gprof(1)gprof(1)NAMEgprof - display call graph profile data
SYNOPSIS
[options] [a.out [gmon.out...]]
DESCRIPTION
The command produces an execution profile of C++, C and FORTRAN pro‐
grams. The effect of called routines is incorporated into the profile
of each caller. Profile data is taken from the call graph profile file
default) that is created by programs compiled with the option of and
The option also links in versions of the library routines that are com‐
piled for profiling.
On Itanium(R)-based systems, supports multiple shared libraries profil‐
ing. On PA-RISC systems, supports single shared library profiling.
For details on this see the section below,
The symbol table for the load modules being profiled are read and cor‐
related with the call graph profile file To have the full call graph,
no load module symbol table may be chopped; that is, no compiles may
use the option. If more than one profile file is specified, output
shows the sum of the profile information in the given profile files.
First, a flat profile is given, similar to that provided by (see
prof(1)). This listing gives the total execution times and call counts
for each function in the load modules being profiled, sorted by
decreasing time. On Itanium-based systems, the module index is also
reported for each function signifying the load module in which the
function is defined.
Next, these times are propagated along the edges of the call graph.
discovers all cycles in the call graph. All calls made into the cycle
share the time of that cycle. A second listing shows the functions
sorted according to the time they represent including the time of their
call graph descendants. Below each function entry is shown its
(direct) call graph children, and how their times are propagated to
this function. A similar display above the function shows how the time
of this function and the time of its descendants are propagated to its
(direct) call graph parents.
Cycles are also shown, with an entry for the cycle as a whole and a
listing of the members of the cycle, each with their contributions to
the time and call counts of the cycle.
On Itanium-based systems, in the end a mapping of all module indices to
module names is given. The modules not being profiled are reported at
the top of output.
Shared Library Profiling
Support for profiling of shared libraries is available both on 32-bit
and 64-bit Itanium-based systems. On PA-RISC systems only 32-bit
shared library profiling is supported.
The environment variable determines what load modules get pro‐
filed. Set to profile all load modules; that is, report timing
and call count information for all loadable modules, including
Set to profile only loadable modules ldm1 and ldm2. ldm1 and
ldm2 are not full pathnames; they are the names recorded in the
executables, which can be displayed using chatr(1). If is not
set, behaves as though
The environment variable controls the size of profiling coun‐
ters. The acceptable value for this variable is 16 or 32.
Counter size can also be specified at compile time using the
option. The runtime value overrides the compile time value. A
warning is issued if the counter size is set to a value other
than 16 or 32; in this case the value specified at compile time
is used. The default value of the counter is 16, which is used
if a valid value is not specified. See the description of the
option in cc(1) for more details.
At program termination the library dumps all profiling informa‐
tion on a per-module basis in which the command reads and
matches to corresponding functions in the load modules.
To profile a shared library, set the environment variable to the
path of the shared library to be profiled. (See for details.)
Do not use the option to compile programs for shared library
profiling. Do not link the executable or This turns on profil‐
ing of which is not compatible with profiling of shared
libraries. You can either profile your executable or a shared
library, but not both.
Set to the exact string with which you call If the library is
implicitly loaded, must match the path encoded in the You can
find this value by running the command on the executable.
At the termination of the program, a profile file with the name
of the shared library prepended to it is generated by a run-time
library. To get the complete listing, provide the command with
names of the shared library and the profile file for the shared
library as arguments.
Options
The command recognizes the following options:
Suppress printing statically declared functions.
If this option is given, all relevant information
about the static function (such as time samples,
calls to other functions, and calls from other
functions) belongs to the function loaded just
before the static function in the file.
Suppress printing a description of each field in the profile.
Suppress printing the graph profile entry for routine
name and all its descendants (unless they have
other ancestors that are not suppressed). More
than one option can be given. Only one name can
be given with each option.
Suppress printing the graph profile entry for routine
name (and its descendants) as above, and also
exclude the time spent in name (and its descen‐
dants) from the total and percentage time compu‐
tations. is the default.
Print only the graph profile entry of the specified routine
name and its descendants. More than one option
can be given. Only one name can be given with
each option.
