perf tool: Add PERF_SAMPLE_READ sample read support
cover perf tool: Add PERF_SAMPLE_READ sample read support
hi,
adding support to read sample values through the PERF_SAMPLE_READ sample type. It's now possible to specify 'S' modifier for an event and get its sample value by PERF_SAMPLE_READ.
For group the 'S' modifier will enable sampling only for the leader and read all the group member by PERF_SAMPLE_READ smple type with PERF_FORMAT_GROUP read format.
This was first introduced in here:
https://lkml.org/lkml/2012/10/20/75
Example:
$ perf record -e '{cycles,cache-misses}:S' ls
...
$ perf report --group --show-total-period --stdio
...
# Samples: 36 of event 'anon group { cycles, cache-misses }'
# Event count (approx.): 12585593
#
# Overhead Period Command Shared Object Symbol
# ................ ........................ ....... ................. ..........................
#
19.92% 1.20% 2505936 31 ls [kernel.kallsyms] [k] mark_held_locks
13.74% 0.47% 1729327 12 ls [kernel.kallsyms] [k] sched_clock_local
13.64% 23.72% 1716147 612 ls ld-2.14.90.so [.] check_match.10805
13.12% 23.22% 1650778 599 ls libc-2.14.90.so [.] _nl_intern_locale_data
11.24% 29.19% 1414554 753 ls [kernel.kallsyms] [k] sched_clock_cpu
8.50% 0.35% 1070150 9 ls [kernel.kallsyms] [k] check_chain_key
...The patchset is based on following fix:
http://lkml.org/lkml/2013/2/4/122
and is available also at:git://git.kernel.org/pub/scm/linux/kernel/git/jolsa/linux.git
perf/group6
TODO: add column names as suggested by Ingo in the original discussion.
thanks,
jirka
---
Jiri Olsa (11):
perf ui/hist: Add support to display whole group data for raw columns
perf: Add PERF_EVENT_IOC_ID ioctl to return event ID
perf: Do not get values from disabled counters in group format read perf tools: Use PERF_EVENT_IOC_ID perf ioctl to read event id perf tools: Add support for parsing PERF_SAMPLE_READ sample type perf tools: Fix event ID retrieval for group format read case perf tools: Add perf_evlist__id2sid function to get event ID related data perf tools: Add PERF_SAMPLE_READ sample related processing perf tools: Add 'S' event/group modifier to read sample value perf tests: Add attr record group sampling test
perf tests: Add parse events tests for leader sampling
include/uapi/linux/perf_event.h | 1 + kernel/events/core.c | 12 ++++++++- tools/perf/Documentation/perf-list.txt | 1 + tools/perf/tests/attr/test-record-group-sampling | 36 ++++++++++++++++++++++++++ tools/perf/tests/parse-events.c | 115 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ tools/perf/ui/hist.c | 53 +++++++++++++++++++------------------- tools/perf/util/event.h | 18 +++++++++++++ tools/perf/util/evlist.c | 73 +++++++++++++++++++++++++++++++++++++++++++++++----- tools/perf/util/evlist.h | 4 +++ tools/perf/util/evsel.c | 59 ++++++++++++++++++++++++++++++++++++++++-- tools/perf/util/evsel.h | 4 +++ tools/perf/util/parse-events.c | 8 +++++- tools/perf/util/parse-events.l | 2 +- tools/perf/util/session.c | 110 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++- 14 files changed, 457 insertions(+), 39 deletions(-)
PATCH 1/11 perf ui/hist: Add support to display whole group data for raw columns
Currently we don't display group members' values for raw columns like 'Samples' and 'Period' when in group report mode.
Uniting '__hpp__percent_fmt' and '__hpp__raw_fmt' function under new function __hpp__fmt. It's basically '__hpp__percent_fmt' code with new 'fmt_percent' bool parameter added saying whether raw number or percentage should be printed.
This way raw columns print out all the group members when in group report mode, like:
$ perf record -e '{cycles,cache-misses}' ls
...
$ perf report --group --show-total-period --stdio
...
# Overhead Period Command Shared Object Symbol
# ................ ........................ ....... ................. .................................
#
23.63% 11.24% 3331335 317 ls [kernel.kallsyms] [k] __lock_acquire
12.72% 0.00% 1793100 0 ls [kernel.kallsyms] [k] native_sched_clock
9.72% 0.00% 1369920 0 ls libc-2.14.90.so [.] _nl_find_locale
0.03% 0.07% 4476 2 ls [kernel.kallsyms] [k] intel_pmu_enable_all
0.00% 11.73% 0 331 ls ld-2.14.90.so [.] _dl_cache_libcmp
0.00% 11.06% 0 312 ls [kernel.kallsyms] [k] vma_interval_tree_insert--- tools/perf/ui/hist.c | 53 ++++++++++++++++++++++++++-------------------------- 1 file changed, 26 insertions(+), 27 deletions(-)
tools/perf/ui/hist.c +26 -27
@@ -9,18 +9,24 @@typedef int (*hpp_snprint_fn )(char *buf,size_t size,const char *fmt, ...); -static int __hpp__percent_fmt (struct perf_hpp *hpp,struct hist_entry *he, -u64 (*get_field)(struct hist_entry *), -const char *fmt,hpp_snprint_fn print_fn) +static int __hpp__fmt (struct perf_hpp *hpp,struct hist_entry *he, +u64 (*get_field)(struct hist_entry *), +const char *fmt,hpp_snprint_fn print_fn, +bool fmt_percent) {int ret; -double percent =0.0 ;struct hists *hists = he->hists; -if (hists->stats.total_period) - percent =100.0 *get_field (he) / hists->stats.total_period; +if (fmt_percent) { +double percent =0.0 ; + +if (hists->stats.total_period) + percent =100.0 *get_field (he) / + hists->stats.total_period; - ret =print_fn (hpp->buf, hpp->size, fmt, percent); + ret =print_fn (hpp->buf, hpp->size, fmt, percent); + }else + ret =print_fn (hpp->buf, hpp->size, fmt,get_field (he));if (symbol_conf.event_group) {int prev_idx, idx_delta;
@@ -49,11 +55,15 @@ static int __hpp__percent_fmt(struct perf_hpp *hpp, struct hist_entry *he,* have no sample */ ret +=print_fn (hpp->buf + ret, hpp->size - ret, - fmt,0.0 ); + fmt,0 ); } - ret +=print_fn (hpp->buf + ret, hpp->size - ret, - fmt,100.0 * period / total); +if (fmt_percent) + ret +=print_fn (hpp->buf + ret, hpp->size - ret, + fmt,100.0 * period / total); +else + ret +=print_fn (hpp->buf + ret, hpp->size - ret, + fmt, period); prev_idx =perf_evsel__group_idx (evsel); }
@@ -65,23 +75,12 @@ static int __hpp__percent_fmt(struct perf_hpp *hpp, struct hist_entry *he,* zero-fill group members at last which have no sample */ ret +=print_fn (hpp->buf + ret, hpp->size - ret, - fmt,0.0 ); + fmt,0 ); } }return ret; } -static int __hpp__raw_fmt (struct perf_hpp *hpp,struct hist_entry *he, -u64 (*get_field)(struct hist_entry *), -const char *fmt,hpp_snprint_fn print_fn) -{ -int ret; - - ret =print_fn (hpp->buf, hpp->size, fmt,get_field (he)); -return ret; -} - -#define __HPP_HEADER_FN (_type, _str, _min_width, _unit_width) \ static int hpp__header_##_type(struct perf_hpp *hpp) \ { \
