[Devel] cgroup, RT reservation per core(s)?
Rolando Martins
rolando.martins at gmail.com
Tue Feb 10 02:45:40 PST 2009
Hi,
I would like to have in a quad-core, 1 core totally (100%) dedicated
to RT tasks (SCHED_RR and SCHED_FIFO) and the other 3 cores with
normal behavior, better said, allowing SCHED_OTHER & SCHED_FIFO &
SCHED_RR tasks but still with a RT reservation. Follows an example:
# Setup first domain (cpu 0,1,2)
echo 0-2 > /dev/cgroup/0/cpuset.cpus
echo 0 > /dev/cgroup/0/cpuset.mems
# Setup RT bandwidth for firstdomain (80% for RT, 20% others)
echo 1000000 > /dev/cgroup/0/cpu.rt_period_us
echo 800000 > /dev/cgroup/0/cpu.rt_runtime_us
# Setup second domain (cpu 3)
mkdir /dev/cgroup/1
echo 3 > /dev/cgroup/1/cpuset.cpus
echo 0 > /dev/cgroup/1/cpuset.mems
# Setup RT bandwidth for second domain (100% for RT)
echo 1000000 > /dev/cgroup/1/cpu.rt_period_us
echo 1000000 > /dev/cgroup/1/cpu.rt_runtime_us
# Setup RT bandwidth for third domain
echo 1000000 > /dev/cgroup/1/0/cpu.rt_period_us
echo 500000 > /dev/cgroup/1/0/cpu.rt_runtime_us
# Setup RT bandwidth for fourth domain
echo 1000000 > /dev/cgroup/1/1/cpu.rt_period_us
echo 500000 > /dev/cgroup/1/1/cpu.rt_runtime_us
root
----|----
| |
(80% rt, 20% others 0 1 (100% rt @ core 3)
@ cores 1,2,3) ------
| |
0 1 (50% rt for
each group @ core 3)
Is there anyway for doing this?
Or must we have a separate /proc/sys/kernel/sched_rt_runtime_us &
/proc/sys/kernel/sched_rt_period_us for each core/cpu?
In this case:
/proc/sys/kernel/sched_rt_runtime_us_0
/proc/sys/kernel/sched_rt_period_us_0
...
/proc/sys/kernel/sched_rt_runtime_us_n (n, cpu count)
/proc/sys/kernel/sched_rt_period_us_n
Thanks,
Rol
_______________________________________________
Containers mailing list
Containers at lists.linux-foundation.org
https://lists.linux-foundation.org/mailman/listinfo/containers
More information about the Devel
mailing list