[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <1455036424-6403-1-git-send-email-david@weave.works>
Date: Tue, 9 Feb 2016 16:47:01 +0000
From: David Wragg <david@...ve.works>
To: netdev@...r.kernel.org, dev@...nvswitch.org
Cc: Jesse Gross <jesse@...nel.org>, David Miller <davem@...emloft.net>,
Hannes Frederic Sowa <hannes@...essinduktion.org>,
Thomas Graf <tgraf@...g.ch>,
Roopa Prabhu <roopa@...ulusnetworks.com>,
David Wragg <david@...ve.works>
Subject: [PATCH net v2 0/3] Set a large MTU on ovs-created tunnel devices
Prior to 4.3, tunnel vports (vxlan, gre and geneve) could transmit
vxlan packets of any size, constrained only by the ability to send out
the resulting packets. 4.3 introduced netdevs corresponding to tunnel
vports. These netdevs have an MTU, which limits the size of a packet
that can be successfully encapsulated. The default value for the MTUs
are low (1500 or less), which is awkwardly small in the context of
physical networks supporting jumbo frames, and leads to a conspicuous
change in behaviour for userspace.
This patch series sets the MTU on openvswitch-created netdevs to be
the relevant maximum (i.e. the maximum IP packet size minus any
relevant overhead), effectively restoring the behaviour prior to 4.3.
Where appropriate, the limits on MTU values when set on the netdevs
directly are also relaxed.
Changes in v2:
* Extend to all openvswitch tunnel types, i.e. gre and geneve as well
* Use IP_MAX_MTU
David Wragg (3):
vxlan: Relax the MTU constraints
geneve: Relax MTU constraints
vxlan, gre, geneve: Set a large MTU on ovs-created tunnel devices
drivers/net/geneve.c | 29 +++++++++++++++++++++-----
drivers/net/vxlan.c | 47 ++++++++++++++++++++++++++++++-------------
include/net/ip_tunnels.h | 1 +
net/ipv4/ip_gre.c | 7 +++++++
net/ipv4/ip_tunnel.c | 21 ++++++++++++++++---
net/openvswitch/vport-vxlan.c | 2 ++
6 files changed, 85 insertions(+), 22 deletions(-)
--
2.5.0
Powered by blists - more mailing lists