@@ -116,16 +115,16 @@ static u64 he_get_##_field(struct hist_entry *he) \ \ static int hpp__color_##_type(struct perf_hpp *hpp, struct hist_entry *he) \ { \ - return __hpp__percent_fmt(hpp, he, he_get_##_field, " %6.2f%%", \ - (hpp_snprint_fn )percent_color_snprintf); \ + return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%", \ + (hpp_snprint_fn )percent_color_snprintf, true); \ }#define __HPP_ENTRY_PERCENT_FN (_type, _field) \ static int hpp__entry_##_type(struct perf_hpp *hpp, struct hist_entry *he) \ { \ const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%"; \ - return __hpp__percent_fmt(hpp, he, he_get_##_field, fmt, \ - scnprintf); \ + return __hpp__fmt(hpp, he, he_get_##_field, fmt, \ + scnprintf, true); \ }#define __HPP_ENTRY_RAW_FN (_type, _field) \
@@ -137,7 +136,7 @@ static u64 he_get_raw_##_field(struct hist_entry *he) \ static int hpp__entry_##_type(struct perf_hpp *hpp, struct hist_entry *he) \ { \const char *fmt = symbol_conf.field_sep ?" %" PRIu64 :" %11" PRIu64; \ - return __hpp__raw_fmt(hpp, he, he_get_raw_##_field, fmt, scnprintf); \ + return __hpp__fmt(hpp, he, he_get_raw_##_field, fmt, scnprintf, false); \ }#define HPP_PERCENT_FNS (_type, _str, _field, _min_width, _unit_width) \
Signature · 1 line
1.7.11.7
Namhyung Kim
maintainerRe: [PATCH 01/11] perf ui/hist: Add support to display whole group data for raw columns
Hi Jiri,
Quoted 3 lines · Jiri Olsa
Currently we don't display group members' values for raw columns like 'Samples' and 'Period' when in group report mode.
Oops, it was lost during the rework. Thanks for fixing this.
Thanks,
Namhyung
[tip:perf/core] perf hists browser: Add support to display whole group data for raw columns
In reply to Jiri OlsaCommit-ID: 0c5268bf2218144469dde3228f14898fadbbcdcd Gitweb: http://git.kernel.org/tip/0c5268bf2218144469dde3228f14898fadbbcdcd Author: Jiri Olsa <[email protected]> AuthorDate: Mon, 4 Feb 2013 13:32:55 +0100 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitDate: Wed, 6 Feb 2013 18:09:27 -0300
perf hists browser: Add support to display whole group data for raw columns
Currently we don't display group members' values for raw columns like 'Samples' and 'Period' when in group report mode.
Uniting '__hpp__percent_fmt' and '__hpp__raw_fmt' function under new function __hpp__fmt. It's basically '__hpp__percent_fmt' code with new 'fmt_percent' bool parameter added saying whether raw number or percentage should be printed.
This way raw columns print out all the group members when in group report mode, like:
$ perf record -e '{cycles,cache-misses}' ls
...
$ perf report --group --show-total-period --stdio
...
# Overhead Period Command Shared Object Symbol
# ................ ........................ ....... ................. .................................
#
23.63% 11.24% 3331335 317 ls [kernel.kallsyms] [k] __lock_acquire
12.72% 0.00% 1793100 0 ls [kernel.kallsyms] [k] native_sched_clock
9.72% 0.00% 1369920 0 ls libc-2.14.90.so [.] _nl_find_locale
0.03% 0.07% 4476 2 ls [kernel.kallsyms] [k] intel_pmu_enable_all
0.00% 11.73% 0 331 ls ld-2.14.90.so [.] _dl_cache_libcmp
0.00% 11.06% 0 312 ls [kernel.kallsyms] [k] vma_interval_tree_insert--- tools/perf/ui/hist.c | 53 ++++++++++++++++++++++++++-------------------------- 1 file changed, 26 insertions(+), 27 deletions(-)
tools/perf/ui/hist.c +26 -27
@@ -9,18 +9,24 @@typedef int (*hpp_snprint_fn )(char *buf,size_t size,const char *fmt, ...); -static int __hpp__percent_fmt (struct perf_hpp *hpp,struct hist_entry *he, -u64 (*get_field)(struct hist_entry *), -const char *fmt,hpp_snprint_fn print_fn) +static int __hpp__fmt (struct perf_hpp *hpp,struct hist_entry *he, +u64 (*get_field)(struct hist_entry *), +const char *fmt,hpp_snprint_fn print_fn, +bool fmt_percent) {int ret; -double percent =0.0 ;struct hists *hists = he->hists; -if (hists->stats.total_period) - percent =100.0 *get_field (he) / hists->stats.total_period; +if (fmt_percent) { +double percent =0.0 ; + +if (hists->stats.total_period) + percent =100.0 *get_field (he) / + hists->stats.total_period; - ret =print_fn (hpp->buf, hpp->size, fmt, percent); + ret =print_fn (hpp->buf, hpp->size, fmt, percent); + }else + ret =print_fn (hpp->buf, hpp->size, fmt,get_field (he));if (symbol_conf.event_group) {int prev_idx, idx_delta;
@@ -49,11 +55,15 @@ static int __hpp__percent_fmt(struct perf_hpp *hpp, struct hist_entry *he,* have no sample */ ret +=print_fn (hpp->buf + ret, hpp->size - ret, - fmt,0.0 ); + fmt,0 ); } - ret +=print_fn (hpp->buf + ret, hpp->size - ret, - fmt,100.0 * period / total); +if (fmt_percent) + ret +=print_fn (hpp->buf + ret, hpp->size - ret, + fmt,100.0 * period / total); +else + ret +=print_fn (hpp->buf + ret, hpp->size - ret, + fmt, period); prev_idx =perf_evsel__group_idx (evsel); }
@@ -65,23 +75,12 @@ static int __hpp__percent_fmt(struct perf_hpp *hpp, struct hist_entry *he,* zero-fill group members at last which have no sample */ ret +=print_fn (hpp->buf + ret, hpp->size - ret, - fmt,0.0 ); + fmt,0 ); } }return ret; } -static int __hpp__raw_fmt (struct perf_hpp *hpp,struct hist_entry *he, -u64 (*get_field)(struct hist_entry *), -const char *fmt,hpp_snprint_fn print_fn) -{ -int ret; - - ret =print_fn (hpp->buf, hpp->size, fmt,get_field (he)); -return ret; -} - -#define __HPP_HEADER_FN (_type, _str, _min_width, _unit_width) \ static int hpp__header_##_type(struct perf_hpp *hpp) \ { \
@@ -116,16 +115,16 @@ static u64 he_get_##_field(struct hist_entry *he) \ \ static int hpp__color_##_type(struct perf_hpp *hpp, struct hist_entry *he) \ { \ - return __hpp__percent_fmt(hpp, he, he_get_##_field, " %6.2f%%", \ - (hpp_snprint_fn )percent_color_snprintf); \ + return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%", \ + (hpp_snprint_fn )percent_color_snprintf, true); \ }#define __HPP_ENTRY_PERCENT_FN (_type, _field) \ static int hpp__entry_##_type(struct perf_hpp *hpp, struct hist_entry *he) \ { \ const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%"; \ - return __hpp__percent_fmt(hpp, he, he_get_##_field, fmt, \ - scnprintf); \ + return __hpp__fmt(hpp, he, he_get_##_field, fmt, \ + scnprintf, true); \ }#define __HPP_ENTRY_RAW_FN (_type, _field) \
@@ -137,7 +136,7 @@ static u64 he_get_raw_##_field(struct hist_entry *he) \ static int hpp__entry_##_type(struct perf_hpp *hpp, struct hist_entry *he) \ { \const char *fmt = symbol_conf.field_sep ?" %" PRIu64 :" %11" PRIu64; \ - return __hpp__raw_fmt(hpp, he, he_get_raw_##_field, fmt, scnprintf); \ + return __hpp__fmt(hpp, he, he_get_raw_##_field, fmt, scnprintf, false); \ }#define HPP_PERCENT_FNS (_type, _str, _field, _min_width, _unit_width) \
PATCH 2/11 perf: Add PERF_EVENT_IOC_ID ioctl to return event ID
In reply to Jiri OlsaFrom: "[email protected]" <[email protected]>
The only way to get the event ID is by reading the event fd, followed by parsing the ID value out of the returned data.
