diff options
Diffstat (limited to 'tools/perf/bench/numa.c')
| -rw-r--r-- | tools/perf/bench/numa.c | 16 |
1 files changed, 10 insertions, 6 deletions
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 8efe904e486b..469d65b21122 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -4,6 +4,7 @@ * numa: Simulate NUMA-sensitive workload and measure their NUMA performance */ +#include <inttypes.h> /* For the CLR_() macros */ #include <pthread.h> @@ -30,6 +31,7 @@ #include <sys/wait.h> #include <sys/prctl.h> #include <sys/types.h> +#include <linux/kernel.h> #include <linux/time64.h> #include <numa.h> @@ -43,6 +45,7 @@ /* * Debug printf: */ +#undef dprintf #define dprintf(x...) do { if (g && g->p.show_details >= 1) printf(x); } while (0) struct thread_data { @@ -186,7 +189,8 @@ static const struct option options[] = { OPT_INCR ('d', "show_details" , &p0.show_details, "Show details"), OPT_INCR ('a', "all" , &p0.run_all, "Run all tests in the suite"), OPT_INTEGER('H', "thp" , &p0.thp, "MADV_NOHUGEPAGE < 0 < MADV_HUGEPAGE"), - OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details"), + OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details, " + "convergence is reached when each process (all its threads) is running on a single NUMA node."), OPT_BOOLEAN('m', "measure_convergence", &p0.measure_convergence, "measure convergence latency"), OPT_BOOLEAN('q', "quiet" , &p0.show_quiet, "quiet mode"), OPT_BOOLEAN('S', "serialize-startup", &p0.serialize_startup,"serialize thread startup"), @@ -696,7 +700,7 @@ static inline uint32_t lfsr_32(uint32_t lfsr) * kernel (KSM, zero page, etc.) cannot optimize away RAM * accesses: */ -static inline u64 access_data(u64 *data __attribute__((unused)), u64 val) +static inline u64 access_data(u64 *data, u64 val) { if (g->p.data_reads) val += *data; @@ -1573,13 +1577,13 @@ static int __bench_numa(const char *name) "GB/sec,", "total-speed", "GB/sec total speed"); if (g->p.show_details >= 2) { - char tname[32]; + char tname[14 + 2 * 10 + 1]; 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); + memset(tname, 0, sizeof(tname)); td = g->threads + p*g->p.nr_threads + t; - snprintf(tname, 32, "process%d:thread%d", p, t); + snprintf(tname, sizeof(tname), "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 / NSEC_PER_SEC, @@ -1765,7 +1769,7 @@ static int bench_all(void) return 0; } -int bench_numa(int argc, const char **argv, const char *prefix __maybe_unused) +int bench_numa(int argc, const char **argv) { init_params(&p0, "main,", argc, argv); argc = parse_options(argc, argv, options, bench_numa_usage, 0); |
