Re: [PATCH 21/22] /dev/random: kill batching of entropy mixing

[Matt Mackall]

On Sat, Mar 27, 2004 at 01:52:45PM +0000, Jamie Lokier wrote:
> Matt Mackall wrote:
> > Rather than batching up entropy samples, resulting in longer lock hold
> > times when we actually process the samples, mix in samples
> > immediately. The trickle code should eliminate almost all the
> > additional interrupt-time overhead this would otherwise incur, with or
> > without locking.
> 
> What do you mean by "the trickle code"?  I didn't see anything in your
> patch set which makes the interrupt-time overhead faster.

This code which is in the existing driver to prevent pathological lock
contention on large SMP:

        /* if over the trickle threshold, use only 1 in 4096 samples
	*/
        if ( input_pool.entropy_count > trickle_thresh &&
             (__get_cpu_var(trickle_count)++ & 0xfff))
                return;

-- 
Matt Mackall : http://www.selenic.com : Linux development and consulting
-
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/