While this is ok for current read format used by perf tool, it is not ok when we use PERF_FORMAT_GROUP format.
With this format the data are returned for the whole group and there's no way to find out what ID belongs to our fd (if we are not group leader event).
Adding a simple ioctl that returns event primary ID for given fd.
--- include/uapi/linux/perf_event.h | 1 + kernel/events/core.c | 9 +++++++++ 2 files changed, 10 insertions(+)
include/uapi/linux/perf_event.h +1 -0
@@ -316,6 +316,7 @@ struct perf_event_attr {#define PERF_EVENT_IOC_PERIOD _IOW('$', 4, __u64)#define PERF_EVENT_IOC_SET_OUTPUT _IO ('$', 5)#define PERF_EVENT_IOC_SET_FILTER _IOW('$', 6, char *) +#define PERF_EVENT_IOC_ID _IOR('$', 7, u64 *)enum perf_event_ioc_flags {PERF_IOC_FLAG_GROUP =1U <<0 ,
kernel/events/core.c +9 -0
@@ -3277,6 +3277,15 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)case PERF_EVENT_IOC_PERIOD :return perf_event_period (event, (u64 __user *)arg); +case PERF_EVENT_IOC_ID : + { +u64 id =primary_event_id (event); + +if (copy_to_user ((void __user *)arg, &id,sizeof (id))) +return -EFAULT ; +return 0 ; + } +case PERF_EVENT_IOC_SET_OUTPUT : {int ret;
Signature · 1 line
1.7.11.7
Re: [PATCH 02/11] perf: Add PERF_EVENT_IOC_ID ioctl to return event ID
Quoted 8 lines · Jiri Olsa
From: "[email protected]" <[email protected]>
The only way to get the event ID is by reading the event fd, followed by parsing the ID value out of the returned data.
While this is ok for current read format used by perf tool, it is not ok when we use
PERF_FORMAT_GROUPformat.
Quoted 8 lines
With this format the data are returned for the whole group and there's no way to find out what ID belongs to our fd (if we are not group leader event).
Adding a simple ioctl that returns event primary ID for given fd.
Signed-off-by Jiri Olsa <[email protected]>Cc Arnaldo Carvalho de Melo <[email protected]>
Quoted 45 lines
Cc Ingo Molnar <[email protected]>Cc Paul Mackerras <[email protected]>Cc Corey Ashford <[email protected]>Cc Frederic Weisbecker <[email protected]>Cc Namhyung Kim <[email protected]>--- include/uapi/linux/perf_event.h | 1 + kernel/events/core.c | 9 +++++++++ 2 files changed, 10 insertions(+)include/uapi/linux/perf_event.h +1
-0@@ -316,6 +316,7 @@ struct perf_event_attr {#define PERF_EVENT_IOC_PERIOD _IOW('$', 4, __u64)#define PERF_EVENT_IOC_SET_OUTPUT _IO ('$', 5)#define PERF_EVENT_IOC_SET_FILTER _IOW('$', 6, char *) +#define PERF_EVENT_IOC_ID _IOR('$', 7, u64 *)enum perf_event_ioc_flags {PERF_IOC_FLAG_GROUP =1U <<0 ,kernel/events/core.c +9
-0@@ -3277,6 +3277,15 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)case PERF_EVENT_IOC_PERIOD :return perf_event_period (event, (u64 __user *)arg); +case PERF_EVENT_IOC_ID : + { +u64 id =primary_event_id (event); + +if (copy_to_user ((void __user *)arg, &id,sizeof (id))) +return -EFAULT ; +return 0 ; + } +case PERF_EVENT_IOC_SET_OUTPUT : {int ret;Signature · 1 line
1.7.11.7
PATCH 3/11 perf: Do not get values from disabled counters in group format read
In reply to Jiri OlsaFrom: "[email protected]" <[email protected]>
It's possible some of the counters in the group could be disabled when sampling member of the event group is reading the rest via PERF_SAMPLE_READ sample type processing. Disabled counters could then produce wrong numbers.
Fixing that by reading only enabled counters for PERF_SAMPLE_READ sample type processing.
--- kernel/events/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
kernel/events/core.c +2 -1
@@ -4018,7 +4018,8 @@ static void perf_output_read_group(struct perf_output_handle *handle,list_for_each_entry (sub, &leader->sibling_list, group_entry) { n =0 ; -if (sub != event) +if ((sub != event) && + (sub->state ==PERF_EVENT_STATE_ACTIVE )) sub->pmu->read (sub); values[n++] =perf_event_count (sub);
Signature · 1 line
1.7.11.7
Re: [PATCH 03/11] perf: Do not get values from disabled counters in group format read
Quoted 7 lines · Jiri Olsa
From: "[email protected]" <[email protected]>
It's possible some of the counters in the group could be disabled when sampling member of the event group is reading the rest via
PERF_SAMPLE_READsample type processing. Disabled counters could then produce wrong numbers.
