Re: Help in DSM design

From: Albert D. Cahalan (acahalan@cs.uml.edu)
Date: Fri Mar 03 2000 - 22:09:37 EST


Richard Gooch writes:
> mauro@alusis.ucb.edu.bo writes:
>> Hi friends!
>>
>> I'm trying to develop a Dristributed Shared Memory sytem(DSM) using
>> Linux. I was wondering myself if using IP for the protocol of the
>> comunicationg nodes were correct?. I thing using IP will add so much
>> bytes to the messages(actually packets) sent by the nodes. Will be
>> better try another lighter protocol?. Could you also point me to
>> other similar projects that are being develop? it will clear my
>> ideas and help me with my problems
>
> Ach! Not another DSM project :-( Don't do it. There's already a DSM
> implementation for Linux,

Obviously this is a feature people want.

> and besides, you're better off with a message-passing interface.
> That way application coders can see how costly operations are.
> Using DSM hides that, resulting in inefficient code.

Message passing can be more costly! On the hardware I develop for,
a "message" involves setting up some DMA control data. Distributed
shared memory has a one-time setup cost, so it is faster for
frequent access to small bits of data.

You could really mess up performance by using a message-passing API
for repeated random access to 8-byte values. Actually, I think the
break-even point is near 2 kB.

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Tue Mar 07 2000 - 21:00:16 EST