mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-05 10:29:37 +00:00
perf hist: Add fast path for duplicate entries check
Perf checks the duplicate entries in a callchain before adding an entry. However the check is very slow especially with deeper call stack. Almost ~50% elapsed time of perf report is spent on the check when the call stack is always depth of 32. The hist_entry__cmp() is used to compare the new entry with the old entries. It will go through all the available sorts in the sort_list, and call the specific cmp of each sort, which is very slow. Actually, for most cases, there are no duplicate entries in callchain. The symbols are usually different. It's much faster to do a quick check for symbols first. Only do the full cmp when the symbols are exactly the same. The quick check is only to check symbols, not dso. Export _sort__sym_cmp. $ perf record --call-graph lbr ./tchain_edit_64 Without the patch $time perf report --stdio real 0m21.142s user 0m21.110s sys 0m0.033s With the patch $time perf report --stdio real 0m10.977s user 0m10.948s sys 0m0.027s Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexey Budankov <alexey.budankov@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Pavel Gerasimov <pavel.gerasimov@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Stephane Eranian <eranian@google.com> Cc: Vitaly Slobodskoy <vitaly.slobodskoy@intel.com> Link: http://lore.kernel.org/lkml/20200319202517.23423-18-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
parent
d80da766d1
commit
12e89e65f4
3 changed files with 26 additions and 1 deletions
|
@ -1070,6 +1070,20 @@ iter_next_cumulative_entry(struct hist_entry_iter *iter,
|
|||
return fill_callchain_info(al, node, iter->hide_unresolved);
|
||||
}
|
||||
|
||||
static bool
|
||||
hist_entry__fast__sym_diff(struct hist_entry *left,
|
||||
struct hist_entry *right)
|
||||
{
|
||||
struct symbol *sym_l = left->ms.sym;
|
||||
struct symbol *sym_r = right->ms.sym;
|
||||
|
||||
if (!sym_l && !sym_r)
|
||||
return left->ip != right->ip;
|
||||
|
||||
return !!_sort__sym_cmp(sym_l, sym_r);
|
||||
}
|
||||
|
||||
|
||||
static int
|
||||
iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
|
||||
struct addr_location *al)
|
||||
|
@ -1096,6 +1110,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
|
|||
};
|
||||
int i;
|
||||
struct callchain_cursor cursor;
|
||||
bool fast = hists__has(he_tmp.hists, sym);
|
||||
|
||||
callchain_cursor_snapshot(&cursor, &callchain_cursor);
|
||||
|
||||
|
@ -1106,6 +1121,14 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
|
|||
* It's possible that it has cycles or recursive calls.
|
||||
*/
|
||||
for (i = 0; i < iter->curr; i++) {
|
||||
/*
|
||||
* For most cases, there are no duplicate entries in callchain.
|
||||
* The symbols are usually different. Do a quick check for
|
||||
* symbols first.
|
||||
*/
|
||||
if (fast && hist_entry__fast__sym_diff(he_cache[i], &he_tmp))
|
||||
continue;
|
||||
|
||||
if (hist_entry__cmp(he_cache[i], &he_tmp) == 0) {
|
||||
/* to avoid calling callback function */
|
||||
iter->he = NULL;
|
||||
|
|
|
@ -237,7 +237,7 @@ static int64_t _sort__addr_cmp(u64 left_ip, u64 right_ip)
|
|||
return (int64_t)(right_ip - left_ip);
|
||||
}
|
||||
|
||||
static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
|
||||
int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
|
||||
{
|
||||
if (!sym_l || !sym_r)
|
||||
return cmp_null(sym_l, sym_r);
|
||||
|
|
|
@ -311,5 +311,7 @@ int64_t
|
|||
sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right);
|
||||
int64_t
|
||||
sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right);
|
||||
int64_t
|
||||
_sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r);
|
||||
char *hist_entry__srcline(struct hist_entry *he);
|
||||
#endif /* __PERF_SORT_H */
|
||||
|
|
Loading…
Reference in a new issue