Quoted 5 lines
Fixing that by reading only enabled counters for
PERF_SAMPLE_READsample type processing.Signed-off-by Jiri Olsa <[email protected]>Cc Arnaldo Carvalho de Melo <[email protected]>
I had to like re-read our previous thread on this; which I think says that the Changelog isn't perfect. However:
Quoted 26 lines
Cc Ingo Molnar <[email protected]>Cc Paul Mackerras <[email protected]>Cc Corey Ashford <[email protected]>Cc Frederic Weisbecker <[email protected]>Cc Namhyung Kim <[email protected]>--- kernel/events/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)kernel/events/core.c +2
-1@@ -4018,7 +4018,8 @@ static void perf_output_read_group(struct perf_output_handle *handle,list_for_each_entry (sub, &leader->sibling_list, group_entry) { n =0 ; -if (sub != event) +if ((sub != event) && + (sub->state ==PERF_EVENT_STATE_ACTIVE )) sub->pmu->read (sub); values[n++] =perf_event_count (sub);Signature · 1 line
1.7.11.7
PATCH 4/11 perf tools: Use PERF_EVENT_IOC_ID perf ioctl to read event id
In reply to Jiri OlsaChanging the way we retrieve the event ID. Instead of parsing out the ID out of the read data, using the PERF_EVENT_IOC_ID ioctl.
Keeping the old way in place to support kernels without PERF_EVENT_IOC_ID ioctl support.
This will be useful for retrieving the event ID for events with PERF_FORMAT_GROUP read format set, where it's impossible to get correct event id out of the read call data.
--- tools/perf/util/evlist.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-)
tools/perf/util/evlist.c +15 -1
@@ -298,6 +298,17 @@ static int perf_evlist__id_add_fd(struct perf_evlist *evlist, {u64 read_data[4 ] = {0 , };int id_idx =1 ;/* The first entry is the counter value */ +u64 id; +int ret; + + ret =ioctl (fd,PERF_EVENT_IOC_ID , &id); +if (!ret) + goto add; + +if (errno !=ENOTTY ) +return -1 ; + +/* Legacy way to get event id.. All hail to old kernels! */ if (!(evsel->attr.read_format &PERF_FORMAT_ID ) ||read (fd, &read_data,sizeof (read_data)) ==-1 )
@@ -308,7 +319,10 @@ static int perf_evlist__id_add_fd(struct perf_evlist *evlist,if (evsel->attr.read_format &PERF_FORMAT_TOTAL_TIME_RUNNING ) ++id_idx; -perf_evlist__id_add (evlist, evsel, cpu, thread, read_data[id_idx]); + id = read_data[id_idx]; + + add: +perf_evlist__id_add (evlist, evsel, cpu, thread, id);return 0 ; }
Signature · 1 line
1.7.11.7
PATCH 5/11 perf tools: Add support for parsing PERF_SAMPLE_READ sample type
In reply to Jiri OlsaAdding support to parse out the PERF_SAMPLE_READ sample bits. The code contains both single and group format specification.
This code parse out and prepare PERF_SAMPLE_READ data into the perf_sample struct. It will be used for group leader sampling feature comming in shortly.
--- tools/perf/util/event.h | 18 ++++++++++++++++++ tools/perf/util/evlist.c | 27 +++++++++++++++++++++++++++ tools/perf/util/evlist.h | 2 ++ tools/perf/util/evsel.c | 30 ++++++++++++++++++++++++++++-- tools/perf/util/session.c | 38 ++++++++++++++++++++++++++++++++++++++ 5 files changed, 113 insertions(+), 2 deletions(-)
tools/perf/util/event.h +18 -0
@@ -80,6 +80,23 @@ struct stack_dump {char *data; }; +struct sample_read_value { +u64 value; +u64 id; +}; + +struct sample_read { +u64 time_enabled; +u64 time_running; +union { +struct { +u64 nr; +struct sample_read_value *values; + } group; +struct sample_read_value one; + }; +}; +struct perf_sample {u64 ip;u32 pid, tid;
@@ -95,6 +112,7 @@ struct perf_sample {struct branch_stack *branch_stack;struct regs_dump user_regs;struct stack_dump user_stack; +struct sample_read read; };struct build_id_event {
tools/perf/util/evlist.c +27 -0
@@ -674,6 +674,33 @@ u64 perf_evlist__sample_type(struct perf_evlist *evlist)return first->attr.sample_type; } +bool perf_evlist__valid_read_format (struct perf_evlist *evlist) +{ +struct perf_evsel *first =perf_evlist__first (evlist), *pos = first; +u64 read_format = first->attr.read_format; +u64 sample_type = first->attr.sample_type; + +list_for_each_entry_continue (pos, &evlist->entries, node) { +if (read_format != pos->attr.read_format) +return false; + } + +/* PERF_SAMPLE_READ imples PERF_FORMAT_ID. */ +if ((sample_type &PERF_SAMPLE_READ ) && + !(read_format &PERF_FORMAT_ID )) { +pr_err ("Wrong format type for sample read type.\n" ); +return false; + } + +return true; +} + +u64 perf_evlist__read_format (struct perf_evlist *evlist) +{ +struct perf_evsel *first =perf_evlist__first (evlist); +return first->attr.read_format; +} +u16 perf_evlist__id_hdr_size (struct perf_evlist *evlist) {struct perf_evsel *first =perf_evlist__first (evlist);
tools/perf/util/evlist.h +2 -0
@@ -111,6 +111,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist);void __perf_evlist__set_leader (struct list_head *list);void perf_evlist__set_leader (struct perf_evlist *evlist); +u64 perf_evlist__read_format (struct perf_evlist *evlist);u64 perf_evlist__sample_type (struct perf_evlist *evlist);bool perf_evlist__sample_id_all (struct perf_evlist *evlist);u16 perf_evlist__id_hdr_size (struct perf_evlist *evlist);
@@ -120,6 +121,7 @@ int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *evenbool perf_evlist__valid_sample_type (struct perf_evlist *evlist);bool perf_evlist__valid_sample_id_all (struct perf_evlist *evlist); +bool perf_evlist__valid_read_format (struct perf_evlist *evlist); void perf_evlist__splice_list_tail(struct perf_evlist *evlist, struct list_head *list,
tools/perf/util/evsel.c +28 -2
@@ -1084,8 +1084,34 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, }if (type &PERF_SAMPLE_READ ) { -fprintf (stderr,"PERF_SAMPLE_READ is unsupported for now\n" ); -return -1 ; +u64 read_format = evsel->attr.read_format; + +if (read_format &PERF_FORMAT_GROUP ) + data->read.group.nr = *array; +else + data->read.one.value = *array; + + array++; + +if (read_format &PERF_FORMAT_TOTAL_TIME_ENABLED ) { + data->read.time_enabled = *array; + array++; + } + +if (read_format &PERF_FORMAT_TOTAL_TIME_RUNNING ) { + data->read.time_running = *array; + array++; + } + +/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ +if (read_format &PERF_FORMAT_GROUP ) { + data->read.group.values = (struct sample_read_value *) array; + array = (void *) array + data->read.group.nr * +sizeof (struct sample_read_value ); + }else { + data->read.one.id = *array; + array++; + } }if (type &PERF_SAMPLE_CALLCHAIN ) {
tools/perf/util/session.c +38 -0
@@ -73,6 +73,11 @@ static int perf_session__open(struct perf_session *self, bool force) goto out_close; } +if (!perf_evlist__valid_read_format (self->evlist)) { +pr_err ("non matching read_format" ); + goto out_close; + } + self->size = input_stat.st_size;return 0 ;
@@ -757,6 +762,36 @@ static void perf_session__print_tstamp(struct perf_session *session,printf ("%" PRIu64" " , sample->time); } +static void sample_read__printf (struct perf_sample *sample,u64 read_format) +{ +printf ("... sample_read:\n" ); + +if (read_format &PERF_FORMAT_TOTAL_TIME_ENABLED ) +printf ("...... time enabled %016" PRIx64"\n" , + sample->read.time_enabled); + +if (read_format &PERF_FORMAT_TOTAL_TIME_RUNNING ) +printf ("...... time running %016" PRIx64"\n" , + sample->read.time_running); + +if (read_format &PERF_FORMAT_GROUP ) { +u64 i; + +printf (".... group nr %" PRIu64"\n" , sample->read.group.nr); + +for (i =0 ; i < sample->read.group.nr; i++) { +struct sample_read_value *value; + + value = &sample->read.group.values[i]; +printf ("..... id %016" PRIx64 +", value %016" PRIx64"\n" , + value->id, value->value); + } + }else +printf ("..... id %016" PRIx64", value %016" PRIx64"\n" , + sample->read.one.id, sample->read.one.value); +} +static void dump_event (struct perf_session *session,union perf_event *event,u64 file_offset,struct perf_sample *sample) {
@@ -800,6 +835,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,if (sample_type &PERF_SAMPLE_STACK_USER )stack_user__printf (&sample->user_stack); + +if (sample_type &PERF_SAMPLE_READ ) +sample_read__printf (sample, evsel->attr.read_format); } static struct machine *
Signature · 1 line
1.7.11.7
PATCH 6/11 perf tools: Fix event ID retrieval for group format read case
In reply to Jiri OlsaFrom: "[email protected]" <[email protected]>
We need to fail the event ID retrieval in case both following conditions are true:
- we are on kernel with no PERF_EVENT_IOC_ID support
- PERF_FORMAT_GROUP read format is set
The PERF_FORMAT_GROUP read format bit is the killer for retrieving event ID out of the read syscall, because we have no guarantee of the event placement within leader kernel sibling list.
