RUSAGE_THREAD
PATCH 1/1 RUSAGE_THREAD
Hi Andrew,
This adds the RUSAGE_THREAD option for the getrusage system call. This is essentially Roland's patch from http://lkml.org/lkml/2008/1/18/589,
but the line about RUSAGE_LWP line has been removed, as suggested by Ulrich and Christoph.
Thanks,
Sripathi.
This adds the RUSAGE_THREAD option for the getrusage system call.
--- include/linux/resource.h | 1 + kernel/sys.c | 31 ++++++++++++++++++++++--------- 2 files changed, 23 insertions(+), 9 deletions(-)
include/linux/resource.h +1 -0
@@ -19,6 +19,7 @@ struct task_struct;#define RUSAGE_SELF 0#define RUSAGE_CHILDREN (-1)#define RUSAGE_BOTH (-2)/* sys_wait4() uses this */ +#define RUSAGE_THREAD 1/* only the calling thread */ struct rusage {struct timeval ru_utime;/* user time used */
kernel/sys.c +22 -9
@@ -1554,6 +1554,19 @@ out:* */ +static void accumulate_thread_rusage (struct task_struct *t,struct rusage *r, +cputime_t *utimep,cputime_t *stimep) +{ + *utimep =cputime_add (*utimep, t->utime); + *stimep =cputime_add (*stimep, t->stime); + r->ru_nvcsw += t->nvcsw; + 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); +} +static void k_getrusage (struct task_struct *p,int who,struct rusage *r) {struct task_struct *t;
@@ -1563,6 +1576,11 @@ static void k_getrusage(struct task_strumemset ((char *) r,0 ,sizeof *r); utime = stime = cputime_zero; +if (who ==RUSAGE_THREAD ) { +accumulate_thread_rusage (p, r, &utime, &stime); + goto out; + } +rcu_read_lock ();if (!lock_task_sighand (p, &flags)) {rcu_read_unlock ();
@@ -1595,14 +1613,7 @@ static void k_getrusage(struct task_stru r->ru_oublock += p->signal->oublock; t = p;do { - utime =cputime_add (utime, t->utime); - stime =cputime_add (stime, t->stime); - r->ru_nvcsw += t->nvcsw; - 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); +accumulate_thread_rusage (t, r, &utime, &stime); t =next_thread (t); }while (t != p);break ;
@@ -1614,6 +1625,7 @@ static void k_getrusage(struct task_struunlock_task_sighand (p, &flags);rcu_read_unlock (); +out:cputime_to_timeval (utime, &r->ru_utime);cputime_to_timeval (stime, &r->ru_stime); }
@@ -1627,7 +1639,8 @@ int getrusage(struct task_struct *p, intasmlinkage long sys_getrusage (int who,struct rusage __user *ru) { -if (who !=RUSAGE_SELF && who !=RUSAGE_CHILDREN ) +if (who !=RUSAGE_SELF && who !=RUSAGE_CHILDREN && + who !=RUSAGE_THREAD )return -EINVAL ;return getrusage (current, who, ru); }
Quoted 11 lines · Sripathi Kodi
Hi Andrew,
This adds the
RUSAGE_THREADoption for the getrusage system call. This is essentially Roland's patch from http://lkml.org/lkml/2008/1/18/589,
but the line aboutRUSAGE_LWPline has been removed, as suggested by Ulrich and Christoph.Thanks,
Sripathi.This adds the
RUSAGE_THREADoption for the getrusage system call.
Sripathi,
Could you write some small piece of text for the getrusage.2 man page that describes the intended behavior of RUSAGE_THREAD?
Thanks,
Michael
Signature · 5 lines
Michael Kerrisk Maintainer of the Linux man-pages project http://www.kernel.org/doc/man-pages/ Want to report a man-pages bug? Look here: http://www.kernel.org/doc/man-pages/reporting_bugs.html
Quoted 11 lines · Michael Kerrisk
Quoted 10 lines · Sripathi Kodi
Hi Andrew,
This adds the
RUSAGE_THREADoption for the getrusage system call. This is essentially Roland's patch from
http://lkml.org/lkml/2008/1/18/589, but the line aboutRUSAGE_LWPline has been removed, as suggested by Ulrich and Christoph.Thanks,
Sripathi.
