From: "Jin, Yao" <yao.jin@linux.intel.com>
To: Arnaldo Carvalho de Melo <acme@kernel.org>, kan.liang@linux.intel.com
Cc: peterz@infradead.org, mingo@kernel.org,
linux-kernel@vger.kernel.org, tglx@linutronix.de, bp@alien8.de,
namhyung@kernel.org, jolsa@redhat.com, ak@linux.intel.com,
alexander.shishkin@linux.intel.com, adrian.hunter@intel.com,
"Jin, Yao" <yao.jin@intel.com>
Subject: Re: [PATCH 43/49] perf stat: Add default hybrid events
Date: Tue, 9 Feb 2021 08:36:36 +0800 [thread overview]
Message-ID: <1c87bd51-949c-cc3e-2726-8da5d504eb16@linux.intel.com> (raw)
In-Reply-To: <20210208191011.GO920417@kernel.org>
Hi Arnaldo,
On 2/9/2021 3:10 AM, Arnaldo Carvalho de Melo wrote:
> Em Mon, Feb 08, 2021 at 07:25:40AM -0800, kan.liang@linux.intel.com escreveu:
>> From: Jin Yao <yao.jin@linux.intel.com>
>>
>> Previously if '-e' is not specified in perf stat, some software events
>> and hardware events are added to evlist by default.
>>
>> root@otcpl-adl-s-2:~# ./perf stat -- ./triad_loop
>>
>> Performance counter stats for './triad_loop':
>>
>> 109.43 msec task-clock # 0.993 CPUs utilized
>> 1 context-switches # 0.009 K/sec
>> 0 cpu-migrations # 0.000 K/sec
>> 105 page-faults # 0.960 K/sec
>> 401,161,982 cycles # 3.666 GHz
>> 1,601,216,357 instructions # 3.99 insn per cycle
>> 200,217,751 branches # 1829.686 M/sec
>> 14,555 branch-misses # 0.01% of all branches
>>
>> 0.110176860 seconds time elapsed
>>
>> Among the events, cycles, instructions, branches and branch-misses
>> are hardware events.
>>
>> One hybrid platform, two events are created for one hardware event.
>>
>> core cycles,
>> atom cycles,
>> core instructions,
>> atom instructions,
>> core branches,
>> atom branches,
>> core branch-misses,
>> atom branch-misses
>>
>> These events will be added to evlist in order on hybrid platform
>> if '-e' is not set.
>>
>> 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:
>> root@otcpl-adl-s-2:~# ./perf stat -vv -- taskset -c 16 ./triad_loop
>> ...
>> ------------------------------------------------------------
>> perf_event_attr:
>> type 1
>> size 120
>> config 0x1
>> sample_type IDENTIFIER
>> read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
>> disabled 1
>> inherit 1
>> enable_on_exec 1
>> exclude_guest 1
>> ------------------------------------------------------------
>> sys_perf_event_open: pid 27954 cpu -1 group_fd -1 flags 0x8 = 3
>> ------------------------------------------------------------
>> perf_event_attr:
>> type 1
>> size 120
>> config 0x3
>> sample_type IDENTIFIER
>> read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
>> disabled 1
>> inherit 1
>> enable_on_exec 1
>> exclude_guest 1
>> ------------------------------------------------------------
>> sys_perf_event_open: pid 27954 cpu -1 group_fd -1 flags 0x8 = 4
>> ------------------------------------------------------------
>> perf_event_attr:
>> type 1
>> size 120
>> config 0x4
>> sample_type IDENTIFIER
>> read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
>> disabled 1
>> inherit 1
>> enable_on_exec 1
>> exclude_guest 1
>> ------------------------------------------------------------
>> sys_perf_event_open: pid 27954 cpu -1 group_fd -1 flags 0x8 = 5
>> ------------------------------------------------------------
>> perf_event_attr:
>> type 1
>> size 120
>> config 0x2
>> sample_type IDENTIFIER
>> read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
>> disabled 1
>> inherit 1
>> enable_on_exec 1
>> exclude_guest 1
>> ------------------------------------------------------------
>> sys_perf_event_open: pid 27954 cpu -1 group_fd -1 flags 0x8 = 7
>> ------------------------------------------------------------
>> perf_event_attr:
>> type 6
>> size 120
>> config 0x400000000
>> sample_type IDENTIFIER
