operf - Performance profiler tool for Linux
operf [ options ] [ --system-wide | --pid <pid> | [ command [ args ] ] ]
Operf is the profiler tool provided with OProfile. Operf uses the Linux Performance Events Subsystem and, thus, does not require the obsolete oprofile kernel driver. By default, operf uses <current_dir>/oprofile_data as the session-dir and stores profiling data there. You can change this by way of the --session-dir option. The usual post-profiling analysis tools such as opreport(1) and opannotate(1) can be used to generate profile reports. Unless a session-dir is specified, the post-processing analysis tools will search for samples in <current_dir>/oprofile_data first. If that directory does not exist, the post-processing tools use the standard session-dir of /var/lib/oprofile. Statistics, such as total samples received and lost samples, are written to the operf.log file that can be found in the <session_dir>/samples directory.
One (and only one) of the following run modes must be specified: command[args] The command or application to be profiled. args are the input arguments that the command or application requires. --pid / -p PID This option enables operf to profile a running application. PID should be the process ID of the process you wish to profile. When finished profiling (e.g., when the profiled process ends), press Ctrl-c to stop operf. If you run operf --pid as a background job (i.e., with the &), you must stop it in a controlled manner in order for it to process the profile data it has collected. Use kill -SIGINT <operf-PID> for this purpose. Limitation: When using this option to profile a multi-threaded application that also forks new processes, be aware that samples for processes that are forked before profiling is started may not be recorded (depending on timing of thread creation and when operf is started). --system-wide / -s This option is for performing a system-wide profile. You must have root authority to run operf in this mode. When finished profiling, Ctrl-c to stop operf. If you run operf --system-wide as a background job (i.e., with the &), you must stop it in a controlled manner in order for it to process the profile data it has collected. Use kill -SIGINT <operf-PID> for this purpose. It is recommended that when running operf with this option, the user's current working directory should be /root or a subdirectory of /root to avoid storing sample data files in locations accessible by regular users.
--vmlinux / -k vmlinux_path A vmlinux file that matches the running kernel that has symbol and/or debuginfo. Kernel samples will be attributed to this binary, allowing post-processing tools (like opreport) to attribute samples to the appropriate kernel symbols. The kernel symbol information may be obtained from /proc/kallsyms if the user does not specify a vmlinux file. The symbol addresses are given in /proc/kallsyms if permitted by the setting of /proc/sys/kernel/kptr_restrict. If the --vmlinux option is not used and kernel symbols cannot be obtained from /proc/kallsyms, then all kernel samples are attributed to "no-vmlinux", which is simply a bucket to hold the samples and not an actual file. --events / -e event1[,event2[,...]] This option is for passing a comma-separated list of event specifications for profiling. Each event spec is of the form: name:count[:unitmask[:kernel[:user]]] The count value is used to control the sampling rate for profiling; it is the number of events to occur between samples. The rate is lowered by specifying a higher count value --- i.e., a higher number of events to occur between samples. 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 collect samples for kernel space and user space. Note: In order to specify the kernel/user bits, you must also specify a unitmask value, even if the processor type (or the specified event) does not use unit masks --- in which case, use the value '0' to signify a null unit mask; for example: -e INST_RETIRED_ANY_P:100000:0:1:0 ^ ^ ^ ^ | | | |--- '0': do not record user space samples | | |-- '1': record kernel space samples | |-- '0': the null unit mask |--count value Event names for some IBM PowerPC systems include a _GRP<n> (group number) suffix. You can pass either the full event name or the base event name (i.e., without the suffix) to operf. If the base event name is passed, operf will automatically choose an appropriate group number suffix for the event; thus, OProfile post-processing tools will always show real event names that include the group number suffix. When no event specification is given, the default event for the running processor type will be used for profiling. Use ophelp to list the available events for your processor type. --callgraph / -g This option enables the callgraph to be saved during profiling. NOTE: The full callchain is recorded, so there is no depth limit. --separate-thread / -t This option categorizes samples by thread group ID (tgid) and thread ID (tid). The '--separate-thread' option is useful for seeing per-thread samples in multi-threaded applications. When used in conjunction with the '--system-wide' option, the '--separate-thread' option is also useful for seeing per-process (i.e., per-thread group) samples for the case where multiple processes are executing the same program during a profiling run. --separate-cpu / -c This option categorizes samples by cpu. --session-dir / -d path This option specifies the session path to hold the sample data. If not specified, the data is saved in the oprofile_data directory on the current path. --lazy-conversion / -l Use this option to reduce the overhead of operf during profiling. Normally, profile data received from the kernel is converted to OProfile format during profiling time. This is typically not an issue when profiling a single application. But when using the --system-wide option, this on-the-fly conversion process can cause noticeable overhead, particularly on busy multi-processor systems. The --lazy-conversion option directs operf to wait until profiling is completed to do the conversion of profile data. Note: This option is not recommended to be used in conjunction with the --pid option for profiling multi-threaded processes. Depending on the order of thread creation (or forking of new processes), you may not get any samples for the new threads/processes. --append / -a By default, operf moves old profile data from <session_dir>/samples/current to <session_dir>/samples/previous. If a 'previous' profile already existed, it will be replaced. If the --append option is passed, old profile data is left in place and new profile data will be added to it, and the 'previous' profile (if one existed) will remain untouched. To access the 'previous' profile, simply add a session specification to the normal invocation of oprofile post- processing tools. For example: opreport session:previous --verbose / -V level A comma-separated list of debugging control values, used to increase the verbosity of the output. Valid values are: debug, record, convert, misc, sfile, arcs, or the special value, 'all'. --version / -v Show operf version. --help / -h Display brief usage message. --usage / -u Display brief usage message.
$ operf make
This man page is current for oprofile-1.1.0.
More Linux Commands
Tcl_GetBoolean(3) - convert from string to integer, double,
These procedures convert from strings to integers or double-precision floating-point values or booleans (represented as 0- or 1-valued integers). Each of the pr
Tk_Main(3) - main program for Tk-based applications.........
Tk_Main acts as the main program for most Tk-based applications. Starting with Tk 4.0 it is not called main anymore because it is part of the Tk library and hav
XrmQGetSearchList(3) - retrieve database resources and searc
The XrmGetResource and XrmQGetResource functions retrieve a resource from the specified database. Both take a fully qualified name/class pair, a destination res
mmap2(2) - map files or devices into memory - Linux man page
This is probably not the system call that you are interested in; instead, see mmap(2), which describes the glibc wrapper function that invokes this system call.
XvGetStill(3) - capture a single frame of video from a drawa
captures a single frame of video from a drawable. The position and size of the destination (video) rectangle is specified by vx, vy, vw, and vh. The position an
capget(2) - set/get capabilities of thread(s) (Man Page)....
As of Linux 2.2, the power of the superuser (root) has been partitioned into a set of discrete capabilities. Each thread has a set of effective capabilities ide
DBI::Util::CacheMemory(3pm) - a very fast but very minimal s
Like Cache::Memory (part of the Cache distribution) but doesnt support any fancy features. This module aims to be a very fast compatible strict sub-set for simp
putwchar(3) - write a wide character to standard output.....
The putwchar() function is the wide-character equivalent of the putchar(3) function. It writes the wide character wc to stdout. If ferror(stdout) becomes true,
tcl_startOfPreviousWord(n) - standard library of Tcl procedu
Tcl includes a library of Tcl procedures for commonly-needed functions. The procedures defined in the Tcl library are generic ones suitable for use by many diff
sigreturn(2) - return from signal handler and cleanup stack
When the Linux kernel creates the stack frame for a signal handler, a call to sigreturn() is inserted into the stack frame so that upon return from the signal h
mvinwstr(3ncurses) - get a string of wchar_t characters from
These routines return a string of wchar_t characters in wstr, extracted starting at the current cursor position in the named window. Attributes are stripped fro
scale(n) - Create and manipulate scale widgets (Man Page)...
The scale command creates a new window (given by the pathName argument) and makes it into a scale widget. Additional options, described above, may be specified