[PATCH 1/4] perf tools: callchain: Warn only once in empty node detection

[PATCH 1/4] perf tools: callchain: Warn only once in empty node detection

[Frederic Weisbecker]

When we fill a new node that is found to be empty (sign of a bug),
we print a message each time that happens. Sometimes we reach thousands
of lines printed.

Just warn only once in that case (and use stderr instead of stdout).

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
---
 tools/perf/util/callchain.c |    3 ++-
 tools/perf/util/util.h      |    3 +++
 tools/perf/util/wrapper.c   |   16 ++++++++++++++++
 3 files changed, 21 insertions(+), 1 deletions(-)

diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 98c5627..ce0c6d4 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -13,6 +13,7 @@
 #include <stdio.h>
 #include <stdbool.h>
 #include <errno.h>
+#include "util.h"
 
 #include "callchain.h"
 
@@ -203,7 +204,7 @@ fill_node(struct callchain_node *node, struct ip_callchain *chain,
 	}
 	node->val_nr = chain->nr - start;
 	if (!node->val_nr)
-		printf("Warning: empty node in callchain tree\n");
+		fprintf_once(stderr, "Warning: empty node in callchain tree\n");
 }
 
 static void
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 68fe157..386ea40 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -148,6 +148,9 @@ static inline const char *skip_prefix(const char *str, const char *prefix)
 	return strncmp(str, prefix, len) ? NULL : str + len;
 }
 
+extern int fprintf_once(FILE *fp, const char *fmt, ...)
+	__attribute__((format (printf, 2, 3)));
+
 #if defined(NO_MMAP) || defined(USE_WIN32_MMAP)
 
 #ifndef PROT_READ
diff --git a/tools/perf/util/wrapper.c b/tools/perf/util/wrapper.c
index 4574ac2..026c87c 100644
--- a/tools/perf/util/wrapper.c
+++ b/tools/perf/util/wrapper.c
@@ -205,3 +205,19 @@ int xmkstemp(char *template)
 		die("Unable to create temporary file: %s", strerror(errno));
 	return fd;
 }
+
+int fprintf_once(FILE *fp, const char *fmt, ...)
+{
+	va_list args;
+	int ret;
+	static int once;
+
+	if (once++)
+		return 1;
+
+	va_start(args, fmt);
+	ret = vfprintf(fp, fmt, args);
+	va_end(args);
+
+	return ret;
+}
-- 
1.6.2.3

[PATCH 2/4] perf tools: callchain: Ignore empty callchains

[Frederic Weisbecker]

When the callchain tree comes to insert an empty backtrace, it raises
a spurious warning about the fact we are inserting an empty.
This is spurious because the radix tree assumes it did something
wrong to reach this state. But it didn't, we just met an empty
callchain that has to be ignored.

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
---
 tools/perf/util/callchain.c |    2 ++
 1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index ce0c6d4..4c09b25 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -337,5 +337,7 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain,
 void append_chain(struct callchain_node *root, struct ip_callchain *chain,
 		  struct symbol **syms)
 {
+	if (!chain->nr)
+		return;
 	__append_chain_children(root, chain, syms, 0);
 }
-- 
1.6.2.3

[PATCH 3/4] perf tools: callchain: Default display callchain from report if recorded with -g

[Frederic Weisbecker]

If we recorded with -g option to record the callchain, let's display
the callchain by default from perf report.

The user can override this default using "-g none" option from
perf report.

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
---
 tools/perf/builtin-report.c |   16 +++++++++++++++-
 tools/perf/util/callchain.h |    1 +
 2 files changed, 16 insertions(+), 1 deletions(-)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index a5e2f8d..c4a8e10 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -68,7 +68,7 @@ static int		callchain;
 
 static
 struct callchain_param	callchain_param = {
-	.mode	= CHAIN_GRAPH_ABS,
+	.mode	= CHAIN_GRAPH_REL,
 	.min_percent = 0.5
 };
 
@@ -1836,6 +1836,13 @@ static int __cmd_report(void)
 					" -g?\n");
 			exit(-1);
 		}
+	} else if (callchain_param.mode != CHAIN_NONE && !callchain) {
+			callchain = 1;
+			if (register_callchain_param(&callchain_param) < 0) {
+				fprintf(stderr, "Can't register callchain"
+						" params\n");
+				exit(-1);
+			}
 	}
 
 	if (load_kernel() < 0) {
@@ -1974,6 +1981,13 @@ parse_callchain_opt(const struct option *opt __used, const char *arg,
 	else if (!strncmp(tok, "fractal", strlen(arg)))
 		callchain_param.mode = CHAIN_GRAPH_REL;
 
+	else if (!strncmp(tok, "none", strlen(arg))) {
+		callchain_param.mode = CHAIN_NONE;
+		callchain = 0;
+
+		return 0;
+	}
+
 	else
 		return -1;
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index b2d128e..a926ae4 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -7,6 +7,7 @@
 #include "symbol.h"
 
 enum chain_mode {
+	CHAIN_NONE,
 	CHAIN_FLAT,
 	CHAIN_GRAPH_ABS,
 	CHAIN_GRAPH_REL
-- 
1.6.2.3

[PATCH 4/4] perf tools: callchain: Display amount of ignored chains in fractal mode

[Frederic Weisbecker]

When we filter the callchains below a given percentage, we ignore them
and the end result only shows entries that have an upper percentage
than the filter threshold. It seems then that we have an imbalance in
the percentage, as if the sum inside a profiled branch doesn't reach
100%.

Fix this by displaying the remaining hits that have been filtered but
without more detail than their amount in each branches.
Example while filtering below 50%:

7.73%  [k] delay_tsc
                |
                |--98.22%-- __const_udelay
                |          |
                |          |--86.37%-- ath5k_hw_register_timeout
                |          |          ath5k_hw_noise_floor_calibration
                |          |          ath5k_hw_reset
                |          |          ath5k_reset
                |          |          ath5k_config
                |          |          ieee80211_hw_config
                |          |          |
                |          |          |--88.53%-- ieee80211_scan_work
                |          |          |          worker_thread
                |          |          |          kthread
                |          |          |          child_rip
                |          |           --11.47%-- [...]
                |           --13.63%-- [...]
                 --1.78%-- [...]

