parse_events() may succeed but leave string memory allocations reachable
in the error.
Add an init/exit that must be called to initialize and clean up the
error. This fixes a leak in metricgroup parse_ids.
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20211107090002.3784612-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Group error functions and name after the data type they manipulate.
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20211107090002.3784612-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
An iostate use case like "perf iostat 0000:16,0000:97 -- ls" should be
implemented to work in system-wide mode to ensure that the output from
print_header() is consistent with the user documentation perf-iostat.txt,
rather than incorrectly assuming that the kernel does not support it:
Error:
The sys_perf_event_open() syscall returned with 22 (Invalid argument) \
for event (uncore_iio_0/event=0x83,umask=0x04,ch_mask=0xF,fc_mask=0x07/).
/bin/dmesg | grep -i perf may provide additional information.
This error is easily fixed by assigning system-wide mode by default
for IOSTAT_RUN only when the target cpu_list is unspecified.
Fixes: f07952b179 ("perf stat: Basic support for iostat in perf")
Signed-off-by: Like Xu <likexu@tencent.com>
Cc: Alexander Antonov <alexander.antonov@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20210927081115.39568-1-likexu@tencent.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The cgroup mode should work with cpu events. Warn if --for-each-cgroup
option is used with a task target like existing -G option.
# perf stat --for-each-cgroup . sleep 1
both cgroup and no-aggregation modes only available in system-wide mode
Usage: perf stat [<options>] [<command>]
-G, --cgroup <name> monitor event in cgroup name only
-A, --no-aggr disable CPU count aggregation
-a, --all-cpus system-wide collection from all CPUs
--for-each-cgroup <name>
expand events for each cgroup
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210830170200.55652-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The 'perf record' and 'perf stat' commands have supported the option
'-C/--cpus' to count or collect only on the list of CPUs provided. This
option needs to be supported for hybrid as well.
For hybrid support, it needs to check that the cpu list are available
on hybrid PMU. One example for AlderLake, cpu0-7 is 'cpu_core', cpu8-11
is 'cpu_atom'.
Before:
# perf stat -e cpu_core/cycles/ -C11 -- sleep 1
Performance counter stats for 'CPU(s) 11':
<not supported> cpu_core/cycles/
1.006179431 seconds time elapsed
The 'perf stat' command silently returned "<not supported>" without any
helpful information. It should error out pointing out that that cpu11
was not 'cpu_core'.
After:
# perf stat -e cpu_core/cycles/ -C11 -- sleep 1
WARNING: 11 isn't a 'cpu_core', please use a CPU list in the 'cpu_core' range (0-7)
failed to use cpu list 11
We also need to support the events without pmu prefix specified.
# perf stat -e cycles -C11 -- sleep 1
WARNING: 11 isn't a 'cpu_core', please use a CPU list in the 'cpu_core' range (0-7)
Performance counter stats for 'CPU(s) 11':
1,067,373 cpu_atom/cycles/
1.005544738 seconds time elapsed
The perf tool creates two cycles events automatically, cpu_core/cycles/ and
cpu_atom/cycles/. It checks that cpu11 is not 'cpu_core', then shows a warning
for cpu_core/cycles/ and only count the cpu_atom/cycles/.
If part of cpus are 'cpu_core' and part of cpus are 'cpu_atom', for example,
# perf stat -e cycles -C0,11 -- sleep 1
WARNING: use 0 in 'cpu_core' for 'cycles', skip other cpus in list.
WARNING: use 11 in 'cpu_atom' for 'cycles', skip other cpus in list.
Performance counter stats for 'CPU(s) 0,11':
1,914,704 cpu_core/cycles/
2,036,983 cpu_atom/cycles/
1.005815641 seconds time elapsed
It now automatically selects cpu0 for cpu_core/cycles/, selects cpu11 for
cpu_atom/cycles/, and output with some warnings.
Some more complex examples,
# perf stat -e cycles,instructions -C0,11 -- sleep 1
WARNING: use 0 in 'cpu_core' for 'cycles', skip other cpus in list.
WARNING: use 11 in 'cpu_atom' for 'cycles', skip other cpus in list.
WARNING: use 0 in 'cpu_core' for 'instructions', skip other cpus in list.
WARNING: use 11 in 'cpu_atom' for 'instructions', skip other cpus in list.
Performance counter stats for 'CPU(s) 0,11':
2,780,387 cpu_core/cycles/
1,583,432 cpu_atom/cycles/
3,957,277 cpu_core/instructions/
1,167,089 cpu_atom/instructions/
1.006005124 seconds time elapsed
# perf stat -e cycles,cpu_atom/instructions/ -C0,11 -- sleep 1
WARNING: use 0 in 'cpu_core' for 'cycles', skip other cpus in list.
WARNING: use 11 in 'cpu_atom' for 'cycles', skip other cpus in list.
WARNING: use 11 in 'cpu_atom' for 'cpu_atom/instructions/', skip other cpus in list.
Performance counter stats for 'CPU(s) 0,11':
3,290,301 cpu_core/cycles/
1,953,073 cpu_atom/cycles/
1,407,869 cpu_atom/instructions/
1.006260912 seconds time elapsed
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https //lore.kernel.org/r/20210723063433.7318-4-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The repipe argument is only used by perf inject and the all others
passes 'false'. Let's remove it from the function signature and add
__perf_session__new() to be called from perf inject directly.
This is a preparation of the change the pipe input/output.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210719223153.1618812-2-namhyung@kernel.org
[ Fixed up some trivial conflicts as this patchset fell thru the cracks ;-( ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
On a hybrid platform, by default 'perf stat' aggregates and reports the
event counts per PMU. For example,
# perf stat -e cycles -a true
Performance counter stats for 'system wide':
1,400,445 cpu_core/cycles/
680,881 cpu_atom/cycles/
0.001770773 seconds time elapsed
But for uncore events that's not a suitable method. Uncore has nothing
to do with hybrid. So for uncore events, we aggregate event counts from
all PMUs and report the counts without PMUs.