--- tools/perf/util/evlist.c | 9 +++++++++ 1 file changed, 9 insertions(+)
tools/perf/util/evlist.c +9 -0
@@ -310,6 +310,15 @@ static int perf_evlist__id_add_fd(struct perf_evlist *evlist,/* Legacy way to get event id.. All hail to old kernels! */ +/* +* This way does not work with group format read, so bail +* out in that case. +*/ +if (perf_evlist__read_format (evlist) &PERF_FORMAT_GROUP ) { +pr_err ("No kernel support for ':S' group modifier\n" ); +return -1 ; + } +if (!(evsel->attr.read_format &PERF_FORMAT_ID ) ||read (fd, &read_data,sizeof (read_data)) ==-1 )return -1 ;
Signature · 1 line
1.7.11.7
PATCH 7/11 perf tools: Add perf_evlist__id2sid function to get event ID related data
In reply to Jiri OlsaAdding perf_evlist__id2sid function to be able to get ID related data. This will be helpful for PERF_FORMAT_GROUP samples where we need to store ID related period value for each event.
--- tools/perf/util/evlist.c | 21 ++++++++++++++++----- tools/perf/util/evlist.h | 2 ++ 2 files changed, 18 insertions(+), 5 deletions(-)
tools/perf/util/evlist.c +16 -5
@@ -335,22 +335,33 @@ static int perf_evlist__id_add_fd(struct perf_evlist *evlist,return 0 ; } -struct perf_evsel *perf_evlist__id2evsel (struct perf_evlist *evlist,u64 id) +struct perf_sample_id *perf_evlist__id2sid (struct perf_evlist *evlist,u64 id) {struct hlist_head *head;struct hlist_node *pos;struct perf_sample_id *sid;int hash; -if (evlist->nr_entries ==1 ) -return perf_evlist__first (evlist); - hash =hash_64 (id,PERF_EVLIST__HLIST_BITS ); head = &evlist->heads[hash];hlist_for_each_entry (sid, pos, head, node)if (sid->id == id) -return sid->evsel; +return sid; + +return NULL ; +} + +struct perf_evsel *perf_evlist__id2evsel (struct perf_evlist *evlist,u64 id) +{ +struct perf_sample_id *sid; + +if (evlist->nr_entries ==1 ) +return perf_evlist__first (evlist); + + sid =perf_evlist__id2sid (evlist, id); +if (sid) +return sid->evsel;if (!perf_evlist__sample_id_all (evlist))return perf_evlist__first (evlist);
tools/perf/util/evlist.h +2 -0
@@ -73,6 +73,8 @@ void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);struct perf_evsel *perf_evlist__id2evsel (struct perf_evlist *evlist,u64 id); +struct perf_sample_id *perf_evlist__id2sid (struct perf_evlist *evlist,u64 id); +union perf_event *perf_evlist__mmap_read (struct perf_evlist *self,int idx);int perf_evlist__open (struct perf_evlist *evlist);
Signature · 1 line
1.7.11.7
PATCH 8/11 perf tools: Add PERF_SAMPLE_READ sample related processing
In reply to Jiri OlsaFor sample with sample type PERF_SAMPLE_READ the period value is stored in the 'struct sample_read'.
Moreover if the read format has PERF_FORMAT_GROUP, the 'struct sample_read' contains period values for all events in the group (for which the sample's event is a leader).
We deliver separated samples for all the values contained within the 'struct sample_read'.
--- tools/perf/util/evsel.h | 3 ++ tools/perf/util/session.c | 72 ++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 74 insertions(+), 1 deletion(-)
tools/perf/util/evsel.h +3 -0
@@ -37,6 +37,9 @@ struct perf_sample_id {struct hlist_node node;u64 id;struct perf_evsel *evsel; + +/* Holds total ID period value for PERF_SAMPLE_READ processing. */ +u64 period; };/** struct perf_evsel - event selector
tools/perf/util/session.c +71 -1
84 lines not on this page · raw message
Signature · 1 line
1.7.11.7
PATCH 9/11 perf tools: Add 'S' event/group modifier to read sample value
In reply to Jiri OlsaAdding 'S' event/group modifier to specify that the event value/s are read by PERF_SAMPLE_READ sample type processing, instead of the period value offered by lower layers.
There's additional behaviour change for 'S' modifier being specified on event group:
Currently all the events within a group makes samples. If user now specifies 'S' within group modifier, only the leader will trigger samples. The rest of events in the group will have sampling disabled.
And same as for single events, values of all events within the group (including leader) are read by PERF_SAMPLE_READ sample type processing.
Following example will create event group with cycles and cache-misses events, setting the cycles as group leader and the only event to actually sample. Both cycles and cache-misses event period values are read by PERF_SAMPLE_READ sample type processing with PERF_FORMAT_GROUP read format.
Example:
$ perf record -e '{cycles,cache-misses}:S' ls
...
$ perf report --group --show-total-period --stdio
...
