[<prev] [next>] [day] [month] [year] [list]
Message-ID: <CAHKr1a5tHy1o1Tve87jkgC6AT_Nic6G+BTb8zVEX8KZXwC0Vbg@mail.gmail.com>
Date: Mon, 30 Sep 2013 11:48:06 -0700
From: Sashi Madduri <mail.to.sashi@...il.com>
To: linux-kernel@...r.kernel.org
Cc: tglx@...utronix.de
Subject: getitimer() returns a value different from the one set by setitimer()
for ITIMER_PROF
Doing a getitimer() immediately after a setitimer() on ITIMER_PROF
returns the value incremented by 4ms. I can reproduce the issue with
itimer values less than 1s.
I verified that this issue does not occur on CentOS (kernel 2.6 from Dec 2009).
I checked the source code for kernel/itimer.c, and the following
commit in 2011 seems relevant:
http://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/kernel/itimer.c?id=648616343cdbe904c585a6c12e323d3b3c72e46f
I do not understand the source fully to confirm that the issue is due
to the above commit.
Test program:
#include <sys/time.h>
#include <sys/syscall.h>
#include <unistd.h>
#include <iostream>
int main(int argc, char** argv) {
struct itimerval ts;
ts.it_value.tv_sec = 0;
ts.it_value.tv_usec = 8000;
ts.it_interval.tv_sec = 0;
ts.it_interval.tv_usec = 8000;
for (int i = 0; i < 10; ++i) {
syscall(SYS_setitimer, ITIMER_PROF, &ts, NULL);
syscall(SYS_getitimer, ITIMER_PROF, &ts);
std::cout << "Got back itimer value of " << ts.it_interval.tv_sec
<< ", " << ts.it_interval.tv_usec << "\n";
}
}
My current setup:
/proc/version:
Linux version 3.8.0-19-generic (buildd@...spice) (gcc version 4.7.3
(Ubuntu/Linaro 4.7.3-1ubuntu1) ) #29-Ubuntu SMP Wed Apr 17 18:16:28
UTC 2013
/proc/cpuinfo:
processor : 0
vendor_id : GenuineIntel
cpu family : 6
model : 58
model name : Intel(R) Core(TM) i5-3210M CPU @ 2.50GHz
stepping : 9
cpu MHz : 2379.182
cache size : 6144 KB
physical id : 0
siblings : 4
core id : 0
cpu cores : 4
apicid : 0
initial apicid : 0
fpu : yes
fpu_exception : yes
cpuid level : 5
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov
pat pse36 clflush mmx fxsr sse sse2 ht syscall nx rdtscp lm
constant_tsc rep_good nopl pni ssse3 lahf_lm
bogomips : 4758.36
clflush size : 64
cache_alignment : 64
address sizes : 36 bits physical, 48 bits virtual
power management:
Sashi.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists