ocount man page

ocount — Event counting tool for Linux


ocount [ options ] [ --system-wide | --process-list <pids> | --thread-list <tids> | --cpu-list <cpus> | [ command [ args ] ] ]


ocount is an OProfile tool that can be used to count native hardware events occurring in either a given application, a set of processes or threads, a subset of active system processors, or the entire system. The data collected during a counting session is displayed to stdout by default or, optionally, to a file.

When counting multiple events, the kernel may not be able to count all events simultaneously and, thus, may need to multiplex the counting of the events. If this happens, the "Percent time enabled" column in the ocount output will be less than 100, but counts are scaled up to a 100% estimated value.

Run Modes

One (and only one) of the following run modes must be specified.  If you run ocount using a run mode other than command [args] , press Ctrl-c to stop ocount when finished counting (e.g., when the monitored process ends). If you background ocount (i.e., with '&') while using one these run modes, you must stop it in a controlled manner so that the data collection process can be shut down cleanly and final results can be displayed. Use kill -SIGINT <ocount-PID> for this purpose.

command [args]

The command is the application for which to count events. args are the input arguments required by the application. The command and its arguments must be positioned at the end of the command line, after all ocount options.

--process-list / -p pids

Use this option to count events for one or more already-running applications, specified via a comma-separated list ( pids ). Event counts will be collected for all children of the passed process(es) as well. You must have privileges for the user ID under which the specified process(es) are running; e.g., for a non-root user, the user ID of the process(es) is the same as that used for running ocount. A lack of privileges will result in the following failure message:
       perf_event_open failed with Permission denied

--thread-list / -r tids

Use this option to count events for one or more already-running threads, specified via a comma-separated list ( tids ). Event counts will not be collected for any children of the passed thread(s). See the description of --process-list concerning required privileges.

--system-wide / -s

This option is for counting events for all processes running on your system.  You must have root authority to run ocount in this mode.

--cpu-list / -C cpus

This option is for counting events on a subset of processors on your system. You must have root authority to run ocount in this mode. This is a comma-separated list, where each element in the list may be either a single processor number or a range of processor numbers; for example: '-C 2,3,4-11,15'.

Other Options

--events / -e event1[,event2[,...]]

This option is for passing a comma-separated list of event specifications for counting. Each event spec is of the form:
Note: Do not include a count value in the event spec, as that parameter is only needed when profiling.

You can specify unitmask values using either a numerical value (hex values must begin with "0x") or a symbolic name (if the name=<um_name> field is shown in the ophelp output). For some named unit masks, the hex value is not unique; thus, OProfile tools enforce specifying such unit masks value by name. If no unit mask is specified, the default unit mask value for the event is used.

The kernel and user parts of the event specification are binary values ('1' or '0') indicating whether or not to count events in kernel space and user space.
Note: In order to specify the kernel/user bits, you must also specify a unitmask value, even if the running processor type does not use unit masks — in which case, use the value '0' to signify a null unit mask; for example:
                        ^ ^ ^
                        | | |--- '0': do not count user space events
                        | |-- '1': count kernel space events
                        |-- '0': the null unit mask

Event names for certain processor types include a _GRP<n> suffix.  For such cases, the --events option may be specified with or without the _GRP<n> suffix.

When no event specification is given, the default event for the running processor type will be used for counting. Use ophelp to list the available events for your processor type.

--separate-thread / -t

This option can be used in conjunction with either the --process-list or --thread-list option to display event counts on a per-thread (per-process) basis.  Without this option, all counts are aggregated.

NOTE: If new threads are started by the process(es) being monitored after counting begins, the counts for those threads are aggregated with their parent's counts.

--separate-cpu / -c

This option can be used in conjunction with either the --system-wide or --cpu-list option to display event counts on a per-cpu basis.  Without this option, all counts are aggregated.

--time-interval / -i interval_length[:num_intervals]

Note: The interval_length is given in milliseconds. However, the current implementation only supports 100 ms granularity, so the given interval_length will be rounded to the nearest 100 ms. Results collected for each time interval are printed immediately instead of the default of one dump of cumulative event counts at the end of the run. Counters are reset to zero at the start of each interval.

If num_intervals is specified, ocount exits after the specified number of intervals occur.

--brief-format / -b

Use this option to print results in the following brief format:
   [cpu or thread,]<event_name>[:umask[:K:U]],<count>,<percent_time_enabled>
   [    <u32>    ,]<  string  >[< u32>[<bb>]],< u64 >,<       double       >

The umask, Kernel and User modes are only printed if the values were specified as part of the event. The 'K' and 'U' fields are binary fields separated by colons, where the value for each binary field may be either '0' or '1'.

If --timer-interval is specified, a separate line formatted as
is printed ahead of each dump of event counts. If the time interval specified is less than one second, the timestamp will have 1/10 second precision.

--output-file / -f outfile_name

Results are written to outfile_name instead of interactively to the terminal.

--verbose / -V

Use this option to increase the verbosity of the output.

--version / -v

Show ocount version.

--help / -h

Display brief usage message.

--usage / -u

Display brief usage message.


$ ocount make


This man page is current for oprofile-1.2.0.

See Also


Referenced By


Sat 14 July 2018 oprofile 1.2.0