Before:
# perf stat -e arb/event=0x81,umask=0x1/,arb/event=0x84,umask=0x1/ -a true
Performance counter stats for 'system wide':
2,058 uncore_arb_0/event=0x81,umask=0x1/
2,028 uncore_arb_1/event=0x81,umask=0x1/
0 uncore_arb_0/event=0x84,umask=0x1/
0 uncore_arb_1/event=0x84,umask=0x1/
0.000614498 seconds time elapsed
After:
# perf stat -e arb/event=0x81,umask=0x1/,arb/event=0x84,umask=0x1/ -a true
Performance counter stats for 'system wide':
3,996 arb/event=0x81,umask=0x1/
0 arb/event=0x84,umask=0x1/
0.000630046 seconds time elapsed
Of course, we also keep the '--no-merge' working for uncore events.
# perf stat -e arb/event=0x81,umask=0x1/,arb/event=0x84,umask=0x1/ --no-merge true
Performance counter stats for 'system wide':
1,952 uncore_arb_0/event=0x81,umask=0x1/
1,921 uncore_arb_1/event=0x81,umask=0x1/
0 uncore_arb_0/event=0x84,umask=0x1/
0 uncore_arb_1/event=0x84,umask=0x1/
0.000575536 seconds time elapsed
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210707055652.962-1-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The Topdown Microarchitecture Analysis (TMA) Method is a structured
analysis methodology to identify critical performance bottlenecks in
out-of-order processors.
The Topdown metrics L1 event was added as default in 42641d6f4d
("perf stat: Add Topdown metrics events as default events")
From the Sapphire Rapids server and later platforms, the same dedicated
"metrics" register is extended to support both L1 and L2 events.
Add both L1 and L2 Topdown metrics events as default to enrich the
default measuring information if the new measurement register is
available.
On legacy systems there is no change to avoid extra multiplexing.
The topdown_level indicates the max metrics level for the top-down
statistics. Set it to 2 to display all L1 and L2 Topdown metrics events.
With the patch:
$ perf stat sleep 1
Performance counter stats for 'sleep 1':
0.59 msec task-clock # 0.001 CPUs utilized
1 context-switches # 1.687 K/sec
0 cpu-migrations # 0.000 /sec
76 page-faults # 128.198 K/sec
1,405,318 cycles # 2.371 GHz
1,471,136 instructions # 1.05 insn per cycle
310,132 branches # 523.136 M/sec
10,435 branch-misses # 3.36% of all branches
8,431,908 slots # 14.223 G/sec
1,554,116 topdown-retiring # 18.4% retiring
1,289,585 topdown-bad-spec # 15.2% bad speculation
2,810,636 topdown-fe-bound # 33.2% frontend bound
2,810,636 topdown-be-bound # 33.2% backend bound
231,464 topdown-heavy-ops # 2.7% heavy operations # 15.6% light operations
1,223,453 topdown-br-mispredict # 14.5% branch mispredict # 0.8% machine clears
1,884,779 topdown-fetch-lat # 22.3% fetch latency # 10.9% fetch bandwidth
1,454,917 topdown-mem-bound # 17.2% memory bound # 16.0% Core bound
1.001179699 seconds time elapsed
0.000000000 seconds user
0.001238000 seconds sys
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lore.kernel.org/lkml/1625760169-18396-1-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Move evsel::leader to perf_evsel::leader, so we can move the group
interface to libperf.
Also add several evsel helpers to ease up the transition:
struct evsel *evsel__leader(struct evsel *evsel);
- get leader evsel
bool evsel__has_leader(struct evsel *evsel, struct evsel *leader);
- true if evsel has leader as leader
bool evsel__is_leader(struct evsel *evsel);
- true if evsel is itw own leader
void evsel__set_leader(struct evsel *evsel, struct evsel *leader);
- set leader for evsel
Committer notes:
Fix this when building with 'make BUILD_BPF_SKEL=1'
tools/perf/util/bpf_counter.c
- if (evsel->leader->core.nr_members > 1) {
+ if (evsel->core.leader->nr_members > 1) {
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Requested-by: Shunsuke Nakamura <nakamura.shun@fujitsu.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210706151704.73662-4-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When all events of a perf-stat session use BPF, it is not necessary to
call evlist__enable() and evlist__disable(). Skip them when
all_counters_use_bpf is true.
Signed-off-by: Song Liu <song@kernel.org>
Reported-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
If a group has events which are from different hybrid PMUs,
shows a warning:
"WARNING: events in group from different hybrid PMUs!"
This is to remind the user not to put the core event and atom
event into one group.
Next, just disable grouping.
# perf stat -e "{cpu_core/cycles/,cpu_atom/cycles/}" -a -- sleep 1
WARNING: events in group from different hybrid PMUs!
WARNING: grouped events cpus do not match, disabling group:
anon group { cpu_core/cycles/, cpu_atom/cycles/ }
Performance counter stats for 'system wide':
5,438,125 cpu_core/cycles/
3,914,586 cpu_atom/cycles/
1.004250966 seconds time elapsed
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210427070139.25256-17-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Previously if '-e' is not specified in perf stat, some software events
and hardware events are added to evlist by default.
Before:
# perf stat -a -- sleep 1
Performance counter stats for 'system wide':
24,044.40 msec cpu-clock # 23.946 CPUs utilized
99 context-switches # 4.117 /sec
24 cpu-migrations # 0.998 /sec
3 page-faults # 0.125 /sec
7,000,244 cycles # 0.000 GHz
2,955,024 instructions # 0.42 insn per cycle
608,941 branches # 25.326 K/sec
31,991 branch-misses # 5.25% of all branches
1.004106859 seconds time elapsed
Among the events, cycles, instructions, branches and branch-misses
are hardware events.
