X-Git-Url: https://git.octo.it/?a=blobdiff_plain;f=src%2Fprocesses.c;fp=src%2Fprocesses.c;h=beee341f6b691b4b4dd4ecee4496fcd40590f541;hb=ca4a6c8a856a9012270ec10389b08d54e70e3401;hp=aca18b9919b53107ced78c15163035178fca86bc;hpb=63f8df381c3c7d5c349fdfb1f4ea1cf6ae40d521;p=collectd.git diff --git a/src/processes.c b/src/processes.c index aca18b99..beee341f 100644 --- a/src/processes.c +++ b/src/processes.c @@ -25,7 +25,7 @@ * * Authors: * Lyonel Vincent - * Florian octo Forster + * Florian octo Forster * Oleg King * Sebastian Harl * Andrés J. Díaz @@ -94,13 +94,13 @@ # endif /* #endif KERNEL_LINUX */ -#elif HAVE_LIBKVM_GETPROCS && HAVE_STRUCT_KINFO_PROC_FREEBSD +#elif HAVE_LIBKVM_GETPROCS && (HAVE_STRUCT_KINFO_PROC_FREEBSD || HAVE_STRUCT_KINFO_PROC_OPENBSD) # include # include # include # include # include -/* #endif HAVE_LIBKVM_GETPROCS && HAVE_STRUCT_KINFO_PROC_FREEBSD */ +/* #endif HAVE_LIBKVM_GETPROCS && (HAVE_STRUCT_KINFO_PROC_FREEBSD || HAVE_STRUCT_KINFO_PROC_OPENBSD) */ #elif HAVE_PROCINFO_H # include @@ -143,8 +143,12 @@ # include #endif -#ifndef ARG_MAX -# define ARG_MAX 4096 +#ifndef CMDLINE_BUFFER_SIZE +# if defined(ARG_MAX) && (ARG_MAX < 4096) +# define CMDLINE_BUFFER_SIZE ARG_MAX +# else +# define CMDLINE_BUFFER_SIZE 4096 +# endif #endif typedef struct procstat_entry_s @@ -176,6 +180,9 @@ typedef struct procstat_entry_s derive_t io_syscr; derive_t io_syscw; + derive_t cswitch_vol; + derive_t cswitch_invol; + struct procstat_entry_s *next; } procstat_entry_t; @@ -207,12 +214,17 @@ typedef struct procstat derive_t io_syscr; derive_t io_syscw; + derive_t cswitch_vol; + derive_t cswitch_invol; + struct procstat *next; struct procstat_entry_s *instances; } procstat_t; static procstat_t *list_head_g = NULL; +static _Bool report_ctx_switch = 0; + #if HAVE_THREAD_INFO static mach_port_t port_host_self; static mach_port_t port_task_self; @@ -225,9 +237,9 @@ static mach_msg_type_number_t pset_list_len; static long pagesize_g; /* #endif KERNEL_LINUX */ -#elif HAVE_LIBKVM_GETPROCS && HAVE_STRUCT_KINFO_PROC_FREEBSD +#elif HAVE_LIBKVM_GETPROCS && (HAVE_STRUCT_KINFO_PROC_FREEBSD || HAVE_STRUCT_KINFO_PROC_OPENBSD) static int pagesize; -/* #endif HAVE_LIBKVM_GETPROCS && HAVE_STRUCT_KINFO_PROC_FREEBSD */ +/* #endif HAVE_LIBKVM_GETPROCS && (HAVE_STRUCT_KINFO_PROC_FREEBSD || HAVE_STRUCT_KINFO_PROC_OPENBSD) */ #elif HAVE_PROCINFO_H static struct procentry64 procentry[MAXPROCENTRY]; @@ -275,8 +287,8 @@ static void ps_list_register (const char *name, const char *regexp) if (status != 0) { DEBUG ("ProcessMatch: compiling the regular expression \"%s\" failed.", regexp); - sfree(new->re); - sfree(new); + sfree (new->re); + sfree (new); return; } } @@ -395,6 +407,8 @@ static void ps_list_add (const char *name, const char *cmdline, procstat_entry_t pse->io_wchar = entry->io_wchar; pse->io_syscr = entry->io_syscr; pse->io_syscw = entry->io_syscw; + pse->cswitch_vol = entry->cswitch_vol; + pse->cswitch_invol = entry->cswitch_invol; ps->num_proc += pse->num_proc; ps->num_lwp += pse->num_lwp; @@ -409,6 +423,9 @@ static void ps_list_add (const char *name, const