1// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) 2// Copyright (c) 2019 Facebook 3#include <argp.h> 4#include <stdio.h> 5#include <stdlib.h> 6#include <string.h> 7#include <sys/resource.h> 8#include <time.h> 9#include <bpf/libbpf.h> 10#include <bpf/bpf.h> 11#include "runqslower.h" 12#include "runqslower.skel.h" 13 14struct env { 15 pid_t pid; 16 __u64 min_us; 17 bool verbose; 18} env = { 19 .min_us = 10000, 20}; 21 22const char *argp_program_version = "runqslower 0.1"; 23const char *argp_program_bug_address = "<bpf@vger.kernel.org>"; 24const char argp_program_doc[] = 25"runqslower Trace long process scheduling delays.\n" 26" For Linux, uses eBPF, BPF CO-RE, libbpf, BTF.\n" 27"\n" 28"This script traces high scheduling delays between tasks being\n" 29"ready to run and them running on CPU after that.\n" 30"\n" 31"USAGE: runqslower [-p PID] [min_us]\n" 32"\n" 33"EXAMPLES:\n" 34" runqslower # trace run queue latency higher than 10000 us (default)\n" 35" runqslower 1000 # trace run queue latency higher than 1000 us\n" 36" runqslower -p 123 # trace pid 123 only\n"; 37 38static const struct argp_option opts[] = { 39 { "pid", 'p', "PID", 0, "Process PID to trace"}, 40 { "verbose", 'v', NULL, 0, "Verbose debug output" }, 41 {}, 42}; 43 44static error_t parse_arg(int key, char *arg, struct argp_state *state) 45{ 46 static int pos_args; 47 int pid; 48 long long min_us; 49 50 switch (key) { 51 case 'v': 52 env.verbose = true; 53 break; 54 case 'p': 55 errno = 0; 56 pid = strtol(arg, NULL, 10); 57 if (errno || pid <= 0) { 58 fprintf(stderr, "Invalid PID: %s\n", arg); 59 argp_usage(state); 60 } 61 env.pid = pid; 62 break; 63 case ARGP_KEY_ARG: 64 if (pos_args++) { 65 fprintf(stderr, 66 "Unrecognized positional argument: %s\n", arg); 67 argp_usage(state); 68 } 69 errno = 0; 70 min_us = strtoll(arg, NULL, 10); 71 if (errno || min_us <= 0) { 72 fprintf(stderr, "Invalid delay (in us): %s\n", arg); 73 argp_usage(state); 74 } 75 env.min_us = min_us; 76 break; 77 default: 78 return ARGP_ERR_UNKNOWN; 79 } 80 return 0; 81} 82 83int libbpf_print_fn(enum libbpf_print_level level, 84 const char *format, va_list args) 85{ 86 if (level == LIBBPF_DEBUG && !env.verbose) 87 return 0; 88 return vfprintf(stderr, format, args); 89} 90 91static int bump_memlock_rlimit(void) 92{ 93 struct rlimit rlim_new = { 94 .rlim_cur = RLIM_INFINITY, 95 .rlim_max = RLIM_INFINITY, 96 }; 97 98 return setrlimit(RLIMIT_MEMLOCK, &rlim_new); 99} 100 101void handle_event(void *ctx, int cpu, void *data, __u32 data_sz) 102{ 103 const struct event *e = data; 104 struct tm *tm; 105 char ts[32]; 106 time_t t; 107 108 time(&t); 109 tm = localtime(&t); 110 strftime(ts, sizeof(ts), "%H:%M:%S", tm); 111 printf("%-8s %-16s %-6d %14llu\n", ts, e->task, e->pid, e->delta_us); 112} 113 114void handle_lost_events(void *ctx, int cpu, __u64 lost_cnt) 115{ 116 printf("Lost %llu events on CPU #%d!\n", lost_cnt, cpu); 117} 118 119int main(int argc, char **argv) 120{ 121 static const struct argp argp = { 122 .options = opts, 123 .parser = parse_arg, 124 .doc = argp_program_doc, 125 }; 126 struct perf_buffer_opts pb_opts; 127 struct perf_buffer *pb = NULL; 128 struct runqslower_bpf *obj; 129 int err; 130 131 err = argp_parse(&argp, argc, argv, 0, NULL, NULL); 132 if (err) 133 return err; 134 135 libbpf_set_print(libbpf_print_fn); 136 137 err = bump_memlock_rlimit(); 138 if (err) { 139 fprintf(stderr, "failed to increase rlimit: %d", err); 140 return 1; 141 } 142 143 obj = runqslower_bpf__open(); 144 if (!obj) { 145 fprintf(stderr, "failed to open and/or load BPF object\n"); 146 return 1; 147 } 148 149 /* initialize global data (filtering options) */ 150 obj->rodata->targ_pid = env.pid; 151 obj->rodata->min_us = env.min_us; 152 153 err = runqslower_bpf__load(obj); 154 if (err) { 155 fprintf(stderr, "failed to load BPF object: %d\n", err); 156 goto cleanup; 157 } 158 159 err = runqslower_bpf__attach(obj); 160 if (err) { 161 fprintf(stderr, "failed to attach BPF programs\n"); 162 goto cleanup; 163 } 164 165 printf("Tracing run queue latency higher than %llu us\n", env.min_us); 166 printf("%-8s %-16s %-6s %14s\n", "TIME", "COMM", "PID", "LAT(us)"); 167 168 pb_opts.sample_cb = handle_event; 169 pb_opts.lost_cb = handle_lost_events; 170 pb = perf_buffer__new(bpf_map__fd(obj->maps.events), 64, &pb_opts); 171 err = libbpf_get_error(pb); 172 if (err) { 173 pb = NULL; 174 fprintf(stderr, "failed to open perf buffer: %d\n", err); 175 goto cleanup; 176 } 177 178 while ((err = perf_buffer__poll(pb, 100)) >= 0) 179 ; 180 printf("Error polling perf buffer: %d\n", err); 181 182cleanup: 183 perf_buffer__free(pb); 184 runqslower_bpf__destroy(obj); 185 186 return err != 0; 187} 188