Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1354436 > unrolled thread

[RFC 0/5] ftrace perf: Fixes and speedup

Back to article view | Back to linux.kernel

Contents

  [RFC 0/5] ftrace perf: Fixes and speedup Jiri Olsa <jolsa@kernel.org> - 2016-03-09 21:50 +0100
    [PATCH 5/5] ftrace: Update dynamic ftrace calls only if necessary Jiri Olsa <jolsa@kernel.org> - 2016-03-09 21:50 +0100
    [PATCH 4/5] ftrace: Make ftrace_hash_rec_enable return update bool Jiri Olsa <jolsa@kernel.org> - 2016-03-09 21:50 +0100
      Re: [PATCH 4/5] ftrace: Make ftrace_hash_rec_enable return update  bool Namhyung Kim <namhyung@kernel.org> - 2016-03-11 15:30 +0100
        Re: [PATCH 4/5] ftrace: Make ftrace_hash_rec_enable return update  bool Jiri Olsa <jolsa@redhat.com> - 2016-03-11 19:20 +0100
          Re: [PATCH 4/5] ftrace: Make ftrace_hash_rec_enable return update  bool Namhyung Kim <namhyung@kernel.org> - 2016-03-12 09:40 +0100
            Re: [PATCH 4/5] ftrace: Make ftrace_hash_rec_enable return update  bool Steven Rostedt <rostedt@goodmis.org> - 2016-03-15 20:50 +0100

#1354436 — [RFC 0/5] ftrace perf: Fixes and speedup

hi,
sending some small perf related fixes plus one change
to speedup ftrace:function perf registration. I'm still
testing this, but any feedback would be great.

Also available in here:
  git://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf.git
  ftrace/fixes

thanks,
jirka
---
Jiri Olsa (5):
      ftrace perf: Check sample types only for sampling events
      ftrace perf: Move exclude_kernel tracepoint check to init event
      ftrace perf: Use ftrace_ops::private to store event pointer
      ftrace: Make ftrace_hash_rec_enable return update bool
      ftrace: Update dynamic ftrace calls only if necessary

 include/linux/perf_event.h      |  3 +++
 kernel/events/core.c            | 27 ++++++++++++++++++++++-----
 kernel/trace/ftrace.c           | 36 +++++++++++++++++++++---------------
 kernel/trace/trace_event_perf.c | 39 ++++++++++++++++++++++++++++++---------
 4 files changed, 76 insertions(+), 29 deletions(-)

[toc] | [next] | [standalone]

#1354437 — [PATCH 5/5] ftrace: Update dynamic ftrace calls only if necessary

Currently dynamic ftrace calls are updated any time
the ftrace_ops is un/registered. If we do  this update
only when it's needed, we save lot of time for perf
system wide ftrace function sampling/counting.

The reason is that for system wide sampling/counting,
perf creates event for each cpu in the system.

Each event then registers separate copy of ftrace_ops,
which ends up in FTRACE_UPDATE_CALLS updates. On servers
with many cpus that means serious stall (240 cpus server):

Counting:
  # time ./perf stat -e ftrace:function -a sleep 1

   Performance counter stats for 'system wide':

              370,663      ftrace:function

          1.401427505 seconds time elapsed

  real    3m51.743s
  user    0m0.023s
  sys     3m48.569s

Sampling:
  # time ./perf record -e ftrace:function -a sleep 1
  [ perf record: Woken up 0 times to write data ]
  Warning:
  Processed 141200 events and lost 5 chunks!

  [ perf record: Captured and wrote 10.703 MB perf.data (135950 samples) ]

  real    2m31.429s
  user    0m0.213s
  sys     2m29.494s

There's no reason to do the FTRACE_UPDATE_CALLS update
for each event in perf case, because all the ftrace_ops
always share the same filter, so the updated calls are
always the same.

It's required that only first ftrace_ops registration
does the FTRACE_UPDATE_CALLS update (also sometimes
the second if the first one used the trampoline), but
the rest can be only cheaply linked into the ftrace_ops
list.

