Date: Sat, 6 Sep 1997 18:31:32 -0700 (PDT) From: Alex <garbanzo@hooked.net> To: current@freebsd.org Subject: Re: lousy disk perf. under cpu load (was IDE vs SCSI) Message-ID: <Pine.BSF.3.96.970906181504.17575D-100000@zippy.dyn.ml.org> In-Reply-To: <199709061909.VAA25891@kairos>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sat, 6 Sep 1997, Mats Lofkvist wrote: > For fun I tested the dd benchmark on my new machine (intel providence > board with pp200, 64M, quantum viking 4.5G uw connected to the aic7880). > > As long as I run the dd with the machine idle, I get over 10MB/s. > But with a single cpu-bound process running, the throughput drops > to less than 1.5MB/s with 64k blocks (and it gets even worse with > smaller blocks). > > I tested with a few different block sizes, and it seems like dd > never reads more than 20 records per second. Isn't the scheduler > run when an io request returns? If not, shouldn't it ?-) > > This behaviour kills any advantage with scsi over eide since as > soon as you start using all the cpu cycles not needed to talk to > the disk, disk performance goes down the drain :-( > > I'm running 2.2.2 so I know this is the wrong list, but is current > any different? I'm running a P166/64mb Ram/7880 (Ultra Wide), Quantum Fireball 3.2gb (Ultra not Wide), and a Quantum Lightning 740 (Fast SCSI-2). The Fireball is my main drive, and the Lightning has the /usr/home and /mnt/dos0 partitons. Make world involved running make world and waiting for the cleanup stuff and the depend stuff to finish, and then starting dd. I had previously ran x and the Bovine rc5 client, but that made a minimal differnce. The Lightning is drive #2 (id 1), and in actual use is much slower *shrug*. #rsd0 no load no x 800+0 records in 800+0 records out 52428800 bytes transferred in 18.281164 secs (2867914 bytes/sec) #rsd1 no load no x 800+0 records in 800+0 records out 52428800 bytes transferred in 14.177823 secs (3697944 bytes/sec) #rsd0 make world no x 800+0 records in 800+0 records out 52428800 bytes transferred in 25.763400 secs (2035011 bytes/sec) #rsd1 make world no x 800+0 records in 800+0 records out 52428800 bytes transferred in 14.324715 secs (3660024 bytes/sec) - alex
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSF.3.96.970906181504.17575D-100000>