On Mon, 9 Oct 2000, Rik van Riel wrote:
> In that case the time the process has been running and the
> CPU time used will save the process if it's been running for
> a long time.
'importance' is not something we can measure reliably within the kernel.
And assuming that a niced, not long-running process is unimportant misses
the bus as well. What if i just started an important simulation before
going to vacation for two weeks?
> would you really care if a simulation would be killed after
> 5 minutes? [...]
yes, i would. I would probably end up not using nice values. Please, Rik,
dont penalize an unrelated kernel feature!
> [...] The objective is to destroy the least amount of work, which
> means giving a bonus to processes which have used a lot of CPU time
> already ... regardless of nice value.
your OOM code does not follow this objective:
+ /*
+ * Niced processes are most likely less important, so double
+ * their badness points.
+ */
+ if (p->nice > 0)
+ points *= 2;
Niced processes *can be just as important*.
> If you have a better algorithm, feel free to send patches.
yes. Please remove the above part.
Ingo
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Sun Oct 15 2000 - 21:00:12 EST