> BINGO! Running 2.5.2-pre8 with the scheduler changes backed out made
> all the difference! Interactive responsiveness is much improved and
> performance in the above two tests I ran is back to 2.4.18pre1 levels.
>
> With 2.5.2-pre8 vanilla the 486 is getting large variation in Test 2
> above (157s, 237s, 292s), but is never even close to 2.2/2.4 levels.
This means, it's the same problem.
I also tried the elevator fixes from Peter Osterlund posted in LKML
yesterday, which did not change anything for me. So it really seems, that
the culprit is the scheduler.
I'm not an expert in that area, so I am a little bit stuck right now. If
anybody has an suggestion, what we can investigate next (like backing out
only parts of the scheduler patch or place some strategic printf's), I am
willing to try this on my machine.
By the way, I also tried Ingo's scheduler yesterday, which at least didn't
show up with these problems. It even survived some hours of stress
testing.
Regards,
Matze
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/