<div dir="ltr"><div class="gmail_default" style="font-family:courier new,monospace;font-size:small">Vertical Scalability of
Route-Servers
on very large IXP is a challenge!<br>We are talking about 400-2200 peers...<br><a href="https://ixpdb.euro-ix.net/en/ixpdb/ixps/?sort=participants&reverse=1&">https://ixpdb.euro-ix.net/en/ixpdb/ixps/?sort=participants&reverse=1&</a><br><br>As already mentioned, Bird still does not deal very well with multi-threading(even on version 2).<br>So, for that, threads with more gigahertz are better de several threads.<br><br>In Bird's world, the solution for that is the MultiBird.<br>That solution is explained here:<br> -> <a href="https://www.euro-ix.net/media/filer_public/40/8b/408bd0bb-6835-4807-8677-0a1961bd3fba/flock-of-birds_ljtmypd.pdf">https://www.euro-ix.net/media/filer_public/40/8b/408bd0bb-6835-4807-8677-0a1961bd3fba/flock-of-birds_ljtmypd.pdf</a><br> -> <a href="https://www.youtube.com/watch?v=dwRwF7Bu8as">https://www.youtube.com/watch?v=dwRwF7Bu8as</a> <br> In pt_BR, but I believe that if you activate the automatic subtitles and automatic translation to your language will be enough to understand.<br><br><br>What I'm proposing here is just a different method of doing multiple instances of Bird, with the possibility of those being on diferente boxes, or even different sites.<br><br><br></div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">Em ter., 19 de jan. de 2021 às 12:22, Alexander Zubkov <<a href="mailto:green@qrator.net">green@qrator.net</a>> escreveu:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">But you wrote that for scaling there are load balancers to balance<br>
sessions among different bird instances. So VRRP + Load Balancer will<br>
give you what you want. You can also try to bind several birds to a<br>
single address in linux (probably little patchin is required to set<br>
socket options) and linux will balance sessions between them. You may<br>
also want to exchange routing information somehow between your bird<br>
instances, but I think it also can be solved somehow, a couple of<br>
route reflectors for example.<br>
I still do not understand what you want to see in Bird itself. I<br>
haven't run large IXPs, so I may be not aware of something and would<br>
be glad if you explained it in more detail.<br>
<br>
On Tue, Jan 19, 2021 at 3:22 PM Douglas Fischer<br>
<<a href="mailto:fischerdouglas@gmail.com" target="_blank">fischerdouglas@gmail.com</a>> wrote:<br>
><br>
> As I mentioned initially, my focus was on "large environments of IXPs".<br>
> Considering that, L3 anycast does not apply very well to that scenario.<br>
> (I don't know any IXPs that use Route-Servers outside of the MPLA-LAN of the IXP.)<br>
><br>
> Using VRRP is an excellent method to provide fail-over on L2.<br>
> (I used it a lot on several application scenarios).<br>
> But it does not provide load-balancing, just fail-over.<br>
><br>
> Considering "large environments of IXPs", and the fact that even on Bird 2, the multi-thread limitation is not completely solved.<br>
> The solution for that is Load-Balance. MultiBird does it VERY WELL.<br>
> But until now we(at least me) have seen only "single-host" based solutions, using nat/forwarding connections.<br>
><br>
> With this suggestion, using L2 load-balancing based on MAC-IP-Mapping manipulations, is possible to remove the "single-host" point of failure.<br>
><br>
> Em ter., 19 de jan. de 2021 às 10:48, Alexander Zubkov <<a href="mailto:green@qrator.net" target="_blank">green@qrator.net</a>> escreveu:<br>
>><br>
>> Hi,<br>
>><br>
>> You can use VRRP or alike protocol on L2 or dynamic routing with<br>
>> anycast on L3 for reliability. I do not see what you want in Bird.<br>
>> Could you explain more?<br>
>><br>
>> On Tue, Jan 19, 2021 at 1:26 PM Douglas Fischer<br>
>> <<a href="mailto:fischerdouglas@gmail.com" target="_blank">fischerdouglas@gmail.com</a>> wrote:<br>
>> ><br>
>> > I was studying the concepts of multi-bird for large environments of IXPs.<br>
>> ><br>
>> > And, beyond the extra complexity that it brings to the environment, one of the weak points I saw was the fact that all the Bird instances are at the same box(vm, container, etc...).<br>
>> ><br>
>> > A friend mentioned that some tests were made with a LoadBalancer redirecting the post-nated connections to other boxes.<br>
>> > But even in that scenario, that load balancer would be a single-point-of-failure/bottleneck.<br>
>> ><br>
>> > So I was remembering Cisco GLBP and Heart-Beat protocol.<br>
>> > Those protocols inform different Mac-Addresses to the same IPv4/IPv6 Address, based on the source of the ARP/ND query.<br>
>> > Making a load-balance/fail-over based on the glue between layer2 and layer3.<br>
>> > P.S.: Several scenarios uses that concept. Corosync, Windows Cluster, Orale RAC, etc...<br>
>> ><br>
>> > Considering that concept, and joining it with multibird:<br>
>> > Would be possible to create groups of sources and assigning different priorities to those groups on each instance of Bird.<br>
>> > In this case, each Bird instance could run on a different box, or even on a different site.<br>
>> ><br>
>> > Further than that, on IXPs with a large number of participants, would be possible to define some affinity between that group of priority based for example on the facility where those participants are connected.<br>
>> ><br>
>> > I have a feeling that this would be especially useful for remote peering scenarios.<br>
>> ><br>
>> ><br>
>> > Just a crazy idea to share with colleagues.<br>
>> > Maybe from here, some good thing could rise.<br>
>> ><br>
>> ><br>
>> > --<br>
>> > Douglas Fernando Fischer<br>
>> > Engº de Controle e Automação<br>
><br>
><br>
><br>
> --<br>
> Douglas Fernando Fischer<br>
> Engº de Controle e Automação<br>
</blockquote></div><br clear="all"><div><br></div>-- <br><div dir="ltr" class="gmail_signature"><font size="2"><span style="font-family:"courier new",monospace">Douglas Fernando Fischer</span><br style="font-family:"courier new",monospace"><span style="font-family:"courier new",monospace">Engº de Controle e Automação</span></font><div style="padding:0px;margin-left:0px;margin-top:0px;overflow:hidden;color:black;text-align:left;line-height:130%;font-family:"courier new",monospace"></div></div>