* [PATCH] perf stat: Skip duration_time in setup_system_wide @ 2020-09-22 1:50 Jin Yao 2020-09-22 17:56 ` Arnaldo Carvalho de Melo 0 siblings, 1 reply; 4+ messages in thread From: Jin Yao @ 2020-09-22 1:50 UTC (permalink / raw) To: acme, jolsa, peterz, mingo, alexander.shishkin Cc: Linux-kernel, ak, kan.liang, yao.jin, Jin Yao 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: 648b5af3f3ae ("libperf: Move 'system_wide' from 'struct evsel' to 'struct perf_evsel'") Signed-off-by: Jin Yao <yao.jin@linux.intel.com> --- tools/perf/builtin-stat.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 7f8d756d9408..9bcc93bc0973 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -2047,8 +2047,10 @@ static void setup_system_wide(int forks) struct evsel *counter; evlist__for_each_entry(evsel_list, counter) { - if (!counter->core.system_wide) + if (!counter->core.system_wide && + strcmp(counter->name, "duration_time")) { return; + } } if (evsel_list->core.nr_entries) -- 2.17.1 ^ permalink raw reply related [flat|nested] 4+ messages in thread
* Re: [PATCH] perf stat: Skip duration_time in setup_system_wide 2020-09-22 1:50 [PATCH] perf stat: Skip duration_time in setup_system_wide Jin Yao @ 2020-09-22 17:56 ` Arnaldo Carvalho de Melo 2020-09-22 18:02 ` Arnaldo Carvalho de Melo 0 siblings, 1 reply; 4+ messages in thread From: Arnaldo Carvalho de Melo @ 2020-09-22 17:56 UTC (permalink / raw) To: Jin Yao Cc: jolsa, peterz, mingo, alexander.shishkin, Linux-kernel, ak, kan.liang, yao.jin Em Tue, Sep 22, 2020 at 09:50:04AM +0800, Jin Yao escreveu: > 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: 648b5af3f3ae ("libperf: Move 'system_wide' from 'struct evsel' to 'struct perf_evsel'") Humm, what makes you think that this cset was the one introducing this problem? It just moves evsel->system_wide to evsel->core.system_wide. - Arnaldo > Signed-off-by: Jin Yao <yao.jin@linux.intel.com> > --- > tools/perf/builtin-stat.c | 4 +++- > 1 file changed, 3 insertions(+), 1 deletion(-) > > diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c > index 7f8d756d9408..9bcc93bc0973 100644 > --- a/tools/perf/builtin-stat.c > +++ b/tools/perf/builtin-stat.c > @@ -2047,8 +2047,10 @@ static void setup_system_wide(int forks) > struct evsel *counter; > > evlist__for_each_entry(evsel_list, counter) { > - if (!counter->core.system_wide) > + if (!counter->core.system_wide && > + strcmp(counter->name, "duration_time")) { > return; > + } > } > > if (evsel_list->core.nr_entries) > -- > 2.17.1 > -- - Arnaldo ^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] perf stat: Skip duration_time in setup_system_wide 2020-09-22 17:56 ` Arnaldo Carvalho de Melo @ 2020-09-22 18:02 ` Arnaldo Carvalho de Melo 2020-09-23 2:05 ` Jin, Yao 0 siblings, 1 reply; 4+ messages in thread From: Arnaldo Carvalho de Melo @ 2020-09-22 18:02 UTC (permalink / raw) To: Jin Yao Cc: jolsa, peterz, mingo, alexander.shishkin, Linux-kernel, ak, kan.liang, yao.jin Em Tue, Sep 22, 2020 at 02:56:30PM -0300, Arnaldo Carvalho de Melo escreveu: > Em Tue, Sep 22, 2020 at 09:50:04AM +0800, Jin Yao escreveu: > > 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: 648b5af3f3ae ("libperf: Move 'system_wide' from 'struct evsel' to 'struct perf_evsel'") > > Humm, what makes you think that this cset was the one introducing this > problem? It just moves evsel->system_wide to evsel->core.system_wide. Apart from that I reproduced the problem and after applying your patch it seems cured: [acme@quaco perf]$ grep 'model name' -m1 /proc/cpuinfo model name : Intel(R) Core(TM) i7-8650U CPU @ 1.90GHz Before (with -v to see details): [root@quaco ~]# perf stat -v -M DRAM_BW_Use -- sleep 1 Using CPUID GenuineIntel-6-8E-A metric expr 64 * ( arb@event\=0x81\,umask\=0x1@ + arb@event\=0x84\,umask\=0x1@ ) / 1000000 / duration_time / 1000 for DRAM_BW_Use found event duration_time found event arb/event=0x84,umask=0x1/ found event arb/event=0x81,umask=0x1/ adding {arb/event=0x84,umask=0x1/,arb/event=0x81,umask=0x1/}:W,duration_time Control descriptor is not initialized Warning: arb/event=0x84,umask=0x1/ event is not supported by the kernel. 