Hi,
We have declared an outage on storage (Castor) and batch systems at the
RAL Tier1 while the Linux kernels are updated in order to apply a security
fix.
In particular batch and Castor systems have an Outage declared from 08:30
to 14:30 (local time). During this time any current batch jobs will be
paused as Castor nodes are updated.
The FTS will be drained for an hour ahead of this intervention, although
during this time jobs will be queued. The FTS itself will have kernel
updates applied between 08:30 and 09:30.
Some other services (e.g. BDII, MyProxy and lfc-atlas) have an 'At Risk'
declared during the morning (09:00 to 10:30 local time) as these nodes are
rebooted to make use of the new kernel.
The batch system worker nodes are being updated separately as part of a
rolling update that will not affect production.
Gareth Smith
RAL Tier1 Production Manager.
|