home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.sys.ibm.pc.hardware
- Path: sparky!uunet!spool.mu.edu!caen!zaphod.mps.ohio-state.edu!cs.utexas.edu!csc.ti.com!tilde.csc.ti.com!mksol!mccall
- From: mccall@mksol.dseg.ti.com (fred j mccall 575-3539)
- Subject: Re: Local bus IDE or SCSI?
- Message-ID: <1992Dec11.201540.9903@mksol.dseg.ti.com>
- Organization: Texas Instruments Inc
- References: <matess.723242527@gsusgi1.gsu.edu> <aLH6uB3w165w@hale.cts.com> <1992Dec3.232234.14704@mksol.dseg.ti.com> <CARL.92Dec7114825@atlantis.Cayman.COM>
- Date: Fri, 11 Dec 1992 20:15:40 GMT
- Lines: 29
-
- In <CARL.92Dec7114825@atlantis.Cayman.COM> carl@Cayman.COM (Carl Heinzl) writes:
-
-
- >>Oh, I don't know. IDE seems to make more sense for a VL slot. Why
- >>have a SCSI controller plugged into a VL slot that it can't possibly
- >>use the bandwidth of?
-
- >Everyone seems to be forgetting about caching controllers. If you
- >have a controller sitting out there with 4 meg, 8 meg (or even more)
- >then it can certainly go quite a bit faster than any SCSI II
- >limitation. In fact, I'd bet that it can probably go just about as
- >fast as main memory (since it uses exactly the same type of memory!).
-
- Assuming, of course, that you're getting cache hits with the
- controller. Under most multitasking OS's, it's a lot harder to get
- those cache hits because multiple stuff is running at once. The head
- tends to get to bounce around the drive, and the cache tends to get to
- read stuff over and over, just as if the cache is not there. The
- caching built into the file systems of multitasking OS's tends to be a
- better win than a caching controller, and a caching controller may
- actually slow you down.
-
-
-
- --
- "Insisting on perfect safety is for people who don't have the balls to live
- in the real world." -- Mary Shafer, NASA Ames Dryden
- ------------------------------------------------------------------------------
- Fred.McCall@dseg.ti.com - I don't speak for others and they don't speak for me.
-