>> read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
>> disabled 1
>> inherit 1
>> enable_on_exec 1
>> exclude_guest 1
>> ------------------------------------------------------------
>> sys_perf_event_open: pid 27954 cpu -1 group_fd -1 flags 0x8 = 8
>> ------------------------------------------------------------
>> perf_event_attr:
>> type 6
>> size 120
>> config 0xa00000000
>> sample_type IDENTIFIER
>> read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
>> disabled 1
>> inherit 1
>> enable_on_exec 1
>> exclude_guest 1
>> ------------------------------------------------------------
>> sys_perf_event_open: pid 27954 cpu -1 group_fd -1 flags 0x8 = 9
>> ------------------------------------------------------------
>> perf_event_attr:
>> type 6
>> size 120
>> config 0x400000001
>> sample_type IDENTIFIER
>> read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
>> disabled 1
>> inherit 1
>> enable_on_exec 1
>> exclude_guest 1
>> ------------------------------------------------------------
>> sys_perf_event_open: pid 27954 cpu -1 group_fd -1 flags 0x8 = 10
>> ------------------------------------------------------------
>> perf_event_attr:
>> type 6
>> size 120
>> config 0xa00000001
>> sample_type IDENTIFIER
>> read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
>> disabled 1
>> inherit 1
>> enable_on_exec 1
>> exclude_guest 1
>> ------------------------------------------------------------
>> sys_perf_event_open: pid 27954 cpu -1 group_fd -1 flags 0x8 = 11
>> ------------------------------------------------------------
>> perf_event_attr:
>> type 6
>> size 120
>> config 0x400000004
>> sample_type IDENTIFIER
>> read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
>> disabled 1
>> inherit 1
>> enable_on_exec 1
>> exclude_guest 1
>> ------------------------------------------------------------
>> sys_perf_event_open: pid 27954 cpu -1 group_fd -1 flags 0x8 = 12
>> ------------------------------------------------------------
>> perf_event_attr:
>> type 6
>> size 120
>> config 0xa00000004
>> sample_type IDENTIFIER
>> read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
>> disabled 1
>> inherit 1
>> enable_on_exec 1
>> exclude_guest 1
>> ------------------------------------------------------------
>> sys_perf_event_open: pid 27954 cpu -1 group_fd -1 flags 0x8 = 13
>> ------------------------------------------------------------
>> perf_event_attr:
>> type 6
>> size 120
>> config 0x400000005
>> sample_type IDENTIFIER
>> read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
>> disabled 1
>> inherit 1
>> enable_on_exec 1
>> exclude_guest 1
>> ------------------------------------------------------------
>> sys_perf_event_open: pid 27954 cpu -1 group_fd -1 flags 0x8 = 14
>> ------------------------------------------------------------
>> perf_event_attr:
>> type 6
>> size 120
>> config 0xa00000005
>> sample_type IDENTIFIER
>> read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
>> disabled 1
>> inherit 1
>> enable_on_exec 1
>> exclude_guest 1
>> ------------------------------------------------------------
>> ...
>>
>> Performance counter stats for 'taskset -c 16 ./triad_loop':
>>
>> 201.31 msec task-clock # 0.997 CPUs utilized
>> 1 context-switches # 0.005 K/sec
>> 1 cpu-migrations # 0.005 K/sec
>> 166 page-faults # 0.825 K/sec
>> 623,267,134 cycles # 3096.043 M/sec (0.16%)
>> 603,082,383 cycles # 2995.777 M/sec (99.84%)
>> 406,410,481 instructions # 2018.820 M/sec (0.16%)
>> 1,604,213,375 instructions # 7968.837 M/sec (99.84%)
>> 81,444,171 branches # 404.569 M/sec (0.16%)
>> 200,616,430 branches # 996.550 M/sec (99.84%)
>> 3,769,856 branch-misses # 18.727 M/sec (0.16%)
>> 16,111 branch-misses # 0.080 M/sec (99.84%)
>>
>> 0.201895853 seconds time elapsed
>>
>> We can see two events are created for one hardware event.
