Skip to contentSkip to conversation

perf: Allow suppressing useless AUX records

PATCH In review Alexander Shishkin 6 participants 15 messages Nov 14, 2017 – Sep 25, 2018 perf events

lore
Share & tools
lore

Alexander Shishkin

author reviewer
#0 lore raw

cover perf: Allow suppressing useless AUX records

Hi guys,

[Fixed the braindamage of the previous version as pointed out by Adrian]

It's been brought to my attention many times that the AUX records are not always useful. One instance is the AUX overwrite mode, where we generate one such record every time the target task schedules out.

This patchset adds a bit to the attribute structure that would enable suppressing the AUX records when the only the only set flag is OVERWRITE. In this case, at least for the PT and BTS data we just ignore these records. But at the same time, AUX overwrite events are likely to be kept running over longer periods of time, making the buildup of AUX records an unnecessary annoyance.

Alexander Shishkin (4):
perf: Allow suppressing AUX records
tools, perf_event.h: Synchronize
perf tools: Add 'suppress_aux' attribute bit definition and fallback perf intel-pt, intel-bts: Suppress useless AUX records by default

 include/uapi/linux/perf_event.h       |  3 ++-
 kernel/events/core.c                  |  5 +++++
 kernel/events/ring_buffer.c           | 12 ++++++++++--
 tools/include/uapi/linux/perf_event.h |  3 ++-
 tools/perf/arch/x86/util/auxtrace.c   |  2 ++
 tools/perf/util/evsel.c               |  9 +++++++++
 6 files changed, 30 insertions(+), 4 deletions(-)
Signature · 1 line
2.15.0
author reviewer
#1 lore raw

PATCH 1/4 perf: Allow suppressing AUX records

It has been pointed out to me many times that it is useful to be able to switch off AUX records to save the bandwidth for records that actually matter, for example, in AUX overwrite mode.

The usefulness of PERF_RECORD_AUX is in some of its flags, like the TRUNCATED flag that tells the decoder where exactly gaps in the trace are. The OVERWRITE flag, on the other hand will be set on every single record in overwrite mode. However, a PERF_RECORD_AUX[flags=OVERWRITE] is generated on every target task's sched_out, which over time adds up to a lot of useless information.

This patch adds an attribute bit that enables suppressing such records.

Cc Markus Metzger <[email protected]>
Cc Adrian Hunter <[email protected]>
---
 include/uapi/linux/perf_event.h |  3 ++-
 kernel/events/core.c            |  5 +++++
 kernel/events/ring_buffer.c     | 12 ++++++++++--
 3 files changed, 17 insertions(+), 3 deletions(-)
include/uapi/linux/perf_event.h +2 -1
index 362493a2f950..fa3821d9dc52 100644
@@ -370,7 +370,8 @@ struct perf_event_attr {
 				context_switch :  1, /* context switch data */
 				write_backward :  1, /* Write ring buffer from end to beginning */
 				namespaces     :  1, /* include namespaces data */
-				__reserved_1   : 35;
+				suppress_aux   :  1, /* don't generate PERF_RECORD_AUX */
+				__reserved_1   : 34;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
kernel/events/core.c +5 -0
index 81dd57b9e5e3..483122c73936 100644
@@ -10014,6 +10014,11 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_context;
 	}
 
+	if (attr.suppress_aux && !pmu->setup_aux) {
+		err = -EINVAL;
+		goto err_context;
+	}
+
 	/*
 	 * Look up the group leader (we will attach this event to it):
 	 */
kernel/events/ring_buffer.c +10 -2
index f684d8e5fa2b..ecd8da78d387 100644
@@ -425,6 +425,12 @@ static bool __always_inline rb_need_aux_wakeup(struct ring_buffer *rb)
 	return false;
 }
 
+/*
+ * These flags won't generate a PERF_RECORD_AUX on their own if
+ * attr::suppress_aux is set.
+ */
+#define SUPPRESSABLE_FLAGS	PERF_AUX_FLAG_OVERWRITE
+
 /*
  * Commit the data written by hardware into the ring buffer by adjusting
  * aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the
@@ -459,8 +465,10 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 		 * Only send RECORD_AUX if we have something useful to communicate
 		 */
 