# Samples: 36 of event 'anon group { cycles, cache-misses }'
# Event count (approx.): 12585593
#
# Overhead Period Command Shared Object Symbol
# ................ ........................ ....... ................. ..........................
#
19.92% 1.20% 2505936 31 ls [kernel.kallsyms] [k] mark_held_locks
13.74% 0.47% 1729327 12 ls [kernel.kallsyms] [k] sched_clock_local
13.64% 23.72% 1716147 612 ls ld-2.14.90.so [.] check_match.10805
13.12% 23.22% 1650778 599 ls libc-2.14.90.so [.] _nl_intern_locale_data
11.24% 29.19% 1414554 753 ls [kernel.kallsyms] [k] sched_clock_cpu
8.50% 0.35% 1070150 9 ls [kernel.kallsyms] [k] check_chain_key
...--- tools/perf/Documentation/perf-list.txt | 1 + tools/perf/util/evsel.c | 29 +++++++++++++++++++++++++++++ tools/perf/util/evsel.h | 1 + tools/perf/util/parse-events.c | 8 +++++++- tools/perf/util/parse-events.l | 2 +- 5 files changed, 39 insertions(+), 2 deletions(-)
tools/perf/Documentation/perf-list.txt +1 -0
@@ -29,6 +29,7 @@ counted. The following modifiers exist: G - guest counting (in KVM guests) H - host counting (not in KVM guests) p - precise level + S - read sample value (PERF_SAMPLE_READ) The 'p' modifier can be used for specifying how precise the instruction address should be. The 'p' modifier can be specified multiple times:
tools/perf/util/evsel.c +29 -0
@@ -490,6 +490,7 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)void perf_evsel__config (struct perf_evsel *evsel,struct perf_record_opts *opts) { +struct perf_evsel *leader = evsel->leader;struct perf_event_attr *attr = &evsel->attr;int track = !evsel->idx;/* only the first counter needs these */
@@ -499,6 +500,25 @@ void perf_evsel__config(struct perf_evsel *evsel,perf_evsel__set_sample_bit (evsel,IP );perf_evsel__set_sample_bit (evsel,TID ); +if (evsel->sample_read) { +perf_evsel__set_sample_bit (evsel,READ ); + +/* +* We need ID even in case of single event, because +* PERF_SAMPLE_READ process ID specific data. +*/ +perf_evsel__set_sample_id (evsel); + +/* +* Apply group format only if we belong to group +* with more than one members. +*/ +if (leader->nr_members >1 ) { + attr->read_format |=PERF_FORMAT_GROUP ; + attr->inherit =0 ; + } + } +/* * We default some events to a 1 default interval. But keep * it a weak assumption overridable by the user.
@@ -514,6 +534,15 @@ void perf_evsel__config(struct perf_evsel *evsel, } } +/* +* Disable sampling for all group members other +* than leader in case leader 'leads' the sampling. +*/ +if ((leader != evsel) && leader->sample_read) { + attr->sample_freq =0 ; + attr->sample_period =0 ; + } +if (opts->no_samples) attr->sample_freq =0 ;
tools/perf/util/evsel.h +1 -0
@@ -78,6 +78,7 @@ struct perf_evsel {/* parse modifier helper */ int exclude_GH;int nr_members; +int sample_read;struct perf_evsel *leader;char *group_name; };
tools/perf/util/parse-events.c +7 -1
@@ -684,6 +684,7 @@ struct event_modifier {int eG;int precise;int exclude_GH; +int sample_read; }; static int get_event_modifier(struct event_modifier *mod, char *str,
@@ -695,6 +696,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str,int eH = evsel ? evsel->attr.exclude_host :0 ;int eG = evsel ? evsel->attr.exclude_guest :0 ;int precise = evsel ? evsel->attr.precise_ip :0 ; +int sample_read =0 ;int exclude = eu | ek | eh;int exclude_GH = evsel ? evsel->exclude_GH :0 ;
@@ -727,6 +729,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str,/* use of precise requires exclude_guest */ if (!exclude_GH) eG =1 ; + }else if (*str =='S' ) { + sample_read =1 ; }else break ;
@@ -753,6 +757,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str, mod->eG = eG; mod->precise = precise; mod->exclude_GH = exclude_GH; + mod->sample_read = sample_read;return 0 ; }
@@ -765,7 +770,7 @@ static int check_modifier(char *str)char *p = str;/* The sizeof includes 0 byte as well. */ -if (strlen (str) > (sizeof ("ukhGHppp" ) -1 )) +if (strlen (str) > (sizeof ("ukhGHpppS" ) -1 ))return -1 ;while (*p) {
@@ -803,6 +808,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add) evsel->attr.exclude_host = mod.eH; evsel->attr.exclude_guest = mod.eG; evsel->exclude_GH = mod.exclude_GH; + evsel->sample_read = mod.sample_read; }return 0 ;
tools/perf/util/parse-events.l +1 -1
@@ -82,7 +82,7 @@ num_hex 0x[a-fA-F0-9]+ num_raw_hex [a-fA-F0-9]+ name [a-zA-Z_*?][a-zA-Z0-9_*?]* name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?]* -modifier_event [ukhpGH]+ +modifier_event [ukhpGHS]+ modifier_bp [rwx]{1,3} %%
Signature · 1 line
1.7.11.7
PATCH 10/11 perf tests: Add attr record group sampling test
In reply to Jiri OlsaAdding test to validate perf_event_attr data for command:
'record -e '{cycles,cache-misses}:S'
--- tools/perf/tests/attr/test-record-group-sampling | 36 ++++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 tools/perf/tests/attr/test-record-group-sampling
tools/perf/tests/attr/test-record-group-sampling new file +36 -0
@@ -0,0 +1,36 @@ +[config] +command = record +args = -e '{cycles,cache-misses}:S' kill >/dev/null 2>&1 + +[event-1:base-record] +fd=1 +group_fd=-1 +sample_type=343 +read_format=12 +inherit=0 + +[event-2:base-record] +fd=2 +group_fd=1 + +# cache-misses +type=0 +config=3 + +# default | PERF_SAMPLE_READ +sample_type=343 + +# PERF_FORMAT_ID | PERF_FORMAT_GROUP +read_format=12 + +mmap=0 +comm=0 +enable_on_exec=0 +disabled=0 + +# inherit is disabled for group sampling +inherit=0 + +# sampling disabled +sample_freq=0 +sample_period=0
Signature · 1 line
1.7.11.7
PATCH 11/11 perf tests: Add parse events tests for leader sampling
In reply to Jiri OlsaAdding 2 more tests to the automated parse events suite for following event config:
'{cycles,cache-misses,branch-misses}:S'
'{instructions,branch-misses}:Su'
--- tools/perf/tests/parse-events.c | 115 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 115 insertions(+)
tools/perf/tests/parse-events.c +115 -0
