>>> There just isn't a 1e4 factor difference between paging and overlays,
>>> I'd be surprised if you get more than a factor of 2.
>>
>> You can do very well. Start your IO early and asynchronously, so that it
>> completes just as you need the code/data. The OS can not predict this.
>
> Then you have the RAM and don't need the overlay.
No you don't. Say you need 1000 units of memory (any unit you like).
There are 100 units of real memory. While leaving 30 to run in,
start to load the next 70 that will be needed.
We would do this if we really cared about performance. Obviously most
of us are willing to give up some performance for ease of hacking.
Distributed memory has the same kind of tradeoff, and people should
make that tradeoff based on their own priorities. It is just cruel
to force everyone to write software the same way.
The argument against distributed memory goes like this:
1. you won't get maximum performance
2. therefore, you are wrong, lazy, stupid, ignorant, etc.
I could apply that to LISP. Let's ban LISP because it sucks. :-)
We should ban shell scripts, perl, and Java too. The binfmt_script
support does not belong in the kernel. It only encourages bad code.
-
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/