Re: Odd sched behaviour; It takes 5 threads or more to load 2 CPU cores during kernel build

On 2/28/06, Christian <christiand59@xxxxxx> wrote:
Am Dienstag, 28. Februar 2006 20:59 schrieb Jesper Juhl:
[snip]

Do we have a scheduler problem?
An io-scheduler problem?

I'm not really into this, but what happens if you simply start 5 different
kernel-builds in parallel? I think if it makes a difference then this would
mean that there's something wrong with make and you could eliminate the first
two possibilities?!


Well, no need for 5 kernel builds in that case.
If I clone my source tree and then simply run
$ make distclean ; make allnoconfig ; nice make
in each directory in two different shells at the same time, then both
cores get fully loaded.


Is it "make" that's being difficult?
Is it something in the kernels Makefile that causes the build to
behave this way?
Could it be a bottleneck in my system somewhere?

Anyone got a clue?



--
Jesper Juhl <jesper.juhl@xxxxxxxxx>
Don't top-post http://www.catb.org/~esr/jargon/html/T/top-post.html
Plain text mails only, please http://www.expita.com/nomime.html
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/