Counting:
  # time ./perf stat -e ftrace:function -a sleep 1

   Performance counter stats for 'system wide':

             398,571      ftrace:function

         1.377503733 seconds time elapsed

  real    0m2.787s
  user    0m0.005s
  sys     0m1.883s

Sampling:
  # time ./perf record -e ftrace:function -a sleep 1
  [ perf record: Woken up 0 times to write data ]
  Warning:
  Processed 261730 events and lost 9 chunks!

  [ perf record: Captured and wrote 19.907 MB perf.data (256293 samples) ]

  real    1m31.948s
  user    0m0.309s
  sys     1m32.051s

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 kernel/trace/ftrace.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 123dddc660e9..48b491463549 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2650,7 +2650,6 @@ static int ftrace_startup(struct ftrace_ops *ops, int command)
 		return ret;
 
 	ftrace_start_up++;
-	command |= FTRACE_UPDATE_CALLS;
 
 	/*
 	 * Note that ftrace probes uses this to start up
@@ -2671,7 +2670,8 @@ static int ftrace_startup(struct ftrace_ops *ops, int command)
 		return ret;
 	}
 
-	ftrace_hash_rec_enable(ops, 1);
+	if (ftrace_hash_rec_enable(ops, 1))
+		command |= FTRACE_UPDATE_CALLS;
 
 	ftrace_startup_enable(command);
 
@@ -2701,11 +2701,11 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 
 	/* Disabling ipmodify never fails */
 	ftrace_hash_ipmodify_disable(ops);
-	ftrace_hash_rec_disable(ops, 1);
 
-	ops->flags &= ~FTRACE_OPS_FL_ENABLED;
+	if (ftrace_hash_rec_disable(ops, 1))
+		command |= FTRACE_UPDATE_CALLS;
 
-	command |= FTRACE_UPDATE_CALLS;
+	ops->flags &= ~FTRACE_OPS_FL_ENABLED;
 
 	if (saved_ftrace_func != ftrace_trace_function) {
 		saved_ftrace_func = ftrace_trace_function;
-- 
2.4.3

[toc] | [prev] | [next] | [standalone]

#1354439 — [PATCH 4/5] ftrace: Make ftrace_hash_rec_enable return update bool

Change __ftrace_hash_rec_update to return true in case
we need to update dynamic ftrace call records. It return
false in case no update is needed.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 kernel/trace/ftrace.c | 26 ++++++++++++++++----------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index eca592f977b2..123dddc660e9 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1610,7 +1610,7 @@ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec)
 	return  keep_regs;
 }
 
-static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
+static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
 				     int filter_hash,
 				     bool inc)
 {
@@ -1618,12 +1618,13 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 	struct ftrace_hash *other_hash;
 	struct ftrace_page *pg;
 	struct dyn_ftrace *rec;
+	bool update = false;
 	int count = 0;
 	int all = 0;
 
 	/* Only update if the ops has been registered */
 	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
-		return;
+		return false;
 
 	/*
 	 * In the filter_hash case:
@@ -1650,7 +1651,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 		 * then there's nothing to do.
 		 */
 		if (ftrace_hash_empty(hash))
-			return;
+			return false;
 	}
 
 	do_for_each_ftrace_rec(pg, rec) {
@@ -1694,7 +1695,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 		if (inc) {
 			rec->flags++;
 			if (FTRACE_WARN_ON(ftrace_rec_count(rec) == FTRACE_REF_MAX))
-				return;
+				return false;
 
 			/*
 			 * If there's only a single callback registered to a
@@ -1720,7 +1721,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 				rec->flags |= FTRACE_FL_REGS;
 		} else {
 			if (FTRACE_WARN_ON(ftrace_rec_count(rec) == 0))
-				return;
+				return false;
 			rec->flags--;
 
 			/*
@@ -1753,22 +1754,27 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 			 */
 		}
 		count++;
+
+		update |= ftrace_test_record(rec, 1) != FTRACE_UPDATE_IGNORE;
+
 		/* Shortcut, if we handled all records, we are done. */
 		if (!all && count == hash->count)
-			return;
+			return update;
 	} while_for_each_ftrace_rec();
+
+	return update;
 }
 