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. [root@quaco ~]# After: [root@quaco ~]# perf stat -M DRAM_BW_Use -- sleep 1 Performance counter stats for 'system wide': 2,806 arb/event=0x84,umask=0x1/ # 0.63 DRAM_BW_Use 10,001,820 arb/event=0x81,umask=0x1/ 1,016,875,686 ns duration_time 1.016875686 seconds time elapsed [root@quaco ~]# So I'm removing that fixes and adding this one, that I think is where "duration_time" was being considered... Fixes: e3ba76deef23064f ("perf tools: Force uncore events to system wide monitoring") Also, wouldn't it be better to have the duration_time event with its evsel->core.system_wide set to true? - Arnaldo ^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] perf stat: Skip duration_time in setup_system_wide 2020-09-22 18:02 ` Arnaldo Carvalho de Melo @ 2020-09-23 2:05 ` Jin, Yao 0 siblings, 0 replies; 4+ messages in thread From: Jin, Yao @ 2020-09-23 2:05 UTC (permalink / raw) To: Arnaldo Carvalho de Melo Cc: jolsa, peterz, mingo, alexander.shishkin, Linux-kernel, ak, kan.liang, yao.jin Hi Arnaldo, On 9/23/2020 2:02 AM, Arnaldo Carvalho de Melo wrote: > Em Tue, Sep 22, 2020 at 02:56:30PM -0300, Arnaldo Carvalho de Melo escreveu: >> Em Tue, Sep 22, 2020 at 09:50:04AM +0800, Jin Yao escreveu: >>> 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: 648b5af3f3ae ("libperf: Move 'system_wide' from 'struct evsel' to 'struct perf_evsel'") >> >> Humm, what makes you think that this cset was the one introducing this >> problem? It just moves evsel->system_wide to evsel->core.system_wide. > > Apart from that I reproduced the problem and after applying your patch > it seems cured: > > [acme@quaco perf]$ grep 'model name' -m1 /proc/cpuinfo > model name : Intel(R) Core(TM) i7-8650U CPU @ 1.90GHz > > Before (with -v to see details): > > [root@quaco ~]# perf stat -v -M DRAM_BW_Use -- sleep 1 > Using CPUID GenuineIntel-6-8E-A > metric expr 64 * ( arb@event\=0x81\,umask\=0x1@ + arb@event\=0x84\,umask\=0x1@ ) / 1000000 / duration_time / 1000 for DRAM_BW_Use > found event duration_time > found event arb/event=0x84,umask=0x1/ > found event arb/event=0x81,umask=0x1/ > adding {arb/event=0x84,umask=0x1/,arb/event=0x81,umask=0x1/}:W,duration_time > Control descriptor is not initialized > Warning: > arb/event=0x84,umask=0x1/ event is not supported by the kernel. > 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. > > [root@quaco ~]# > > After: > > [root@quaco ~]# perf stat -M DRAM_BW_Use -- sleep 1 > > Performance counter stats for 'system wide': > > 2,806 arb/event=0x84,umask=0x1/ # 0.63 DRAM_BW_Use > 10,001,820 arb/event=0x81,umask=0x1/ > 1,016,875,686 ns duration_time > > 1.016875686 seconds time elapsed > > [root@quaco ~]# > > So I'm removing that fixes and adding this one, that I think is where > "duration_time" was being considered... > > Fixes: e3ba76deef23064f ("perf tools: Force uncore events to system wide monitoring") > Yes, this fixes is much better, thanks. > Also, wouldn't it be better to have the duration_time event with its > evsel->core.system_wide set to true? > That looks to be another solution, should be OK too I think. :) But anyway we need a test. Thanks Jin Yao > - Arnaldo > ^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2020-09-23 2:06 UTC | newest] Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed) -- links below jump to the message on this page -- 2020-09-22 1:50 [PATCH] perf stat: Skip duration_time in setup_system_wide Jin Yao 2020-09-22 17:56 ` Arnaldo Carvalho de Melo 2020-09-22 18:02 ` Arnaldo Carvalho de Melo 2020-09-23 2:05 ` Jin, Yao
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).