> Within the next year, we'll have networked computer chips that
> use 1-4 Gbit per second serial links between them. Imagine
> a SIMM/DIMM kind of thing holding 8 CPU chips each with 64 MB on die
> ...plug in as many as you like on your motherboard. The interconnect
> protocol uses DSM so it looks like an SMP.
Which is exactly why itd be good to start work now. Nearby is a lab w/
100Mbit ethernet and Giga-Ethernet. Both are very fast, and aside from
using a Paragon backplane, the Giga is about as fast as it gets. This is
*now* in 5 years Giga Ether will be consumer product. Imagine a 16-node
Dual P-II Linux cluster on a switched full-duplex gigabit network...
Right now pretty spendy (if you forgive the fact that there isn't free
clustering in the kernel) but it *is* possible. Flash forward five years
when the P-II can be bought at a garage sale and a Gigabit Ether switch
would cost $50.
Heck even if this view is off and skewed to heck, *it is possible*. And
things are getting faster, it's only a matter of time before networking
is fast enough (or integrated enough) that clustering such as this would
be possible.
Think ahead, think outside of the computer and equipment you have/can get
now.... That's what you need to do. When you can do that you can
realise that startinga project for this isn't such a stupid idea. If we
get rock-solid clustering on top of the existing network layer it'll only
be a matter of time before the world catches on to the possibilities of
this.
But if it's going to be done, it *must* be done *right*. While the
kernel may have started out as a college CS project, Linus did it
*right*. If he hadn't it wouldda died. I say we keep doing things
right, look ahead a bit. In a few years clustering a large amount of
pentium class machines could be cheap, and it could blow away even the
biggest and baddest SuperComputers....
[end of rabbit track rant]
What is being talked about, having CPUs connected to the I/O fabric
(NexGenIO, I2O, whatever it may be) is not that far ahead in the future.
If we've got a kernel that could be dumped on an eeprom (hey they can
easily store 8MB now) and booted from these cpu cards and they could then
self register with the host machine (or whatever) -- it be instant CPU
upgrade, no changes, just add more horsepower!!!
Just remember, the world has its eyes on Linux. If we make a move in a
certain direction *someone will notice*. And when people notice, they
react.
Think.
-- Michael Loftis
- 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/