char *cmdline, procstat_entry_t ps->io_syscr += ((pse->io_syscr == -1)?0:pse->io_syscr); ps->io_syscw += ((pse->io_syscw == -1)?0:pse->io_syscw); + ps->cswitch_vol += ((pse->cswitch_vol == -1)?0:pse->cswitch_vol); + ps->cswitch_invol += ((pse->cswitch_invol == -1)?0:pse->cswitch_invol); + if ((entry->vmem_minflt_counter == 0) && (entry->vmem_majflt_counter == 0)) { @@ -505,6 +522,8 @@ static void ps_list_reset (void) ps->io_wchar = -1; ps->io_syscr = -1; ps->io_syscw = -1; + ps->cswitch_vol = -1; + ps->cswitch_invol = -1; pse_prev = NULL; pse = ps->instances; @@ -589,6 +608,10 @@ static int ps_config (oconfig_item_t *ci) ps_list_register (c->values[0].value.string, c->values[1].value.string); } + else if (strcasecmp (c->key, "CollectContextSwitch") == 0) + { + cf_util_get_boolean (c, &report_ctx_switch); + } else { ERROR ("processes plugin: The `%s' configuration option is not " @@ -635,9 +658,9 @@ static int ps_init (void) pagesize_g, CONFIG_HZ); /* #endif KERNEL_LINUX */ -#elif HAVE_LIBKVM_GETPROCS && HAVE_STRUCT_KINFO_PROC_FREEBSD +#elif HAVE_LIBKVM_GETPROCS && (HAVE_STRUCT_KINFO_PROC_FREEBSD || HAVE_STRUCT_KINFO_PROC_OPENBSD) pagesize = getpagesize(); -/* #endif HAVE_LIBKVM_GETPROCS && HAVE_STRUCT_KINFO_PROC_FREEBSD */ +/* #endif HAVE_LIBKVM_GETPROCS && (HAVE_STRUCT_KINFO_PROC_FREEBSD || HAVE_STRUCT_KINFO_PROC_OPENBSD) */ #elif HAVE_PROCINFO_H pagesize = getpagesize(); @@ -738,19 +761,36 @@ static void ps_submit_proc_list (procstat_t *ps) plugin_dispatch_values (&vl); } + if ( report_ctx_switch ) + { + sstrncpy (vl.type, "contextswitch", sizeof (vl.type)); + sstrncpy (vl.type_instance, "voluntary", sizeof (vl.type_instance)); + vl.values[0].derive = ps->cswitch_vol; + vl.values_len = 1; + plugin_dispatch_values (&vl); + + sstrncpy (vl.type, "contextswitch", sizeof (vl.type)); + sstrncpy (vl.type_instance, "involuntary", sizeof (vl.type_instance)); + vl.values[0].derive = ps->cswitch_invol; + vl.values_len = 1; + plugin_dispatch_values (&vl); + } + DEBUG ("name = %s; num_proc = %lu; num_lwp = %lu; " "vmem_size = %lu; vmem_rss = %lu; vmem_data = %lu; " "vmem_code = %lu; " "vmem_minflt_counter = %"PRIi64"; vmem_majflt_counter = %"PRIi64"; " "cpu_user_counter = %"PRIi64"; cpu_system_counter = %"PRIi64"; " "io_rchar = %"PRIi64"; io_wchar = %"PRIi64"; " - "io_syscr = %"PRIi64"; io_syscw = %"PRIi64";", + "io_syscr = %"PRIi64"; io_syscw = %"PRIi64"; " + "cswitch_vol = %"PRIi64"; cswitch_invol = %"PRIi64";", ps->name, ps->num_proc, ps->num_lwp, ps->vmem_size, ps->vmem_rss, ps->vmem_data, ps->vmem_code, ps->vmem_minflt_counter, ps->vmem_majflt_counter, ps->cpu_user_counter, ps->cpu_system_counter, - ps->io_rchar, ps->io_wchar, ps->io_syscr, ps->io_syscw); + ps->io_rchar, ps->io_wchar, ps->io_syscr, ps->io_syscw, + ps->cswitch_vol, ps->cswitch_invol); } /* void ps_submit_proc_list */ #if KERNEL_LINUX || KERNEL_SOLARIS @@ -775,42 +815,99 @@ static void ps_submit_fork_rate (derive_t value) /* ------- additional functions for KERNEL_LINUX/HAVE_THREAD_INFO ------- */ #if KERNEL_LINUX -static int ps_read_tasks (int pid) +static procstat_t *ps_read_tasks_status (int pid, procstat_t *ps) { char dirname[64]; DIR *dh; + char filename[64]; + FILE *fh; struct dirent *ent; - int count = 0; + derive_t cswitch_vol = 0; + derive_t cswitch_invol = 0; + char buffer[1024]; + char *fields[8]; + int numfields; ssnprintf (dirname, sizeof (dirname), "/proc/%i/task", pid); if ((dh = opendir (dirname)) == NULL) { DEBUG ("Failed to open directory `%s'", dirname); - return (-1); + return (NULL); } while ((ent = readdir (dh)) != NULL) { + char *tpid; + if (!isdigit ((int) ent->d_name[0])) continue; - else - count++; + + tpid = ent->d_name; + + ssnprintf (filename, sizeof (filename), "/proc/%i/task/%s/status", pid, tpid); + if ((fh = fopen (filename, "r")) == NULL) + { + DEBUG ("Failed to open file `%s'", filename); + continue; + } + + while (fgets (buffer, sizeof(buffer), fh) != NULL) + { + derive_t tmp; + char *endptr; + + if (strncmp (buffer, "voluntary_ctxt_switches", 23) != 0 + && strncmp (buffer, "nonvoluntary_ctxt_switches", 26) != 0) + continue; + + numfields = strsplit (buffer, fields, + STATIC_ARRAY_SIZE (fields)); + + if (numfields < 2) + continue; + + errno = 0; + endptr = NULL; + tmp = (derive_t) strtoll (fields[1], &endptr, /* base = */ 10); + if ((errno == 0) && (endptr != fields[1])) + { + if (strncmp (buffer, "voluntary_ctxt_switches", 23) == 0) + { + cswitch_vol += tmp; + } + else if (strncmp (buffer, "nonvoluntary_ctxt_switches", 26) == 0) + { + cswitch_invol += tmp; + } + } + } /* while (fgets) */ + + if (fclose (fh)) + { + char errbuf[1024]; + WARNING ("processes: fclose: %s", + sstrerror (errno, errbuf, sizeof (errbuf))); + } } closedir (dh); - return ((count >= 1) ? count : 1); -} /* int *ps_read_tasks */ + ps->cswitch_vol = cswitch_vol; + ps->cswitch_invol = cswitch_invol; + + return (ps); +} /* int *ps_read_tasks_status */ -/* Read advanced virtual memory data from /proc/pid/status */ -static procstat_t *ps_read_vmem (int pid, procstat_t *ps) +/* Read data from /proc/pid/status */ +static procstat_t *ps_read_status (int pid, procstat_t *ps) { FILE *fh; char buffer[1024]; char filename[64]; - unsigned long long lib = 0; - unsigned long long exe = 0; - unsigned long long data = 0; + unsigned long lib = 0; + unsigned long exe = 0; + unsigned long data = 0; + unsigned long threads = 0; char *fields[8]; int numfields; @@ -820,10 +917,11 @@ static procstat_t *ps_read_vmem (int pid, procstat_t *ps) while (fgets (buffer, sizeof(buffer), fh) != NULL) { - long long tmp; + unsigned long tmp; char *endptr; - if (strncmp (buffer, "Vm", 2) != 0) + if (strncmp (buffer, "Vm", 2) != 0 + && strncmp (buffer, "Threads", 7) != 0) continue; numfields = strsplit (buffer, fields, @@ -834,7 +932,7 @@ static procstat_t *ps_read_vmem (int pid, procstat_t *ps) errno = 0; endptr = NULL; - tmp = strtoll (fields[1], &endptr, /* base = */ 10); + tmp = strtoul (fields[1], &endptr, /* base = */ 10); if ((errno == 0) && (endptr != fields[1])) { if (strncmp (buffer, "VmData", 6) == 0) @@ -849,6 +947,10 @@ static procstat_t *ps_read_vmem (int pid, procstat_t *ps) { exe = tmp; } + else if (strncmp(buffer, "Threads", 7) == 0) + { + threads = tmp; + } } } /* while (fgets) */ @@ -861,6 +963,8 @@ static procstat_t *ps_read_vmem (int pid, procstat_t *ps) ps->vmem_data = data * 1024; ps->vmem_code = (exe + lib) * 1024; + if (threads != 0) + ps->num_lwp = threads; return (ps); } /* procstat_t *ps_read_vmem */ @@ -928,9 +1032,9 @@ int ps_read_process (int pid, procstat_t *ps, char *state) char *fields[64]; char fields_len; - int buffer_len; + size_t buffer_len; - char *buffer_ptr; + char *buffer_ptr; size_t name_start_pos; size_t name_end_pos; size_t name_len; @@ -941,14 +1045,16 @@ int ps_read_process (int pid, procstat_t *ps, char *state) long long unsigned vmem_rss; long long unsigned stack_size; + ssize_t status; + memset (ps, 0, sizeof (procstat_t)); ssnprintf (filename, sizeof (filename), "/proc/%i/stat", pid); - buffer_len = read_file_contents (filename, - buffer, sizeof(buffer) - 1); - if (buffer_len <= 0) + status = read_file_contents (filename, buffer, sizeof(buffer) - 1); + if (status <= 0) return (-1); + buffer_len = (size_t) status; buffer[buffer_len] = 0; /* The name of the process is enclosed in parens. Since the name can @@ -1003,11 +1109,16 @@ int ps_read_process (int pid, procstat_t *ps, char *state) } else { - if ( (ps->num_lwp = ps_read_tasks (pid)) == -1 ) + ps->num_lwp = strtoul (fields[17], /* endptr = */ NULL, /* base = */ 10); + if ((ps_read_status(pid, ps)) == NULL) { - /* returns -1 => kernel 2.4 */ - ps->num_lwp = 1; + /* No VMem data */ + ps->vmem_data = -1; + ps->vmem_code = -1; + DEBUG("ps_read_process: did not get vmem data for pid %i",pid); } + if (ps->num_lwp <= 0) + ps->num_lwp = 1; ps->num_proc = 1; } @@ -1040,14 +1151,6 @@ int ps_read_process (int pid, procstat_t *ps, char *state) cpu_system_counter = cpu_system_counter * 1000000 / CONFIG_HZ; vmem_rss = vmem_rss * pagesize_g; - if ( (ps_read_vmem(pid, ps)) == NULL) - { - /* No VMem data */ - ps->vmem_data = -1; - ps->vmem_code = -1; - DEBUG("ps_read_process: did not get vmem data for pid %i",pid); - } - ps->cpu_user_counter = cpu_user_counter; ps->cpu_system_counter = cpu_system_counter; ps->vmem_size = (unsigned long) vmem_size; @@ -1065,6 +1168,18 @@ int ps_read_process (int pid, procstat_t *ps, char *state) DEBUG("ps_read_process: not get io data for pid %i",pid); } + if ( report_ctx_switch ) + { + if ( (ps_read_tasks_status(pid, ps)) == NULL) + { + ps->cswitch_vol = -1; + ps->cswitch_invol = -1; + + DEBUG("ps_read_tasks_status: not get context " + "switch data for pid %i",pid); + } + } + /* success */ return (0); } /* int ps_read_process (...) */ @@ -1216,16 +1331,16 @@ static const char *ps_get_cmdline (long pid, /* {{{ */ { char path[PATH_MAX]; psinfo_t info; - int status; + ssize_t status; snprintf(path, sizeof (path), "/proc/%li/psinfo", pid); status = read_file_contents (path, (void *) &info, sizeof (info)); - if (status != sizeof (info)) + if ((status < 0) || (((size_t) status) != sizeof (info))) { ERROR ("processes plugin: Unexpected return value " "while reading \"%s\": " - "Returned %i but expected %zu.", + "Returned %zd but expected %zu.", path, status, buffer_size); return (NULL); } @@ -1322,6 +1437,12 @@ static int ps_read_process(long pid, procstat_t *ps, char *state) ps->io_syscr = myUsage->pr_sysc; ps->io_syscw = myUsage->pr_sysc; + /* + * TODO: context switch counters for Solaris + */ + ps->cswitch_vol = -1; + ps->cswitch_invol = -1; + /* * TODO: Find way of setting BLOCKED and PAGING status @@ -1559,6 +1680,10 @@ static int ps_read (void) pse.cpu_user_counter = task_absolutetime_info.total_user; pse.cpu_system_counter = task_absolutetime_info.total_system; + + /* context switch counters not implemented */ + pse.cswitch_vol = -1; + pse.cswitch_invol = -1; } status = task_threads (task_list[task], &thread_list, @@ -1702,7 +1827,7 @@ static int ps_read (void) DIR *proc; int pid; - char cmdline[ARG_MAX]; + char cmdline[CMDLINE_BUFFER_SIZE]; int status; procstat_t ps; @@ -1737,6 +1862,7 @@ static int ps_read (void) continue; } + memset (&pse, 0, sizeof (pse)); pse.id = pid; pse.age = 0; @@ -1763,6 +1889,9 @@ static int ps_read (void) pse.io_syscr = ps.io_syscr; pse.io_syscw = ps.io_syscw; + pse.cswitch_vol = ps.cswitch_vol; + pse.cswitch_invol = ps.cswitch_invol; + switch (state) { case 'R': running++; break; @@ -1840,7 +1969,7 @@ static int ps_read (void) * filter out threads (duplicate PID entries). */ if ((proc_ptr == NULL) || (proc_ptr->ki_pid != procs[i].ki_pid)) { - char cmdline[ARG_MAX] = ""; + char cmdline[CMDLINE_BUFFER_SIZE] = ""; _Bool have_cmdline = 0; proc_ptr = &(procs[i]); @@ -1908,6 +2037,10 @@ static int ps_read (void) pse.io_syscr = -1; pse.io_syscw = -1; + /* context switch counters not implemented */ + pse.cswitch_vol = -1; + pse.cswitch_invol = -1; + ps_list_add (procs[i].ki_comm, have_cmdline ? cmdline : NULL, &pse); switch (procs[i].ki_stat) @@ -1937,6 +2070,143 @@ static int ps_read (void) ps_submit_proc_list (ps_ptr); /* #endif HAVE_LIBKVM_GETPROCS && HAVE_STRUCT_KINFO_PROC_FREEBSD */ +#elif HAVE_LIBKVM_GETPROCS && HAVE_STRUCT_KINFO_PROC_OPENBSD + int running = 0; + int sleeping = 0; + int zombies = 0; + int stopped = 0; + int onproc = 0; + int idle = 0; + int dead = 0; + + kvm_t *kd; + char errbuf[1024]; + struct kinfo_proc *procs; /* array of processes */ + struct kinfo_proc *proc_ptr = NULL; + int count; /* returns number of processes */ + int i; + + procstat_t *ps_ptr; + procstat_entry_t pse; + + ps_list_reset (); + + /* Open the kvm interface, get a descriptor */ + kd = kvm_open (NULL, NULL, NULL, 0, errbuf); + if (kd == NULL) + { + ERROR ("processes plugin: Cannot open kvm interface: %s", + errbuf); + return (0); + } + + /* Get the list of processes. */ + procs = kvm_getprocs(kd, KERN_PROC_ALL, 0, sizeof(struct kinfo_proc), &count); + if (procs == NULL) + { + ERROR ("processes plugin: Cannot get kvm processes list: %s", + kvm_geterr(kd)); + kvm_close (kd); + return (0); + } + + /* Iterate through the processes in kinfo_proc */ + for (i = 0; i < count; i++) + { + /* Create only one process list entry per _process_, i.e. + * filter out threads (duplicate PID entries). */ + if ((proc_ptr == NULL) || (proc_ptr->p_pid != procs[i].p_pid)) + { + char cmdline[CMDLINE_BUFFER_SIZE] = ""; + _Bool have_cmdline = 0; + + proc_ptr = &(procs[i]); + /* Don't probe zombie processes */ + if (!P_ZOMBIE(proc_ptr)) + { + char **argv; + int argc; + int status; + + /* retrieve the arguments */ + argv = kvm_getargv (kd, proc_ptr, /* nchr = */ 0); + argc = 0; + if ((argv != NULL) && (argv[0] != NULL)) + { + while (argv[argc] != NULL) + argc++; + + status = strjoin (cmdline, sizeof (cmdline), argv, argc, " "); + if (status < 0) + WARNING ("processes plugin: Command line did not fit into buffer."); + else + have_cmdline = 1; + } + } /* if (process has argument list) */ + + memset (&pse, 0, sizeof (pse)); + pse.id = procs[i].p_pid; + pse.age = 0; + + pse.num_proc = 1; + pse.num_lwp = 1; /* XXX: accumulate p_tid values for a single p_pid ? */ + + pse.vmem_rss = procs[i].p_vm_rssize * pagesize; + pse.vmem_data = procs[i].p_vm_dsize * pagesize; + pse.vmem_code = procs[i].p_vm_tsize * pagesize; + pse.stack_size = procs[i].p_vm_ssize * pagesize; + pse.vmem_size = pse.stack_size + pse.vmem_code + pse.vmem_data; + pse.vmem_minflt = 0; + pse.vmem_minflt_counter = procs[i].p_uru_minflt; + pse.vmem_majflt = 0; + pse.vmem_majflt_counter = procs[i].p_uru_majflt; + + pse.cpu_user = 0; + pse.cpu_system = 0; + pse.cpu_user_counter = procs[i].p_uutime_usec + + (1000000lu * procs[i].p_uutime_sec); + pse.cpu_system_counter = procs[i].p_ustime_usec + + (1000000lu * procs[i].p_ustime_sec); + + /* no I/O data */ + pse.io_rchar = -1; + pse.io_wchar = -1; + pse.io_syscr = -1; + pse.io_syscw = -1; + + /* context switch counters not implemented */ + pse.cswitch_vol = -1; + pse.cswitch_invol = -1; + + ps_list_add (procs[i].p_comm, have_cmdline ? cmdline : NULL, &pse); + + switch (procs[i].p_stat) + { + case SSTOP: stopped++; break; + case SSLEEP: sleeping++; break; + case SRUN: running++; break; + case SIDL: idle++; break; + case SONPROC: onproc++; break; + case SDEAD: dead++; break; + case SZOMB: zombies++; break; + } + } /* if ((proc_ptr == NULL) || (proc_ptr->p_pid != procs[i].p_pid)) */ + } + + kvm_close(kd); + + ps_submit_state ("running", running); + ps_submit_state ("sleeping", sleeping); + ps_submit_state ("zombies", zombies); + ps_submit_state ("stopped", stopped); + ps_submit_state ("onproc", onproc); + ps_submit_state ("idle", idle); + ps_submit_state ("dead", dead); + + for (ps_ptr = list_head_g; ps_ptr != NULL; ps_ptr = ps_ptr->next) + ps_submit_proc_list (ps_ptr); +/* #endif HAVE_LIBKVM_GETPROCS && HAVE_STRUCT_KINFO_PROC_OPENBSD */ + #elif HAVE_PROCINFO_H /* AIX */ int running = 0; @@ -2054,6 +2324,9 @@ static int ps_read (void) pse.io_syscr = -1; pse.io_syscw = -1; + pse.cswitch_vol = -1; + pse.cswitch_invol = -1; + ps_list_add (cmdline, cargs, &pse); } /* for (i = 0 .. nprocs) */ @@ -2123,6 +2396,7 @@ static int ps_read (void) continue; } + memset (&pse, 0, sizeof (pse)); pse.id = pid; pse.age = 0; @@ -2149,6 +2423,9 @@ static int ps_read (void) pse.io_syscr = ps.io_syscr; pse.io_syscw = ps.io_syscw; + pse.cswitch_vol = -1; + pse.cswitch_invol = -1; + switch (state) { case 'R': running++; break;