
dates back to when we introduced syncookies in the 90s and it shows. The
fact that we've started abusing it for other things doesn't help.

-- 
Mathematics is the supreme nostalgia of our time.


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/