One hybrid platform, two hardware events are created for one
hardware event.
cpu_core/cycles/,
cpu_atom/cycles/,
cpu_core/instructions/,
cpu_atom/instructions/,
cpu_core/branches/,
cpu_atom/branches/,
cpu_core/branch-misses/,
cpu_atom/branch-misses/
These events would be added to evlist on hybrid platform.
Since parse_events() has been supported to create two hardware events
for one event on hybrid platform, so we just use parse_events(evlist,
"cycles,instructions,branches,branch-misses") to create the default
events and add them to evlist.
After:
# perf stat -a -- sleep 1
Performance counter stats for 'system wide':
24,043.99 msec cpu-clock # 23.991 CPUs utilized
139 context-switches # 5.781 /sec
25 cpu-migrations # 1.040 /sec
6 page-faults # 0.250 /sec
10,381,751 cpu_core/cycles/ # 431.782 K/sec
1,264,216 cpu_atom/cycles/ # 52.579 K/sec
3,406,958 cpu_core/instructions/ # 141.697 K/sec
414,588 cpu_atom/instructions/ # 17.243 K/sec
705,149 cpu_core/branches/ # 29.327 K/sec
82,358 cpu_atom/branches/ # 3.425 K/sec
40,821 cpu_core/branch-misses/ # 1.698 K/sec
9,086 cpu_atom/branch-misses/ # 377.891 /sec
1.002228863 seconds time elapsed
We can see two events are created for one hardware event.
One TODO is, the shadow stats looks a bit different, now it's just
'M/sec'.
The perf_stat__update_shadow_stats and perf_stat__print_shadow_stats
need to be improved in future if we want to get the original shadow
stats.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210427070139.25256-15-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
It would be useful to let user know the pmu which the event belongs to.
perf-stat has supported '--no-merge' option and it can print the pmu
name after the event name, such as:
"cycles [cpu_core]"
Now this option is enabled by default for hybrid platform but change
the format to:
"cpu_core/cycles/"
If user configs the name, we still use the user specified name.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
ink: https://lore.kernel.org/r/20210427070139.25256-8-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Currently, to use BPF to aggregate perf event counters, the user uses
--bpf-counters option. Enable "use bpf by default" events with a config
option, stat.bpf-counter-events. Events with name in the option will use
BPF.
This also enables mixed BPF event and regular event in the same sesssion.
For example:
perf config stat.bpf-counter-events=instructions
perf stat -e instructions,cs
The second command will use BPF for "instructions" but not "cs".
Signed-off-by: Song Liu <song@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/r/20210425214333.1090950-4-song@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add basic flow for a new iostat mode in perf. Mode is intended to
provide four I/O performance metrics per each PCIe root port: Inbound Read,
Inbound Write, Outbound Read, Outbound Write.
The actual code to compute the metrics and attribute it to
root port is in follow-on patches.
Signed-off-by: Alexander Antonov <alexander.antonov@linux.intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey V Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210419094147.15909-2-alexander.antonov@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The 'perf stat' subcommand supports the request for a summary of the
interval counter readings. But the summary lines break the CSV output
so it's hard for scripts to parse the result.
Before:
# perf stat -x, -I1000 --interval-count 1 --summary
1.001323097,8013.48,msec,cpu-clock,8013483384,100.00,8.013,CPUs utilized
1.001323097,270,,context-switches,8013513297,100.00,0.034,K/sec
1.001323097,13,,cpu-migrations,8013530032,100.00,0.002,K/sec
1.001323097,184,,page-faults,8013546992,100.00,0.023,K/sec
1.001323097,20574191,,cycles,8013551506,100.00,0.003,GHz
1.001323097,10562267,,instructions,8013564958,100.00,0.51,insn per cycle
1.001323097,2019244,,branches,8013575673,100.00,0.252,M/sec
1.001323097,106152,,branch-misses,8013585776,100.00,5.26,of all branches
8013.48,msec,cpu-clock,8013483384,100.00,7.984,CPUs utilized
270,,context-switches,8013513297,100.00,0.034,K/sec
13,,cpu-migrations,8013530032,100.00,0.002,K/sec
184,,page-faults,8013546992,100.00,0.023,K/sec
20574191,,cycles,8013551506,100.00,0.003,GHz
10562267,,instructions,8013564958,100.00,0.51,insn per cycle
2019244,,branches,8013575673,100.00,0.252,M/sec
106152,,branch-misses,8013585776,100.00,5.26,of all branches
The summary line loses the timestamp column, which breaks the CSV
output.
We add a column at the original 'timestamp' position and it just says
'summary' for the summary line.
After:
# perf stat -x, -I1000 --interval-count 1 --summary
1.001196053,8012.72,msec,cpu-clock,8012722903,100.00,8.013,CPUs utilized
1.001196053,218,,context-switches,8012753271,100.00,0.027,K/sec
1.001196053,9,,cpu-migrations,8012769767,100.00,0.001,K/sec
1.001196053,0,,page-faults,8012786257,100.00,0.000,K/sec
1.001196053,15004518,,cycles,8012790637,100.00,0.002,GHz
1.001196053,7954691,,instructions,8012804027,100.00,0.53,insn per cycle
1.001196053,1590259,,branches,8012814766,100.00,0.198,M/sec
1.001196053,82601,,branch-misses,8012824365,100.00,5.19,of all branches
summary,8012.72,msec,cpu-clock,8012722903,100.00,7.986,CPUs utilized
summary,218,,context-switches,8012753271,100.00,0.027,K/sec
summary,9,,cpu-migrations,8012769767,100.00,0.001,K/sec
summary,0,,page-faults,8012786257,100.00,0.000,K/sec
summary,15004518,,cycles,8012790637,100.00,0.002,GHz
summary,7954691,,instructions,8012804027,100.00,0.53,insn per cycle
summary,1590259,,branches,8012814766,100.00,0.198,M/sec
summary,82601,,branch-misses,8012824365,100.00,5.19,of all branches
Now it's easy for script to analyse the summary lines.
