home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!olivea!xenitec!zswamp!geoff
- From: geoff@zswamp.UUCP (Geoffrey Welsh)
- Newsgroups: biz.sco.general
- Subject: Re: Performance issues revisited
- Message-ID: <FwX8VB13w165w@zswamp.UUCP>
- Date: 23 Dec 92 04:49:02 GMT
- References: <9212221815.aa19372@scoke.sco.COM>
- Organization: Izot's Swamp
- Lines: 19
-
- Bela Lubkin <belal@sco.COM> writes:
-
- > Real conclusions: you'd better run some extensive tests like this before
- > you can even begin to understand the transfer rate characteristics of
- > your disk & CPU combination -- and that's only one small part of
- > characterizing the overall performance of your disk subsystem.
-
- Hmm, might that test be affected by fragmentation of available space? If
- so, it would explain why the track buffer (which is only sensible controller
- design: since, on average, it takes only slightly more than twice as long to
- read a whole track as it would take to wait for and read a single sector, why
- not?) is not having the desired effect.
-
- Geoffrey Welsh, 7 Strath Humber Court, Islington, Ontario, M9A 4C8 Canada
- geoff@zswamp.uucp, [xenitec.on.ca|m2xenix.psg.com]!zswamp!geoff (416)258-8467
- Now I've lost everything, I give to you my soul
- And the meaning of all that I believed before escapes me
- In this world of none, no thing, and no one
- - Genesis, _Afterglow_
-