On 5 Apr 2005, at 20:53, Jeffrey Buell wrote:
> I installed FC4 test1 and xen0 straight from Fedora and ran
some simple
> kernel microbenchmarks (loops over getpid, fork/wait, signal, etc.)
> and the
> results are pretty ugly compared to a 2.6.1 install. FC4
ranges from
> 1.5X to
> 20X slower, while xen0 is about 2X to 6X slower. Is this
expected? I'm
> looking for configuration differences now, but I'm wondering if
> anybody can
> comment on how FC4 and xen0 were built. debug? asserts? One
difference
> between FC4 and xen0 is that FC4 was configured with
HIGHMEM and xen0
> wasn't.
Did you moved /lib/tls to /lib/tls.disabled?
Yes. Also, xen0 is configured with SMP and FC4 wasn't. My 2.6.1 has neither
SMP or HIGHMEM, but these things shouldn't have that much effect, or could
they?
Jeff