Subject: Re: Network speed question...
To: None <erich@wrq.com>
From: Bruce Anderson <brucea@wavefront.com>
List: port-mac68k
Date: 08/05/1998 19:51:00
--Cyberdog-MixedBoundary-000FB9BC
Content-Type: text/enriched; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

On Wed, Aug 5, 1998 12:14 PM, 
--Cyberdog-MixedBoundary-000FB9BC
Content-Type: application/X-url
Content-Transfer-Encoding: base64
Content-Description: erich@wrq.com

bWFpbHRvOmVyaWNoQHdycS5jb20=
--Cyberdog-MixedBoundary-000FB9BC
Content-Type: text/enriched; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

 wrote:

<SMALLER><X-FONTSIZE><PARAM>10</PARAM><FIXED><FONTFAMILY><PARAM>Monaco<=
/PARAM>>  I was just pinging around the local subnet and discovered
that the 

>      return times for each of the machines on the net was radically 

>      different.  This wasn't a huge surprise since the hardware is
all 

>      radically different.  It did get me wondering though.

>      

>      Ping from Pentium 100 Linux Box w/ISA 10BaseT NIC

>      

>      yielded response times from:

>      Pentium 200 w/PCI 10/100BaseT NIC (Win95)               of
~1.8ms

>      PPC7100 w/internal AAUI (MacOS 8.1)                     of
~2.2ms 

>      Mac IIcx w/10BaseT Nubus NIC  (MacBSD June-ish vintage) of
~6.8ms


	  That is exactly what you should get. 

       IIci 25Mhz 030   w/MacCon NuBus-A , 32KB memory (NetBSD 1.3)

       ping from Cyrix233MX -> IIci ~(5.5-6.3)ms

       Max thruput to a Cyrix233MX w/ISA 10BaseT 3COM NIC (NetBSD
1.3.2) 

        ftp> get ghostscript-5.10.tgz

        local: ghostscript-5.10.tgz remote: ghostscript-5.10.tgz

        200 PORT command successful.

        150 Opening BINARY mode data connection for \

        'ghostscript-5.10.tgz' (3594574 bytes).

        100%   3510 KB    00:00 ETA

        226 Transfer complete.

        3594574 bytes received in 11.75 seconds (298.83 KB/s)

        ftp> quit

        It should handle 200 KB/s 


>      All cable lengths are the same and all are connected to the
same hub.

>      

>      Does this slower response to a simple (simple-minded?) network
test 

>      imply that using it as IPNAT firewall would slow routing
through the 

>      cable modem?  The comparison is the Linux box which is doing
really 

>      well with IP Masq while carrying a full load. Would the MacBSD
box 

>      just be over-whelemed/under-used/just-right?

>      

>      Any thoughts?

</FONTFAMILY></FIXED></X-FONTSIZE></SMALLER>>
<SMALLER><X-FONTSIZE><PARAM>10</PARAM><FIXED><FONTFAMILY><PARAM>Monaco<=
/PARAM>     Eric Holcomb

</FONTFAMILY></FIXED></X-FONTSIZE></SMALLER>>
<SMALLER><X-FONTSIZE><PARAM>10</PARAM><FIXED><FONTFAMILY><PARAM>Monaco<=
/PARAM>

</FONTFAMILY></FIXED></X-FONTSIZE></SMALLER>> 


 

----------------------------------------------------------------

This message was created and sent using the Cyberdog Mail System

----------------------------------------------------------------


--Cyberdog-MixedBoundary-000FB9BC--