This is the mail archive of the glibc-bugs@sourceware.org mailing list for the glibc project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

[Bug nptl/1256] New: Thread/process-specific CPU-time clock not implemented correctly?


it seems that CLOCK_THREAD_CPUTIME_ID clock returns wall-clock time since thread
was started instead of CPU-time used by thread.

reproducible: always
how to reproduce:
create a thread that runs the following loop:
        for (;;) {
                sleep(3);
                clock_gettime(CLOCK_THREAD_CPUTIME_ID, &end);
                printf("sleepy: %d, %d\n", end.tv_sec, end.tv_nsec);
        }
this produces the following output:
sleepy: 2, 999741259
sleepy: 5, 999491833
sleepy: 8, 999247698
sleepy: 11, 999174019
...

expected result:
minor steps in cpu-time, since the thread is mostly sleeping.

CLOCK_PROCESS_CPUTIME_ID behaves exactly the same, measuring wall-clock time
instead of CPU-time.

-- 
           Summary: Thread/process-specific CPU-time clock not implemented
                    correctly?
           Product: glibc
           Version: 2.3.4
            Status: NEW
          Severity: normal
          Priority: P2
         Component: nptl
        AssignedTo: drepper at redhat dot com
        ReportedBy: myself at rojer dot pp dot ru
                CC: glibc-bugs at sources dot redhat dot com


http://sources.redhat.com/bugzilla/show_bug.cgi?id=1256

------- You are receiving this mail because: -------
You are on the CC list for the bug, or are watching someone who is.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]