Re: [ovs-dev] [RFC ovn-heater] OVN scale testing with OpenStack workloads - questionnaire

[Robin Jarry]

Hello OVN community,

Following up on my previous email:

Robin Jarry, Jul 26, 2023 at 21:19:
> as discussed yesterday during the community meeting and today on IRC,
> I have created a public form that we can use to aggregate the results.
>
> https://forms.gle/bmZARvrxgfrJvzkn6
>
> No account is required to fill in the form and the results are
> anonymous.

The form is now live.

If you run one (or several) OpenStack cluster(s) using OVN, please do
take the time to respond to this survey.

All results are publicly available and will be added to this spreadsheet
automatically as responses are provided:

https://docs.google.com/spreadsheets/d/1HMAhy0zQDhhD59PNJWeS3PWCrVmNkAkwo-BrqDay4FU

Thanks!

___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Re: [ovs-dev] [RFC ovn-heater] OVN scale testing with OpenStack workloads - questionnaire

[Dumitru Ceara]

On 7/26/23 21:19, Robin Jarry wrote:
> Hi all,
> 
> as discussed yesterday during the community meeting and today on IRC,
> I have created a public form that we can use to aggregate the results.
> 
> https://forms.gle/bmZARvrxgfrJvzkn6
> 
> No account is required to fill in the form and the results are
> anonymous.
> 
> Please hold off before providing any responses. It is planned to do
> a final review of all questions during the OVN IRC meeting tomorrow
> (Thursday, July 26 2023, 17:15 UTC) before making it official.

It seems the ovn.org website is wrong, sorry about that.

The meeting is actually scheduled for "Thurs 9:15 AM US Pacific", which
today translates to "16:15 UTC".

I opened a PR to fix the website content too:

https://github.com/ovn-org/ovn-website/pull/57

Sorry for the confusion!

Regards,
Dumitru

> 
> https://www.ovn.org/en/#irc-meetings
> 
> All results are publicly available in various formats:
> 
> Web page:
> https://docs.google.com/spreadsheets/d/e/2PACX-1vSR9TrcGLg1WO327Uy1ihAeJaACfnJSgBl_JcTez0mjYdFZpgF9NAUPe6fod0nyI5_fatJ7_GSre_I3/pubhtml?gid=1526075983=true
> CSV:
> https://docs.google.com/spreadsheets/d/e/2PACX-1vSR9TrcGLg1WO327Uy1ihAeJaACfnJSgBl_JcTez0mjYdFZpgF9NAUPe6fod0nyI5_fatJ7_GSre_I3/pub?gid=1526075983=true=csv
> TSV:
> https://docs.google.com/spreadsheets/d/e/2PACX-1vSR9TrcGLg1WO327Uy1ihAeJaACfnJSgBl_JcTez0mjYdFZpgF9NAUPe6fod0nyI5_fatJ7_GSre_I3/pub?gid=1526075983=true=tsv
> 
> Let me know if you have any remarks, corrections or questions regarding
> this form. It was based on the document created by Dumitru:
> 
> https://docs.google.com/document/d/151saO5a5PmCt7cIZQ7DkgvU755od76BlN2bKjXc1n08/edit?usp=sharing
> 
> Cheers,
> 

___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Re: [ovs-dev] [RFC ovn-heater] OVN scale testing with OpenStack workloads - questionnaire

[Robin Jarry]

Hi all,

as discussed yesterday during the community meeting and today on IRC,
I have created a public form that we can use to aggregate the results.

https://forms.gle/bmZARvrxgfrJvzkn6

No account is required to fill in the form and the results are
anonymous.

Please hold off before providing any responses. It is planned to do
a final review of all questions during the OVN IRC meeting tomorrow
(Thursday, July 26 2023, 17:15 UTC) before making it official.

https://www.ovn.org/en/#irc-meetings

All results are publicly available in various formats:

Web page:
https://docs.google.com/spreadsheets/d/e/2PACX-1vSR9TrcGLg1WO327Uy1ihAeJaACfnJSgBl_JcTez0mjYdFZpgF9NAUPe6fod0nyI5_fatJ7_GSre_I3/pubhtml?gid=1526075983=true
CSV:
https://docs.google.com/spreadsheets/d/e/2PACX-1vSR9TrcGLg1WO327Uy1ihAeJaACfnJSgBl_JcTez0mjYdFZpgF9NAUPe6fod0nyI5_fatJ7_GSre_I3/pub?gid=1526075983=true=csv
TSV:
https://docs.google.com/spreadsheets/d/e/2PACX-1vSR9TrcGLg1WO327Uy1ihAeJaACfnJSgBl_JcTez0mjYdFZpgF9NAUPe6fod0nyI5_fatJ7_GSre_I3/pub?gid=1526075983=true=tsv

Let me know if you have any remarks, corrections or questions regarding
this form. It was based on the document created by Dumitru:

https://docs.google.com/document/d/151saO5a5PmCt7cIZQ7DkgvU755od76BlN2bKjXc1n08/edit?usp=sharing

Cheers,

-- 
Robin

___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Re: [ovs-dev] [RFC ovn-heater] OVN scale testing with OpenStack workloads - questionnaire

[Dumitru Ceara]

On 7/12/23 10:51, Dumitru Ceara wrote:
> Hi all,
> 
> During the ovn-heater community meeting organized by Frode yesterday
> (thanks again for that!) we agreed to follow up on some points.  Two of
> these are related to gathering more information that allow us to build
> realistic test scenarios (1) and define targets for them (2).
> 
> On that note we have agreed to prepare a _short_ questionnaire to be
> shared with OpenStack + OVN users (companies and other operators).
> 
> I started a draft document here:
> 
> https://docs.google.com/document/d/151saO5a5PmCt7cIZQ7DkgvU755od76BlN2bKjXc1n08
> 

Based on feedback received both through comments/suggestions in the
google doc and here on-list we seem to have reached a stable version of
the questionnaire.  I tagged the version as V1.

https://docs.google.com/document/d/151saO5a5PmCt7cIZQ7DkgvU755od76BlN2bKjXc1n08/

During yesterday's ovn-heater community meeting we agreed to take a few
minutes from the weekly OVN community meeting (Thursday, 1715 UTC [0])
and iron out any potential last issues before sharing this questionnaire
with users.

Best regards,
Dumitru

[0] https://www.ovn.org/en/#irc-meetings

___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Re: [ovs-dev] [RFC ovn-heater] OVN scale testing with OpenStack workloads - questionnaire

[Dumitru Ceara]

On 7/14/23 09:19, Felix Huettner wrote:
> On Wed, Jul 12, 2023 at 09:38:23PM +0200, Dumitru Ceara wrote:
>> On 7/12/23 14:42, Frode Nordahl wrote:
>>> On Wed, Jul 12, 2023 at 2:31 PM Felix Huettner
>>>  wrote:

 On Wed, Jul 12, 2023 at 01:57:18PM +0200, Dumitru Ceara wrote:
> On 7/12/23 13:00, Felix Huettner wrote:
>> Hi everyone,
>>
>> On Wed, Jul 12, 2023 at 12:29:58PM +0200, Dumitru Ceara wrote:
>>> On 7/12/23 12:04, Frode Nordahl wrote:
 On Wed, Jul 12, 2023 at 10:51 AM Dumitru Ceara  
 wrote:
>
> Hi all,
>
> During the ovn-heater community meeting organized by Frode yesterday
> (thanks again for that!) we agreed to follow up on some points.  Two 
> of
> these are related to gathering more information that allow us to build
> realistic test scenarios (1) and define targets for them (2).
>
> On that note we have agreed to prepare a _short_ questionnaire to be
> shared with OpenStack + OVN users (companies and other operators).
>
> I started a draft document here:
>
> https://docs.google.com/document/d/151saO5a5PmCt7cIZQ7DkgvU755od76BlN2bKjXc1n08
>
> It's mostly based on the previous discussion and information we 
> received
> from Felix Hüttner [0].  I gave access to everyone with the link to
> suggest changes/comment on the document.  Also, if people prefer a
> different way of building this questionnaire (e.g., a PR on
> github/ovn-org/ovn-heater) please let me know.
>
> An additional note: I don't think the goal is to get an 100%
> comprehensive list of all possible workloads and scale targets.  AFAIU
> the intention is to quickly (in a few weeks?) identify a "few" 
> relevant
> types of workloads and start with writing test scenarios for those.  
> We
> could then, incrementally, build on top of that.

