benchmarking SCSI host adapters

[Heiko Blume]

chip at chinacat.Unicom.COM (Chip Rosenthal) writes:
>My questions are twofold:  (1) has anybody looked at the BusTek adapter
>critically, and what results did you obtain, and (2) how useful is "bonnie"
>for disk system benchmarking?

re (1): never heard of :-)
re (2):
well, it says it's for file*system* benchmarking, but hardware is a issue
too, of course. here's what i get with ISC 2.2, 1542A and 638MB Imprimis:

              -------Sequential Output-------- ---Sequential Input-- --Random--
              -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
Machine    MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU  /sec %CPU
386/33     80   243 91.8   351 28.4   396 65.6   216 97.6   742 62.6  17.3 14.4

it should be noted that the throughput of data is influenced by DMA rate 
etc, but the (l)seeks/sec are not (unless you have a 3 second average seek
drive :-) given three processes that seek on the same file. does someone
know why this is so?
-- 
      Heiko Blume <-+-> src at scuzzy.in-berlin.de <-+-> (+49 30) 691 88 93
                    public source archive [HST V.42bis]:
        scuzzy Any ACU,f 38400 6919520 gin:--gin: nuucp sword: nuucp
                 uucp scuzzy!/src/README /your/home