cpuacct: per-cgroup utime/stime statistics - v3
PATCH 1/1 cpuacct: per-cgroup utime/stime statistics - v3
Hi,
Here is the next version of the cpuacct stime/utime statistics patch.
Ingo, Could you please consider this for -tip ?
Changes for v3:
- Fix a small race in the cpuacct hierarchy walk.
v2:
http://lkml.org/lkml/2009/3/12/170
v1:
http://lkml.org/lkml/2009/3/10/150
--
cpuacct: Add stime and utime statistics
Add per-cgroup cpuacct controller statistics like the system and user time consumed by the group of tasks.
--- Documentation/cgroups/cpuacct.txt | 17 +++++++ kernel/sched.c | 92 +++++++++++++++++++++++++++++++++++--- 2 files changed, 103 insertions(+), 6 deletions(-)
Documentation/cgroups/cpuacct.txt +17 -0
@@ -30,3 +30,20 @@ The above steps create a new group g1 an process (bash) into it. CPU time consumed by this bash and its children can be obtained from g1/cpuacct.usage and the same is accumulated in /cgroups/cpuacct.usage also. + +cpuacct.stat file lists a few statistics which further divide the +CPU time obtained by the cgroup into user and system times. Currently +the following statistics are supported: + +utime: Time spent by tasks of the cgroup in user mode. +stime: Time spent by tasks of the cgroup in kernel mode. + +utime and stime are in USER_HZ unit. + +cpuacct controller uses percpu_counter interface to collect utime and +stime. This causes two side effects: + +- It is theoritically possible to see wrong values for stime and utime. + This is because percpu_counter_read() on 32bit systems is broken. +- It is possible to see slightly outdated values for stime and utime + due to the batch processing nature of percpu_counter.
kernel/sched.c +86 -6
160 lines not on this page · raw message
Quoted 39 lines · On Tue, 17 Mar 2009 11:51:55 +0530 Bharata B Rao <[email protected]>…
Hi,
Here is the next version of the cpuacct stime/utime statistics patch.
Ingo, Could you please consider this for -tip ?
Changes for v3:
- Fix a small race in the cpuacct hierarchy walk.v2:
http://lkml.org/lkml/2009/3/12/170v1:
http://lkml.org/lkml/2009/3/10/150
--cpuacct: Add stime and utime statistics
Add per-cgroup cpuacct controller statistics like the system and user time consumed by the group of tasks.
Signed-off-by Bharata B Rao <[email protected]>Signed-off-by Balaji Rao <[email protected]>--- Documentation/cgroups/cpuacct.txt | 17 +++++++ kernel/sched.c | 92 +++++++++++++++++++++++++++++++++++--- 2 files changed, 103 insertions(+), 6 deletions(-)Documentation/cgroups/cpuacct.txt +5
-0@@ -30,3 +30,20 @@ The above steps create a new group g1 an process (bash) into it. CPU time consumed by this bash and its children can be obtained from g1/cpuacct.usage and the same is accumulated in /cgroups/cpuacct.usage also. + +cpuacct.stat file lists a few statistics which further divide the +CPU time obtained by the cgroup into user and system times. Currently +the following statistics are supported: +
Documentation/cgroups/cpuacct.txt The above steps create a new group g1 an · line 47
Quoted 10 lines
Documentation/cgroups/cpuacct.txt +10
-0+utime: Time spent by tasks of the cgroup in user mode. +stime: Time spent by tasks of the cgroup in kernel mode. + +utime and stime are in USER_HZ unit. + +cpuacct controller uses percpu_counter interface to collect utime and +stime. This causes two side effects: + +- It is theoritically possible to see wrong values for stime and utime. + This is because percpu_counter_read() on 32bit systems is broken.
<snip> Hmm, I don't want to say "BROKEN" but..
Documentation/cgroups/cpuacct.txt The above steps create a new group g1 an · line 49
Quoted 2 lines
Documentation/cgroups/cpuacct.txt +2
-0+- It is possible to see slightly outdated values for stime and utime + due to the batch processing nature of percpu_counter.
no objection to here. My customer will ask me "To what extent it delayes ?" maybe I can answer...