 Thanks alot for putting this together, I think it is a great start.

 There is currently no mention of what type of topology is being used
 though, I do not want to complicate things, but I do think we need to
 at least gauge what is used behind the numbers being presented, as it
 would have consequences for how we lay out the tests, and consequently
 what we scale for.

>>>
>>> I was hoping for targets that make sense for all topologies.
>>>
 I think these should cover the most normal cases:

 Gateway topologies:
 * Distributed gateways with distributed FIPs
 * Distributed gateways with centralized NAT
 * Centralized gateways

 IP topologies:
 * Project networks mainly use IPv4 RFC1918 and SNAT/DNAT
 * Project networks mainly use routed IPv4 (no NAT)
 * Project networks mainly use routed IPv6 (no NAT)

>>>
>>> Do we really need to differentiate between IP topologies?  I think the
>>> only significant difference above is NAT vs noNAT.  From ovn-heater
>>> perspective there should be no difference between private and routed
>>> IPv4 or v6.
>>>
>>> If we test and optimize OVN for the worst case and always configure NAT
>>> we should be fine, right?
>>
>> i'm not sure if that works. With centralized gateways it makes a big
>> difference if you have NAT or no NAT. The reason (iirc) is that without
>> NAT you are not actually using these gateways for most of the traffic in
>> your environment. But with NAT you need to use them.
>>
>
> Well, from a control plane perspective, I thought the "worst case" is
> when we also configure NAT.

 thats probably right. Maybe we just stick to it then for now (until we
 see special scaling issues just for the non nat path)
>>>
>>> I brought up the NAT / no NAT cases because with the current way
>>> OpenStack lays out logical routers and logical router ports the
>>> traffic is in practice centralized when not using NAT. But as you
>>> point out, this would be a data plane scaling issue and more a
>>> question to feed into possible future topology changes for OpenStack
>>> Neutron rather than a question informing the control plane scale
>>> testing.
>>>
>>> So I agree, let's drop them.
>>>
 Any suggestions for how to tie these into the questionnaire without
 causing a matrix explosion?

>>>
>>> Not really, but if we only have "Gateway topologies" as a variable then
>>> we end up with a way smaller matrix. :)
>>>
>>
>> i would go for a matrix with gateways (distributed or central) and nat
>> (yes or no).
>>>
>>> +1
>>>
> Should we also give up on the "cluster type" differentiation and just
> focus on "large clusters"?  In the end that's what we want to be able to
> run.

Re: [ovs-dev] [RFC ovn-heater] OVN scale testing with OpenStack workloads - questionnaire

[Felix Huettner via dev]

On Wed, Jul 12, 2023 at 09:38:23PM +0200, Dumitru Ceara wrote:
> On 7/12/23 14:42, Frode Nordahl wrote:
> > On Wed, Jul 12, 2023 at 2:31 PM Felix Huettner
> >  wrote:
> >>
> >> On Wed, Jul 12, 2023 at 01:57:18PM +0200, Dumitru Ceara wrote:
> >>> On 7/12/23 13:00, Felix Huettner wrote:
>  Hi everyone,
> 
>  On Wed, Jul 12, 2023 at 12:29:58PM +0200, Dumitru Ceara wrote:
> > On 7/12/23 12:04, Frode Nordahl wrote:
> >> On Wed, Jul 12, 2023 at 10:51 AM Dumitru Ceara  
> >> wrote:
> >>>
> >>> Hi all,
> >>>
> >>> During the ovn-heater community meeting organized by Frode yesterday
> >>> (thanks again for that!) we agreed to follow up on some points.  Two 
> >>> of
> >>> these are related to gathering more information that allow us to build
> >>> realistic test scenarios (1) and define targets for them (2).
> >>>
> >>> On that note we have agreed to prepare a _short_ questionnaire to be
> >>> shared with OpenStack + OVN users (companies and other operators).
> >>>
> >>> I started a draft document here:
> >>>
> >>> https://docs.google.com/document/d/151saO5a5PmCt7cIZQ7DkgvU755od76BlN2bKjXc1n08
> >>>
> >>> It's mostly based on the previous discussion and information we 
> >>> received
> >>> from Felix Hüttner [0].  I gave access to everyone with the link to
> >>> suggest changes/comment on the document.  Also, if people prefer a
> >>> different way of building this questionnaire (e.g., a PR on
> >>> github/ovn-org/ovn-heater) please let me know.
> >>>
> >>> An additional note: I don't think the goal is to get an 100%
> >>> comprehensive list of all possible workloads and scale targets.  AFAIU
> >>> the intention is to quickly (in a few weeks?) identify a "few" 
> >>> relevant
> >>> types of workloads and start with writing test scenarios for those.  
> >>> We
> >>> could then, incrementally, build on top of that.
> >>
> >> Thanks alot for putting this together, I think it is a great start.
> >>
> >> There is currently no mention of what type of topology is being used
> >> though, I do not want to complicate things, but I do think we need to
> >> at least gauge what is used behind the numbers being presented, as it
> >> would have consequences for how we lay out the tests, and consequently
> >> what we scale for.
> >>
> >
> > I was hoping for targets that make sense for all topologies.
> >
> >> I think these should cover the most normal cases:
> >>
> >> Gateway topologies:
> >> * Distributed gateways with distributed FIPs
> >> * Distributed gateways with centralized NAT
> >> * Centralized gateways
> >>
> >> IP topologies:
> >> * Project networks mainly use IPv4 RFC1918 and SNAT/DNAT
> >> * Project networks mainly use routed IPv4 (no NAT)
> >> * Project networks mainly use routed IPv6 (no NAT)
> >>
> >
> > Do we really need to differentiate between IP topologies?  I think the
> > only significant difference above is NAT vs noNAT.  From ovn-heater
> > perspective there should be no difference between private and routed
> > IPv4 or v6.
> >
> > If we test and optimize OVN for the worst case and always configure NAT
> > we should be fine, right?
> 
>  i'm not sure if that works. With centralized gateways it makes a big
>  difference if you have NAT or no NAT. The reason (iirc) is that without
>  NAT you are not actually using these gateways for most of the traffic in
>  your environment. But with NAT you need to use them.
> 
> >>>
> >>> Well, from a control plane perspective, I thought the "worst case" is
> >>> when we also configure NAT.
> >>
> >> thats probably right. Maybe we just stick to it then for now (until we
> >> see special scaling issues just for the non nat path)
> >
> > I brought up the NAT / no NAT cases because with the current way
> > OpenStack lays out logical routers and logical router ports the
> > traffic is in practice centralized when not using NAT. But as you
> > point out, this would be a data plane scaling issue and more a
> > question to feed into possible future topology changes for OpenStack
> > Neutron rather than a question informing the control plane scale
> > testing.
> >
> > So I agree, let's drop them.
> >
> >> Any suggestions for how to tie these into the questionnaire without
> >> causing a matrix explosion?
> >>
> >
> > Not really, but if we only have "Gateway topologies" as a variable then
> > we end up with a way smaller matrix. :)
> >
> 
>  i would go for a matrix with gateways (distributed or central) and nat
>  (yes or no).
> >
> > +1
> >
> >>> Should we also give up on the "cluster type" differentiation and just
> >>> focus on "large clusters"?  In the end that's what we want to be able to
> >>> run.
> >>
> >> I think that makes sense. If someone 

