These changes are the raw update to linux-4.4.6-rt14. Kernel sources

[kvmfornfv.git] / kernel / tools / perf / bench / numa.c

diff --git a/kernel/tools/perf/bench/numa.c b/kernel/tools/perf/bench/numa.c
index ba5efa4..492df27 100644 (file)
--- a/kernel/tools/perf/bench/numa.c
+++ b/kernel/tools/perf/bench/numa.c
@@ -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 <pthread.h>
 #include <sys/mman.h>
 #include <sys/time.h>
+#include <sys/resource.h>
 #include <sys/wait.h>
 #include <sys/prctl.h>
 #include <sys/types.h>
@@ -51,6 +53,9 @@ struct thread_data {
        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 @@ static const struct option options[] = {
        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)"),
@@ -1042,6 +1047,7 @@ static void *worker_thread(void *__tdata)
        u64 bytes_done;
        long work_done;
        u32 l;
+       struct rusage rusage;
 
        bind_to_cpumask(td->bind_cpumask);
        bind_to_memnode(td->bind_node);
@@ -1194,6 +1200,13 @@ static void *worker_thread(void *__tdata)
        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);
 
@@ -1420,7 +1433,7 @@ static int __bench_numa(const char *name)
        double runtime_sec_min;
        int wait_stat;
        double bytes;
-       int i, t;
+       int i, t, p;
 
        if (init())
                return -1;
@@ -1556,6 +1569,24 @@ static int __bench_numa(const char *name)
        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();