Of course, we also consider not to break possible existing scripts which
can continue to use the broken CSV format by using a new '--no-csv-summary.'
option.
# perf stat -x, -I1000 --interval-count 1 --summary --no-csv-summary
1.001213261,8012.67,msec,cpu-clock,8012672327,100.00,8.013,CPUs utilized
1.001213261,197,,context-switches,8012703742,100.00,24.586,/sec
1.001213261,9,,cpu-migrations,8012720902,100.00,1.123,/sec
1.001213261,644,,page-faults,8012738266,100.00,80.373,/sec
1.001213261,18350698,,cycles,8012744109,100.00,0.002,GHz
1.001213261,12745021,,instructions,8012759001,100.00,0.69,insn per cycle
1.001213261,2458033,,branches,8012770864,100.00,306.768,K/sec
1.001213261,102107,,branch-misses,8012781751,100.00,4.15,of all branches
8012.67,msec,cpu-clock,8012672327,100.00,7.985,CPUs utilized
197,,context-switches,8012703742,100.00,24.586,/sec
9,,cpu-migrations,8012720902,100.00,1.123,/sec
644,,page-faults,8012738266,100.00,80.373,/sec
18350698,,cycles,8012744109,100.00,0.002,GHz
12745021,,instructions,8012759001,100.00,0.69,insn per cycle
2458033,,branches,8012770864,100.00,306.768,K/sec
102107,,branch-misses,8012781751,100.00,4.15,of all branches
This option can be enabled in perf config by setting the variable
'stat.no-csv-summary'.
# perf config stat.no-csv-summary=true
# perf config -l
stat.no-csv-summary=true
# perf stat -x, -I1000 --interval-count 1 --summary
1.001330198,8013.28,msec,cpu-clock,8013279201,100.00,8.013,CPUs utilized
1.001330198,205,,context-switches,8013308394,100.00,25.583,/sec
1.001330198,10,,cpu-migrations,8013324681,100.00,1.248,/sec
1.001330198,0,,page-faults,8013340926,100.00,0.000,/sec
1.001330198,8027742,,cycles,8013344503,100.00,0.001,GHz
1.001330198,2871717,,instructions,8013356501,100.00,0.36,insn per cycle
1.001330198,553564,,branches,8013366204,100.00,69.081,K/sec
1.001330198,54021,,branch-misses,8013375952,100.00,9.76,of all branches
8013.28,msec,cpu-clock,8013279201,100.00,7.985,CPUs utilized
205,,context-switches,8013308394,100.00,25.583,/sec
10,,cpu-migrations,8013324681,100.00,1.248,/sec
0,,page-faults,8013340926,100.00,0.000,/sec
8027742,,cycles,8013344503,100.00,0.001,GHz
2871717,,instructions,8013356501,100.00,0.36,insn per cycle
553564,,branches,8013366204,100.00,69.081,K/sec
54021,,branch-misses,8013375952,100.00,9.76,of all branches
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20210319070156.20394-1-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Take measurements of 't0' and 'ref_time' after enable_counters(), so
that they only measure the time consumed when the counters are enabled.
Signed-off-by: Song Liu <songliubraving@fb.com>
Acked-by: Andi Kleen <andi@firstfloor.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: kernel-team@fb.com
Link: http://lore.kernel.org/lkml/20210316211837.910506-3-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The perf tool uses performance monitoring counters (PMCs) to monitor
system performance. The PMCs are limited hardware resources. For
example, Intel CPUs have 3x fixed PMCs and 4x programmable PMCs per cpu.
Modern data center systems use these PMCs in many different ways: system
level monitoring, (maybe nested) container level monitoring, per process
monitoring, profiling (in sample mode), etc. In some cases, there are
more active perf_events than available hardware PMCs. To allow all
perf_events to have a chance to run, it is necessary to do expensive
time multiplexing of events.
On the other hand, many monitoring tools count the common metrics
(cycles, instructions). It is a waste to have multiple tools create
multiple perf_events of "cycles" and occupy multiple PMCs.
bperf tries to reduce such wastes by allowing multiple perf_events of
"cycles" or "instructions" (at different scopes) to share PMUs. Instead
of having each perf-stat session to read its own perf_events, bperf uses
BPF programs to read the perf_events and aggregate readings to BPF maps.
Then, the perf-stat session(s) reads the values from these BPF maps.
Please refer to the comment before the definition of bperf_ops for the
description of bperf architecture.
bperf is off by default. To enable it, pass --bpf-counters option to
perf-stat. bperf uses a BPF hashmap to share information about BPF
programs and maps used by bperf. This map is pinned to bpffs. The
default path is /sys/fs/bpf/perf_attr_map. The user could change the
path with option --bpf-attr-map.
Committer testing:
# dmesg|grep "Performance Events" -A5
[ 0.225277] Performance Events: Fam17h+ core perfctr, AMD PMU driver.
[ 0.225280] ... version: 0
[ 0.225280] ... bit width: 48
[ 0.225281] ... generic registers: 6
[ 0.225281] ... value mask: 0000ffffffffffff
[ 0.225281] ... max period: 00007fffffffffff
#
# for a in $(seq 6) ; do perf stat -a -e cycles,instructions sleep 100000 & done
[1] 2436231
[2] 2436232
[3] 2436233
[4] 2436234
[5] 2436235
[6] 2436236
# perf stat -a -e cycles,instructions sleep 0.1
Performance counter stats for 'system wide':
310,326,987 cycles (41.87%)
236,143,290 instructions # 0.76 insn per cycle (41.87%)
0.100800885 seconds time elapsed
#
We can see that the counters were enabled for this workload 41.87% of
the time.