Re: [ovs-dev] [RFC ovn-heater] OVN scale testing with OpenStack workloads - questionnaire

[Odintsov Vladislav]

On 12 Jul 2023, at 23:09, Dumitru Ceara  wrote:

On 7/12/23 21:46, Odintsov Vladislav wrote:
Hi Dumitru,


Hi Vladislav,

first of all, I’l like to mention that’s a great idea!
I’m wondering wether ovn interconnection infrastructure and ovn vtep could also 
be a part of this testing?


There's actually already work in progress to add ovn interconnection
support to the current ovn-heater workloads.  Lorenzo, in cc, is working
on that:

https://github.com/ovn-org/ovn-heater/pull/169


Oh, that’s very good, thanks!

OVN VTEP was not on our immediate list but it's definitely nice to have.
Do you maybe have time to contribute a formal description of the OVN
VTEP topology and maybe what workloads to simulate on it for testing the
control plane?

I’ll try to see if I can do anything in this direction.


Thanks!

On 12 Jul 2023, at 22:38, Dumitru Ceara  wrote:

On 7/12/23 14:42, Frode Nordahl wrote:
On Wed, Jul 12, 2023 at 2:31 PM Felix Huettner
 wrote:

On Wed, Jul 12, 2023 at 01:57:18PM +0200, Dumitru Ceara wrote:
On 7/12/23 13:00, Felix Huettner wrote:
Hi everyone,

On Wed, Jul 12, 2023 at 12:29:58PM +0200, Dumitru Ceara wrote:
On 7/12/23 12:04, Frode Nordahl wrote:
On Wed, Jul 12, 2023 at 10:51 AM Dumitru Ceara  wrote:

Hi all,

During the ovn-heater community meeting organized by Frode yesterday
(thanks again for that!) we agreed to follow up on some points.  Two of
these are related to gathering more information that allow us to build
realistic test scenarios (1) and define targets for them (2).

On that note we have agreed to prepare a _short_ questionnaire to be
shared with OpenStack + OVN users (companies and other operators).

I started a draft document here:

https://docs.google.com/document/d/151saO5a5PmCt7cIZQ7DkgvU755od76BlN2bKjXc1n08

It's mostly based on the previous discussion and information we received
from Felix Hüttner [0].  I gave access to everyone with the link to
suggest changes/comment on the document.  Also, if people prefer a
different way of building this questionnaire (e.g., a PR on
github/ovn-org/ovn-heater) please let me know.

An additional note: I don't think the goal is to get an 100%
comprehensive list of all possible workloads and scale targets.  AFAIU
the intention is to quickly (in a few weeks?) identify a "few" relevant
types of workloads and start with writing test scenarios for those.  We
could then, incrementally, build on top of that.

Thanks alot for putting this together, I think it is a great start.

There is currently no mention of what type of topology is being used
though, I do not want to complicate things, but I do think we need to
at least gauge what is used behind the numbers being presented, as it
would have consequences for how we lay out the tests, and consequently
what we scale for.


I was hoping for targets that make sense for all topologies.

I think these should cover the most normal cases:

Gateway topologies:
* Distributed gateways with distributed FIPs
* Distributed gateways with centralized NAT
* Centralized gateways

IP topologies:
* Project networks mainly use IPv4 RFC1918 and SNAT/DNAT
* Project networks mainly use routed IPv4 (no NAT)
* Project networks mainly use routed IPv6 (no NAT)


Do we really need to differentiate between IP topologies?  I think the
only significant difference above is NAT vs noNAT.  From ovn-heater
perspective there should be no difference between private and routed
IPv4 or v6.

If we test and optimize OVN for the worst case and always configure NAT
we should be fine, right?

i'm not sure if that works. With centralized gateways it makes a big
difference if you have NAT or no NAT. The reason (iirc) is that without
NAT you are not actually using these gateways for most of the traffic in
your environment. But with NAT you need to use them.


Well, from a control plane perspective, I thought the "worst case" is
when we also configure NAT.

thats probably right. Maybe we just stick to it then for now (until we
see special scaling issues just for the non nat path)

I brought up the NAT / no NAT cases because with the current way
OpenStack lays out logical routers and logical router ports the
traffic is in practice centralized when not using NAT. But as you
point out, this would be a data plane scaling issue and more a
question to feed into possible future topology changes for OpenStack
Neutron rather than a question informing the control plane scale
testing.

So I agree, let's drop them.

Any suggestions for how to tie these into the questionnaire without
causing a matrix explosion?


Not really, but if we only have "Gateway topologies" as a variable then
we end up with a way smaller matrix. :)


i would go for a matrix with gateways (distributed or central) and nat
(yes or no).

+1

Should we also give up on the "cluster type" differentiation and just
focus on "large clusters"?  In the end that's what we want to be able to
run.

I think that makes sense. If someone finds a small cluster that has
issues thats probably also 

Re: [ovs-dev] [RFC ovn-heater] OVN scale testing with OpenStack workloads - questionnaire

[Dumitru Ceara]

On 7/12/23 21:46, Odintsov Vladislav wrote:
> Hi Dumitru,
> 

Hi Vladislav,

> first of all, I’l like to mention that’s a great idea!
> I’m wondering wether ovn interconnection infrastructure and ovn vtep could 
> also be a part of this testing?
> 

There's actually already work in progress to add ovn interconnection
support to the current ovn-heater workloads.  Lorenzo, in cc, is working
on that:

https://github.com/ovn-org/ovn-heater/pull/169

OVN VTEP was not on our immediate list but it's definitely nice to have.
 Do you maybe have time to contribute a formal description of the OVN
VTEP topology and maybe what workloads to simulate on it for testing the
control plane?

Thanks!

