[Outages-discussion] [outages] ovh network outage

[Filip Hruska]

Roubaix is the most important part of their network, which hosts many internal systems as well.
Seems they lost one of the two routers in there, which resulted in congested links among other things. 

All OVH datacenters are connected to the same backbone and they do cold potato routing. A lot of traffic passing through that PoP got blackholed -> traffic from and to other datacenters got dropped as well. 

On 30 March 2020 8:09:44 pm GMT+02:00, Jeremy Chadwick <jdc at koitsu.org> wrote:
>This looked to be specific to their Roubaix (RBX) datacentre, despite 
>the ticket being for the "Entire OVH network".
>
>-- 
>| Jeremy Chadwick                                 jdc at koitsu.org |
>| UNIX Systems Administrator                      PGP 0x2A389531 |
>| Making life hard for others since 1977.                        |
>
>On Mon, Mar 30, 2020 at 04:00:03PM +0000, hiro via Outages wrote:
>> i had issues with tcp SYN, dns traffic and icmp not getting through.
>> finally they added an entry, too:
>> http://travaux.ovh.net/?do=details&id=43793&
>> _______________________________________________
>> Outages mailing list
>> Outages at outages.org
>> https://puck.nether.net/mailman/listinfo/outages
>_______________________________________________
>Outages-discussion mailing list
>Outages-discussion at outages.org
>https://puck.nether.net/mailman/listinfo/outages-discussion

-- 
Sent from my mobile device. Please excuse my brevity.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://puck.nether.net/pipermail/outages-discussion/attachments/20200330/3e75add6/attachment-0001.htm>