Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <e0724ba0-a8f6-b36b-0c09-fff48c4282ad@redhat.com>
Date:   Mon, 11 Jul 2022 16:02:21 -0400
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101
 Thunderbird/91.9.1
Subject: Re: [PATCH v3] locking/rtmutex: Limit # of lock stealing for non-RT
 waiters
Content-Language: en-US
To:     Peter Zijlstra <peterz@infradead.org>
Cc:     Ingo Molnar <mingo@redhat.com>, Will Deacon <will@kernel.org>,
        Boqun Feng <boqun.feng@gmail.com>,
        linux-kernel@vger.kernel.org, Thomas Gleixner <tglx@linutronix.de>,
        Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
        Juri Lelli <juri.lelli@redhat.com>,
        Mike Stowell <mstowell@redhat.com>
References: <20220706135916.980580-1-longman@redhat.com>
 <YsvuwfeY/dSngl8c@hirez.programming.kicks-ass.net>
From:   Waiman Long <longman@redhat.com>
In-Reply-To: <YsvuwfeY/dSngl8c@hirez.programming.kicks-ass.net>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 7/11/22 05:34, Peter Zijlstra wrote:
> On Wed, Jul 06, 2022 at 09:59:16AM -0400, Waiman Long wrote:
>> Commit 48eb3f4fcfd3 ("locking/rtmutex: Implement equal priority lock
>> stealing") allows unlimited number of lock stealing's for non-RT
>> tasks. That can lead to lock starvation of non-RT top waiter tasks if
>> there is a constant incoming stream of non-RT lockers. This can cause
>> rcu_preempt self-detected stall or even task lockup in PREEMPT_RT kernel.
>> For example,
>>
>> [77107.424943] rcu: INFO: rcu_preempt self-detected stall on CPU
>> [ 1249.921363] INFO: task systemd:2178 blocked for more than 622 seconds.
>>
>> Avoiding this problem and ensuring forward progress by limiting the
>> number of times that a lock can be stolen from each waiter. This patch
>> sets a threshold of 32. That number is arbitrary and can be changed
>> if needed.
>>
> Why not do the same thing we do for regular mutexes?
>
The mutex way is another possible alternative. So we can set a flag to 
disable lock stealing if the current top waiter wake up and the rtmutex 
has been stolen. I will need to run some tests to find out how many time 
lock stealing can happen before it is blocked. I would like to allow 
sufficient number of lock stealing to minimize the performance impact of 
this change.

Cheers,
Longman