From 1b3a0e9592ebf174af934b3908a2bf6a6fa86169 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 14 Jan 2011 04:51:58 +0100 Subject: perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 25 ++++++++++++------------- 1 file changed, 12 insertions(+), 13 deletions(-) (limited to 'tools/perf/builtin-report.c') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index c27e31f289e6..c95599a82f9e 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -81,18 +81,17 @@ static int perf_session__add_hist_entry(struct perf_session *self, struct addr_location *al, struct sample_data *data) { - struct map_symbol *syms = NULL; struct symbol *parent = NULL; - int err = -ENOMEM; + int err = 0; struct hist_entry *he; struct hists *hists; struct perf_event_attr *attr; if ((sort__has_parent || symbol_conf.use_callchain) && data->callchain) { - syms = perf_session__resolve_callchain(self, al->thread, - data->callchain, &parent); - if (syms == NULL) - return -ENOMEM; + err = perf_session__resolve_callchain(self, al->thread, + data->callchain, &parent); + if (err) + return err; } attr = perf_header__find_attr(data->id, &self->header); @@ -101,16 +100,17 @@ static int perf_session__add_hist_entry(struct perf_session *self, else hists = perf_session__hists_findnew(self, data->id, 0, 0); if (hists == NULL) - goto out_free_syms; + return -ENOMEM; + he = __hists__add_entry(hists, al, parent, data->period); if (he == NULL) - goto out_free_syms; - err = 0; + return -ENOMEM; + if (symbol_conf.use_callchain) { - err = callchain_append(he->callchain, data->callchain, syms, + err = callchain_append(he->callchain, &self->callchain_cursor, data->period); if (err) - goto out_free_syms; + return err; } /* * Only in the newt browser we are doing integrated annotation, @@ -119,8 +119,7 @@ static int perf_session__add_hist_entry(struct perf_session *self, */ if (use_browser > 0) err = hist_entry__inc_addr_samples(he, al->addr); -out_free_syms: - free(syms); + return err; } -- cgit v1.2.3