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: <8bfd13a7-ed02-00dd-63a1-7144f2e55ef0@igalia.com>
Date:   Thu, 14 Jul 2022 12:00:59 -0300
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101
 Thunderbird/91.11.0
Subject: Re: [RFC] futex2: add NUMA awareness
Content-Language: en-US
To:     Andrey Semashev <andrey.semashev@gmail.com>
Cc:     linux-api@vger.kernel.org, fweimer@redhat.com,
        linux-kernel@vger.kernel.org, Darren Hart <dvhart@infradead.org>,
        Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@redhat.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        libc-alpha@sourceware.org, Davidlohr Bueso <dave@stgolabs.net>,
        Steven Rostedt <rostedt@goodmis.org>,
        Sebastian Andrzej Siewior <bigeasy@linutronix.de>
References: <36a8f60a-69b2-4586-434e-29820a64cd88@igalia.com>
 <74ba5239-27b0-299e-717c-595680cd52f9@gmail.com>
From:   =?UTF-8?Q?Andr=c3=a9_Almeida?= <andrealmeid@igalia.com>
In-Reply-To: <74ba5239-27b0-299e-717c-595680cd52f9@gmail.com>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Precedence: bulk

Hi Andrey,

Thanks for the feedback.

Às 08:01 de 14/07/22, Andrey Semashev escreveu:
> On 7/14/22 06:18, André Almeida wrote:
[...]
>>
>> Feedback? Who else should I CC?
> 
> Just a few questions:
> 
> Do I understand correctly that notifiers won't be able to wake up
> waiters unless they know on which node they are waiting?
> 

If userspace is using NUMA_FLAG, yes. Otherwise all futexes would be
located in the default node, and userspace doesn't need to know which
one is the default.

> Is it possible to wait on a futex on different nodes?

Yes, given that you specify `.hint = id` with the proper node id.

> 
> Is it possible to wake waiters on a futex on all nodes? When a single
> (or N, where N is not "all") waiter is woken, which node is selected? Is
> there a rotation of nodes, so that nodes are not skewed in terms of
> notified waiters?

Regardless of which node the waiter process is running, what matter is
in which node the futex hash table is. So for instance if we have:

	struct futex32_numa f = {.value = 0, hint = 2};

And now we add some waiters for this futex:

Thread 1, running on node 3:

	futex_wait(&f, 0, FUTEX_NUMA | FUTEX_32, NULL);

Thread 2, running on node 0:

	futex_wait(&f, 0, FUTEX_NUMA | FUTEX_32, NULL);

Thread 3, running on node 2:

	futex_wait(&f, 0, FUTEX_NUMA | FUTEX_32, NULL);

And then, Thread 4, running on node 3:

	futex_wake(&f, 2, FUTEX_NUMA | FUTEX_32);

Now, two waiter would wake up (e.g. T1 and T3, node 3 and 2) and they
are from different nodes. futex_wake() doesn't provide guarantees of
which waiter will be selected, so I can't say which node would be
selected. There's no policy for fairness/starvation for futex_wake(). Do
you think this would be important for the NUMA case?

Let me know if this clarifies your questions.