perf hist: Only allocate callchain_node if processing callchains

The struct callchain_node size is 120 bytes, that are never used when
there are no callchains or '-g none' is specified, so conditionally
allocate it, reducing sizeof(struct hist_entry) from 210 bytes to only
96, greatly speeding the non-callchain processing.

LKML-Reference: <new-submission>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
Arnaldo Carvalho de Melo
2010-04-02 09:50:42 -03:00
parent 71cf8b8ff7
commit b9fb930477
3 changed files with 6 additions and 5 deletions

View File

@@ -50,7 +50,8 @@ struct hist_entry *__perf_session__add_hist_entry(struct rb_root *hists,
p = &(*p)->rb_right;
}
he = malloc(sizeof(*he));
he = malloc(sizeof(*he) + (symbol_conf.use_callchain ?
sizeof(struct callchain_node) : 0));
if (!he)
return NULL;
*he = entry;
@@ -168,7 +169,7 @@ static void perf_session__insert_output_hist_entry(struct rb_root *root,
struct hist_entry *iter;
if (symbol_conf.use_callchain)
callchain_param.sort(&he->sorted_chain, &he->callchain,
callchain_param.sort(&he->sorted_chain, he->callchain,
min_callchain_hits, &callchain_param);
while (*p != NULL) {