[MicroChip123]

Hello
1 month ago we made the "split" of vss-2 (double
chassis) to a configuration in a single chassis. This
fixed all the problems we have had with the vss. PMO
walk fast and does not saturate the CPU more and more problems ARP.

We will "splitter" vss-1 router that night from
midnight. It will take about 30 minutes to complete.
This is a configuration change and reboot the total
the router to completely change the configuration. During
this time 30 minutes, the servers managed by the vss-1
be cut.

More:
http://travaux.ovh.com/?do=details&id=4440

After vss-1, there will be more than the last vss-3.
As a result, we have more problems.

2 years ago, we made the wrong choice of configuration
and we waited, in vain, we fix our problems. In
being as formerly "with the means at hand, all problems
to be established, will be resolved one by one without waiting.
We still have two weeks of work.

Otherwise, we will not use the Nexus 7016 we
have originally planned. We ordered one to
tests and what we received was not consistent with
what we expected. There are limitations in RAM that
prevents us from running the BGP properly,
Cloud Computing functions undeveloped and will not
and apparently not different bugs in the implementation
example of the proxy-ARP with HSRP mac with the forced
no proxy-arp ipv6 etc.. In short, the equipment is not
ready for the moment working in L3. In short, we
lost time. Lot of time. We spent the
Juniper and Brocade controls similar hardware and
the RAS 9000. All this to make the tests (for now)
and see firsthand the operation and bugs
that suit ...

Does it undermines our plans?
Oddly, no. The routers used today
functioning properly until there certain level.
The idea is not to exceed this limit rather
seek a new material with which one might
exceed. And so instead of upgrade routers, we
will bring new products in parallel. Simply.
The backbone will be "less centralized" and therefore "more distributed".
Divide, divide and divide to make 2 or 3 backbones
in parallel, each of 500Gbps of capacity and each
operating almost independently of each other.

Other work current network:

The implementation of BGP route reflector:
http://travaux.ovh.com/?do=details&id=4490
The issue of QoS on the switches bay:
http://travaux.ovh.com/?do=details&id=4384
The protections against attacks on UDP:
http://travaux.ovh.com/?do=details&id=4249

Regards
Octave

Good evening
completed (with great difficulty and a problem on IP failover
the HG).

Octave

...

[oles@ovh.net]

Bonsoir,
terminé (avec beaucoup de mal et un probleme sur les IP failover
sur les HG).

Octave

[turbanator]

poor kitten

lol

[Myatu]

Poor kitten

[oles@ovh.net]

Hello,

1 month ago we "split" the vss-2 (double frame) to a configuration in a single chassis. This has fixed all the problems we had with the vss. The BGP works quickly and does not further saturate the CPU and more ARP problems.

We will "split" vss-1 router tonight at midnight. It will take about 30 minutes to complete. This is a configuration change and a total reboot of the router to change all the configuration completely. During this 30 minute period, the servers managed by the vss-1 will be cut.

More information:
http://status.ovh.net/?do=details&id=472

After the vss-1, there will be more than the last vss-3. As a result, we do not have more problems.

2 years ago, we made the wrong choice of configuration and we waited, in vain, to fix our problems. By pretending that the past "with the means at hand", all the problems still to be determined, will be resolved one by one without waiting. We still have two weeks of work.

Otherwise, we will not use the Nexus 7016 as we originally planned. We ordered one to do the tests and what we received was not what we expected. There are RAM limitations that prevent us from running the BGP properly, the Cloud Computing functions are undeveloped and different bugs in the development for example of the proxy-ARP with HSRP with forced mac , no proxy-arp ipv6 etc.. In short, the hardware is not ready for the moment to work in L3. In short, we lost time. Lots of time. We had orders to Juniper and Brocade for similar equipment and ASR 9000. All this to make the tests (for now) and see firsthand the operation and bugs ...

It challenges our plans? Oddly, no. The routers in use today function properly to a certain level. The idea is not to exceed this limit rather than seeking a new material with which one could pass it. And so instead of upgrading the routers, we will implement something new in parallel. Simple. The backbone will be "less centralised" and therefore "more distributed". Divide, divide and divide to make 2 or 3 parallel backbones, each of 500Gbps of capacity and each operating almost independently of each other.

The other network in progress:

BGP route reflector:
http://status.ovh.net/?do=details&id=420
QoS Problem on the rack switches:
http://status.ovh.net/?do=details&id=301
Protection against attacks in UDP:
http://status.ovh.net/?do=details&id=158

All the best,
Octave