Re: POSIX timer syscalls

From: Eric Piel (Eric.Piel@Bull.Net)
Date: Fri Mar 07 2003 - 07:14:33 EST


george anzinger wrote:
>
> By the way, I am seeing some reports from the clock_nanosleep test
> about sleeping too long or too short. The too long appears to be just
> not being able to preempt what ever else is running. The too short
> (on the x86) is, I believe, due to the fact that more that 1/HZ is
> clocked on the wall clock each jiffie.
>
> Try this:
>
> time sleep 60
>
> On the x86 it reports less than 60, NOT good.
>
I've run the test programs and they pass everything well (with my
patchs) excepted the nanosleeps which seems to be finnished a bit too
early. My system test is a 2.5.64 patched on a 4xItaniumII.

My main question is to know if it's a problem even if the difference
between the wakeup time and the requested time is smaller than the
resolution of the clock, 976562ns ? I mean, at the resolution of the
clock we could consider we woke up right at the good time, couldn't we?

In addition time sleep 60 always gave me time over 1 minute, I guess
it's a good point.

Here is a part of the log of 'do_test':

Testing behavor with clock seting...
Retarding the clock
Clock did not seem to move
 was: 1046969027s 703359000ns
 requested: 1046969023s 703359000ns
 now: 1046969022s 467072000ns
 diff is -1.236286998sec
Cool clock_nanosleeptest.c,379:clock_nanosleep(clock, TIMER_ABSTIME,
&ts, NULL)

Testing signal behavor...
handler1 entered: signal 31
expected clock_nanosleeptest.c,227:clock_nanosleep(clock, 0, &ts, &rs):
Interrupted system call
Time remaining is 0s 989257306ns
clock_nanosleeptest.c,245:slept too short!
 requested: 275s 207032000ns
 now: 275s 207030632ns
 diff is -0.000001368sec

Testing undelivered signal behavor...
Cool clock_nanosleeptest.c,267:clock_nanosleep(clock, 0, &ts, &rs)
clock_nanosleeptest.c,283:slept too short!
 requested: 275s 223633000ns
 now: 275s 223632698ns
 diff is -0.000000302sec

 --Eric
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Fri Mar 07 2003 - 22:00:36 EST