1ocount(1) General Commands Manual ocount(1)
2
3
4
6 ocount - Event counting tool for Linux
7
8
10 ocount [ options ] [ --system-wide | --process-list <pids> | --thread-
11 list <tids> | --cpu-list <cpus> [ command [ args ] ] ]
12
13
15 ocount is an OProfile tool that can be used to count native hardware
16 events occurring in either a given application, a set of processes or
17 threads, a subset of active system processors, or the entire system.
18 The data collected during a counting session is displayed to stdout by
19 default or, optionally, to a file.
20
21 When counting multiple events, the kernel may not be able to count all
22 events simultaneously and, thus, may need to multiplex the counting of
23 the events. If this happens, the "Percent time enabled" column in the
24 ocount output will be less than 100, but counts are scaled up to a 100%
25 estimated value.
26
27
29 One (and only one) of the following run modes must be specified. If
30 you run ocount using a run mode other than command [args] , press Ctrl-
31 c to stop ocount when finished counting (e.g., when the monitored
32 process ends). If you background ocount (i.e., with '&') while using
33 one these run modes, you must stop it in a controlled manner so that
34 the data collection process can be shut down cleanly and final results
35 can be displayed. Use kill -SIGINT <ocount-PID> for this purpose.
36
37 command [args]
38 The command is the application for which to count events. args
39 are the input arguments required by the application. The com‐
40 mand and its arguments must be positioned at the end of the com‐
41 mand line, after all ocount options.
42
43 --process-list / -p pids
44 Use this option to count events for one or more already-running
45 applications, specified via a comma-separated list ( pids ).
46 Event counts will be collected for all children of the passed
47 process(es) as well.
48
49
50 --thread-list / -r tids
51 Use this option to count events for one or more already-running
52 threads, specified via a comma-separated list ( tids ). Event
53 counts will not be collected for any children of the passed
54 thread(s).
55
56
57 --system-wide / -s
58 This option is for counting events for all processes running on
59 your system. You must have root authority to run ocount in this
60 mode.
61
62
63 --cpu-list / -C cpus
64 This option is for counting events on a subset of processors on
65 your system. You must have root authority to run ocount in this
66 mode. This is a comma-separated list, where each element in the
67 list may be either a single processor number or a range of pro‐
68 cessor numbers; for example: '-C 2,3,4-11,15'.
69
70
72 --events / -e event1[,event2[,...]]
73 This option is for passing a comma-separated list of event spec‐
74 ifications for counting. Each event spec is of the form:
75 name[:unitmask[:kernel[:user]]]
76 Note: Do not include a count value in the event spec, as that
77 parameter is only need when profiling.
78
79 You can specify unit mask values using either a numerical value
80 (hex values must begin with "0x") or a symbolic name (if the
81 name=<um_name> field is shown in the ophelp output). For some
82 named unit masks, the hex value is not unique; thus, OProfile
83 tools enforce specifying such unit masks value by name. If no
84 unit mask is specified, the default unit mask value for the
85 event is used.
86
87 Event names for certain processor types include a _GRP<n> suf‐
88 fix. For such cases, the --events option may be specified with
89 or without the _GRP<n> suffix.
90
91 When no event specification is given, the default event for the
92 running processor type will be used for counting. Use ophelp to
93 list the available events for your processor type.
94
95
96 --separate-thread / -t
97 This option can be used in conjunction with either the
98 --process-list or --thread-list option to display event counts
99 on a per-thread (per-process) basis. Without this option, all
100 counts are aggregated.
101
102 NOTE: If new threads are started by the process(es) being moni‐
103 tored after counting begins, the counts for those threads are
104 aggregated with their parent's counts.
105
106
107 --separate-cpu / -c
108 This option can be used in conjunction with either the --system-
109 wide or --cpu-list option to display event counts on a per-cpu
110 basis. Without this option, all counts are aggregated.
111
112
113 --time-interval / -i num_seconds[:num_intervals]
114 Results collected for each time interval are printed every
115 num_seconds instead of the default of one dump of cumulative
116 event counts at the end of the run. If num_intervals is speci‐
117 fied, ocount exits after the specified number of intervals
118 occur.
119
120
121 --brief-format / -b
122 Use this option to print results in the following brief format:
123 [optional cpu or thread,]<event_name>,<count>,<per‐
124 cent_time_enabled>
125 [ <int> ,]< string >,< u64 >,< double
126 >
127
128 If --timer-interval is specified, a separate line formatted as
129 timestamp,<num_seconds_since_epoch>
130 is printed ahead of each dump of event counts.
131
132
133 --output-file / -f outfile_name
134 Results are written to outfile_name instead of interactively to
135 the terminal.
136
137 --verbose / -V
138 Use this option to increase the verbosity of the output.
139
140 --version / -v
141 Show ocount version.
142
143 --help / -h
144 Display brief usage message.
145
146 --usage / -u
147 Display brief usage message.
148
149
151 $ ocount make
152
153
155 This man page is current for oprofile-0.9.9.
156
157
159 operf(1).
160
161
162
163oprofile 0.9.9 Tue 21 March 2017 ocount(1)