qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Yuri Benditovich <yuri.benditovich@daynix.com>
To: Akihiko Odaki <akihiko.odaki@daynix.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>,
	Jason Wang <jasowang@redhat.com>,
	qemu-devel@nongnu.org, Andrew Melnychenko <andrew@daynix.com>
Subject: Re: [PATCH v6 11/21] virtio-net: Return an error when vhost cannot enable RSS
Date: Mon, 13 Nov 2023 13:44:10 +0200	[thread overview]
Message-ID: <CAOEp5Oee2qinrZJgMMxUQt6zmPVFPCnThfqnLFSWqsSyAoHpjQ@mail.gmail.com> (raw)
In-Reply-To: <8439be4e-a739-4cbd-a569-89b6c7f68ab9@daynix.com>

[-- Attachment #1: Type: text/plain, Size: 4127 bytes --]

On Sat, Nov 11, 2023 at 5:28 PM Akihiko Odaki <akihiko.odaki@daynix.com>
wrote:

> On 2023/11/03 22:14, Yuri Benditovich wrote:
> >
> >
> > On Fri, Nov 3, 2023 at 11:55 AM Akihiko Odaki <akihiko.odaki@daynix.com
> > <mailto:akihiko.odaki@daynix.com>> wrote:
> >
> >     On 2023/11/03 18:35, Yuri Benditovich wrote:
> >      >
> >      >
> >      > On Thu, Nov 2, 2023 at 4:56 PM Akihiko Odaki
> >     <akihiko.odaki@daynix.com <mailto:akihiko.odaki@daynix.com>
> >      > <mailto:akihiko.odaki@daynix.com
> >     <mailto:akihiko.odaki@daynix.com>>> wrote:
> >      >
> >      >     On 2023/11/02 19:20, Yuri Benditovich wrote:
> >      >      >
> >      >      >
> >      >      > On Thu, Nov 2, 2023 at 11:33 AM Michael S. Tsirkin
> >      >     <mst@redhat.com <mailto:mst@redhat.com>
> >     <mailto:mst@redhat.com <mailto:mst@redhat.com>>
> >      >      > <mailto:mst@redhat.com <mailto:mst@redhat.com>
> >     <mailto:mst@redhat.com <mailto:mst@redhat.com>>>> wrote:
> >      >      >
> >      >      >     On Thu, Nov 02, 2023 at 11:09:27AM +0200, Yuri
> >     Benditovich wrote:
> >      >      >      > Probably we mix two different patches in this
> >     discussion.
> >      >      >      > Focusing on the patch in the e-mail header:
> >      >      >      >
> >      >      >      > IMO it is not acceptable to fail QEMU run for one
> >     feature
> >      >     that we
> >      >      >     can't make
> >      >      >      > active when we silently drop all other features in
> >     such a
> >      >     case.
> >      >      >
> >      >      >     If the feature is off by default then it seems more
> >     reasonable
> >      >      >     and silent masking can be seen as a bug.
> >      >      >     Most virtio features are on by default this is why it's
> >      >      >     reasonable to mask them.
> >      >      >
> >      >      >
> >      >      > If we are talking about RSS: setting it initially off is
> the
> >      >     development
> >      >      > time decision.
> >      >      > When it will be completely stable there is no reason to
> >     keep it
> >      >     off by
> >      >      > default, so this is more a question of time and of a
> >     readiness of
> >      >     libvirt.
> >      >
> >      >     It is not ok to make "on" the default; that will enable RSS
> >     even when
> >      >     eBPF steering support is not present and can result in
> >     performance
> >      >     degradation.
> >      >
> >      >
> >      > Exactly as it is today - with vhost=on the host does not suggest
> RSS
> >      > without  eBPF.
> >      > I do not understand what you call "performance degradation", can
> you
> >      > describe the scenario?
> >
> >     I was not clear, but I was talking about the case of vhost=off or
> peers
> >     other than tap (e.g., user). rss=on employs in-qemu RSS, which incurs
> >     overheads for such configurations.
> >
> >
> > So, vhost=off OR peers other than tap:
> >
> > In the case of peers other than tap (IMO) we're not talking about
> > performance at all.
> > Backends like "user" (without vnet_hdr) do not support _many_
> > performance-oriented features.
> > If RSS is somehow "supported" for such backends this is rather a
> > misunderstanding (IMO again).
>
> We do not need to ensure good performance when RSS is enabled by the
> guest for backends without eBPF steering program as you say. In-QEMU RSS
> is only useful for testing and not meant to improve the performance.
>
> However, if you set rss=on, QEMU will advertise the availability of RSS
> feature. The guest will have no mean to know if it's implemented in a
> way not performance-wise so it may decide to use the feature to improve
> the performance, which can result in performance degradation. Therefore,
> it's better not to set rss=on for such backends.
>

I still do not understand what is the scenario where you see or suspect the
mentioned "performance degradation".
We can discuss whether such a problem exists as soon as you explain it.

