linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: kajoljain <kjain@linux.ibm.com>
To: Jiri Olsa <jolsa@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	lkml <linux-kernel@vger.kernel.org>,
	Ingo Molnar <mingo@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Michael Petlan <mpetlan@redhat.com>,
	Andi Kleen <ak@linux.intel.com>,
	John Garry <john.garry@huawei.com>,
	"Paul A. Clarke" <pc@us.ibm.com>,
	Stephane Eranian <eranian@google.com>,
	Ian Rogers <irogers@google.com>
Subject: Re: [PATCHv3 00/19] perf metric: Add support to reuse metric
Date: Sun, 26 Jul 2020 14:44:05 +0530	[thread overview]
Message-ID: <906aa237-e300-aaf5-2de3-0041985ae646@linux.ibm.com> (raw)
In-Reply-To: <20200725115143.GA1157288@krava>



On 7/25/20 5:21 PM, Jiri Olsa wrote:
> On Fri, Jul 24, 2020 at 11:22:28AM +0530, kajoljain wrote:
> 
> SNIP
> 
>>
>> Hi Jiri,
>>        The change looks good to me. I tried with adding this patch on top of your perf/metric branch. It did resolve the issue of not printing
>> all chips data. And now I can see proper values for hv-24x7 metric events.
>>
>> I was also trying by adding new metric using the feature added in this patchset with something like this:
>>
>> diff --git a/tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json b/tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json
>> index 8383a37647ad..dfe4bd63b587 100644
>> --- a/tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json
>> +++ b/tools/perf/pmu-events/arch/powerpc/power9/nest_metrics.json
>> @@ -16,6 +16,11 @@
>>          "MetricName": "PowerBUS_Frequency",
>>          "ScaleUnit": "2.5e-7GHz"
>>      },
>> +    {
>> +       "MetricExpr": "Memory_WR_BW_Chip + Memory_RD_BW_Chip",
>> +        "MetricName": "Total_Memory_BW",
>> +        "ScaleUnit": "1.6e-2MB"
>> +    },
> 
> hum, we'll need special case this.. because Memory_WR_BW_Chip will
> unwind to Memory_WR_BW_Chip_[01] and Total_Memory_BW is not aware of
> that.. what's the expected behaviour in here?
> 
> have Total_Memory_BW_[01] for each runtime arg?

Hi Jiri,
    Yes right. So we want Total_Memory_BW to show sum results of both chip 0 and 1 seperately, which is missing here.
> 
> I think this will need to come on top of this changes,
> it's already too big
> 

Yes make sense. We can send separate patches on top of this patch set for this use case. 

Other then that the whole patchset looks good to me with the change to rectify Paul A. Clarke concern.

Tested/Reviewed-By : Kajol Jain<kjain@linux.ibm.com>

Thanks,
Kajol Jain
> thanks,
> jirka
> 
>>
>> I guess as we have dependency on '?' symbol, I am not able to see all chips data for Total_Memory_BW.
>> I am not sure if Its expected behavior?
>>
>> This is what I am getting:
>>
>> [root@ltc-zz189-lp4 perf]# ./perf stat --metric-only -M Total_Memory_BW,Memory_WR_BW_Chip,Memory_RD_BW_Chip -I 1000 -C 0
>> #           time  MB  Total_Memory_BW MB  Memory_RD_BW_Chip_1 MB  Memory_WR_BW_Chip_1 MB  Memory_WR_BW_Chip_0 MB  Memory_RD_BW_Chip_0 
>>      1.000067388                 36.4                      0.2                     36.3                     65.0                     72.1 
>>      2.000374276                 36.2                      0.3                     35.9                     65.4                     77.9 
>>      3.000543202                 36.3                      0.3                     36.0                     68.7                     81.2 
>>      4.000702855                 36.3                      0.3                     36.0                     70.9                     93.3 
>>      5.000856837                 36.0                      0.2                     35.8                     67.4                     81.5 
>> ^C     5.367865273                 13.2                      0.1                     13.1                     23.5                     28.3 
>>  Performance counter stats for 'CPU(s) 0':
>>                194.4                      1.3                    193.1                    361.0                    434.3 
>>        5.368039176 seconds time elapsed
>>
>> We can only get single chip data's sum in Total_Memory_BW. Please let me know if I am missing something.
> 
> SNIP
> 

  reply	other threads:[~2020-07-26  9:14 UTC|newest]

