I am not sure what module problem you are talking about. There was a
bug in my original patch that caused a link error in most situations
where CONFIG_MODULE was set, but this had to do with
atomic_dec_and_lock, not preempt_xxx -- what preempt_xxx symbols?
Anyhow, I suggest you grab 2.4.9-ac10 and
http://tech9.net/rml/linux/patch-rml-2.4.9-ac10-preempt-kernel-1 and
enable CONFIG_PREEMPT and give that a whirl. You should have no
problems on a UP system.
> Aside from that I saw some nice speed increase (UP Athlon) and very snappy
> system.
Very glad. Especially to hear there are no problems on Athlon.
> dbench-1.1 32 clients load drops to mostly below 16 (33 before)
Great. Data points such as this are welcome. What about the actual
throughput? Both I and Nigel (see http://kpreempt.sourceforge.net)
benched the patch with `dbench -16' and we both got decent throughput
increase.
> Go on with your great work!
Thanks.
-- Robert M. Love rml at ufl.edu rml at tech9.net- 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/