Starting on v4.12 event parsing code for dynamic pmu events already
supports prefix-based matching of multiple pmus when creating dynamic
events. E.g., in a system with the following dynamic pmus:
mypmu_0
mypmu_1
mypmu_2
mypmu_4
passing mypmu/<config>/ as an event spec will result in the creation
of the event in all of the pmus. This change expands this matching
through the use of fnmatch so glob-like expressions can be used to
create events in multiple pmus. E.g., in the system described above
if a user only wants to create the event in mypmu_0 and mypmu_1,
mypmu_[01]/<config>/ can be passed.
Signed-off-by: Agustin Vega-Frias <[email protected]>
---
tools/perf/Documentation/perf-list.txt | 8 +++++++-
tools/perf/Documentation/perf-stat.txt | 13 +++++++++++++
tools/perf/util/parse-events.l | 2 +-
tools/perf/util/parse-events.y | 14 ++++++++++++--
4 files changed, 33 insertions(+), 4 deletions(-)
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index e2a897a..2549c34 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -141,7 +141,13 @@ on the first memory controller on socket 0 of a Intel Xeon system
Each memory controller has its own PMU. Measuring the complete system
bandwidth would require specifying all imc PMUs (see perf list output),
-and adding the values together.
+and adding the values together. To simplify creation of multiple events,
+prefix and glob matching is supported in the PMU name, and the prefix
+'uncore_' is also ignored when performing the match. So the command above
+can be expanded to all memory controllers by using the syntaxes:
+
+ perf stat -C 0 -a imc/cas_count_read/,imc/cas_count_write/ -I 1000 ...
+ perf stat -C 0 -a *imc*/cas_count_read/,*imc*/cas_count_write/ -I 1000 ...
This example measures the combined core power every second
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 823fce7..5ee954f 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -49,6 +49,13 @@ report::
parameters are defined by corresponding entries in
/sys/bus/event_source/devices/<pmu>/format/*
+ Note that the last two syntaxes support prefix and glob matching in
+ the PMU name to simplify creation of events accross multiple instances
+ of the same type of PMU in large systems (e.g. memory controller PMUs).
+ Multiple PMU instances are typical for uncore PMUs, so the prefix
+ 'uncore_' is also ignored when performing this match.
+
+
-i::
--no-inherit::
child tasks do not inherit counters
@@ -246,6 +253,12 @@ taskset.
--no-merge::
Do not merge results from same PMUs.
+When multiple events are created from a single event alias, stat will,
+by default, aggregate the event counts and show the result in a single
+row. This option disables that behavior and shows the individual events
+and counts. Aliases are listed immediately after the Kernel PMU events
+by perf list.
+
--smi-cost::
Measure SMI cost if msr/aperf/ and msr/smi/ events are supported.
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 655ecff..a1a01b1 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -175,7 +175,7 @@ bpf_source [^,{}]+\.c[a-zA-Z0-9._]*
num_dec [0-9]+
num_hex 0x[a-fA-F0-9]+
num_raw_hex [a-fA-F0-9]+
-name [a-zA-Z_*?][a-zA-Z0-9_*?.]*
+name [a-zA-Z_*?\[\]][a-zA-Z0-9_*?.\[\]]*
name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
drv_cfg_term [a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)?
/* If you add a modifier you need to update check_modifier() */
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index e81a20e..dedf184 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -8,6 +8,7 @@
#define YYDEBUG 1
+#include <fnmatch.h>
#include <linux/compiler.h>
#include <linux/list.h>
#include <linux/types.h>
@@ -234,6 +235,10 @@ PE_NAME opt_event_config
if (parse_events_add_pmu(_parse_state, list, $1, $2)) {
struct perf_pmu *pmu = NULL;
int ok = 0;
+ char *pattern;
+
+ if (asprintf(&pattern, "%s*", $1) < 0)
+ YYABORT;
while ((pmu = perf_pmu__scan(pmu)) != NULL) {
char *name = pmu->name;
@@ -241,14 +246,19 @@ PE_NAME opt_event_config
if (!strncmp(name, "uncore_", 7) &&
strncmp($1, "uncore_", 7))
name += 7;
- if (!strncmp($1, name, strlen($1))) {
- if (parse_events_copy_term_list(orig_terms, &terms))
+ if (!fnmatch(pattern, name, 0)) {
+ if (parse_events_copy_term_list(orig_terms, &terms)) {
+ free(pattern);
YYABORT;
+ }
if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms))
ok++;
parse_events_terms__delete(terms);
}
}
+
+ free(pattern);
+
if (!ok)
YYABORT;
}
--
Qualcomm Datacenter Technologies, Inc. on behalf of the Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum, a Linux Foundation Collaborative Project.
