From: Steffen Klassert <steffen.klassert@secunet.com>
To: Paolo Abeni <pabeni@redhat.com>
Cc: <netdev@vger.kernel.org>, Willem de Bruijn <willemb@google.com>
Subject: Re: [RFC PATCH v2 00/10] udp: implement GRO support
Date: Wed, 24 Oct 2018 12:55:14 +0200 [thread overview]
Message-ID: <20181024105514.GR3823@gauss3.secunet.de> (raw)
In-Reply-To: <7aecb7871f3e330debdeb81fd8a401ec5692fa81.camel@redhat.com>
On Tue, Oct 23, 2018 at 02:22:12PM +0200, Paolo Abeni wrote:
> On Tue, 2018-10-23 at 14:10 +0200, Steffen Klassert wrote:
>
> > Some quick benchmark numbers with UDP packet forwarding
> > (1460 byte packets) through two gateways:
> >
> > net-next: 16.4 Gbps
> >
> > net-next + UDP GRO: 20.3 Gbps
>
> uhmmm... what do you think about this speed-up ?
skb_segment() burns a lot of cycles. If I do the same test with
TCP and disable HW TSO, throughput drops also down to similar
values.
In case of software segmentation, the skb chain appropach
is likely faster because packets are not mangled. So no need
to allocate skbs, no new checksum calculations, less memcpy etc.
If we have an early route lookup in GRO, we could have a good
guess on the offload capabilities of the outgoing device.
So in case that software segmentation is likely, use the
skb chaining method. If HW segmentation is likely, merge
IP packets.
The chaining method might be also faster on non UDP GRO enabled
sockets.
I'll try to implement the skb chaining method on top of this
to see what we get from that.
prev parent reply other threads:[~2018-10-24 19:22 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-19 14:25 [RFC PATCH v2 00/10] udp: implement GRO support Paolo Abeni
2018-10-19 14:25 ` [RFC PATCH v2 01/10] udp: implement complete book-keeping for encap_needed Paolo Abeni
2018-10-22 16:06 ` Willem de Bruijn
2018-10-25 13:00 ` Paolo Abeni
2018-10-19 14:25 ` [RFC PATCH v2 02/10] udp: implement GRO for plain UDP sockets Paolo Abeni
2018-10-21 20:06 ` Willem de Bruijn
2018-10-22 10:13 ` Paolo Abeni
2018-10-22 15:15 ` Willem de Bruijn
2018-10-22 11:24 ` Steffen Klassert
2018-10-22 13:41 ` Paolo Abeni
2018-10-22 15:51 ` Willem de Bruijn
2018-10-19 14:25 ` [RFC PATCH v2 03/10] udp: add support for UDP_GRO cmsg Paolo Abeni
2018-10-21 20:07 ` Willem de Bruijn
2018-10-22 15:44 ` Paolo Abeni
2018-10-19 14:25 ` [RFC PATCH v2 04/10] ip: factor out protocol delivery helper Paolo Abeni
2018-10-19 14:25 ` [RFC PATCH v2 05/10] ipv6: " Paolo Abeni
2018-10-19 14:25 ` [RFC PATCH v2 06/10] udp: cope with UDP GRO packet misdirection Paolo Abeni
2018-10-21 20:08 ` Willem de Bruijn
2018-10-22 10:29 ` Paolo Abeni
2018-10-22 16:00 ` Willem de Bruijn
2018-10-22 11:43 ` Steffen Klassert
2018-10-22 12:51 ` Paolo Abeni
2018-10-23 10:29 ` Steffen Klassert
2018-10-22 19:04 ` Subash Abhinov Kasiviswanathan
2018-10-23 7:59 ` Paolo Abeni
2018-10-24 0:55 ` Subash Abhinov Kasiviswanathan
2018-10-19 14:25 ` [RFC PATCH v2 07/10] selftests: add GRO support to udp bench rx program Paolo Abeni
2018-10-21 20:08 ` Willem de Bruijn
2018-10-22 10:31 ` Paolo Abeni
2018-10-19 14:25 ` [RFC PATCH v2 08/10] selftests: conditionally enable XDP support in udpgso_bench_rx Paolo Abeni
2018-10-21 20:09 ` Willem de Bruijn
2018-10-22 10:37 ` Paolo Abeni
2018-10-19 14:25 ` [RFC PATCH v2 09/10] selftests: add some benchmark for UDP GRO Paolo Abeni
2018-10-19 14:25 ` [RFC PATCH v2 10/10] selftests: add functionals test " Paolo Abeni
2018-10-21 20:09 ` Willem de Bruijn
2018-10-22 10:46 ` Paolo Abeni
2018-10-21 20:05 ` [RFC PATCH v2 00/10] udp: implement GRO support Willem de Bruijn
2018-10-22 9:41 ` Paolo Abeni
2018-10-23 12:10 ` Steffen Klassert
2018-10-23 12:22 ` Paolo Abeni
2018-10-24 10:55 ` Steffen Klassert [this message]
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=20181024105514.GR3823@gauss3.secunet.de \
--to=steffen.klassert@secunet.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=willemb@google.com \
/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).