Quoted 6 lines
Quoted 1 line
This adds the
RUSAGE_THREADoption for the getrusage system call.Sripathi,
Could you write some small piece of text for the getrusage.2 man page that describes the intended behavior of
RUSAGE_THREAD?
Michael,
Please take a look at the following patch to getrusage.2. This is the first time I have edited a manpage, so I hope I have done it correctly!
Also, the RUSAGE_THREAD patch is currently in -mm, but not in mainline yet. Hoping that it will make it, I have put a line in the patch that it is supported from 2.6.25 onwards.
Thanks,
Sripathi.
PS: I fixed spelling error in Ulrich's mail id in the CC list.
getrusage.2 renamed from getrusage.2.org +16 -3
@@ -44,12 +44,22 @@ getrusage \- get resource usage .PP .BR getrusage () returns current resource usages, for a \fIwho\fP -of either +of +.B RUSAGE_THREAD, .B RUSAGE_SELF or .BR RUSAGE_CHILDREN . -The former asks for resources used by the current process, -the latter for resources used by those of its children +.PP +.B RUSAGE_THREAD +asks for resources used by the calling thread. +.PP +.B RUSAGE_SELF +asks for resources used by the current process, +which is the sum of resources used by all threads +in the process. +.PP +.B RUSAGE_CHILDREN +asks for resources used by those of its children that have terminated and have been waited for. .PP .in +0.5i
@@ -130,6 +140,9 @@ Since Linux 2.6, and .I ru_nivcsw are also maintained. +.PP +.B RUSAGE_THREAD +is supported only in Linux kernel versions 2.6.25 and above. .SH "SEE ALSO" .BR getrlimit (2), .BR times (2),
Quoted 18 lines · Sripathi Kodi
Quoted 8 lines · Michael Kerrisk
Quoted 7 lines · Sripathi Kodi
Hi Andrew,
This adds the
RUSAGE_THREADoption for the getrusage system call. This is essentially Roland's patch from
http://lkml.org/lkml/2008/1/18/589, but the line aboutRUSAGE_LWPline has been removed, as suggested by Ulrich and Christoph.Quoted 8 lines
Quoted 4 lines
Thanks,
Sripathi.This adds the
RUSAGE_THREADoption for the getrusage system call.Sripathi,
Could you write some small piece of text for the getrusage.2 man page that describes the intended behavior of
RUSAGE_THREAD?
Quoted 8 lines
Michael,
Please take a look at the following patch to getrusage.2. This is the first time I have edited a manpage, so I hope I have done it correctly!
Also, the
RUSAGE_THREADpatch is currently in -mm, but not in mainline yet. Hoping that it will make it, I have put a line in the patch that it is supported from 2.6.25 onwards.
Sripathi,
Thanks for the patch -- looks reasonable to me.
I see that RUSAGE_THREAD didin't make the cut for 2.6.25. If you remember, could you ping me when it does hit mainline.
Cheers,
Michael
Quoted 43 lines
PS: I fixed spelling error in Ulrich's mail id in the CC list.
Signed-off-by Sripathi Kodi <[email protected]>getrusage.2 renamed from getrusage.2.org +16
-3@@ -44,12 +44,22 @@ getrusage \- get resource usage .PP .BR getrusage () returns current resource usages, for a \fIwho\fP -of either +of +.B RUSAGE_THREAD, .B RUSAGE_SELF or .BR RUSAGE_CHILDREN . -The former asks for resources used by the current process, -the latter for resources used by those of its children +.PP +.B RUSAGE_THREAD +asks for resources used by the calling thread. +.PP +.B RUSAGE_SELF +asks for resources used by the current process, +which is the sum of resources used by all threads +in the process. +.PP +.B RUSAGE_CHILDREN +asks for resources used by those of its children that have terminated and have been waited for. .PP .in +0.5i@@ -130,6 +140,9 @@ Since Linux 2.6, and .I ru_nivcsw are also maintained. +.PP +.B RUSAGE_THREAD +is supported only in Linux kernel versions 2.6.25 and above. .SH "SEE ALSO" .BR getrlimit (2), .BR times (2),
Signature · 5 lines
Michael Kerrisk Maintainer of the Linux man-pages project http://www.kernel.org/doc/man-pages/ Want to report a man-pages bug? Look here: http://www.kernel.org/doc/man-pages/reporting_bugs.html