Em Wed, Mar 07, 2018 at 03:35:47PM -0500, Agustin Vega-Frias escreveu:
> +++ b/tools/perf/util/parse-events.y
> @@ -8,6 +8,7 @@
>
> #define YYDEBUG 1
>
> +#include <fnmatch.h>
> #include <linux/compiler.h>
> #include <linux/list.h>
> #include <linux/types.h>
> @@ -234,6 +235,10 @@ PE_NAME opt_event_config
> if (parse_events_add_pmu(_parse_state, list, $1, $2)) {
> struct perf_pmu *pmu = NULL;
> int ok = 0;
> + char *pattern;
> +
> + if (asprintf(&pattern, "%s*", $1) < 0)
> + YYABORT;
+ if (asprintf(&pattern, "?(uncore_)%s*", $1) < 0)
I completely overlook that you were using this and thus needed that
extension, duh, thanks for the patience 8-) and for the new patch.
- Arnaldo
On 2018-03-08 08:03, Arnaldo Carvalho de Melo wrote:
> Em Wed, Mar 07, 2018 at 03:35:47PM -0500, Agustin Vega-Frias escreveu:
>> +++ b/tools/perf/util/parse-events.y
>> @@ -8,6 +8,7 @@
>>
>> #define YYDEBUG 1
>>
>> +#include <fnmatch.h>
>> #include <linux/compiler.h>
>> #include <linux/list.h>
>> #include <linux/types.h>
>> @@ -234,6 +235,10 @@ PE_NAME opt_event_config
>> if (parse_events_add_pmu(_parse_state, list, $1, $2)) {
>> struct perf_pmu *pmu = NULL;
>> int ok = 0;
>> + char *pattern;
>> +
>> + if (asprintf(&pattern, "%s*", $1) < 0)
>> + YYABORT;
>
> + if (asprintf(&pattern, "?(uncore_)%s*", $1) < 0)
>
> I completely overlook that you were using this and thus needed that
> extension, duh, thanks for the patience 8-) and for the new patch.
>
NP Arnaldo, thanks for the quick turnaround on these patches :o)
Just so I know, since these are my first patches on perf tools,
where are perf tools patches queued once acked?
Thanks!
--
Qualcomm Datacenter Technologies, Inc. on behalf of the Qualcomm
Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum, a
Linux Foundation Collaborative Project.
Em Thu, Mar 08, 2018 at 08:28:13AM -0500, Agustin Vega-Frias escreveu:
> On 2018-03-08 08:03, Arnaldo Carvalho de Melo wrote:
> > Em Wed, Mar 07, 2018 at 03:35:47PM -0500, Agustin Vega-Frias escreveu:
> > > +++ b/tools/perf/util/parse-events.y
> > > @@ -8,6 +8,7 @@
> > >
> > > #define YYDEBUG 1
> > >
> > > +#include <fnmatch.h>
> > > #include <linux/compiler.h>
> > > #include <linux/list.h>
> > > #include <linux/types.h>
> > > @@ -234,6 +235,10 @@ PE_NAME opt_event_config
> > > if (parse_events_add_pmu(_parse_state, list, $1, $2)) {
> > > struct perf_pmu *pmu = NULL;
> > > int ok = 0;
> > > + char *pattern;
> > > +
> > > + if (asprintf(&pattern, "%s*", $1) < 0)
> > > + YYABORT;
> > + if (asprintf(&pattern, "?(uncore_)%s*", $1) < 0)
> > I completely overlook that you were using this and thus needed that
> > extension, duh, thanks for the patience 8-) and for the new patch.
Further trying to remove my brown paper bag: I thought the '?(...)' type
of thing would be something _users_ would pass on the perf tool command
line, not something used by the tool itself, like on the original
patch.... :-)
> NP Arnaldo, thanks for the quick turnaround on these patches :o)
> Just so I know, since these are my first patches on perf tools,
> where are perf tools patches queued once acked?
git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git perf/core
If they are super urgent, then they will go to a different branch,
perf/urgent, that is targetted for the current merge window, i.e. right
now:
perf/core -> 4.17
perf/urgent -> 4.16
Thanks, and keep the patches flowing!
- Arnaldo
Commit-ID: b2b9d3a3f0211c5d08c7befdf9d4adad48cda315
Gitweb: https://git.kernel.org/tip/b2b9d3a3f0211c5d08c7befdf9d4adad48cda315
Author: Agustin Vega-Frias <[email protected]>
AuthorDate: Tue, 6 Mar 2018 09:04:42 -0500
Committer: Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Thu, 8 Mar 2018 10:05:25 -0300
perf pmu: Support wildcards on pmu name in dynamic pmu events
Starting on v4.12 event parsing code for dynamic pmu events already
supports prefix-based matching of multiple pmus when creating dynamic
events. E.g., in a system with the following dynamic pmus:
mypmu_0
mypmu_1
mypmu_2
mypmu_4
passing mypmu/<config>/ as an event spec will result in the creation of
the event in all of the pmus. This change expands this matching through
the use of fnmatch so glob-like expressions can be used to create events
in multiple pmus. E.g., in the system described above if a user only
wants to create the event in mypmu_0 and mypmu_1, mypmu_[01]/<config>/
can be passed.
