There is an "interesting" quality of POWER6 cores, which each have 2
hardware threads: assuming one thread on the core is idle, the primary
thread is a little "faster" than the secondary thread. To illustrate:
for cpumask in 0x1 0x2 ; do
taskset $cpumask /usr/bin/time -f "%e elapsed, %U user, %S sys" \
/bin/sh -c "i=1000000 ; while (( i-- )) ; do : ; done"
done
17.05 elapsed, 16.83 user, 0.22 sys
17.54 elapsed, 17.32 user, 0.22 sys
(The first result is for a primary thread; the second result for a
secondary thread.)
So it would be nice to have the scheduler slightly prefer primary
threads on POWER6 machines. These patches, which allow the
architecture to override the scheduler's CPU "power" calculation, are
one possible approach, but I'm open to others. Please note: these
seemed to have the desired effect on 2.6.25-rc kernels (2-3%
improvement in a kernbench-like make -j <nr_cores>), but I'm not
seeing this improvement with 2.6.26-rc kernels for some reason I am
still trying to track down.
Nathan Lynch (3):
sched: support arch override of sched_group cpu power
add cpu_power to machdep_calls, override SD_SIBLING_INIT
adjust cpu power for secondary threads on POWER6
arch/powerpc/kernel/setup-common.c | 7 ++++++
arch/powerpc/platforms/pseries/setup.c | 37 ++++++++++++++++++++++++++++++++
include/asm-powerpc/cputable.h | 3 +-
include/asm-powerpc/machdep.h | 2 +
include/asm-powerpc/topology.h | 31 ++++++++++++++++++++++++++
include/linux/sched.h | 1 +
kernel/sched.c | 14 ++++++++++++
7 files changed, 94 insertions(+), 1 deletions(-)
_______________________________________________
Linuxppc-dev mailing list
Linuxppc-dev@ozlabs.org
https://ozlabs.org/mailman/listinfo/linuxppc-dev
