1. Patchew
  2. linux
  3. [RFC PATCH v4 0/7] fix task state report from sched tracepoint
  4. View patch

[RFC PATCH v4 4/7] sched, tracing: reorganize fields of switch event struct

Ze Gao posted 7 patches 2 years, 1 month ago
There is a newer version of this series
[RFC PATCH v4 4/7] sched, tracing: reorganize fields of switch event struct
Posted by Ze Gao 2 years, 1 month ago 
From: Ze Gao <zegao2021@gmail.com>

Report priorities in 'short' and prev_state in 'int' to save
some buffer space. And also reorder the fields so that we take
struct alignment into consideration to make the record compact.

Suggested-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Ze Gao <zegao@tencent.com>
---
 include/trace/events/sched.h | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index fbb99a61f714..7d34db20b2c6 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -187,7 +187,7 @@ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
 	     TP_ARGS(p));
 
 #ifdef CREATE_TRACE_POINTS
-static inline long __trace_sched_switch_state(bool preempt,
+static inline int __trace_sched_switch_state(bool preempt,
 					      unsigned int prev_state,
 					      struct task_struct *p)
 {
@@ -229,23 +229,23 @@ TRACE_EVENT(sched_switch,
 	TP_ARGS(preempt, prev, next, prev_state),
 
 	TP_STRUCT__entry(
-		__array(	char,	prev_comm,	TASK_COMM_LEN	)
 		__field(	pid_t,	prev_pid			)
-		__field(	int,	prev_prio			)
-		__field(	long,	prev_state			)
-		__array(	char,	next_comm,	TASK_COMM_LEN	)
 		__field(	pid_t,	next_pid			)
-		__field(	int,	next_prio			)
+		__field(	short,	prev_prio			)
+		__field(	short,	next_prio			)
+		__field(	int,	prev_state			)
+		__array(	char,	prev_comm,	TASK_COMM_LEN	)
+		__array(	char,	next_comm,	TASK_COMM_LEN	)
 	),
 
 	TP_fast_assign(
-		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
-		__entry->prev_pid	= prev->pid;
-		__entry->prev_prio	= prev->prio;
-		__entry->prev_state	= __trace_sched_switch_state(preempt, prev_state, prev);
+		__entry->prev_pid		= prev->pid;
+		__entry->next_pid		= next->pid;
+		__entry->prev_prio		= (short) prev->prio;
+		__entry->next_prio		= (short) next->prio;
+		__entry->prev_state		= __trace_sched_switch_state(preempt, prev_state, prev);
 		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
-		__entry->next_pid	= next->pid;
-		__entry->next_prio	= next->prio;
+		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
 		/* XXX SCHED_DEADLINE */
 	),
 
-- 
2.41.0
Re: [RFC PATCH v4 4/7] sched, tracing: reorganize fields of switch event struct
Posted by Steven Rostedt 2 years, 1 month ago 
On Wed,  2 Aug 2023 08:09:59 -0400
Ze Gao <zegao2021@gmail.com> wrote:

> From: Ze Gao <zegao2021@gmail.com>
> 
> Report priorities in 'short' and prev_state in 'int' to save
> some buffer space. And also reorder the fields so that we take
> struct alignment into consideration to make the record compact.
> 
> Suggested-by: Steven Rostedt (Google) <rostedt@goodmis.org>
> Signed-off-by: Ze Gao <zegao@tencent.com>
> ---
>  include/trace/events/sched.h | 24 ++++++++++++------------
>  1 file changed, 12 insertions(+), 12 deletions(-)
> 
> diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
> index fbb99a61f714..7d34db20b2c6 100644
> --- a/include/trace/events/sched.h
> +++ b/include/trace/events/sched.h
> @@ -187,7 +187,7 @@ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
>  	     TP_ARGS(p));
>  
>  #ifdef CREATE_TRACE_POINTS
> -static inline long __trace_sched_switch_state(bool preempt,
> +static inline int __trace_sched_switch_state(bool preempt,
>  					      unsigned int prev_state,
>  					      struct task_struct *p)
>  {
> @@ -229,23 +229,23 @@ TRACE_EVENT(sched_switch,
>  	TP_ARGS(preempt, prev, next, prev_state),
>  
>  	TP_STRUCT__entry(
> -		__array(	char,	prev_comm,	TASK_COMM_LEN	)
>  		__field(	pid_t,	prev_pid			)
> -		__field(	int,	prev_prio			)
> -		__field(	long,	prev_state			)
> -		__array(	char,	next_comm,	TASK_COMM_LEN	)
>  		__field(	pid_t,	next_pid			)
> -		__field(	int,	next_prio			)
> +		__field(	short,	prev_prio			)
> +		__field(	short,	next_prio			)
> +		__field(	int,	prev_state			)