Signed-off-by: Agustin Vega-Frias <[email protected]>
Acked-by: Andi Kleen <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: [email protected]
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Timur Tabi <[email protected]>
Change-Id: Icb25653fc5d5239c20f3bffdfdf4ab4c9c9bb20b
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
---
tools/perf/Documentation/perf-list.txt | 8 +++++++-
tools/perf/Documentation/perf-stat.txt | 13 +++++++++++++
tools/perf/util/parse-events.l | 2 +-
tools/perf/util/parse-events.y | 14 ++++++++++++--
4 files changed, 33 insertions(+), 4 deletions(-)
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index e2a897ae3596..2549c34a7895 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -141,7 +141,13 @@ on the first memory controller on socket 0 of a Intel Xeon system
Each memory controller has its own PMU. Measuring the complete system
bandwidth would require specifying all imc PMUs (see perf list output),
-and adding the values together.
+and adding the values together. To simplify creation of multiple events,
+prefix and glob matching is supported in the PMU name, and the prefix
+'uncore_' is also ignored when performing the match. So the command above
+can be expanded to all memory controllers by using the syntaxes:
+
+ perf stat -C 0 -a imc/cas_count_read/,imc/cas_count_write/ -I 1000 ...
+ perf stat -C 0 -a *imc*/cas_count_read/,*imc*/cas_count_write/ -I 1000 ...
This example measures the combined core power every second
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 2b38e222016a..628026dbedc5 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -49,6 +49,13 @@ report::
parameters are defined by corresponding entries in
/sys/bus/event_source/devices/<pmu>/format/*
+ Note that the last two syntaxes support prefix and glob matching in
+ the PMU name to simplify creation of events accross multiple instances
+ of the same type of PMU in large systems (e.g. memory controller PMUs).
+ Multiple PMU instances are typical for uncore PMUs, so the prefix
+ 'uncore_' is also ignored when performing this match.
+
+
-i::
--no-inherit::
child tasks do not inherit counters
@@ -260,6 +267,12 @@ taskset.
--no-merge::
Do not merge results from same PMUs.
+When multiple events are created from a single event alias, stat will,
+by default, aggregate the event counts and show the result in a single
+row. This option disables that behavior and shows the individual events
+and counts. Aliases are listed immediately after the Kernel PMU events
+by perf list.
+
--smi-cost::
Measure SMI cost if msr/aperf/ and msr/smi/ events are supported.
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 655ecff636a8..a1a01b1ac8b8 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -175,7 +175,7 @@ bpf_source [^,{}]+\.c[a-zA-Z0-9._]*
num_dec [0-9]+
num_hex 0x[a-fA-F0-9]+
num_raw_hex [a-fA-F0-9]+
-name [a-zA-Z_*?][a-zA-Z0-9_*?.]*
+name [a-zA-Z_*?\[\]][a-zA-Z0-9_*?.\[\]]*
name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
drv_cfg_term [a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)?
/* If you add a modifier you need to update check_modifier() */
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index e81a20ea8d7d..dedf184b5bed 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -8,6 +8,7 @@
#define YYDEBUG 1
+#include <fnmatch.h>
#include <linux/compiler.h>
#include <linux/list.h>
#include <linux/types.h>
@@ -234,6 +235,10 @@ PE_NAME opt_event_config
if (parse_events_add_pmu(_parse_state, list, $1, $2)) {
struct perf_pmu *pmu = NULL;
int ok = 0;
+ char *pattern;
+
+ if (asprintf(&pattern, "%s*", $1) < 0)
+ YYABORT;
while ((pmu = perf_pmu__scan(pmu)) != NULL) {
char *name = pmu->name;
@@ -241,14 +246,19 @@ PE_NAME opt_event_config
if (!strncmp(name, "uncore_", 7) &&
strncmp($1, "uncore_", 7))
name += 7;
- if (!strncmp($1, name, strlen($1))) {
- if (parse_events_copy_term_list(orig_terms, &terms))
+ if (!fnmatch(pattern, name, 0)) {
+ if (parse_events_copy_term_list(orig_terms, &terms)) {
+ free(pattern);
YYABORT;
+ }
if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms))
ok++;
parse_events_terms__delete(terms);
}
}
+
+ free(pattern);
+
if (!ok)
YYABORT;
}