-static void ftrace_hash_rec_disable(struct ftrace_ops *ops,
+static bool ftrace_hash_rec_disable(struct ftrace_ops *ops,
 				    int filter_hash)
 {
-	__ftrace_hash_rec_update(ops, filter_hash, 0);
+	return __ftrace_hash_rec_update(ops, filter_hash, 0);
 }
 
-static void ftrace_hash_rec_enable(struct ftrace_ops *ops,
+static bool ftrace_hash_rec_enable(struct ftrace_ops *ops,
 				   int filter_hash)
 {
-	__ftrace_hash_rec_update(ops, filter_hash, 1);
+	return __ftrace_hash_rec_update(ops, filter_hash, 1);
 }
 
 static void ftrace_hash_rec_update_modify(struct ftrace_ops *ops,
-- 
2.4.3

[toc] | [prev] | [next] | [standalone]

#1355948 — Re: [PATCH 4/5] ftrace: Make ftrace_hash_rec_enable return update bool

On Wed, Mar 09, 2016 at 09:46:44PM +0100, Jiri Olsa wrote:
> Change __ftrace_hash_rec_update to return true in case
> we need to update dynamic ftrace call records. It return
> false in case no update is needed.
> 
> Signed-off-by: Jiri Olsa <jolsa@kernel.org>
> ---
>  kernel/trace/ftrace.c | 26 ++++++++++++++++----------
>  1 file changed, 16 insertions(+), 10 deletions(-)
> 
> diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
> index eca592f977b2..123dddc660e9 100644
> --- a/kernel/trace/ftrace.c
> +++ b/kernel/trace/ftrace.c
> @@ -1610,7 +1610,7 @@ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec)
>  	return  keep_regs;
>  }
>  
> -static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
> +static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
>  				     int filter_hash,
>  				     bool inc)
>  {
> @@ -1618,12 +1618,13 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
>  	struct ftrace_hash *other_hash;
>  	struct ftrace_page *pg;
>  	struct dyn_ftrace *rec;
> +	bool update = false;
>  	int count = 0;
>  	int all = 0;
>  
>  	/* Only update if the ops has been registered */
>  	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
> -		return;
> +		return false;
>  
>  	/*
>  	 * In the filter_hash case:
> @@ -1650,7 +1651,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
>  		 * then there's nothing to do.
>  		 */
>  		if (ftrace_hash_empty(hash))
> -			return;
> +			return false;
>  	}
>  
>  	do_for_each_ftrace_rec(pg, rec) {
> @@ -1694,7 +1695,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
>  		if (inc) {
>  			rec->flags++;
>  			if (FTRACE_WARN_ON(ftrace_rec_count(rec) == FTRACE_REF_MAX))
> -				return;
> +				return false;
>  
>  			/*
>  			 * If there's only a single callback registered to a
> @@ -1720,7 +1721,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
>  				rec->flags |= FTRACE_FL_REGS;
>  		} else {
>  			if (FTRACE_WARN_ON(ftrace_rec_count(rec) == 0))
> -				return;
> +				return false;
>  			rec->flags--;
>  
>  			/*
> @@ -1753,22 +1754,27 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
>  			 */
>  		}
>  		count++;
> +
> +		update |= ftrace_test_record(rec, 1) != FTRACE_UPDATE_IGNORE;

Shouldn't it use 'inc' instead of 1 for the second argument of
the ftrace_test_record()?

Thanks,
Namhyung


> +
>  		/* Shortcut, if we handled all records, we are done. */
>  		if (!all && count == hash->count)
> -			return;
> +			return update;
>  	} while_for_each_ftrace_rec();
> +
> +	return update;
>  }
>  
> -static void ftrace_hash_rec_disable(struct ftrace_ops *ops,
> +static bool ftrace_hash_rec_disable(struct ftrace_ops *ops,
>  				    int filter_hash)
>  {
> -	__ftrace_hash_rec_update(ops, filter_hash, 0);
> +	return __ftrace_hash_rec_update(ops, filter_hash, 0);
>  }
>  
> -static void ftrace_hash_rec_enable(struct ftrace_ops *ops,
> +static bool ftrace_hash_rec_enable(struct ftrace_ops *ops,
>  				   int filter_hash)
>  {
> -	__ftrace_hash_rec_update(ops, filter_hash, 1);
> +	return __ftrace_hash_rec_update(ops, filter_hash, 1);
>  }
>  
>  static void ftrace_hash_rec_update_modify(struct ftrace_ops *ops,
> -- 
> 2.4.3
> 

