Commit 09338fb0 authored by Mauro Carvalho Chehab's avatar Mauro Carvalho Chehab Committed by Jonathan Corbet

cpu-load: standardize document format

Each text file under Documentation follows a different
format. Some doesn't even have titles!

Change its representation to follow the adopted standard,
using ReST markups for it to be parseable by Sphinx:

- mark literals;
- Adjust document title;
- Use a list for references.
Signed-off-by: default avatarMauro Carvalho Chehab <mchehab@s-opensource.com>
Signed-off-by: default avatarJonathan Corbet <corbet@lwn.net>
parent f68ac62d
========
CPU load CPU load
-------- ========
Linux exports various bits of information via `/proc/stat' and Linux exports various bits of information via ``/proc/stat`` and
`/proc/uptime' that userland tools, such as top(1), use to calculate ``/proc/uptime`` that userland tools, such as top(1), use to calculate
the average time system spent in a particular state, for example: the average time system spent in a particular state, for example::
$ iostat $ iostat
Linux 2.6.18.3-exp (linmac) 02/20/2007 Linux 2.6.18.3-exp (linmac) 02/20/2007
...@@ -17,7 +18,7 @@ Here the system thinks that over the default sampling period the ...@@ -17,7 +18,7 @@ Here the system thinks that over the default sampling period the
system spent 10.01% of the time doing work in user space, 2.92% in the system spent 10.01% of the time doing work in user space, 2.92% in the
kernel, and was overall 81.63% of the time idle. kernel, and was overall 81.63% of the time idle.
In most cases the `/proc/stat' information reflects the reality quite In most cases the ``/proc/stat`` information reflects the reality quite
closely, however due to the nature of how/when the kernel collects closely, however due to the nature of how/when the kernel collects
this data sometimes it can not be trusted at all. this data sometimes it can not be trusted at all.
...@@ -33,78 +34,78 @@ Example ...@@ -33,78 +34,78 @@ Example
------- -------
If we imagine the system with one task that periodically burns cycles If we imagine the system with one task that periodically burns cycles
in the following manner: in the following manner::
time line between two timer interrupts time line between two timer interrupts
|--------------------------------------| |--------------------------------------|
^ ^ ^ ^
|_ something begins working | |_ something begins working |
|_ something goes to sleep |_ something goes to sleep
(only to be awaken quite soon) (only to be awaken quite soon)
In the above situation the system will be 0% loaded according to the In the above situation the system will be 0% loaded according to the
`/proc/stat' (since the timer interrupt will always happen when the ``/proc/stat`` (since the timer interrupt will always happen when the
system is executing the idle handler), but in reality the load is system is executing the idle handler), but in reality the load is
closer to 99%. closer to 99%.
One can imagine many more situations where this behavior of the kernel One can imagine many more situations where this behavior of the kernel
will lead to quite erratic information inside `/proc/stat'. will lead to quite erratic information inside ``/proc/stat``::
/* gcc -o hog smallhog.c */ /* gcc -o hog smallhog.c */
#include <time.h> #include <time.h>
#include <limits.h> #include <limits.h>
#include <signal.h> #include <signal.h>
#include <sys/time.h> #include <sys/time.h>
#define HIST 10 #define HIST 10
static volatile sig_atomic_t stop; static volatile sig_atomic_t stop;
static void sighandler (int signr) static void sighandler (int signr)
{ {
(void) signr; (void) signr;
stop = 1; stop = 1;
} }
static unsigned long hog (unsigned long niters) static unsigned long hog (unsigned long niters)
{ {
stop = 0; stop = 0;
while (!stop && --niters); while (!stop && --niters);
return niters; return niters;
} }
int main (void) int main (void)
{ {
int i; int i;
struct itimerval it = { .it_interval = { .tv_sec = 0, .tv_usec = 1 }, struct itimerval it = { .it_interval = { .tv_sec = 0, .tv_usec = 1 },
.it_value = { .tv_sec = 0, .tv_usec = 1 } }; .it_value = { .tv_sec = 0, .tv_usec = 1 } };
sigset_t set; sigset_t set;
unsigned long v[HIST]; unsigned long v[HIST];
double tmp = 0.0; double tmp = 0.0;
unsigned long n; unsigned long n;
signal (SIGALRM, &sighandler); signal (SIGALRM, &sighandler);
setitimer (ITIMER_REAL, &it, NULL); setitimer (ITIMER_REAL, &it, NULL);
hog (ULONG_MAX); hog (ULONG_MAX);
for (i = 0; i < HIST; ++i) v[i] = ULONG_MAX - hog (ULONG_MAX); for (i = 0; i < HIST; ++i) v[i] = ULONG_MAX - hog (ULONG_MAX);
for (i = 0; i < HIST; ++i) tmp += v[i]; for (i = 0; i < HIST; ++i) tmp += v[i];
tmp /= HIST; tmp /= HIST;
n = tmp - (tmp / 3.0); n = tmp - (tmp / 3.0);
sigemptyset (&set); sigemptyset (&set);
sigaddset (&set, SIGALRM); sigaddset (&set, SIGALRM);
for (;;) { for (;;) {
hog (n); hog (n);
sigwait (&set, &i); sigwait (&set, &i);
} }
return 0; return 0;
} }
References References
---------- ----------
http://lkml.org/lkml/2007/2/12/6 - http://lkml.org/lkml/2007/2/12/6
Documentation/filesystems/proc.txt (1.8) - Documentation/filesystems/proc.txt (1.8)
Thanks Thanks
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment