perf: Keep track of the max depth of a callchain

In order to implement callchains collapsing, we need to keep
track of the maximum depth in a histogram tree of callchains.
This way we'll avoid allocating an arbitrary temporary buffer
size on callchain merge time.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Christoph Hellwig <hch@infradead.org>
This commit is contained in:
Frederic Weisbecker
2010-08-22 20:05:22 +02:00
parent f4e7ac0a23
commit d2009c5130
4 changed files with 29 additions and 20 deletions

View File

@@ -87,7 +87,7 @@ static void hist_entry__add_cpumode_period(struct hist_entry *self,
static struct hist_entry *hist_entry__new(struct hist_entry *template)
{
size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_node) : 0;
size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_root) : 0;
struct hist_entry *self = malloc(sizeof(*self) + callchain_size);
if (self != NULL) {