[PATCH v1 1/2] perf annotate: Record the max/min cycles
From: Jin Yao
Date: Thu May 17 2018 - 02:07:59 EST
Currently perf has a feature to account cycles for LBRs
For example, on skylake,
perf record -b ...
perf report or perf annotate
And then browsing the annotate browser gives average cycle counts
for program blocks.
For some analysis it would be useful if we could know not only
the average cycles but also the max and min cycles.
This patch records the max and min cycles.
Signed-off-by: Jin Yao <yao.jin@xxxxxxxxxxxxxxx>
---
tools/perf/util/annotate.c | 14 +++++++++++++-
tools/perf/util/annotate.h | 4 ++++
2 files changed, 17 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 536ee14..934a172 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -760,6 +760,15 @@ static int __symbol__account_cycles(struct annotation *notes,
ch[offset].num_aggr++;
ch[offset].cycles_aggr += cycles;
+ if (cycles > ch[offset].cycles_max)
+ ch[offset].cycles_max = cycles;
+
+ if (ch[offset].cycles_min) {
+ if (cycles && cycles < ch[offset].cycles_min)
+ ch[offset].cycles_min = cycles;
+ } else
+ ch[offset].cycles_min = cycles;
+
if (!have_start && ch[offset].have_start)
return 0;
if (ch[offset].num) {
@@ -953,8 +962,11 @@ void annotation__compute_ipc(struct annotation *notes, size_t size)
if (ch->have_start)
annotation__count_and_fill(notes, ch->start, offset, ch);
al = notes->offsets[offset];
- if (al && ch->num_aggr)
+ if (al && ch->num_aggr) {
al->cycles = ch->cycles_aggr / ch->num_aggr;
+ al->cycles_max = ch->cycles_max;
+ al->cycles_min = ch->cycles_min;
+ }
notes->have_cycles = true;
}
}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index f28a9e4..d50363d 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -105,6 +105,8 @@ struct annotation_line {
int jump_sources;
float ipc;
u64 cycles;
+ u64 cycles_max;
+ u64 cycles_min;
size_t privsize;
char *path;
u32 idx;
@@ -186,6 +188,8 @@ struct cyc_hist {
u64 start;
u64 cycles;
u64 cycles_aggr;
+ u64 cycles_max;
+ u64 cycles_min;
u32 num;
u32 num_aggr;
u8 have_start;
--
2.7.4