Use total latency info in the SPE counter packet as sample weight so
that we can see it in local_weight and (global) weight sort keys.
Maybe we can use PERF_SAMPLE_WEIGHT_STRUCT to support ins_lat as well
but I'm not sure which latency it matches. So just adding total
latency first.
Cc: German Gomez <[email protected]>
Cc: Leo Yan <[email protected]>
Cc: Mark Rutland <[email protected]>
Signed-off-by: Namhyung Kim <[email protected]>
---
tools/perf/util/arm-spe-decoder/arm-spe-decoder.c | 2 ++
tools/perf/util/arm-spe-decoder/arm-spe-decoder.h | 1 +
tools/perf/util/arm-spe.c | 4 +++-
3 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
index 3fc528c9270c..5e390a1a79ab 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
@@ -179,6 +179,8 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder)
decoder->record.phys_addr = ip;
break;
case ARM_SPE_COUNTER:
+ if (idx == SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT)
+ decoder->record.latency = payload;
break;
case ARM_SPE_CONTEXT:
decoder->record.context_id = payload;
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
index 46a8556a9e95..69b31084d6be 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
@@ -33,6 +33,7 @@ struct arm_spe_record {
enum arm_spe_sample_type type;
int err;
u32 op;
+ u32 latency;
u64 from_ip;
u64 to_ip;
u64 timestamp;
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 4748bcfe61de..a756325c72a7 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -317,6 +317,7 @@ static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq,
sample.addr = record->virt_addr;
sample.phys_addr = record->phys_addr;
sample.data_src = data_src;
+ sample.weight = record->latency;
return arm_spe_deliver_synth_event(spe, speq, event, &sample);
}
@@ -980,7 +981,8 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
attr.type = PERF_TYPE_HARDWARE;
attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
- PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC;
+ PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC |
+ PERF_SAMPLE_WEIGHT;
if (spe->timeless_decoding)
attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
else
--
2.34.0.rc2.393.gf8c9666880-goog
Hi Namhyung,
On Tue, Nov 30, 2021 at 04:39:08PM -0800, Namhyung Kim wrote:
> Use total latency info in the SPE counter packet as sample weight so
> that we can see it in local_weight and (global) weight sort keys.
>
> Maybe we can use PERF_SAMPLE_WEIGHT_STRUCT to support ins_lat as well
> but I'm not sure which latency it matches. So just adding total
> latency first.
>
> Cc: German Gomez <[email protected]>
> Cc: Leo Yan <[email protected]>
> Cc: Mark Rutland <[email protected]>
> Signed-off-by: Namhyung Kim <[email protected]>
> ---
> tools/perf/util/arm-spe-decoder/arm-spe-decoder.c | 2 ++
> tools/perf/util/arm-spe-decoder/arm-spe-decoder.h | 1 +
> tools/perf/util/arm-spe.c | 4 +++-
> 3 files changed, 6 insertions(+), 1 deletion(-)
>
> diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
> index 3fc528c9270c..5e390a1a79ab 100644
> --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
> +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
> @@ -179,6 +179,8 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder)
> decoder->record.phys_addr = ip;
> break;
> case ARM_SPE_COUNTER:
> + if (idx == SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT)
> + decoder->record.latency = payload;
> break;
> case ARM_SPE_CONTEXT:
> decoder->record.context_id = payload;
> diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
> index 46a8556a9e95..69b31084d6be 100644
> --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
> +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
> @@ -33,6 +33,7 @@ struct arm_spe_record {
> enum arm_spe_sample_type type;
> int err;
> u32 op;
> + u32 latency;
> u64 from_ip;
> u64 to_ip;
> u64 timestamp;
> diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
> index 4748bcfe61de..a756325c72a7 100644
> --- a/tools/perf/util/arm-spe.c
> +++ b/tools/perf/util/arm-spe.c
> @@ -317,6 +317,7 @@ static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq,
> sample.addr = record->virt_addr;
> sample.phys_addr = record->phys_addr;
> sample.data_src = data_src;
> + sample.weight = record->latency;
The latency can be used for branch operations as well, it's good to
assign latency for branch samples in the function
arm_spe__synth_branch_sample().
