summaryrefslogtreecommitdiffstats
path: root/tools/perf/bench
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2015-05-06 19:47:25 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2015-05-06 19:47:25 +0200
commitd8fce2db7220fc46067c825fc417fb295eac7d0a (patch)
tree8d6f4403f4433956a02e0ed490b4f3b54005d817 /tools/perf/bench
parentMerge branch 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/ke... (diff)
parentMerge tag 'perf-urgent-for-mingo' of git://git.kernel.org/pub/scm/linux/kerne... (diff)
downloadlinux-d8fce2db7220fc46067c825fc417fb295eac7d0a.tar.xz
linux-d8fce2db7220fc46067c825fc417fb295eac7d0a.zip
Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf fixes from Ingo Molnar: "Mostly tooling fixes, but also an uncore PMU driver fix and an uncore PMU driver hardware-enablement addition" * 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: perf probe: Fix segfault if passed with ''. perf report: Fix -T/--threads option to work again perf bench numa: Fix immediate meeting of convergence condition perf bench numa: Fixes of --quiet argument perf bench futex: Fix hung wakeup tasks after requeueing perf probe: Fix bug with global variables handling perf top: Fix a segfault when kernel map is restricted. tools lib traceevent: Fix build failure on 32-bit arch perf kmem: Fix compiles on RHEL6/OL6 tools lib api: Undefine _FORTIFY_SOURCE before setting it perf kmem: Consistently use PRIu64 for printing u64 values perf trace: Disable events and drain events when forked workload ends perf trace: Enable events when doing system wide tracing and starting a workload perf/x86/intel/uncore: Move PCI IDs for IMC to uncore driver perf/x86/intel/uncore: Add support for Intel Haswell ULT (lower power Mobile Processor) IMC uncore PMUs perf/x86/intel: Add cpu_(prepare|starting|dying) for core_pmu
Diffstat (limited to 'tools/perf/bench')
-rw-r--r--tools/perf/bench/futex-requeue.c15
-rw-r--r--tools/perf/bench/numa.c12
2 files changed, 18 insertions, 9 deletions
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index bedff6b5b3cf..ad0d9b5342fb 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -132,6 +132,9 @@ int bench_futex_requeue(int argc, const char **argv,
if (!fshared)
futex_flag = FUTEX_PRIVATE_FLAG;
+ if (nrequeue > nthreads)
+ nrequeue = nthreads;
+
printf("Run summary [PID %d]: Requeuing %d threads (from [%s] %p to %p), "
"%d at a time.\n\n", getpid(), nthreads,
fshared ? "shared":"private", &futex1, &futex2, nrequeue);
@@ -161,20 +164,18 @@ int bench_futex_requeue(int argc, const char **argv,
/* Ok, all threads are patiently blocked, start requeueing */
gettimeofday(&start, NULL);
- for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue) {
+ while (nrequeued < nthreads) {
/*
* Do not wakeup any tasks blocked on futex1, allowing
* us to really measure futex_wait functionality.
*/
- futex_cmp_requeue(&futex1, 0, &futex2, 0,
- nrequeue, futex_flag);
+ nrequeued += futex_cmp_requeue(&futex1, 0, &futex2, 0,
+ nrequeue, futex_flag);
}
+
gettimeofday(&end, NULL);
timersub(&end, &start, &runtime);
- if (nrequeued > nthreads)
- nrequeued = nthreads;
-
update_stats(&requeued_stats, nrequeued);
update_stats(&requeuetime_stats, runtime.tv_usec);
@@ -184,7 +185,7 @@ int bench_futex_requeue(int argc, const char **argv,
}
/* everybody should be blocked on futex2, wake'em up */
- nrequeued = futex_wake(&futex2, nthreads, futex_flag);
+ nrequeued = futex_wake(&futex2, nrequeued, futex_flag);
if (nthreads != nrequeued)
warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads);
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index ebfa163b80b5..ba5efa4710b5 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -180,7 +180,7 @@ static const struct option options[] = {
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: */
@@ -828,6 +828,9 @@ static int count_process_nodes(int process_nr)
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;
}
@@ -882,6 +885,11 @@ static void calc_convergence_compression(int *strong)
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);
}
@@ -1395,7 +1403,7 @@ static void print_res(const char *name, double val,
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);