Re: Mach RPC Throughput...

Article View: comp.os.mach

Article #864

#864

From: Bill Schilit
Date: Fri, 15 Mar 1991 05:52

35 lines
1692 bytes

Our measurements of Mach RPC show that TCP is the dominant cost when
sending synchronous RPC consisting of a small request and a 4K
response.

On an i386 machine with an AT bus running Mach 2.5 we tried to account
for the measured round trip time of 33ms by computing the cost of
ethernet and bus transfer and separately measuring TCP loopback and
Mach RPC without going over the network.  The results are shown below.

			4K RPC
			------
Packets			7		(observed)
Bytes			4738		(observed)

AT bus (times 2)	9.5 ms		(computed)
Ethernet		3.8 ms		(computed)
TCP Loopback		12  ms		(measured)
Mach IPC (times 2)	4   ms		(measured)
Total		       29.3 ms

Network RPC	       33   ms		(measured)

Breaking the times down with into these four components gets pretty
close to the observed network RPC rate.

These tests are fully described in "Adaptive remote paging for mobile
computing" TR CUCS-004-91, available by anonymous FTP from
cs.columbia.edu::pub/reports.

- Bill
-- 
Bill Schilit
Columbia University Computer Science Department
bill@cs.columbia.edu

Technical Details

Message-ID: <BILL.91Mar14235254@cs.cs.columbia.edu>

Path:

arc1-ca.pugleaf.net!utzoo!news-server.csri.toronto.edu!cs.utexas.edu!swrinde!zaphod.mps.ohio-state.edu!sol.ctr.columbia.edu!cunixf.cc.columbia.edu!cs.columbia.edu!bill

References: <MORSE.91Mar14091659@quark.mpr.ca>

Show Full Headers

Complete Article Headers

Path: arc1-ca.pugleaf.net!utzoo!news-server.csri.toronto.edu!cs.utexas.edu!swrinde!zaphod.mps.ohio-state.edu!sol.ctr.columbia.edu!cunixf.cc.columbia.edu!cs.columbia.edu!bill
From: bill@cs.columbia.edu (Bill Schilit)
Newsgroups: comp.os.mach
Subject: Re: Mach RPC Throughput...
Message-ID: <BILL.91Mar14235254@cs.cs.columbia.edu>
Date: 15 Mar 91 05:52:54 GMT
References: <MORSE.91Mar14091659@quark.mpr.ca>
Sender: bill@cs.columbia.edu (Bill Schilit)
Distribution: comp
Organization: Columbia University Department of Computer Science
Lines: 35
In-Reply-To: morse@quark.mpr.ca's message of 14 Mar 91 14:16:59 GMT

Reply to Parent Message