Sign up for our newsletter
Technology / Cloud

Capacity overload creates Google Cloud outage

Google’s trouble with outages continues as it went offline for over an hour last week.

Affecting Google Cloud’s Europe-west1 region, the outage occurred after a network owner connected a new peering link to Google and advertised reach-ability for more traffic than the service could handle.

Google explained in a blog post that this resulted in lost traffic in destination addresses across Eastern Europe and the Middle East.

The company said: "The peer’s network signalled that it could route traffic to many more destinations than Google engineers had anticipated, and more than the link had capacity for.

White papers from our partners

"Google’s network responded accordingly by routing a large volume of traffic to the link. At 11:55, the link saturated and began dropping the majority of its traffic."

To further the problem, the automated safety checks had failed, "due to an unrelated failure," which meant that the link was brought online manually.

To stop this issue happening again, the company has decided to change procedures in order to disallow manual link activation.

Google has suffered a number of outages through the year, in March a patch caused an outage to its Compute Engine. This latest outage lasted for 70 minutes.

This article is from the CBROnline archive: some formatting and images may not be present.