10:53 p.m.
Hello,
Yesterday, we discussed options for a Linux Plumber's Conference
networking track talk.
Here is a first draft of an abstract. Feel free to comment and react:
===
Multipath TCP (MPTCP) is more and more popular these days but it is not
in the upstream Linux kernel yet. A fork is still being maintained on
the side and has been since March 2009. But it cannot be upstreamed as
it is because this implementation is designed for MPTCP and the TCP
stack is too heavily impacted in term of maintainability but also a bit
regarding the performances.
In this presentation, we would like to present the challenges we are
facing. Some are introduced by this MPTCP protocol, others by objectives
we defined: limit at the maximum the impact on the existing TCP stack.
We would like to have no performance regression, a maintainable and
configurable solution and an MPTCP implementation that can be used in a
variety of deployments.
The MPTCP upstreaming community is working on a RFC patch set for
net-next. We should be able to send it before the next LPC in September.
In the current situation, a socket can be created with IPPROTO_MPTCP to
initiate and accept an MPTCP connection. This socket remains compatible
with regular TCP and IPPROTO_TCP socket behavior is unchanged. This
implementation makes use of ULP between the userspace-facing MPTCP
socket and the set of in-kernel TCP sockets it controls to limit the
minimum impact on the current TCP stack. ULP has been extended for use
with listening sockets. skb_ext is used to carry MPTCP metadata.
Both the communication and the code are public and opened. You can find
us at mptcp(a)lists.01.org and https://is.gd/mptcp_upstream
===
Do not hesitate to improve it, fix typo or restart from scratch if
needed, I don't mind!
Cheers,
Matt
--
Matthieu Baerts | R&D Engineer
matthieu.baerts(a)tessares.net
Tessares SA | Hybrid Access Solutions
www.tessares.net
1 Avenue Jean Monnet, 1348 Louvain-la-Neuve, Belgium
7:36 a.m.
On Fri, 7 Jun 2019, Matthieu Baerts wrote:
Hello,
Yesterday, we discussed options for a Linux Plumber's Conference
networking track talk.
Here is a first draft of an abstract. Feel free to comment and react:
===
...
===
Do not hesitate to improve it, fix typo or restart from scratch if
needed, I don't mind!
I edited and rewrote part of the draft to focus on the long-term roadmap
and how we phase in features. The main audiences I'm thinking of are the
maintainers and present users of the multipath-tcp.org kernel.
It's not ready for submission yet, but given our plan to submit
mid-next-week I wanted to share a draft before the weekend:
"""
Multipath TCP (MPTCP) is an increasingly popular protocol that members of
the kernel community are actively working to upstream. A Linux kernel fork
implementing the protocol has been developed and maintained since March
2009. While there are some large MPTCP deployments using this custom
kernel, an upstream implementation will make the protocol available on
Linux devices of all flavors.
MPTCP is closely coupled to TCP, but an implementation does not need to
interfere with operation of normal TCP connections. Our roadmap for MPTCP
in Linux begins with the server use case, where connections and additional
subflows are generally initiated by peer devices. This will start with RFC
6824 compliance, but with a minimal feature set to limit the code
footprint for initial review and testing.
The MPTCP upstreaming community has shared a RFC patch set on the netdev
list that shows our progress and how we plan to build around the TCP
stack. We'll share our roadmap for how this patch set will evolve before
final submission, and discuss how this first step will differ from the
forked implementation.
Once we have merged our baseline code, we have plans to continue
development of more advanced features for managing subflow creation (path
management), scheduling outgoing packets across subflows, and other
capabilities important for client devices that initiate connections. This
includes making use of a userspace path manager, which has an alpha
release available already. In future kernel releases we will make use of
additional TCP features and optimize MPTCP performance as we get more
feedback from kernel users.
Both the communication and the code are public and open. You can find us
at mptcp(a)lists.01.org and https://is.gd/mptcp_upstream
"""
--
Mat Martineau
Intel
7:31 p.m.
Hi Mat,
On 29/06/2019 01:36, Mat Martineau wrote:
On Fri, 7 Jun 2019, Matthieu Baerts wrote:
> Hello,
>
> Yesterday, we discussed options for a Linux Plumber's Conference
> networking track talk.
>
> Here is a first draft of an abstract. Feel free to comment and react:
>
> ===
...
> ===
>
> Do not hesitate to improve it, fix typo or restart from scratch if
> needed, I don't mind!
>
I edited and rewrote part of the draft to focus on the long-term roadmap
and how we phase in features. The main audiences I'm thinking of are the
maintainers and present users of the multipath-tcp.org kernel.
It's not ready for submission yet, but given our plan to submit
mid-next-week I wanted to share a draft before the weekend:
Thank you for this updated version.
