GPROF(1) BSD Reference Manual GPROF(1) NNAAMMEE ggpprrooff - display call graph profile data SSYYNNOOPPSSIISS ggpprrooff [options] [_a_._o_u_t [_g_m_o_n_._o_u_t _._._.]] DDEESSCCRRIIPPTTIIOONN GGpprrooff 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 --ppgg option of cc(1), pc(1), and f77(1). The --ppgg option also links in versions of the library routines that are compiled for profiling. GGpprrooff 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 ggpprrooff output shows the sum of the profile information in the given profile files. GGpprrooff 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: --aa 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. --bb Suppresses the printing of a description of each field in the profile. --cc 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. --CC _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 ggpprrooff to run for a very long time. --ee _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 --ee option may be given. Only one _n_a_m_e may be given with each --ee option. --EE _n_a_m_e Suppresses the printing of the graph profile entry for rou- tine _n_a_m_e (and its descendants) as --ee, 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, --EE _m_c_o_u_n_t --EE _m_c_l_e_a_n_u_p is the default.) --ff _n_a_m_e Prints the graph profile entry of only the specified routine _n_a_m_e and its descendants. More than one --ff option may be given. Only one _n_a_m_e may be given with each --ff option. --FF _n_a_m_e Prints the graph profile entry of only the routine _n_a_m_e and its descendants (as --ff, above) and also uses only the times of the printed routines in total time and percentage computa- tions. More than one --FF option may be given. Only one _n_a_m_e may be given with each --FF option. The --FF option overrides the --EE option. --kk _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 --kk option may be given. Only one pair of routine names may be given with each --kk option. --ss 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 --ss) to accumulate pro- file data across several runs of an _a_._o_u_t file. --zz Displays routines that have zero usage (as shown by call counts and accumulated time). This is useful with the --cc op- tion for discovering which routines were never called. FFIILLEESS a.out The namelist and text space. gmon.out Dynamic call graph and profile. gmon.sum Summarized dynamic call graph and profile. SSEEEE AALLSSOO 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. HHIISSTTOORRYY The ggpprrooff profiler appeared in 4.2BSD. BBUUGGSS 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 June 6, 1993 3