> On 12 Jul 2023, at 22:38, Dumitru Ceara  wrote:
> 
> On 7/12/23 14:42, Frode Nordahl wrote:
> On Wed, Jul 12, 2023 at 2:31 PM Felix Huettner
>  wrote:
> 
> On Wed, Jul 12, 2023 at 01:57:18PM +0200, Dumitru Ceara wrote:
> On 7/12/23 13:00, Felix Huettner wrote:
> Hi everyone,
> 
> On Wed, Jul 12, 2023 at 12:29:58PM +0200, Dumitru Ceara wrote:
> On 7/12/23 12:04, Frode Nordahl wrote:
> On Wed, Jul 12, 2023 at 10:51 AM Dumitru Ceara  wrote:
> 
> Hi all,
> 
> During the ovn-heater community meeting organized by Frode yesterday
> (thanks again for that!) we agreed to follow up on some points.  Two of
> these are related to gathering more information that allow us to build
> realistic test scenarios (1) and define targets for them (2).
> 
> On that note we have agreed to prepare a _short_ questionnaire to be
> shared with OpenStack + OVN users (companies and other operators).
> 
> I started a draft document here:
> 
> https://docs.google.com/document/d/151saO5a5PmCt7cIZQ7DkgvU755od76BlN2bKjXc1n08
> 
> It's mostly based on the previous discussion and information we received
> from Felix Hüttner [0].  I gave access to everyone with the link to
> suggest changes/comment on the document.  Also, if people prefer a
> different way of building this questionnaire (e.g., a PR on
> github/ovn-org/ovn-heater) please let me know.
> 
> An additional note: I don't think the goal is to get an 100%
> comprehensive list of all possible workloads and scale targets.  AFAIU
> the intention is to quickly (in a few weeks?) identify a "few" relevant
> types of workloads and start with writing test scenarios for those.  We
> could then, incrementally, build on top of that.
> 
> Thanks alot for putting this together, I think it is a great start.
> 
> There is currently no mention of what type of topology is being used
> though, I do not want to complicate things, but I do think we need to
> at least gauge what is used behind the numbers being presented, as it
> would have consequences for how we lay out the tests, and consequently
> what we scale for.
> 
> 
> I was hoping for targets that make sense for all topologies.
> 
> I think these should cover the most normal cases:
> 
> Gateway topologies:
> * Distributed gateways with distributed FIPs
> * Distributed gateways with centralized NAT
> * Centralized gateways
> 
> IP topologies:
> * Project networks mainly use IPv4 RFC1918 and SNAT/DNAT
> * Project networks mainly use routed IPv4 (no NAT)
> * Project networks mainly use routed IPv6 (no NAT)
> 
> 
> Do we really need to differentiate between IP topologies?  I think the
> only significant difference above is NAT vs noNAT.  From ovn-heater
> perspective there should be no difference between private and routed
> IPv4 or v6.
> 
> If we test and optimize OVN for the worst case and always configure NAT
> we should be fine, right?
> 
> i'm not sure if that works. With centralized gateways it makes a big
> difference if you have NAT or no NAT. The reason (iirc) is that without
> NAT you are not actually using these gateways for most of the traffic in
> your environment. But with NAT you need to use them.
> 
> 
> Well, from a control plane perspective, I thought the "worst case" is
> when we also configure NAT.
> 
> thats probably right. Maybe we just stick to it then for now (until we
> see special scaling issues just for the non nat path)
> 
> I brought up the NAT / no NAT cases because with the current way
> OpenStack lays out logical routers and logical router ports the
> traffic is in practice centralized when not using NAT. But as you
> point out, this would be a data plane scaling issue and more a
> question to feed into possible future topology changes for OpenStack
> Neutron rather than a question informing the control plane scale
> testing.
> 
> So I agree, let's drop them.
> 
> Any suggestions for how to tie these into the questionnaire without
> causing a matrix explosion?
> 
> 
> Not really, but if we only have "Gateway topologies" as a variable then
> we end up with a way smaller matrix. :)
> 
> 
> i would go for a matrix with gateways (distributed or central) and nat
> (yes or no).
> 
> +1
> 
> Should we also give up on the "cluster type" differentiation and just
> focus on "large clusters"?  In the end that's what we want to be able to
> run.
> 

Re: [ovs-dev] [RFC ovn-heater] OVN scale testing with OpenStack workloads - questionnaire

[Odintsov Vladislav]

Hi Dumitru,

first of all, I’l like to mention that’s a great idea!
I’m wondering wether ovn interconnection infrastructure and ovn vtep could also 
be a part of this testing?

On 12 Jul 2023, at 22:38, Dumitru Ceara  wrote:

On 7/12/23 14:42, Frode Nordahl wrote:
On Wed, Jul 12, 2023 at 2:31 PM Felix Huettner
 wrote:

On Wed, Jul 12, 2023 at 01:57:18PM +0200, Dumitru Ceara wrote:
On 7/12/23 13:00, Felix Huettner wrote:
Hi everyone,

On Wed, Jul 12, 2023 at 12:29:58PM +0200, Dumitru Ceara wrote:
On 7/12/23 12:04, Frode Nordahl wrote:
On Wed, Jul 12, 2023 at 10:51 AM Dumitru Ceara  wrote:

Hi all,

During the ovn-heater community meeting organized by Frode yesterday
(thanks again for that!) we agreed to follow up on some points.  Two of
these are related to gathering more information that allow us to build
realistic test scenarios (1) and define targets for them (2).

On that note we have agreed to prepare a _short_ questionnaire to be
shared with OpenStack + OVN users (companies and other operators).

I started a draft document here:

https://docs.google.com/document/d/151saO5a5PmCt7cIZQ7DkgvU755od76BlN2bKjXc1n08

It's mostly based on the previous discussion and information we received
from Felix Hüttner [0].  I gave access to everyone with the link to
suggest changes/comment on the document.  Also, if people prefer a
different way of building this questionnaire (e.g., a PR on
github/ovn-org/ovn-heater) please let me know.

An additional note: I don't think the goal is to get an 100%
comprehensive list of all possible workloads and scale targets.  AFAIU
the intention is to quickly (in a few weeks?) identify a "few" relevant
types of workloads and start with writing test scenarios for those.  We
could then, incrementally, build on top of that.

Thanks alot for putting this together, I think it is a great start.

There is currently no mention of what type of topology is being used
though, I do not want to complicate things, but I do think we need to
at least gauge what is used behind the numbers being presented, as it
would have consequences for how we lay out the tests, and consequently
what we scale for.


I was hoping for targets that make sense for all topologies.

I think these should cover the most normal cases:

Gateway topologies:
* Distributed gateways with distributed FIPs
* Distributed gateways with centralized NAT
* Centralized gateways

IP topologies:
* Project networks mainly use IPv4 RFC1918 and SNAT/DNAT
* Project networks mainly use routed IPv4 (no NAT)
* Project networks mainly use routed IPv6 (no NAT)


Do we really need to differentiate between IP topologies?  I think the
only significant difference above is NAT vs noNAT.  From ovn-heater
perspective there should be no difference between private and routed
IPv4 or v6.

If we test and optimize OVN for the worst case and always configure NAT
we should be fine, right?

i'm not sure if that works. With centralized gateways it makes a big
difference if you have NAT or no NAT. The reason (iirc) is that without
NAT you are not actually using these gateways for most of the traffic in
your environment. But with NAT you need to use them.


Well, from a control plane perspective, I thought the "worst case" is
when we also configure NAT.

thats probably right. Maybe we just stick to it then for now (until we
see special scaling issues just for the non nat path)

I brought up the NAT / no NAT cases because with the current way
OpenStack lays out logical routers and logical router ports the
traffic is in practice centralized when not using NAT. But as you
point out, this would be a data plane scaling issue and more a
question to feed into possible future topology changes for OpenStack
Neutron rather than a question informing the control plane scale
testing.

So I agree, let's drop them.

Any suggestions for how to tie these into the questionnaire without
causing a matrix explosion?


Not really, but if we only have "Gateway topologies" as a variable then
we end up with a way smaller matrix. :)


i would go for a matrix with gateways (distributed or central) and nat
(yes or no).

+1

Should we also give up on the "cluster type" differentiation and just
focus on "large clusters"?  In the end that's what we want to be able to
run.