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
---
 tools/perf/builtin-report.c |   47 ++++++++++++++++++++++++++++++++++++++++--
 1 files changed, 44 insertions(+), 3 deletions(-)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index c4a8e10..99274ce 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -891,6 +891,21 @@ ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, int depth,
 	return ret;
 }
 
+static struct symbol *rem_sq_bracket;
+static struct callchain_list rem_hits;
+
+static void init_rem_hits(void)
+{
+	rem_sq_bracket = malloc(sizeof(*rem_sq_bracket) + 6);
+	if (!rem_sq_bracket) {
+		fprintf(stderr, "Not enough memory to display remaining hits\n");
+		return;
+	}
+
+	strcpy(rem_sq_bracket->name, "[...]");
+	rem_hits.sym = rem_sq_bracket;
+}
+
 static size_t
 callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 			u64 total_samples, int depth, int depth_mask)
@@ -900,6 +915,7 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 	struct callchain_list *chain;
 	int new_depth_mask = depth_mask;
 	u64 new_total;
+	u64 remaining;
 	size_t ret = 0;
 	int i;
 
@@ -908,17 +924,25 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 	else
 		new_total = total_samples;
 
+	remaining = new_total;
+
 	node = rb_first(&self->rb_root);
 	while (node) {
+		u64 cumul;
+
 		child = rb_entry(node, struct callchain_node, rb_node);
+		cumul = cumul_hits(child);
+		remaining -= cumul;
 
 		/*
 		 * The depth mask manages the output of pipes that show
 		 * the depth. We don't want to keep the pipes of the current
-		 * level for the last child of this depth
+		 * level for the last child of this depth.
+		 * Except if we have remaining filtered hits. They will
+		 * supersede the last child
 		 */
 		next = rb_next(node);
-		if (!next)
+		if (!next && (callchain_param.mode != CHAIN_GRAPH_REL || !remaining))
 			new_depth_mask &= ~(1 << (depth - 1));
 
 		/*
@@ -933,7 +957,7 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 			ret += ipchain__fprintf_graph(fp, chain, depth,
 						      new_depth_mask, i++,
 						      new_total,
-						      cumul_hits(child));
+						      cumul);
 		}
 		ret += callchain__fprintf_graph(fp, child, new_total,
 						depth + 1,
@@ -941,6 +965,19 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 		node = next;
 	}
 
+	if (callchain_param.mode == CHAIN_GRAPH_REL &&
+		remaining && remaining != new_total) {
+
+		if (!rem_sq_bracket)
+			return ret;
+
+		new_depth_mask &= ~(1 << (depth - 1));
+
+		ret += ipchain__fprintf_graph(fp, &rem_hits, depth,
+					      new_depth_mask, 0, new_total,
+					      remaining);
+	}
+
 	return ret;
 }
 
@@ -1361,6 +1398,8 @@ static size_t output__fprintf(FILE *fp, u64 total_samples)
 	unsigned int width;
 	char *col_width = col_width_list_str;
 
+	init_rem_hits();
+
 	fprintf(fp, "# Samples: %Ld\n", (u64)total_samples);
 	fprintf(fp, "#\n");
 
@@ -1432,6 +1471,8 @@ print_entries:
 	}
 	fprintf(fp, "\n");
 
+	free(rem_sq_bracket);
+
 	return ret;
 }
 
-- 
1.6.2.3

Re: [PATCH 1/4] perf tools: callchain: Warn only once in empty node detection

[Arnaldo Carvalho de Melo]

Em Sat, Aug 08, 2009 at 02:16:22AM +0200, Frederic Weisbecker escreveu:
> When we fill a new node that is found to be empty (sign of a bug),
> we print a message each time that happens. Sometimes we reach thousands
> of lines printed.
> 
> Just warn only once in that case (and use stderr instead of stdout).

Wouldn't this be better done with a macro so that the every message is
print once instead of any fprintf_once message?

I think it would even be nice to just use the same thing the kernel
uses... WARN_ON_ONCE, and also using asm/bug.h, etc, just add it to
tools/perf/util/include/asm, etc.

That way one can even forget that this is not kernel programming... :-)

- Arnaldo
 
> Reported-by: Ingo Molnar <mingo@elte.hu>
> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
> Cc: Mike Galbraith <efault@gmx.de>
> ---
>  tools/perf/util/callchain.c |    3 ++-
>  tools/perf/util/util.h      |    3 +++
>  tools/perf/util/wrapper.c   |   16 ++++++++++++++++
>  3 files changed, 21 insertions(+), 1 deletions(-)
> 
> diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
> index 98c5627..ce0c6d4 100644
> --- a/tools/perf/util/callchain.c
> +++ b/tools/perf/util/callchain.c
> @@ -13,6 +13,7 @@
>  #include <stdio.h>
>  #include <stdbool.h>
>  #include <errno.h>
> +#include "util.h"
>  
>  #include "callchain.h"
>  
> @@ -203,7 +204,7 @@ fill_node(struct callchain_node *node, struct ip_callchain *chain,
>  	}
>  	node->val_nr = chain->nr - start;
>  	if (!node->val_nr)
> -		printf("Warning: empty node in callchain tree\n");
> +		fprintf_once(stderr, "Warning: empty node in callchain tree\n");
>  }
>  
>  static void
> diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
> index 68fe157..386ea40 100644
> --- a/tools/perf/util/util.h
> +++ b/tools/perf/util/util.h
> @@ -148,6 +148,9 @@ static inline const char *skip_prefix(const char *str, const char *prefix)
>  	return strncmp(str, prefix, len) ? NULL : str + len;
>  }
>  
> +extern int fprintf_once(FILE *fp, const char *fmt, ...)
> +	__attribute__((format (printf, 2, 3)));
> +
>  #if defined(NO_MMAP) || defined(USE_WIN32_MMAP)
>  
>  #ifndef PROT_READ
> diff --git a/tools/perf/util/wrapper.c b/tools/perf/util/wrapper.c
> index 4574ac2..026c87c 100644
> --- a/tools/perf/util/wrapper.c
> +++ b/tools/perf/util/wrapper.c
> @@ -205,3 +205,19 @@ int xmkstemp(char *template)
>  		die("Unable to create temporary file: %s", strerror(errno));
>  	return fd;
>  }
> +
> +int fprintf_once(FILE *fp, const char *fmt, ...)
> +{
> +	va_list args;
> +	int ret;
> +	static int once;
> +
> +	if (once++)
> +		return 1;
> +
> +	va_start(args, fmt);
> +	ret = vfprintf(fp, fmt, args);
> +	va_end(args);
> +
> +	return ret;
> +}
> -- 
> 1.6.2.3

Re: [PATCH 1/4] perf tools: callchain: Warn only once in empty node detection

[Frederic Weisbecker]

On Fri, Aug 07, 2009 at 10:06:48PM -0300, Arnaldo Carvalho de Melo wrote:
> Em Sat, Aug 08, 2009 at 02:16:22AM +0200, Frederic Weisbecker escreveu:
> > When we fill a new node that is found to be empty (sign of a bug),
> > we print a message each time that happens. Sometimes we reach thousands
> > of lines printed.
> > 
> > Just warn only once in that case (and use stderr instead of stdout).
> 
> Wouldn't this be better done with a macro so that the every message is
> print once instead of any fprintf_once message?



