Received-SPF: pass (google.com: domain of linux-kernel+bounces-41172-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
From: Hillf Danton <hdanton@sina.com>
To: Benjamin Segall <bsegall@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Will Deacon <will@kernel.org>,
	Waiman Long <longman@redhat.com>,
	Boqun Feng <boqun.feng@gmail.com>,
	linux-kernel@vger.kernel.org
Subject: Re: [RFC PATCH] locking/percpu-rwsem: do not do lock handoff in percpu_up_write
Date: Sat, 27 Jan 2024 19:20:39 +0800
Message-Id: <20240127112039.896-1-hdanton@sina.com>
In-Reply-To: <xm26sf2j3k1g.fsf@google.com>
References: <xm26zfwx7z5p.fsf@google.com> <20240123150541.1508-1-hdanton@sina.com> <20240125110456.783-1-hdanton@sina.com> <20240126122230.838-1-hdanton@sina.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

On Fri, 26 Jan 2024 12:40:43 -0800 Benjamin Segall <bsegall@google.com>
> 
> I'm fine with "no, fairness is more important than these performance
> numbers or mitigating already-sorta-broken situations", but it's not

Fine too because your patch is never able to escape standing ovation.

And feel free to specify the broken situations you saw.

> clear to me you've even understood the patch, because you keep only
> talking about completely different forms of starvation, and suggesting

Given woken writer in your reply and sem->ww is write waiters, there is
only one starvation in this thread.

  |> >> My patch makes the entire #4 available to writers (or new readers), so
  |> >> that the woken writer will instead get to run immediately. This is

> changes that would if anything make the situation worse.

I mitigate the starvation by making use of the known method without
any heuristic added, though, I am happy to see why it no longer works.