[toc] | [prev] | [next] | [standalone]

#1356116 — Re: [PATCH 4/5] ftrace: Make ftrace_hash_rec_enable return update bool

On Fri, Mar 11, 2016 at 11:28:00PM +0900, Namhyung Kim wrote:

SNIP

> > @@ -1694,7 +1695,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
> >  		if (inc) {
> >  			rec->flags++;
> >  			if (FTRACE_WARN_ON(ftrace_rec_count(rec) == FTRACE_REF_MAX))
> > -				return;
> > +				return false;
> >  
> >  			/*
> >  			 * If there's only a single callback registered to a
> > @@ -1720,7 +1721,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
> >  				rec->flags |= FTRACE_FL_REGS;
> >  		} else {
> >  			if (FTRACE_WARN_ON(ftrace_rec_count(rec) == 0))
> > -				return;
> > +				return false;
> >  			rec->flags--;
> >  
> >  			/*
> > @@ -1753,22 +1754,27 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
> >  			 */
> >  		}
> >  		count++;
> > +
> > +		update |= ftrace_test_record(rec, 1) != FTRACE_UPDATE_IGNORE;
> 
> Shouldn't it use 'inc' instead of 1 for the second argument of
> the ftrace_test_record()?

I dont think so, 1 is to update calls (FTRACE_UPDATE_CALLS)
check ftrace_modify_all_code:

        if (command & FTRACE_UPDATE_CALLS)
                ftrace_replace_code(1);
        else if (command & FTRACE_DISABLE_CALLS)
                ftrace_replace_code(0);

both ftrace_startup, ftrace_shutdown use FTRACE_UPDATE_CALLS

you'd use 0 only to disable all, check ftrace_check_record comments:

        /*
         * If we are updating calls:
         *
         *   If the record has a ref count, then we need to enable it
         *   because someone is using it.
         *
         *   Otherwise we make sure its disabled.
         *
         * If we are disabling calls, then disable all records that
         * are enabled.
         */
        if (enable && ftrace_rec_count(rec))
                flag = FTRACE_FL_ENABLED;


used by ftrace_shutdown_sysctl

thanks,
jirka

[toc] | [prev] | [next] | [standalone]

#1356378 — Re: [PATCH 4/5] ftrace: Make ftrace_hash_rec_enable return update bool

Hi Jiri,

On Fri, Mar 11, 2016 at 07:15:06PM +0100, Jiri Olsa wrote:
> On Fri, Mar 11, 2016 at 11:28:00PM +0900, Namhyung Kim wrote:
> 
> SNIP
> 
> > > @@ -1694,7 +1695,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
> > >  		if (inc) {
> > >  			rec->flags++;
> > >  			if (FTRACE_WARN_ON(ftrace_rec_count(rec) == FTRACE_REF_MAX))
> > > -				return;
> > > +				return false;
> > >  
> > >  			/*
> > >  			 * If there's only a single callback registered to a
> > > @@ -1720,7 +1721,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
> > >  				rec->flags |= FTRACE_FL_REGS;
> > >  		} else {
> > >  			if (FTRACE_WARN_ON(ftrace_rec_count(rec) == 0))
> > > -				return;
> > > +				return false;
> > >  			rec->flags--;
> > >  
> > >  			/*
> > > @@ -1753,22 +1754,27 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
> > >  			 */
> > >  		}
> > >  		count++;
> > > +
> > > +		update |= ftrace_test_record(rec, 1) != FTRACE_UPDATE_IGNORE;
> > 
> > Shouldn't it use 'inc' instead of 1 for the second argument of
> > the ftrace_test_record()?
> 
> I dont think so, 1 is to update calls (FTRACE_UPDATE_CALLS)
> check ftrace_modify_all_code:
> 
>         if (command & FTRACE_UPDATE_CALLS)
>                 ftrace_replace_code(1);
>         else if (command & FTRACE_DISABLE_CALLS)
>                 ftrace_replace_code(0);
> 
> both ftrace_startup, ftrace_shutdown use FTRACE_UPDATE_CALLS

