Skip to contentSkip to conversation

Bug fixes on topdown events reordering

PATCH Superseded Dapeng Mi 3 participants 16 messages Jul 12, 2024 – Aug 15, 2024 perf events

v3 of 5 Superseded Latest is v5 →

lore
Share & tools
lore

Dapeng Mi

author
#0 lore raw

v3 cover Bug fixes on topdown events reordering

Changes:
v2 -> v3:
* Refine arch_is_topdown_metrics() (Kan Liang)
* Only move topdown metric events forward when they are not in the group with previous event (Ian)
* Check if topdown events is supported before test topown events leader sampling (Kan Liang)

History:
v1: https://lore.kernel.org/all/[email protected]/
v2: https://lore.kernel.org/all/[email protected]/

Dapeng Mi (5):
perf x86/topdown: Complete topdown slots/metrics events check perf x86/topdown: Correct leader selection with sample_read enabled perf x86/topdown: Don't move topdown metric events in group perf tests: Add leader sampling test in record tests perf tests: Add topdown events counting and sampling tests

 tools/perf/arch/x86/util/evlist.c  | 13 +++++--
 tools/perf/arch/x86/util/evsel.c   |  3 +-
 tools/perf/arch/x86/util/topdown.c | 62 +++++++++++++++++++++++++++++-
 tools/perf/arch/x86/util/topdown.h |  2 +
 tools/perf/tests/shell/record.sh   | 45 ++++++++++++++++++++++
 tools/perf/tests/shell/stat.sh     |  6 +++
 6 files changed, 124 insertions(+), 7 deletions(-)

base-commit: 73e931504f8e0d42978bfcda37b323dbbd1afc08

Signature · 1 line
2.40.1
author
#1 lore raw

PATCH v3 1/5 perf x86/topdown: Complete topdown slots/metrics events check

It's not complete to check whether an event is a topdown slots or topdown metrics event by only comparing the event name since user may assign the event by RAW format, e.g.

perf stat -e '{instructions,cpu/r400/,cpu/r8300/}' sleep 1

Performance counter stats for 'sleep 1':

     <not counted>      instructions
     <not counted>      cpu/r400/
   <not supported>      cpu/r8300/
       1.002917796 seconds time elapsed

       0.002955000 seconds user
       0.000000000 seconds sys

The RAW format slots and topdown-be-bound events are not recognized and not regroup the events, and eventually cause error.

Thus add two helpers arch_is_topdown_slots()/arch_is_topdown_metrics() to detect whether an event is topdown slots/metrics event by comparing the event config directly, and use these two helpers to replace the original event name comparisons.

---
 tools/perf/arch/x86/util/evlist.c  |  8 ++---
 tools/perf/arch/x86/util/evsel.c   |  3 +-
 tools/perf/arch/x86/util/topdown.c | 48 +++++++++++++++++++++++++++++-
 tools/perf/arch/x86/util/topdown.h |  2 ++
 4 files changed, 55 insertions(+), 6 deletions(-)
tools/perf/arch/x86/util/evlist.c +4 -4
index b1ce0c52d88d..332e8907f43e 100644
@@ -78,14 +78,14 @@ int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
 	if (topdown_sys_has_perf_metrics() &&
 	    (arch_evsel__must_be_in_group(lhs) || arch_evsel__must_be_in_group(rhs))) {
 		/* Ensure the topdown slots comes first. */
-		if (strcasestr(lhs->name, "slots") && !strcasestr(lhs->name, "uops_retired.slots"))
+		if (arch_is_topdown_slots(lhs))
 			return -1;
-		if (strcasestr(rhs->name, "slots") && !strcasestr(rhs->name, "uops_retired.slots"))
+		if (arch_is_topdown_slots(rhs))
 			return 1;
 		/* Followed by topdown events. */
-		if (strcasestr(lhs->name, "topdown") && !strcasestr(rhs->name, "topdown"))
+		if (arch_is_topdown_metrics(lhs) && !arch_is_topdown_metrics(rhs))
 			return -1;
-		if (!strcasestr(lhs->name, "topdown") && strcasestr(rhs->name, "topdown"))
+		if (!arch_is_topdown_metrics(lhs) && arch_is_topdown_metrics(rhs))
 			return 1;
 	}
 
tools/perf/arch/x86/util/evsel.c +2 -1
index 090d0f371891..181f2ba0bb2a 100644
@@ -6,6 +6,7 @@
 #include "util/pmu.h"
 #include "util/pmus.h"
 #include "linux/string.h"
+#include "topdown.h"
 #include "evsel.h"
 #include "util/debug.h"
 #include "env.h"
@@ -44,7 +45,7 @@ bool arch_evsel__must_be_in_group(const struct evsel *evsel)
 	    strcasestr(evsel->name, "uops_retired.slots"))
 		return false;
 
-	return strcasestr(evsel->name, "topdown") || strcasestr(evsel->name, "slots");
+	return arch_is_topdown_metrics(evsel) || arch_is_topdown_slots(evsel);
 }
 
 int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
tools/perf/arch/x86/util/topdown.c +47 -1

60 lines not on this page · raw message

tools/perf/arch/x86/util/topdown.h +2 -0
index 46bf9273e572..1bae9b1822d7 100644
@@ -3,5 +3,7 @@
 #define _TOPDOWN_H 1
 
 bool topdown_sys_has_perf_metrics(void);
+bool arch_is_topdown_slots(const struct evsel *evsel);
+bool arch_is_topdown_metrics(const struct evsel *evsel);
 
 #endif
Signature · 1 line
2.40.1
#2 lore raw

Re: [Patch v3 1/5] perf x86/topdown: Complete topdown slots/metrics events check

Quoted 17 lines · Dapeng Mi

It's not complete to check whether an event is a topdown slots or topdown metrics event by only comparing the event name since user may assign the event by RAW format, e.g.

perf stat -e '{instructions,cpu/r400/,cpu/r8300/}' sleep 1

Performance counter stats for 'sleep 1':

     <not counted>      instructions
     <not counted>      cpu/r400/
   <not supported>      cpu/r8300/
       1.002917796 seconds time elapsed

       0.002955000 seconds user
       0.000000000 seconds sys
Quoted 7 lines

The RAW format slots and topdown-be-bound events are not recognized and not regroup the events, and eventually cause error.

Thus add two helpers arch_is_topdown_slots()/arch_is_topdown_metrics() to detect whether an event is topdown slots/metrics event by comparing the event config directly, and use these two helpers to replace the original event name comparisons.

