+ getrusage-fill-ru_inblock-and-ru_oublock-fields-if-possible.patch added to -mm tree
Quoted 20 lines · Eric Dumazet
(quoted diff) +4
-0@@ -2021,6 +2022,8 @@ static void k_getrusage(struct task_stru r->ru_nivcsw = p->signal->cnivcsw; r->ru_minflt = p->signal->cmin_flt; r->ru_majflt = p->signal->cmaj_flt; + r->ru_inblock = task_io_get_inblock(p); + r->ru_oublock = task_io_get_oublock(p); if (who == RUSAGE_CHILDREN) break;@@ -2032,6 +2035,8 @@ static void k_getrusage(struct task_stru r->ru_nivcsw += p->signal->nivcsw; r->ru_minflt += p->signal->min_flt; r->ru_majflt += p->signal->maj_flt; + r->ru_inblock += task_io_get_inblock(p); + r->ru_oublock += task_io_get_oublock(p); t = p; do { utime = cputime_add(utime, t->utime);
Review static void k_getrusage(struct task_stru · line 2049
Quoted 5 lines
(quoted diff) +2
-0@@ -2040,6 +2045,8 @@ static void k_getrusage(struct task_stru r->ru_nivcsw += t->nivcsw; r->ru_minflt += t->min_flt; r->ru_majflt += t->maj_flt; + r->ru_inblock += task_io_get_inblock(t); + r->ru_oublock += task_io_get_oublock(t);
I can't understand this. Consider k_getrusage(RUSAGE_BOTH). The end result is that r->ru_inblock == 3 * task_io_get_inblock(p).
No?
Oleg.
Quoted 29 lines · Oleg Nesterov
Quoted 19 lines · Eric Dumazet
(quoted diff) +4
-0@@ -2021,6 +2022,8 @@ static void k_getrusage(struct task_stru r->ru_nivcsw = p->signal->cnivcsw; r->ru_minflt = p->signal->cmin_flt; r->ru_majflt = p->signal->cmaj_flt; + r->ru_inblock = task_io_get_inblock(p); + r->ru_oublock = task_io_get_oublock(p); if (who == RUSAGE_CHILDREN) break;@@ -2032,6 +2035,8 @@ static void k_getrusage(struct task_stru r->ru_nivcsw += p->signal->nivcsw; r->ru_minflt += p->signal->min_flt; r->ru_majflt += p->signal->maj_flt; + r->ru_inblock += task_io_get_inblock(p); + r->ru_oublock += task_io_get_oublock(p); t = p; do { utime = cputime_add(utime, t->utime);Review static void k_getrusage(struct task_stru · line 2049
Quoted 5 lines
(quoted diff) +2
-0@@ -2040,6 +2045,8 @@ static void k_getrusage(struct task_stru r->ru_nivcsw += t->nivcsw; r->ru_minflt += t->min_flt; r->ru_majflt += t->maj_flt; + r->ru_inblock += task_io_get_inblock(t); + r->ru_oublock += task_io_get_oublock(t);I can't understand this. Consider
k_getrusage(RUSAGE_BOTH). The end result is thatr->ru_inblock== 3 *task_io_get_inblock(p).
Quoted 1 line
No?
Yes :)
Very good point, you found a bug in k_getrusage().
I just followed the existing logic, but it seems this logic is bad.
So not only ru_inblock/ru_oublock are multiplied by 3 : others fields as well are wrong.
Also the definition of RUSAGE_CHILDREN is not conformant to standard
http://www.opengroup.org/onlinepubs/009695399/functions/getrusage.html
"If the value of the who argument is RUSAGE_CHILDREN, information shall be "returned about resources used by the terminated and waited-for children of "the current process
We currently do a sum of rusage stats of still alive children.. thats totally wrong...
Eric
Quoted 10 lines · Eric Dumazet
Very good point, you found a bug in
k_getrusage().I just followed the existing logic, but it seems this logic is bad.
So not only ru_inblock/ru_oublock are multiplied by 3 : others fields as well are wrong.
Also the definition of
RUSAGE_CHILDRENis not conformant to standard
Quoted 8 lines
http://www.opengroup.org/onlinepubs/009695399/functions/getrusage.html
"If the value of the who argument is
RUSAGE_CHILDREN, information shall be "returned about resources used by the terminated and waited-for children
of "the current processWe currently do a sum of rusage stats of still alive children.. thats totally wrong...
Please ignore this mail, I was very wrong.
I shall rethink a proper patch.
Quoted 31 lines · Eric Dumazet
Quoted 29 lines · Oleg Nesterov
Quoted 19 lines · Eric Dumazet
(quoted diff) +4
-0@@ -2021,6 +2022,8 @@ static void k_getrusage(struct task_stru r->ru_nivcsw = p->signal->cnivcsw; r->ru_minflt = p->signal->cmin_flt; r->ru_majflt = p->signal->cmaj_flt; + r->ru_inblock = task_io_get_inblock(p); + r->ru_oublock = task_io_get_oublock(p); if (who == RUSAGE_CHILDREN) break;@@ -2032,6 +2035,8 @@ static void k_getrusage(struct task_stru r->ru_nivcsw += p->signal->nivcsw; r->ru_minflt += p->signal->min_flt; r->ru_majflt += p->signal->maj_flt; + r->ru_inblock += task_io_get_inblock(p); + r->ru_oublock += task_io_get_oublock(p); t = p; do { utime = cputime_add(utime, t->utime);Review static void k_getrusage(struct task_stru · line 2049
Quoted 5 lines
(quoted diff) +2
-0@@ -2040,6 +2045,8 @@ static void k_getrusage(struct task_stru r->ru_nivcsw += t->nivcsw; r->ru_minflt += t->min_flt; r->ru_majflt += t->maj_flt; + r->ru_inblock += task_io_get_inblock(t); + r->ru_oublock += task_io_get_oublock(t);I can't understand this. Consider
k_getrusage(RUSAGE_BOTH). The end result is thatr->ru_inblock== 3 *task_io_get_inblock(p).
Quoted 5 lines
Quoted 1 line
No?
Yes :)
Very good point, you found a bug in
k_getrusage().
No, no, please check the code.
Quoted 10 lines
So not only ru_inblock/ru_oublock are multiplied by 3 : others fields as well are wrong.
Also the definition of
RUSAGE_CHILDRENis not conformant to standardhttp://www.opengroup.org/onlinepubs/009695399/functions/getrusage.html
"If the value of the who argument is
RUSAGE_CHILDREN, information shall be "returned about resources used by the terminated and waited-for children of "the current process
This exactly happens. We are reading ->signal->*, see wait_task_zombie().
Quoted 2 lines
We currently do a sum of rusage stats of still alive children.. thats totally wrong...
I hope not :)
Oleg.