summaryrefslogtreecommitdiffstats
path: root/tools/perf/bench
diff options
context:
space:
mode:
authorJiri Olsa <jolsa@kernel.org>2018-06-20 11:40:36 +0200
committerArnaldo Carvalho de Melo <acme@redhat.com>2018-06-25 11:59:37 -0300
commit983107072be1a39cbde67d45cb0059138190e015 (patch)
treea6e3768d99fe34d3ac21e6ffabd739dd44d53be4 /tools/perf/bench
parent6dde6429c5ff5b38d6d40a14a6ee105117e6364d (diff)
downloadlinux-983107072be1a39cbde67d45cb0059138190e015.tar.gz
linux-983107072be1a39cbde67d45cb0059138190e015.tar.bz2
linux-983107072be1a39cbde67d45cb0059138190e015.zip
perf bench: Fix numa report output code
Currently we can hit following assert when running numa bench: $ perf bench numa mem -p 3 -t 1 -P 512 -s 100 -zZ0cm --thp 1 perf: bench/numa.c:1577: __bench_numa: Assertion `!(!(((wait_stat) & 0x7f) == 0))' failed. The assertion is correct, because we hit the SIGFPE in following line: Thread 2.2 "thread 0/0" received signal SIGFPE, Arithmetic exception. [Switching to Thread 0x7fffd28c6700 (LWP 11750)] 0x000.. in worker_thread (__tdata=0x7.. ) at bench/numa.c:1257 1257 td->speed_gbs = bytes_done / (td->runtime_ns / NSEC_PER_SEC) / 1e9; We don't check if the runtime is actually bigger than 1 second, and thus this might end up with zero division within FPU. Adding the check to prevent this. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20180620094036.17278-1-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/perf/bench')
-rw-r--r--tools/perf/bench/numa.c5
1 files changed, 3 insertions, 2 deletions
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 63eb49082774..44195514b19e 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -1098,7 +1098,7 @@ static void *worker_thread(void *__tdata)
u8 *global_data;
u8 *process_data;
u8 *thread_data;
- u64 bytes_done;
+ u64 bytes_done, secs;
long work_done;
u32 l;
struct rusage rusage;
@@ -1254,7 +1254,8 @@ static void *worker_thread(void *__tdata)
timersub(&stop, &start0, &diff);
td->runtime_ns = diff.tv_sec * NSEC_PER_SEC;
td->runtime_ns += diff.tv_usec * NSEC_PER_USEC;
- td->speed_gbs = bytes_done / (td->runtime_ns / NSEC_PER_SEC) / 1e9;
+ secs = td->runtime_ns / NSEC_PER_SEC;
+ td->speed_gbs = secs ? bytes_done / secs / 1e9 : 0;
getrusage(RUSAGE_THREAD, &rusage);
td->system_time_ns = rusage.ru_stime.tv_sec * NSEC_PER_SEC;