summaryrefslogtreecommitdiffstats
path: root/tools/perf/util
diff options
context:
space:
mode:
authorAnton Blanchard <anton@samba.org>2011-07-04 21:57:50 +1000
committerIngo Molnar <mingo@elte.hu>2011-07-05 10:44:44 +0200
commit5d67be97f8903d05ce53597fb5f3bc25a45e8026 (patch)
tree5ce8c2407d50570d7fee79b9c7f24e8eb89384b4 /tools/perf/util
parent9f8b6a6cf0ee78de87ebe1e87f54bec1c1741ef7 (diff)
downloadop-kernel-dev-5d67be97f8903d05ce53597fb5f3bc25a45e8026.zip
op-kernel-dev-5d67be97f8903d05ce53597fb5f3bc25a45e8026.tar.gz
perf report/annotate/script: Add option to specify a CPU range
Add an option to perf report/annotate/script to specify which CPUs to operate on. This enables us to take a single system wide profile and analyse each CPU (or group of CPUs) in isolation. This was useful when profiling a multiprocess workload where the bottleneck was on one CPU but this was hidden in the overall profile. Per process and per thread breakdowns didn't help because multiple processes were running on each CPU and no single process consumed an entire CPU. The patch converts the list of CPUs returned by cpu_map__new into a bitmap for fast lookup. I wanted to use -C to be consistent with perf top/record/stat, but unfortunately perf report already uses -C <comms>. v2: Incorporate suggestions from David Ahern: - Added -c to perf script - Check that SAMPLE_CPU is set when -c is used - Update documentation v3: Create perf_session__cpu_bitmap() Signed-off-by: Anton Blanchard <anton@samba.org> Acked-by: David Ahern <dsahern@gmail.com> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Link: http://lkml.kernel.org/r/20110704215750.11647eb9@kryten Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'tools/perf/util')
-rw-r--r--tools/perf/util/session.c38
-rw-r--r--tools/perf/util/session.h3
2 files changed, 41 insertions, 0 deletions
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 558bcf9..080e533 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -12,6 +12,7 @@
#include "session.h"
#include "sort.h"
#include "util.h"
+#include "cpumap.h"
static int perf_session__open(struct perf_session *self, bool force)
{
@@ -1282,3 +1283,40 @@ void perf_session__print_ip(union perf_event *event,
}
}
}
+
+int perf_session__cpu_bitmap(struct perf_session *session,
+ const char *cpu_list, unsigned long *cpu_bitmap)
+{
+ int i;
+ struct cpu_map *map;
+
+ for (i = 0; i < PERF_TYPE_MAX; ++i) {
+ struct perf_evsel *evsel;
+
+ evsel = perf_session__find_first_evtype(session, i);
+ if (!evsel)
+ continue;
+
+ if (!(evsel->attr.sample_type & PERF_SAMPLE_CPU)) {
+ pr_err("File does not contain CPU events. "
+ "Remove -c option to proceed.\n");
+ return -1;
+ }
+ }
+
+ map = cpu_map__new(cpu_list);
+
+ for (i = 0; i < map->nr; i++) {
+ int cpu = map->map[i];
+
+ if (cpu >= MAX_NR_CPUS) {
+ pr_err("Requested CPU %d too large. "
+ "Consider raising MAX_NR_CPUS\n", cpu);
+ return -1;
+ }
+
+ set_bit(cpu, cpu_bitmap);
+ }
+
+ return 0;
+}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index de4178d..5de754f 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -172,4 +172,7 @@ void perf_session__print_ip(union perf_event *event,
struct perf_session *session,
int print_sym, int print_dso);
+int perf_session__cpu_bitmap(struct perf_session *session,
+ const char *cpu_list, unsigned long *cpu_bitmap);
+
#endif /* __PERF_SESSION_H */
OpenPOWER on IntegriCloud