Дата-центры OVH

12 читателей, 739 топиков

SLA Information – November 9 incident Roubaix (RBX)

On Thursday November 9, some of your services were affected by a network incident in our French site, in Roubaix (RBX). We would like to extend our sincerest apologies.

Flagged at 8:01am (French time), the incident was declared closed by our teams at 10:34am (French time). You were unable to access your services during this time.

All of your services are now working again, and we are here to answer any questions which you may have regarding your products.

We are well aware of the consequences of this service interruption, and we will, of course, be activating the planned compensation for products which are contractually bound by an SLA. As a reminder, you can find all the SLA levels pertaining to your products, in the customer control panel. You can view all compensation details via this link.

The causes of this incident are still being analyzed, and we have already taken some measures which will further strengthen the reliability of our services, even in the most unexpected situations.

You can find additional information about the event and the resulting actions here. Rest assured that we are doing everything to learn from each new situation encountered, to further improve our service availability. We will keep you informed of the implementation of these measures.

We are very sorry for the inconvenience this incident may have caused, and would like to reiterate our sincerest apologies.
Regards, The OVH team

от редакции
по русски написано ТУТ

400 серверов меняли детали

There are still ~2000 ips that are still down on multiple hosts. Tech in DC working on it.
— pci / vps
64 hosts with
1000 VPS/PCI
no issue on ceph
A technician manages about 25 heavy interventions per day. With 400 issues to solve, the calculation is simple: we need between 15 to 25 technicians to complete the incident. That's why the teams take turns since yesterday noon thanks to the staff who arrived from the others DCs. OneTeam
У нас осталось чуть меньше 400 серверов. У нас есть все типы аппаратных проблем с этими серверами, и мы заменяем их к концу дня.

  • PCI/VPS: there is 10 hosts that has to be reparted. the host is very complex and we need 1H per host.
  • Servers (SYS/OVH) We have 200 serveurs that the hardware issues that we are working on.