oles@ovh.net
01-29-2011, 01:36 PM
Hello,
As has already been stated, we are currently finalising all work on our network. This week we will finish 90% of the heavy work. Now, all routing to Roubaix will be done with 2 large centralised ASR 9010 routers with a total capacity of 1.2Tbps. Between Roubaix and "the world" we are at 620Gbps capacity.
This week, we exceeded 380Gbps outbound traffic managed by 90,000 servers that OVH host. A new thing: we have about 50Gbps of internal traffic between your servers and it is increasing every month. This shows us that our customers are building their infrastructures and clusters based on multiple servers in different datacentres and servers and these are connected together.
All this work on the network has also enabled us to better load balance between Roubaix / London / Amsterdam / Frankfurt / Paris. We've added a router in Amsterdam and one in Frankfurt. We have 2x (4x10G) on Amsix and 2x (4x10G) on Decix. We have increased the capacity of Sfinx in Paris to around 2x10G. The connection to Milan, Warsaw and Madrid are better balanced now, but we still have some work to do. Bottom line: we
gained approximately 100Gbps capacity between Roubaix and "the rest of the world" just by centralising routing.
The Network:
http://weathermap.ovh.net/backbone
Currently, we still have some refining to do but also some capacity increases.
Apart from Roubaix, in Europe we still working on:
- Increasing capacity through the peer point with Orange the regional peering in Lille, Lyon and Bordeaux.
We have 2x (2x10G) in Paris and are looking into about 3x (1x10G) or more.
- In London, we need to transfer the main POP Global Switch to Telehouse. We'll add a 2nd router and increase capacity from LINX
to the USA.
- in Warsaw increase capacity of PLIX to the tune of 4x10Gbps
- Increase capacity between Amsterdam / Warsaw and Frankfurt / Warsaw to 2x (4x10G)
- In Milan peering capacity increase with the traditional operator in Italy (Interbusiness) to 2x10G see 3x10g
- Increase in capacity between Frankfurt / Milan to 2x (2x10G)
In the U.S., we are beginning to sign the POPs with transits and peering, but we are approaching this sensibly and calmly.
We will expand to Philadelphia and we have started recruiting and training staff.
In Roubaix we must establish the internal network routers for new beta services, which should be out soon. The famous privateCloud and VPS
the Exchange and the publiCloud (ex miniCloud / coreCloud) based on the CCP, the CCP's routing is particularly important: it must 100% availability guaranteed .
To better differentiate between the services, we will also establish a separate network for "kimsufi" servers and also made innovations on the "OVH" servers. The goal is to ensure the new innovations ... so our customers can begin to make use of them on a regular basis. Basically, we will better meet their needs. This work will take a few weeks and should be finished for the start of the fourth OVH datacentre in Roubaix Valley: RBX-4.
So in short, it's coming together
Regards
Octave
As has already been stated, we are currently finalising all work on our network. This week we will finish 90% of the heavy work. Now, all routing to Roubaix will be done with 2 large centralised ASR 9010 routers with a total capacity of 1.2Tbps. Between Roubaix and "the world" we are at 620Gbps capacity.
This week, we exceeded 380Gbps outbound traffic managed by 90,000 servers that OVH host. A new thing: we have about 50Gbps of internal traffic between your servers and it is increasing every month. This shows us that our customers are building their infrastructures and clusters based on multiple servers in different datacentres and servers and these are connected together.
All this work on the network has also enabled us to better load balance between Roubaix / London / Amsterdam / Frankfurt / Paris. We've added a router in Amsterdam and one in Frankfurt. We have 2x (4x10G) on Amsix and 2x (4x10G) on Decix. We have increased the capacity of Sfinx in Paris to around 2x10G. The connection to Milan, Warsaw and Madrid are better balanced now, but we still have some work to do. Bottom line: we
gained approximately 100Gbps capacity between Roubaix and "the rest of the world" just by centralising routing.
The Network:
http://weathermap.ovh.net/backbone
Currently, we still have some refining to do but also some capacity increases.
Apart from Roubaix, in Europe we still working on:
- Increasing capacity through the peer point with Orange the regional peering in Lille, Lyon and Bordeaux.
We have 2x (2x10G) in Paris and are looking into about 3x (1x10G) or more.
- In London, we need to transfer the main POP Global Switch to Telehouse. We'll add a 2nd router and increase capacity from LINX
to the USA.
- in Warsaw increase capacity of PLIX to the tune of 4x10Gbps
- Increase capacity between Amsterdam / Warsaw and Frankfurt / Warsaw to 2x (4x10G)
- In Milan peering capacity increase with the traditional operator in Italy (Interbusiness) to 2x10G see 3x10g
- Increase in capacity between Frankfurt / Milan to 2x (2x10G)
In the U.S., we are beginning to sign the POPs with transits and peering, but we are approaching this sensibly and calmly.
We will expand to Philadelphia and we have started recruiting and training staff.
In Roubaix we must establish the internal network routers for new beta services, which should be out soon. The famous privateCloud and VPS
the Exchange and the publiCloud (ex miniCloud / coreCloud) based on the CCP, the CCP's routing is particularly important: it must 100% availability guaranteed .
To better differentiate between the services, we will also establish a separate network for "kimsufi" servers and also made innovations on the "OVH" servers. The goal is to ensure the new innovations ... so our customers can begin to make use of them on a regular basis. Basically, we will better meet their needs. This work will take a few weeks and should be finished for the start of the fourth OVH datacentre in Roubaix Valley: RBX-4.
So in short, it's coming together
Regards
Octave