-		perf_event_aux_event(handle->event, aux_head, size,
-		                     handle->aux_flags);
+		if (!handle->event->attr.suppress_aux ||
+		    (handle->aux_flags & ~(u64)SUPPRESSABLE_FLAGS))
+			perf_event_aux_event(handle->event, aux_head, size,
+					     handle->aux_flags);
 	}
 
 	rb->user_page->aux_head = rb->aux_head;
Signature · 1 line
2.15.0
maintainer
#2 lore raw

Re: [PATCH v1 1/4] perf: Allow suppressing AUX records

Quoted 4 lines · Alexander Shishkin

It has been pointed out to me many times that it is useful to be able to switch off AUX records to save the bandwidth for records that actually matter, for example, in AUX overwrite mode.

Quoted 8 lines

The usefulness of PERF_RECORD_AUX is in some of its flags, like the TRUNCATED flag that tells the decoder where exactly gaps in the trace are. The OVERWRITE flag, on the other hand will be set on every single record in overwrite mode. However, a PERF_RECORD_AUX[flags=OVERWRITE] is generated on every target task's sched_out, which over time adds up to a lot of useless information.

This patch adds an attribute bit that enables suppressing such records.

What this fails to explain is why a separate suppression flag makes sense. Why not suppress the thing on overwrite mode and be done with it?

kernel/events/ring_buffer.c void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) · line 471

Quoted 4 lines
kernel/events/ring_buffer.c +4 -0
+		if (!handle->event->attr.suppress_aux ||
+		    (handle->aux_flags & ~(u64)SUPPRESSABLE_FLAGS))
+			perf_event_aux_event(handle->event, aux_head, size,
+					     handle->aux_flags);

That wants { }

author reviewer
#3 lore raw

PATCH 1/1 perf: Allow suppressing AUX records

It has been pointed out to me many times that it is useful to be able to switch off AUX records to save the bandwidth for records that actually matter, for example, in AUX overwrite mode.

The usefulness of PERF_RECORD_AUX is in some of its flags, like the TRUNCATED flag that tells the decoder where exactly gaps in the trace are. The OVERWRITE flag, on the other hand will be set on every single record in overwrite mode. However, a PERF_RECORD_AUX[flags=OVERWRITE] is generated on every target task's sched_out, which over time adds up to a lot of useless information.

In case the existing userspace depends on AUX records in the overwrite mode, we preserve the original behavior and add an opt-in for the new behavior, wherein the 'useless' records get suppressed.

This patch adds an attribute bit to the described effect.

Cc Markus Metzger <[email protected]>
Cc Adrian Hunter <[email protected]>
---
 include/uapi/linux/perf_event.h |  3 ++-
 kernel/events/core.c            |  5 +++++
 kernel/events/ring_buffer.c     | 13 +++++++++++--
 3 files changed, 18 insertions(+), 3 deletions(-)
include/uapi/linux/perf_event.h +2 -1
index c77c9a2ebbbb..d7a981130561 100644
@@ -370,7 +370,8 @@ struct perf_event_attr {
 				context_switch :  1, /* context switch data */
 				write_backward :  1, /* Write ring buffer from end to beginning */
 				namespaces     :  1, /* include namespaces data */
-				__reserved_1   : 35;
+				suppress_aux   :  1, /* don't generate PERF_RECORD_AUX */
+				__reserved_1   : 34;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
kernel/events/core.c +5 -0
index 4e1a1bf8d867..6245a88c2bda 100644
@@ -10012,6 +10012,11 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_context;
 	}
 
+	if (attr.suppress_aux && !pmu->setup_aux) {
+		err = -EINVAL;
+		goto err_context;
+	}
+
 	/*
 	 * Look up the group leader (we will attach this event to it):
 	 */
kernel/events/ring_buffer.c +11 -2
index 141aa2ca8728..381f080e6409 100644
@@ -426,6 +426,12 @@ static bool __always_inline rb_need_aux_wakeup(struct ring_buffer *rb)
 	return false;
 }
 