Thread overview: 87+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-19 18:13 [PATCHv3 00/19] perf metric: Add support to reuse metric Jiri Olsa
2020-07-19 18:13 ` [PATCH 01/19] perf metric: Fix memory leak in expr__add_id function Jiri Olsa
2020-07-19 21:41   ` Ian Rogers
2020-07-28 12:26     ` Arnaldo Carvalho de Melo
2020-07-19 18:13 ` [PATCH 02/19] perf metric: Add " Jiri Olsa
2020-07-26  9:16   ` kajoljain
2020-07-28 12:27     ` Arnaldo Carvalho de Melo
2020-07-19 18:13 ` [PATCH 03/19] perf metric: Change expr__get_id to return struct expr_id_data Jiri Olsa
2020-07-26  9:17   ` kajoljain
2020-07-28 12:28     ` Arnaldo Carvalho de Melo
2020-07-19 18:13 ` [PATCH 04/19] perf metric: Add expr__del_id function Jiri Olsa
2020-07-26  9:17   ` kajoljain
2020-07-28 12:28     ` Arnaldo Carvalho de Melo
2020-07-19 18:13 ` [PATCH 05/19] perf metric: Add macros for iterating map events Jiri Olsa
2020-07-19 21:46   ` Ian Rogers
2020-07-28 12:29     ` Arnaldo Carvalho de Melo
2020-07-26  9:17   ` kajoljain
2020-07-19 18:13 ` [PATCH 06/19] perf metric: Add add_metric function Jiri Olsa
2020-07-26  9:17   ` kajoljain
2020-07-28 12:30     ` Arnaldo Carvalho de Melo
2020-07-19 18:13 ` [PATCH 07/19] perf metric: Rename __metricgroup__add_metric to __add_metric Jiri Olsa
2020-07-26  9:18   ` kajoljain
2020-07-28 12:30     ` Arnaldo Carvalho de Melo
2020-07-19 18:13 ` [PATCH 08/19] perf metric: Collect referenced metrics in struct metric_ref_node Jiri Olsa
2020-07-19 22:18   ` Ian Rogers
2020-07-26  9:18     ` kajoljain
2020-07-28 12:31     ` Arnaldo Carvalho de Melo
2020-07-19 18:13 ` [PATCH 09/19] perf metric: Collect referenced metrics in struct metric_expr Jiri Olsa
2020-07-26  9:18   ` kajoljain
2020-07-28 12:32     ` Arnaldo Carvalho de Melo
2020-07-19 18:13 ` [PATCH 10/19] perf metric: Add referenced metrics to hash data Jiri Olsa
2020-07-19 22:32   ` Ian Rogers
2020-07-26  9:18     ` kajoljain
2020-07-28 12:32     ` Arnaldo Carvalho de Melo
2020-07-19 18:13 ` [PATCH 11/19] perf metric: Compute referenced metrics Jiri Olsa
2020-07-26  9:19   ` kajoljain
2020-07-28 12:33     ` Arnaldo Carvalho de Melo
2020-07-19 18:13 ` [PATCH 12/19] perf metric: Add events for the current list Jiri Olsa
2020-07-19 22:34   ` Ian Rogers
2020-07-26  9:19     ` kajoljain
2020-07-28 12:33     ` Arnaldo Carvalho de Melo
2020-07-19 18:13 ` [PATCH 13/19] perf metric: Add cache_miss_cycles to metric parse test Jiri Olsa
2020-07-26  9:19   ` kajoljain
2020-07-28 12:34     ` Arnaldo Carvalho de Melo
2020-07-19 18:13 ` [PATCH 14/19] perf metric: Add DCache_L2 " Jiri Olsa
2020-07-26  9:19   ` kajoljain
2020-07-28 12:34     ` Arnaldo Carvalho de Melo
2020-07-19 18:13 ` [PATCH 15/19] perf metric: Add recursion check when processing nested metrics Jiri Olsa
2020-07-19 22:40   ` Ian Rogers
2020-07-26  9:20     ` kajoljain
2020-07-28 12:35     ` Arnaldo Carvalho de Melo
2020-07-19 18:13 ` [PATCH 16/19] perf metric: Make compute_single function more precise Jiri Olsa
2020-07-28 12:36   ` Arnaldo Carvalho de Melo
2020-07-28 17:26     ` Ian Rogers
2020-07-28 20:17       ` kajoljain
2020-07-29 11:08         ` Arnaldo Carvalho de Melo
2020-07-19 18:13 ` [PATCH 17/19] perf metric: Add metric group test Jiri Olsa
2020-07-19 22:41   ` Ian Rogers
2020-07-26  9:20     ` kajoljain
2020-07-28 12:37     ` Arnaldo Carvalho de Melo
2020-07-19 18:13 ` [PATCH 18/19] perf metric: Rename struct egroup to metric Jiri Olsa
2020-07-26  9:20   ` kajoljain
2020-07-19 18:13 ` [PATCH 19/19] perf metric: Rename group_list to metric_list Jiri Olsa
2020-07-19 22:42   ` Ian Rogers
2020-07-26  9:21   ` kajoljain
2020-07-28 12:38     ` Arnaldo Carvalho de Melo
2020-07-20  6:44 ` [PATCHv3 00/19] perf metric: Add support to reuse metric kajoljain
2020-07-20  7:22   ` Jiri Olsa
2020-07-20  8:09     ` kajoljain
2020-07-20  8:19       ` Jiri Olsa
2020-07-20  9:02         ` kajoljain
2020-07-20 19:16           ` Jiri Olsa
2020-07-24  5:52             ` kajoljain
2020-07-25 11:51               ` Jiri Olsa
2020-07-26  9:14                 ` kajoljain [this message]
2020-07-28 12:39             ` Arnaldo Carvalho de Melo
2020-07-28 12:54               ` Jiri Olsa
2020-07-28 13:01                 ` Jiri Olsa
2020-07-28 13:34                   ` [PATCHv3 20/19] perf metric: Fix runtime metric for powerpc Jiri Olsa
2020-07-28 15:22                   ` [PATCHv3 00/19] perf metric: Add support to reuse metric Arnaldo Carvalho de Melo
2020-07-21 14:48 ` Paul A. Clarke
2020-07-22 18:11   ` Jiri Olsa
2020-07-23 15:59     ` Paul A. Clarke
2020-07-25 11:52       ` Jiri Olsa
2020-07-28 12:42       ` Arnaldo Carvalho de Melo
2020-07-23 17:14     ` Paul A. Clarke
2020-07-23 17:40       ` Andi Kleen

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=906aa237-e300-aaf5-2de3-0041985ae646@linux.ibm.com \
    --to=kjain@linux.ibm.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=acme@kernel.org \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=eranian@google.com \
    --cc=irogers@google.com \
    --cc=john.garry@huawei.com \
    --cc=jolsa@kernel.org \
    --cc=jolsa@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=mpetlan@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=pc@us.ibm.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).