I think that makes sense. If someone finds a small cluster that has
issues thats probably also interesting, but they will hopefully write
that in there as well.

+1


Thanks, Felix and Frode!  I tried to re-phrase the questionnaire
according to our discussion until now.  I ended up with two topologies
(distributed/centralized gateways) and questions applicable to both
topologies.  NAT vs noNAT is now expressed through two different questions.

I created an "RFC-v1" document version before these changes so we can
always roll back to that but I'm not sure if anyone else except the
owner of the document can actually see it.

On a different note, I'm starting to wonder if this "questionnaire"
shouldn't just live in a form or 

Re: [ovs-dev] [RFC ovn-heater] OVN scale testing with OpenStack workloads - questionnaire

[Dumitru Ceara]

On 7/12/23 14:42, Frode Nordahl wrote:
> On Wed, Jul 12, 2023 at 2:31 PM Felix Huettner
>  wrote:
>>
>> On Wed, Jul 12, 2023 at 01:57:18PM +0200, Dumitru Ceara wrote:
>>> On 7/12/23 13:00, Felix Huettner wrote:
 Hi everyone,

 On Wed, Jul 12, 2023 at 12:29:58PM +0200, Dumitru Ceara wrote:
> On 7/12/23 12:04, Frode Nordahl wrote:
>> On Wed, Jul 12, 2023 at 10:51 AM Dumitru Ceara  wrote:
>>>
>>> Hi all,
>>>
>>> During the ovn-heater community meeting organized by Frode yesterday
>>> (thanks again for that!) we agreed to follow up on some points.  Two of
>>> these are related to gathering more information that allow us to build
>>> realistic test scenarios (1) and define targets for them (2).
>>>
>>> On that note we have agreed to prepare a _short_ questionnaire to be
>>> shared with OpenStack + OVN users (companies and other operators).
>>>
>>> I started a draft document here:
>>>
>>> https://docs.google.com/document/d/151saO5a5PmCt7cIZQ7DkgvU755od76BlN2bKjXc1n08
>>>
>>> It's mostly based on the previous discussion and information we received
>>> from Felix Hüttner [0].  I gave access to everyone with the link to
>>> suggest changes/comment on the document.  Also, if people prefer a
>>> different way of building this questionnaire (e.g., a PR on
>>> github/ovn-org/ovn-heater) please let me know.
>>>
>>> An additional note: I don't think the goal is to get an 100%
>>> comprehensive list of all possible workloads and scale targets.  AFAIU
>>> the intention is to quickly (in a few weeks?) identify a "few" relevant
>>> types of workloads and start with writing test scenarios for those.  We
>>> could then, incrementally, build on top of that.
>>
>> Thanks alot for putting this together, I think it is a great start.
>>
>> There is currently no mention of what type of topology is being used
>> though, I do not want to complicate things, but I do think we need to
>> at least gauge what is used behind the numbers being presented, as it
>> would have consequences for how we lay out the tests, and consequently
>> what we scale for.
>>
>
> I was hoping for targets that make sense for all topologies.
>
>> I think these should cover the most normal cases:
>>
>> Gateway topologies:
>> * Distributed gateways with distributed FIPs
>> * Distributed gateways with centralized NAT
>> * Centralized gateways
>>
>> IP topologies:
>> * Project networks mainly use IPv4 RFC1918 and SNAT/DNAT
>> * Project networks mainly use routed IPv4 (no NAT)
>> * Project networks mainly use routed IPv6 (no NAT)
>>
>
> Do we really need to differentiate between IP topologies?  I think the
> only significant difference above is NAT vs noNAT.  From ovn-heater
> perspective there should be no difference between private and routed
> IPv4 or v6.
>
> If we test and optimize OVN for the worst case and always configure NAT
> we should be fine, right?

 i'm not sure if that works. With centralized gateways it makes a big
 difference if you have NAT or no NAT. The reason (iirc) is that without
 NAT you are not actually using these gateways for most of the traffic in
 your environment. But with NAT you need to use them.

>>>
>>> Well, from a control plane perspective, I thought the "worst case" is
>>> when we also configure NAT.
>>
>> thats probably right. Maybe we just stick to it then for now (until we
>> see special scaling issues just for the non nat path)
> 
> I brought up the NAT / no NAT cases because with the current way
> OpenStack lays out logical routers and logical router ports the
> traffic is in practice centralized when not using NAT. But as you
> point out, this would be a data plane scaling issue and more a
> question to feed into possible future topology changes for OpenStack
> Neutron rather than a question informing the control plane scale
> testing.
> 
> So I agree, let's drop them.
> 
>> Any suggestions for how to tie these into the questionnaire without
>> causing a matrix explosion?
>>
>
> Not really, but if we only have "Gateway topologies" as a variable then
> we end up with a way smaller matrix. :)
>

 i would go for a matrix with gateways (distributed or central) and nat
 (yes or no).
> 
> +1
> 
>>> Should we also give up on the "cluster type" differentiation and just
>>> focus on "large clusters"?  In the end that's what we want to be able to
>>> run.
>>
>> I think that makes sense. If someone finds a small cluster that has
>> issues thats probably also interesting, but they will hopefully write
>> that in there as well.
> 
> +1
> 

Thanks, Felix and Frode!  I tried to re-phrase the questionnaire
according to our discussion until now.  I ended up with two topologies
(distributed/centralized gateways) and questions 

Re: [ovs-dev] [RFC ovn-heater] OVN scale testing with OpenStack workloads - questionnaire

[Frode Nordahl]

On Wed, Jul 12, 2023 at 2:31 PM Felix Huettner
 wrote:
>
> On Wed, Jul 12, 2023 at 01:57:18PM +0200, Dumitru Ceara wrote:
> > On 7/12/23 13:00, Felix Huettner wrote:
> > > Hi everyone,
> > >
> > > On Wed, Jul 12, 2023 at 12:29:58PM +0200, Dumitru Ceara wrote:
> > >> On 7/12/23 12:04, Frode Nordahl wrote:
> > >>> On Wed, Jul 12, 2023 at 10:51 AM Dumitru Ceara  
> > >>> wrote:
> > 
> >  Hi all,
> > 
> >  During the ovn-heater community meeting organized by Frode yesterday
> >  (thanks again for that!) we agreed to follow up on some points.  Two of
> >  these are related to gathering more information that allow us to build
> >  realistic test scenarios (1) and define targets for them (2).
> > 
> >  On that note we have agreed to prepare a _short_ questionnaire to be
> >  shared with OpenStack + OVN users (companies and other operators).
> > 
> >  I started a draft document here:
> > 
> >  https://docs.google.com/document/d/151saO5a5PmCt7cIZQ7DkgvU755od76BlN2bKjXc1n08
> > 
> >  It's mostly based on the previous discussion and information we 
> >  received
> >  from Felix Hüttner [0].  I gave access to everyone with the link to
> >  suggest changes/comment on the document.  Also, if people prefer a
> >  different way of building this questionnaire (e.g., a PR on
> >  github/ovn-org/ovn-heater) please let me know.
> > 
> >  An additional note: I don't think the goal is to get an 100%
> >  comprehensive list of all possible workloads and scale targets.  AFAIU
> >  the intention is to quickly (in a few weeks?) identify a "few" relevant
> >  types of workloads and start with writing test scenarios for those.  We
> >  could then, incrementally, build on top of that.
> > >>>
> > >>> Thanks alot for putting this together, I think it is a great start.
> > >>>
> > >>> There is currently no mention of what type of topology is being used
> > >>> though, I do not want to complicate things, but I do think we need to
> > >>> at least gauge what is used behind the numbers being presented, as it
> > >>> would have consequences for how we lay out the tests, and consequently
> > >>> what we scale for.
> > >>>
> > >>
> > >> I was hoping for targets that make sense for all topologies.
> > >>
> > >>> I think these should cover the most normal cases:
> > >>>
> > >>> Gateway topologies:
> > >>> * Distributed gateways with distributed FIPs
> > >>> * Distributed gateways with centralized NAT
> > >>> * Centralized gateways
> > >>>
> > >>> IP topologies:
> > >>> * Project networks mainly use IPv4 RFC1918 and SNAT/DNAT
> > >>> * Project networks mainly use routed IPv4 (no NAT)
> > >>> * Project networks mainly use routed IPv6 (no NAT)
> > >>>
> > >>
> > >> Do we really need to differentiate between IP topologies?  I think the
> > >> only significant difference above is NAT vs noNAT.  From ovn-heater
> > >> perspective there should be no difference between private and routed
> > >> IPv4 or v6.
> > >>
> > >> If we test and optimize OVN for the worst case and always configure NAT
> > >> we should be fine, right?
> > >
> > > i'm not sure if that works. With centralized gateways it makes a big
> > > difference if you have NAT or no NAT. The reason (iirc) is that without
> > > NAT you are not actually using these gateways for most of the traffic in
> > > your environment. But with NAT you need to use them.
> > >
> >
> > Well, from a control plane perspective, I thought the "worst case" is
> > when we also configure NAT.
>
> thats probably right. Maybe we just stick to it then for now (until we
> see special scaling issues just for the non nat path)

