[tip:perf/core] perf stat: Move the shadow stats scale computation in perf_stat__update_shadow_stats
From: tip-bot for Jiri Olsa
Date: Fri Nov 03 2017 - 10:25:13 EST
Commit-ID: 54830dd0c342525de2ff10f8be7cf0a9f062b896
Gitweb: https://git.kernel.org/tip/54830dd0c342525de2ff10f8be7cf0a9f062b896
Author: Jiri Olsa <jolsa@xxxxxxxxxx>
AuthorDate: Mon, 23 Jan 2017 22:42:56 +0100
Committer: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
CommitDate: Mon, 30 Oct 2017 13:40:33 -0300
perf stat: Move the shadow stats scale computation in perf_stat__update_shadow_stats
Move the shadow stats scale computation to the
perf_stat__update_shadow_stats() function, so it's centralized and we
don't forget to do it. It also saves few lines of code.
Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Andi Kleen <andi@xxxxxxxxxxxxxx>
Cc: Changbin Du <changbin.du@xxxxxxxxx>
Cc: David Ahern <dsahern@xxxxxxxxx>
Cc: Jin Yao <yao.jin@xxxxxxxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Wang Nan <wangnan0@xxxxxxxxxx>
Link: http://lkml.kernel.org/n/tip-htg7mmyxv6pcrf57qyo6msid@xxxxxxxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
tools/perf/builtin-stat.c | 3 +--
tools/perf/util/stat-shadow.c | 48 ++++++++++++++++++++++---------------------
tools/perf/util/stat.c | 6 ++----
tools/perf/util/stat.h | 2 +-
4 files changed, 29 insertions(+), 30 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index fa58962..59af5a8 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1267,8 +1267,7 @@ static void aggr_update_shadow(void)
continue;
val += perf_counts(counter->counts, cpu, 0)->val;
}
- val = val * counter->scale;
- perf_stat__update_shadow_stats(counter, &val,
+ perf_stat__update_shadow_stats(counter, val,
first_shadow_cpu(counter, id));
}
}
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index a2c12d1e..51ad03a 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -178,58 +178,60 @@ void perf_stat__reset_shadow_stats(void)
* more semantic information such as miss/hit ratios,
* instruction rates, etc:
*/
-void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
int cpu)
{
int ctx = evsel_context(counter);
+ count *= counter->scale;
+
if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK) ||
perf_evsel__match(counter, SOFTWARE, SW_CPU_CLOCK))
- update_stats(&runtime_nsecs_stats[cpu], count[0]);
+ update_stats(&runtime_nsecs_stats[cpu], count);
else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
- update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_cycles_stats[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
- update_stats(&runtime_cycles_in_tx_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_cycles_in_tx_stats[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, TRANSACTION_START))
- update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_transaction_stats[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, ELISION_START))
- update_stats(&runtime_elision_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_elision_stats[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS))
- update_stats(&runtime_topdown_total_slots[ctx][cpu], count[0]);
+ update_stats(&runtime_topdown_total_slots[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED))
- update_stats(&runtime_topdown_slots_issued[ctx][cpu], count[0]);
+ update_stats(&runtime_topdown_slots_issued[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED))
- update_stats(&runtime_topdown_slots_retired[ctx][cpu], count[0]);
+ update_stats(&runtime_topdown_slots_retired[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES))
- update_stats(&runtime_topdown_fetch_bubbles[ctx][cpu],count[0]);
+ update_stats(&runtime_topdown_fetch_bubbles[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
- update_stats(&runtime_topdown_recovery_bubbles[ctx][cpu], count[0]);
+ update_stats(&runtime_topdown_recovery_bubbles[ctx][cpu], count);
else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
- update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count);
else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
- update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count);
else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
- update_stats(&runtime_branches_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_branches_stats[ctx][cpu], count);
else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
- update_stats(&runtime_cacherefs_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_cacherefs_stats[ctx][cpu], count);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
- update_stats(&runtime_l1_dcache_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_l1_dcache_stats[ctx][cpu], count);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
- update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_ll_cache_stats[ctx][cpu], count);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
- update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_ll_cache_stats[ctx][cpu], count);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
- update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
- update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_itlb_cache_stats[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, SMI_NUM))
- update_stats(&runtime_smi_num_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_smi_num_stats[ctx][cpu], count);
else if (perf_stat_evsel__is(counter, APERF))
- update_stats(&runtime_aperf_stats[ctx][cpu], count[0]);
+ update_stats(&runtime_aperf_stats[ctx][cpu], count);
if (counter->collect_stat) {
struct saved_value *v = saved_value_lookup(counter, cpu, true);
- update_stats(&v->stats, count[0]);
+ update_stats(&v->stats, count);
}
}
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 933de91..ef00c91 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -277,7 +277,7 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel
perf_evsel__compute_deltas(evsel, cpu, thread, count);
perf_counts_values__scale(count, config->scale, NULL);
if (config->aggr_mode == AGGR_NONE)
- perf_stat__update_shadow_stats(evsel, count->values, cpu);
+ perf_stat__update_shadow_stats(evsel, count->val, cpu);
break;
case AGGR_GLOBAL:
aggr->val += count->val;
@@ -320,7 +320,6 @@ int perf_stat_process_counter(struct perf_stat_config *config,
struct perf_counts_values *aggr = &counter->counts->aggr;
struct perf_stat_evsel *ps = counter->stats;
u64 *count = counter->counts->aggr.values;
- u64 val;
int i, ret;
aggr->val = aggr->ena = aggr->run = 0;
@@ -360,8 +359,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
/*
* Save the full runtime - to allow normalization during printout:
*/
- val = counter->scale * *count;
- perf_stat__update_shadow_stats(counter, &val, 0);
+ perf_stat__update_shadow_stats(counter, *count, 0);
return 0;
}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 47915df..490b78a 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -82,7 +82,7 @@ typedef void (*new_line_t )(void *ctx);
void perf_stat__init_shadow_stats(void);
void perf_stat__reset_shadow_stats(void);
-void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
int cpu);
struct perf_stat_output_ctx {
void *ctx;