GPROF(1)                    NetBSD Reference Manual                   GPROF(1)

NNAAMMEE
     ggpprrooff - display call graph profile data

SSYYNNOOPPSSIISS
     ggpprrooff [options] [_a_._o_u_t [_g_m_o_n_._o_u_t _._._.]]

DDEESSCCRRIIPPTTIIOONN
     GGpprrooff produces an execution profile of C, Pascal, or Fortran77 programs.
     The effect of called routines is incorporated in the profile of each
     caller.  The profile data is taken from the call graph profile file
     (_g_m_o_n_._o_u_t default) which is created by programs that are compiled with
     the --ppgg option of cc(1),  pc(1),  and f77(1).  The --ppgg option also links
     in versions of the library routines that are compiled for profiling.
     GGpprrooff reads the given object file (the default is _a_._o_u_t_) and establishes
     the relation between it's symbol table and the call graph profile from
     _g_m_o_n_._o_u_t. If more than one profile file is specified, the ggpprrooff output
     shows the sum of the profile information in the given profile files.

     GGpprrooff calculates the amount of time spent in each routine.  Next, these
     times are propagated along the edges of the call graph.  Cycles are dis-
     covered, and calls into a cycle are made to share the time of the cycle.
     The first listing shows the functions sorted according to the time they
     represent including the time of their call graph descendents.  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 func-
     tion shows how this function's time and the time of its descendents is
     propagated to its (direct) call graph parents.

     Cycles are also shown, with an entry for the cycle as a whole and a list-
     ing of the members of the cycle and their contributions to the time and
     call counts of the cycle.

     Second, a flat profile is given, similar to that provided by prof(1).
     This listing gives the total execution times, the call counts, the time
     in milleseconds the call spent in the routine itself, and the time in
     milleseconds the call spent in the routine itself including its descen-
     dents.

     Finally, an index of the function names is provided.

     The following options are available:

     --aa          Suppresses the printing of statically declared functions.  If
                 this option is given, all relevant information about the
                 static function (e.g., time samples, calls to other func-
                 tions, calls from other functions) belongs to the function
                 loaded just before the static function in the _a_._o_u_t file.

     --bb          Suppresses the printing of a description of each field in the
                 profile.

     --cc          The static call graph of the program is discovered by a
                 heuristic that examines the text space of the object file.
                 Static-only parents or children are shown with call counts of
                 0.

     --CC _c_o_u_n_t    Find a minimal set of arcs that can be broken to eliminate
                 all cycles with _c_o_u_n_t or more members.  Caution: the algo-
                 rithm used to break cycles is exponential, so using this op-
                 tion may cause ggpprrooff to run for a very long time.

     --ee _n_a_m_e     Suppresses the printing of the graph profile entry for rou-
                 tine _n_a_m_e and all its descendants (unless they have other an-
                 cestors that aren't suppressed).  More than one --ee option may
                 be given.  Only one _n_a_m_e may be given with each --ee option.

     --EE _n_a_m_e     Suppresses the printing of the graph profile entry for rou-
                 tine _n_a_m_e (and its descendants) as --ee, above, and also ex-
                 cludes the time spent in _n_a_m_e (and its descendants) from the
                 total and percentage time computations.  (For example, --EE
                 _m_c_o_u_n_t --EE _m_c_l_e_a_n_u_p is the default.)

     --ff _n_a_m_e     Prints the graph profile entry of only the specified routine
                 _n_a_m_e and its descendants.  More than one --ff option may be
                 given.  Only one _n_a_m_e may be given with each --ff option.

     --FF _n_a_m_e     Prints the graph profile entry of only the routine _n_a_m_e and
                 its descendants (as --ff, above) and also uses only the times
                 of the printed routines in total time and percentage computa-
                 tions.  More than one --FF option may be given.  Only one _n_a_m_e
                 may be given with each --FF option.  The --FF option overrides
                 the --EE option.

     --kk _f_r_o_m_n_a_m_e _t_o_n_a_m_e
                 Will delete any arcs from routine _f_r_o_m_n_a_m_e to routine _t_o_n_a_m_e.
                 This can be used to break undesired cycles.  More than one --kk
                 option may be given.  Only one pair of routine names may be
                 given with each --kk option.

     --ss          A profile file _g_m_o_n_._s_u_m is produced that represents the sum
                 of the profile information in all the specified profile
                 files.  This summary profile file may be given to later exe-
                 cutions of gprof (probably also with a --ss) to accumulate pro-
                 file data across several runs of an _a_._o_u_t file.

     --zz          Displays routines that have zero usage (as shown by call
                 counts and accumulated time).  This is useful with the --cc op-
                 tion for discovering which routines were never called.

FFIILLEESS
     a.out     The namelist and text space.
     gmon.out  Dynamic call graph and profile.
     gmon.sum  Summarized dynamic call graph and profile.

SSEEEE AALLSSOO
     monitor(3),  profil(2),  cc(1),  prof(1)

     S. Graham, P. Kessler, and M. McKusick, "An Execution Profiler for
     Modular Programs", _S_o_f_t_w_a_r_e _- _P_r_a_c_t_i_c_e _a_n_d _E_x_p_e_r_i_e_n_c_e, 13, pp. 671-685,
     1983.

     S. Graham, P. Kessler, and M. McKusick, "gprof: A Call Graph Execution
     Profiler", _P_r_o_c_e_e_d_i_n_g_s _o_f _t_h_e _S_I_G_P_L_A_N _'_8_2 _S_y_m_p_o_s_i_u_m _o_n _C_o_m_p_i_l_e_r
     _C_o_n_s_t_r_u_c_t_i_o_n_, _S_I_G_P_L_A_N _N_o_t_i_c_e_s, 6, 17, pp. 120-126, June 1982.

HHIISSTTOORRYY
     The ggpprrooff profiler appeared in 4.2BSD.

BBUUGGSS
     The granularity of the sampling is shown, but remains statistical at
     best.  We assume 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 the function's parents is directly proportional to the num-
     ber of times that arc is traversed.

     Parents that are not themselves profiled will have the time of their pro-
     filed children propagated to them, but they will appear to be sponta-
     neously invoked in the call graph listing, and will not have their time
     propagated further.  Similarly, signal catchers, even though profiled,
     will 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 profiled program must call exit(2) or return normally for the profil-
     ing information to be saved in the _g_m_o_n_._o_u_t file.

4.2 Berkeley Distribution      October 19, 1994                              3
