Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.34 as permitted sender) client-ip=23.128.96.34;
MIME-Version: 1.0
References: <20231122100016.GO8262@noisy.programming.kicks-ass.net>
 <6564a012.c80a0220.adb78.f0e4SMTPIN_ADDED_BROKEN@mx.google.com>
 <d4110c79-d64f-49bd-9f69-0a94369b5e86@bytedance.com> <07513.123120701265800278@us-mta-474.us.mimecast.lan>
 <20231207014626-mutt-send-email-mst@kernel.org> <56082.123120804242300177@us-mta-137.us.mimecast.lan>
 <20231208052150-mutt-send-email-mst@kernel.org> <53044.123120806415900549@us-mta-342.us.mimecast.lan>
 <20231209053443-mutt-send-email-mst@kernel.org> <CACGkMEuSGT-e-i-8U7hum-N_xEnsEKL+_07Mipf6gMLFFhj2Aw@mail.gmail.com>
 <20231211115329-mutt-send-email-mst@kernel.org>
In-Reply-To: <20231211115329-mutt-send-email-mst@kernel.org>
From:   Jason Wang <jasowang@redhat.com>
Date:   Tue, 12 Dec 2023 11:00:12 +0800
Message-ID: <CACGkMEudZnF7hUajgt0wtNPCxH8j6A3L1DgJj2ayJWhv9Bh1WA@mail.gmail.com>
Subject: Re: Re: Re: EEVDF/vhost regression (bisected to 86bfbb7ce4f6
 sched/fair: Add lag based placement)
To:     "Michael S. Tsirkin" <mst@redhat.com>
Cc:     Tobias Huschle <huschle@linux.ibm.com>,
        Abel Wu <wuyun.abel@bytedance.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Linux Kernel <linux-kernel@vger.kernel.org>,
        kvm@vger.kernel.org, virtualization@lists.linux.dev,
        netdev@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

On Tue, Dec 12, 2023 at 12:54=E2=80=AFAM Michael S. Tsirkin <mst@redhat.com=
> wrote:
>
> On Mon, Dec 11, 2023 at 03:26:46PM +0800, Jason Wang wrote:
> > > Try reducing the VHOST_NET_WEIGHT limit and see if that improves thin=
gs any?
> >
> > Or a dirty hack like cond_resched() in translate_desc().
>
> what do you mean, exactly?

Ideally it should not matter, but Tobias said there's an unexpectedly
long time spent on translate_desc() which may indicate that the
might_sleep() or other doesn't work for some reason.

Thanks

>
> --
> MST
>