Now with --bpf-counters:
# for a in $(seq 32) ; do perf stat --bpf-counters -a -e cycles,instructions sleep 100000 & done
[1] 2436514
[2] 2436515
[3] 2436516
[4] 2436517
[5] 2436518
[6] 2436519
[7] 2436520
[8] 2436521
[9] 2436522
[10] 2436523
[11] 2436524
[12] 2436525
[13] 2436526
[14] 2436527
[15] 2436528
[16] 2436529
[17] 2436530
[18] 2436531
[19] 2436532
[20] 2436533
[21] 2436534
[22] 2436535
[23] 2436536
[24] 2436537
[25] 2436538
[26] 2436539
[27] 2436540
[28] 2436541
[29] 2436542
[30] 2436543
[31] 2436544
[32] 2436545
#
# ls -la /sys/fs/bpf/perf_attr_map
-rw-------. 1 root root 0 Mar 23 14:53 /sys/fs/bpf/perf_attr_map
# bpftool map | grep bperf | wc -l
64
#
# bpftool map | tail
1265: percpu_array name accum_readings flags 0x0
key 4B value 24B max_entries 1 memlock 4096B
1266: hash name filter flags 0x0
key 4B value 4B max_entries 1 memlock 4096B
1267: array name bperf_fo.bss flags 0x400
key 4B value 8B max_entries 1 memlock 4096B
btf_id 996
pids perf(2436545)
1268: percpu_array name accum_readings flags 0x0
key 4B value 24B max_entries 1 memlock 4096B
1269: hash name filter flags 0x0
key 4B value 4B max_entries 1 memlock 4096B
1270: array name bperf_fo.bss flags 0x400
key 4B value 8B max_entries 1 memlock 4096B
btf_id 997
pids perf(2436541)
1285: array name pid_iter.rodata flags 0x480
key 4B value 4B max_entries 1 memlock 4096B
btf_id 1017 frozen
pids bpftool(2437504)
1286: array flags 0x0
key 4B value 32B max_entries 1 memlock 4096B
#
# bpftool map dump id 1268 | tail
value (CPU 21):
8f f3 bc ca 00 00 00 00 80 fd 2a d1 4d 00 00 00
80 fd 2a d1 4d 00 00 00
value (CPU 22):
7e d5 64 4d 00 00 00 00 a4 8a 2e ee 4d 00 00 00
a4 8a 2e ee 4d 00 00 00
value (CPU 23):
a7 78 3e 06 01 00 00 00 b2 34 94 f6 4d 00 00 00
b2 34 94 f6 4d 00 00 00
Found 1 element
# bpftool map dump id 1268 | tail
value (CPU 21):
c6 8b d9 ca 00 00 00 00 20 c6 fc 83 4e 00 00 00
20 c6 fc 83 4e 00 00 00
value (CPU 22):
9c b4 d2 4d 00 00 00 00 3e 0c df 89 4e 00 00 00
3e 0c df 89 4e 00 00 00
value (CPU 23):
18 43 66 06 01 00 00 00 5b 69 ed 83 4e 00 00 00
5b 69 ed 83 4e 00 00 00
Found 1 element
# bpftool map dump id 1268 | tail
value (CPU 21):
f2 6e db ca 00 00 00 00 92 67 4c ba 4e 00 00 00
92 67 4c ba 4e 00 00 00
value (CPU 22):
dc 8e e1 4d 00 00 00 00 d9 32 7a c5 4e 00 00 00
d9 32 7a c5 4e 00 00 00
value (CPU 23):
bd 2b 73 06 01 00 00 00 7c 73 87 bf 4e 00 00 00
7c 73 87 bf 4e 00 00 00
Found 1 element
#
# perf stat --bpf-counters -a -e cycles,instructions sleep 0.1
Performance counter stats for 'system wide':
119,410,122 cycles
152,105,479 instructions # 1.27 insn per cycle
0.101395093 seconds time elapsed
#
See? We had the counters enabled all the time.
Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: kernel-team@fb.com
Link: http://lore.kernel.org/lkml/20210316211837.910506-2-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The TMA method level 2 metrics is supported from the Intel Sapphire
Rapids server, which expose four L2 Topdown metrics events to user
space. There are eight L2 events in total. The other four L2 Topdown
metrics events are calculated from the corresponding L1 and the exposed
L2 events.
Now, the --topdown prints the complete top-down metrics that supported
by the CPU. For the Intel Sapphire Rapids server, there are 4 L1 events
and 8 L2 events displyed in one line.
Add a new option, --td-level, to display the top-down statistics that
equal to or lower than the input level.
The L2 event is marked only when both its L1 parent event and itself
crosse the threshold.
Here is an example:
$ perf stat --topdown --td-level=2 --no-metric-only sleep 1
Topdown accuracy may decrease when measuring long periods.
Please print the result regularly, e.g. -I1000
Performance counter stats for 'sleep 1':
16,734,390 slots
2,100,001 topdown-retiring # 12.6% retiring
2,034,376 topdown-bad-spec # 12.3% bad speculation
4,003,128 topdown-fe-bound # 24.1% frontend bound
328,125 topdown-heavy-ops # 2.0% heavy operations # 10.6% light operations
1,968,751 topdown-br-mispredict # 11.9% branch mispredict # 0.4% machine clears
2,953,127 topdown-fetch-lat # 17.8% fetch latency # 6.3% fetch bandwidth
5,906,255 topdown-mem-bound # 35.6% memory bound # 15.4% core bound
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/1612296553-21962-9-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The Topdown Microarchitecture Analysis (TMA) Method is a structured
analysis methodology to identify critical performance bottlenecks in
out-of-order processors. From the Ice Lake and later platforms, the
Topdown information can be retrieved from the dedicated "metrics"
register, which isn't impacted by other events. Also, the Topdown
metrics support both per thread/process and per core measuring. Adding
Topdown metrics events as default events can enrich the default
measuring information, and would not cost any extra multiplexing.
Introduce arch_evlist__add_default_attrs() to allow architecture
specific default events. Add the Topdown metrics events in the X86
specific arch_evlist__add_default_attrs(). Other architectures can add
their own default events later separately.
