234 lines · c
1/* SPDX-License-Identifier: GPL-2.0 */2/*3 * Copyright (c) 2023 Meta Platforms, Inc. and affiliates.4 * Copyright (c) 2023 Tejun Heo <tj@kernel.org>5 * Copyright (c) 2023 David Vernet <dvernet@meta.com>6 */7#include <stdio.h>8#include <signal.h>9#include <unistd.h>10#include <libgen.h>11#include <limits.h>12#include <inttypes.h>13#include <fcntl.h>14#include <time.h>15#include <bpf/bpf.h>16#include <scx/common.h>17#include "scx_flatcg.h"18#include "scx_flatcg.bpf.skel.h"19 20#ifndef FILEID_KERNFS21#define FILEID_KERNFS 0xfe22#endif23 24const char help_fmt[] =25"A flattened cgroup hierarchy sched_ext scheduler.\n"26"\n"27"See the top-level comment in .bpf.c for more details.\n"28"\n"29"Usage: %s [-s SLICE_US] [-i INTERVAL] [-f] [-v]\n"30"\n"31" -s SLICE_US Override slice duration\n"32" -i INTERVAL Report interval\n"33" -f Use FIFO scheduling instead of weighted vtime scheduling\n"34" -v Print libbpf debug messages\n"35" -h Display this help and exit\n";36 37static bool verbose;38static volatile int exit_req;39 40static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args)41{42 if (level == LIBBPF_DEBUG && !verbose)43 return 0;44 return vfprintf(stderr, format, args);45}46 47static void sigint_handler(int dummy)48{49 exit_req = 1;50}51 52static float read_cpu_util(__u64 *last_sum, __u64 *last_idle)53{54 FILE *fp;55 char buf[4096];56 char *line, *cur = NULL, *tok;57 __u64 sum = 0, idle = 0;58 __u64 delta_sum, delta_idle;59 int idx;60 61 fp = fopen("/proc/stat", "r");62 if (!fp) {63 perror("fopen(\"/proc/stat\")");64 return 0.0;65 }66 67 if (!fgets(buf, sizeof(buf), fp)) {68 perror("fgets(\"/proc/stat\")");69 fclose(fp);70 return 0.0;71 }72 fclose(fp);73 74 line = buf;75 for (idx = 0; (tok = strtok_r(line, " \n", &cur)); idx++) {76 char *endp = NULL;77 __u64 v;78 79 if (idx == 0) {80 line = NULL;81 continue;82 }83 v = strtoull(tok, &endp, 0);84 if (!endp || *endp != '\0') {85 fprintf(stderr, "failed to parse %dth field of /proc/stat (\"%s\")\n",86 idx, tok);87 continue;88 }89 sum += v;90 if (idx == 4)91 idle = v;92 }93 94 delta_sum = sum - *last_sum;95 delta_idle = idle - *last_idle;96 *last_sum = sum;97 *last_idle = idle;98 99 return delta_sum ? (float)(delta_sum - delta_idle) / delta_sum : 0.0;100}101 102static void fcg_read_stats(struct scx_flatcg *skel, __u64 *stats)103{104 __u64 cnts[FCG_NR_STATS][skel->rodata->nr_cpus];105 __u32 idx;106 107 memset(stats, 0, sizeof(stats[0]) * FCG_NR_STATS);108 109 for (idx = 0; idx < FCG_NR_STATS; idx++) {110 int ret, cpu;111 112 ret = bpf_map_lookup_elem(bpf_map__fd(skel->maps.stats),113 &idx, cnts[idx]);114 if (ret < 0)115 continue;116 for (cpu = 0; cpu < skel->rodata->nr_cpus; cpu++)117 stats[idx] += cnts[idx][cpu];118 }119}120 121int main(int argc, char **argv)122{123 struct scx_flatcg *skel;124 struct bpf_link *link;125 struct timespec intv_ts = { .tv_sec = 2, .tv_nsec = 0 };126 bool dump_cgrps = false;127 __u64 last_cpu_sum = 0, last_cpu_idle = 0;128 __u64 last_stats[FCG_NR_STATS] = {};129 unsigned long seq = 0;130 __s32 opt;131 __u64 ecode;132 133 libbpf_set_print(libbpf_print_fn);134 signal(SIGINT, sigint_handler);135 signal(SIGTERM, sigint_handler);136restart:137 skel = SCX_OPS_OPEN(flatcg_ops, scx_flatcg);138 139 skel->rodata->nr_cpus = libbpf_num_possible_cpus();140 141 while ((opt = getopt(argc, argv, "s:i:dfvh")) != -1) {142 double v;143 144 switch (opt) {145 case 's':146 v = strtod(optarg, NULL);147 skel->rodata->cgrp_slice_ns = v * 1000;148 break;149 case 'i':150 v = strtod(optarg, NULL);151 intv_ts.tv_sec = v;152 intv_ts.tv_nsec = (v - (float)intv_ts.tv_sec) * 1000000000;153 break;154 case 'd':155 dump_cgrps = true;156 break;157 case 'f':158 skel->rodata->fifo_sched = true;159 break;160 case 'v':161 verbose = true;162 break;163 case 'h':164 default:165 fprintf(stderr, help_fmt, basename(argv[0]));166 return opt != 'h';167 }168 }169 170 printf("slice=%.1lfms intv=%.1lfs dump_cgrps=%d",171 (double)skel->rodata->cgrp_slice_ns / 1000000.0,172 (double)intv_ts.tv_sec + (double)intv_ts.tv_nsec / 1000000000.0,173 dump_cgrps);174 175 SCX_OPS_LOAD(skel, flatcg_ops, scx_flatcg, uei);176 link = SCX_OPS_ATTACH(skel, flatcg_ops, scx_flatcg);177 178 while (!exit_req && !UEI_EXITED(skel, uei)) {179 __u64 acc_stats[FCG_NR_STATS];180 __u64 stats[FCG_NR_STATS];181 float cpu_util;182 int i;183 184 cpu_util = read_cpu_util(&last_cpu_sum, &last_cpu_idle);185 186 fcg_read_stats(skel, acc_stats);187 for (i = 0; i < FCG_NR_STATS; i++)188 stats[i] = acc_stats[i] - last_stats[i];189 190 memcpy(last_stats, acc_stats, sizeof(acc_stats));191 192 printf("\n[SEQ %6lu cpu=%5.1lf hweight_gen=%" PRIu64 "]\n",193 seq++, cpu_util * 100.0, skel->data->hweight_gen);194 printf(" act:%6llu deact:%6llu global:%6llu local:%6llu\n",195 stats[FCG_STAT_ACT],196 stats[FCG_STAT_DEACT],197 stats[FCG_STAT_GLOBAL],198 stats[FCG_STAT_LOCAL]);199 printf("HWT cache:%6llu update:%6llu skip:%6llu race:%6llu\n",200 stats[FCG_STAT_HWT_CACHE],201 stats[FCG_STAT_HWT_UPDATES],202 stats[FCG_STAT_HWT_SKIP],203 stats[FCG_STAT_HWT_RACE]);204 printf("ENQ skip:%6llu race:%6llu\n",205 stats[FCG_STAT_ENQ_SKIP],206 stats[FCG_STAT_ENQ_RACE]);207 printf("CNS keep:%6llu expire:%6llu empty:%6llu gone:%6llu\n",208 stats[FCG_STAT_CNS_KEEP],209 stats[FCG_STAT_CNS_EXPIRE],210 stats[FCG_STAT_CNS_EMPTY],211 stats[FCG_STAT_CNS_GONE]);212 printf("PNC next:%6llu empty:%6llu nocgrp:%6llu gone:%6llu race:%6llu fail:%6llu\n",213 stats[FCG_STAT_PNC_NEXT],214 stats[FCG_STAT_PNC_EMPTY],215 stats[FCG_STAT_PNC_NO_CGRP],216 stats[FCG_STAT_PNC_GONE],217 stats[FCG_STAT_PNC_RACE],218 stats[FCG_STAT_PNC_FAIL]);219 printf("BAD remove:%6llu\n",220 acc_stats[FCG_STAT_BAD_REMOVAL]);221 fflush(stdout);222 223 nanosleep(&intv_ts, NULL);224 }225 226 bpf_link__destroy(link);227 ecode = UEI_REPORT(skel, uei);228 scx_flatcg__destroy(skel);229 230 if (UEI_ECODE_RESTART(ecode))231 goto restart;232 return 0;233}234