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/util/hist.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'tools/perf/util/hist.c') diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 32f4f1f2f6e4..a438a0652d23 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -211,7 +211,9 @@ void hist_entry__free(struct hist_entry *he) * collapse the histogram */ -static bool collapse__insert_entry(struct rb_root *root, struct hist_entry *he) +static bool hists__collapse_insert_entry(struct hists *self, + struct rb_root *root, + struct hist_entry *he) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; @@ -226,8 +228,11 @@ static bool collapse__insert_entry(struct rb_root *root, struct hist_entry *he) if (!cmp) { iter->period += he->period; - if (symbol_conf.use_callchain) - callchain_merge(iter->callchain, he->callchain); + if (symbol_conf.use_callchain) { + callchain_cursor_reset(&self->callchain_cursor); + callchain_merge(&self->callchain_cursor, iter->callchain, + he->callchain); + } hist_entry__free(he); return false; } @@ -262,7 +267,7 @@ void hists__collapse_resort(struct hists *self) next = rb_next(&n->rb_node); rb_erase(&n->rb_node, &self->entries); - if (collapse__insert_entry(&tmp, n)) + if (hists__collapse_insert_entry(self, &tmp, n)) hists__inc_nr_entries(self, n); } -- cgit v1.2.2 From f08c3154ac439c4b5762a40107d84e839e08fbc5 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 14 Jan 2011 04:51:59 +0100 Subject: perf callchain: Rename cumul_hits into callchain_cumul_hits That makes the callchain API naming more consistent and reduce potential naming clashes. Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra LKML-Reference: <1294977121-5700-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hist.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/util/hist.c') diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index a438a0652d23..02ed318d7312 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -430,7 +430,7 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct callchain_node *self, u64 cumul; child = rb_entry(node, struct callchain_node, rb_node); - cumul = cumul_hits(child); + cumul = callchain_cumul_hits(child); remaining -= cumul; /* -- cgit v1.2.2