Re: [mm PATCH 4/6] RCU: preemptible RCU

[Andrew Morton]

On Sat, 27 Jan 2007 02:30:17 +0530
Dipankar Sarma <dipankar@xxxxxxxxxx> wrote:

> > > As a consequence of keeping track of RCU readers, the readers
> > > have a slight overhead (optimizations in the paper).
> > > This implementation co-exists with the "classic" RCU
> > > implementations and can be switched to at compiler.
> > 
> > That's yet another question we need to ask people when their kernel dies,
> > and yet another deviation between the kernels which we all test, causing
> > more dilution of testing efforts.  It would be much better if we could
> > remove classic RCU.  You say this would incur extra cost, but the magnitude
> > of that cost is not clear.  Please help us make that decision.
> 
> See the Table 2, page 10 of the paper mentioned above.

argh.

Seems I have to wade through half the paper to understand Table 2.

> There is a
> ~100ns cost per read-side critical section involved in the preemptible
> version of RCU at the moment. Until, we are sure that we don't have
> an impact on common workloads, we need to keep the "classic" 
> implementation around.

Ratios, please..  that 100ns appears to be a 100% increase.  ie 100ns -> 200ns.

There are a couple of ways of working out how much that really matters: a)
run a workload or b) instrument a kernel, work out how many times/sec the
kernel runs rcu_read_lock().  I suspect b) would be more useful and
informative.

Either way, please always prepare such info up-front and summarise in the
changelog?  It's kinda important...
-
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/