perf session: Cache sample objects

When the sample queue is flushed we free the sample reference objects. Though
we need to malloc new objects when we process further. Stop the malloc/free
orgy and cache the already allocated object for resuage. Only allocate when
the cache is empty.

Performance gain: ~ 10%

Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <20101130163820.338488630@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 c989583141029d3a42c699766e9abd28fb87b39d..9fef587ff11ff1f8e3c3f20a3dfcc8b067d2036d 100644 (file)
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -113,6 +113,7 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc
        self->machines = RB_ROOT;
        self->repipe = repipe;
        INIT_LIST_HEAD(&self->ordered_samples.samples);
+       INIT_LIST_HEAD(&self->ordered_samples.sample_cache);
        machine__init(&self->host_machine, "", HOST_KERNEL_ID);
 
        if (mode == O_RDONLY) {
@@ -398,6 +399,19 @@ struct sample_queue {
        struct list_head        list;
 };
 
+static void perf_session_free_sample_buffers(struct perf_session *session)
+{
+       struct ordered_samples *os = &session->ordered_samples;
+
+       while (!list_empty(&os->sample_cache)) {
+               struct sample_queue *sq;
+
+               sq = list_entry(os->sample_cache.next, struct sample_queue, list);
+               list_del(&sq->list);
+               free(sq);
+       }
+}
+
 static void flush_sample_queue(struct perf_session *s,
                               struct perf_event_ops *ops)
 {
@@ -418,7 +432,7 @@ static void flush_sample_queue(struct perf_session *s,
 
                os->last_flush = iter->timestamp;
                list_del(&iter->list);
-               free(iter);
+               list_add(&iter->list, &os->sample_cache);
        }
 
        if (list_empty(head)) {
@@ -527,6 +541,7 @@ static void __queue_sample_event(struct sample_queue *new,
 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;
        u64 timestamp = data->time;
        struct sample_queue *new;
 
@@ -535,9 +550,14 @@ static int queue_sample_event(event_t *event, struct sample_data *data,
                return -EINVAL;
        }
 
-       new = malloc(sizeof(*new));
-       if (!new)
-               return -ENOMEM;
+       if (!list_empty(sc)) {
+               new = list_entry(sc->next, struct sample_queue, list);
+               list_del(&new->list);
+       } else {
+               new = malloc(sizeof(*new));
+               if (!new)
+                       return -ENOMEM;
+       }
 
        new->timestamp = timestamp;
        new->event = event;
@@ -730,6 +750,7 @@ more:
 done:
        err = 0;
 out_err:
+       perf_session_free_sample_buffers(self);
        return err;
 }
 
@@ -862,6 +883,7 @@ out_err:
                            session->hists.stats.nr_unknown_events);
        }
 
+       perf_session_free_sample_buffers(session);
        return err;
 }
 

diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index a00f32ed1c7944a8fe75b80c1cdec7d24d2caa92..e4a7ff2ba8d593f688a83fc698bc108c1b2db6f6 100644 (file)
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -18,6 +18,7 @@ struct ordered_samples {
        u64                     next_flush;
        u64                     max_timestamp;
        struct list_head        samples;
+       struct list_head        sample_cache;
        struct sample_queue     *last_sample;
 };