>> First one is core event the second one is atom event.
>
> Can we have that (core/atom) as a prefix or in the comment area?
>
In next patch "perf stat: Uniquify hybrid event name", it would tell user the pmu which the event
belongs to.
For example, I run the triad_loop on core cpu,
root@ssp-pwrt-002:# ./perf stat -- taskset -c 0 ./triad_loop
Performance counter stats for 'taskset -c 0 ./triad_loop':
287.87 msec task-clock # 0.990 CPUs utilized
30 context-switches # 0.104 K/sec
1 cpu-migrations # 0.003 K/sec
168 page-faults # 0.584 K/sec
450,089,808 cycles [cpu_core] # 1563.496 M/sec
<not counted> cycles [cpu_atom] (0.00%)
1,602,536,074 instructions [cpu_core] # 5566.797 M/sec
<not counted> instructions [cpu_atom] (0.00%)
200,474,560 branches [cpu_core] # 696.397 M/sec
<not counted> branches [cpu_atom] (0.00%)
23,002 branch-misses [cpu_core] # 0.080 M/sec
<not counted> branch-misses [cpu_atom] (0.00%)
We can see cpu_atom is not counted.
Thanks
Jin Yao
>> One thing 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.
>>
>> Reviewed-by: Andi Kleen <ak@linux.intel.com>
>> Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
>> ---
>> tools/perf/builtin-stat.c | 22 ++++++++++++++++++++++
>> 1 file changed, 22 insertions(+)
>>
>> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
>> index 44d1a5f..0b08665 100644
>> --- a/tools/perf/builtin-stat.c
>> +++ b/tools/perf/builtin-stat.c
>> @@ -1137,6 +1137,13 @@ static int parse_hybrid_type(const struct option *opt,
>> return 0;
>> }
>>
>> +static int add_default_hybrid_events(struct evlist *evlist)
>> +{
>> + struct parse_events_error err;
>> +
>> + return parse_events(evlist, "cycles,instructions,branches,branch-misses", &err);
>> +}
>> +
>> static struct option stat_options[] = {
>> OPT_BOOLEAN('T', "transaction", &transaction_run,
>> "hardware transaction statistics"),
>> @@ -1613,6 +1620,12 @@ static int add_default_attributes(void)
>> { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES },
>>
>> };
>> + struct perf_event_attr default_sw_attrs[] = {
>> + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK },
>> + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES },
>> + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS },
>> + { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS },
>> +};
>>
>> /*
>> * Detailed stats (-d), covering the L1 and last level data caches:
>> @@ -1849,6 +1862,15 @@ static int add_default_attributes(void)
>> }
>>
>> if (!evsel_list->core.nr_entries) {
>> + perf_pmu__scan(NULL);
>> + if (perf_pmu__hybrid_exist()) {
>> + if (evlist__add_default_attrs(evsel_list,
>> + default_sw_attrs) < 0) {
>> + return -1;
>> + }
>> + return add_default_hybrid_events(evsel_list);
>> + }
>> +
>> if (target__has_cpu(&target))
>> default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK;
>>
>> --
>> 2.7.4
>>
>
next prev parent reply other threads:[~2021-02-09 0:38 UTC|newest]
Thread overview: 82+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-08 15:24 [PATCH 00/49] Add Alder Lake support for perf kan.liang
