Re: Larger Blocks?

Edwin Foo (efoo@mit.edu)
Sat, 10 May 1997 13:42:49 -0400


At 01:23 PM 5/10/97, Ronald Van Iwaarden wrote:
>Shouldn't this reduce the load on the server considerably as well?
>With twice as large of blocks, each machine now polls the server only
>half as often. While the load won't go down by a half, it should be
>reduced considerably.

This makes a lot of sense and is probably the most likely answer. I doubt
you can really "run out" of 2^29 blocks, seeing as how we've only searched
a little over 4% of the keyspace. :)

>BTW, I think it says quite a bit about Rockne's forsight when you
>notice that DESChal is only requiring an old rickety 486/66 for a
>server when Solnet is requiring 4 servers just to keep up. Go
>DESChal!!!!
>

Hey, who's calling 486s "old" and "rickety"?!??! I like my 386-40 just fine
the way it is, thank you. With 32 megs of RAM and Linux, it still fools
people who log in on it into asking me if I finally got a new computer. =)

On a side note, it looks like MIT is getting beaten by schools whose IS
departments have somewhat endorsed DESCHALL. That's too bad; I had dreams
of staying at 2nd place for a while... I think we're doing a good job
considering we are using only our own dorm machines and a few machines in
various labs we work in on campus. If we could only bring all our Sparc 5s
and SGIs in the clusters to bear...

-Edwin

------------------------------------------------------------------------
The FooBunny | MIT Computer Science '98 - Systems and Architecture
efoo@mit.edu | DEC Cambridge Research Lab - Parallel Computing Group
(617) 225-8837 | Residential Computing Consultant (RCC) - New House

"Love must be sincere; Hate what is evil; cling to what is good."
- Romans 12:9 <><
------------------------------------------------------------------------