Date: Wed, 9 Mar 2016 13:24:23 +0100
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
To: Josh Cartwright <joshc@ni.com>
Cc: Daniel Wagner <wagi@monom.org>, linux-kernel@vger.kernel.org,
        linux-rt-users@vger.kernel.org,
        "Peter Zijlstra (Intel)" <peterz@infradead.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Daniel Wagner <daniel.wagner@bmw-carit.de>
Subject: Re: [RFC v0] Use swait in completion
Message-ID: <20160309122423.GD10517@linutronix.de>
References: <1457452754-24029-1-git-send-email-wagi@monom.org>
 <20160308175206.GD21842@linutronix.de>
 <20160308182656.GA27081@jcartwri.amer.corp.natinst.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: <20160308182656.GA27081@jcartwri.amer.corp.natinst.com>
User-Agent: Mutt/1.5.21 (2010-09-15)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 852
Lines: 23

* Josh Cartwright | 2016-03-08 12:26:56 [-0600]:

>Is it really just about latency?  Does this deferral not lead to an
>inversion in the case where the single woken task isn't the highest
>priority waiter on the completion (and doesn't run due to a
>middle-priority thing spinning)?

This would be case, yes. Not only with deferral. Say you have two
waters: 1st one is MID-prio and the second is HI-prio. Currently after
the wakeup of the MID-prio waiter you get preempted. Waking all of them
at once would put the second waiter first on the CPU.
Samething without the deferral flag.

>In order for this to work, it seems like the chosen waiter would need to
>inherit the highest priority of all waiters (which AFAICT isn't
>happening).

sorting the waiters by priority? This will be fun. This is only done for
the rtmutex waiters.

>  Josh

Sebastian