2021-02-08 15:24 ` [PATCH 01/49] x86/cpufeatures: Enumerate Intel Hybrid Technology feature bit kan.liang
2021-02-08 15:24 ` [PATCH 02/49] x86/cpu: Describe hybrid CPUs in cpuinfo_x86 kan.liang
2021-02-08 17:56 ` Borislav Petkov
2021-02-08 19:04 ` Liang, Kan
2021-02-08 19:10 ` Luck, Tony
2021-02-08 19:19 ` Borislav Petkov
2021-02-08 15:25 ` [PATCH 03/49] perf/x86/intel: Hybrid PMU support for perf capabilities kan.liang
2021-02-08 15:25 ` [PATCH 04/49] perf/x86: Hybrid PMU support for intel_ctrl kan.liang
2021-02-08 15:25 ` [PATCH 05/49] perf/x86: Hybrid PMU support for counters kan.liang
2021-02-08 15:25 ` [PATCH 06/49] perf/x86: Hybrid PMU support for unconstrained kan.liang
2021-02-08 15:25 ` [PATCH 07/49] perf/x86: Hybrid PMU support for hardware cache event kan.liang
2021-02-08 15:25 ` [PATCH 08/49] perf/x86: Hybrid PMU support for event constraints kan.liang
2021-02-08 15:25 ` [PATCH 09/49] perf/x86: Hybrid PMU support for extra_regs kan.liang
2021-02-08 15:25 ` [PATCH 10/49] perf/x86/intel: Factor out intel_pmu_check_num_counters kan.liang
2021-02-08 15:25 ` [PATCH 11/49] perf/x86/intel: Factor out intel_pmu_check_event_constraints kan.liang
2021-02-08 15:25 ` [PATCH 12/49] perf/x86/intel: Factor out intel_pmu_check_extra_regs kan.liang
2021-02-08 15:25 ` [PATCH 13/49] perf/x86: Expose check_hw_exists kan.liang
2021-02-08 15:25 ` [PATCH 14/49] perf/x86: Remove temporary pmu assignment in event_init kan.liang
2021-02-08 15:25 ` [PATCH 15/49] perf/x86: Factor out x86_pmu_show_pmu_cap kan.liang
2021-02-08 15:25 ` [PATCH 16/49] perf/x86: Register hybrid PMUs kan.liang
2021-02-08 15:25 ` [PATCH 17/49] perf/x86: Add structures for the attributes of Hybrid PMUs kan.liang
2021-02-08 15:25 ` [PATCH 18/49] perf/x86/intel: Add attr_update for " kan.liang
2021-02-08 15:25 ` [PATCH 19/49] perf/x86: Support filter_match callback kan.liang
2021-02-08 15:25 ` [PATCH 20/49] perf/x86/intel: Add Alder Lake Hybrid support kan.liang
2021-02-08 15:25 ` [PATCH 21/49] perf: Introduce PERF_TYPE_HARDWARE_PMU and PERF_TYPE_HW_CACHE_PMU kan.liang
2021-02-08 15:25 ` [PATCH 22/49] perf/x86/intel/uncore: Add Alder Lake support kan.liang
2021-02-09 4:18 ` kernel test robot
2021-02-08 15:25 ` [PATCH 23/49] perf/x86/msr: Add Alder Lake CPU support kan.liang
2021-02-09 3:58 ` kernel test robot
2021-02-09 13:44 ` Liang, Kan
2021-02-09 5:15 ` kernel test robot
2021-02-08 15:25 ` [PATCH 24/49] perf/x86/cstate: " kan.liang
2021-02-08 15:25 ` [PATCH 25/49] perf/x86/rapl: Add support for Intel Alder Lake kan.liang
2021-02-09 5:16 ` kernel test robot
2021-02-08 15:25 ` [PATCH 26/49] perf jevents: Support unit value "cpu_core" and "cpu_atom" kan.liang
2021-02-08 15:25 ` [PATCH 27/49] perf util: Save pmu name to struct perf_pmu_alias kan.liang
2021-02-08 18:57 ` Arnaldo Carvalho de Melo
2021-02-09 0:17 ` Jin, Yao
2021-02-08 15:25 ` [PATCH 28/49] perf pmu: Save detected hybrid pmus to a global pmu list kan.liang
2021-02-08 18:55 ` Arnaldo Carvalho de Melo
2021-02-09 0:05 ` Jin, Yao