Doh! You're right...
/me slaps his face.


 
> I think it would even be nice to just use the same thing the kernel
> uses... WARN_ON_ONCE, and also using asm/bug.h, etc, just add it to
> tools/perf/util/include/asm, etc.
> 


Ok, I'll try that.



> That way one can even forget that this is not kernel programming... :-)

Hehe :)


> - Arnaldo
>  
> > Reported-by: Ingo Molnar <mingo@elte.hu>
> > Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
> > Cc: Peter Zijlstra <peterz@infradead.org>
> > Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
> > Cc: Mike Galbraith <efault@gmx.de>
> > ---
> >  tools/perf/util/callchain.c |    3 ++-
> >  tools/perf/util/util.h      |    3 +++
> >  tools/perf/util/wrapper.c   |   16 ++++++++++++++++
> >  3 files changed, 21 insertions(+), 1 deletions(-)
> > 
> > diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
> > index 98c5627..ce0c6d4 100644
> > --- a/tools/perf/util/callchain.c
> > +++ b/tools/perf/util/callchain.c
> > @@ -13,6 +13,7 @@
> >  #include <stdio.h>
> >  #include <stdbool.h>
> >  #include <errno.h>
> > +#include "util.h"
> >  
> >  #include "callchain.h"
> >  
> > @@ -203,7 +204,7 @@ fill_node(struct callchain_node *node, struct ip_callchain *chain,
> >  	}
> >  	node->val_nr = chain->nr - start;
> >  	if (!node->val_nr)
> > -		printf("Warning: empty node in callchain tree\n");
> > +		fprintf_once(stderr, "Warning: empty node in callchain tree\n");
> >  }
> >  
> >  static void
> > diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
> > index 68fe157..386ea40 100644
> > --- a/tools/perf/util/util.h
> > +++ b/tools/perf/util/util.h
> > @@ -148,6 +148,9 @@ static inline const char *skip_prefix(const char *str, const char *prefix)
> >  	return strncmp(str, prefix, len) ? NULL : str + len;
> >  }
> >  
> > +extern int fprintf_once(FILE *fp, const char *fmt, ...)
> > +	__attribute__((format (printf, 2, 3)));
> > +
> >  #if defined(NO_MMAP) || defined(USE_WIN32_MMAP)
> >  
> >  #ifndef PROT_READ
> > diff --git a/tools/perf/util/wrapper.c b/tools/perf/util/wrapper.c
> > index 4574ac2..026c87c 100644
> > --- a/tools/perf/util/wrapper.c
> > +++ b/tools/perf/util/wrapper.c
> > @@ -205,3 +205,19 @@ int xmkstemp(char *template)
> >  		die("Unable to create temporary file: %s", strerror(errno));
> >  	return fd;
> >  }
> > +
> > +int fprintf_once(FILE *fp, const char *fmt, ...)
> > +{
> > +	va_list args;
> > +	int ret;
> > +	static int once;
> > +
> > +	if (once++)
> > +		return 1;
> > +
> > +	va_start(args, fmt);
> > +	ret = vfprintf(fp, fmt, args);
> > +	va_end(args);
> > +
> > +	return ret;
> > +}
> > -- 
> > 1.6.2.3

[tip:perfcounters/core] perf tools: callchain: Fix spurious 'perf report' warnings: ignore empty callchains

[tip-bot for Frederic Weisbecker]

Commit-ID:  d6bda845b99fbdfa2f88ac9f82d757297783b5d5
Gitweb:     http://git.kernel.org/tip/d6bda845b99fbdfa2f88ac9f82d757297783b5d5
Author:     Frederic Weisbecker <fweisbec@gmail.com>
AuthorDate: Sat, 8 Aug 2009 02:16:23 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Sat, 8 Aug 2009 13:49:21 +0200

perf tools: callchain: Fix spurious 'perf report' warnings: ignore empty callchains

When the callchain tree comes to insert an empty backtrace, it
raises a spurious warning about the fact we are inserting an
empty. This is spurious because the radix tree assumes it did
something wrong to reach this state. But it didn't, we just met
an empty callchain that has to be ignored.

This happens occasionally with certain types of call-chain
recordings. If it happens it's a big nuisance as perf report
output starts with thousands of warning lines.

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
LKML-Reference: <1249690585-9145-2-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 tools/perf/util/callchain.c |    2 ++
 1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 98c5627..a8e67aa 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -336,5 +336,7 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain,
 void append_chain(struct callchain_node *root, struct ip_callchain *chain,
 		  struct symbol **syms)
 {
+	if (!chain->nr)
+		return;
 	__append_chain_children(root, chain, syms, 0);
 }

[tip:perfcounters/core] perf tools: callchain: Fix 'perf report' display to be callchain by default

[tip-bot for Frederic Weisbecker]

Commit-ID:  0b51a97cec68a953629cc388d762c61b2c05886e
Gitweb:     http://git.kernel.org/tip/0b51a97cec68a953629cc388d762c61b2c05886e
Author:     Frederic Weisbecker <fweisbec@gmail.com>
AuthorDate: Sat, 8 Aug 2009 02:16:24 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Sat, 8 Aug 2009 13:49:21 +0200

perf tools: callchain: Fix 'perf report' display to be callchain by default

If we recorded with -g option to record the callchain, right now
we require a -g option to perf report as well - and people reported
this as unnecessary complication: the user already specified -g
once, no need to require it a second time.

So if the recording includes call-chains, display the callchain by
default from perf report.

( The user can override this default using "-g none" option from
  perf report. )

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
LKML-Reference: <1249690585-9145-3-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 tools/perf/builtin-report.c |   16 +++++++++++++++-
 tools/perf/util/callchain.h |    1 +
 2 files changed, 16 insertions(+), 1 deletions(-)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index a5e2f8d..c4a8e10 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -68,7 +68,7 @@ static int		callchain;
 
 static
 struct callchain_param	callchain_param = {
-	.mode	= CHAIN_GRAPH_ABS,
+	.mode	= CHAIN_GRAPH_REL,
 	.min_percent = 0.5
 };
 
@@ -1836,6 +1836,13 @@ static int __cmd_report(void)
 					" -g?\n");
 			exit(-1);
 		}
+	} else if (callchain_param.mode != CHAIN_NONE && !callchain) {
+			callchain = 1;
+			if (register_callchain_param(&callchain_param) < 0) {
+				fprintf(stderr, "Can't register callchain"
+						" params\n");
+				exit(-1);
+			}
 	}
 
 	if (load_kernel() < 0) {
@@ -1974,6 +1981,13 @@ parse_callchain_opt(const struct option *opt __used, const char *arg,
 	else if (!strncmp(tok, "fractal", strlen(arg)))
 		callchain_param.mode = CHAIN_GRAPH_REL;
 
