Any difference between clock_gettime( CLOCK_REALTIME .... ) and time()?

Question

A simple question: do time(...) and clock_gettime( CLOCK_REALTIME, ... ) produce the same time theoretically (in respect to seconds only)?

Here's what I mean:

time_t epoch;
time( &epoch );

and

struct timespec spec;
clock_gettime( CLOCK_REALTIME, &spec );

Are these two supposed to return exactly the same result (in respect to seconds)?

I "tested" this with changing time and time zones and epoch and spec.tv_sec always show the same result, but the documentation of CLOCK_REATIME confuses me a bit and I'm not sure, that they will always be the same.

Real world situation: I have a piece of code, which uses time. Now I want to have the time in milliseconds (which can be taken from spec.tv_nsec, multiplied by 1000000). So I think about removing time and using directly clock_gettime, but I'm not sure if this will remain the same in all situations.

_{The question is somehow related to Measure time in Linux - time vs clock vs getrusage vs clock_gettime vs gettimeofday vs timespec_get? but the information there was not enough for me.. I think.}

In C++ there is also third option, `std::chrono::system_clock::now()`. — dreamlax, Aug 12 '16 at 11:02
@dreamlax Yep, but the new standard cannot be used for my case, that's why I explicitly asked for these two. Thanks anyway :) — Kiril Kirov, Aug 12 '16 at 11:06

Koshinae · Accepted Answer · 2016-08-12T12:58:38.553

8

[Note: I used the git master branch and v4.7 for the reference links below, x86 only, as I'm lazy.]

time() is in fact an alias for the equally named syscall, which calls get_seconds, happens at kernel/time/time.c. That syscall uses the get_seconds function to return the UNIX timestamp, which is read from the core timekeeping struct, more precisely from the "Current CLOCK_REALTIME time in seconds" field (xtime_sec).

clock_gettime() is a glibc function in sysdeps\unix\clock_gettime.c, which simply calls gettimeofday if the supplied clock ID is CLOCK_REALTIME, which is again backed by the equally named syscall (source is in the same time.c file, above). This one calls do_gettimeofday, which eventually ends up calling __getnstimeofday64, that queries... the very same xtime_sec field from the same struct as above.

Update:

As @MaximEgorushkin cleverly pointed out, a new vDSO mechanism hijacks (a good sign it is present, if your binary depends on linux-vdso.so.*) the clock_gettime call and redirects it to __vdso_clock_gettime. This one uses a new clock source management framework (gtod - Generic Time Of Day). A call to do_realtime, and it reads from a structure, struct vsyscall_gtod_data's wall_time_sec field. This structure is maintained by update_vsyscall, from the same timekeeper struct as the above.

tl;dr

The answer is: yes, they get the time from the same clock source.

edited Aug 12 '16 at 12:58

answered Aug 12 '16 at 10:43

Koshinae

2,240
2
30
40

What do you mean by "if the clock is CLOCK_REALTIME" ? – Kiril Kirov Aug 12 '16 at 10:51
1

@KirilKirov `clock_gettime`'s first argument is a clock ID. One possible value is the mentioned `CLOCK_REALTIME`. – Koshinae Aug 12 '16 at 10:52
1

Yes, I know the first argument, but I did not understand what you meant. Thanks for the clarification and the edit, I get it now. – Kiril Kirov Aug 12 '16 at 11:06
To be pedantic _return the epoch_ must be _return duration in seconds **since UNIX epoch**_. – Maxim Egorushkin Aug 12 '16 at 11:09
@MaximEgorushkin : There. – Koshinae Aug 12 '16 at 11:16
The details about `clock_gettime()` are totally wrong, that is an old implementation. This function resides in [the VDSO](http://man7.org/linux/man-pages/man7/vdso.7.html). `__vdso_clock_gettime` does not call `__vdso_gettimeofday`. – Maxim Egorushkin Aug 12 '16 at 11:16
Okie, write your own answer then, please :) – Koshinae Aug 12 '16 at 11:18
@Koshinae I prefer commenting on inaccurate answers. – Maxim Egorushkin Aug 12 '16 at 11:19
@MaximEgorushkin Okay, it was embarrassing for me :) – Koshinae Aug 12 '16 at 12:59
@Koshinae Aww, do not take it personally. – Maxim Egorushkin Aug 12 '16 at 13:01
@MaximEgorushkin Can do sir. – Koshinae Aug 12 '16 at 13:04
@MaximEgorushkin - okay, do you say, that they are semantically different then (ignoring for a moment the implementation)? I guess not, because the behavior should be still the same, but still.. – Kiril Kirov Aug 12 '16 at 14:34
@KirilKirov `clock_gettime` has nanosecond resolution. `gettimeofday` only has microsecond resolution, so that `clock_gettime` implemented in terms of `gettimeofday` did not have nanosecond resolution. – Maxim Egorushkin Aug 12 '16 at 14:47

Any difference between clock_gettime( CLOCK_REALTIME .... ) and time()?

1 Answers1

tl;dr

Linked