Looks ok, I made a comment below, please take a look

Quoted 86 lines
---
 tools/perf/arch/x86/util/evlist.c  |  8 ++---
 tools/perf/arch/x86/util/evsel.c   |  3 +-
 tools/perf/arch/x86/util/topdown.c | 48 +++++++++++++++++++++++++++++-
 tools/perf/arch/x86/util/topdown.h |  2 ++
 4 files changed, 55 insertions(+), 6 deletions(-)
tools/perf/arch/x86/util/evlist.c +4 -4
index b1ce0c52d88d..332e8907f43e 100644
@@ -78,14 +78,14 @@ int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
 	if (topdown_sys_has_perf_metrics() &&
 	    (arch_evsel__must_be_in_group(lhs) || arch_evsel__must_be_in_group(rhs))) {
 		/* Ensure the topdown slots comes first. */
-		if (strcasestr(lhs->name, "slots") && !strcasestr(lhs->name, "uops_retired.slots"))
+		if (arch_is_topdown_slots(lhs))
 			return -1;
-		if (strcasestr(rhs->name, "slots") && !strcasestr(rhs->name, "uops_retired.slots"))
+		if (arch_is_topdown_slots(rhs))
 			return 1;
 		/* Followed by topdown events. */
-		if (strcasestr(lhs->name, "topdown") && !strcasestr(rhs->name, "topdown"))
+		if (arch_is_topdown_metrics(lhs) && !arch_is_topdown_metrics(rhs))
 			return -1;
-		if (!strcasestr(lhs->name, "topdown") && strcasestr(rhs->name, "topdown"))
+		if (!arch_is_topdown_metrics(lhs) && arch_is_topdown_metrics(rhs))
 			return 1;
 	}
 
tools/perf/arch/x86/util/evsel.c +2 -1
index 090d0f371891..181f2ba0bb2a 100644
@@ -6,6 +6,7 @@
 #include "util/pmu.h"
 #include "util/pmus.h"
 #include "linux/string.h"
+#include "topdown.h"
 #include "evsel.h"
 #include "util/debug.h"
 #include "env.h"
@@ -44,7 +45,7 @@ bool arch_evsel__must_be_in_group(const struct evsel *evsel)
 	    strcasestr(evsel->name, "uops_retired.slots"))
 		return false;
 
-	return strcasestr(evsel->name, "topdown") || strcasestr(evsel->name, "slots");
+	return arch_is_topdown_metrics(evsel) || arch_is_topdown_slots(evsel);
 }
 
 int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
tools/perf/arch/x86/util/topdown.c +26 -0
index 3f9a267d4501..49f25d67ed77 100644
@@ -32,6 +32,52 @@ bool topdown_sys_has_perf_metrics(void)
 }
 
 #define TOPDOWN_SLOTS		0x0400
+bool arch_is_topdown_slots(const struct evsel *evsel)
+{
+	if (evsel->core.attr.config == TOPDOWN_SLOTS)
+		return true;
+
+	return false;
+}
+
+static int compare_topdown_event(void *vstate, struct pmu_event_info *info)
+{
+	int *config = vstate;
+	int event = 0;
+	int umask = 0;
+	char *str;
+
+	if (!strcasestr(info->name, "topdown"))
+		return 0;
+
+	str = strcasestr(info->str, "event=");
+	if (str)
+		sscanf(str, "event=%x", &event);
+
+	str = strcasestr(info->str, "umask=");
+	if (str)
+		sscanf(str, "umask=%x", &umask);
+

tools/perf/arch/x86/util/topdown.c bool topdown_sys_has_perf_metrics(void) · line 70

Quoted 10 lines
tools/perf/arch/x86/util/topdown.c +10 -0
+	if (event == 0 && *config == (event | umask << 8))
+		return 1;
+
+	return 0;
+}
+
+bool arch_is_topdown_metrics(const struct evsel *evsel)
+{
+	struct perf_pmu *pmu = evsel__find_pmu(evsel);
+	int config = evsel->core.attr.config;

Humm, can we cache this information? I.e. have some evsel->is_topdown:1 bit to avoid having to traverse all events if we call this multiple times for the same evsel?

- Arnaldo

Quoted 36 lines
tools/perf/arch/x86/util/topdown.c +10 -1
+	if (!pmu || !pmu->is_core)
+		return false;
+
+	if (perf_pmu__for_each_event(pmu, false, &config,
+				     compare_topdown_event))
+		return true;
+
+	return false;
+}
 
 /*
  * Check whether a topdown group supports sample-read.
@@ -44,7 +90,7 @@ bool arch_topdown_sample_read(struct evsel *leader)
 	if (!evsel__sys_has_perf_metrics(leader))
 		return false;
 
-	if (leader->core.attr.config == TOPDOWN_SLOTS)
+	if (arch_is_topdown_slots(leader))
 		return true;
 
 	return false;
tools/perf/arch/x86/util/topdown.h +2 -0
index 46bf9273e572..1bae9b1822d7 100644
@@ -3,5 +3,7 @@
 #define _TOPDOWN_H 1
 
 bool topdown_sys_has_perf_metrics(void);
+bool arch_is_topdown_slots(const struct evsel *evsel);
+bool arch_is_topdown_metrics(const struct evsel *evsel);
 
 #endif
Signature · 1 line
2.40.1
author
#3 lore raw

Re: [Patch v3 1/5] perf x86/topdown: Complete topdown slots/metrics events check

Quoted 118 lines · Arnaldo Carvalho de Melo
Quoted 17 lines · Dapeng Mi

It's not complete to check whether an event is a topdown slots or topdown metrics event by only comparing the event name since user may assign the event by RAW format, e.g.

perf stat -e '{instructions,cpu/r400/,cpu/r8300/}' sleep 1

Performance counter stats for 'sleep 1':

     <not counted>      instructions
     <not counted>      cpu/r400/
   <not supported>      cpu/r8300/
       1.002917796 seconds time elapsed

       0.002955000 seconds user
       0.000000000 seconds sys
Quoted 7 lines

The RAW format slots and topdown-be-bound events are not recognized and not regroup the events, and eventually cause error.

Thus add two helpers arch_is_topdown_slots()/arch_is_topdown_metrics() to detect whether an event is topdown slots/metrics event by comparing the event config directly, and use these two helpers to replace the original event name comparisons.