Quoted 4 lines
Documentation/cgroups/cpuacct.txt +4
-0+static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft, + struct cgroup_map_cb *cb) +{ + struct cpuacct *ca = cgroup_ca(cgrp);
Documentation/cgroups/cpuacct.txt
Quoted 10 lines
Documentation/cgroups/cpuacct.txt +10
-0+ int i; + + for (i = 0; i < CPUACCT_STAT_NSTATS; i++) { + s64 val = percpu_counter_read(&ca->cpustat[i]); + val = cputime_to_clock_t(val); + cb->fill(cb, cpuacct_stat_desc[i], val); + } + return 0; +} +
No objection to this patch itself, but, Hmm...can this work ?
#ifdef CONFIG_32BIT
/* can be used only when update is not very frequent */ s64 percpu_counter_read_positive_slow(fbc)
{
s64 ret;
retry:
/* wait until it seems to be safe */
smp_mb();
spin_unlock_wait(&ca->lock);
ret = fbc->count;
if (ret < 0)
goto retry;
return ret;
}#else
s64 percpu_counter_read_positive_slow(fbc)
{
retrun fbc->count;
}
#endif
I wonder why percpu_counter_read_positive() is designed to return 1...
Thanks,
-Kame
Quoted 16 lines · Bharata B Rao
Hi,
Here is the next version of the cpuacct stime/utime statistics patch.
Ingo, Could you please consider this for -tip ?
Changes for v3:
- Fix a small race in the cpuacct hierarchy walk.
Quoted 7 lines
cpuacct: Add stime and utime statistics
Add per-cgroup cpuacct controller statistics like the system and user time consumed by the group of tasks.
Signed-off-by Bharata B Rao <[email protected]>Signed-off-by Balaji Rao <[email protected]>
Quoted 199 lines
--- Documentation/cgroups/cpuacct.txt | 17 +++++++ kernel/sched.c | 92 +++++++++++++++++++++++++++++++++++--- 2 files changed, 103 insertions(+), 6 deletions(-)Documentation/cgroups/cpuacct.txt +17
-0@@ -30,3 +30,20 @@ The above steps create a new group g1 an process (bash) into it. CPU time consumed by this bash and its children can be obtained from g1/cpuacct.usage and the same is accumulated in /cgroups/cpuacct.usage also. + +cpuacct.stat file lists a few statistics which further divide the +CPU time obtained by the cgroup into user and system times. Currently +the following statistics are supported: + +utime: Time spent by tasks of the cgroup in user mode. +stime: Time spent by tasks of the cgroup in kernel mode. + +utime and stime are in USER_HZ unit. + +cpuacct controller uses percpu_counter interface to collect utime and +stime. This causes two side effects: + +- It is theoritically possible to see wrong values for stime and utime. + This is because percpu_counter_read() on 32bit systems is broken. +- It is possible to see slightly outdated values for stime and utime + due to the batch processing nature of percpu_counter.kernel/sched.c +86
-6@@ -1442,10 +1442,22 @@ iter_move_one_task(struct rq *this_rq, i struct rq_iterator *iterator);#endif +/* Time spent by the tasks of the cpu accounting group executing in ... */ +enum cpuacct_stat_index { +CPUACCT_STAT_UTIME ,/* ... user mode */ +CPUACCT_STAT_STIME ,/* ... kernel mode */ + +CPUACCT_STAT_NSTATS , +}; +#ifdef CONFIG_CGROUP_CPUACCT static void cpuacct_charge (struct task_struct *tsk,u64 cputime); +static void cpuacct_update_stats (struct task_struct *tsk, +enum cpuacct_stat_index idx,cputime_t val);#else static inline void cpuacct_charge (struct task_struct *tsk,u64 cputime) {} +static inline void cpuacct_update_stats (struct task_struct *tsk, +enum cpuacct_stat_index idx,cputime_t val) {}#endif static inline void inc_cpu_load (struct rq *rq,unsigned long load)@@ -4387,6 +4399,8 @@ void account_user_time(struct task_struc cpustat->nice =cputime64_add (cpustat->nice, tmp); else cpustat->user = cputime64_add(cpustat->user, tmp); + +cpuacct_update_stats (p,CPUACCT_STAT_UTIME , cputime);/* Account for user time used */ acct_update_integrals (p); }@@ -4448,6 +4462,8 @@ void account_system_time(struct task_strelse cpustat->system =cputime64_add (cpustat->system, tmp); +cpuacct_update_stats (p,CPUACCT_STAT_STIME , cputime); +/* Account for system time used */ acct_update_integrals (p); }@@ -9727,6 +9743,7 @@ struct cpuacct {struct cgroup_subsys_state css;/* cpuusage holds pointer to a u64-type object on every cpu */ u64 *cpuusage; +struct percpu_counter cpustat[CPUACCT_STAT_NSTATS ];struct cpuacct *parent; };@@ -9751,20 +9768,33 @@ static struct cgroup_subsys_state *cpuac struct cgroup_subsys *ss, struct cgroup *cgrp) { struct cpuacct *ca = kzalloc(sizeof(*ca), GFP_KERNEL); +int i;if (!ca) -return ERR_PTR (-ENOMEM ); + goto out; ca->cpuusage =alloc_percpu (u64); -if (!ca->cpuusage) { -kfree (ca); -return ERR_PTR (-ENOMEM ); - } +if (!ca->cpuusage) + goto out_free_ca; + +for (i =0 ; i <CPUACCT_STAT_NSTATS ; i++) +if (percpu_counter_init (&ca->cpustat[i],0 )) + goto out_free_counters;if (cgrp->parent) ca->parent =cgroup_ca (cgrp->parent);return &ca->css; + +out_free_counters: + i--; +while (i-- >=0 ) +percpu_counter_destroy (&ca->cpustat[i]); +free_percpu (ca->cpuusage); +out_free_ca: +kfree (ca); +out: +return ERR_PTR (-ENOMEM ); }/* destroy an existing cpu accounting group */ @@ -9772,7 +9802,10 @@ static void cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) { struct cpuacct *ca = cgroup_ca(cgrp); +int i; +for (i =0 ; i <CPUACCT_STAT_NSTATS ; i++) +percpu_counter_destroy (&ca->cpustat[i]);free_percpu (ca->cpuusage);kfree (ca); }@@ -9859,6 +9892,25 @@ static int cpuacct_percpu_seq_read(strucreturn 0 ; } +static const char *cpuacct_stat_desc[] = { + [CPUACCT_STAT_UTIME ] ="utime" , + [CPUACCT_STAT_STIME ] ="stime" , +}; + +static int cpuacct_stats_show (struct cgroup *cgrp,struct cftype *cft, +struct cgroup_map_cb *cb) +{ +struct cpuacct *ca =cgroup_ca (cgrp); +int i; + +for (i =0 ; i <CPUACCT_STAT_NSTATS ; i++) { +s64 val =percpu_counter_read (&ca->cpustat[i]); + val =cputime_to_clock_t (val); + cb->fill (cb, cpuacct_stat_desc[i], val); + } +return 0 ; +} +static struct cftype files[] = { { .name ="usage" ,@@ -9869,7 +9921,10 @@ static struct cftype files[] = { .name = "usage_percpu", .read_seq_string = cpuacct_percpu_seq_read, }, - + { + .name = "stat", + .read_map = cpuacct_stats_show, + }, };static int cpuacct_populate (struct cgroup_subsys *ss,struct cgroup *cgrp)@@ -9908,6 +9963,31 @@ static void cpuacct_charge(struct task_srcu_read_unlock (); } +/* +* Charge the system/user time to the task's accounting group. +*/ +static void cpuacct_update_stats (struct task_struct *tsk, +enum cpuacct_stat_index idx,cputime_t val) +{ +struct cpuacct *ca; + +if (unlikely (!cpuacct_subsys.active)) +return ; + +/* +* rcu_read_lock() protects ca thus making sure that hierarchy +* walk is safe. +*/ +rcu_read_lock (); + ca =task_ca (tsk); + +do { +percpu_counter_add (&ca->cpustat[idx], val); + ca = ca->parent; + }while (ca); +rcu_read_unlock (); +} +struct cgroup_subsys cpuacct_subsys = { .name ="cpuacct" , .create = cpuacct_create,
Quoted 19 lines · Peter Zijlstra
Quoted 18 lines · Bharata B Rao
Hi,
Here is the next version of the cpuacct stime/utime statistics patch.
Ingo, Could you please consider this for -tip ?
Changes for v3:
- Fix a small race in the cpuacct hierarchy walk.v2:
http://lkml.org/lkml/2009/3/12/170v1:
http://lkml.org/lkml/2009/3/10/150
--cpuacct: Add stime and utime statistics
Quoted 8 lines
Quoted 5 lines
Add per-cgroup cpuacct controller statistics like the system and user time consumed by the group of tasks.
Signed-off-by Bharata B Rao <[email protected]>Signed-off-by Balaji Rao <[email protected]>Acked-by Peter Zijlstra <[email protected]>
Sorry, I should done this earlier
Signature · 1 line
Balbir