+/*
+ * These flags won't generate a PERF_RECORD_AUX on their own if
+ * attr::suppress_aux is set.
+ */
+#define SUPPRESSABLE_FLAGS	PERF_AUX_FLAG_OVERWRITE
+
 /*
  * Commit the data written by hardware into the ring buffer by adjusting
  * aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the
@@ -460,8 +466,11 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 		 * Only send RECORD_AUX if we have something useful to communicate
 		 */
 
-		perf_event_aux_event(handle->event, aux_head, size,
-		                     handle->aux_flags);
+		if (!handle->event->attr.suppress_aux ||
+		    (handle->aux_flags & ~(u64)SUPPRESSABLE_FLAGS)) {
+			perf_event_aux_event(handle->event, aux_head, size,
+					     handle->aux_flags);
+		}
 	}
 
 	rb->user_page->aux_head = rb->aux_head;
Signature · 1 line
2.15.1
maintainer
#4 lore raw

Re: [PATCH] perf: Allow suppressing AUX records

Quoted 31 lines · Alexander Shishkin

It has been pointed out to me many times that it is useful to be able to switch off AUX records to save the bandwidth for records that actually matter, for example, in AUX overwrite mode.

The usefulness of PERF_RECORD_AUX is in some of its flags, like the TRUNCATED flag that tells the decoder where exactly gaps in the trace are. The OVERWRITE flag, on the other hand will be set on every single record in overwrite mode. However, a PERF_RECORD_AUX[flags=OVERWRITE] is generated on every target task's sched_out, which over time adds up to a lot of useless information.

In case the existing userspace depends on AUX records in the overwrite mode, we preserve the original behavior and add an opt-in for the new behavior, wherein the 'useless' records get suppressed.

This patch adds an attribute bit to the described effect.

Cc Markus Metzger <[email protected]>
Cc Adrian Hunter <[email protected]>
---
 include/uapi/linux/perf_event.h |  3 ++-
 kernel/events/core.c            |  5 +++++
 kernel/events/ring_buffer.c     | 13 +++++++++++--
 3 files changed, 18 insertions(+), 3 deletions(-)
include/uapi/linux/perf_event.h +0 -0
index c77c9a2ebbbb..d7a981130561 100644

include/uapi/linux/perf_event.h struct perf_event_attr { · line 377

Quoted 9 lines
include/uapi/linux/perf_event.h +2 -1
@@ -370,7 +370,8 @@ struct perf_event_attr {
 				context_switch :  1, /* context switch data */
 				write_backward :  1, /* Write ring buffer from end to beginning */
 				namespaces     :  1, /* include namespaces data */
-				__reserved_1   : 35;
+				suppress_aux   :  1, /* don't generate PERF_RECORD_AUX */
+				__reserved_1   : 34;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */

So I'm basically fine with this patch, however I wonder if we really need this suppress flag and can't just unconditionally drop these events.

Ash said that as far as he knows no Intel-PT user actually relies on it; Will is there anything ARM that is known to rely on them?

In anycase, tentative ACK on this, unless we wants to be brave and forgo this flag.

Ingo, any opinions?

Quoted 50 lines
kernel/events/core.c +5 -0
index 4e1a1bf8d867..6245a88c2bda 100644
@@ -10012,6 +10012,11 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_context;
 	}
 
+	if (attr.suppress_aux && !pmu->setup_aux) {
+		err = -EINVAL;
+		goto err_context;
+	}
+
 	/*
 	 * Look up the group leader (we will attach this event to it):
 	 */
kernel/events/ring_buffer.c +11 -2
index 141aa2ca8728..381f080e6409 100644
@@ -426,6 +426,12 @@ static bool __always_inline rb_need_aux_wakeup(struct ring_buffer *rb)
 	return false;
 }
 
+/*
+ * These flags won't generate a PERF_RECORD_AUX on their own if
+ * attr::suppress_aux is set.
+ */
+#define SUPPRESSABLE_FLAGS	PERF_AUX_FLAG_OVERWRITE
+
 /*
  * Commit the data written by hardware into the ring buffer by adjusting
  * aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the
@@ -460,8 +466,11 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 		 * Only send RECORD_AUX if we have something useful to communicate
 		 */
 
