Linux and UNIX Man Pages

Linux & Unix Commands - Search Man Pages

mlprof(1) [debian man page]

mlprof(1)						      General Commands Manual							 mlprof(1)

NAME
mlprof - display profiling information for a MLton-compiled executable SYNOPSIS
mlprof [option ...] a.out [mlmon.out ...] DESCRIPTION
mlprof extracts information from an executable compiled by MLton with -profile alloc or -profile time and the resulting mlmon.out file pro- duced by running the executable. The output of mlprof consists of an initial line indicating the total amount of CPU time or bytes allocated. After this, source functions are listed along with the percentage of this total that they used, in decreasing order. If the program was compiled with -profile-stack true, mlprof will display the time spent or bytes allocated while the function was on the stack and in GC in addition to the time or bytes that the function is directly responsible for. With multiple mlmon.out files, mlprof will sum the profiling information. OPTIONS
-call-graph file Write a call graph containing the table data to a dot file. See the MLton User Guide for details. -graph-title string Set the call-graph title. -gray {false|true} Gray call-graph nodes according to stack %. This only makes sense if the executable was compiled -profile-stack true. -keep exp Only show functions specified by exp. For details on the allowed expressions, see the MLton User Guide. Multiple -keep expressions are not allowed. -mlmon file Process the list of whitespace-separated mlmon.out files found in the specified file. -raw {false|true} Show the raw counts in addition to the percentages. -show-line {false|true} Show the file and line for each function. -split regexp Treat duplicates of functions whose name matches regexp as different functions. -thresh x An abbreviation for -keep '(thresh x)', which only prints information about functions whose percentage is greater than or equal to x, where 0 <= x <= 100.0. -tolerant {false|true} Print a warning about broken mlmon.out files, but do not exit. SEE ALSO
mlton(1) and the MLton Guide. June 8, 2010 mlprof(1)

Check Out this Related Man Page

gprof(1)						      General Commands Manual							  gprof(1)

NAME
gprof - display call graph profile data SYNOPSIS
[options] [a.out [gmon.out...]] DESCRIPTION
The command produces an execution profile of C++, C and FORTRAN programs. 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 compiled for profiling. On Itanium(R)-based systems, supports multiple shared libraries profiling. 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 correlated 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 profiled. 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 counters. 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 information 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 profiling 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 descendants) from the total and percentage time computations. 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 information in all specified profile files. This summary profile file can be given to subsequent executions of (probably also with a option) to accumulate 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 "); } $ 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 "); 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 "); } $ 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 spontaneous (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 routine, in which case all is lost. The following limitations exist for shared library profiling on PA-RISC systems: o Local, static, and hidden functions are not profiled. o Shared libraries built with are not profiled. o Any function calls made from library initializers are not collected. 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 ALSO
aCC(1), cc(1), cc_bundled(1), f90(1), ld(1), prof(1), exit(2), profil(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)
Man Page

Featured Tech Videos