+	else if (!strncmp(tok, "none", strlen(arg))) {
+		callchain_param.mode = CHAIN_NONE;
+		callchain = 0;
+
+		return 0;
+	}
+
 	else
 		return -1;
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index b2d128e..a926ae4 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -7,6 +7,7 @@
 #include "symbol.h"
 
 enum chain_mode {
+	CHAIN_NONE,
 	CHAIN_FLAT,
 	CHAIN_GRAPH_ABS,
 	CHAIN_GRAPH_REL

[tip:perfcounters/core] perf tools: callchain: Fix sum of percentages to be 100% by displaying amount of ignored chains in fractal mode

[tip-bot for Frederic Weisbecker]

Commit-ID:  84fce09c6b21ef675de079a724c13a205c89520b
Gitweb:     http://git.kernel.org/tip/84fce09c6b21ef675de079a724c13a205c89520b
Author:     Frederic Weisbecker <fweisbec@gmail.com>
AuthorDate: Sat, 8 Aug 2009 02:16:25 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Sat, 8 Aug 2009 13:49:21 +0200

perf tools: callchain: Fix sum of percentages to be 100% by displaying amount of ignored chains in fractal mode

When we filter the callchains below a given percentage, we
ignore them and the end result only shows entries that have an
upper percentage than the filter threshold.

It seems to users then that we have an imbalance in the
percentage, as if the sum inside a profiled branch doesn't
reach 100%.

Since in the past there have been real perf report bugs that
showed the same sypmtom, it would be nice to assure the user
that the data is perfect and trustable and it all sums up to
100.00%.

So fix this by displaying the remaining hits that have been
filtered but without more detail than their amount in each
branches. Example while filtering below 50%:

7.73%  [k] delay_tsc
                |
                |--98.22%-- __const_udelay
                |          |
                |          |--86.37%-- ath5k_hw_register_timeout
                |          |          ath5k_hw_noise_floor_calibration
                |          |          ath5k_hw_reset
                |          |          ath5k_reset
                |          |          ath5k_config
                |          |          ieee80211_hw_config
                |          |          |
                |          |          |--88.53%-- ieee80211_scan_work
                |          |          |          worker_thread
                |          |          |          kthread
                |          |          |          child_rip
                |          |           --11.47%-- [...]
                |           --13.63%-- [...]
                 --1.78%-- [...]

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
LKML-Reference: <1249690585-9145-4-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 tools/perf/builtin-report.c |   47 ++++++++++++++++++++++++++++++++++++++++--
 1 files changed, 44 insertions(+), 3 deletions(-)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index c4a8e10..99274ce 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -891,6 +891,21 @@ ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, int depth,
 	return ret;
 }
 
+static struct symbol *rem_sq_bracket;
+static struct callchain_list rem_hits;
+
+static void init_rem_hits(void)
+{
+	rem_sq_bracket = malloc(sizeof(*rem_sq_bracket) + 6);
+	if (!rem_sq_bracket) {
+		fprintf(stderr, "Not enough memory to display remaining hits\n");
+		return;
+	}
+
+	strcpy(rem_sq_bracket->name, "[...]");
+	rem_hits.sym = rem_sq_bracket;
+}
+
 static size_t
 callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 			u64 total_samples, int depth, int depth_mask)
@@ -900,6 +915,7 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 	struct callchain_list *chain;
 	int new_depth_mask = depth_mask;
 	u64 new_total;
+	u64 remaining;
 	size_t ret = 0;
 	int i;
 
@@ -908,17 +924,25 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 	else
 		new_total = total_samples;
 
+	remaining = new_total;
+
 	node = rb_first(&self->rb_root);
 	while (node) {
+		u64 cumul;
+
 		child = rb_entry(node, struct callchain_node, rb_node);
+		cumul = cumul_hits(child);
+		remaining -= cumul;
 
 		/*
 		 * The depth mask manages the output of pipes that show
 		 * the depth. We don't want to keep the pipes of the current
-		 * level for the last child of this depth
+		 * level for the last child of this depth.
+		 * Except if we have remaining filtered hits. They will
+		 * supersede the last child
 		 */
 		next = rb_next(node);
-		if (!next)
+		if (!next && (callchain_param.mode != CHAIN_GRAPH_REL || !remaining))
 			new_depth_mask &= ~(1 << (depth - 1));
 
 		/*
@@ -933,7 +957,7 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 			ret += ipchain__fprintf_graph(fp, chain, depth,
 						      new_depth_mask, i++,
 						      new_total,
-						      cumul_hits(child));
+						      cumul);
 		}
 		ret += callchain__fprintf_graph(fp, child, new_total,
 						depth + 1,
@@ -941,6 +965,19 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 		node = next;
 	}
 
+	if (callchain_param.mode == CHAIN_GRAPH_REL &&
+		remaining && remaining != new_total) {
+
+		if (!rem_sq_bracket)
+			return ret;
+
+		new_depth_mask &= ~(1 << (depth - 1));
+
+		ret += ipchain__fprintf_graph(fp, &rem_hits, depth,
+					      new_depth_mask, 0, new_total,
+					      remaining);
+	}
+
 	return ret;
 }
 
@@ -1361,6 +1398,8 @@ static size_t output__fprintf(FILE *fp, u64 total_samples)
 	unsigned int width;
 	char *col_width = col_width_list_str;
 
+	init_rem_hits();
+
 	fprintf(fp, "# Samples: %Ld\n", (u64)total_samples);
 	fprintf(fp, "#\n");
 
@@ -1432,6 +1471,8 @@ print_entries:
 	}
 	fprintf(fp, "\n");
 
+	free(rem_sq_bracket);
+
 	return ret;
 }
 

Re: [tip:perfcounters/core] perf tools: callchain: Fix sum of percentages to be 100% by displaying amount of ignored chains in fractal mode

[Ingo Molnar]

* tip-bot for Frederic Weisbecker <fweisbec@gmail.com> wrote:

> Commit-ID:  84fce09c6b21ef675de079a724c13a205c89520b
> Gitweb:     http://git.kernel.org/tip/84fce09c6b21ef675de079a724c13a205c89520b
> Author:     Frederic Weisbecker <fweisbec@gmail.com>
> AuthorDate: Sat, 8 Aug 2009 02:16:25 +0200
> Committer:  Ingo Molnar <mingo@elte.hu>
> CommitDate: Sat, 8 Aug 2009 13:49:21 +0200
> 
> perf tools: callchain: Fix sum of percentages to be 100% by displaying amount of ignored chains in fractal mode
> 
> When we filter the callchains below a given percentage, we
> ignore them and the end result only shows entries that have an
> upper percentage than the filter threshold.
> 
> It seems to users then that we have an imbalance in the
> percentage, as if the sum inside a profiled branch doesn't
> reach 100%.
> 
> Since in the past there have been real perf report bugs that
> showed the same sypmtom, it would be nice to assure the user
> that the data is perfect and trustable and it all sums up to
> 100.00%.
> 
> So fix this by displaying the remaining hits that have been
> filtered but without more detail than their amount in each
> branches. Example while filtering below 50%:
> 
> 7.73%  [k] delay_tsc
>                 |
>                 |--98.22%-- __const_udelay
>                 |          |
>                 |          |--86.37%-- ath5k_hw_register_timeout
>                 |          |          ath5k_hw_noise_floor_calibration
>                 |          |          ath5k_hw_reset
>                 |          |          ath5k_reset
>                 |          |          ath5k_config
>                 |          |          ieee80211_hw_config
>                 |          |          |
>                 |          |          |--88.53%-- ieee80211_scan_work
>                 |          |          |          worker_thread
>                 |          |          |          kthread
>                 |          |          |          child_rip
>                 |          |           --11.47%-- [...]
>                 |           --13.63%-- [...]
>                  --1.78%-- [...]

i dont seem to be able to get the bracketed numbers. I only get:

  titan:~> perf record -f -g -a ./hackbench 10
  titan:~> perf report -g fractal,10.0

# Samples: 26832
#
# Overhead         Command             Shared Object  Symbol
# ........  ..............  ........................  ......
#
     8.69%       hackbench  [kernel]                  [k] copy_user_generic_string

     6.84%       hackbench  [kernel]                  [k] unix_stream_recvmsg

     6.07%       hackbench  [kernel]                  [k] sock_alloc_send_pskb

     4.33%       hackbench  [kernel]                  [k] _spin_lock

     3.77%       hackbench  [kernel]                  [k] __kmalloc_node_track_caller

     3.74%       hackbench  [kernel]                  [k] __alloc_skb
                |          
                |--80.00%-- sock_alloc_send_pskb
                |          sock_alloc_send_skb
                |          unix_stream_sendmsg
                |          __sock_sendmsg
                |          sock_aio_write
                |          do_sync_write
                |          vfs_write
                |          sys_write
                |          sysenter_dispatch
                |          0xf7ffa430
                |          0xffadeb0000000014
                |          
                 --20.00%-- sock_alloc_send_skb
                           unix_stream_sendmsg
                           __sock_sendmsg
                           sock_aio_write
                           do_sync_write
                           vfs_write
                           sys_write
                           sysenter_dispatch
                           0xf7ffa430
                           0xffadeb0000000014

     3.53%       hackbench  [kernel]                  [k] ia32_sysenter_target

     2.92%       hackbench  [vdso]                    [.] 0x000000f7ffa430
                |          
                |--66.67%-- 0xf7ffa430
                |          0xffadeb0000000014
                |          
                 --33.33%-- 0xf7ffa431
                           0xffadeb0000000014

     2.56%       hackbench  [kernel]                  [k] virt_to_head_page

     2.37%       hackbench  [kernel]                  [k] kmem_cache_alloc_node

     2.33%       hackbench  [kernel]                  [k] _spin_lock_irqsave
                |          
                |--78.57%-- remove_wait_queue
                |          poll_freewait
                |          do_sys_poll
                |          sys_poll
                |          sysenter_dispatch
                |          0xf7ffa430
                |          0x1ffadea3c
                |          
                |--7.14%-- __up_read
                |          up_read
                |          do_page_fault
                |          page_fault
                |          0xf7ffa430
                |          0xa0df710000000a
                |          
                |--7.14%-- unix_stream_sendmsg
                |          __sock_sendmsg
                |          sock_aio_write
                |          do_sync_write
                |          vfs_write
                |          sys_write
                |          sysenter_dispatch
                |          0xf7ffa430
                |          0xffadeb0000000014
                |          
                 --7.14%-- skb_queue_tail
                           unix_stream_sendmsg
                           __sock_sendmsg
                           sock_aio_write
                           do_sync_write
                           vfs_write
                           sys_write
                           sysenter_dispatch
                           0xf7ffa430
                           0xffadeb0000000014


I dont see the brackets anymore, nor does the 10% limit seem to have 
been listened to for the 7.14% result above, right?

	Ingo

Re: [tip:perfcounters/core] perf tools: callchain: Fix sum of percentages to be 100% by displaying amount of ignored chains in fractal mode

[Frederic Weisbecker]