It looks ready to me :-)
I don't think we really need to improve it, the main idea is there and
people can easily find more about this project by looking at the ML,
wiki, code, previous presentations at netdev and netconf.
What do you think? Or what do you want to improve?
Cheers,
Matt
--
Matthieu Baerts | R&D Engineer
matthieu.baerts(a)tessares.net
Tessares SA | Hybrid Access Solutions
www.tessares.net
1 Avenue Jean Monnet, 1348 Louvain-la-Neuve, Belgium
4:32 a.m.
On Mon, 1 Jul 2019, Matthieu Baerts wrote:
Hi Mat,
On 29/06/2019 01:36, Mat Martineau wrote:
>
> On Fri, 7 Jun 2019, Matthieu Baerts wrote:
>
>> Hello,
>>
>> Yesterday, we discussed options for a Linux Plumber's Conference
>> networking track talk.
>>
>> Here is a first draft of an abstract. Feel free to comment and react:
>>
>> ===
> ...
>> ===
>>
>> Do not hesitate to improve it, fix typo or restart from scratch if
>> needed, I don't mind!
>>
>
> I edited and rewrote part of the draft to focus on the long-term roadmap
> and how we phase in features. The main audiences I'm thinking of are the
> maintainers and present users of the multipath-tcp.org kernel.
>
> It's not ready for submission yet, but given our plan to submit
> mid-next-week I wanted to share a draft before the weekend:
Thank you for this updated version.
It looks ready to me :-)
Ok, thanks!
I don't think we really need to improve it, the main idea is
there and
people can easily find more about this project by looking at the ML,
wiki, code, previous presentations at netdev and netconf.
What do you think? Or what do you want to improve?
If people are ok with it, I don't have to change much. My main goal was to
see if others wanted to add any topics or give other suggestions before
sending it in.
Hopefully I can get some more feedback, but if I don't I will polish it up
one more time and send on Wednesday.
--
Mat Martineau
Intel
6:23 p.m.
Hi Mat,
On 01/07/2019 22:32, Mat Martineau wrote:
On Mon, 1 Jul 2019, Matthieu Baerts wrote:
...
>
> It looks ready to me :-)
Ok, thanks!
> I don't think we really need to improve it, the main idea is there and
> people can easily find more about this project by looking at the ML,
> wiki, code, previous presentations at netdev and netconf.
>
> What do you think? Or what do you want to improve?
If people are ok with it, I don't have to change much. My main goal was
to see if others wanted to add any topics or give other suggestions
before sending it in.
Hopefully I can get some more feedback, but if I don't I will polish it
up one more time and send on Wednesday.
Looks good to me! Thank you for looking at that.
When submitting the proposal, please add multiple people in the
"Authors" section to be sure we can all attend this conference :)
Cheers,
Matt
--
Matthieu Baerts | R&D Engineer
matthieu.baerts(a)tessares.net
Tessares SA | Hybrid Access Solutions
www.tessares.net
1 Avenue Jean Monnet, 1348 Louvain-la-Neuve, Belgium
11:52 p.m.
New subject: LPC networking CfP: Presenters/authors/co-authors?
On Tue, 2 Jul 2019, Matthieu Baerts wrote:
When submitting the proposal, please add multiple people in the
"Authors" section to be sure we can all attend this conference :)
We haven't discussed presenters/authors yet :)
I'm happy to work on the presentation & paper, and present/co-present.
Matthieu, do you want to share the presentation again?
Anyone else want to contribute and be listed as co-author? (The proposal
form has separate fields for an "authors" list and a "co-authors"
list)
--
Mat Martineau
Intel
11:59 p.m.
New subject: LPC networking CfP: Presenters/authors/co-authors?
Hi Mat,
On 02/07/2019 17:52, Mat Martineau wrote:
On Tue, 2 Jul 2019, Matthieu Baerts wrote:
> When submitting the proposal, please add multiple people in the
> "Authors" section to be sure we can all attend this conference :)
We haven't discussed presenters/authors yet :)
I thought that this list was a proposal, like we did for netdev. I mean:
we list different people and we decide after who will present.
I'm happy to work on the presentation & paper, and
present/co-present.
Matthieu, do you want to share the presentation again?
Sure I am happy to work on both!
I don't know if we can have multiple presenters.
Anyone else want to contribute and be listed as co-author? (The
proposal
form has separate fields for an "authors" list and a "co-authors"
list)
I missed this second list. What's the difference between the two? :-)
Cheers,
Matt
--
Matthieu Baerts | R&D Engineer
matthieu.baerts(a)tessares.net
Tessares SA | Hybrid Access Solutions
www.tessares.net
1 Avenue Jean Monnet, 1348 Louvain-la-Neuve, Belgium
1:21 a.m.
New subject: LPC networking CfP: Presenters/authors/co-authors?
