> This is with an i810 chipset and a Maxtor DiamondMax Plus 40. This
> drive has made me really rethink IDE vs. SCSI. It blows away our
here's that disk with a more traditional (and believable) benchmark,
bonnie (dual cel/550 BP6, 128M ram, 2.3.99-pre9-1, HPT, udma66):
-------Sequential Output-------- ---Sequential Input-- --Random--
-Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU
384 22004 95.4 33295 38.8 11500 15.3 12128 38.6 29432 25.4 162.7 1.1
384 21569 95.9 33927 40.6 11578 15.7 12207 39.3 29454 26.0 165.5 1.3
384 21370 95.8 33694 34.5 11384 14.4 12024 39.1 29366 24.3 172.3 1.4
384 21676 96.6 33927 32.5 11467 13.4 12043 38.2 29366 25.2 168.0 0.8
384 22103 96.6 33636 34.1 11228 15.0 12017 37.9 29213 26.3 174.4 1.2
384 22065 97.4 33182 40.5 11484 14.7 12423 39.0 29235 24.5 167.2 1.1
as usual, ignore the per-char and %cpu columns, since the first is
just measuring libc and the latter is overestimated by about 8x.
I have no idea what the point of parallel hdparm's is.
regards, mark hahn.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Tue May 23 2000 - 21:00:17 EST