[-- Attachment #2: Type: text/html, Size: 6389 bytes --]

  reply	other threads:[~2023-11-13 11:44 UTC|newest]

Thread overview: 59+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-10-30  5:12 [PATCH v6 00/21] virtio-net RSS/hash report fixes and improvements Akihiko Odaki
2023-10-30  5:12 ` [PATCH v6 01/21] tap: Remove tap_probe_vnet_hdr_len() Akihiko Odaki
2023-10-30  5:12 ` [PATCH v6 02/21] tap: Remove qemu_using_vnet_hdr() Akihiko Odaki
2023-10-30  5:12 ` [PATCH v6 03/21] net: Move virtio-net header length assertion Akihiko Odaki
2023-10-30  5:12 ` [PATCH v6 04/21] net: Remove receive_raw() Akihiko Odaki
2023-10-30  5:12 ` [PATCH v6 05/21] tap: Remove tap_receive() Akihiko Odaki
2023-10-30 18:52   ` Zhang, Chen
2023-10-31  4:57     ` Akihiko Odaki
2023-10-30  5:12 ` [PATCH v6 06/21] net: Remove flag propagation Akihiko Odaki
2023-11-10  7:35   ` Pavel Dovgalyuk
2023-11-11 14:27     ` Akihiko Odaki
2023-11-13  8:14       ` Pavel Dovgalyuk
2023-10-30  5:12 ` [PATCH v6 07/21] tap: Shrink zeroed virtio-net header Akihiko Odaki
2023-10-30  5:12 ` [PATCH v6 08/21] virtio-net: Copy header only when necessary Akihiko Odaki
2023-10-30  5:12 ` [PATCH v6 09/21] virtio-net: Disable RSS on reset Akihiko Odaki
2023-10-30  5:12 ` [PATCH v6 10/21] virtio-net: Unify the logic to update NIC state for RSS Akihiko Odaki
2023-10-30  5:12 ` [PATCH v6 11/21] virtio-net: Return an error when vhost cannot enable RSS Akihiko Odaki
2023-10-30 12:14   ` Yuri Benditovich
2023-10-30 12:21     ` Akihiko Odaki
2023-10-30 12:51       ` Yuri Benditovich
2023-10-30 13:14         ` Akihiko Odaki
2023-11-01  4:19           ` Jason Wang
2023-11-01  4:50             ` Akihiko Odaki
2023-11-01  6:38               ` Michael S. Tsirkin
2023-11-01  8:35                 ` Akihiko Odaki
2023-11-01  9:09                   ` Michael S. Tsirkin
2023-11-01  9:15                     ` Akihiko Odaki
2023-11-02  9:09                       ` Yuri Benditovich
2023-11-02  9:33                         ` Michael S. Tsirkin
2023-11-02 10:20                           ` Yuri Benditovich
2023-11-02 11:26                             ` Michael S. Tsirkin
2023-11-02 12:00                               ` Yuri Benditovich
2023-11-02 13:18                                 ` Michael S. Tsirkin
2023-11-02 14:56                             ` Akihiko Odaki
2023-11-03  9:35                               ` Yuri Benditovich
2023-11-03  9:55                                 ` Akihiko Odaki
2023-11-03 13:14                                   ` Yuri Benditovich
2023-11-11 15:28                                     ` Akihiko Odaki
2023-11-13 11:44                                       ` Yuri Benditovich [this message]
2023-11-13 12:44                                         ` Akihiko Odaki
2023-11-13 17:26                                           ` Yuri Benditovich
2023-11-14  7:03                                             ` Akihiko Odaki
2023-11-14 22:09                                               ` Yuri Benditovich
2023-11-15  6:09                                                 ` Akihiko Odaki
2023-11-16  5:14                                                   ` Jason Wang
2023-10-30  5:12 ` [PATCH v6 12/21] virtio-net: Enable software RSS Akihiko Odaki
2023-10-30 12:42   ` Yuri Benditovich
2023-10-30  5:12 ` [PATCH v6 13/21] virtio-net: Always set populate_hash Akihiko Odaki
2023-10-30 19:02   ` Zhang, Chen
2023-10-31  4:47     ` Akihiko Odaki
2023-10-30  5:12 ` [PATCH v6 14/21] virtio-net: Do not write hashes to peer buffer Akihiko Odaki
2023-10-30  5:12 ` [PATCH v6 15/21] virtio-net: Do not clear VIRTIO_NET_F_HASH_REPORT Akihiko Odaki
2023-11-03 13:26   ` Yuri Benditovich
2023-10-30  5:12 ` [PATCH v6 16/21] ebpf: Fix RSS error handling Akihiko Odaki
2023-10-30  5:12 ` [PATCH v6 17/21] ebpf: Use standard section name Akihiko Odaki
2023-10-30  5:12 ` [PATCH v6 18/21] ebpf: Simplify error handling Akihiko Odaki
2023-10-30  5:12 ` [PATCH v6 19/21] ebpf: Return 0 when configuration fails Akihiko Odaki
2023-10-30  5:12 ` [PATCH v6 20/21] ebpf: Refactor tun_rss_steering_prog() Akihiko Odaki
2023-10-30  5:12 ` [PATCH v6 21/21] ebpf: Add a separate target for skeleton Akihiko Odaki

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=CAOEp5Oee2qinrZJgMMxUQt6zmPVFPCnThfqnLFSWqsSyAoHpjQ@mail.gmail.com \
    --to=yuri.benditovich@daynix.com \
    --cc=akihiko.odaki@daynix.com \
    --cc=andrew@daynix.com \
    --cc=jasowang@redhat.com \
    --cc=mst@redhat.com \
    --cc=qemu-devel@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).