On Wed, Aug 30, 2000 at 05:47:39PM +0200, Jens Axboe wrote:
> On Wed, Aug 30 2000, Marcel J.E. Mol wrote:
> > > .....
> > > do {
> > > q = blk_get_queue(bh->b_rdev);
> > > if (!q) {
> > > ... no such device ..
> > > }
> > > + statistics(q, rw, bh->b_size);
> > > } while (q->make_request_fn(q, rw, bh)));
> > > ...
> >
> > Does this setup also allow to maintain time statistics, like the times between
> > make_request_time, io_start_time and io_end_time so things like queuetime
> > and io servicetime can be determined?
>
> Not right now, because with this setup we are accounting buffers and not
> the requests themselves. If you want that you should look at Stephen's sard
> patches.
But if the sar patches are applied, don't we have double stats? Isn't
it better to somehow combine this and make a clean statistics setup including
what the sar patches offer? I like the Stephen's sard output and think this
should be included in the mainstream kernel.
-Marcel
-- ======-------- Marcel J.E. Mol MESA Consulting B.V. =======--------- ph. +31-(0)6-54724868 P.O. Box 112 =======--------- marcel@mesa.nl 2630 AC Nootdorp __==== www.mesa.nl ---____U_n_i_x______I_n_t_e_r_n_e_t____ The Netherlands ____ They couldn't think of a number, so they gave me a name! -- Rupert Hine- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Thu Aug 31 2000 - 21:00:25 EST