To everyone,
Today, around 8:30 CEST, the CPU cooling system of the main BGA server suddenly stopped working. In such a case, the server slows down (a lot) to minimize the temperature and save the system. This causes a very sloooooooooow service between 8:30 and 11:00, and after that the service stopped completely.
This is a very unusual failure, which explains why we have difficulties to identity it. It required a manual technical operation in the datacenter, which explains why it took so long to restore the service.
Service was fully restored at 14:00 CEST.
Note : we do have spare server to manage these kind of issues, but for both technical and cost reasons this is not realistic to have spare server for ALL Board Game Arena servers. This is why we are vulnerable in case of a technical hardware failure on a key BGA server with no spare.
As always, we removed all penalties linked to this period of time.
Sorry for this incident and for the (realtime) games that has been lost.
Today, around 8:30 CEST, the CPU cooling system of the main BGA server suddenly stopped working. In such a case, the server slows down (a lot) to minimize the temperature and save the system. This causes a very sloooooooooow service between 8:30 and 11:00, and after that the service stopped completely.
This is a very unusual failure, which explains why we have difficulties to identity it. It required a manual technical operation in the datacenter, which explains why it took so long to restore the service.
Service was fully restored at 14:00 CEST.
Note : we do have spare server to manage these kind of issues, but for both technical and cost reasons this is not realistic to have spare server for ALL Board Game Arena servers. This is why we are vulnerable in case of a technical hardware failure on a key BGA server with no spare.
As always, we removed all penalties linked to this period of time.
Sorry for this incident and for the (realtime) games that has been lost.