I got a debug patch from Manfred Spraul to debug slab.c. With this patch
the machine ran for about 3 hours. No problem. I looked into slab.c and had an
idea. What about just one CPU. So I built a new Kernel with just one CPU.
Result: 1 CPU 1 Minute - 2 CPU 20 Minutes. I aspected a different result.
In my opinion the whole thing has something to do with slab, SMP and threads.
The machine (450Mhz PII, 448 MB, Intel L440GX Mainboard, Adaptec) it self is solid.
It has run every 2.3.x and 2.4.x Kernel, Oracle and Sybase (only development).
No problem.
.
Regards
Hartmut
-
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/