summaryrefslogtreecommitdiffstats
path: root/tools/perf/util
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/util
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/util')
-rw-r--r--tools/perf/util/cpumap.c59
-rw-r--r--tools/perf/util/cpumap.h7
2 files changed, 66 insertions, 0 deletions
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
new file mode 100644
index 0000000..4e01490
--- /dev/null
+++ b/tools/perf/util/cpumap.c
@@ -0,0 +1,59 @@
+#include "util.h"
+#include "../perf.h"
+#include "cpumap.h"
+#include <assert.h>
+#include <stdio.h>
+
+int cpumap[MAX_NR_CPUS];
+
+static int default_cpu_map(void)
+{
+ int nr_cpus, i;
+
+ nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+ assert(nr_cpus <= MAX_NR_CPUS);
+ assert((int)nr_cpus >= 0);
+
+ for (i = 0; i < nr_cpus; ++i)
+ cpumap[i] = i;
+
+ return nr_cpus;
+}
+
+int read_cpu_map(void)
+{
+ FILE *onlnf;
+ int nr_cpus = 0;
+ int n, cpu, prev;
+ char sep;
+
+ onlnf = fopen("/sys/devices/system/cpu/online", "r");
+ if (!onlnf)
+ return default_cpu_map();
+
+ sep = 0;
+ prev = -1;
+ for (;;) {
+ n = fscanf(onlnf, "%u%c", &cpu, &sep);
+ if (n <= 0)
+ break;
+ if (prev >= 0) {
+ assert(nr_cpus + cpu - prev - 1 < MAX_NR_CPUS);
+ while (++prev < cpu)
+ cpumap[nr_cpus++] = prev;
+ }
+ assert (nr_cpus < MAX_NR_CPUS);
+ cpumap[nr_cpus++] = cpu;
+ if (n == 2 && sep == '-')
+ prev = cpu;
+ else
+ prev = -1;
+ if (n == 1 || sep == '\n')
+ break;
+ }
+ fclose(onlnf);
+ if (nr_cpus > 0)
+ return nr_cpus;
+
+ return default_cpu_map();
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
new file mode 100644
index 0000000..86c78bb
--- /dev/null
+++ b/tools/perf/util/cpumap.h
@@ -0,0 +1,7 @@
+#ifndef __PERF_CPUMAP_H
+#define __PERF_CPUMAP_H
+
+extern int read_cpu_map(void);
+extern int cpumap[];
+
+#endif /* __PERF_CPUMAP_H */
OpenPOWER on IntegriCloud