Path: utzoo!mnetor!uunet!ncc!alberta!access!edm!rroot
From: rroot@edm.UUCP (uucp)
Newsgroups: comp.dcom.modems
Subject: Re: Merits of compression (was Re: hayes 9600 vs. trailblazer)
Message-ID: <261@edm.UUCP>
Date: 19 Apr 88 03:29:05 GMT
References: <1441@pt.cs.cmu.edu>
Organization: Unexsys Systems, Edmonton,AB.
Lines: 24

From article <1441@pt.cs.cmu.edu>, by tgl@ZOG.CS.CMU.EDU (Tom Lane):
> In article <4435@hoptoad.uucp>, gnu@hoptoad.uucp (John Gilmore) writes:
>> It's sad but true that the bottleneck in sending ASCII data between
>> systems through a Telebit modem is getting to be the 19200 max speed on
>> the serial cable.  Telebit really should support 38,400 baud.

> The way I understand it, the problem is that the serial drivers don't *have*
> an inner loop; they're interrupt-per-character, and the context swap into
> the kernel, for each byte, is what kills you.  Since most serial interfaces
Note that only applies for MOST systems.  There are, in fact some that can
handle block I/O. I believe the some of the Convergent I/O boards fit 
in this category, since I have seen the box I'm on sustain a baud rate
in the high 8000's running UUCP at 9600 baud. (I've never seen it run
at 19200, though).
  If the processor is set up for DMA, then having the modem do the 
compression SHOULD be a win. I think that would be the case here.
  PC-type boxes/boards, because they aren't generally designed for 
heavy multi-user work are more likely to have real problems with I/O
interrupts.
-- 
-------------
 Stephen Samuel 
  {ihnp4,ubc-vision,vax135}!alberta!edm!steve
  or userzxcv@uqv-mts.bitnet