Skip to contentSkip to conversation

Use of AI for process scheduling

DISCUSSION Jeff Sipek 1 participant 1 message Sep 8, 2003

lore
Share & tools
lore

Jeff Sipek

author
#0 lore raw

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

Quoted 8 lines · you

Well, we have this to deal with: Someone is exercising the scheduler and notices some kind of misscheduling which causes the system to crawl.

How are they going to get to the /proc and /sys directories to do much of anything? The system is completely unresponsive. Furthermore, even if the system IS responsive, we need some way to for the user to hit a key and freeze the current state for examination. Some slow-downs last only seconds, but we need to be able to catch them.

Agreed.

Quoted 7 lines

You talk about weights. Would the linux community be willing to put a neural net into the kernel? I'm sure we could optimize it to not take a lot of processing overhead, but it's an "unknown". It would be scary to some people to be unable to disect the actual workings of it and have no way of determining corner-case behavior from examining code. But if we have, say, only a 2-layer neural net, we might still be able to reverse-engineer it.

I meant weights in a more general way - variables in calculations is more appropriate. Neural nets can do a lot of interesting things, but they really need optimization. If we were to use them, we should make it a config option in the kernel (nnet or standard scheduler.)

Jeff.

- --
Trust me, you don't want me doing _anything_ first thing in the morning.
- Linus Torvalds
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.3 (GNU/Linux)

iD8DBQE/XRRHwFP0+seVj/4RAs3KAJ9IISM5bALaOTCJtSWxPDlHxOGVEwCfedgD bCPO9/Mf1dtmA4zVgGP2Tcc=
=vrNw
-----END PGP SIGNATURE-----