Print only the graph profile entry of the routine
name and its descendants (as above) and also use
only the times of the printed routines in total
time and percentage computations. More than one
option can be given. Only one name can be given
with each option. The option overrides the
option.
Produce just the flat profile output
exactly similar to one given by (see prof(1)).
Produce a profile file
that represents the sum of the profile informa‐
tion in all specified profile files. This sum‐
mary profile file can be given to subsequent exe‐
cutions of (probably also with a option) to accu‐
mulate profile data across several runs of an
file. should be set to the same string for all
the runs.
Produce just the static output in
This is used for testing purposes. It eliminates
all the timing information from normal output and
reports only the call count part.
Display routines that have zero usage
(as indicated by call counts and accumulated
time).
The environment variable controls the name of the file created by a
profiled program. If is not set, is produced in the current directory
when the program terminates. If is produced, where progname is with
any path prefix removed, and pid is the program's process ID. If is
set to a null string, no profiling output is produced.
EXTERNAL INFLUENCES
Environment Variables
determines the modules to be profiled.
controls the size of profiling counters.
controls the path and name of the file created by a profiled program.
EXAMPLES
To profile and on Itanium-based systems:
$ cat > test.c
void a()
{
printf("I in a\n");
}
$ cc -c +Z -G test.c
$ ld -b -o libtest.so.1 test.o
$ ln -s ./libtest.so.1 libtest.so
$ cat > main.c
extern void a();
main()
{
printf("Hello world\n");
a();
}
$ cc -G main.c -L. -ltest
$ export LD_PROFILE=a.out:libtest.so
$ export LD_PROFILEBUCKET_SIZE=16
$ ./a.out
hello world
I in a
$ unset LD_PROFILE
$ unset LD_PROFILEBUCKET_SIZE
$ ls gmon.out
gmon.out
$ gprof
To profile on PA-RISC systems:
$ cat > test.c
main()
{
printf("hello world\n");
}
$ cc test.c -lc
$ ldd a.out
/usr/lib/libc.2 => /usr/lib/libc.2
/usr/lib/libdld.2 => /usr/lib/libdld.2
/usr/lib/libc.2 => /usr/lib/libc.2
$ export LD_PROFILE=/usr/lib/libc.2
$ ./a.out
hello world
$ unset LD_PROFILE
$ ls libc.2.profile
libc.2.profile
$ gprof /usr/lib/libc.2 libc.2.profile
WARNINGS
Beware of quantization errors. The granularity of the sampling is
shown, but remains statistical at best. It is assumed that the time
for each execution of a function can be expressed by the total time for
the function, divided by the number of times the function is called.
Thus the time propagated along the call graph arcs to parents of that
function is directly proportional to the number of times that arc is
traversed.
Parents that are not profiled have the time of their profiled children
propagated to them, but they appear to be spontaneously invoked in the
call graph listing, and do not have their time propagated further.
Similarly, signal catchers, even though profiled, appear to be sponta‐
neous (although for more obscure reasons). Any profiled children of
signal catchers should have their times propagated properly unless the
signal catcher was invoked during the execution of the profiling rou‐
tine, in which case all is lost.
The following limitations exist for shared library profiling on PA-RISC
systems:
· Local, static, and hidden functions are not profiled.
· Shared libraries built with are not profiled.
· Any function calls made from library initializers are not col‐
lected.
DEPENDENCIES
cannot be used with dynamically linked executables (built with in pre-
HP-UX 10.20 releases).
AUTHOR
was developed by the University of California, Berkeley.
FILES
Default object file.
Default dynamic call graph and profile.
Summarized dynamic call graph and profile.
Call graph description.
Flat profile description.
32-bit shared library on Itanium-based systems.
64-bit shared library on Itanium-based systems.
32-bit shared library on PA-RISC systems.
64-bit shared library on PA-RISC systems.
SEE ALSOaCC(1), cc(1), cc_bundled(1), f90(1), ld(1), prof(1), exit(2), pro‐
fil(2), sprofil(2), monitor(3C), smonitor(3C), crt0(3).
Graham, S.L., Kessler, P.B., McKusick, M.K.
SIGPLAN Notices; Vol. 17, No. 6, pp. 120-126, June 1982.
(See the option).
gprof(1)
