netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: David Ahern <dsahern@gmail.com>
To: Florian Westphal <fw@strlen.de>
Cc: Stefano Brivio <sbrivio@redhat.com>,
	netdev@vger.kernel.org, aconole@redhat.com
Subject: Re: [PATCH net-next 1/3] udp_tunnel: allow to turn off path mtu discovery on encap sockets
Date: Mon, 13 Jul 2020 08:41:52 -0600	[thread overview]
Message-ID: <a6821eac-82f8-0d9e-6388-ea6c9f5535d1@gmail.com> (raw)
In-Reply-To: <20200713140219.GM32005@breakpoint.cc>

On 7/13/20 8:02 AM, Florian Westphal wrote:
> David Ahern <dsahern@gmail.com> wrote:
>> On 7/13/20 2:04 AM, Florian Westphal wrote:
>>>> As PMTU discovery happens, we have a route exception on the lower
>>>> layer for the given path, and we know that VXLAN will use that path,
>>>> so we also know there's no point in having a higher MTU on the VXLAN
>>>> device, it's really the maximum packet size we can use.
>>> No, in the setup that prompted this series the route exception is wrong.
>>
>> Why is the exception wrong and why can't the exception code be fixed to
>> include tunnel headers?
> 
> I don't know.  This occurs in a 3rd party (read: "cloud") environment.
> After some days, tcp connections on the overlay network hang.
> 
> Flushing the route exception in the namespace of the vxlan interface makes
> the traffic flow again, i.e. if the vxlan tunnel would just use the
> physical devices MTU things would be fine.
> 
> I don't know what you mean by 'fix exception code to include tunnel
> headers'.  Can you elaborate?

lwtunnel has lwtunnel_headroom which allows ipv4_mtu to accommodate the
space needed for the encap header. Can something similar be adapted for
the device based tunnels?

> 
> AFAICS everyhing functions as designed, except:
> 1. The route exception should not exist in first place in this case
> 2. The route exception never times out (gets refreshed every time
>    tunnel tries to send a mtu-sized packet).
> 3. The original sender never learns about the pmtu event

meaning the VM / container? ie., this is a VPC using VxLAN in the host
to send packets to another hypervisor. If that is the case why isn't the
underlay MTU bumped to handle the encap header, or the VMs MTU lowered
to handle the encap header? seems like a config problem.

  reply	other threads:[~2020-07-13 14:41 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-12 20:07 [PATCH net-next 0/3] vxlan, geneve: allow to turn off PMTU updates on encap socket Florian Westphal
2020-07-12 20:07 ` [PATCH net-next 1/3] udp_tunnel: allow to turn off path mtu discovery on encap sockets Florian Westphal
2020-07-12 22:38   ` Stefano Brivio
2020-07-13  8:04     ` Florian Westphal
2020-07-13 10:04       ` Stefano Brivio
2020-07-13 10:51         ` Numan Siddique
2020-07-14 20:38           ` Aaron Conole
2020-07-15 11:58             ` Stefano Brivio
2020-07-13 13:25       ` David Ahern
2020-07-13 14:02         ` Florian Westphal
2020-07-13 14:41           ` David Ahern [this message]
2020-07-13 14:59             ` Florian Westphal
2020-07-13 15:57               ` Stefano Brivio
2020-07-13 16:22                 ` Florian Westphal
2020-07-14 12:33                   ` Stefano Brivio
2020-07-14 12:33           ` Stefano Brivio
2020-07-15 12:42             ` Florian Westphal
2020-07-15 13:35               ` Stefano Brivio
2020-07-15 14:33                 ` Florian Westphal
2020-07-17 12:27                   ` Stefano Brivio
2020-07-17 15:04                     ` David Ahern
2020-07-17 18:43                       ` Florian Westphal
2020-07-18  6:56                       ` Stefano Brivio
2020-07-18 17:02                         ` David Ahern
2020-07-18 17:58                           ` Stefano Brivio
2020-07-18 18:04                             ` Stefano Brivio
2020-07-19 18:43                             ` David Ahern
2020-07-19 21:49                               ` Stefano Brivio
2020-07-20  3:19                                 ` David Ahern
2020-07-26 17:01                                   ` Stefano Brivio
2020-07-12 20:07 ` [PATCH net-next 2/3] vxlan: allow to disable path mtu learning on encap socket Florian Westphal
2020-07-16 19:33   ` Jakub Kicinski
2020-07-17 10:13     ` Florian Westphal
2020-07-12 20:07 ` [PATCH net-next 3/3] geneve: allow disabling of pmtu detection on encap sk Florian Westphal
2020-07-12 22:39 ` [PATCH net-next 0/3] vxlan, geneve: allow to turn off PMTU updates on encap socket Stefano Brivio

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=a6821eac-82f8-0d9e-6388-ea6c9f5535d1@gmail.com \
    --to=dsahern@gmail.com \
    --cc=aconole@redhat.com \
    --cc=fw@strlen.de \
    --cc=netdev@vger.kernel.org \
    --cc=sbrivio@redhat.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).