Re: [PATCHv2 2/3] cpupower: mperf_monitor: Introduce per_cpu_schedule flag

From: Natarajan, Janakarajan
Date: Mon Oct 28 2019 - 12:37:10 EST

On 10/25/2019 10:33 AM, shuah wrote:
> On 10/25/19 4:39 AM, Thomas Renninger wrote:
>> Hi Natarajan,
>> sorry for answering that late.
>> I post on top as it doesn't fit to the patch context:
>> While I like the 2 other patches, especially the first preparing for
>> a generic "ensure to always run on the measured CPU at measure time"
>> interface..., this patch does make use of it in a very static manner.
>> I then tried to get this more generic..., without any outcome for now.
>> If someone likes to play with this, my idea would be:
>> - the monitors need cpu_start() and cpu_stop() callbacks to register
>> - either start(), stop() and/or cpu_start(), cpu_stop() callbacks
>> have to
>> ÂÂ be provided by a monitor.
>> - current behavior is only start/stop which means the whole per_cpu
>> logic
>> ÂÂ resides inside the monitor
>> - if cpu_start/cpu_stop is provided, iterating over all cpus is done in
>> ÂÂ fork_it and general start/stop functions are an optionally entry
>> point
>> ÂÂ before and after the per_cpu calls.
>> Then the cpu binding can be done from outside.
>> Another enhancement could be then to fork as many processes as there
>> are CPUs
>> in case of per_cpu_schedule (or an extra param/flag) and then:
>> - Bind these forked processes to each cpu.
>> - Execute start measures via the forked processes on each cpu
>> - Execute test executable (which runs in yet another fork as done
>> already)
>> - Execute stop measures via the forked processes on each cpu
>> This should be ideal environment to not interfere with the tested
>> executable.
>> It would also allow a nicer program structure.
> It will be good to capture these ideas in the ToDo file.
> Natarajan! WOuld you like to send a patch updating the ToDo file with
> these ideas?

Sure. I can send out a patch capturing these ideas.


> thanks,
> -- Shuah