@@ -528,6 +528,7 @@ static int test__group1(struct perf_evlist *evlist)TEST_ASSERT_VAL ("wrong leader" ,perf_evsel__is_group_leader (evsel));TEST_ASSERT_VAL ("wrong nr_members" , evsel->nr_members ==2 );TEST_ASSERT_VAL ("wrong group_idx" ,perf_evsel__group_idx (evsel) ==0 ); +TEST_ASSERT_VAL ("wrong sample_read" , !evsel->sample_read);/* cycles:upp */ evsel =perf_evsel__next (evsel);
@@ -543,6 +544,7 @@ static int test__group1(struct perf_evlist *evlist)TEST_ASSERT_VAL ("wrong precise_ip" , evsel->attr.precise_ip ==2 );TEST_ASSERT_VAL ("wrong leader" , evsel->leader == leader);TEST_ASSERT_VAL ("wrong group_idx" ,perf_evsel__group_idx (evsel) ==1 ); +TEST_ASSERT_VAL ("wrong sample_read" , !evsel->sample_read);return 0 ; }
@@ -568,6 +570,7 @@ static int test__group2(struct perf_evlist *evlist)TEST_ASSERT_VAL ("wrong leader" ,perf_evsel__is_group_leader (evsel));TEST_ASSERT_VAL ("wrong nr_members" , evsel->nr_members ==2 );TEST_ASSERT_VAL ("wrong group_idx" ,perf_evsel__group_idx (evsel) ==0 ); +TEST_ASSERT_VAL ("wrong sample_read" , !evsel->sample_read);/* cache-references + :u modifier */ evsel =perf_evsel__next (evsel);
@@ -582,6 +585,7 @@ static int test__group2(struct perf_evlist *evlist)TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->attr.precise_ip);TEST_ASSERT_VAL ("wrong leader" , evsel->leader == leader);TEST_ASSERT_VAL ("wrong group_idx" ,perf_evsel__group_idx (evsel) ==1 ); +TEST_ASSERT_VAL ("wrong sample_read" , !evsel->sample_read);/* cycles:k */ evsel =perf_evsel__next (evsel);
@@ -595,6 +599,7 @@ static int test__group2(struct perf_evlist *evlist)TEST_ASSERT_VAL ("wrong exclude host" , !evsel->attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->attr.precise_ip);TEST_ASSERT_VAL ("wrong leader" ,perf_evsel__is_group_leader (evsel)); +TEST_ASSERT_VAL ("wrong sample_read" , !evsel->sample_read);return 0 ; }
@@ -623,6 +628,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) !strcmp(leader->group_name, "group1"));TEST_ASSERT_VAL ("wrong nr_members" , evsel->nr_members ==2 );TEST_ASSERT_VAL ("wrong group_idx" ,perf_evsel__group_idx (evsel) ==0 ); +TEST_ASSERT_VAL ("wrong sample_read" , !evsel->sample_read);/* group1 cycles:kppp */ evsel =perf_evsel__next (evsel);
@@ -639,6 +645,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong leader" , evsel->leader == leader);TEST_ASSERT_VAL ("wrong group name" , !evsel->group_name);TEST_ASSERT_VAL ("wrong group_idx" ,perf_evsel__group_idx (evsel) ==1 ); +TEST_ASSERT_VAL ("wrong sample_read" , !evsel->sample_read);/* group2 cycles + G modifier */ evsel = leader =perf_evsel__next (evsel);
@@ -656,6 +663,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused) !strcmp(leader->group_name, "group2"));TEST_ASSERT_VAL ("wrong nr_members" , evsel->nr_members ==2 );TEST_ASSERT_VAL ("wrong group_idx" ,perf_evsel__group_idx (evsel) ==0 ); +TEST_ASSERT_VAL ("wrong sample_read" , !evsel->sample_read);/* group2 1:3 + G modifier */ evsel =perf_evsel__next (evsel);
@@ -669,6 +677,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->attr.precise_ip);TEST_ASSERT_VAL ("wrong leader" , evsel->leader == leader);TEST_ASSERT_VAL ("wrong group_idx" ,perf_evsel__group_idx (evsel) ==1 ); +TEST_ASSERT_VAL ("wrong sample_read" , !evsel->sample_read);/* instructions:u */ evsel =perf_evsel__next (evsel);
@@ -682,6 +691,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong exclude host" , !evsel->attr.exclude_host);TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->attr.precise_ip);TEST_ASSERT_VAL ("wrong leader" ,perf_evsel__is_group_leader (evsel)); +TEST_ASSERT_VAL ("wrong sample_read" , !evsel->sample_read);return 0 ; }
@@ -709,6 +719,7 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong leader" ,perf_evsel__is_group_leader (evsel));TEST_ASSERT_VAL ("wrong nr_members" , evsel->nr_members ==2 );TEST_ASSERT_VAL ("wrong group_idx" ,perf_evsel__group_idx (evsel) ==0 ); +TEST_ASSERT_VAL ("wrong sample_read" , !evsel->sample_read);/* instructions:kp + p */ evsel =perf_evsel__next (evsel);
@@ -724,6 +735,7 @@ static int test__group4(struct perf_evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong precise_ip" , evsel->attr.precise_ip ==2 );TEST_ASSERT_VAL ("wrong leader" , evsel->leader == leader);TEST_ASSERT_VAL ("wrong group_idx" ,perf_evsel__group_idx (evsel) ==1 ); +TEST_ASSERT_VAL ("wrong sample_read" , !evsel->sample_read);return 0 ; }
@@ -750,6 +762,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong leader" ,perf_evsel__is_group_leader (evsel));TEST_ASSERT_VAL ("wrong nr_members" , evsel->nr_members ==2 );TEST_ASSERT_VAL ("wrong group_idx" ,perf_evsel__group_idx (evsel) ==0 ); +TEST_ASSERT_VAL ("wrong sample_read" , !evsel->sample_read);/* instructions + G */ evsel =perf_evsel__next (evsel);
@@ -764,6 +777,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->attr.precise_ip);TEST_ASSERT_VAL ("wrong leader" , evsel->leader == leader);TEST_ASSERT_VAL ("wrong group_idx" ,perf_evsel__group_idx (evsel) ==1 ); +TEST_ASSERT_VAL ("wrong sample_read" , !evsel->sample_read);/* cycles:G */ evsel = leader =perf_evsel__next (evsel);
@@ -780,6 +794,7 @@ static int test__group5(struct perf_evlist *evlist __maybe_unused)TEST_ASSERT_VAL ("wrong leader" ,perf_evsel__is_group_leader (evsel));TEST_ASSERT_VAL ("wrong nr_members" , evsel->nr_members ==2 );TEST_ASSERT_VAL ("wrong group_idx" ,perf_evsel__group_idx (evsel) ==0 ); +TEST_ASSERT_VAL ("wrong sample_read" , !evsel->sample_read);/* instructions:G */ evsel =perf_evsel__next (evsel);