With adding latency for branch sample, the change would be good for me:
Reviewed-by: Leo Yan <[email protected]>
> return arm_spe_deliver_synth_event(spe, speq, event, &sample);
> }
> @@ -980,7 +981,8 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
> attr.type = PERF_TYPE_HARDWARE;
> attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
> attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
> - PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC;
> + PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC |
> + PERF_SAMPLE_WEIGHT;
> if (spe->timeless_decoding)
> attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
> else
> --
> 2.34.0.rc2.393.gf8c9666880-goog
>
Hi Leo,
On Tue, Nov 30, 2021 at 9:08 PM Leo Yan <[email protected]> wrote:
>
> Hi Namhyung,
>
> On Tue, Nov 30, 2021 at 04:39:08PM -0800, Namhyung Kim wrote:
> > Use total latency info in the SPE counter packet as sample weight so
> > that we can see it in local_weight and (global) weight sort keys.
> >
> > Maybe we can use PERF_SAMPLE_WEIGHT_STRUCT to support ins_lat as well
> > but I'm not sure which latency it matches. So just adding total
> > latency first.
> >
> > Cc: German Gomez <[email protected]>
> > Cc: Leo Yan <[email protected]>
> > Cc: Mark Rutland <[email protected]>
> > Signed-off-by: Namhyung Kim <[email protected]>
> > ---
> > tools/perf/util/arm-spe-decoder/arm-spe-decoder.c | 2 ++
> > tools/perf/util/arm-spe-decoder/arm-spe-decoder.h | 1 +
> > tools/perf/util/arm-spe.c | 4 +++-
> > 3 files changed, 6 insertions(+), 1 deletion(-)
> >
> > diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
> > index 3fc528c9270c..5e390a1a79ab 100644
> > --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
> > +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
> > @@ -179,6 +179,8 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder)
> > decoder->record.phys_addr = ip;
> > break;
> > case ARM_SPE_COUNTER:
> > + if (idx == SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT)
> > + decoder->record.latency = payload;
> > break;
> > case ARM_SPE_CONTEXT:
> > decoder->record.context_id = payload;
> > diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
> > index 46a8556a9e95..69b31084d6be 100644
> > --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
> > +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
> > @@ -33,6 +33,7 @@ struct arm_spe_record {
> > enum arm_spe_sample_type type;
> > int err;
> > u32 op;
> > + u32 latency;
> > u64 from_ip;
> > u64 to_ip;
> > u64 timestamp;
> > diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
> > index 4748bcfe61de..a756325c72a7 100644
> > --- a/tools/perf/util/arm-spe.c
> > +++ b/tools/perf/util/arm-spe.c
> > @@ -317,6 +317,7 @@ static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq,
> > sample.addr = record->virt_addr;
> > sample.phys_addr = record->phys_addr;
> > sample.data_src = data_src;
> > + sample.weight = record->latency;
>
> The latency can be used for branch operations as well, it's good to
> assign latency for branch samples in the function
> arm_spe__synth_branch_sample().
Yep, I'll update.
>
> With adding latency for branch sample, the change would be good for me:
>
> Reviewed-by: Leo Yan <[email protected]>
Thanks for your review!
Namhyung
>
> > return arm_spe_deliver_synth_event(spe, speq, event, &sample);
> > }
> > @@ -980,7 +981,8 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
> > attr.type = PERF_TYPE_HARDWARE;
> > attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
> > attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
> > - PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC;
> > + PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC |
> > + PERF_SAMPLE_WEIGHT;
> > if (spe->timeless_decoding)
> > attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
> > else
> > --
> > 2.34.0.rc2.393.gf8c9666880-goog
> >