Re: [RFT][patch 17/18] sched: use jump labels to reduce overhead when bandwidth control is inactive

[Paul Turner <pjt@google.com>]

> --- a/kernel/Makefile
> +++ b/kernel/Makefile
> @@ -10,7 +10,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
>            kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
>            hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
>            notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
> -           async.o range.o jump_label.o
> +           async.o range.o
>  obj-y += groups.o
>
>  ifdef CONFIG_FUNCTION_TRACER
> @@ -107,6 +107,7 @@ obj-$(CONFIG_PERF_EVENTS) += events/
>  obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o
>  obj-$(CONFIG_PADATA) += padata.o
>  obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
> +obj-$(CONFIG_JUMP_LABEL) += jump_label.o
>
>  ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
>  # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
>

Tested-by: Paul Turner <pjt@google.com>

Let me know if you need any result tables for the actual commit msg.
Same goes for making CONFIG_JUMP_LABEL equivalent to default in
CC_HAS_ASM_GOTO case (at least on x86 anyway).


>
> I've tested the patch using a single 'static_branch()' in the getppid() path,
> and basically running tight loops of calls to getppid(). Before, the
> patch, I was seeing results similar to what you reported, after the
> patch, things improved for all metrics. Here are my results for the
> branch disabled case:
>
> With jump labels turned on (CONFIG_JUMP_LABEL), branch disabled:
>
>  Performance counter stats for 'bash -c /tmp/timing;true' (50 runs):
>
>     3,969,510,217 instructions             #      0.864 IPC     ( +-0.000% )
>     4,592,334,954 cycles                     ( +-   0.046% )
>       751,634,470 branches                   ( +-   0.000% )
>
>        1.722635797  seconds time elapsed   ( +-   0.046% )
>
> Jump labels turned off (CONFIG_JUMP_LABEL not set), branch disabled:
>
>  Performance counter stats for 'bash -c /tmp/timing;true' (50 runs):
>
>     4,009,611,846 instructions             #      0.867 IPC     ( +-0.000% )
>     4,622,210,580 cycles                     ( +-   0.012% )
>       771,662,904 branches                   ( +-   0.000% )
>
>        1.734341454  seconds time elapsed   ( +-   0.022% )
>
>
> So all of the measured metrics improved in the jump labels case b/w
> 0.5% - 2.5%.
>
> I'm curious to see what you find with this patch.
>
> Thanks,
>
> -Jason
>
>
>