On Tue, 2 Jul 2019, Matthieu Baerts wrote:
Hi Mat,
On 02/07/2019 17:52, Mat Martineau wrote:
>
> On Tue, 2 Jul 2019, Matthieu Baerts wrote:
>
>> When submitting the proposal, please add multiple people in the
>> "Authors" section to be sure we can all attend this conference :)
>
> We haven't discussed presenters/authors yet :)
I thought that this list was a proposal, like we did for netdev. I mean:
we list different people and we decide after who will present.
> I'm happy to work on the presentation & paper, and present/co-present.
> Matthieu, do you want to share the presentation again?
Sure I am happy to work on both!
I don't know if we can have multiple presenters.
> Anyone else want to contribute and be listed as co-author? (The proposal
> form has separate fields for an "authors" list and a "co-authors"
list)
I missed this second list. What's the difference between the two? :-)
The difference isn't totally clear. My interpretation is that the
"authors" would likely be the presenters and the "co-authors" are
people
who contribute to the paper & slides - that's what I plan to do when
submitting and we can make final decisions before the event.
--
Mat Martineau
Intel
5:55 a.m.
On Tue, 2 Jul 2019, Matthieu Baerts wrote:
Hi Mat,
On 01/07/2019 22:32, Mat Martineau wrote:
>
> On Mon, 1 Jul 2019, Matthieu Baerts wrote:
...
>>
>> It looks ready to me :-)
>
> Ok, thanks!
>
>> I don't think we really need to improve it, the main idea is there and
>> people can easily find more about this project by looking at the ML,
>> wiki, code, previous presentations at netdev and netconf.
>>
>> What do you think? Or what do you want to improve?
>
> If people are ok with it, I don't have to change much. My main goal was
> to see if others wanted to add any topics or give other suggestions
> before sending it in.
>
> Hopefully I can get some more feedback, but if I don't I will polish it
> up one more time and send on Wednesday.
Looks good to me! Thank you for looking at that.
When submitting the proposal, please add multiple people in the
"Authors" section to be sure we can all attend this conference :)
Ok, I've submitted the proposal with Matthieu and I as authors. It was
nearly identical to the draft from Friday, I only made a few grammatical
fixes.
--
Mat Martineau
Intel
2:26 p.m.
Hi Mat,
On 03/07/2019 23:55, Mat Martineau wrote:
On Tue, 2 Jul 2019, Matthieu Baerts wrote:
> Hi Mat,
>
> On 01/07/2019 22:32, Mat Martineau wrote:
>>
>> On Mon, 1 Jul 2019, Matthieu Baerts wrote:
>
> ...
>
>>>
>>> It looks ready to me :-)
>>
>> Ok, thanks!
>>
>>> I don't think we really need to improve it, the main idea is there and
>>> people can easily find more about this project by looking at the ML,
>>> wiki, code, previous presentations at netdev and netconf.
>>>
>>> What do you think? Or what do you want to improve?
>>
>> If people are ok with it, I don't have to change much. My main goal was
>> to see if others wanted to add any topics or give other suggestions
>> before sending it in.
>>
>> Hopefully I can get some more feedback, but if I don't I will polish it
>> up one more time and send on Wednesday.
>
> Looks good to me! Thank you for looking at that.
>
> When submitting the proposal, please add multiple people in the
> "Authors" section to be sure we can all attend this conference :)
>
Ok, I've submitted the proposal with Matthieu and I as authors. It was
nearly identical to the draft from Friday, I only made a few grammatical
fixes.
Thank you for having sent that!
Cheers,
Matt
--
Matthieu Baerts | R&D Engineer
matthieu.baerts(a)tessares.net
Tessares SA | Hybrid Access Solutions
www.tessares.net
1 Avenue Jean Monnet, 1348 Louvain-la-Neuve, Belgium
3:42 p.m.
Hello,
On 04/07/2019 08:26, Matthieu Baerts wrote:
On 03/07/2019 23:55, Mat Martineau wrote:
(...)
> Ok, I've submitted the proposal with Matthieu and I as
authors. It was
> nearly identical to the draft from Friday, I only made a few grammatical
> fixes.
Thank you for having sent that!
Good news! It seems our proposal has been accepted:
We are pleased to announce that your proposal
"Mutipath TCP Upstreaming"
has been accepted as a Linux Plumbers Conference 2019 Networking
Summit talk.
We can talk about that at our meeting tomorrow!
Cheers,
Matt
--
Matthieu Baerts | R&D Engineer
matthieu.baerts(a)tessares.net
Tessares SA | Hybrid Access Solutions
www.tessares.net
1 Avenue Jean Monnet, 1348 Louvain-la-Neuve, Belgium
539
days inactive
600
days old
11 comments
3 participants
participants (3)
-
Florian Westphal -
Mat Martineau -
Matthieu Baerts