On Sat, Aug 08, 2009 at 02:29:23PM +0200, Ingo Molnar wrote:
> 
> * tip-bot for Frederic Weisbecker <fweisbec@gmail.com> wrote:
> 
> > Commit-ID:  84fce09c6b21ef675de079a724c13a205c89520b
> > Gitweb:     http://git.kernel.org/tip/84fce09c6b21ef675de079a724c13a205c89520b
> > Author:     Frederic Weisbecker <fweisbec@gmail.com>
> > AuthorDate: Sat, 8 Aug 2009 02:16:25 +0200
> > Committer:  Ingo Molnar <mingo@elte.hu>
> > CommitDate: Sat, 8 Aug 2009 13:49:21 +0200
> > 
> > perf tools: callchain: Fix sum of percentages to be 100% by displaying amount of ignored chains in fractal mode
> > 
> > When we filter the callchains below a given percentage, we
> > ignore them and the end result only shows entries that have an
> > upper percentage than the filter threshold.
> > 
> > It seems to users then that we have an imbalance in the
> > percentage, as if the sum inside a profiled branch doesn't
> > reach 100%.
> > 
> > Since in the past there have been real perf report bugs that
> > showed the same sypmtom, it would be nice to assure the user
> > that the data is perfect and trustable and it all sums up to
> > 100.00%.
> > 
> > So fix this by displaying the remaining hits that have been
> > filtered but without more detail than their amount in each
> > branches. Example while filtering below 50%:
> > 
> > 7.73%  [k] delay_tsc
> >                 |
> >                 |--98.22%-- __const_udelay
> >                 |          |
> >                 |          |--86.37%-- ath5k_hw_register_timeout
> >                 |          |          ath5k_hw_noise_floor_calibration
> >                 |          |          ath5k_hw_reset
> >                 |          |          ath5k_reset
> >                 |          |          ath5k_config
> >                 |          |          ieee80211_hw_config
> >                 |          |          |
> >                 |          |          |--88.53%-- ieee80211_scan_work
> >                 |          |          |          worker_thread
> >                 |          |          |          kthread
> >                 |          |          |          child_rip
> >                 |          |           --11.47%-- [...]
> >                 |           --13.63%-- [...]
> >                  --1.78%-- [...]
> 
> i dont seem to be able to get the bracketed numbers. I only get:
> 
>   titan:~> perf record -f -g -a ./hackbench 10
>   titan:~> perf report -g fractal,10.0
> 
> # Samples: 26832
> #
> # Overhead         Command             Shared Object  Symbol
> # ........  ..............  ........................  ......
> #
>      8.69%       hackbench  [kernel]                  [k] copy_user_generic_string
> 
>      6.84%       hackbench  [kernel]                  [k] unix_stream_recvmsg
> 
>      6.07%       hackbench  [kernel]                  [k] sock_alloc_send_pskb
> 
>      4.33%       hackbench  [kernel]                  [k] _spin_lock
> 
>      3.77%       hackbench  [kernel]                  [k] __kmalloc_node_track_caller
> 
>      3.74%       hackbench  [kernel]                  [k] __alloc_skb
>                 |          
>                 |--80.00%-- sock_alloc_send_pskb
>                 |          sock_alloc_send_skb
>                 |          unix_stream_sendmsg
>                 |          __sock_sendmsg
>                 |          sock_aio_write
>                 |          do_sync_write
>                 |          vfs_write
>                 |          sys_write
>                 |          sysenter_dispatch
>                 |          0xf7ffa430
>                 |          0xffadeb0000000014
>                 |          
>                  --20.00%-- sock_alloc_send_skb
>                            unix_stream_sendmsg
>                            __sock_sendmsg
>                            sock_aio_write
>                            do_sync_write
>                            vfs_write
>                            sys_write
>                            sysenter_dispatch
>                            0xf7ffa430
>                            0xffadeb0000000014
> 
>      3.53%       hackbench  [kernel]                  [k] ia32_sysenter_target
> 
>      2.92%       hackbench  [vdso]                    [.] 0x000000f7ffa430
>                 |          
>                 |--66.67%-- 0xf7ffa430
>                 |          0xffadeb0000000014
>                 |          
>                  --33.33%-- 0xf7ffa431
>                            0xffadeb0000000014
> 
>      2.56%       hackbench  [kernel]                  [k] virt_to_head_page
> 
>      2.37%       hackbench  [kernel]                  [k] kmem_cache_alloc_node
> 
>      2.33%       hackbench  [kernel]                  [k] _spin_lock_irqsave
>                 |          
>                 |--78.57%-- remove_wait_queue
>                 |          poll_freewait
>                 |          do_sys_poll
>                 |          sys_poll
>                 |          sysenter_dispatch
>                 |          0xf7ffa430
>                 |          0x1ffadea3c
>                 |          
>                 |--7.14%-- __up_read
>                 |          up_read
>                 |          do_page_fault
>                 |          page_fault
>                 |          0xf7ffa430
>                 |          0xa0df710000000a
>                 |          
>                 |--7.14%-- unix_stream_sendmsg
>                 |          __sock_sendmsg
>                 |          sock_aio_write
>                 |          do_sync_write
>                 |          vfs_write
>                 |          sys_write
>                 |          sysenter_dispatch
>                 |          0xf7ffa430
>                 |          0xffadeb0000000014
>                 |          
>                  --7.14%-- skb_queue_tail
>                            unix_stream_sendmsg
>                            __sock_sendmsg
>                            sock_aio_write
>                            do_sync_write
>                            vfs_write
>                            sys_write
>                            sysenter_dispatch
>                            0xf7ffa430
>                            0xffadeb0000000014
> 
> 
> I dont see the brackets anymore, nor does the 10% limit seem to have 
> been listened to for the 7.14% result above, right?
> 
> 	Ingo


Oh damn. I've been investigating for several hours in the wrong direction
just because this bug triggered only when I wasn't using -s s

Actually, it's just that the other kind of sorting make this bug occur
much more quickly: in the first results. It was then more obvious in these
cases, but the issue was present in every kind of sorting.

Please find the fix below, thanks!

Frederic.

---
>From 52c89279744db58a68fa2339b3c8038e67113fca Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Sun, 9 Aug 2009 04:19:15 +0200
Subject: [PATCH] perf tools: callchain: Fix bad rounding of minimum rate

Sometimes we get callchain branches that have a rate under the limit
given by the user.

Say you launched:

perf record -f -g -a ./hackbench 10
perf report -g fractal,10.0

And you get:

2.33%       hackbench  [kernel]                  [k] _spin_lock_irqsave
                |
                |--78.57%-- remove_wait_queue
                |          poll_freewait
                |          do_sys_poll
                |          sys_poll
                |          sysenter_dispatch
                |          0xf7ffa430
                |          0x1ffadea3c
                |
                |--7.14%-- __up_read
                |          up_read
                |          do_page_fault
                |          page_fault
                |          0xf7ffa430
                |          0xa0df710000000a
                ...

It is abnormal to get a 7.14% branch whereas we passed a 10% filter.

The problem is that we round down the minimum threshold.
This happens mostly when we have very low number of events.
If the total amount of your branch is 4 and you have a subranch of 3
events, filtering to 90% will be computed like follows:

limit = 4 * 0.9;

The result is about 3.6, but the cast to integer will round down to 3.
It means that our filter is actually of 75%

We must then explicitly round up the minimum threshold.

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
---
 tools/perf/util/callchain.c |    5 +++--
 1 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index a8e67aa..0114734 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -13,6 +13,7 @@
 #include <stdio.h>
 #include <stdbool.h>
 #include <errno.h>
+#include <math.h>
 
 #include "callchain.h"
 
@@ -112,7 +113,7 @@ static void __sort_chain_graph_rel(struct callchain_node *node,
 	u64 min_hit;
 
 	node->rb_root = RB_ROOT;
-	min_hit = node->children_hit * min_percent / 100.0;
+	min_hit = ceil(node->children_hit * min_percent);
 
 	chain_for_each_child(child, node) {
 		__sort_chain_graph_rel(child, min_percent);
@@ -126,7 +127,7 @@ static void
 sort_chain_graph_rel(struct rb_root *rb_root, struct callchain_node *chain_root,
 		     u64 min_hit __used, struct callchain_param *param)
 {
-	__sort_chain_graph_rel(chain_root, param->min_percent);
+	__sort_chain_graph_rel(chain_root, param->min_percent / 100.0);
 	rb_root->rb_node = chain_root->rb_root.rb_node;
 }
 
-- 
1.6.2.3

[tip:perfcounters/core] perf tools: callchain: Fix spurious 'perf report' warnings: ignore empty callchains

[tip-bot for Frederic Weisbecker]

Commit-ID:  b0efe213f84f7fd5ccfe07053e3d9fb827b7c188
Gitweb:     http://git.kernel.org/tip/b0efe213f84f7fd5ccfe07053e3d9fb827b7c188
Author:     Frederic Weisbecker <fweisbec@gmail.com>
AuthorDate: Sat, 8 Aug 2009 02:16:23 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Sun, 9 Aug 2009 12:54:41 +0200

perf tools: callchain: Fix spurious 'perf report' warnings: ignore empty callchains

When the callchain tree comes to insert an empty backtrace, it
raises a spurious warning about the fact we are inserting an
empty. This is spurious because the radix tree assumes it did
something wrong to reach this state. But it didn't, we just met
an empty callchain that has to be ignored.