@@ -971,6 +986,98 @@ static int test__group_gh4(struct perf_evlist *evlist)return 0 ; } +static int test__leader_sample1 (struct perf_evlist *evlist) +{ +struct perf_evsel *evsel, *leader; + +TEST_ASSERT_VAL ("wrong number of entries" ,3 == evlist->nr_entries); + +/* cycles - sampling group leader */ + evsel = leader =perf_evlist__first (evlist); +TEST_ASSERT_VAL ("wrong type" ,PERF_TYPE_HARDWARE == evsel->attr.type); +TEST_ASSERT_VAL ("wrong config" , +PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config); +TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->attr.exclude_user); +TEST_ASSERT_VAL ("wrong exclude_kernel" , !evsel->attr.exclude_kernel); +TEST_ASSERT_VAL ("wrong exclude_hv" , !evsel->attr.exclude_hv); +TEST_ASSERT_VAL ("wrong exclude guest" , evsel->attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude host" , !evsel->attr.exclude_host); +TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->attr.precise_ip); +TEST_ASSERT_VAL ("wrong group name" , !evsel->group_name); +TEST_ASSERT_VAL ("wrong leader" , evsel->leader == leader); +TEST_ASSERT_VAL ("wrong sample_read" , evsel->sample_read); + +/* cache-misses - not sampling */ + evsel =perf_evsel__next (evsel); +TEST_ASSERT_VAL ("wrong type" ,PERF_TYPE_HARDWARE == evsel->attr.type); +TEST_ASSERT_VAL ("wrong config" , +PERF_COUNT_HW_CACHE_MISSES == evsel->attr.config); +TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->attr.exclude_user); +TEST_ASSERT_VAL ("wrong exclude_kernel" , !evsel->attr.exclude_kernel); +TEST_ASSERT_VAL ("wrong exclude_hv" , !evsel->attr.exclude_hv); +TEST_ASSERT_VAL ("wrong exclude guest" , evsel->attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude host" , !evsel->attr.exclude_host); +TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->attr.precise_ip); +TEST_ASSERT_VAL ("wrong leader" , evsel->leader == leader); +TEST_ASSERT_VAL ("wrong sample_read" , evsel->sample_read); + +/* branch-misses - not sampling */ + evsel =perf_evsel__next (evsel); +TEST_ASSERT_VAL ("wrong type" ,PERF_TYPE_HARDWARE == evsel->attr.type); +TEST_ASSERT_VAL ("wrong config" , +PERF_COUNT_HW_BRANCH_MISSES == evsel->attr.config); +TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->attr.exclude_user); +TEST_ASSERT_VAL ("wrong exclude_kernel" , !evsel->attr.exclude_kernel); +TEST_ASSERT_VAL ("wrong exclude_hv" , !evsel->attr.exclude_hv); +TEST_ASSERT_VAL ("wrong exclude guest" , evsel->attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude host" , !evsel->attr.exclude_host); +TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->attr.precise_ip); +TEST_ASSERT_VAL ("wrong group name" , !evsel->group_name); +TEST_ASSERT_VAL ("wrong leader" , evsel->leader == leader); +TEST_ASSERT_VAL ("wrong sample_read" , evsel->sample_read); + +return 0 ; +} + +static int test__leader_sample2 (struct perf_evlist *evlist__maybe_unused ) +{ +struct perf_evsel *evsel, *leader; + +TEST_ASSERT_VAL ("wrong number of entries" ,2 == evlist->nr_entries); + +/* instructions - sampling group leader */ + evsel = leader =perf_evlist__first (evlist); +TEST_ASSERT_VAL ("wrong type" ,PERF_TYPE_HARDWARE == evsel->attr.type); +TEST_ASSERT_VAL ("wrong config" , +PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config); +TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->attr.exclude_user); +TEST_ASSERT_VAL ("wrong exclude_kernel" , evsel->attr.exclude_kernel); +TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->attr.exclude_hv); +TEST_ASSERT_VAL ("wrong exclude guest" , evsel->attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude host" , !evsel->attr.exclude_host); +TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->attr.precise_ip); +TEST_ASSERT_VAL ("wrong group name" , !evsel->group_name); +TEST_ASSERT_VAL ("wrong leader" , evsel->leader == leader); +TEST_ASSERT_VAL ("wrong sample_read" , evsel->sample_read); + +/* branch-misses - not sampling */ + evsel =perf_evsel__next (evsel); +TEST_ASSERT_VAL ("wrong type" ,PERF_TYPE_HARDWARE == evsel->attr.type); +TEST_ASSERT_VAL ("wrong config" , +PERF_COUNT_HW_BRANCH_MISSES == evsel->attr.config); +TEST_ASSERT_VAL ("wrong exclude_user" , !evsel->attr.exclude_user); +TEST_ASSERT_VAL ("wrong exclude_kernel" , evsel->attr.exclude_kernel); +TEST_ASSERT_VAL ("wrong exclude_hv" , evsel->attr.exclude_hv); +TEST_ASSERT_VAL ("wrong exclude guest" , evsel->attr.exclude_guest); +TEST_ASSERT_VAL ("wrong exclude host" , !evsel->attr.exclude_host); +TEST_ASSERT_VAL ("wrong precise_ip" , !evsel->attr.precise_ip); +TEST_ASSERT_VAL ("wrong group name" , !evsel->group_name); +TEST_ASSERT_VAL ("wrong leader" , evsel->leader == leader); +TEST_ASSERT_VAL ("wrong sample_read" , evsel->sample_read); + +return 0 ; +} +static int count_tracepoints (void ) {char events_path[PATH_MAX ];
@@ -1187,6 +1294,14 @@ static struct evlist_test test__events[] = { .name = "{cycles:G,cache-misses:H}:uG", .check = test__group_gh4, }, + [38] = { + .name = "{cycles,cache-misses,branch-misses}:S", + .check = test__leader_sample1, + }, + [39] = { + .name = "{instructions,branch-misses}:Su", + .check = test__leader_sample2, + }, }; static struct evlist_test test__events_pmu[] = {
Signature · 1 line
1.7.11.7
Quoted 33 lines · Jiri Olsa
hi,
adding support to read sample values through thePERF_SAMPLE_READsample type. It's now possible to specify 'S' modifier for an event and get its sample value byPERF_SAMPLE_READ.For group the 'S' modifier will enable sampling only for the leader and read all the group member by
PERF_SAMPLE_READsmple type withPERF_FORMAT_GROUPread format.This was first introduced in here:
https://lkml.org/lkml/2012/10/20/75Example:
$ perf record -e '{cycles,cache-misses}:S' ls ... $ perf report --group --show-total-period --stdio ... # Samples: 36 of event 'anon group { cycles, cache-misses }' # Event count (approx.): 12585593 # # Overhead Period Command Shared Object Symbol # ................ ........................ ....... ................. .......................... # 19.92% 1.20% 2505936 31 ls [kernel.kallsyms] [k] mark_held_locks 13.74% 0.47% 1729327 12 ls [kernel.kallsyms] [k] sched_clock_local 13.64% 23.72% 1716147 612 ls ld-2.14.90.so [.] check_match.10805 13.12% 23.22% 1650778 599 ls libc-2.14.90.so [.] _nl_intern_locale_data 11.24% 29.19% 1414554 753 ls [kernel.kallsyms] [k] sched_clock_cpu 8.50% 0.35% 1070150 9 ls [kernel.kallsyms] [k] check_chain_key ...
Quoted 6 lines
The patchset is based on following fix:
http://lkml.org/lkml/2013/2/4/122and is available also at:
git://git.kernel.org/pub/scm/linux/kernel/git/jolsa/linux.git
perf/group6
For the whole series:
Thanks,
Namhyung