I'm currently looking at a slightly changed scheduler
design where p->counter and the actual task priority
(which is mainly used for task latency anyway) are
separated and we can get rid of the large recalculation
of all processes' priorities alltogether.
I think this might be worthwhile because the large
recalculation holds the tasklist_lock for a _long_
time, blocking the other CPU's access to the runqueue.
If we smeared out this overhead by adding a new variable
to the task_struct and can simplify goodness() at the
same time, would that be worth it? -- especially when we
take SMP scalability into account...
cheers,
Rik -- Open Source: you deserve to be in control of your data.
+-------------------------------------------------------------------+
| Le Reseau netwerksystemen BV: http://www.reseau.nl/ |
| Linux Memory Management site: http://humbolt.geo.uu.nl/Linux-MM/ |
| Nederlandse Linux documentatie: http://www.nl.linux.org/ |
+-------------------------------------------------------------------+
-
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/