Subversion Repositories openrisc

<PART ID="services-cpuload">
<TITLE>CPU load measurements</TITLE>
<PARTINTRO>
<PARA>
The cpuload package provides a way to estimate the cpuload. It gives
an estimated percentage load for the last 100 milliseconds, 1 second
and 10 seconds.
</PARA>
</PARTINTRO>
<CHAPTER id="cpuload-functions">
<TITLE>CPU Load Measurements</TITLE>
<SECT1 id="services-cpuload-api">
<TITLE>CPU Load API</TITLE>
<para>
The package allows the CPU load to be estimated. The measurement code
must first be calibrated to the target it is running on. Once this
has been performed the measurement process can be started. This is a
continuous process, so always providing the most up to data
measurements. The process can be stopped at any time if required. Once
the process is active, the results can be retrieved.
</para>
<para>
Note that if the target/processor performs any power saving actions,
such as reducing the clock speed, or halting until the next interrupt
etc, these will interfere with the CPU load measurement. Under these
conditions the measurement results are undefined. The synthetic target
is one such system. See the implementation details at the foot of this
page for further information.  </para>
<para>
SMP systems are not supported, only uniprocessor system.
</para> 
<para> The API for load measuring functions can be
found in the file <filename>cyg/cpuload/cpuload.h</filename>.
</para>
<sect2 id="services-cpuload-api-cyg-cpuload-calibrate">
<title>cyg_cpuload_calibrate</title>
<para>
This function is used to calibrate the cpu load measurement code. It
makes a measurement to determine the CPU properties while idle.
</para>
<programlisting>
void cyg_cpuload_calibrate(cyg_uint32  *calibration);
</programlisting>
<para>
The function returns the calibration value at the location pointed to
by <parameter>calibration</parameter>.
</para>
<para>
This function is quite unusual. For it to work correctly a few
conditions must be met. The function makes use of the two highest
thread priorities. No other threads must be using these priorities
while the function is being used. The kernel scheduler must be started
and not disabled. The function takes 100ms to complete during which
time no other threads will be run.
</para>
</sect2>
<sect2 id="services-cpuload-api-cyg-cpuload-create">
<title>cyg_cpuload_create</title>
<para>
This function starts the CPU load measurments.
</para>
<programlisting>
void cyg_cpuload_create(cyg_cpuload_t *cpuload, 
                        cyg_uint32 calibrate,
                        cyg_handle_t *handle);
</programlisting>
<para>
The measurement process is started and a handle to it is returned in
<parameter>*handle</parameter>. This handle is used to access the
results and the stop the measurement process. </para>
</sect2>

<sect2 id="services-cpuload-api-cyg-cpuload-delete">
<title>cyg_cpuload_delete</title>
<para>
This function stops the measurement process. 
</para>
<programlisting>
void cyg_cpuload_delete(cyg_handle_t handle);
</programlisting>
<para>
<parameter>handle</parameter> should be the value returned by the create function.</para>
</sect2>

<sect2 id="services-cpuload-api-cyg-cpuload-get">
<title>cyg_cpuload_get</title>
<para>
This function returns the latest measurements.
</para>
<programlisting>
void cyg_cpuload_get(cyg_handle_t handle,
                 cyg_uint32 *average_point1s,       
                 cyg_uint32 *average_1s,            
                 cyg_uint32 *average_10s);
</programlisting>
<para>
<parameter>handle</parameter> should be the value returned by the
create function. The load measurements for the last 100ms, 1s and 10s
are returned in
<parameter>*average_point1s</parameter>,<parameter>*average_1s</parameter>
and <parameter>*average_10s</parameter> respectively.
</para>
</sect2>
<sect2 id="services-cpuload-api-implementation">
<title>Implementation details</title>
<para>
This section gives a few details of how the measurements are
made. This should help to understand what the results mean.
</para>
<para>
When there are no other threads runnable, eCos will execute the idle
thread. This thread is always runnable and uses the lowest thread
priority. The idle thread does little. It is an endless loop which
increments the variable, <literal>idle_thread_loops</literal> and
executes the macro <literal>HAL_IDLE_THREAD_ACTION</literal>. The cpu
load measurement code makes use of the variable. It periodically
examines the value of the variable and sees how much it has
changed. The idler the system, the more it will have incremented. From
this it is simple to determine the load of the system.
</para>
<para>
The function <literal>cyg_cpuload_calibrate</literal> executes the
idle thread for 100ms to determine how much
<literal>idle_thread_loops</literal> is incremented on a system idle
for 100ms. <literal>cyg_cpuload_create</literal> starts an alarm which
every 100ms calls an alarm function. This function looks at the
difference in <literal>idle_thread_loops</literal> since the last
invocation of the alarm function and so calculated how idle or busy
the system has been. The structure <literal>cyg_cpuload</literal> is
updated during the alarm functions with the new results.  The 100ms
result is simply the result from the last measurement period. A simple
filter is used to average the load over a period of time, namely 1s
and 10s. Due to rounding errors, the 1s and 10s value will probably
never reach 100% on a fully loaded system, but 99% is often seen.
</para>
<para>
As stated above, clever power management code will interfere with
these measurements. The basic assumption is that the idle thread will
be executed un-hindered and under the same conditions as when the
calibration function was executed. If the CPU clock rate is reduced,
the idle thread counter will be incremented less and so the CPU load
measurements will give values too high. If the CPU is halted entirely,
100% cpu load will be measured.
</para>
</sect2>
</SECT1>
</CHAPTER>
</PART>