perf tools: Use rb_tree for maps
Threads can have many and kernel modules will be represented as a
tree of maps as well.
Ah, and for a perf.data with 146607 samples:
Before:
[root@doppio ~]# perf stat -r 5 perf report > /dev/null
Performance counter stats for 'perf report' (5 runs):
699.823680 task-clock-msecs # 0.991 CPUs ( +- 0.454% )
74 context-switches # 0.000 M/sec ( +- 1.709% )
2 CPU-migrations # 0.000 M/sec ( +- 17.008% )
23114 page-faults # 0.033 M/sec ( +- 0.000% )
1381257019 cycles # 1973.721 M/sec ( +- 0.290% )
1456894438 instructions # 1.055 IPC ( +- 0.007% )
18779818 cache-references # 26.835 M/sec ( +- 0.380% )
641799 cache-misses # 0.917 M/sec ( +- 1.200% )
0.705972729 seconds time elapsed ( +- 0.501% )
[root@doppio ~]#
After
Performance counter stats for 'perf report' (5 runs):
691.261451 task-clock-msecs # 0.993 CPUs ( +- 0.307% )
72 context-switches # 0.000 M/sec ( +- 0.829% )
6 CPU-migrations # 0.000 M/sec ( +- 18.409% )
23127 page-faults # 0.033 M/sec ( +- 0.000% )
1366395876 cycles # 1976.670 M/sec ( +- 0.153% )
1443136016 instructions # 1.056 IPC ( +- 0.012% )
17956402 cache-references # 25.976 M/sec ( +- 0.325% )
661924 cache-misses # 0.958 M/sec ( +- 1.335% )
0.696127275 seconds time elapsed ( +- 0.377% )
I.e. we see some speedup too.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
LKML-Reference: <20090928174846.GA3361@ghostprotocols.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 693ed1e..bbb37c1 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -2,13 +2,12 @@
#define __PERF_THREAD_H
#include <linux/rbtree.h>
-#include <linux/list.h>
#include <unistd.h>
#include "symbol.h"
struct thread {
struct rb_node rb_node;
- struct list_head maps;
+ struct rb_root maps;
pid_t pid;
char shortname[3];
char *comm;
@@ -21,7 +20,14 @@
register_idle_thread(struct rb_root *threads, struct thread **last_match);
void thread__insert_map(struct thread *self, struct map *map);
int thread__fork(struct thread *self, struct thread *parent);
-struct map *thread__find_map(struct thread *self, u64 ip);
size_t threads__fprintf(FILE *fp, struct rb_root *threads);
+void maps__insert(struct rb_root *maps, struct map *map);
+struct map *maps__find(struct rb_root *maps, u64 ip);
+
+static inline struct map *thread__find_map(struct thread *self, u64 ip)
+{
+ return self ? maps__find(&self->maps, ip) : NULL;
+}
+
#endif /* __PERF_THREAD_H */