With the patch:
$ perf stat sleep 1
Performance counter stats for 'sleep 1':
0.82 msec task-clock:u # 0.001 CPUs utilized
0 context-switches:u # 0.000 K/sec
0 cpu-migrations:u # 0.000 K/sec
61 page-faults:u # 0.074 M/sec
319,941 cycles:u # 0.388 GHz
242,802 instructions:u # 0.76 insn per cycle
54,380 branches:u # 66.028 M/sec
4,043 branch-misses:u # 7.43% of all branches
1,585,555 slots:u # 1925.189 M/sec
238,941 topdown-retiring:u # 15.0% retiring
410,378 topdown-bad-spec:u # 25.8% bad speculation
634,222 topdown-fe-bound:u # 39.9% frontend bound
304,675 topdown-be-bound:u # 19.2% backend bound
1.001791625 seconds time elapsed
0.000000000 seconds user
0.001572000 seconds sys
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lore.kernel.org/lkml/20210121133752.118327-1-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add a control 'ping' command to detect if perf is up and its control
interface is operational.
It will be used in following daemon patches to synchronize with record
session - when control interface is up and running, we know that perf
record is monitoring and ready to receive signals.
Example session:
terminal 1:
# mkfifo control ack
# perf record --control=fifo:control,ack
terminal 2:
# echo ping > control
# cat ack
ack
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Budankov <abudankov@huawei.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20201226232038.390883-5-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Adding control 'stop' command to stop perf record.
When it is received, perf will set the 'done' variable to 1 to stop its
mmap ring buffer reading loop.
Example session:
terminal 1:
# mkfifo control ack
# perf record --control=fifo:control,ack
terminal 2:
# echo stop > control
terminal 1:
[ perf record: Woken up 7 times to write data ]
[ perf record: Captured and wrote 3.214 MB perf.data (38280 samples) ]
#
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Budankov <abudankov@huawei.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20201226232038.390883-4-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add a new 'evlist' control command to display all the evlist events.
When it is received, perf will scan and print current evlist into perf
record terminal.
The interface string for control file is:
evlist [-v|-g|-F]
The syntax follows perf evlist command:
-F Show just the sample frequency used for each event.
-v Show all fields.
-g Show event group information.
Example session:
terminal 1:
# mkfifo control ack
# perf record --control=fifo:control,ack -e '{cycles,instructions}'
terminal 2:
# echo evlist > control
terminal 1:
cycles
instructions
dummy:HG
terminal 2:
# echo 'evlist -v' > control
terminal 1:
cycles: size: 120, { sample_period, sample_freq }: 4000, sample_type: \
IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, disabled: 1, inherit: 1, freq: 1, \
sample_id_all: 1, exclude_guest: 1
instructions: size: 120, config: 0x1, { sample_period, sample_freq }: 4000, \
sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, inherit: 1, freq: 1, \
sample_id_all: 1, exclude_guest: 1
dummy:HG: type: 1, size: 120, config: 0x9, { sample_period, sample_freq }: 4000, \
sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, inherit: 1, mmap: 1, \
comm: 1, freq: 1, task: 1, sample_id_all: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, \
bpf_event: 1
terminal 2:
# echo 'evlist -g' > control
terminal 1:
{cycles,instructions}
dummy:HG
terminal 2:
# echo 'evlist -F' > control
terminal 1:
cycles: sample_freq=4000
instructions: sample_freq=4000
dummy:HG: sample_freq=4000
This new evlist command is handy to get real event names when
wildcards are used.
Adding evsel_fprintf.c object to python/perf.so build, because
it's now evlist.c dependency.
Adding PYTHON_PERF define for python/perf.so compilation, so we
can use it to compile in only evsel__fprintf from evsel_fprintf.c
object.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Budankov <abudankov@huawei.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20201226232038.390883-3-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Adding new control events to enable/disable specific event.
The interface string for control file are:
'enable <EVENT NAME>'
'disable <EVENT NAME>'
when received the command, perf will scan the current evlist
for <EVENT NAME> and if found it's enabled/disabled.
Example session:
terminal 1:
# mkfifo control ack perf.pipe
# perf record --control=fifo:control,ack -D -1 --no-buffering -e 'sched:*' -o - > perf.pipe
terminal 2:
# cat perf.pipe | perf --no-pager script -i -
terminal 1:
Events disabled
NOTE Above message will show only after read side of the pipe ('>')
is started on 'terminal 2'. The 'terminal 1's bash does not execute
perf before that, hence the delyaed perf record message.
terminal 3:
# echo 'enable sched:sched_process_fork' > control
terminal 1:
event sched:sched_process_fork enabled
terminal 2:
bash 33349 [034] 149587.674295: sched:sched_process_fork: comm=bash pid=33349 child_comm=bash child_pid=34056
bash 33349 [034] 149588.239521: sched:sched_process_fork: comm=bash pid=33349 child_comm=bash child_pid=34057
terminal 3:
# echo 'enable sched:sched_wakeup_new' > control
terminal 1:
event sched:sched_wakeup_new enabled
terminal 2:
bash 33349 [034] 149632.228023: sched:sched_process_fork: comm=bash pid=33349 child_comm=bash child_pid=34059
bash 33349 [034] 149632.228050: sched:sched_wakeup_new: bash:34059 [120] success=1 CPU:036
bash 33349 [034] 149633.950005: sched:sched_process_fork: comm=bash pid=33349 child_comm=bash child_pid=34060
bash 33349 [034] 149633.950030: sched:sched_wakeup_new: bash:34060 [120] success=1 CPU:036
Committer testing:
If I use 'sched:*' and then enable all events, I can't get 'perf record'
to react to further commands, so I tested it with:
[root@five ~]# perf record --control=fifo:control,ack -D -1 --no-buffering -e 'sched:sched_process_*' -o - > perf.pipe
Events disabled
Events enabled
Events disabled
And then it works as expected, so we need to fix this pre-existing
problem.