I brought up the NAT / no NAT cases because with the current way
OpenStack lays out logical routers and logical router ports the
traffic is in practice centralized when not using NAT. But as you
point out, this would be a data plane scaling issue and more a
question to feed into possible future topology changes for OpenStack
Neutron rather than a question informing the control plane scale
testing.

So I agree, let's drop them.

> > >>> Any suggestions for how to tie these into the questionnaire without
> > >>> causing a matrix explosion?
> > >>>
> > >>
> > >> Not really, but if we only have "Gateway topologies" as a variable then
> > >> we end up with a way smaller matrix. :)
> > >>
> > >
> > > i would go for a matrix with gateways (distributed or central) and nat
> > > (yes or no).

+1

> > Should we also give up on the "cluster type" differentiation and just
> > focus on "large clusters"?  In the end that's what we want to be able to
> > run.
>
> I think that makes sense. If someone finds a small cluster that has
> issues thats probably also interesting, but they will hopefully write
> that in there as well.

+1

-- 
Frode Nordahl

> >
> > > Thanks
> > > Felix
> > > Diese E Mail enthält möglicherweise vertrauliche Inhalte und ist nur für 
> > > die Verwertung durch den vorgesehenen 

Re: [ovs-dev] [RFC ovn-heater] OVN scale testing with OpenStack workloads - questionnaire

[Felix Huettner via dev]

On Wed, Jul 12, 2023 at 01:57:18PM +0200, Dumitru Ceara wrote:
> On 7/12/23 13:00, Felix Huettner wrote:
> > Hi everyone,
> >
> > On Wed, Jul 12, 2023 at 12:29:58PM +0200, Dumitru Ceara wrote:
> >> On 7/12/23 12:04, Frode Nordahl wrote:
> >>> On Wed, Jul 12, 2023 at 10:51 AM Dumitru Ceara  wrote:
> 
>  Hi all,
> 
>  During the ovn-heater community meeting organized by Frode yesterday
>  (thanks again for that!) we agreed to follow up on some points.  Two of
>  these are related to gathering more information that allow us to build
>  realistic test scenarios (1) and define targets for them (2).
> 
>  On that note we have agreed to prepare a _short_ questionnaire to be
>  shared with OpenStack + OVN users (companies and other operators).
> 
>  I started a draft document here:
> 
>  https://docs.google.com/document/d/151saO5a5PmCt7cIZQ7DkgvU755od76BlN2bKjXc1n08
> 
>  It's mostly based on the previous discussion and information we received
>  from Felix Hüttner [0].  I gave access to everyone with the link to
>  suggest changes/comment on the document.  Also, if people prefer a
>  different way of building this questionnaire (e.g., a PR on
>  github/ovn-org/ovn-heater) please let me know.
> 
>  An additional note: I don't think the goal is to get an 100%
>  comprehensive list of all possible workloads and scale targets.  AFAIU
>  the intention is to quickly (in a few weeks?) identify a "few" relevant
>  types of workloads and start with writing test scenarios for those.  We
>  could then, incrementally, build on top of that.
> >>>
> >>> Thanks alot for putting this together, I think it is a great start.
> >>>
> >>> There is currently no mention of what type of topology is being used
> >>> though, I do not want to complicate things, but I do think we need to
> >>> at least gauge what is used behind the numbers being presented, as it
> >>> would have consequences for how we lay out the tests, and consequently
> >>> what we scale for.
> >>>
> >>
> >> I was hoping for targets that make sense for all topologies.
> >>
> >>> I think these should cover the most normal cases:
> >>>
> >>> Gateway topologies:
> >>> * Distributed gateways with distributed FIPs
> >>> * Distributed gateways with centralized NAT
> >>> * Centralized gateways
> >>>
> >>> IP topologies:
> >>> * Project networks mainly use IPv4 RFC1918 and SNAT/DNAT
> >>> * Project networks mainly use routed IPv4 (no NAT)
> >>> * Project networks mainly use routed IPv6 (no NAT)
> >>>
> >>
> >> Do we really need to differentiate between IP topologies?  I think the
> >> only significant difference above is NAT vs noNAT.  From ovn-heater
> >> perspective there should be no difference between private and routed
> >> IPv4 or v6.
> >>
> >> If we test and optimize OVN for the worst case and always configure NAT
> >> we should be fine, right?
> >
> > i'm not sure if that works. With centralized gateways it makes a big
> > difference if you have NAT or no NAT. The reason (iirc) is that without
> > NAT you are not actually using these gateways for most of the traffic in
> > your environment. But with NAT you need to use them.
> >
>
> Well, from a control plane perspective, I thought the "worst case" is
> when we also configure NAT.

thats probably right. Maybe we just stick to it then for now (until we
see special scaling issues just for the non nat path)
>
> >>
> >>> Any suggestions for how to tie these into the questionnaire without
> >>> causing a matrix explosion?
> >>>
> >>
> >> Not really, but if we only have "Gateway topologies" as a variable then
> >> we end up with a way smaller matrix. :)
> >>
> >
> > i would go for a matrix with gateways (distributed or central) and nat
> > (yes or no).
> >
>
> Should we also give up on the "cluster type" differentiation and just
> focus on "large clusters"?  In the end that's what we want to be able to
> run.

