Date: Tue, 17 Feb 1998 02:54:43 -0800 From: brian@worldcontrol.com To: freebsd-current@FreeBSD.ORG Subject: softupdates4 ruins performance of my wide drive 8-) Message-ID: <19980217025443.51503@top.worldcontrol.com>
next in thread | raw e-mail | index | archive | help
softupdates4 + ***********
SMP 2xPP150 w/64MB
Adaptec 2940W with
options AHC_TAGENABLE
options AHC_SCBPAGING_ENABLE
options AHC_ALLOW_MEMIO
SEAGATE ST43400N 5400rpm SCSI2-FAST avg(r/w)seek 10/11ms
(8 bit interface drive, tag enabled)
(-j)
build1-4 7840.03 real 6474.63 user 4048.94 sys 1.3422 130.66
build2-4 7898.67 real 6468.78 user 4070.07 sys 1.3342 131.64
build3-8 7959.24 real 6497.00 user 4085.74 sys 1.3297 132.65
build4-2 8787.30 real 6389.92 user 3846.45 sys 1.1649 146.46
SEAGATE ST15150W 7200rpm SCSI2-FAST-WIDE avg(r/w)seek 8/9ms
(16 bit interface drive, tag enabled)
build1-4 7479.70 real 6462.32 user 4061.98 sys 1.4070 124.66
So all the extra expense of the wide controller and wide drive bought
me 6 minutes or a 4.5% improvement.
Can't wait to upgrade to ultra-wide or ultra2-wide! or fire-wire! 8-)
(satire impaired readers: it is likely that the softupdates are removing
the drive as the bottlenecking factor, or at least reducing the
influence of the drives in the overall performance, which is actually
quite cool. I guess it is time to get out the old klunkers and put
them back online. 8-) )
(in all tests above the drive specified was SCSI ID 0 in the same
system and was the only drive. One drive was pax'ed from the other
so they contained the identical data. Though not necessarily
distributed around the drive the same. Also, the ST43400N is
a 2GB drive while the ST15150W is a 4GB drive.)
--
Brian Litzinger <brian@worldcontrol.com>
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-current" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?19980217025443.51503>