From: Peter Zijlstra <peterz@infradead.org>
To: "Arve Hjønnevåg" <arve@android.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Thomas Gleixner <tglx@linutronix.de>,
"devel@driverdev.osuosl.org" <devel@driverdev.osuosl.org>,
Riley Andrews <riandrews@android.com>,
LKML <linux-kernel@vger.kernel.org>,
Christoph Hellwig <hch@infradead.org>,
Todd Kjos <tkjos@google.com>
Subject: Re: [PATCH] android: binder: Disable preemption while holding the global binder lock
Date: Wed, 14 Sep 2016 09:41:52 +0200 [thread overview]
Message-ID: <20160914074152.GC5020@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <20160914071001.GI5008@twins.programming.kicks-ass.net>
On Wed, Sep 14, 2016 at 09:10:01AM +0200, Peter Zijlstra wrote:
> We could define a meaningful something for CFS and implement that, but
> it isn't currently done.
So the generalization of the Priority Inheritance Protocol is Proxy
Execution Protocol, which basically lets the boosted task run _as_ the
task on the block chain as picked by the schedule function (treating all
of them as runnable). Where 'as' means it really consumes scheduling
resources of the (blocked) donor task.
Since the scheduling function for FIFO is: pick the highest prio one and
go for it, this trivially reduces to PI for FIFO.
Now, Proxy Execution Protocol is 'trivial' to implement on UP, but has a
few wobbles on SMP.
But we can use it to define a sensible definition for a WFQ class
scheduler (like CFS). For these the scheduling function basically runs
the boosted task as every donor task on the block chain gets their slice.
Alternatively, since it treats all 'blocked' tasks as runnable, the
total weight of the boosted task is its own weight plus the sum of
weight on the block chain.
Which is something that shouldn't be too hard to implement, but very
much isn't what happens today.
next prev parent reply other threads:[~2016-09-14 7:42 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-09-08 16:12 [PATCH] android: binder: Disable preemption while holding the global binder lock Todd Kjos
2016-09-08 16:15 ` Todd Kjos
2016-09-08 17:46 ` Greg Kroah-Hartman
2016-09-10 16:16 ` Christoph Hellwig
2016-09-10 16:22 ` Peter Zijlstra
2016-09-10 16:37 ` Thomas Gleixner
2016-09-10 17:28 ` Greg Kroah-Hartman
2016-09-12 15:49 ` Todd Kjos
2016-09-13 3:44 ` Arve Hjønnevåg
2016-09-13 6:42 ` Greg Kroah-Hartman
2016-09-13 19:52 ` Arve Hjønnevåg
2016-09-13 7:32 ` Peter Zijlstra
2016-09-13 19:53 ` Arve Hjønnevåg
2016-09-14 7:10 ` Peter Zijlstra
2016-09-14 7:41 ` Peter Zijlstra [this message]
2016-09-14 13:38 ` Peter Zijlstra
2016-09-14 16:11 ` Peter Zijlstra
2016-09-14 16:13 ` Peter Zijlstra
2016-09-14 16:55 ` Peter Zijlstra
2016-09-17 0:42 ` Todd Kjos
-- strict thread matches above, loose matches on Subject: below --
2016-09-09 15:17 Todd Kjos
2016-09-09 15:44 ` Greg KH
2016-09-09 17:39 ` Todd Kjos
2016-09-10 11:18 ` Greg KH
2016-09-10 11:25 ` Greg KH
2016-09-09 16:37 ` kbuild test robot
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=20160914074152.GC5020@twins.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=arve@android.com \
--cc=devel@driverdev.osuosl.org \
--cc=gregkh@linuxfoundation.org \
--cc=hch@infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=riandrews@android.com \
--cc=tglx@linutronix.de \
--cc=tkjos@google.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