[Devel] Re: [PATCH v3 3/6] expose fine-grained per-cpu data for cpuacct stats

Glauber Costa glommer at parallels.com
Wed May 30 03:34:08 PDT 2012


On 05/30/2012 02:34 PM, Peter Zijlstra wrote:
> On Wed, 2012-05-30 at 13:48 +0400, Glauber Costa wrote:
>
>> +static int cpuacct_stats_percpu_show(struct cgroup *cgrp, struct cftype *cft,
>> +				     struct cgroup_map_cb *cb)
>> +{
>> +	struct cpuacct *ca = cgroup_ca(cgrp);
>> +	int cpu;
>> +
>> +	for_each_online_cpu(cpu) {
>> +		do_fill_cb(cb, ca, "user", cpu, CPUTIME_USER);
>> +		do_fill_cb(cb, ca, "nice", cpu, CPUTIME_NICE);
>> +		do_fill_cb(cb, ca, "system", cpu, CPUTIME_SYSTEM);
>> +		do_fill_cb(cb, ca, "irq", cpu, CPUTIME_IRQ);
>> +		do_fill_cb(cb, ca, "softirq", cpu, CPUTIME_SOFTIRQ);
>> +		do_fill_cb(cb, ca, "guest", cpu, CPUTIME_GUEST);
>> +		do_fill_cb(cb, ca, "guest_nice", cpu, CPUTIME_GUEST_NICE);
>> +	}
>> +
>> +	return 0;
>> +}
>
> Uhm, hotplug anyone?
What's with hotplug ?

If you mean we should accumulate that on hotplug, I don't see why. We 
certainly don't do that for the tick-based counters. Or do you mean I am 
missing a get_online_cpus() lock ?

humm, I don't see it being taken on other loops like that




More information about the Devel mailing list