I was talking with Peter on IRC and since the biggest number that
prev_state can be is TASK_REPORT_MASK which is 0x100, I think we can make
prev_state into a short as well.

-- Steve


> +		__array(	char,	prev_comm,	TASK_COMM_LEN	)
> +		__array(	char,	next_comm,	TASK_COMM_LEN	)
>  	),
>  
>  	TP_fast_assign(
> -		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
> -		__entry->prev_pid	= prev->pid;
> -		__entry->prev_prio	= prev->prio;
> -		__entry->prev_state	= __trace_sched_switch_state(preempt, prev_state, prev);
> +		__entry->prev_pid		= prev->pid;
> +		__entry->next_pid		= next->pid;
> +		__entry->prev_prio		= (short) prev->prio;
> +		__entry->next_prio		= (short) next->prio;
> +		__entry->prev_state		= __trace_sched_switch_state(preempt, prev_state, prev);
>  		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
> -		__entry->next_pid	= next->pid;
> -		__entry->next_prio	= next->prio;
> +		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
>  		/* XXX SCHED_DEADLINE */
>  	),
>
Re: [RFC PATCH v4 4/7] sched, tracing: reorganize fields of switch event struct
Posted by Ze Gao 2 years, 1 month ago 
On Wed, Aug 2, 2023 at 11:05 PM Steven Rostedt <rostedt@goodmis.org> wrote:
>
> On Wed,  2 Aug 2023 08:09:59 -0400
> Ze Gao <zegao2021@gmail.com> wrote:
>
> > From: Ze Gao <zegao2021@gmail.com>
> >
> > Report priorities in 'short' and prev_state in 'int' to save
> > some buffer space. And also reorder the fields so that we take
> > struct alignment into consideration to make the record compact.
> >
> > Suggested-by: Steven Rostedt (Google) <rostedt@goodmis.org>
> > Signed-off-by: Ze Gao <zegao@tencent.com>
> > ---
> >  include/trace/events/sched.h | 24 ++++++++++++------------
> >  1 file changed, 12 insertions(+), 12 deletions(-)
> >
> > diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
> > index fbb99a61f714..7d34db20b2c6 100644
> > --- a/include/trace/events/sched.h
> > +++ b/include/trace/events/sched.h
> > @@ -187,7 +187,7 @@ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
> >            TP_ARGS(p));
> >
> >  #ifdef CREATE_TRACE_POINTS
> > -static inline long __trace_sched_switch_state(bool preempt,
> > +static inline int __trace_sched_switch_state(bool preempt,
> >                                             unsigned int prev_state,
> >                                             struct task_struct *p)
> >  {
> > @@ -229,23 +229,23 @@ TRACE_EVENT(sched_switch,
> >       TP_ARGS(preempt, prev, next, prev_state),
> >
> >       TP_STRUCT__entry(
> > -             __array(        char,   prev_comm,      TASK_COMM_LEN   )
> >               __field(        pid_t,  prev_pid                        )
> > -             __field(        int,    prev_prio                       )
> > -             __field(        long,   prev_state                      )
> > -             __array(        char,   next_comm,      TASK_COMM_LEN   )
> >               __field(        pid_t,  next_pid                        )
> > -             __field(        int,    next_prio                       )
> > +             __field(        short,  prev_prio                       )
> > +             __field(        short,  next_prio                       )
> > +             __field(        int,    prev_state                      )
>
> I was talking with Peter on IRC and since the biggest number that
> prev_state can be is TASK_REPORT_MASK which is 0x100, I think we can make
> prev_state into a short as well.

Make sense, let's change it to short.

Regards,
Ze

Patchew 2.1-devel-b67e4c2

© 2016 - 2025 Red Hat, Inc.