perf session: Allocate chunks of sample objects

The ordered sample code allocates singular reference objects struct
sample_queue which have 48byte size on 64bit and 20 bytes on 32bit. That's
silly. Allocate ~64k sized chunks and hand them out.

Performance gain: ~ 15%

Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <20101130163820.398713983@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 9fef587ff11ff1f8e3c3f20a3dfcc8b067d2036d..52672dad1fe93c5a6d219ef89de2c7ae67498f4b 100644 (file)
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -114,6 +114,7 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc
        self->repipe = repipe;
        INIT_LIST_HEAD(&self->ordered_samples.samples);
        INIT_LIST_HEAD(&self->ordered_samples.sample_cache);
+       INIT_LIST_HEAD(&self->ordered_samples.to_free);
        machine__init(&self->host_machine, "", HOST_KERNEL_ID);
 
        if (mode == O_RDONLY) {
@@ -403,10 +404,10 @@ static void perf_session_free_sample_buffers(struct perf_session *session)
 {
        struct ordered_samples *os = &session->ordered_samples;
 
-       while (!list_empty(&os->sample_cache)) {
+       while (!list_empty(&os->to_free)) {
                struct sample_queue *sq;
 
-               sq = list_entry(os->sample_cache.next, struct sample_queue, list);
+               sq = list_entry(os->to_free.next, struct sample_queue, list);
                list_del(&sq->list);
                free(sq);
        }
@@ -538,10 +539,13 @@ static void __queue_sample_event(struct sample_queue *new,
        }
 }
 
+#define MAX_SAMPLE_BUFFER      (64 * 1024 / sizeof(struct sample_queue))
+
 static int queue_sample_event(event_t *event, struct sample_data *data,
                              struct perf_session *s)
 {
-       struct list_head *sc = &s->ordered_samples.sample_cache;
+       struct ordered_samples *os = &s->ordered_samples;
+       struct list_head *sc = &os->sample_cache;
        u64 timestamp = data->time;
        struct sample_queue *new;
 
@@ -553,10 +557,17 @@ static int queue_sample_event(event_t *event, struct sample_data *data,
        if (!list_empty(sc)) {
                new = list_entry(sc->next, struct sample_queue, list);
                list_del(&new->list);
+       } else if (os->sample_buffer) {
+               new = os->sample_buffer + os->sample_buffer_idx;
+               if (++os->sample_buffer_idx == MAX_SAMPLE_BUFFER)
+                       os->sample_buffer = NULL;
        } else {
-               new = malloc(sizeof(*new));
-               if (!new)
+               os->sample_buffer = malloc(MAX_SAMPLE_BUFFER * sizeof(*new));
+               if (!os->sample_buffer)
                        return -ENOMEM;
+               list_add(&os->sample_buffer->list, &os->to_free);
+               os->sample_buffer_idx = 2;
+               new = os->sample_buffer + 1;
        }
 
        new->timestamp = timestamp;

diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index e4a7ff2ba8d593f688a83fc698bc108c1b2db6f6..5bf6efa3788a66eb3b675736e32ebf4225dc4dd3 100644 (file)
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -19,7 +19,10 @@ struct ordered_samples {
        u64                     max_timestamp;
        struct list_head        samples;
        struct list_head        sample_cache;
+       struct list_head        to_free;
+       struct sample_queue     *sample_buffer;
        struct sample_queue     *last_sample;
+       int                     sample_buffer_idx;
 };
 
 struct perf_session {