Another issue, we need to check if a event is already enabled or
disabled and change the message to be clearer, i.e.:
[root@five ~]# perf record --control=fifo:control,ack -D -1 --no-buffering -e 'sched:sched_process_*' -o - > perf.pipe
Events disabled
If we receive a 'disable' command, then it should say:
[root@five ~]# perf record --control=fifo:control,ack -D -1 --no-buffering -e 'sched:sched_process_*' -o - > perf.pipe
Events disabled
Events already disabled
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Budankov <abudankov@huawei.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20201226232038.390883-2-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Introduce 'perf stat -b' option, which counts events for BPF programs, like:
[root@localhost ~]# ~/perf stat -e ref-cycles,cycles -b 254 -I 1000
1.487903822 115,200 ref-cycles
1.487903822 86,012 cycles
2.489147029 80,560 ref-cycles
2.489147029 73,784 cycles
3.490341825 60,720 ref-cycles
3.490341825 37,797 cycles
4.491540887 37,120 ref-cycles
4.491540887 31,963 cycles
The example above counts 'cycles' and 'ref-cycles' of BPF program of id
254. This is similar to bpftool-prog-profile command, but more
flexible.
'perf stat -b' creates per-cpu perf_event and loads fentry/fexit BPF
programs (monitor-progs) to the target BPF program (target-prog). The
monitor-progs read perf_event before and after the target-prog, and
aggregate the difference in a BPF map. Then the user space reads data
from these maps.
A new 'struct bpf_counter' is introduced to provide a common interface
that uses BPF programs/maps to count perf events.
Committer notes:
Removed all but bpf_counter.h includes from evsel.h, not needed at all.
Also BPF map lookups for PERCPU_ARRAYs need to have as its value receive
buffer passed to the kernel libbpf_num_possible_cpus() entries, not
evsel__nr_cpus(evsel), as the former uses
/sys/devices/system/cpu/possible while the later uses
/sys/devices/system/cpu/online, which may be less than the 'possible'
number making the bpf map lookup overwrite memory and cause hard to
debug memory corruption.
We need to continue using evsel__nr_cpus(evsel) when accessing the
perf_counts array tho, not to overwrite another are of memory :-)
Signed-off-by: Song Liu <songliubraving@fb.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: https://lore.kernel.org/lkml/20210120163031.GU12699@kernel.org/
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: kernel-team@fb.com
Link: http://lore.kernel.org/lkml/20201229214214.3413833-4-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add core as a separate member so that it doesn't have to be packed into
the int value.
Signed-off-by: James Clark <james.clark@arm.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: John Garry <john.garry@huawei.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Link: https://lore.kernel.org/r/20201126141328.6509-12-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add die as a separate member so that it doesn't have to be packed into
the int value.
Signed-off-by: James Clark <james.clark@arm.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: John Garry <john.garry@huawei.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Link: https://lore.kernel.org/r/20201126141328.6509-11-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add socket as a separate member so that it doesn't have to be packed
into the int value.
When the socket ID was larger than 8 bits the output appeared corrupted
or incomplete.
For example, here on ThunderX2 'perf stat' reports a socket of -1 and an
invalid die number:
./perf stat -a --per-die
The socket id number is too big.
Performance counter stats for 'system wide':
S-1-D255 128 687.99 msec cpu-clock # 57.240 CPUs utilized
...
S36-D0 128 842.34 msec cpu-clock # 70.081 CPUs utilized
...
And with --per-core there is an entry with an invalid core ID:
./perf stat record -a --per-core
The socket id number is too big.
Performance counter stats for 'system wide':
S-1-D255-C65535 128 671.04 msec cpu-clock # 54.112 CPUs utilized
...
S36-D0-C0 4 28.27 msec cpu-clock # 2.279 CPUs utilized
...
This fixes the "Session topology" self test on ThunderX2.
After this fix the output contains the correct socket and die IDs and no
longer prints a warning about the size of the socket ID:
./perf stat --per-die -a
Performance counter stats for 'system wide':
S36-D0 128 169,869.39 msec cpu-clock # 127.501 CPUs utilized
...
S3612-D0 128 169,733.05 msec cpu-clock # 127.398 CPUs utilized
Signed-off-by: James Clark <james.clark@arm.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: John Garry <john.garry@huawei.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Link: https://lore.kernel.org/r/20201126141328.6509-10-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add node as a separate member so that it doesn't have to be packed into
the int value.
Signed-off-by: James Clark <james.clark@arm.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: John Garry <john.garry@huawei.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Link: https://lore.kernel.org/r/20201126141328.6509-9-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Use the new cpu_aggr_id struct in the cpu map instead of int so that it
can store more data.
No functional changes.
Signed-off-by: James Clark <james.clark@arm.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: John Garry <john.garry@huawei.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Link: https://lore.kernel.org/r/20201126141328.6509-8-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Replace usages of perf_cpu_map with cpu_aggr map in places that are
involved with 'perf stat' aggregation.
This will then later be changed to be a map of cpu_aggr_id rather than
an int so that more data can be stored.
No functional changes.
Signed-off-by: James Clark <james.clark@arm.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: John Garry <john.garry@huawei.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Link: https://lore.kernel.org/r/20201126141328.6509-7-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Replace all occurences of the usage of int with the new struct
cpu_aggr_id.
No functional changes.
Signed-off-by: James Clark <james.clark@arm.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: John Garry <john.garry@huawei.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Link: https://lore.kernel.org/r/20201126141328.6509-5-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf_evlist__ is for 'struct perf_evlist' methods, in tools/lib/perf/,
go on completing this split.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf_evlist__ is for 'struct perf_evlist' methods, in tools/lib/perf/,
go on completing this split.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf_evlist__ is for 'struct perf_evlist' methods, in tools/lib/perf/,
go on completing this split.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf_evlist__ is for 'struct perf_evlist' methods, in tools/lib/perf/,
go on completing this split.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf_evlist__ is for 'struct perf_evlist' methods, in tools/lib/perf/,
go on completing this split.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf_evlist__ is for 'struct perf_evlist' methods, in tools/lib/perf/,
go on completing this split.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf_evlist__ is for 'struct perf_evlist' methods, in tools/lib/perf/,
go on completing this split.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add a new --quiet option to 'perf stat'. This is useful with 'perf stat
record' to write the data only to the perf.data file, which can lower
measurement overhead because the data doesn't need to be formatted.