-		perf_event_aux_event(handle->event, aux_head, size,
-		                     handle->aux_flags);
+		if (!handle->event->attr.suppress_aux ||
+		    (handle->aux_flags & ~(u64)SUPPRESSABLE_FLAGS)) {
+			perf_event_aux_event(handle->event, aux_head, size,
+					     handle->aux_flags);
+		}
 	}
 
 	rb->user_page->aux_head = rb->aux_head;
Signature · 1 line
2.15.1
#5 lore raw

Re: [PATCH] perf: Allow suppressing AUX records

Quoted 46 lines · Peter Zijlstra
Quoted 31 lines · Alexander Shishkin

It has been pointed out to me many times that it is useful to be able to switch off AUX records to save the bandwidth for records that actually matter, for example, in AUX overwrite mode.

The usefulness of PERF_RECORD_AUX is in some of its flags, like the TRUNCATED flag that tells the decoder where exactly gaps in the trace are. The OVERWRITE flag, on the other hand will be set on every single record in overwrite mode. However, a PERF_RECORD_AUX[flags=OVERWRITE] is generated on every target task's sched_out, which over time adds up to a lot of useless information.

In case the existing userspace depends on AUX records in the overwrite mode, we preserve the original behavior and add an opt-in for the new behavior, wherein the 'useless' records get suppressed.

This patch adds an attribute bit to the described effect.

Cc Markus Metzger <[email protected]>
Cc Adrian Hunter <[email protected]>
---
 include/uapi/linux/perf_event.h |  3 ++-
 kernel/events/core.c            |  5 +++++
 kernel/events/ring_buffer.c     | 13 +++++++++++--
 3 files changed, 18 insertions(+), 3 deletions(-)
include/uapi/linux/perf_event.h +0 -0
index c77c9a2ebbbb..d7a981130561 100644

include/uapi/linux/perf_event.h struct perf_event_attr { · line 377

Quoted 9 lines
include/uapi/linux/perf_event.h +2 -1
@@ -370,7 +370,8 @@ struct perf_event_attr {
 				context_switch :  1, /* context switch data */
 				write_backward :  1, /* Write ring buffer from end to beginning */
 				namespaces     :  1, /* include namespaces data */
-				__reserved_1   : 35;
+				suppress_aux   :  1, /* don't generate PERF_RECORD_AUX */
+				__reserved_1   : 34;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */

So I'm basically fine with this patch, however I wonder if we really need this suppress flag and can't just unconditionally drop these events.

Quoted 7 lines

Ash said that as far as he knows no Intel-PT user actually relies on it; Will is there anything ARM that is known to rely on them?

In anycase, tentative ACK on this, unless we wants to be brave and forgo this flag.

Ingo, any opinions?

Yeah, I'd suggest we just supress those record, and wait for complaints - let's not complicate the ABI if not necessary?

Thanks,

Ingo

#6 lore raw

Re: [PATCH] perf: Allow suppressing AUX records

Quoted 24 lines · Ingo Molnar
Quoted 23 lines · Peter Zijlstra
Quoted 5 lines · Alexander Shishkin
include/uapi/linux/perf_event.h +0 -0
index c77c9a2ebbbb..d7a981130561 100644

include/uapi/linux/perf_event.h struct perf_event_attr { · line 377

Quoted 9 lines
include/uapi/linux/perf_event.h +2 -1
@@ -370,7 +370,8 @@ struct perf_event_attr {
 				context_switch :  1, /* context switch data */
 				write_backward :  1, /* Write ring buffer from end to beginning */
 				namespaces     :  1, /* include namespaces data */
-				__reserved_1   : 35;
+				suppress_aux   :  1, /* don't generate PERF_RECORD_AUX */
+				__reserved_1   : 34;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */

So I'm basically fine with this patch, however I wonder if we really need this suppress flag and can't just unconditionally drop these events.

Ash said that as far as he knows no Intel-PT user actually relies on it; Will is there anything ARM that is known to rely on them?

