Newsgroups: comp.os.mach
Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!mstar!mstar.morningstar.com!bob
From: bob@MorningStar.Com (Bob Sutterfield)
Subject: Re: Mach RPC Throughput...
In-Reply-To: ast@cs.vu.nl's message of 15 Mar 91 20:43:27 GMT
Message-ID: <BOB.91Mar18130146@volitans.MorningStar.Com>
Sender: usenet@MorningStar.COM (USENET Administrator)
Reply-To: bob@MorningStar.Com (Bob Sutterfield)
Organization: Morning Star Technologies
References: <MORSE.91Mar14091659@quark.mpr.ca> <9332@star.cs.vu.nl>
Distribution: comp
Date: Mon, 18 Mar 91 18:01:53 GMT
Lines: 16

In article <9332@star.cs.vu.nl> ast@cs.vu.nl (Andy Tanenbaum) writes:
   The protocol used [by Amoeba] on the Ethernet ... is not IP ...
   The loss of performance when going through the TCP/IP server is not
   so important because usually the TCP connections go over a
   narrow-band wide-area link anyway, so there is no way to get
   high-performance no matter what.  In essence, we have chosen to
   optimize the local case, and accepted worse performance when one
   specifically wishes to speak TCP/IP.

What about when the non-"local" case involves RPC with a machine on a
different Ethernet in the next room, accessible via a high-bandwidth
IP router?  IP is useful in environments other than wide area
networks.  Local distributed computing environments might involve
multiple networks connected by routers, rather than bridges or
repeaters, and it seems that you're designing in a penalty for Amoeba
users whose clusters grow too big for one Ethernet.
