Xref: utzoo comp.unix.xenix:2047 comp.unix.microport:518
Path: utzoo!mnetor!uunet!husc6!bloom-beacon!mit-eddie!uw-beaver!tektronix!reed!omen!caf
From: caf@omen.UUCP (Chuck Forsberg WA7KGX)
Newsgroups: comp.unix.xenix,comp.unix.microport
Subject: Re: Do we need a serial I/O benchmark (BAUDSTONE)?
Message-ID: <665@omen.UUCP>
Date: 18 Apr 88 22:15:05 GMT
References: <1974@ubc-cs.UUCP> <661@omen.UUCP> <2063@ubc-cs.UUCP>
Reply-To: caf@omen.UUCP (Chuck Forsberg WA7KGX)
Organization: Omen Technology Inc, Portland Oregon
Lines: 13
Keywords: rs232 serial data communications benchmark

In article <2063@ubc-cs.UUCP> pajari@grads.cs.ubc.ca (George Pajari) writes:
:In <661@omen.UUCP>, caf@omen.UUCP (Chuck Forsberg WA7KGX) writes:
:
:> A loopback configuration is next to useless for predicting the
:> ability of a system to receive data at speed from external
:> sources (other computers).
:
:I don't agree.

An ex-boss of mine didn't agree either, and bought a system based on
loopback tests, only to discover the real world performance was as I had
feared.  I loopback test does not necessarily detect throughput
bottlenecks caused by interrupt latency from critical regions.