Quoted 7 lines
Quoted 4 lines

In anycase, tentative ACK on this, unless we wants to be brave and forgo this flag.

Ingo, any opinions?

Yeah, I'd suggest we just supress those record, and wait for complaints - let's not complicate the ABI if not necessary?

Works for me. We've not had SPE support in mainline perf for very long and the availability of hardware is extremely limited at the moment, so I don't anticipate any ABI implications on the arm64 side.

Cheers,

Will

author reviewer
#7 lore raw

PATCH v2 1/1 perf: Suppress AUX/OVERWRITE records

It has been pointed out to me many times that it is useful to be able to switch off AUX records to save the bandwidth for records that actually matter, for example, in AUX overwrite mode.

The usefulness of PERF_RECORD_AUX is in some of its flags, like the TRUNCATED flag that tells the decoder where exactly gaps in the trace are. The OVERWRITE flag, on the other hand will be set on every single record in overwrite mode. However, a PERF_RECORD_AUX[flags=OVERWRITE] is generated on every target task's sched_out, which over time adds up to a lot of useless information.

If any folks out there have userspace that depends on a constant stream of OVERWRITE records for a good reason, they'll have to let us know.

Cc Markus Metzger <[email protected]>
Cc Adrian Hunter <[email protected]>
---
 kernel/events/ring_buffer.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)
kernel/events/ring_buffer.c +12 -2
index 6c6b3c48db71..c4edd8fbc5d9 100644
@@ -458,10 +458,20 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 	if (size || handle->aux_flags) {
 		/*
 		 * Only send RECORD_AUX if we have something useful to communicate
+		 *
+		 * Note: the OVERWRITE records by themselves are not considered
+		 * useful, as they don't communicate any *new* information,
+		 * aside from the short-lived offset, that becomes history at
+		 * the next event sched-in and therefore isn't useful.
+		 * The userspace that needs to copy out AUX data in overwrite
+		 * mode should know to use user_page::aux_head for the actual
+		 * offset. So, from now on we don't output AUX records that
+		 * have *only* OVERWRITE flag set.
 		 */
 
-		perf_event_aux_event(handle->event, aux_head, size,
-		                     handle->aux_flags);
+		if (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE)
+			perf_event_aux_event(handle->event, aux_head, size,
+			                     handle->aux_flags);
 	}
 
 	rb->user_page->aux_head = rb->aux_head;
Signature · 1 line
2.16.3
author reviewer
#8 lore raw

Re: [PATCH v2] perf: Suppress AUX/OVERWRITE records

Quoted 11 lines · Alexander Shishkin

It has been pointed out to me many times that it is useful to be able to switch off AUX records to save the bandwidth for records that actually matter, for example, in AUX overwrite mode.

The usefulness of PERF_RECORD_AUX is in some of its flags, like the TRUNCATED flag that tells the decoder where exactly gaps in the trace are. The OVERWRITE flag, on the other hand will be set on every single record in overwrite mode. However, a PERF_RECORD_AUX[flags=OVERWRITE] is generated on every target task's sched_out, which over time adds up to a lot of useless information.

Quoted 6 lines

If any folks out there have userspace that depends on a constant stream of OVERWRITE records for a good reason, they'll have to let us know.

Cc Markus Metzger <[email protected]>
Cc Adrian Hunter <[email protected]>

This one seems to be slipping through the cracks.

Cheers,
--
Alex

#9 lore raw

Re: [PATCH v2] perf: Suppress AUX/OVERWRITE records

Em Fri, May 04, 2018 at 03:09:59PM +0300, Alexander Shishkin escreveu:

Quoted 12 lines · Alexander Shishkin
Quoted 11 lines

It has been pointed out to me many times that it is useful to be able to switch off AUX records to save the bandwidth for records that actually matter, for example, in AUX overwrite mode.

The usefulness of PERF_RECORD_AUX is in some of its flags, like the TRUNCATED flag that tells the decoder where exactly gaps in the trace are. The OVERWRITE flag, on the other hand will be set on every single record in overwrite mode. However, a PERF_RECORD_AUX[flags=OVERWRITE] is generated on every target task's sched_out, which over time adds up to a lot of useless information.