Looks ok, I made a comment below, please take a look

Quoted 91 lines
---
 tools/perf/arch/x86/util/evlist.c  |  8 ++---
 tools/perf/arch/x86/util/evsel.c   |  3 +-
 tools/perf/arch/x86/util/topdown.c | 48 +++++++++++++++++++++++++++++-
 tools/perf/arch/x86/util/topdown.h |  2 ++
 4 files changed, 55 insertions(+), 6 deletions(-)
tools/perf/arch/x86/util/evlist.c +4 -4
index b1ce0c52d88d..332e8907f43e 100644
@@ -78,14 +78,14 @@ int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
 	if (topdown_sys_has_perf_metrics() &&
 	    (arch_evsel__must_be_in_group(lhs) || arch_evsel__must_be_in_group(rhs))) {
 		/* Ensure the topdown slots comes first. */
-		if (strcasestr(lhs->name, "slots") && !strcasestr(lhs->name, "uops_retired.slots"))
+		if (arch_is_topdown_slots(lhs))
 			return -1;
-		if (strcasestr(rhs->name, "slots") && !strcasestr(rhs->name, "uops_retired.slots"))
+		if (arch_is_topdown_slots(rhs))
 			return 1;
 		/* Followed by topdown events. */
-		if (strcasestr(lhs->name, "topdown") && !strcasestr(rhs->name, "topdown"))
+		if (arch_is_topdown_metrics(lhs) && !arch_is_topdown_metrics(rhs))
 			return -1;
-		if (!strcasestr(lhs->name, "topdown") && strcasestr(rhs->name, "topdown"))
+		if (!arch_is_topdown_metrics(lhs) && arch_is_topdown_metrics(rhs))
 			return 1;
 	}
 
tools/perf/arch/x86/util/evsel.c +2 -1
index 090d0f371891..181f2ba0bb2a 100644
@@ -6,6 +6,7 @@
 #include "util/pmu.h"
 #include "util/pmus.h"
 #include "linux/string.h"
+#include "topdown.h"
 #include "evsel.h"
 #include "util/debug.h"
 #include "env.h"
@@ -44,7 +45,7 @@ bool arch_evsel__must_be_in_group(const struct evsel *evsel)
 	    strcasestr(evsel->name, "uops_retired.slots"))
 		return false;
 
-	return strcasestr(evsel->name, "topdown") || strcasestr(evsel->name, "slots");
+	return arch_is_topdown_metrics(evsel) || arch_is_topdown_slots(evsel);
 }
 
 int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
tools/perf/arch/x86/util/topdown.c +31 -0
index 3f9a267d4501..49f25d67ed77 100644
@@ -32,6 +32,52 @@ bool topdown_sys_has_perf_metrics(void)
 }
 
 #define TOPDOWN_SLOTS		0x0400
+bool arch_is_topdown_slots(const struct evsel *evsel)
+{
+	if (evsel->core.attr.config == TOPDOWN_SLOTS)
+		return true;
+
+	return false;
+}
+
+static int compare_topdown_event(void *vstate, struct pmu_event_info *info)
+{
+	int *config = vstate;
+	int event = 0;
+	int umask = 0;
+	char *str;
+
+	if (!strcasestr(info->name, "topdown"))
+		return 0;
+
+	str = strcasestr(info->str, "event=");
+	if (str)
+		sscanf(str, "event=%x", &event);
+
+	str = strcasestr(info->str, "umask=");
+	if (str)
+		sscanf(str, "umask=%x", &umask);
+
+	if (event == 0 && *config == (event | umask << 8))
+		return 1;
+
+	return 0;
+}
Quoted 8 lines

tools/perf/arch/x86/util/topdown.c bool topdown_sys_has_perf_metrics(void) · line 70

Quoted 5 lines
tools/perf/arch/x86/util/topdown.c +5 -0
+
+bool arch_is_topdown_metrics(const struct evsel *evsel)
+{
+	struct perf_pmu *pmu = evsel__find_pmu(evsel);
+	int config = evsel->core.attr.config;

Humm, can we cache this information? I.e. have some evsel->is_topdown:1 bit to avoid having to traverse all events if we call this multiple times for the same evsel?

Yeah, good point. Thanks.

Quoted 39 lines

- Arnaldo

Quoted 36 lines
tools/perf/arch/x86/util/topdown.c +10 -1
+	if (!pmu || !pmu->is_core)
+		return false;
+
+	if (perf_pmu__for_each_event(pmu, false, &config,
+				     compare_topdown_event))
+		return true;
+
+	return false;
+}
 
 /*
  * Check whether a topdown group supports sample-read.
@@ -44,7 +90,7 @@ bool arch_topdown_sample_read(struct evsel *leader)
 	if (!evsel__sys_has_perf_metrics(leader))
 		return false;
 
-	if (leader->core.attr.config == TOPDOWN_SLOTS)
+	if (arch_is_topdown_slots(leader))
 		return true;
 
 	return false;
tools/perf/arch/x86/util/topdown.h +2 -0
index 46bf9273e572..1bae9b1822d7 100644
@@ -3,5 +3,7 @@
 #define _TOPDOWN_H 1
 
 bool topdown_sys_has_perf_metrics(void);
+bool arch_is_topdown_slots(const struct evsel *evsel);
+bool arch_is_topdown_metrics(const struct evsel *evsel);
 
 #endif
Signature · 1 line
2.40.1
author
#4 lore raw

Re: [Patch v3 1/5] perf x86/topdown: Complete topdown slots/metrics events check

In reply to Arnaldo Carvalho de Melo
Quoted 118 lines · Arnaldo Carvalho de Melo
Quoted 17 lines · Dapeng Mi

It's not complete to check whether an event is a topdown slots or topdown metrics event by only comparing the event name since user may assign the event by RAW format, e.g.

perf stat -e '{instructions,cpu/r400/,cpu/r8300/}' sleep 1

Performance counter stats for 'sleep 1':

     <not counted>      instructions
     <not counted>      cpu/r400/
   <not supported>      cpu/r8300/
       1.002917796 seconds time elapsed

       0.002955000 seconds user
       0.000000000 seconds sys
Quoted 7 lines

The RAW format slots and topdown-be-bound events are not recognized and not regroup the events, and eventually cause error.

Thus add two helpers arch_is_topdown_slots()/arch_is_topdown_metrics() to detect whether an event is topdown slots/metrics event by comparing the event config directly, and use these two helpers to replace the original event name comparisons.

Looks ok, I made a comment below, please take a look

Quoted 91 lines
---
 tools/perf/arch/x86/util/evlist.c  |  8 ++---
 tools/perf/arch/x86/util/evsel.c   |  3 +-
 tools/perf/arch/x86/util/topdown.c | 48 +++++++++++++++++++++++++++++-
 tools/perf/arch/x86/util/topdown.h |  2 ++
 4 files changed, 55 insertions(+), 6 deletions(-)
tools/perf/arch/x86/util/evlist.c +4 -4
index b1ce0c52d88d..332e8907f43e 100644
@@ -78,14 +78,14 @@ int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
 	if (topdown_sys_has_perf_metrics() &&
 	    (arch_evsel__must_be_in_group(lhs) || arch_evsel__must_be_in_group(rhs))) {
 		/* Ensure the topdown slots comes first. */
-		if (strcasestr(lhs->name, "slots") && !strcasestr(lhs->name, "uops_retired.slots"))
+		if (arch_is_topdown_slots(lhs))
 			return -1;
-		if (strcasestr(rhs->name, "slots") && !strcasestr(rhs->name, "uops_retired.slots"))
+		if (arch_is_topdown_slots(rhs))
 			return 1;
 		/* Followed by topdown events. */
-		if (strcasestr(lhs->name, "topdown") && !strcasestr(rhs->name, "topdown"))
+		if (arch_is_topdown_metrics(lhs) && !arch_is_topdown_metrics(rhs))
 			return -1;
-		if (!strcasestr(lhs->name, "topdown") && strcasestr(rhs->name, "topdown"))
+		if (!arch_is_topdown_metrics(lhs) && arch_is_topdown_metrics(rhs))
 			return 1;
 	}
 
tools/perf/arch/x86/util/evsel.c +2 -1
index 090d0f371891..181f2ba0bb2a 100644
@@ -6,6 +6,7 @@
 #include "util/pmu.h"
 #include "util/pmus.h"
 #include "linux/string.h"
+#include "topdown.h"
 #include "evsel.h"
 #include "util/debug.h"
 #include "env.h"
@@ -44,7 +45,7 @@ bool arch_evsel__must_be_in_group(const struct evsel *evsel)
 	    strcasestr(evsel->name, "uops_retired.slots"))
 		return false;
 
