From: Suzuki.Poulose@arm.com (Suzuki K. Poulose)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH 1/3] arm/pmu: Reject groups spanning multiple hardware PMUs
Date: Tue, 10 Mar 2015 12:00:49 +0000 [thread overview]
Message-ID: <54FEDCF1.7020405@arm.com> (raw)
In-Reply-To: <20150310112723.GY2896@worktop.programming.kicks-ass.net>
On 10/03/15 11:27, Peter Zijlstra wrote:
> On Mon, Mar 09, 2015 at 12:46:30PM +0000, Suzuki K. Poulose wrote:
>> From: "Suzuki K. Poulose" <suzuki.poulose@arm.com>
>>
>> Don't allow grouping hardware events from different PMUs
>> (eg. CCI + CPU).
>
> Uhm, how does this work? If we have multiple hardware PMUs we'll stop
> scheduling events after the first failed event schedule. This can leave
> one of the PMUs severely under utilized.
This is done from pmu->event_init(), where we haven't scheduled an
event yet. Do you think we need to solve it using a different approach
? What is the best way to handle this situation ? Is it OK
to allow different PMUs in the group ?
Suzuki
>
WARNING: multiple messages have this Message-ID (diff)
From: "Suzuki K. Poulose" <Suzuki.Poulose@arm.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <Will.Deacon@arm.com>,
"linux@arm.linux.org.uk" <linux@arm.linux.org.uk>,
"acme@kernel.org" <acme@kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"linux-arm-kernel@lists.infradead.org"
<linux-arm-kernel@lists.infradead.org>,
Punit Agrawal <Punit.Agrawal@arm.com>,
Pawel Moll <Pawel.Moll@arm.com>,
Mark Rutland <Mark.Rutland@arm.com>
Subject: Re: [PATCH 1/3] arm/pmu: Reject groups spanning multiple hardware PMUs
Date: Tue, 10 Mar 2015 12:00:49 +0000 [thread overview]
Message-ID: <54FEDCF1.7020405@arm.com> (raw)
In-Reply-To: <20150310112723.GY2896@worktop.programming.kicks-ass.net>
On 10/03/15 11:27, Peter Zijlstra wrote:
> On Mon, Mar 09, 2015 at 12:46:30PM +0000, Suzuki K. Poulose wrote:
>> From: "Suzuki K. Poulose" <suzuki.poulose@arm.com>
>>
>> Don't allow grouping hardware events from different PMUs
>> (eg. CCI + CPU).
>
> Uhm, how does this work? If we have multiple hardware PMUs we'll stop
> scheduling events after the first failed event schedule. This can leave
> one of the PMUs severely under utilized.
This is done from pmu->event_init(), where we haven't scheduled an
event yet. Do you think we need to solve it using a different approach
? What is the best way to handle this situation ? Is it OK
to allow different PMUs in the group ?
Suzuki
>
next prev parent reply other threads:[~2015-03-10 12:00 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-03-09 12:46 [PATCH 0/3] [4.0] arm/arm64: Do not group hardware events from different PMUs Suzuki K. Poulose
2015-03-09 12:46 ` Suzuki K. Poulose
2015-03-09 12:46 ` [PATCH 1/3] arm/pmu: Reject groups spanning multiple hardware PMUs Suzuki K. Poulose
2015-03-09 12:46 ` Suzuki K. Poulose
2015-03-10 11:27 ` Peter Zijlstra
2015-03-10 11:27 ` Peter Zijlstra
2015-03-10 12:00 ` Suzuki K. Poulose [this message]
2015-03-10 12:00 ` Suzuki K. Poulose
2015-03-10 12:05 ` Mark Rutland
2015-03-10 12:05 ` Mark Rutland
2015-03-10 12:53 ` Peter Zijlstra
2015-03-10 12:53 ` Peter Zijlstra
2015-03-10 13:00 ` Peter Zijlstra
2015-03-10 13:00 ` Peter Zijlstra
2015-03-10 13:57 ` Mark Rutland
2015-03-10 13:57 ` Mark Rutland
2015-03-10 14:05 ` Suzuki K. Poulose
2015-03-10 14:05 ` Suzuki K. Poulose
2015-03-10 15:09 ` Mark Rutland
2015-03-10 15:09 ` Mark Rutland
2015-03-10 15:36 ` Mark Rutland
2015-03-10 15:36 ` Mark Rutland
2015-03-10 15:44 ` Peter Zijlstra
2015-03-10 15:44 ` Peter Zijlstra
2015-03-09 12:46 ` [PATCH 2/3] arm64/pmu: Reject groups spanning multiple HW PMUs Suzuki K. Poulose
2015-03-09 12:46 ` Suzuki K. Poulose
2015-03-09 12:46 ` [PATCH 3/3] arm-cci: " Suzuki K. Poulose
2015-03-09 12:46 ` Suzuki K. Poulose
-- strict thread matches above, loose matches on Subject: below --
2015-03-17 18:14 [PATCHv2 0/3] [4.0] arm/arm64: Do not group hardware events from different PMUs Suzuki K. Poulose
2015-03-17 18:14 ` [PATCH 1/3] arm/pmu: Reject groups spanning multiple hardware PMUs Suzuki K. Poulose
2015-03-09 12:43 [PATCH 0/3] [4.0] arm/arm64: Do not group hardware events from different PMUs a
2015-03-09 12:43 ` [PATCH 1/3] arm/pmu: Reject groups spanning multiple hardware PMUs a
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=54FEDCF1.7020405@arm.com \
--to=suzuki.poulose@arm.com \
--cc=linux-arm-kernel@lists.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.