This happens occasionally with certain types of call-chain
recordings. If it happens it's a big nuisance as perf report
output starts with thousands of warning lines.

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
LKML-Reference: <1249690585-9145-2-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 tools/perf/util/callchain.c |    2 ++
 1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 98c5627..a8e67aa 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -336,5 +336,7 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain,
 void append_chain(struct callchain_node *root, struct ip_callchain *chain,
 		  struct symbol **syms)
 {
+	if (!chain->nr)
+		return;
 	__append_chain_children(root, chain, syms, 0);
 }

[tip:perfcounters/core] perf tools: callchain: Fix 'perf report' display to be callchain by default

[tip-bot for Frederic Weisbecker]

Commit-ID:  b1a88349c37624755b28ac3b3152b48f52c1f487
Gitweb:     http://git.kernel.org/tip/b1a88349c37624755b28ac3b3152b48f52c1f487
Author:     Frederic Weisbecker <fweisbec@gmail.com>
AuthorDate: Sat, 8 Aug 2009 02:16:24 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Sun, 9 Aug 2009 12:54:42 +0200

perf tools: callchain: Fix 'perf report' display to be callchain by default

If we recorded with -g option to record the callchain, right now
we require a -g option to perf report as well - and people reported
this as unnecessary complication: the user already specified -g
once, no need to require it a second time.

So if the recording includes call-chains, display the callchain by
default from perf report.

( The user can override this default using "-g none" option from
  perf report. )

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
LKML-Reference: <1249690585-9145-3-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 tools/perf/builtin-report.c |   16 +++++++++++++++-
 tools/perf/util/callchain.h |    1 +
 2 files changed, 16 insertions(+), 1 deletions(-)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index a5e2f8d..c4a8e10 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -68,7 +68,7 @@ static int		callchain;
 
 static
 struct callchain_param	callchain_param = {
-	.mode	= CHAIN_GRAPH_ABS,
+	.mode	= CHAIN_GRAPH_REL,
 	.min_percent = 0.5
 };
 
@@ -1836,6 +1836,13 @@ static int __cmd_report(void)
 					" -g?\n");
 			exit(-1);
 		}
+	} else if (callchain_param.mode != CHAIN_NONE && !callchain) {
+			callchain = 1;
+			if (register_callchain_param(&callchain_param) < 0) {
+				fprintf(stderr, "Can't register callchain"
+						" params\n");
+				exit(-1);
+			}
 	}
 
 	if (load_kernel() < 0) {
@@ -1974,6 +1981,13 @@ parse_callchain_opt(const struct option *opt __used, const char *arg,
 	else if (!strncmp(tok, "fractal", strlen(arg)))
 		callchain_param.mode = CHAIN_GRAPH_REL;
 
+	else if (!strncmp(tok, "none", strlen(arg))) {
+		callchain_param.mode = CHAIN_NONE;
+		callchain = 0;
+
+		return 0;
+	}
+
 	else
 		return -1;
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index b2d128e..a926ae4 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -7,6 +7,7 @@
 #include "symbol.h"
 
 enum chain_mode {
+	CHAIN_NONE,
 	CHAIN_FLAT,
 	CHAIN_GRAPH_ABS,
 	CHAIN_GRAPH_REL

[tip:perfcounters/core] perf tools: callchain: Fix sum of percentages to be 100% by displaying amount of ignored chains in fractal mode

[tip-bot for Frederic Weisbecker]

Commit-ID:  25446036cbfc2c89faacdb4fb4603943d2197dc6
Gitweb:     http://git.kernel.org/tip/25446036cbfc2c89faacdb4fb4603943d2197dc6
Author:     Frederic Weisbecker <fweisbec@gmail.com>
AuthorDate: Sat, 8 Aug 2009 02:16:25 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Sun, 9 Aug 2009 12:54:43 +0200

perf tools: callchain: Fix sum of percentages to be 100% by displaying amount of ignored chains in fractal mode

When we filter the callchains below a given percentage, we
ignore them and the end result only shows entries that have an
upper percentage than the filter threshold.

It seems to users then that we have an imbalance in the
percentage, as if the sum inside a profiled branch doesn't
reach 100%.

Since in the past there have been real perf report bugs that
showed the same sypmtom, it would be nice to assure the user
that the data is perfect and trustable and it all sums up to
100.00%.

So fix this by displaying the remaining hits that have been
filtered but without more detail than their amount in each
branches. Example while filtering below 50%:

7.73%  [k] delay_tsc
                |
                |--98.22%-- __const_udelay
                |          |
                |          |--86.37%-- ath5k_hw_register_timeout
                |          |          ath5k_hw_noise_floor_calibration
                |          |          ath5k_hw_reset
                |          |          ath5k_reset
                |          |          ath5k_config
                |          |          ieee80211_hw_config
                |          |          |
                |          |          |--88.53%-- ieee80211_scan_work
                |          |          |          worker_thread
                |          |          |          kthread
                |          |          |          child_rip
                |          |           --11.47%-- [...]
                |           --13.63%-- [...]
                 --1.78%-- [...]

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
LKML-Reference: <1249690585-9145-4-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 tools/perf/builtin-report.c |   47 ++++++++++++++++++++++++++++++++++++++++--
 1 files changed, 44 insertions(+), 3 deletions(-)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index c4a8e10..99274ce 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -891,6 +891,21 @@ ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, int depth,
 	return ret;
 }
 
+static struct symbol *rem_sq_bracket;
+static struct callchain_list rem_hits;
+
+static void init_rem_hits(void)
+{
+	rem_sq_bracket = malloc(sizeof(*rem_sq_bracket) + 6);
+	if (!rem_sq_bracket) {
+		fprintf(stderr, "Not enough memory to display remaining hits\n");
+		return;
+	}
+
+	strcpy(rem_sq_bracket->name, "[...]");
+	rem_hits.sym = rem_sq_bracket;
+}
+
 static size_t
 callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 			u64 total_samples, int depth, int depth_mask)
@@ -900,6 +915,7 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 	struct callchain_list *chain;
 	int new_depth_mask = depth_mask;
 	u64 new_total;
+	u64 remaining;
 	size_t ret = 0;
 	int i;
 
@@ -908,17 +924,25 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 	else
 		new_total = total_samples;
 
+	remaining = new_total;
+
 	node = rb_first(&self->rb_root);
 	while (node) {
+		u64 cumul;
+
 		child = rb_entry(node, struct callchain_node, rb_node);
+		cumul = cumul_hits(child);
+		remaining -= cumul;
 