-	return strcasestr(evsel->name, "topdown") || strcasestr(evsel->name, "slots");
+	return arch_is_topdown_metrics(evsel) || arch_is_topdown_slots(evsel);
 }
 
 int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
tools/perf/arch/x86/util/topdown.c +31 -0
index 3f9a267d4501..49f25d67ed77 100644
@@ -32,6 +32,52 @@ bool topdown_sys_has_perf_metrics(void)
 }
 
 #define TOPDOWN_SLOTS		0x0400
+bool arch_is_topdown_slots(const struct evsel *evsel)
+{
+	if (evsel->core.attr.config == TOPDOWN_SLOTS)
+		return true;
+
+	return false;
+}
+
+static int compare_topdown_event(void *vstate, struct pmu_event_info *info)
+{
+	int *config = vstate;
+	int event = 0;
+	int umask = 0;
+	char *str;
+
+	if (!strcasestr(info->name, "topdown"))
+		return 0;
+
+	str = strcasestr(info->str, "event=");
+	if (str)
+		sscanf(str, "event=%x", &event);
+
+	str = strcasestr(info->str, "umask=");
+	if (str)
+		sscanf(str, "umask=%x", &umask);
+
+	if (event == 0 && *config == (event | umask << 8))
+		return 1;
+
+	return 0;
+}
Quoted 8 lines

tools/perf/arch/x86/util/topdown.c bool topdown_sys_has_perf_metrics(void) · line 70

Quoted 5 lines
tools/perf/arch/x86/util/topdown.c +5 -0
+
+bool arch_is_topdown_metrics(const struct evsel *evsel)
+{
+	struct perf_pmu *pmu = evsel__find_pmu(evsel);
+	int config = evsel->core.attr.config;

Humm, can we cache this information? I.e. have some evsel->is_topdown:1 bit to avoid having to traverse all events if we call this multiple times for the same evsel?

Arnaldo, I tried to add a variable in evsel structure to represent if the evsel is a topdown metrics event, but unfortunately the helper argument "evsel" has "const" qualifier, it forces the "evsel" structure can't be modified. If we want to add this optimization, the entire call-chain functions have to be modified and this would reduce the security of code as well. Since this helper is not in a performance critical patch, I suppose it won't introduce too much performance hit as the traverse. I would drop this optimization and keep the original code.

Quoted 39 lines

- Arnaldo

Quoted 36 lines
tools/perf/arch/x86/util/topdown.c +10 -1
+	if (!pmu || !pmu->is_core)
+		return false;
+
+	if (perf_pmu__for_each_event(pmu, false, &config,
+				     compare_topdown_event))
+		return true;
+
+	return false;
+}
 
 /*
  * Check whether a topdown group supports sample-read.
@@ -44,7 +90,7 @@ bool arch_topdown_sample_read(struct evsel *leader)
 	if (!evsel__sys_has_perf_metrics(leader))
 		return false;
 
-	if (leader->core.attr.config == TOPDOWN_SLOTS)
+	if (arch_is_topdown_slots(leader))
 		return true;
 
 	return false;
tools/perf/arch/x86/util/topdown.h +2 -0
index 46bf9273e572..1bae9b1822d7 100644
@@ -3,5 +3,7 @@
 #define _TOPDOWN_H 1
 
 bool topdown_sys_has_perf_metrics(void);
+bool arch_is_topdown_slots(const struct evsel *evsel);
+bool arch_is_topdown_metrics(const struct evsel *evsel);
 
 #endif
Signature · 1 line
2.40.1
author
#5 lore raw

PATCH v3 2/5 perf x86/topdown: Correct leader selection with sample_read enabled

In reply to Dapeng Mi

Addresses an issue where, in the absence of a topdown metrics event within a sampling group, the slots event was incorrectly bypassed as the sampling leader when sample_read was enabled.

perf record -e '{slots,branches}:S' -c 10000 -vv sleep 1

In this case, the slots event should be sampled as leader but the branches event is sampled in fact like the verbose output shows.

perf_event_attr:

  type                             4 (cpu)
  size                             168
  config                           0x400 (slots)
  sample_type                      IP|TID|TIME|READ|CPU|IDENTIFIER
  read_format                      ID|GROUP|LOST
  disabled                         1
  sample_id_all                    1
  exclude_guest                    1

------------------------------------------------------------
sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8 = 5
------------------------------------------------------------
perf_event_attr:

  type                             0 (PERF_TYPE_HARDWARE)
  size                             168
  config                           0x4 (PERF_COUNT_HW_BRANCH_INSTRUCTIONS)
  { sample_period, sample_freq }   10000
  sample_type                      IP|TID|TIME|READ|CPU|IDENTIFIER
  read_format                      ID|GROUP|LOST
  sample_id_all                    1
  exclude_guest                    1

The sample period of slots event instead of branches event is reset to 0.

This fix ensures the slots event remains the leader under these conditions.

---
 tools/perf/arch/x86/util/topdown.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)
tools/perf/arch/x86/util/topdown.c +14 -2
index 49f25d67ed77..857e00cf579f 100644
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "api/fs/fs.h"
 #include "util/evsel.h"
+#include "util/evlist.h"
 #include "util/pmu.h"
 #include "util/pmus.h"
 #include "util/topdown.h"
@@ -87,11 +88,22 @@ bool arch_is_topdown_metrics(const struct evsel *evsel)
  */
 bool arch_topdown_sample_read(struct evsel *leader)
 {
+	struct evsel *evsel;
+
 	if (!evsel__sys_has_perf_metrics(leader))
 		return false;
 
-	if (arch_is_topdown_slots(leader))
-		return true;
+	if (!arch_is_topdown_slots(leader))
+		return false;
+
+	/*
+	 * If slots event as leader event but no topdown metric events
+	 * in group, slots event should still sample as leader.
+	 */
+	evlist__for_each_entry(leader->evlist, evsel) {
+		if (evsel != leader && arch_is_topdown_metrics(evsel))
+			return true;
+	}
 
 	return false;
 }
Signature · 1 line
2.40.1
#6 lore raw

Re: [Patch v3 2/5] perf x86/topdown: Correct leader selection with sample_read enabled

Quoted 5 lines · Dapeng Mi

Addresses an issue where, in the absence of a topdown metrics event within a sampling group, the slots event was incorrectly bypassed as the sampling leader when sample_read was enabled.

perf record -e '{slots,branches}:S' -c 10000 -vv sleep 1

Kan, can you please take a look at this patch and the others in this series?

