Hello Labs, As the very last step in recovering completely from our past NFS failure, we are scheduling a switch back to the primary file server (labstore1001) as part of the recovery process. This requires a maintenance window during which NFS service will be briefly unavailable since physical wiring has to be moved for the procedure. We are planning a brief maintenance window on Wednesday, October 28 starting at 13:30 UTC to return NFS service to the primary server. The maintenance is tracked in phabricator at:
https://phabricator.wikimedia.org/T107038 The maintenance window will cause a (planned brief) suspension of NFS service to labs in the interval between shutting down labstore1002 and starting service on labstore1001, during which I/O operations to NFS will stall (be unable to complete until service is restored). Most labs projects have little to no dependency on NFS anymore, and will not be affected by the switch. Projects that still require use of NFS will lose the ability to access files in /data/project and /home during the outage. This includes tools, maps, and the beta cluster projects. We expect the actual outage will last less than 20 minutes, at some point during the maintenance window. Notices will be posted on this mailing list and on the #wikimedia-labs freenode IRC channel as maintenance begins and ends. In case of issues during the switch, we will rollback the change and return the secondary server (currently in use) to function before we evaluate the situation and prepare an alternative plan. -- Marc _______________________________________________ Labs-announce mailing list [email protected] https://lists.wikimedia.org/mailman/listinfo/labs-announce _______________________________________________ Labs-l mailing list [email protected] https://lists.wikimedia.org/mailman/listinfo/labs-l