2021-02-08 15:25 ` [PATCH 29/49] perf pmu: Add hybrid helper functions kan.liang
2021-02-08 15:25 ` [PATCH 30/49] perf list: Support --cputype option to list hybrid pmu events kan.liang
2021-02-08 15:25 ` [PATCH 31/49] perf stat: Hybrid evsel uses its own cpus kan.liang
2021-02-08 15:25 ` [PATCH 32/49] perf header: Support HYBRID_TOPOLOGY feature kan.liang
2021-02-08 19:05 ` Arnaldo Carvalho de Melo
2021-02-09 0:26 ` Jin, Yao
2021-02-08 15:25 ` [PATCH 33/49] perf header: Support hybrid CPU_PMU_CAPS kan.liang
2021-02-08 15:25 ` [PATCH 34/49] tools headers uapi: Update tools's copy of linux/perf_event.h kan.liang
2021-02-08 15:25 ` [PATCH 35/49] perf parse-events: Create two hybrid hardware events kan.liang
2021-02-08 18:59 ` Arnaldo Carvalho de Melo
2021-02-09 0:23 ` Jin, Yao
2021-02-08 15:25 ` [PATCH 36/49] perf parse-events: Create two hybrid cache events kan.liang
2021-02-08 15:25 ` [PATCH 37/49] perf parse-events: Support hardware events inside PMU kan.liang
2021-02-08 15:25 ` [PATCH 38/49] perf list: Display pmu prefix for partially supported hybrid cache events kan.liang
2021-02-08 15:25 ` [PATCH 39/49] perf parse-events: Support hybrid raw events kan.liang
2021-02-08 19:07 ` Arnaldo Carvalho de Melo
2021-02-09 0:28 ` Jin, Yao
2021-02-08 15:25 ` [PATCH 40/49] perf stat: Support --cputype option for hybrid events kan.liang
2021-02-08 15:25 ` [PATCH 41/49] perf stat: Support metrics with " kan.liang
2021-02-08 15:25 ` [PATCH 42/49] perf evlist: Create two hybrid 'cycles' events by default kan.liang
2021-02-08 15:25 ` [PATCH 43/49] perf stat: Add default hybrid events kan.liang
2021-02-08 19:10 ` Arnaldo Carvalho de Melo
2021-02-09 0:36 ` Jin, Yao [this message]
2021-02-08 15:25 ` [PATCH 44/49] perf stat: Uniquify hybrid event name kan.liang
2021-02-08 15:25 ` [PATCH 45/49] perf stat: Merge event counts from all hybrid PMUs kan.liang
2021-02-08 15:25 ` [PATCH 46/49] perf stat: Filter out unmatched aggregation for hybrid event kan.liang
2021-02-08 19:16 ` Arnaldo Carvalho de Melo
2021-02-09 0:53 ` Jin, Yao
2021-02-08 15:25 ` [PATCH 47/49] perf evlist: Warn as events from different hybrid PMUs in a group kan.liang
2021-02-08 15:25 ` [PATCH 48/49] perf Documentation: Document intel-hybrid support kan.liang
2021-02-08 15:25 ` [PATCH 49/49] perf evsel: Adjust hybrid event and global event mixed group kan.liang
2021-02-08 19:12 ` Arnaldo Carvalho de Melo
2021-02-09 0:47 ` Jin, Yao
2021-02-11 11:40 ` [PATCH 00/49] Add Alder Lake support for perf Jiri Olsa
2021-02-11 16:22 ` Liang, Kan
2021-02-18 0:07 ` Jin, Yao
2021-03-04 15:50 ` Liang, Kan
2021-03-04 17:50 ` Peter Zijlstra
2021-03-05 11:14 ` Peter Zijlstra
2021-03-05 13:36 ` Liang, Kan
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1c87bd51-949c-cc3e-2726-8da5d504eb16@linux.intel.com \
--to=yao.jin@linux.intel.com \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=bp@alien8.de \
--cc=jolsa@redhat.com \
--cc=kan.liang@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--cc=yao.jin@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).