From: "Liang, Kan" <kan.liang@linux.intel.com>
To: Andi Kleen <ak@linux.intel.com>, Greg KH <greg@kroah.com>
Cc: peterz@infradead.org, mingo@redhat.com,
linux-kernel@vger.kernel.org, eranian@google.com,
namhyung@kernel.org, acme@kernel.org, jolsa@redhat.com
Subject: Re: [PATCH 2/7] perf: Create a symlink for a PMU
Date: Fri, 25 Jun 2021 11:03:18 -0400 [thread overview]
Message-ID: <c3ffcdd4-fabb-38fd-6ccd-3497389f94ec@linux.intel.com> (raw)
In-Reply-To: <e670abe2-67b9-a602-410a-0c4170796ec7@linux.intel.com>
On 6/25/2021 10:49 AM, Andi Kleen wrote:
>
>> Device names will change, that's always a given, as the kernel can never
>> always make them the same. That's why userspace needs to scan the bus
>> for all devices and then pick out the one that it wants to look at.
>
> In perf the tool doesn't normally know what devices (= pmu) the users
> want to look at. It's all specified on the command line depending on
> what events you want to measure. There's no way for the tool to figure
> that out on its own.
>
>
>> Don't hard-encode device names into userspace tools, that way lies
>> madness.
>
> There's no hard coding in the tools (or at least not for the non json
> event list case). It all comes from the command line. But that is where
> the problem comes from.
>
>>
>>> Anyways thinking about it if Greg doesn't want symlinks (even though
>>> sysfs
>>> already has symlinks elsewhere), maybe we could just create two devices
>>> without symlinks. Kan, do you think that would work?
>> Do not have 2 different structures represent the same hardware device,
>> that too is a shortcut to madness.
>>
>> What prevents userspace from handling device names changing today? Why
>> are you forcing userspace to pick a specific device name at all?
>
> The way the perf tool works is that you have to specify the names on the
> command line:
>
> perf stat -a -e uncore_cha/event=1/ ...
>
> With the numeric identifiers it would be
>
> perf stat -a -e uncore_type_X_Y/event=1/
>
> The tool handles it all abstractly.
>
> So yes the user tools itself can handle it. But the problem is that it
> is directly exposed to the users, so the users would need to change all
> their scripts when switching between the two cases. That is what we're
> trying to avoid -- provide them a way that works on both.
>
We have an attribute "caps/pmu_name" for the core PMU. Maybe we should
add it for uncore PMU as well. For example,
$ cat /sys/devices/uncore_type_0_0/caps/pmu_name
cha_0
Userspace tool can get clues about what type_0_0 is.
Thanks,
Kan
next prev parent reply other threads:[~2021-06-25 15:04 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-24 1:22 [PATCH 0/7] perf: Add Sapphire Rapids server uncore support kan.liang
2021-06-24 1:22 ` [PATCH 1/7] driver core: Add a way to get to bus devices kset kan.liang
2021-06-24 5:41 ` Greg KH
2021-06-24 1:22 ` [PATCH 2/7] perf: Create a symlink for a PMU kan.liang
2021-06-24 5:48 ` Greg KH
2021-06-24 14:24 ` Andi Kleen
2021-06-24 14:29 ` Greg KH
2021-06-24 15:24 ` Andi Kleen
2021-06-24 15:31 ` Greg KH
2021-06-24 17:07 ` Liang, Kan
2021-06-24 17:35 ` Greg KH
2021-06-24 17:49 ` Andi Kleen
2021-06-25 5:18 ` Greg KH
2021-06-25 5:17 ` Greg KH
2021-06-24 17:28 ` Andi Kleen
2021-06-25 5:19 ` Greg KH
2021-06-25 14:22 ` Andi Kleen
2021-06-25 14:38 ` Greg KH
2021-06-25 14:49 ` Andi Kleen
2021-06-25 15:03 ` Liang, Kan [this message]
2021-06-25 15:44 ` Andi Kleen
2021-06-25 15:57 ` Liang, Kan
2021-06-25 16:18 ` Liang, Kan
2021-06-27 11:02 ` Greg KH
2021-06-27 16:30 ` Andi Kleen
2021-06-28 6:55 ` Greg KH
2021-06-28 15:00 ` Andi Kleen
2021-06-24 1:22 ` [PATCH 3/7] perf/x86/intel/uncore: Create a symlink for an uncore PMU kan.liang
2021-06-24 5:44 ` Greg KH
2021-06-24 1:22 ` [PATCH 4/7] perf/x86/intel/uncore: Add Sapphire Rapids server support kan.liang
2021-06-24 1:22 ` [PATCH 5/7] perf/x86/intel/uncore: Factor out snr_uncore_mmio_map() kan.liang
2021-06-24 1:22 ` [PATCH 6/7] perf/x86/intel/uncore: Support free-running counters on Sapphire Rapids server kan.liang
2021-06-24 1:22 ` [PATCH 7/7] perf/x86/intel/uncore: Fix invalid unit check kan.liang
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=c3ffcdd4-fabb-38fd-6ccd-3497389f94ec@linux.intel.com \
--to=kan.liang@linux.intel.com \
--cc=acme@kernel.org \
--cc=ak@linux.intel.com \
--cc=eranian@google.com \
--cc=greg@kroah.com \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
/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).