 		/*
 		 * The depth mask manages the output of pipes that show
 		 * the depth. We don't want to keep the pipes of the current
-		 * level for the last child of this depth
+		 * level for the last child of this depth.
+		 * Except if we have remaining filtered hits. They will
+		 * supersede the last child
 		 */
 		next = rb_next(node);
-		if (!next)
+		if (!next && (callchain_param.mode != CHAIN_GRAPH_REL || !remaining))
 			new_depth_mask &= ~(1 << (depth - 1));
 
 		/*
@@ -933,7 +957,7 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 			ret += ipchain__fprintf_graph(fp, chain, depth,
 						      new_depth_mask, i++,
 						      new_total,
-						      cumul_hits(child));
+						      cumul);
 		}
 		ret += callchain__fprintf_graph(fp, child, new_total,
 						depth + 1,
@@ -941,6 +965,19 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self,
 		node = next;
 	}
 
+	if (callchain_param.mode == CHAIN_GRAPH_REL &&
+		remaining && remaining != new_total) {
+
+		if (!rem_sq_bracket)
+			return ret;
+
+		new_depth_mask &= ~(1 << (depth - 1));
+
+		ret += ipchain__fprintf_graph(fp, &rem_hits, depth,
+					      new_depth_mask, 0, new_total,
+					      remaining);
+	}
+
 	return ret;
 }
 
@@ -1361,6 +1398,8 @@ static size_t output__fprintf(FILE *fp, u64 total_samples)
 	unsigned int width;
 	char *col_width = col_width_list_str;
 
+	init_rem_hits();
+
 	fprintf(fp, "# Samples: %Ld\n", (u64)total_samples);
 	fprintf(fp, "#\n");
 
@@ -1432,6 +1471,8 @@ print_entries:
 	}
 	fprintf(fp, "\n");
 
+	free(rem_sq_bracket);
+
 	return ret;
 }
 

[tip:perfcounters/urgent] perf tools: callchain: Fix bad rounding of minimum rate

[tip-bot for Frederic Weisbecker]

Commit-ID:  c0a8865e32c8d1a562db38e06ef31ef23282f646
Gitweb:     http://git.kernel.org/tip/c0a8865e32c8d1a562db38e06ef31ef23282f646
Author:     Frederic Weisbecker <fweisbec@gmail.com>
AuthorDate: Sun, 9 Aug 2009 04:19:15 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Sun, 9 Aug 2009 13:07:46 +0200

perf tools: callchain: Fix bad rounding of minimum rate

Sometimes we get callchain branches that have a rate under the
limit given by the user.

Say you launched:

 perf record -f -g -a ./hackbench 10
 perf report -g fractal,10.0

And you got:

2.33%       hackbench  [kernel]                  [k] _spin_lock_irqsave
                |
                |--78.57%-- remove_wait_queue
                |          poll_freewait
                |          do_sys_poll
                |          sys_poll
                |          sysenter_dispatch
                |          0xf7ffa430
                |          0x1ffadea3c
                |
                |--7.14%-- __up_read
                |          up_read
                |          do_page_fault
                |          page_fault
                |          0xf7ffa430
                |          0xa0df710000000a
                ...

It is abnormal to get a 7.14% branch whereas we passed a 10%
filter.

The problem is that we round down the minimum threshold. This
happens mostly when we have very low number of events. If the
total amount of your branch is 4 and you have a subranch of 3
events, filtering to 90% will be computed like follows:

  limit = 4 * 0.9;

The result is about 3.6, but the cast to integer will round
down to 3. It means that our filter is actually of 75%

We must then explicitly round up the minimum threshold.

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: acme@redhat.com
Cc: peterz@infradead.org
Cc: efault@gmx.de
LKML-Reference: <20090809024235.GA10146@nowhere>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 tools/perf/util/callchain.c |    5 +++--
 1 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index a8e67aa..0114734 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -13,6 +13,7 @@
 #include <stdio.h>
 #include <stdbool.h>
 #include <errno.h>
+#include <math.h>
 
 #include "callchain.h"
 
@@ -112,7 +113,7 @@ static void __sort_chain_graph_rel(struct callchain_node *node,
 	u64 min_hit;
 
 	node->rb_root = RB_ROOT;
-	min_hit = node->children_hit * min_percent / 100.0;
+	min_hit = ceil(node->children_hit * min_percent);
 
 	chain_for_each_child(child, node) {
 		__sort_chain_graph_rel(child, min_percent);
@@ -126,7 +127,7 @@ static void
 sort_chain_graph_rel(struct rb_root *rb_root, struct callchain_node *chain_root,
 		     u64 min_hit __used, struct callchain_param *param)
 {
-	__sort_chain_graph_rel(chain_root, param->min_percent);
+	__sort_chain_graph_rel(chain_root, param->min_percent / 100.0);
 	rb_root->rb_node = chain_root->rb_root.rb_node;
 }
 

[PATCH 3/4] perf tools: callchain: Default display callchain from report if recorded with -g

[Frederic Weisbecker]

If we recorded with -g option to record the callchain, let's display
the callchain by default from perf report.

The user can override this default using "-g none" option from
perf report.

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
---
 tools/perf/builtin-report.c |   16 +++++++++++++++-
 tools/perf/util/callchain.h |    1 +
 2 files changed, 16 insertions(+), 1 deletions(-)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index a5e2f8d..c4a8e10 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -68,7 +68,7 @@ static int		callchain;
 
 static
 struct callchain_param	callchain_param = {
-	.mode	= CHAIN_GRAPH_ABS,
+	.mode	= CHAIN_GRAPH_REL,
 	.min_percent = 0.5
 };
 
@@ -1836,6 +1836,13 @@ static int __cmd_report(void)
 					" -g?\n");
 			exit(-1);
 		}
+	} else if (callchain_param.mode != CHAIN_NONE && !callchain) {
+			callchain = 1;
+			if (register_callchain_param(&callchain_param) < 0) {
+				fprintf(stderr, "Can't register callchain"
+						" params\n");
+				exit(-1);
+			}
 	}
 
 	if (load_kernel() < 0) {
@@ -1974,6 +1981,13 @@ parse_callchain_opt(const struct option *opt __used, const char *arg,
 	else if (!strncmp(tok, "fractal", strlen(arg)))
 		callchain_param.mode = CHAIN_GRAPH_REL;
 
+	else if (!strncmp(tok, "none", strlen(arg))) {
+		callchain_param.mode = CHAIN_NONE;
+		callchain = 0;
+
+		return 0;
+	}
+
 	else
 		return -1;
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index b2d128e..a926ae4 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -7,6 +7,7 @@
 #include "symbol.h"
 
 enum chain_mode {
+	CHAIN_NONE,
 	CHAIN_FLAT,
 	CHAIN_GRAPH_ABS,
 	CHAIN_GRAPH_REL
-- 
1.6.2.3