Quoted 8 lines
Quoted 6 lines

If any folks out there have userspace that depends on a constant stream of OVERWRITE records for a good reason, they'll have to let us know.

Cc Markus Metzger <[email protected]>
Cc Adrian Hunter <[email protected]>

This one seems to be slipping through the cracks.

So, did you got Acked-by or tested-by from anyone?

- Arnaldo

#10 lore raw

Re: [PATCH v2] perf: Suppress AUX/OVERWRITE records

Em Fri, May 04, 2018 at 12:35:34PM -0300, Arnaldo Carvalho de Melo escreveu:

Quoted 16 lines

Em Fri, May 04, 2018 at 03:09:59PM +0300, Alexander Shishkin escreveu:

Quoted 15 lines · Alexander Shishkin
Quoted 14 lines

It has been pointed out to me many times that it is useful to be able to switch off AUX records to save the bandwidth for records that actually matter, for example, in AUX overwrite mode.

The usefulness of PERF_RECORD_AUX is in some of its flags, like the TRUNCATED flag that tells the decoder where exactly gaps in the trace are. The OVERWRITE flag, on the other hand will be set on every single record in overwrite mode. However, a PERF_RECORD_AUX[flags=OVERWRITE] is generated on every target task's sched_out, which over time adds up to a lot of useless information.

If any folks out there have userspace that depends on a constant stream of OVERWRITE records for a good reason, they'll have to let us know.

Quoted 7 lines
Quoted 5 lines
Quoted 3 lines
Cc Markus Metzger <[email protected]>
Cc Adrian Hunter <[email protected]>

This one seems to be slipping through the cracks.

So, did you got Acked-by or tested-by from anyone?

Yeah, tons of them, I'll pick this up

- Arnaldo

#11 lore raw

[tip:perf/core] perf: Suppress AUX/OVERWRITE records

In reply to Alexander Shishkin
perf: Suppress AUX/OVERWRITE records
Commit-ID:  1627314fb54a33ebd23bd08f2e215eaed0f44712
Gitweb:     https://git.kernel.org/tip/1627314fb54a33ebd23bd08f2e215eaed0f44712
Author:     Alexander Shishkin <[email protected]>
AuthorDate: Wed, 4 Apr 2018 17:53:23 +0300
Committer:  Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Tue, 18 Sep 2018 17:21:13 -0300

perf: Suppress AUX/OVERWRITE records

It has been pointed out to me many times that it is useful to be able to switch off AUX records to save the bandwidth for records that actually matter, for example, in AUX overwrite mode.

The usefulness of PERF_RECORD_AUX is in some of its flags, like the TRUNCATED flag that tells the decoder where exactly gaps in the trace are. The OVERWRITE flag, on the other hand will be set on every single record in overwrite mode. However, a PERF_RECORD_AUX[flags=OVERWRITE] is generated on every target task's sched_out, which over time adds up to a lot of useless information.

If any folks out there have userspace that depends on a constant stream of OVERWRITE records for a good reason, they'll have to let us know.

---
 kernel/events/ring_buffer.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)
kernel/events/ring_buffer.c +12 -2
index 5d3cf407e374..4a9937076331 100644
@@ -459,10 +459,20 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 	if (size || handle->aux_flags) {
 		/*
 		 * Only send RECORD_AUX if we have something useful to communicate
+		 *
+		 * Note: the OVERWRITE records by themselves are not considered
+		 * useful, as they don't communicate any *new* information,
+		 * aside from the short-lived offset, that becomes history at
+		 * the next event sched-in and therefore isn't useful.
+		 * The userspace that needs to copy out AUX data in overwrite
+		 * mode should know to use user_page::aux_head for the actual
+		 * offset. So, from now on we don't output AUX records that
+		 * have *only* OVERWRITE flag set.
 		 */
 
-		perf_event_aux_event(handle->event, aux_head, size,
-		                     handle->aux_flags);
+		if (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE)
+			perf_event_aux_event(handle->event, aux_head, size,
+			                     handle->aux_flags);
 	}
 
 	rb->user_page->aux_head = rb->aux_head;
author reviewer
#12 lore raw

PATCH 2/4 tools, perf_event.h: Synchronize

In reply to Alexander Shishkin

I've just added attr::suppress_aux bit to the kernel header, adding it to the tools' header too.

