This partial service interruption was caused by a failure of one of our storage nodes. It suffered from a temporary network disconnect which was too short for the failover to take place. We will once again review our failover mechanisms to better compensate such conditions in the future.

Everything should be back to normal again now. Pingdom says about 5 minutes downtime which reflects our measurement.

We have identified the issue. It is a storage issue (one storage node), still investigating. The failover did not worked as expected.

We see "maintenance" messages on some sites/Apps. We are looking into this right now.

Began at: