--- zzzz-none-000/linux-3.10.107/tools/perf/bench/numa.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/tools/perf/bench/numa.c 2021-02-04 17:41:59.000000000 +0000 @@ -8,6 +8,7 @@ #include "../builtin.h" #include "../util/util.h" #include "../util/parse-options.h" +#include "../util/cloexec.h" #include "bench.h" @@ -23,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -51,6 +53,9 @@ unsigned int loops_done; u64 val; u64 runtime_ns; + u64 system_time_ns; + u64 user_time_ns; + double speed_gbs; pthread_mutex_t *process_lock; }; @@ -159,8 +164,8 @@ OPT_STRING('L', "mb_proc_locked", &p0.mb_proc_locked_str,"MB", "process serialized/locked memory access (MBs), <= process_memory"), OPT_STRING('T', "mb_thread" , &p0.mb_thread_str, "MB", "thread memory (MBs)"), - OPT_UINTEGER('l', "nr_loops" , &p0.nr_loops, "max number of loops to run"), - OPT_UINTEGER('s', "nr_secs" , &p0.nr_secs, "max number of seconds to run"), + OPT_UINTEGER('l', "nr_loops" , &p0.nr_loops, "max number of loops to run (default: unlimited)"), + OPT_UINTEGER('s', "nr_secs" , &p0.nr_secs, "max number of seconds to run (default: 5 secs)"), OPT_UINTEGER('u', "usleep" , &p0.sleep_usecs, "usecs to sleep per loop iteration"), OPT_BOOLEAN('R', "data_reads" , &p0.data_reads, "access the data via writes (can be mixed with -W)"), @@ -180,7 +185,7 @@ OPT_INTEGER('H', "thp" , &p0.thp, "MADV_NOHUGEPAGE < 0 < MADV_HUGEPAGE"), OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details"), OPT_BOOLEAN('m', "measure_convergence", &p0.measure_convergence, "measure convergence latency"), - OPT_BOOLEAN('q', "quiet" , &p0.show_quiet, "bzero the initial allocations"), + OPT_BOOLEAN('q', "quiet" , &p0.show_quiet, "quiet mode"), OPT_BOOLEAN('S', "serialize-startup", &p0.serialize_startup,"serialize thread startup"), /* Special option string parsing callbacks: */ @@ -429,14 +434,14 @@ return 0; } -static void parse_setup_cpu_list(void) +static int parse_setup_cpu_list(void) { struct thread_data *td; char *str0, *str; int t; if (!g->p.cpu_list_str) - return; + return 0; dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks); @@ -500,8 +505,12 @@ dprintf("CPUs: %d_%d-%d#%dx%d\n", bind_cpu_0, bind_len, bind_cpu_1, step, mul); - BUG_ON(bind_cpu_0 < 0 || bind_cpu_0 >= g->p.nr_cpus); - BUG_ON(bind_cpu_1 < 0 || bind_cpu_1 >= g->p.nr_cpus); + if (bind_cpu_0 >= g->p.nr_cpus || bind_cpu_1 >= g->p.nr_cpus) { + printf("\nTest not applicable, system has only %d CPUs.\n", g->p.nr_cpus); + return -1; + } + + BUG_ON(bind_cpu_0 < 0 || bind_cpu_1 < 0); BUG_ON(bind_cpu_0 > bind_cpu_1); for (bind_cpu = bind_cpu_0; bind_cpu <= bind_cpu_1; bind_cpu += step) { @@ -541,6 +550,7 @@ printf("# NOTE: %d tasks bound, %d tasks unbound\n", t, g->p.nr_tasks - t); free(str0); + return 0; } static int parse_cpus_opt(const struct option *opt __maybe_unused, @@ -561,14 +571,14 @@ return 0; } -static void parse_setup_node_list(void) +static int parse_setup_node_list(void) { struct thread_data *td; char *str0, *str; int t; if (!g->p.node_list_str) - return; + return 0; dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks); @@ -619,8 +629,12 @@ dprintf("NODEs: %d-%d #%d\n", bind_node_0, bind_node_1, step); - BUG_ON(bind_node_0 < 0 || bind_node_0 >= g->p.nr_nodes); - BUG_ON(bind_node_1 < 0 || bind_node_1 >= g->p.nr_nodes); + if (bind_node_0 >= g->p.nr_nodes || bind_node_1 >= g->p.nr_nodes) { + printf("\nTest not applicable, system has only %d nodes.\n", g->p.nr_nodes); + return -1; + } + + BUG_ON(bind_node_0 < 0 || bind_node_1 < 0); BUG_ON(bind_node_0 > bind_node_1); for (bind_node = bind_node_0; bind_node <= bind_node_1; bind_node += step) { @@ -651,6 +665,7 @@ printf("# NOTE: %d tasks mem-bound, %d tasks unbound\n", t, g->p.nr_tasks - t); free(str0); + return 0; } static int parse_nodes_opt(const struct option *opt __maybe_unused, @@ -818,6 +833,9 @@ td = g->threads + task_nr; node = numa_node_of_cpu(td->curr_cpu); + if (node < 0) /* curr_cpu was likely still -1 */ + return 0; + node_present[node] = 1; } @@ -872,6 +890,11 @@ for (p = 0; p < g->p.nr_proc; p++) { unsigned int nodes = count_process_nodes(p); + if (!nodes) { + *strong = 0; + return; + } + nodes_min = min(nodes, nodes_min); nodes_max = max(nodes, nodes_max); } @@ -1024,6 +1047,7 @@ u64 bytes_done; long work_done; u32 l; + struct rusage rusage; bind_to_cpumask(td->bind_cpumask); bind_to_memnode(td->bind_node); @@ -1110,7 +1134,7 @@ /* Check whether our max runtime timed out: */ if (g->p.nr_secs) { timersub(&stop, &start0, &diff); - if (diff.tv_sec >= g->p.nr_secs) { + if ((u32)diff.tv_sec >= g->p.nr_secs) { g->stop_work = true; break; } @@ -1157,7 +1181,7 @@ runtime_ns_max += diff.tv_usec * 1000; if (details >= 0) { - printf(" #%2d / %2d: %14.2lf nsecs/op [val: %016lx]\n", + printf(" #%2d / %2d: %14.2lf nsecs/op [val: %016"PRIx64"]\n", process_nr, thread_nr, runtime_ns_max / bytes_done, val); } fflush(stdout); @@ -1176,6 +1200,13 @@ timersub(&stop, &start0, &diff); td->runtime_ns = diff.tv_sec * 1000000000ULL; td->runtime_ns += diff.tv_usec * 1000ULL; + td->speed_gbs = bytes_done / (td->runtime_ns / 1e9) / 1e9; + + getrusage(RUSAGE_THREAD, &rusage); + td->system_time_ns = rusage.ru_stime.tv_sec * 1000000000ULL; + td->system_time_ns += rusage.ru_stime.tv_usec * 1000ULL; + td->user_time_ns = rusage.ru_utime.tv_sec * 1000000000ULL; + td->user_time_ns += rusage.ru_utime.tv_usec * 1000ULL; free_data(thread_data, g->p.bytes_thread); @@ -1356,8 +1387,8 @@ init_thread_data(); tprintf("#\n"); - parse_setup_cpu_list(); - parse_setup_node_list(); + if (parse_setup_cpu_list() || parse_setup_node_list()) + return -1; tprintf("#\n"); print_summary(); @@ -1385,7 +1416,7 @@ if (!name) name = "main,"; - if (g->p.show_quiet) + if (!g->p.show_quiet) printf(" %-30s %15.3f, %-15s %s\n", name, val, txt_unit, txt_short); else printf(" %14.3f %s\n", val, txt_long); @@ -1402,7 +1433,7 @@ double runtime_sec_min; int wait_stat; double bytes; - int i, t; + int i, t, p; if (init()) return -1; @@ -1538,6 +1569,24 @@ print_res(name, bytes / runtime_sec_max / 1e9, "GB/sec,", "total-speed", "GB/sec total speed"); + if (g->p.show_details >= 2) { + char tname[32]; + struct thread_data *td; + for (p = 0; p < g->p.nr_proc; p++) { + for (t = 0; t < g->p.nr_threads; t++) { + memset(tname, 0, 32); + td = g->threads + p*g->p.nr_threads + t; + snprintf(tname, 32, "process%d:thread%d", p, t); + print_res(tname, td->speed_gbs, + "GB/sec", "thread-speed", "GB/sec/thread speed"); + print_res(tname, td->system_time_ns / 1e9, + "secs", "thread-system-time", "system CPU time/thread"); + print_res(tname, td->user_time_ns / 1e9, + "secs", "thread-user-time", "user CPU time/thread"); + } + } + } + free(pids); deinit(); @@ -1583,6 +1632,11 @@ p->data_rand_walk = true; p->nr_loops = -1; p->init_random = true; + p->mb_global_str = "1"; + p->nr_proc = 1; + p->nr_threads = 1; + p->nr_secs = 5; + p->run_all = argc == 1; } static int run_bench_numa(const char *name, const char **argv) @@ -1600,7 +1654,6 @@ return 0; err: - usage_with_options(numa_usage, options); return -1; } @@ -1701,8 +1754,7 @@ BUG_ON(ret < 0); for (i = 0; i < nr; i++) { - if (run_bench_numa(tests[i][0], tests[i] + 1)) - return -1; + run_bench_numa(tests[i][0], tests[i] + 1); } printf("\n");