---
 tools/include/uapi/linux/perf_event.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
tools/include/uapi/linux/perf_event.h +2 -1
index 362493a2f950..fa3821d9dc52 100644
@@ -370,7 +370,8 @@ struct perf_event_attr {
 				context_switch :  1, /* context switch data */
 				write_backward :  1, /* Write ring buffer from end to beginning */
 				namespaces     :  1, /* include namespaces data */
-				__reserved_1   : 35;
+				suppress_aux   :  1, /* don't generate PERF_RECORD_AUX */
+				__reserved_1   : 34;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
Signature · 1 line
2.15.0
author reviewer
#13 lore raw

PATCH 3/4 perf tools: Add 'suppress_aux' attribute bit definition and fallback

In reply to Alexander Shishkin

This adds support for suppress_aux, the switch that enables suppressing not-so-useful PERF_RECORD_AUX records. Also handle kernels where it's not supported.

---
 tools/perf/util/evsel.c | 9 +++++++++
 1 file changed, 9 insertions(+)
tools/perf/util/evsel.c +9 -0
index f894893c203d..794e56b42c20 100644
@@ -50,6 +50,7 @@ static struct {
 	bool lbr_flags;
 	bool write_backward;
 	bool group_read;
+	bool suppress_aux;
 } perf_missing_features;
 
 static clockid_t clockid;
@@ -1570,6 +1571,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(use_clockid, p_unsigned);
 	PRINT_ATTRf(context_switch, p_unsigned);
 	PRINT_ATTRf(write_backward, p_unsigned);
+	PRINT_ATTRf(suppress_aux, p_unsigned);
 
 	PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
 	PRINT_ATTRf(bp_type, p_unsigned);
@@ -1686,6 +1688,8 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 				     PERF_SAMPLE_BRANCH_NO_CYCLES);
 	if (perf_missing_features.group_read && evsel->attr.inherit)
 		evsel->attr.read_format &= ~(PERF_FORMAT_GROUP|PERF_FORMAT_ID);
+	if (perf_missing_features.suppress_aux && evsel->attr.suppress_aux)
+		evsel->attr.suppress_aux = 0;
 retry_sample_id:
 	if (perf_missing_features.sample_id_all)
 		evsel->attr.sample_id_all = 0;
@@ -1847,6 +1851,11 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 		perf_missing_features.group_read = true;
 		pr_debug2("switching off group read\n");
 		goto fallback_missing_features;
+	} else if (!perf_missing_features.suppress_aux &&
+		   evsel->attr.suppress_aux) {
+		perf_missing_features.suppress_aux = true;
+		pr_debug2("switching off suppress_aux\n");
+		goto fallback_missing_features;
 	}
 out_close:
 	do {
Signature · 1 line
2.15.0
author reviewer
#14 lore raw

PATCH 4/4 perf intel-pt, intel-bts: Suppress useless AUX records by default

In reply to Alexander Shishkin

This makes use of the shiny new attr::suppress_aux that suppresses the AUX records that don't carry any 'interesting' information for the decoders, that is PERF_RECORD_AUX[flag==OVERWRITE], which just stack up in the DATA buffer for no good reason.

---
 tools/perf/arch/x86/util/auxtrace.c | 2 ++
 1 file changed, 2 insertions(+)
tools/perf/arch/x86/util/auxtrace.c +2 -0
index 6aa3f2a38321..5700e6099608 100644
@@ -45,6 +45,8 @@ struct auxtrace_record *auxtrace_record__init_intel(struct perf_evlist *evlist,
 			if (intel_bts_pmu &&
 			    evsel->attr.type == intel_bts_pmu->type)
 				found_bts = true;
+			if (found_pt || found_bts)
+				evsel->attr.suppress_aux = 1;
 		}
 	}
 
Signature · 1 line
2.15.0