On my 4C desktop:
% time ./perf stat record -e $(python -c 'print ",".join(["cycles"]*1000)') -a -I 1000 sleep 5
...
real 0m5.377s
user 0m0.238s
sys 0m0.452s
% time ./perf stat record --quiet -e $(python -c 'print ",".join(["cycles"]*1000)') -a -I 1000 sleep 5
real 0m5.452s
user 0m0.183s
sys 0m0.423s
In this example it cuts the user time by 20%. On systems with more cores
the savings are higher.
Signed-off-by: Andi Kleen <andi@firstfloor.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Link: http://lore.kernel.org/lkml/20201027002737.30942-1-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This is a preparation for a test case of expanding events for multiple
cgroups. Instead of using real system cgroup, the test will use fake
cgroups so it needs a way to have them without a open file descriptor.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20200924124455.336326-5-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The metricgroup__copy_metric_events() is to handle metrics events when
expanding event for cgroups. As the metric events keep pointers to
evsel, it should be refreshed when events are cloned during the
operation.
The perf_stat__collect_metric_expr() is also called in case an event has
a metric directly.
During the copy, it references evsel by index as the evlist now has
cloned evsels for the given cgroup.
Also kernel test robot found an issue in the python module import so add
empty implementations of those two functions to fix it.
Reported-by: kernel test robot <rong.a.chen@intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20200924124455.336326-4-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The --for-each-cgroup option is a syntax sugar to monitor large number
of cgroups easily. Current command line requires to list all the events
and cgroups even if users want to monitor same events for each cgroup.
This patch addresses that usage by copying given events for each cgroup
on user's behalf.
For instance, if they want to monitor 6 events for 200 cgroups each they
should write 1200 event names (with -e) AND 1200 cgroup names (with -G)
on the command line. But with this change, they can just specify 6
events and 200 cgroups with a new option.
A simpler example below: It wants to measure 3 events for 2 cgroups ('A'
and 'B'). The result is that total 6 events are counted like below.
$ perf stat -a -e cpu-clock,cycles,instructions --for-each-cgroup A,B sleep 1
Performance counter stats for 'system wide':
988.18 msec cpu-clock A # 0.987 CPUs utilized
3,153,761,702 cycles A # 3.200 GHz (100.00%)
8,067,769,847 instructions A # 2.57 insn per cycle (100.00%)
982.71 msec cpu-clock B # 0.982 CPUs utilized
3,136,093,298 cycles B # 3.182 GHz (99.99%)
8,109,619,327 instructions B # 2.58 insn per cycle (99.99%)
1.001228054 seconds time elapsed
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20200924124455.336326-3-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Some metrics (such as DRAM_BW_Use) consists of uncore events and
duration_time. For uncore events, counter->core.system_wide is true. But
for duration_time, counter->core.system_wide is false so
target.system_wide is set to false.
Then 'enable_on_exec' is set in perf_event_attr of uncore event. Kernel
will return error when trying to open the uncore event.
This patch skips the duration_time in setup_system_wide then
target.system_wide will be set to true for the evlist of uncore events +
duration_time.
Before (tested on skylake desktop):
# perf stat -M DRAM_BW_Use -- sleep 1
Error:
The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (arb/event=0x84,umask=0x1/).
/bin/dmesg | grep -i perf may provide additional information.
After:
# perf stat -M DRAM_BW_Use -- sleep 1
Performance counter stats for 'system wide':
169 arb/event=0x84,umask=0x1/ # 0.00 DRAM_BW_Use
40,427 arb/event=0x81,umask=0x1/
1,000,902,197 ns duration_time
1.000902197 seconds time elapsed
Fixes: e3ba76deef ("perf tools: Force uncore events to system wide monitoring")
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20200922015004.30114-1-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Icelake has support for reporting per thread TopDown metrics.
These are reported differently than the previous TopDown support,
each metric is standalone, but scaled to pipeline "slots".
We don't need to do anything special for HyperThreading anymore.
Teach perf stat --topdown to handle these new metrics and
print them in the same way as the previous TopDown metrics.
The restrictions of only being able to report information per core is
gone.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Co-developed-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20200911144808.27603-4-kan.liang@linux.intel.com
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The group.h/c only include TopDown group related functions. The name
"group" is too generic and inaccurate. Use the name "topdown" to replace
it.
Move topdown related functions to a dedicated file, topdown.c.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20200911144808.27603-2-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add 'snapshot' control command to create an AUX area tracing snapshot
the same as if sending SIGUSR2. The advantage of the FIFO is that access
is governed by access to the FIFO.
Example:
$ mkfifo perf.control
$ mkfifo perf.ack
$ cat perf.ack &
[1] 15235
$ sudo ~/bin/perf record --control fifo:perf.control,perf.ack -S -e intel_pt//u -- sleep 60 &
[2] 15243
$ ps -e | grep perf
15244 pts/1 00:00:00 perf
$ kill -USR2 15244
bash: kill: (15244) - Operation not permitted
$ echo snapshot > perf.control
ack
$
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Alexey Budankov <alexey.budankov@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lore.kernel.org/lkml/20200901093758.32293-6-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Ian Rogers
Like Xu
Namhyung Kim
Jin Yao
Kan Liang
Jiri Olsa
Song Liu
Alexander Antonov
Song Liu
Ingo Molnar
Jiri Olsa
James Clark
Arnaldo Carvalho de Melo
Andi Kleen
Andi Kleen
Adrian Hunter