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:   Mon, 5 Jun 2023 16:14:18 -0300
From:   Marcelo Tosatti <mtosatti@redhat.com>
To:     Michal Hocko <mhocko@suse.com>
Cc:     Christoph Lameter <cl@linux.com>,
        Aaron Tomlin <atomlin@atomlin.com>,
        Frederic Weisbecker <frederic@kernel.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        Vlastimil Babka <vbabka@suse.cz>
Subject: Re: [PATCH v2 2/3] vmstat: skip periodic vmstat update for nohz full
 CPUs
Message-ID: <ZH40CnznHeBVb/Rb@tpad>
References: <20230602185757.110910188@redhat.com>
 <20230602190115.521067386@redhat.com>
 <ZH2VDaF9uODTqAfV@dhcp22.suse.cz>
 <ZH33BI9//tAbLvz5@tpad>
 <ZH4FhQ5Lh6xFBjyz@dhcp22.suse.cz>
 <ZH4c/MqHoWiA0PaQ@tpad>
 <ZH4wC0gEbsz+H/Aa@dhcp22.suse.cz>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <ZH4wC0gEbsz+H/Aa@dhcp22.suse.cz>
Precedence: bulk

On Mon, Jun 05, 2023 at 08:57:15PM +0200, Michal Hocko wrote:
> > Guest initiated I/O, since the host CPU is isolated.
> 
> Make it explicit in the changelog.

I think better use of our time would be to focus on

https://lkml.iu.edu/hypermail/linux/kernel/2209.1/01263.html

1) Operate in terms of add CPU, remove CPU on sysfs (to avoid races).
2) Don't allow all CPUs to be marked as "block_interf".
3) Remove percpu rwsem lock.

> I am just wondering how you can achieve your strict deadlines when IO is
> involved but that is another story I guess.

IO can be submitted when the ELF binary and libraries are read
from the virtual disk, for example.