Ah, ok.  So the second argument of the ftrace_test_record() is not
'enable' actually..  :-/

> 
> you'd use 0 only to disable all, check ftrace_check_record comments:
> 
>         /*
>          * If we are updating calls:
>          *
>          *   If the record has a ref count, then we need to enable it
>          *   because someone is using it.
>          *
>          *   Otherwise we make sure its disabled.
>          *
>          * If we are disabling calls, then disable all records that
>          * are enabled.
>          */
>         if (enable && ftrace_rec_count(rec))
>                 flag = FTRACE_FL_ENABLED;
> 
> 
> used by ftrace_shutdown_sysctl

I got it.  Thank you for the explanation!

Thanks,
Namhyung

[toc] | [prev] | [next] | [standalone]

#1358206 — Re: [PATCH 4/5] ftrace: Make ftrace_hash_rec_enable return update bool

On Sat, 12 Mar 2016 17:35:02 +0900
Namhyung Kim <namhyung@kernel.org> wrote:

> Hi Jiri,
> 
> On Fri, Mar 11, 2016 at 07:15:06PM +0100, Jiri Olsa wrote:
> > On Fri, Mar 11, 2016 at 11:28:00PM +0900, Namhyung Kim wrote:
> > 
> > SNIP
> >   
> > > > @@ -1694,7 +1695,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
> > > >  		if (inc) {
> > > >  			rec->flags++;
> > > >  			if (FTRACE_WARN_ON(ftrace_rec_count(rec) == FTRACE_REF_MAX))
> > > > -				return;
> > > > +				return false;
> > > >  
> > > >  			/*
> > > >  			 * If there's only a single callback registered to a
> > > > @@ -1720,7 +1721,7 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
> > > >  				rec->flags |= FTRACE_FL_REGS;
> > > >  		} else {
> > > >  			if (FTRACE_WARN_ON(ftrace_rec_count(rec) == 0))
> > > > -				return;
> > > > +				return false;
> > > >  			rec->flags--;
> > > >  
> > > >  			/*
> > > > @@ -1753,22 +1754,27 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
> > > >  			 */
> > > >  		}
> > > >  		count++;
> > > > +
> > > > +		update |= ftrace_test_record(rec, 1) != FTRACE_UPDATE_IGNORE;  

Yeah, this is confusing. Mind adding a comment above this:

	/* Must match FTRACE_UPDATE_CALLS in ftrace_modify_all_code() */

That way others will know why this is a '1'.

-- Steve

> > > 
> > > Shouldn't it use 'inc' instead of 1 for the second argument of
> > > the ftrace_test_record()?  
> > 
> > I dont think so, 1 is to update calls (FTRACE_UPDATE_CALLS)
> > check ftrace_modify_all_code:
> > 
> >         if (command & FTRACE_UPDATE_CALLS)
> >                 ftrace_replace_code(1);
> >         else if (command & FTRACE_DISABLE_CALLS)
> >                 ftrace_replace_code(0);
> > 
> > both ftrace_startup, ftrace_shutdown use FTRACE_UPDATE_CALLS  
> 
> Ah, ok.  So the second argument of the ftrace_test_record() is not
> 'enable' actually..  :-/
> 
> > 
> > you'd use 0 only to disable all, check ftrace_check_record comments:
> > 
> >         /*
> >          * If we are updating calls:
> >          *
> >          *   If the record has a ref count, then we need to enable it
> >          *   because someone is using it.
> >          *
> >          *   Otherwise we make sure its disabled.
> >          *
> >          * If we are disabling calls, then disable all records that
> >          * are enabled.
> >          */
> >         if (enable && ftrace_rec_count(rec))
> >                 flag = FTRACE_FL_ENABLED;
> > 
> > 
> > used by ftrace_shutdown_sysctl  
> 
> I got it.  Thank you for the explanation!
> 
> Thanks,
> Namhyung

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web