[rescue] u2 drive trays

Jonathan C. Patschke jp at celestrion.net
Tue Aug 19 11:58:28 CDT 2003


On Tue, 19 Aug 2003, Curtis H. Wilbar Jr. wrote:

> OK.... but how is this different from FDDI.... if I have two FDDI
> clients trying to throttle one FDDI server... that is still only
> 100Mbit of bandwidth at the server, and aggregated 200Mbit of clients...
>
> So how does it differ ?

The clients don't have to fight for fair time at the fabric level.  This
is built into the FDDI protocol and is a large portion of why Ethernet
doesn't reach a full 100Mbit in most real-world situations.

To put it another way, FDDI guarantees that each node will have time to
speak.  Ethernet makes the switch deal with it.

> Other than MTU, I don't see a big difference between 100baseTX switched
> and FDDI...  in the example you cite, how is FDDI going to do any better
> than switched 100baseTX (other than an improved MTU) ?

If you're using NFS, SMB, AFS, AFP, or some other distributed
filesystem, that increased MTU is enough.

As soon as I get the DEFPA drivers working on OpenBSD/sparc64, I'll post
benchmarks for some fairly common scenarios.

-- 
Jonathan Patschke   )  "We're Texans.  We figure out ways to do these
Elgin, TX          (    things..."                    --Bill Bradford



More information about the rescue mailing list