From: Kevin Hilman <khilman@deeprootsystems.com>
To: Jean Pihet <jean.pihet@newoldbits.com>
Cc: Paul Walmsley <paul@pwsan.com>, Felipe Balbi <balbi@ti.com>,
aaro.koskinen@iki.fi, linux-omap@vger.kernel.org,
linux-arm-kernel@lists.infradead.org
Subject: Re: OMAP baseline test results for v3.7-rc1
Date: Wed, 31 Oct 2012 11:49:58 +0100 [thread overview]
Message-ID: <87fw4u3oh5.fsf@deeprootsystems.com> (raw)
In-Reply-To: <CAORVsuWqoqrza-qrJskpMTj=2MW6JxNEhVzjWVXkM1mpqVO8cQ@mail.gmail.com> (Jean Pihet's message of "Wed, 31 Oct 2012 04:22:11 -0400")
Hi Jean,
Jean Pihet <jean.pihet@newoldbits.com> writes:
[...]
>> Based on a very quick look, I'd say the original patch 3db11fe is broken.
>> I don't see how it can ensure that its PM_QOS_CPU_DMA_LATENCY request is
>> honored when CONFIG_CPU_IDLE=n. CONFIG_CPU_IDLE=n is the default for
>> omap2plus_defconfig.
>
> Withtout CPU_IDLE set the PM QoS has no influence on the power domains states.
Exactly, which means there is *no* constraint set when CPUidle is
disabled, and it's exactly this that is different from the behavior
before your patch.
Before your patch, the constraint would be set whether or not CPUidle
was enabled, correct?
The solution to this will probably be to make OMAPs non-CPUidle idle path
check the constraints.
Kevin
WARNING: multiple messages have this Message-ID (diff)
From: khilman@deeprootsystems.com (Kevin Hilman)
To: linux-arm-kernel@lists.infradead.org
Subject: OMAP baseline test results for v3.7-rc1
Date: Wed, 31 Oct 2012 11:49:58 +0100 [thread overview]
Message-ID: <87fw4u3oh5.fsf@deeprootsystems.com> (raw)
In-Reply-To: <CAORVsuWqoqrza-qrJskpMTj=2MW6JxNEhVzjWVXkM1mpqVO8cQ@mail.gmail.com> (Jean Pihet's message of "Wed, 31 Oct 2012 04:22:11 -0400")
Hi Jean,
Jean Pihet <jean.pihet@newoldbits.com> writes:
[...]
>> Based on a very quick look, I'd say the original patch 3db11fe is broken.
>> I don't see how it can ensure that its PM_QOS_CPU_DMA_LATENCY request is
>> honored when CONFIG_CPU_IDLE=n. CONFIG_CPU_IDLE=n is the default for
>> omap2plus_defconfig.
>
> Withtout CPU_IDLE set the PM QoS has no influence on the power domains states.
Exactly, which means there is *no* constraint set when CPUidle is
disabled, and it's exactly this that is different from the behavior
before your patch.
Before your patch, the constraint would be set whether or not CPUidle
was enabled, correct?
The solution to this will probably be to make OMAPs non-CPUidle idle path
check the constraints.
Kevin
next prev parent reply other threads:[~2012-10-31 10:50 UTC|newest]
Thread overview: 138+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-10-18 5:20 OMAP baseline test results for v3.7-rc1 Paul Walmsley
2012-10-18 5:20 ` Paul Walmsley
2012-10-18 6:48 ` Paul Walmsley
2012-10-18 6:48 ` Paul Walmsley
2012-10-18 8:37 ` Tero Kristo
2012-10-18 8:37 ` Tero Kristo
2012-10-18 8:48 ` Santosh Shilimkar
2012-10-18 8:48 ` Santosh Shilimkar
2012-10-20 17:30 ` Paul Walmsley
2012-10-20 17:30 ` Paul Walmsley
2012-10-19 16:55 ` Paul Walmsley
2012-10-19 16:55 ` Paul Walmsley
2012-10-19 17:01 ` Felipe Balbi
2012-10-19 17:01 ` Felipe Balbi
2012-10-19 17:56 ` Paul Walmsley
2012-10-19 17:56 ` Paul Walmsley
2012-10-19 18:10 ` Felipe Balbi
2012-10-19 18:10 ` Felipe Balbi
2012-10-19 19:03 ` Aaro Koskinen
2012-10-19 19:03 ` Aaro Koskinen
2012-10-19 19:01 ` Felipe Balbi
2012-10-19 19:01 ` Felipe Balbi
2012-10-19 19:38 ` Aaro Koskinen
2012-10-19 19:38 ` Aaro Koskinen
2012-10-22 17:21 ` Kevin Hilman
2012-10-22 17:21 ` Kevin Hilman
2012-10-22 20:43 ` Kevin Hilman
2012-10-22 20:43 ` Kevin Hilman
2012-10-20 6:14 ` Paul Walmsley
2012-10-20 6:14 ` Paul Walmsley
2012-10-22 16:12 ` Jean Pihet
2012-10-22 16:12 ` Jean Pihet
2012-10-22 17:26 ` Jean Pihet
2012-10-22 17:26 ` Jean Pihet
