cgroup: add cpu.stat file to root cgroup
Currently, the root cgroup does not have a cpu.stat file. Add one which is consistent with /proc/stat to capture global cpu statistics that might not fall under cgroup accounting. We haven't done this in the past because the data are already presented in /proc/stat and we didn't want to add overhead from collecting root cgroup stats when cgroups are configured, but no cgroups have been created. By keeping the data consistent with /proc/stat, I think we avoid the first problem, while improving the usability of cgroups stats. We avoid the second problem by computing the contents of cpu.stat from existing data collected for /proc/stat anyway. Signed-off-by: Boris Burkov <boris@bur.io> Suggested-by: Tejun Heo <tj@kernel.org> Signed-off-by: Tejun Heo <tj@kernel.org>
This commit is contained in:
parent
6b6ebb3474
commit
936f2a70f2
|
@ -714,9 +714,7 @@ Conventions
|
|||
- Settings for a single feature should be contained in a single file.
|
||||
|
||||
- The root cgroup should be exempt from resource control and thus
|
||||
shouldn't have resource control interface files. Also,
|
||||
informational files on the root cgroup which end up showing global
|
||||
information available elsewhere shouldn't exist.
|
||||
shouldn't have resource control interface files.
|
||||
|
||||
- The default time unit is microseconds. If a different unit is ever
|
||||
used, an explicit unit suffix must be present.
|
||||
|
@ -985,7 +983,7 @@ CPU Interface Files
|
|||
All time durations are in microseconds.
|
||||
|
||||
cpu.stat
|
||||
A read-only flat-keyed file which exists on non-root cgroups.
|
||||
A read-only flat-keyed file.
|
||||
This file exists whether the controller is enabled or not.
|
||||
|
||||
It always reports the following three stats:
|
||||
|
|
|
@ -4874,7 +4874,6 @@ static struct cftype cgroup_base_files[] = {
|
|||
},
|
||||
{
|
||||
.name = "cpu.stat",
|
||||
.flags = CFTYPE_NOT_ON_ROOT,
|
||||
.seq_show = cpu_stat_show,
|
||||
},
|
||||
#ifdef CONFIG_PSI
|
||||
|
|
|
@ -389,18 +389,62 @@ void __cgroup_account_cputime_field(struct cgroup *cgrp,
|
|||
cgroup_base_stat_cputime_account_end(cgrp, rstatc);
|
||||
}
|
||||
|
||||
/*
|
||||
* compute the cputime for the root cgroup by getting the per cpu data
|
||||
* at a global level, then categorizing the fields in a manner consistent
|
||||
* with how it is done by __cgroup_account_cputime_field for each bit of
|
||||
* cpu time attributed to a cgroup.
|
||||
*/
|
||||
static void root_cgroup_cputime(struct task_cputime *cputime)
|
||||
{
|
||||
int i;
|
||||
|
||||
cputime->stime = 0;
|
||||
cputime->utime = 0;
|
||||
cputime->sum_exec_runtime = 0;
|
||||
for_each_possible_cpu(i) {
|
||||
struct kernel_cpustat kcpustat;
|
||||
u64 *cpustat = kcpustat.cpustat;
|
||||
u64 user = 0;
|
||||
u64 sys = 0;
|
||||
|
||||
kcpustat_cpu_fetch(&kcpustat, i);
|
||||
|
||||
user += cpustat[CPUTIME_USER];
|
||||
user += cpustat[CPUTIME_NICE];
|
||||
cputime->utime += user;
|
||||
|
||||
sys += cpustat[CPUTIME_SYSTEM];
|
||||
sys += cpustat[CPUTIME_IRQ];
|
||||
sys += cpustat[CPUTIME_SOFTIRQ];
|
||||
cputime->stime += sys;
|
||||
|
||||
cputime->sum_exec_runtime += user;
|
||||
cputime->sum_exec_runtime += sys;
|
||||
cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL];
|
||||
cputime->sum_exec_runtime += cpustat[CPUTIME_GUEST];
|
||||
cputime->sum_exec_runtime += cpustat[CPUTIME_GUEST_NICE];
|
||||
}
|
||||
}
|
||||
|
||||
void cgroup_base_stat_cputime_show(struct seq_file *seq)
|
||||
{
|
||||
struct cgroup *cgrp = seq_css(seq)->cgroup;
|
||||
u64 usage, utime, stime;
|
||||
struct task_cputime cputime;
|
||||
|
||||
if (!cgroup_parent(cgrp))
|
||||
return;
|
||||
|
||||
cgroup_rstat_flush_hold(cgrp);
|
||||
usage = cgrp->bstat.cputime.sum_exec_runtime;
|
||||
cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &utime, &stime);
|
||||
cgroup_rstat_flush_release();
|
||||
if (cgroup_parent(cgrp)) {
|
||||
cgroup_rstat_flush_hold(cgrp);
|
||||
usage = cgrp->bstat.cputime.sum_exec_runtime;
|
||||
cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime,
|
||||
&utime, &stime);
|
||||
cgroup_rstat_flush_release();
|
||||
} else {
|
||||
root_cgroup_cputime(&cputime);
|
||||
usage = cputime.sum_exec_runtime;
|
||||
utime = cputime.utime;
|
||||
stime = cputime.stime;
|
||||
}
|
||||
|
||||
do_div(usage, NSEC_PER_USEC);
|
||||
do_div(utime, NSEC_PER_USEC);
|
||||
|
|
Loading…
Reference in New Issue