I think that makes sense. If someone finds a small cluster that has
issues thats probably also interesting, but they will hopefully write
that in there as well.
>
> > Thanks
> > Felix
> > Diese E Mail enthält möglicherweise vertrauliche Inhalte und ist nur für 
> > die Verwertung durch den vorgesehenen Empfänger bestimmt.
> > Sollten Sie nicht der vorgesehene Empfänger sein, setzen Sie den Absender 
> > bitte unverzüglich in Kenntnis und löschen diese E Mail.
> >
> > Hinweise zum Datenschutz finden Sie hier.
> >
> >
> > This e-mail may contain confidential content and is intended only for the 
> > specified recipient/s.
> > If you are not the intended recipient, please inform the sender immediately 
> > and delete this e-mail.
> >
> > Information on data protection can be found 
> > here.
> >
>
Diese E Mail enthält möglicherweise vertrauliche Inhalte und ist nur für die 
Verwertung durch den vorgesehenen Empfänger bestimmt.
Sollten Sie nicht der 

Re: [ovs-dev] [RFC ovn-heater] OVN scale testing with OpenStack workloads - questionnaire

[Dumitru Ceara]

On 7/12/23 13:00, Felix Huettner wrote:
> Hi everyone,
> 
> On Wed, Jul 12, 2023 at 12:29:58PM +0200, Dumitru Ceara wrote:
>> On 7/12/23 12:04, Frode Nordahl wrote:
>>> On Wed, Jul 12, 2023 at 10:51 AM Dumitru Ceara  wrote:

 Hi all,

 During the ovn-heater community meeting organized by Frode yesterday
 (thanks again for that!) we agreed to follow up on some points.  Two of
 these are related to gathering more information that allow us to build
 realistic test scenarios (1) and define targets for them (2).

 On that note we have agreed to prepare a _short_ questionnaire to be
 shared with OpenStack + OVN users (companies and other operators).

 I started a draft document here:

 https://docs.google.com/document/d/151saO5a5PmCt7cIZQ7DkgvU755od76BlN2bKjXc1n08

 It's mostly based on the previous discussion and information we received
 from Felix Hüttner [0].  I gave access to everyone with the link to
 suggest changes/comment on the document.  Also, if people prefer a
 different way of building this questionnaire (e.g., a PR on
 github/ovn-org/ovn-heater) please let me know.

 An additional note: I don't think the goal is to get an 100%
 comprehensive list of all possible workloads and scale targets.  AFAIU
 the intention is to quickly (in a few weeks?) identify a "few" relevant
 types of workloads and start with writing test scenarios for those.  We
 could then, incrementally, build on top of that.
>>>
>>> Thanks alot for putting this together, I think it is a great start.
>>>
>>> There is currently no mention of what type of topology is being used
>>> though, I do not want to complicate things, but I do think we need to
>>> at least gauge what is used behind the numbers being presented, as it
>>> would have consequences for how we lay out the tests, and consequently
>>> what we scale for.
>>>
>>
>> I was hoping for targets that make sense for all topologies.
>>
>>> I think these should cover the most normal cases:
>>>
>>> Gateway topologies:
>>> * Distributed gateways with distributed FIPs
>>> * Distributed gateways with centralized NAT
>>> * Centralized gateways
>>>
>>> IP topologies:
>>> * Project networks mainly use IPv4 RFC1918 and SNAT/DNAT
>>> * Project networks mainly use routed IPv4 (no NAT)
>>> * Project networks mainly use routed IPv6 (no NAT)
>>>
>>
>> Do we really need to differentiate between IP topologies?  I think the
>> only significant difference above is NAT vs noNAT.  From ovn-heater
>> perspective there should be no difference between private and routed
>> IPv4 or v6.
>>
>> If we test and optimize OVN for the worst case and always configure NAT
>> we should be fine, right?
> 
> i'm not sure if that works. With centralized gateways it makes a big
> difference if you have NAT or no NAT. The reason (iirc) is that without
> NAT you are not actually using these gateways for most of the traffic in
> your environment. But with NAT you need to use them.
> 

Well, from a control plane perspective, I thought the "worst case" is
when we also configure NAT.

>>
>>> Any suggestions for how to tie these into the questionnaire without
>>> causing a matrix explosion?
>>>
>>
>> Not really, but if we only have "Gateway topologies" as a variable then
>> we end up with a way smaller matrix. :)
>>
> 
> i would go for a matrix with gateways (distributed or central) and nat
> (yes or no).
> 

Should we also give up on the "cluster type" differentiation and just
focus on "large clusters"?  In the end that's what we want to be able to
run.

> Thanks
> Felix
> Diese E Mail enthält möglicherweise vertrauliche Inhalte und ist nur für die 
> Verwertung durch den vorgesehenen Empfänger bestimmt.
> Sollten Sie nicht der vorgesehene Empfänger sein, setzen Sie den Absender 
> bitte unverzüglich in Kenntnis und löschen diese E Mail.
> 
> Hinweise zum Datenschutz finden Sie hier.
> 
> 
> This e-mail may contain confidential content and is intended only for the 
> specified recipient/s.
> If you are not the intended recipient, please inform the sender immediately 
> and delete this e-mail.
> 
> Information on data protection can be found 
> here.
> 

___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Re: [ovs-dev] [RFC ovn-heater] OVN scale testing with OpenStack workloads - questionnaire

[Felix Huettner via dev]

Hi everyone,

On Wed, Jul 12, 2023 at 12:29:58PM +0200, Dumitru Ceara wrote:
> On 7/12/23 12:04, Frode Nordahl wrote:
> > On Wed, Jul 12, 2023 at 10:51 AM Dumitru Ceara  wrote:
> >>
> >> Hi all,
> >>
> >> During the ovn-heater community meeting organized by Frode yesterday
> >> (thanks again for that!) we agreed to follow up on some points.  Two of
> >> these are related to gathering more information that allow us to build
> >> realistic test scenarios (1) and define targets for them (2).
> >>
> >> On that note we have agreed to prepare a _short_ questionnaire to be
> >> shared with OpenStack + OVN users (companies and other operators).
> >>
> >> I started a draft document here:
> >>
> >> https://docs.google.com/document/d/151saO5a5PmCt7cIZQ7DkgvU755od76BlN2bKjXc1n08
> >>
> >> It's mostly based on the previous discussion and information we received
> >> from Felix Hüttner [0].  I gave access to everyone with the link to
> >> suggest changes/comment on the document.  Also, if people prefer a
> >> different way of building this questionnaire (e.g., a PR on
> >> github/ovn-org/ovn-heater) please let me know.
> >>
> >> An additional note: I don't think the goal is to get an 100%
> >> comprehensive list of all possible workloads and scale targets.  AFAIU
> >> the intention is to quickly (in a few weeks?) identify a "few" relevant
> >> types of workloads and start with writing test scenarios for those.  We
> >> could then, incrementally, build on top of that.
> >
> > Thanks alot for putting this together, I think it is a great start.
> >
> > There is currently no mention of what type of topology is being used
> > though, I do not want to complicate things, but I do think we need to
> > at least gauge what is used behind the numbers being presented, as it
> > would have consequences for how we lay out the tests, and consequently
> > what we scale for.
> >
>
> I was hoping for targets that make sense for all topologies.
>
> > I think these should cover the most normal cases:
> >
> > Gateway topologies:
> > * Distributed gateways with distributed FIPs
> > * Distributed gateways with centralized NAT
> > * Centralized gateways
> >
> > IP topologies:
> > * Project networks mainly use IPv4 RFC1918 and SNAT/DNAT
> > * Project networks mainly use routed IPv4 (no NAT)
> > * Project networks mainly use routed IPv6 (no NAT)
> >
>
> Do we really need to differentiate between IP topologies?  I think the
> only significant difference above is NAT vs noNAT.  From ovn-heater
> perspective there should be no difference between private and routed
> IPv4 or v6.
>
> If we test and optimize OVN for the worst case and always configure NAT
> we should be fine, right?

i'm not sure if that works. With centralized gateways it makes a big
difference if you have NAT or no NAT. The reason (iirc) is that without
NAT you are not actually using these gateways for most of the traffic in
your environment. But with NAT you need to use them.

