lkml.org 
[lkml]   [2014]   [Mar]   [20]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    Patch in this message
    /
    From
    Subject[PATCH 06/21] perf report: Cache cumulative callchains
    Date
    It is possble that a callchain has cycles or recursive calls.  In that
    case it'll end up having entries more than 100% overhead in the
    output. In order to prevent such entries, cache each callchain node
    and skip if same entry already cumulated.

    Tested-by: Arun Sharma <asharma@fb.com>
    Acked-by: Jiri Olsa <jolsa@redhat.com>
    Cc: Frederic Weisbecker <fweisbec@gmail.com>
    Signed-off-by: Namhyung Kim <namhyung@kernel.org>
    ---
    tools/perf/util/hist.c | 43 +++++++++++++++++++++++++++++++++++++++++++
    1 file changed, 43 insertions(+)

    diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
    index 5ebdc346bffb..c393f13789cb 100644
    --- a/tools/perf/util/hist.c
    +++ b/tools/perf/util/hist.c
    @@ -716,7 +716,22 @@ static int
    iter_prepare_cumulative_entry(struct hist_entry_iter *iter __maybe_unused,
    struct addr_location *al __maybe_unused)
    {
    + struct hist_entry **he_cache;
    +
    callchain_cursor_commit(&callchain_cursor);
    +
    + /*
    + * This is for detecting cycles or recursions so that they're
    + * cumulated only one time to prevent entries more than 100%
    + * overhead.
    + */
    + he_cache = malloc(sizeof(*he_cache) * (PERF_MAX_STACK_DEPTH + 1));
    + if (he_cache == NULL)
    + return -ENOMEM;
    +
    + iter->priv = he_cache;
    + iter->curr = 0;
    +
    return 0;
    }

    @@ -726,6 +741,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
    {
    struct perf_evsel *evsel = iter->evsel;
    struct perf_sample *sample = iter->sample;
    + struct hist_entry **he_cache = iter->priv;
    struct hist_entry *he;

    he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
    @@ -734,6 +750,8 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
    if (he == NULL)
    return -ENOMEM;

    + he_cache[iter->curr++] = he;
    +
    return hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
    }

    @@ -758,7 +776,29 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
    {
    struct perf_evsel *evsel = iter->evsel;
    struct perf_sample *sample = iter->sample;
    + struct hist_entry **he_cache = iter->priv;
    struct hist_entry *he;
    + struct hist_entry he_tmp = {
    + .cpu = al->cpu,
    + .thread = al->thread,
    + .comm = thread__comm(al->thread),
    + .ip = al->addr,
    + .ms = {
    + .map = al->map,
    + .sym = al->sym,
    + },
    + .parent = iter->parent,
    + };
    + int i;
    +
    + /*
    + * Check if there's duplicate entries in the callchain.
    + * It's possible that it has cycles or recursive calls.
    + */
    + for (i = 0; i < iter->curr; i++) {
    + if (hist_entry__cmp(he_cache[i], &he_tmp) == 0)
    + return 0;
    + }

    he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
    sample->period, sample->weight,
    @@ -766,6 +806,8 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
    if (he == NULL)
    return -ENOMEM;

    + he_cache[iter->curr++] = he;
    +
    return hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
    }

    @@ -779,6 +821,7 @@ iter_finish_cumulative_entry(struct hist_entry_iter *iter,
    evsel->hists.stats.total_period += sample->period;
    hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);

    + zfree(&iter->priv);
    return 0;
    }

    --
    1.7.11.7


    \
     
     \ /
      Last update: 2014-03-20 09:01    [W:2.653 / U:0.012 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site