1========
  2CPU load
  3========
  4
  5Linux exports various bits of information via ``/proc/stat`` and
  6``/proc/uptime`` that userland tools, such as top(1), use to calculate
  7the average time system spent in a particular state, for example::
  8
  9    $ iostat
 10    Linux 2.6.18.3-exp (linmac)     02/20/2007
 11
 12    avg-cpu:  %user   %nice %system %iowait  %steal   %idle
 13              10.01    0.00    2.92    5.44    0.00   81.63
 14
 15    ...
 16
 17Here the system thinks that over the default sampling period the
 18system spent 10.01% of the time doing work in user space, 2.92% in the
 19kernel, and was overall 81.63% of the time idle.
 20
 21In most cases the ``/proc/stat``	 information reflects the reality quite
 22closely, however due to the nature of how/when the kernel collects
 23this data sometimes it can not be trusted at all.
 24
 25So how is this information collected?  Whenever timer interrupt is
 26signalled the kernel looks what kind of task was running at this
 27moment and increments the counter that corresponds to this tasks
 28kind/state.  The problem with this is that the system could have
 29switched between various states multiple times between two timer
 30interrupts yet the counter is incremented only for the last state.
 31
 32
 33Example
 34-------
 35
 36If we imagine the system with one task that periodically burns cycles
 37in the following manner::
 38
 39     time line between two timer interrupts
 40    |--------------------------------------|
 41     ^                                    ^
 42     |_ something begins working          |
 43                                          |_ something goes to sleep
 44                                         (only to be awaken quite soon)
 45
 46In the above situation the system will be 0% loaded according to the
 47``/proc/stat`` (since the timer interrupt will always happen when the
 48system is executing the idle handler), but in reality the load is
 49closer to 99%.
 50
 51One can imagine many more situations where this behavior of the kernel
 52will lead to quite erratic information inside ``/proc/stat``::
 53
 54
 55	/* gcc -o hog smallhog.c */
 56	#include <time.h>
 57	#include <limits.h>
 58	#include <signal.h>
 59	#include <sys/time.h>
 60	#define HIST 10
 61
 62	static volatile sig_atomic_t stop;
 63
 64	static void sighandler (int signr)
 65	{
 66	(void) signr;
 67	stop = 1;
 68	}
 69	static unsigned long hog (unsigned long niters)
 70	{
 71	stop = 0;
 72	while (!stop && --niters);
 73	return niters;
 74	}
 75	int main (void)
 76	{
 77	int i;
 78	struct itimerval it = { .it_interval = { .tv_sec = 0, .tv_usec = 1 },
 79				.it_value = { .tv_sec = 0, .tv_usec = 1 } };
 80	sigset_t set;
 81	unsigned long v[HIST];
 82	double tmp = 0.0;
 83	unsigned long n;
 84	signal (SIGALRM, &sighandler);
 85	setitimer (ITIMER_REAL, &it, NULL);
 86
 87	hog (ULONG_MAX);
 88	for (i = 0; i < HIST; ++i) v[i] = ULONG_MAX - hog (ULONG_MAX);
 89	for (i = 0; i < HIST; ++i) tmp += v[i];
 90	tmp /= HIST;
 91	n = tmp - (tmp / 3.0);
 92
 93	sigemptyset (&set);
 94	sigaddset (&set, SIGALRM);
 95
 96	for (;;) {
 97		hog (n);
 98		sigwait (&set, &i);
 99	}
100	return 0;
101	}
102
103
104References
105----------
106
107- http://lkml.org/lkml/2007/2/12/6
108- Documentation/filesystems/proc.txt (1.8)
109
110
111Thanks
112------
113
114Con Kolivas, Pavel Machek