Thanks,

- Arnaldo

Quoted 75 lines

In this case, the slots event should be sampled as leader but the branches event is sampled in fact like the verbose output shows.

perf_event_attr:

  type                             4 (cpu)
  size                             168
  config                           0x400 (slots)
  sample_type                      IP|TID|TIME|READ|CPU|IDENTIFIER
  read_format                      ID|GROUP|LOST
  disabled                         1
  sample_id_all                    1
  exclude_guest                    1

------------------------------------------------------------
sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8 = 5
------------------------------------------------------------
perf_event_attr:

  type                             0 (PERF_TYPE_HARDWARE)
  size                             168
  config                           0x4 (PERF_COUNT_HW_BRANCH_INSTRUCTIONS)
  { sample_period, sample_freq }   10000
  sample_type                      IP|TID|TIME|READ|CPU|IDENTIFIER
  read_format                      ID|GROUP|LOST
  sample_id_all                    1
  exclude_guest                    1

The sample period of slots event instead of branches event is reset to 0.

This fix ensures the slots event remains the leader under these conditions.

---
 tools/perf/arch/x86/util/topdown.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)
tools/perf/arch/x86/util/topdown.c +14 -2
index 49f25d67ed77..857e00cf579f 100644
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "api/fs/fs.h"
 #include "util/evsel.h"
+#include "util/evlist.h"
 #include "util/pmu.h"
 #include "util/pmus.h"
 #include "util/topdown.h"
@@ -87,11 +88,22 @@ bool arch_is_topdown_metrics(const struct evsel *evsel)
  */
 bool arch_topdown_sample_read(struct evsel *leader)
 {
+	struct evsel *evsel;
+
 	if (!evsel__sys_has_perf_metrics(leader))
 		return false;
 
-	if (arch_is_topdown_slots(leader))
-		return true;
+	if (!arch_is_topdown_slots(leader))
+		return false;
+
+	/*
+	 * If slots event as leader event but no topdown metric events
+	 * in group, slots event should still sample as leader.
+	 */
+	evlist__for_each_entry(leader->evlist, evsel) {
+		if (evsel != leader && arch_is_topdown_metrics(evsel))
+			return true;
+	}
 
 	return false;
 }
Signature · 1 line
2.40.1
#7 lore raw

Re: [Patch v3 2/5] perf x86/topdown: Correct leader selection with sample_read enabled

Quoted 9 lines · Arnaldo Carvalho de Melo
Quoted 5 lines · Dapeng Mi

Addresses an issue where, in the absence of a topdown metrics event within a sampling group, the slots event was incorrectly bypassed as the sampling leader when sample_read was enabled.

perf record -e '{slots,branches}:S' -c 10000 -vv sleep 1

Kan, can you please take a look at this patch and the others in this series?

Sure.

Thanks,
Kan

Quoted 81 lines

Thanks,

- Arnaldo

Quoted 75 lines

In this case, the slots event should be sampled as leader but the branches event is sampled in fact like the verbose output shows.

perf_event_attr:

  type                             4 (cpu)
  size                             168
  config                           0x400 (slots)
  sample_type                      IP|TID|TIME|READ|CPU|IDENTIFIER
  read_format                      ID|GROUP|LOST
  disabled                         1
  sample_id_all                    1
  exclude_guest                    1

------------------------------------------------------------
sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8 = 5
------------------------------------------------------------
perf_event_attr:

  type                             0 (PERF_TYPE_HARDWARE)
  size                             168
  config                           0x4 (PERF_COUNT_HW_BRANCH_INSTRUCTIONS)
  { sample_period, sample_freq }   10000
  sample_type                      IP|TID|TIME|READ|CPU|IDENTIFIER
  read_format                      ID|GROUP|LOST
  sample_id_all                    1
  exclude_guest                    1

The sample period of slots event instead of branches event is reset to 0.

This fix ensures the slots event remains the leader under these conditions.

---
 tools/perf/arch/x86/util/topdown.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)
tools/perf/arch/x86/util/topdown.c +14 -2
index 49f25d67ed77..857e00cf579f 100644
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "api/fs/fs.h"
 #include "util/evsel.h"
+#include "util/evlist.h"
 #include "util/pmu.h"
 #include "util/pmus.h"
 #include "util/topdown.h"
@@ -87,11 +88,22 @@ bool arch_is_topdown_metrics(const struct evsel *evsel)
  */
 bool arch_topdown_sample_read(struct evsel *leader)
 {
+	struct evsel *evsel;
+
 	if (!evsel__sys_has_perf_metrics(leader))
 		return false;
 
-	if (arch_is_topdown_slots(leader))
-		return true;
+	if (!arch_is_topdown_slots(leader))
+		return false;
+
+	/*
+	 * If slots event as leader event but no topdown metric events
+	 * in group, slots event should still sample as leader.
+	 */
+	evlist__for_each_entry(leader->evlist, evsel) {
+		if (evsel != leader && arch_is_topdown_metrics(evsel))
+			return true;
+	}
 
 	return false;
 }
Signature · 1 line
2.40.1
#8 lore raw

Re: [Patch v3 2/5] perf x86/topdown: Correct leader selection with sample_read enabled

In reply to Dapeng Mi
Quoted 63 lines · Dapeng Mi

Addresses an issue where, in the absence of a topdown metrics event within a sampling group, the slots event was incorrectly bypassed as the sampling leader when sample_read was enabled.

perf record -e '{slots,branches}:S' -c 10000 -vv sleep 1

In this case, the slots event should be sampled as leader but the branches event is sampled in fact like the verbose output shows.

perf_event_attr:

  type                             4 (cpu)
  size                             168
  config                           0x400 (slots)
  sample_type                      IP|TID|TIME|READ|CPU|IDENTIFIER
  read_format                      ID|GROUP|LOST
  disabled                         1
  sample_id_all                    1
  exclude_guest                    1

------------------------------------------------------------
sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8 = 5
------------------------------------------------------------
perf_event_attr:

  type                             0 (PERF_TYPE_HARDWARE)
  size                             168
  config                           0x4 (PERF_COUNT_HW_BRANCH_INSTRUCTIONS)
  { sample_period, sample_freq }   10000
  sample_type                      IP|TID|TIME|READ|CPU|IDENTIFIER
  read_format                      ID|GROUP|LOST
  sample_id_all                    1
  exclude_guest                    1

The sample period of slots event instead of branches event is reset to 0.

This fix ensures the slots event remains the leader under these conditions.