2012-10-23 19:19 ` Paul Walmsley
2012-10-23 19:19 ` Paul Walmsley
2012-10-23 19:23 ` Jean Pihet
2012-10-23 19:23 ` Jean Pihet
2012-10-25 10:12 ` Felipe Balbi
2012-10-25 10:12 ` Felipe Balbi
2012-10-26 20:15 ` Felipe Balbi
2012-10-26 20:15 ` Felipe Balbi
2012-10-26 22:03 ` Paul Walmsley
2012-10-26 22:03 ` Paul Walmsley
2012-10-29 20:00 ` Felipe Balbi
2012-10-29 20:00 ` Felipe Balbi
2012-10-30 12:17 ` Paul Walmsley
2012-10-30 12:17 ` Paul Walmsley
2012-10-30 12:32 ` Felipe Balbi
2012-10-30 12:32 ` Felipe Balbi
2012-10-30 12:50 ` Paul Walmsley
2012-10-30 12:50 ` Paul Walmsley
2012-10-30 12:54 ` Felipe Balbi
2012-10-30 12:54 ` Felipe Balbi
2012-10-30 13:17 ` Paul Walmsley
2012-10-30 13:17 ` Paul Walmsley
2012-10-30 14:04 ` Paul Walmsley
2012-10-30 14:04 ` Paul Walmsley
2012-10-31 8:34 ` Jean Pihet
2012-10-31 8:34 ` Jean Pihet
2012-10-31 9:05 ` Rafael J. Wysocki
2012-10-31 9:05 ` Rafael J. Wysocki
2012-10-31 8:22 ` Jean Pihet
2012-10-31 8:22 ` Jean Pihet
2012-10-31 10:49 ` Kevin Hilman [this message]
2012-10-31 10:49 ` Kevin Hilman
2012-10-31 21:11 ` Jean Pihet
2012-10-31 21:11 ` Jean Pihet
2012-11-01 2:44 ` Paul Walmsley
2012-11-01 2:44 ` Paul Walmsley
2012-11-01 7:51 ` Jean Pihet
2012-11-01 7:51 ` Jean Pihet
2012-11-03 21:39 ` Jean Pihet
2012-11-03 21:39 ` Jean Pihet
2012-11-05 3:15 ` Paul Walmsley
2012-11-05 3:15 ` Paul Walmsley
2012-11-05 9:26 ` Jean Pihet
2012-11-05 9:26 ` Jean Pihet
2012-11-06 0:01 ` Kevin Hilman
2012-11-06 0:01 ` Kevin Hilman
2012-11-06 9:27 ` Jean Pihet
2012-11-06 9:27 ` Jean Pihet
2012-11-06 16:13 ` Paul Walmsley
2012-11-06 16:13 ` Paul Walmsley
2012-11-06 10:06 ` Shubhrajyoti Datta
2012-11-06 10:06 ` Shubhrajyoti Datta
2012-10-30 4:16 ` Paul Walmsley
2012-10-30 4:16 ` Paul Walmsley
2012-10-30 8:54 ` Jean Pihet
2012-10-30 8:54 ` Jean Pihet
2012-10-30 11:23 ` Paul Walmsley
2012-10-30 11:23 ` Paul Walmsley
2012-10-31 8:18 ` Jean Pihet
2012-10-31 8:18 ` Jean Pihet
2012-10-23 19:17 ` Kevin Hilman
2012-10-23 19:17 ` Kevin Hilman
2012-10-23 19:18 ` Paul Walmsley
2012-10-23 19:18 ` Paul Walmsley
2012-10-20 6:24 ` Paul Walmsley
2012-10-20 6:24 ` Paul Walmsley
2012-10-22 17:53 ` Kevin Hilman
2012-10-22 17:53 ` Kevin Hilman
2012-10-22 20:44 ` Kevin Hilman
2012-10-22 20:44 ` Kevin Hilman
2012-10-20 14:11 ` Richard Cochran
2012-10-20 14:11 ` Richard Cochran
2012-10-20 16:27 ` Paul Walmsley
2012-10-20 16:27 ` Paul Walmsley
2012-10-20 18:01 ` Richard Cochran
2012-10-20 18:01 ` Richard Cochran
2012-10-20 18:12 ` Paul Walmsley
2012-10-20 18:12 ` Paul Walmsley
2012-10-20 18:37 ` Richard Cochran
2012-10-20 18:37 ` Richard Cochran
2012-10-20 18:58 ` Paul Walmsley
2012-10-20 18:58 ` Paul Walmsley
2012-10-21 13:51 ` Matt Porter
2012-10-21 13:51 ` Matt Porter
2012-10-21 16:26 ` Paul Walmsley
2012-10-21 16:26 ` Paul Walmsley
2012-10-22 21:56 ` Kevin Hilman
2012-10-22 21:56 ` Kevin Hilman
2012-10-21 7:35 ` Richard Cochran
2012-10-21 7:35 ` Richard Cochran
2012-10-21 8:23 ` Paul Walmsley
2012-10-21 8:23 ` Paul Walmsley
2012-10-21 11:44 ` Richard Cochran
2012-10-21 11:44 ` Richard Cochran
2012-10-21 16:24 ` Paul Walmsley
2012-10-21 16:24 ` Paul Walmsley
2012-10-21 12:29 ` Mohammed, Afzal
2012-10-21 12:29 ` Mohammed, Afzal
2012-10-21 12:36 ` Richard Cochran
2012-10-21 12:36 ` Richard Cochran
2012-10-20 17:20 ` Paul Walmsley
2012-10-20 17:20 ` Paul Walmsley
2012-10-22 16:13 ` Tero Kristo
2012-10-22 16:13 ` Tero Kristo
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=87fw4u3oh5.fsf@deeprootsystems.com \
--to=khilman@deeprootsystems.com \
--cc=aaro.koskinen@iki.fi \
--cc=balbi@ti.com \
--cc=jean.pihet@newoldbits.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-omap@vger.kernel.org \
--cc=paul@pwsan.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 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.