Messages in this thread | | | Date | Mon, 8 Dec 2008 15:33:52 +0100 | From | Ingo Molnar <> | Subject | Re: [patch] export percpu cpuacct cgroup stats |
| |
* Andrew Morton <akpm@linux-foundation.org> wrote:
> On Fri, 5 Dec 2008 10:16:30 -0800 Ken Chen <kenchen@google.com> wrote: > > > +static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft, > > + struct seq_file *m) > > +{ > > + struct cpuacct *ca = cgroup_ca(cgroup); > > + u64 percpu; > > + int i; > > + > > + for_each_possible_cpu(i) { > > + spin_lock_irq(&cpu_rq(i)->lock); > > + percpu = *percpu_ptr(ca->cpuusage, i); > > + spin_unlock_irq(&cpu_rq(i)->lock); > > + seq_printf(m, "%llu ", (unsigned long long) percpu); > > + } > > + seq_printf(m, "\n"); > > + return 0; > > +} > > The locking is only needed for 32-bit, I assume? > > The iteration across all possible CPUs seems a bit lame - that code > looks pretty easy to convert to hotplug goodness. > > (All of which pertains to existing code, not to this patch).
fair enough. Ken, would you mind updating it in this fashion?
Ingo
| |