French colo and cloud provider OVHcloud is experiencing a global outage.
Earlier this year, one of OVH's data centers burned down, causing significant outages and data loss. The company plans a $4.7 billion IPO later this year.
Update: After an outage lasting more than an hour, services appear to be slowly returning. The outage began at around 7:00 UTC, with a maintenance reconfiguration error.
The outage also brought down OVHcloud's status page.
"Following a human error during the reconfiguration of the network on our DC to VH (US-EST), we have a problem on the whole backbone," OVH founder Octave Klaba said (translated).
"We are going to isolate the DC VH then fix the conf."
He added that "In recent days, the intensity of DDoS attacks has increased significantly. We have decided to increase our DDoS processing capacity by adding new infrastructures in our DC VH (US-EST). A bad configuration of the router caused the failure of the network." This week, Microsoft Azure said that it had mitigated the world's largest DDoS attack with no impact to services - surviving a 2.4Tbps traffic assault.
On March 10, a fire on OVHcloud's Strasbourg campus destroyed its SBG2 data center, and disabled three other buildings, one of them permanently.
The Strasbourg fire affected some 65,000 customers, many of whom lost data and business. The incident could damage the prospects for the IPO - though OVHcloud has said it is working with insurers and other authorities, and cannot reveal the full story of the cause of the fire until 2022, after the IPO has taken place. Initial reports suggested that the fire may have started in UPS systems.
The fire is expected to cost the company more than €105 million ($122m).
This story is developing and will be updated regularly