summaryrefslogtreecommitdiffstats
path: root/tools/perf/builtin-stat.c
diff options
context:
space:
mode:
authorPaul Mackerras <paulus@samba.org>2010-03-10 20:36:09 +1100
committerIngo Molnar <mingo@elte.hu>2010-03-11 13:36:53 +0100
commita12b51c478899fe0b7e874a559b05ba35f1128ee (patch)
tree25b9911c1932c13fd8b468aa18eb17982ba31b59 /tools/perf/builtin-stat.c
parent220b140b52ab6cc133f674a7ffec8fa792054f25 (diff)
downloadop-kernel-dev-a12b51c478899fe0b7e874a559b05ba35f1128ee.zip
op-kernel-dev-a12b51c478899fe0b7e874a559b05ba35f1128ee.tar.gz
perf tools: Fix sparse CPU numbering related bugs
At present, the perf subcommands that do system-wide monitoring (perf stat, perf record and perf top) don't work properly unless the online cpus are numbered 0, 1, ..., N-1. These tools ask for the number of online cpus with sysconf(_SC_NPROCESSORS_ONLN) and then try to create events for cpus 0, 1, ..., N-1. This creates problems for systems where the online cpus are numbered sparsely. For example, a POWER6 system in single-threaded mode (i.e. only running 1 hardware thread per core) will have only even-numbered cpus online. This fixes the problem by reading the /sys/devices/system/cpu/online file to find out which cpus are online. The code that does that is in tools/perf/util/cpumap.[ch], and consists of a read_cpu_map() function that sets up a cpumap[] array and returns the number of online cpus. If /sys/devices/system/cpu/online can't be read or can't be parsed successfully, it falls back to using sysconf to ask how many cpus are online and sets up an identity map in cpumap[]. The perf record, perf stat and perf top code then calls read_cpu_map() in the system-wide monitoring case (instead of sysconf) and uses cpumap[] to get the cpu numbers to pass to perf_event_open. Signed-off-by: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> LKML-Reference: <20100310093609.GA3959@brick.ozlabs.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'tools/perf/builtin-stat.c')
-rw-r--r--tools/perf/builtin-stat.c10
1 files changed, 6 insertions, 4 deletions
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e8c85d5..95db31c 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -45,6 +45,7 @@
#include "util/event.h"
#include "util/debug.h"
#include "util/header.h"
+#include "util/cpumap.h"
#include <sys/prctl.h>
#include <math.h>
@@ -151,7 +152,7 @@ static void create_perf_stat_counter(int counter, int pid)
unsigned int cpu;
for (cpu = 0; cpu < nr_cpus; cpu++) {
- fd[cpu][counter] = sys_perf_event_open(attr, -1, cpu, -1, 0);
+ fd[cpu][counter] = sys_perf_event_open(attr, -1, cpumap[cpu], -1, 0);
if (fd[cpu][counter] < 0 && verbose)
fprintf(stderr, ERR_PERF_OPEN, counter,
fd[cpu][counter], strerror(errno));
@@ -519,9 +520,10 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
nr_counters = ARRAY_SIZE(default_attrs);
}
- nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
- assert(nr_cpus <= MAX_NR_CPUS);
- assert((int)nr_cpus >= 0);
+ if (system_wide)
+ nr_cpus = read_cpu_map();
+ else
+ nr_cpus = 1;
/*
* We dont want to block the signals - that would cause
OpenPOWER on IntegriCloud