---
 tools/perf/arch/x86/util/topdown.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)
tools/perf/arch/x86/util/topdown.c +3 -0
index 49f25d67ed77..857e00cf579f 100644
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "api/fs/fs.h"
 #include "util/evsel.h"
+#include "util/evlist.h"
 #include "util/pmu.h"
 #include "util/pmus.h"
 #include "util/topdown.h"
@@ -87,11 +88,22 @@ bool arch_is_topdown_metrics(const struct evsel *evsel)
  */
 bool arch_topdown_sample_read(struct evsel *leader)
 {
+	struct evsel *evsel;
+
 	if (!evsel__sys_has_perf_metrics(leader))
 		return false;
 

tools/perf/arch/x86/util/topdown.c bool arch_is_topdown_metrics(const struct evsel *evsel) · line 103

Quoted 10 lines
tools/perf/arch/x86/util/topdown.c +8 -2
-	if (arch_is_topdown_slots(leader))
-		return true;
+	if (!arch_is_topdown_slots(leader))
+		return false;
+
+	/*
+	 * If slots event as leader event but no topdown metric events
+	 * in group, slots event should still sample as leader.
+	 */
+	evlist__for_each_entry(leader->evlist, evsel) {
		evsel = leader->leader;
		evlist__for_each_entry_continue(leader->evlist, evsel)
			if (evsel->leader != leader->leader)
				return false;

Maybe we should limit the check in a group, rather than the entire evlist. Something as above (not tested)?

Thanks,
Kan

Quoted 6 lines
tools/perf/arch/x86/util/topdown.c +3 -0
+		if (evsel != leader && arch_is_topdown_metrics(evsel))
+			return true;
+	}
 
 	return false;
 }
author
#9 lore raw

Re: [Patch v3 2/5] perf x86/topdown: Correct leader selection with sample_read enabled

Quoted 80 lines · Kan
Quoted 63 lines · Dapeng Mi

Addresses an issue where, in the absence of a topdown metrics event within a sampling group, the slots event was incorrectly bypassed as the sampling leader when sample_read was enabled.

perf record -e '{slots,branches}:S' -c 10000 -vv sleep 1

In this case, the slots event should be sampled as leader but the branches event is sampled in fact like the verbose output shows.

perf_event_attr:

  type                             4 (cpu)
  size                             168
  config                           0x400 (slots)
  sample_type                      IP|TID|TIME|READ|CPU|IDENTIFIER
  read_format                      ID|GROUP|LOST
  disabled                         1
  sample_id_all                    1
  exclude_guest                    1

------------------------------------------------------------
sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8 = 5
------------------------------------------------------------
perf_event_attr:

  type                             0 (PERF_TYPE_HARDWARE)
  size                             168
  config                           0x4 (PERF_COUNT_HW_BRANCH_INSTRUCTIONS)
  { sample_period, sample_freq }   10000
  sample_type                      IP|TID|TIME|READ|CPU|IDENTIFIER
  read_format                      ID|GROUP|LOST
  sample_id_all                    1
  exclude_guest                    1

The sample period of slots event instead of branches event is reset to 0.

This fix ensures the slots event remains the leader under these conditions.

---
 tools/perf/arch/x86/util/topdown.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)
tools/perf/arch/x86/util/topdown.c +3 -0
index 49f25d67ed77..857e00cf579f 100644
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "api/fs/fs.h"
 #include "util/evsel.h"
+#include "util/evlist.h"
 #include "util/pmu.h"
 #include "util/pmus.h"
 #include "util/topdown.h"
@@ -87,11 +88,22 @@ bool arch_is_topdown_metrics(const struct evsel *evsel)
  */
 bool arch_topdown_sample_read(struct evsel *leader)
 {
+	struct evsel *evsel;
+
 	if (!evsel__sys_has_perf_metrics(leader))
 		return false;
 

tools/perf/arch/x86/util/topdown.c bool arch_is_topdown_metrics(const struct evsel *evsel) · line 103

Quoted 10 lines
tools/perf/arch/x86/util/topdown.c +8 -2
-	if (arch_is_topdown_slots(leader))
-		return true;
+	if (!arch_is_topdown_slots(leader))
+		return false;
+
+	/*
+	 * If slots event as leader event but no topdown metric events
+	 * in group, slots event should still sample as leader.
+	 */
+	evlist__for_each_entry(leader->evlist, evsel) {
		evsel = leader->leader;
		evlist__for_each_entry_continue(leader->evlist, evsel)
			if (evsel->leader != leader->leader)
				return false;
Quoted 2 lines

Maybe we should limit the check in a group, rather than the entire evlist. Something as above (not tested)?

Good point. Would limit the check in the group.

Quoted 9 lines

Thanks,
Kan

Quoted 6 lines
tools/perf/arch/x86/util/topdown.c +3 -0
+		if (evsel != leader && arch_is_topdown_metrics(evsel))
+			return true;
+	}
 
 	return false;
 }
author
#10 lore raw

PATCH v3 3/5 perf x86/topdown: Don't move topdown metric events in group

In reply to Dapeng Mi

when running below perf command, we say error is reported.

perf record -e "{slots,instructions,topdown-retiring}:S" -vv -C0 sleep 1

------------------------------------------------------------
perf_event_attr:

  type                             4 (cpu)
  size                             168
  config                           0x400 (slots)
  sample_type                      IP|TID|TIME|READ|CPU|PERIOD|IDENTIFIER
  read_format                      ID|GROUP|LOST
  disabled                         1
  sample_id_all                    1
  exclude_guest                    1

------------------------------------------------------------
sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8 = 5
------------------------------------------------------------
perf_event_attr:

  type                             4 (cpu)
  size                             168
  config                           0x8000 (topdown-retiring)
  { sample_period, sample_freq }   4000
  sample_type                      IP|TID|TIME|READ|CPU|PERIOD|IDENTIFIER
  read_format                      ID|GROUP|LOST
  freq                             1
  sample_id_all                    1
  exclude_guest                    1

------------------------------------------------------------
sys_perf_event_open: pid -1 cpu 0 group_fd 5 flags 0x8 sys_perf_event_open failed, error -22

Error:
The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (topdown-retiring).

The reason of error is that the events are regrouped and topdown-retiring event is moved to closely after the slots event and topdown-retiring event needs to do the sampling, but Intel PMU driver doesn't support to sample topdown metrics events.

For topdown metrics events, it just requires to be in a group which has slots event as leader. It doesn't require topdown metrics event must be closely after slots event. Thus it's a overkill to move topdown metrics event closely after slots event in events regrouping and furtherly cause the above issue.

Thus don't move topdown metrics events forward if they are already in a group.