>
> > Any suggestions for how to tie these into the questionnaire without
> > causing a matrix explosion?
> >
>
> Not really, but if we only have "Gateway topologies" as a variable then
> we end up with a way smaller matrix. :)
>

i would go for a matrix with gateways (distributed or central) and nat
(yes or no).

Thanks
Felix
Diese E Mail enthält möglicherweise vertrauliche Inhalte und ist nur für die 
Verwertung durch den vorgesehenen Empfänger bestimmt.
Sollten Sie nicht der vorgesehene Empfänger sein, setzen Sie den Absender bitte 
unverzüglich in Kenntnis und löschen diese E Mail.

Hinweise zum Datenschutz finden Sie hier.


This e-mail may contain confidential content and is intended only for the 
specified recipient/s.
If you are not the intended recipient, please inform the sender immediately and 
delete this e-mail.

Information on data protection can be found 
here.
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Re: [ovs-dev] [RFC ovn-heater] OVN scale testing with OpenStack workloads - questionnaire

[Dumitru Ceara]

On 7/12/23 12:04, Frode Nordahl wrote:
> On Wed, Jul 12, 2023 at 10:51 AM Dumitru Ceara  wrote:
>>
>> Hi all,
>>
>> During the ovn-heater community meeting organized by Frode yesterday
>> (thanks again for that!) we agreed to follow up on some points.  Two of
>> these are related to gathering more information that allow us to build
>> realistic test scenarios (1) and define targets for them (2).
>>
>> On that note we have agreed to prepare a _short_ questionnaire to be
>> shared with OpenStack + OVN users (companies and other operators).
>>
>> I started a draft document here:
>>
>> https://docs.google.com/document/d/151saO5a5PmCt7cIZQ7DkgvU755od76BlN2bKjXc1n08
>>
>> It's mostly based on the previous discussion and information we received
>> from Felix Hüttner [0].  I gave access to everyone with the link to
>> suggest changes/comment on the document.  Also, if people prefer a
>> different way of building this questionnaire (e.g., a PR on
>> github/ovn-org/ovn-heater) please let me know.
>>
>> An additional note: I don't think the goal is to get an 100%
>> comprehensive list of all possible workloads and scale targets.  AFAIU
>> the intention is to quickly (in a few weeks?) identify a "few" relevant
>> types of workloads and start with writing test scenarios for those.  We
>> could then, incrementally, build on top of that.
> 
> Thanks alot for putting this together, I think it is a great start.
> 
> There is currently no mention of what type of topology is being used
> though, I do not want to complicate things, but I do think we need to
> at least gauge what is used behind the numbers being presented, as it
> would have consequences for how we lay out the tests, and consequently
> what we scale for.
> 

I was hoping for targets that make sense for all topologies.

> I think these should cover the most normal cases:
> 
> Gateway topologies:
> * Distributed gateways with distributed FIPs
> * Distributed gateways with centralized NAT
> * Centralized gateways
> 
> IP topologies:
> * Project networks mainly use IPv4 RFC1918 and SNAT/DNAT
> * Project networks mainly use routed IPv4 (no NAT)
> * Project networks mainly use routed IPv6 (no NAT)
> 

Do we really need to differentiate between IP topologies?  I think the
only significant difference above is NAT vs noNAT.  From ovn-heater
perspective there should be no difference between private and routed
IPv4 or v6.

If we test and optimize OVN for the worst case and always configure NAT
we should be fine, right?

> Any suggestions for how to tie these into the questionnaire without
> causing a matrix explosion?
> 

Not really, but if we only have "Gateway topologies" as a variable then
we end up with a way smaller matrix. :)

___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev

Re: [ovs-dev] [RFC ovn-heater] OVN scale testing with OpenStack workloads - questionnaire

[Frode Nordahl]

On Wed, Jul 12, 2023 at 10:51 AM Dumitru Ceara  wrote:
>
> Hi all,
>
> During the ovn-heater community meeting organized by Frode yesterday
> (thanks again for that!) we agreed to follow up on some points.  Two of
> these are related to gathering more information that allow us to build
> realistic test scenarios (1) and define targets for them (2).
>
> On that note we have agreed to prepare a _short_ questionnaire to be
> shared with OpenStack + OVN users (companies and other operators).
>
> I started a draft document here:
>
> https://docs.google.com/document/d/151saO5a5PmCt7cIZQ7DkgvU755od76BlN2bKjXc1n08
>
> It's mostly based on the previous discussion and information we received
> from Felix Hüttner [0].  I gave access to everyone with the link to
> suggest changes/comment on the document.  Also, if people prefer a
> different way of building this questionnaire (e.g., a PR on
> github/ovn-org/ovn-heater) please let me know.
>
> An additional note: I don't think the goal is to get an 100%
> comprehensive list of all possible workloads and scale targets.  AFAIU
> the intention is to quickly (in a few weeks?) identify a "few" relevant
> types of workloads and start with writing test scenarios for those.  We
> could then, incrementally, build on top of that.

Thanks alot for putting this together, I think it is a great start.

There is currently no mention of what type of topology is being used
though, I do not want to complicate things, but I do think we need to
at least gauge what is used behind the numbers being presented, as it
would have consequences for how we lay out the tests, and consequently
what we scale for.

I think these should cover the most normal cases:

Gateway topologies:
* Distributed gateways with distributed FIPs
* Distributed gateways with centralized NAT
* Centralized gateways

IP topologies:
* Project networks mainly use IPv4 RFC1918 and SNAT/DNAT
* Project networks mainly use routed IPv4 (no NAT)
* Project networks mainly use routed IPv6 (no NAT)

Any suggestions for how to tie these into the questionnaire without
causing a matrix explosion?

-- 
Frode Nordahl

> Best regards,
> Dumitru
>
> [0] https://mail.openvswitch.org/pipermail/ovs-dev/2023-May/405089.html
>
___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev

[ovs-dev] [RFC ovn-heater] OVN scale testing with OpenStack workloads - questionnaire

[Dumitru Ceara]

Hi all,

During the ovn-heater community meeting organized by Frode yesterday
(thanks again for that!) we agreed to follow up on some points.  Two of
these are related to gathering more information that allow us to build
realistic test scenarios (1) and define targets for them (2).

On that note we have agreed to prepare a _short_ questionnaire to be
shared with OpenStack + OVN users (companies and other operators).

I started a draft document here:

https://docs.google.com/document/d/151saO5a5PmCt7cIZQ7DkgvU755od76BlN2bKjXc1n08

It's mostly based on the previous discussion and information we received
from Felix Hüttner [0].  I gave access to everyone with the link to
suggest changes/comment on the document.  Also, if people prefer a
different way of building this questionnaire (e.g., a PR on
github/ovn-org/ovn-heater) please let me know.

An additional note: I don't think the goal is to get an 100%
comprehensive list of all possible workloads and scale targets.  AFAIU
the intention is to quickly (in a few weeks?) identify a "few" relevant
types of workloads and start with writing test scenarios for those.  We
could then, incrementally, build on top of that.

Best regards,
Dumitru

[0] https://mail.openvswitch.org/pipermail/ovs-dev/2023-May/405089.html

___
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev