What's new on adaptex

[Piercarlo Grandi]

In article <25c97303:579.6comp.unix.xenix;1 at nstar.UUCP> larry at nstar.UUCP (Larry Snyder) writes:

   >So ESDI users should not feel like they missed a great opportunity by not
   >starting off with SCSI. I agree that SCSI may be better from a conceptual

   I agree 100%.  Many times I've seen ESDI subsystems exceed throughput of
   SCSI ones.

I agree 70%. :-)

Throughput in sequential reads from the disc is not the only measure, and
there are funny consequences.

Latency may be important; a multithreaded SCSI controller with
two drives can overlap seeks and transfers.

Random access may be important, for example for directory tree
scans, databases. Read ahead may slow down random accesses.

Writing may be important, even if reading is prevalent. Track buffering,
nairvely implemented, may slow down writes.

I/O thru the filesystem may be important, actually is, usually. There
are already wide variations between buffered and raw disc accesses; file
system accesses have a different profile again.

SCSI is more sophisticated, and will keep better performance is less
favourable conditions. MSDOS, single user UNIX, editing and
compiles, tend not to exploit the advantages of SCSI.
--
Piercarlo "Peter" Grandi           | ARPA: pcg%cs.aber.ac.uk at nsfnet-relay.ac.uk
Dept of CS, UCW Aberystwyth        | UUCP: ...!mcvax!ukc!aber-cs!pcg
Penglais, Aberystwyth SY23 3BZ, UK | INET: pcg at cs.aber.ac.uk