---
 tools/perf/arch/x86/util/evlist.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
tools/perf/arch/x86/util/evlist.c +6 -1
index 332e8907f43e..6ae044f21843 100644
@@ -85,7 +85,12 @@ int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
 		/* Followed by topdown events. */
 		if (arch_is_topdown_metrics(lhs) && !arch_is_topdown_metrics(rhs))
 			return -1;
-		if (!arch_is_topdown_metrics(lhs) && arch_is_topdown_metrics(rhs))
+		/*
+		 * Move topdown events forward only when topdown events
+		 * are not in same group with previous event.
+		 */
+		if (!arch_is_topdown_metrics(lhs) && arch_is_topdown_metrics(rhs) &&
+		    lhs->core.leader != rhs->core.leader)
 			return 1;
 	}
 
Signature · 1 line
2.40.1
#11 lore raw

Re: [Patch v3 3/5] perf x86/topdown: Don't move topdown metric events in group

Quoted 58 lines · Dapeng Mi

when running below perf command, we say error is reported.

perf record -e "{slots,instructions,topdown-retiring}:S" -vv -C0 sleep 1

------------------------------------------------------------
perf_event_attr:

  type                             4 (cpu)
  size                             168
  config                           0x400 (slots)
  sample_type                      IP|TID|TIME|READ|CPU|PERIOD|IDENTIFIER
  read_format                      ID|GROUP|LOST
  disabled                         1
  sample_id_all                    1
  exclude_guest                    1

------------------------------------------------------------
sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8 = 5
------------------------------------------------------------
perf_event_attr:

  type                             4 (cpu)
  size                             168
  config                           0x8000 (topdown-retiring)
  { sample_period, sample_freq }   4000
  sample_type                      IP|TID|TIME|READ|CPU|PERIOD|IDENTIFIER
  read_format                      ID|GROUP|LOST
  freq                             1
  sample_id_all                    1
  exclude_guest                    1

------------------------------------------------------------
sys_perf_event_open: pid -1 cpu 0 group_fd 5 flags 0x8 sys_perf_event_open failed, error -22

Error:
The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (topdown-retiring).

The reason of error is that the events are regrouped and topdown-retiring event is moved to closely after the slots event and topdown-retiring event needs to do the sampling, but Intel PMU driver doesn't support to sample topdown metrics events.

For topdown metrics events, it just requires to be in a group which has slots event as leader. It doesn't require topdown metrics event must be closely after slots event. Thus it's a overkill to move topdown metrics event closely after slots event in events regrouping and furtherly cause the above issue.

Thus don't move topdown metrics events forward if they are already in a group.

---
 tools/perf/arch/x86/util/evlist.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
tools/perf/arch/x86/util/evlist.c +0 -0
index 332e8907f43e..6ae044f21843 100644

tools/perf/arch/x86/util/evlist.c int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs) · line 91

Quoted 8 lines
tools/perf/arch/x86/util/evlist.c +4 -1
@@ -85,7 +85,12 @@ int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
 		/* Followed by topdown events. */
 		if (arch_is_topdown_metrics(lhs) && !arch_is_topdown_metrics(rhs))
 			return -1;
-		if (!arch_is_topdown_metrics(lhs) && arch_is_topdown_metrics(rhs))
+		/*
+		 * Move topdown events forward only when topdown events
+		 * are not in same group with previous event.
+		 */

Do you mean this case?

perf stat -e '{slots,branches},topdown-retiring' -C0 sleep 1
WARNING: events were regrouped to match PMUs

Performance counter stats for 'CPU(s) 0':

        22,568,316      slots
           569,904      branches
         3,805,637      topdown-retiring

But if I add one more event before topdown-retiring, it seems break again.

perf stat -e '{slots,branches},cycles,topdown-retiring' -C0 sleep 1

Performance counter stats for 'CPU(s) 0':

        25,218,108      slots
           647,598      branches
         4,345,121      cycles
   <not supported>      topdown-retiring

I'm not asking to support all the above cases. I just try to understand which cases you plan to support.

Can you please add some comments or update the document to clearly show which format is supported, which format will be automatically adjusted by the tool, and which format will be error out?

We should also need test cases for all the supported formats, not just the standard one.

Thanks,
Kan

Quoted 5 lines
tools/perf/arch/x86/util/evlist.c +2 -0
+		if (!arch_is_topdown_metrics(lhs) && arch_is_topdown_metrics(rhs) &&
+		    lhs->core.leader != rhs->core.leader)
 			return 1;
 	}
 
author
#12 lore raw

Re: [Patch v3 3/5] perf x86/topdown: Don't move topdown metric events in group

Quoted 70 lines · Kan
Quoted 58 lines · Dapeng Mi

when running below perf command, we say error is reported.

perf record -e "{slots,instructions,topdown-retiring}:S" -vv -C0 sleep 1

------------------------------------------------------------
perf_event_attr:

  type                             4 (cpu)
  size                             168
  config                           0x400 (slots)
  sample_type                      IP|TID|TIME|READ|CPU|PERIOD|IDENTIFIER
  read_format                      ID|GROUP|LOST
  disabled                         1
  sample_id_all                    1
  exclude_guest                    1

------------------------------------------------------------
sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8 = 5
------------------------------------------------------------
perf_event_attr:

  type                             4 (cpu)
  size                             168
  config                           0x8000 (topdown-retiring)
  { sample_period, sample_freq }   4000
  sample_type                      IP|TID|TIME|READ|CPU|PERIOD|IDENTIFIER
  read_format                      ID|GROUP|LOST
  freq                             1
  sample_id_all                    1
  exclude_guest                    1

------------------------------------------------------------
sys_perf_event_open: pid -1 cpu 0 group_fd 5 flags 0x8 sys_perf_event_open failed, error -22

Error:
The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (topdown-retiring).

The reason of error is that the events are regrouped and topdown-retiring event is moved to closely after the slots event and topdown-retiring event needs to do the sampling, but Intel PMU driver doesn't support to sample topdown metrics events.

For topdown metrics events, it just requires to be in a group which has slots event as leader. It doesn't require topdown metrics event must be closely after slots event. Thus it's a overkill to move topdown metrics event closely after slots event in events regrouping and furtherly cause the above issue.

Thus don't move topdown metrics events forward if they are already in a group.

---
 tools/perf/arch/x86/util/evlist.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
tools/perf/arch/x86/util/evlist.c +0 -0
index 332e8907f43e..6ae044f21843 100644

tools/perf/arch/x86/util/evlist.c int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs) · line 91

Quoted 8 lines
tools/perf/arch/x86/util/evlist.c +4 -1
@@ -85,7 +85,12 @@ int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
 		/* Followed by topdown events. */
 		if (arch_is_topdown_metrics(lhs) && !arch_is_topdown_metrics(rhs))
 			return -1;
-		if (!arch_is_topdown_metrics(lhs) && arch_is_topdown_metrics(rhs))
+		/*
+		 * Move topdown events forward only when topdown events
+		 * are not in same group with previous event.
+		 */

Do you mean this case?

