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 20:57:15 +0200
From:   Michal Hocko <mhocko@suse.com>
To:     Marcelo Tosatti <mtosatti@redhat.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: <ZH4wC0gEbsz+H/Aa@dhcp22.suse.cz>
References: <20230602185757.110910188@redhat.com>
 <20230602190115.521067386@redhat.com>
 <ZH2VDaF9uODTqAfV@dhcp22.suse.cz>
 <ZH33BI9//tAbLvz5@tpad>
 <ZH4FhQ5Lh6xFBjyz@dhcp22.suse.cz>
 <ZH4c/MqHoWiA0PaQ@tpad>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <ZH4c/MqHoWiA0PaQ@tpad>
Precedence: bulk

On Mon 05-06-23 14:35:56, Marcelo Tosatti wrote:
> On Mon, Jun 05, 2023 at 05:55:49PM +0200, Michal Hocko wrote:
> > > The example above shows an additional 7us for the
> > > 
> > >         oslat -> kworker -> oslat
> > > 
> > > switches. In the case of a virtualized CPU, and the vmstat_update
> > > interruption in the host (of a qemu-kvm vcpu), the latency penalty
> > > observed in the guest is higher than 50us, violating the acceptable
> > > latency threshold.
> > > 
> > > The isolated vCPU can perform operations that modify per-CPU page counters,
> > > for example to complete I/O operations:
> > > 
> > >       CPU 11/KVM-9540    [001] dNh1.  2314.248584: mod_zone_page_state <-__folio_end_writeback
> > >       CPU 11/KVM-9540    [001] dNh1.  2314.248585: <stack trace>
> > >  => 0xffffffffc042b083
> > >  => mod_zone_page_state
> > >  => __folio_end_writeback
> > >  => folio_end_writeback
> > >  => iomap_finish_ioend
> > >  => blk_mq_end_request_batch
> > >  => nvme_irq
> > >  => __handle_irq_event_percpu
> > >  => handle_irq_event
> > >  => handle_edge_irq
> > >  => __common_interrupt
> > >  => common_interrupt
> > >  => asm_common_interrupt
> > >  => vmx_do_interrupt_nmi_irqoff
> > >  => vmx_handle_exit_irqoff
> > >  => vcpu_enter_guest
> > >  => vcpu_run
> > >  => kvm_arch_vcpu_ioctl_run
> > >  => kvm_vcpu_ioctl
> > >  => __x64_sys_ioctl
> > >  => do_syscall_64
> > >  => entry_SYSCALL_64_after_hwframe
> > 
> > OK, this is really useful. It is just not really clear whether the IO
> > triggered here is from the guest or it a host activity.
> 
> Guest initiated I/O, since the host CPU is isolated.

Make it explicit in the changelog.

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

-- 
Michal Hocko
SUSE Labs