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;
Date:   Tue, 18 Apr 2023 15:02:00 -0700
From:   Andrew Morton <akpm@linux-foundation.org>
To:     Marcelo Tosatti <mtosatti@redhat.com>
Cc:     Christoph Lameter <cl@linux.com>,
        Aaron Tomlin <atomlin@atomlin.com>,
        Frederic Weisbecker <frederic@kernel.org>,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        Russell King <linux@armlinux.org.uk>,
        Huacai Chen <chenhuacai@kernel.org>,
        Heiko Carstens <hca@linux.ibm.com>, x86@kernel.org,
        Vlastimil Babka <vbabka@suse.cz>,
        Michal Hocko <mhocko@suse.com>
Subject: Re: [PATCH v7 00/13] fold per-CPU vmstats remotely
Message-Id: <20230418150200.027528c155853fea8e4f58b2@linux-foundation.org>
In-Reply-To: <20230320180332.102837832@redhat.com>
References: <20230320180332.102837832@redhat.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Precedence: bulk

On Mon, 20 Mar 2023 15:03:32 -0300 Marcelo Tosatti <mtosatti@redhat.com> wrote:

> This patch series addresses the following two problems:
> 
> 1. A customer provided evidence indicating that a process
>    was stalled in direct reclaim:
> 
> ...
>
>  2. With a task that busy loops on a given CPU,
>     the kworker interruption to execute vmstat_update
>     is undesired and may exceed latency thresholds
>     for certain applications.
> 

I don't think I'll be sending this upstream in the next merge window. 
Because it isn't clear that the added complexity in vmstat handling is
justified.

- Michal's request for more clarity on the end-user requirements
  seems reasonable.

- You have indicated that additional changelog material is forthcoming.

- The alternative idea of adding a syscall which tells the kernel
  "I'm about to go realtime, so please clear away all the pending crap
  which might later interrupt me" sounds pretty good.

  Partly because there are surely other places where we can use this.

  Partly because it moves all the crap-clearing into special
  crap-clearing code paths while adding less burden to the
  commonly-executed code.

  And I don't think this alternative has been fully investigated and
  discussed.