Quoted 8 lines

perf stat -e '{slots,branches},topdown-retiring' -C0 sleep 1
WARNING: events were regrouped to match PMUs

Performance counter stats for 'CPU(s) 0':

        22,568,316      slots
           569,904      branches
         3,805,637      topdown-retiring

Yes, this case can be regrouped.

Quoted 11 lines

But if I add one more event before topdown-retiring, it seems break again.

perf stat -e '{slots,branches},cycles,topdown-retiring' -C0 sleep 1

Performance counter stats for 'CPU(s) 0':

        25,218,108      slots
           647,598      branches
         4,345,121      cycles
   <not supported>      topdown-retiring

Yes, this case can't be supported by original code. I ever tried to support this format, but it's not easy, it needs to fully change current sort logic.

Quoted 7 lines

I'm not asking to support all the above cases. I just try to understand which cases you plan to support.

Can you please add some comments or update the document to clearly show which format is supported, which format will be automatically adjusted by the tool, and which format will be error out?

Yeah, I would list all currently supported regrouping format. BTW, is there a document to describe the topdown metrics feaeture. If not, I would add comments here.

Quoted 3 lines

We should also need test cases for all the supported formats, not just the standard one.

Sure. thanks.

Quoted 9 lines

Thanks,
Kan

Quoted 5 lines
tools/perf/arch/x86/util/evlist.c +2 -0
+		if (!arch_is_topdown_metrics(lhs) && arch_is_topdown_metrics(rhs) &&
+		    lhs->core.leader != rhs->core.leader)
 			return 1;
 	}
 
author
#13 lore raw

PATCH v3 4/5 perf tests: Add leader sampling test in record tests

In reply to Dapeng Mi

Add leader sampling test to validate event counts are captured into record and the count value is consistent.

---
 tools/perf/tests/shell/record.sh | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)
tools/perf/tests/shell/record.sh +28 -0
index 3d1a7759a7b2..8e3e66780fed 100755
@@ -17,6 +17,7 @@ skip_test_missing_symbol ${testsym}
 
 err=0
 perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+script_output=$(mktemp /tmp/__perf_test.perf.data.XXXXX.script)
 testprog="perf test -w thloop"
 cpu_pmu_dir="/sys/bus/event_source/devices/cpu*"
 br_cntr_file="/caps/branch_counter_nr"
@@ -190,11 +191,38 @@ test_branch_counter() {
   echo "Basic branch counter test [Success]"
 }
 
+test_leader_sampling() {
+  echo "Basic leader sampling test"
+  if ! perf record -o "${perfdata}" -e "{branches,branches}:Su" perf test -w brstack 2> /dev/null
+  then
+    echo "Leader sampling [Failed record]"
+    err=1
+    return
+  fi
+  index=0
+  perf script -i "${perfdata}" > $script_output
+  while IFS= read -r line
+  do
+    # Check if the two branches counts are equal in each record
+    branches=$(echo $line | awk '{for(i=1;i<=NF;i++) if($i=="branches:") print $(i-1)}')
+    if [ $(($index%2)) -ne 0 ] && [ ${branches}x != ${prev_branches}x ]
+    then
+      echo "Leader sampling [Failed inconsistent branches count]"
+      err=1
+      return
+    fi
+    index=$(($index+1))
+    prev_branches=$branches
+  done < $script_output
+  echo "Basic leader sampling test [Success]"
+}
+
 test_per_thread
 test_register_capture
 test_system_wide
 test_workload
 test_branch_counter
+test_leader_sampling
 
 cleanup
 exit $err
Signature · 1 line
2.40.1
author
#14 lore raw

PATCH v3 5/5 perf tests: Add topdown events counting and sampling tests

In reply to Dapeng Mi

Add counting and leader sampling tests to verify topdown events including raw format can be reordered correctly.

---
 tools/perf/tests/shell/record.sh | 17 +++++++++++++++++
 tools/perf/tests/shell/stat.sh   |  6 ++++++
 2 files changed, 23 insertions(+)
tools/perf/tests/shell/record.sh +17 -0
index 8e3e66780fed..9d0c43427811 100755
@@ -217,12 +217,29 @@ test_leader_sampling() {
   echo "Basic leader sampling test [Success]"
 }
 
+test_topdown_leader_sampling() {
+  echo "Topdown leader sampling test"
+  if ! perf stat -e "{slots,topdown-retiring}" true 2> /dev/null
+  then
+    echo "Topdown leader sampling [Skipped event parsing failed]"
+    return
+  fi
+  if ! perf record -o "${perfdata}" -e "{instructions,slots,topdown-retiring}:S" true 2> /dev/null
+  then
+    echo "Topdown leader sampling [Failed topdown events not reordered correctly]"
+    err=1
+    return
+  fi
+  echo "Topdown leader sampling test [Success]"
+}
+
 test_per_thread
 test_register_capture
 test_system_wide
 test_workload
 test_branch_counter
 test_leader_sampling
+test_topdown_leader_sampling
 
 cleanup
 exit $err
tools/perf/tests/shell/stat.sh +6 -0
index 3f1e67795490..092a7a2abcf8 100755
@@ -79,6 +79,12 @@ test_topdown_groups() {
     err=1
     return
   fi
+  if perf stat -e '{instructions,r400,r8000}' true 2>&1 | grep -E -q "<not supported>"
+  then
+    echo "Topdown event group test [Failed raw format slots not reordered first]"
+    err=1
+    return
+  fi
   echo "Topdown event group test [Success]"
 }
 
Signature · 1 line
2.40.1
author
#15 lore raw
In reply to Dapeng Mi

Hi Ian,

Kindly ping, any comments here? Thanks.

Quoted 30 lines · Dapeng Mi

Changes:
v2 -> v3:
* Refine arch_is_topdown_metrics() (Kan Liang)
* Only move topdown metric events forward when they are not in the group with previous event (Ian)
* Check if topdown events is supported before test topown events leader sampling (Kan Liang)

History:
v1: https://lore.kernel.org/all/[email protected]/
v2: https://lore.kernel.org/all/[email protected]/

Dapeng Mi (5):
perf x86/topdown: Complete topdown slots/metrics events check perf x86/topdown: Correct leader selection with sample_read enabled perf x86/topdown: Don't move topdown metric events in group perf tests: Add leader sampling test in record tests perf tests: Add topdown events counting and sampling tests

 tools/perf/arch/x86/util/evlist.c  | 13 +++++--
 tools/perf/arch/x86/util/evsel.c   |  3 +-
 tools/perf/arch/x86/util/topdown.c | 62 +++++++++++++++++++++++++++++-
 tools/perf/arch/x86/util/topdown.h |  2 +
 tools/perf/tests/shell/record.sh   | 45 ++++++++++++++++++++++
 tools/perf/tests/shell/stat.sh     |  6 +++
 6 files changed, 124 insertions(+), 7 deletions(-)

base-commit: 73e931504f8e0d42978bfcda37b323dbbd1afc08