create new tag
view all tags

Scheduled Maintenance on 2012-02-01

The next first working Wednesday of the month we will go into Scheduled Downtime. It will last from 8:30 to 19:30, but we will return to operation as soon as we finish.

As usual, CMS and Atlas queues will be closed 24 hours before the maintenance, and LHCb queue will close 48 hours before the maintenance.

Summary of interventions

We will perform the following operations on the cluster:

IBM firmware update

  • Description: IBM disk and enclosure firmware update
  • Affected nodes: se[40-43]
  • Notes: The first two racks of IBM were in production when we installed the expansion, so we did not touch them. Hence the firmware is older than the rest of the system, and needs to be updated.

se[40-43] upgrade, rename and reboot

  • Description: dCache SE[40-43] ILOM upgrade, rename and reboot
  • Affected nodes: se[40-43], se[05-08]
  • Notes:
    • There is an ILOM update that needs to be done in those nodes (possibly extended to se[05-08])
    • We want to rename se[40-43] to se[01-04] to have a consistent naming schema.
    • All this nodes have to be restarted. Specially need to check that se[40-43] pick up their new raids in the right order

DONE Hardware move from PhaseB racks

  • Description: Hardware move from old PhaseB racks to the new PhaseD/E ones.
  • Affected nodes: fw[01-02], nfs02, some Force10 switches
  • Notes: Those nodes need to be taken out of the old racks, because we want to shut them down and two of them will probably move to Bern. The firewalls are not in production, so that would not be an issue. nfs02 needs to be done during downtime, but the most difficult part would probably be the leftovers from the Force10 Ethernet switches.

DONE Space move on storage01

  • Description: Move space between DB and Billing partitions in storage01
  • Affected nodes: storage01
  • Notes: The billing partition is always getting full, and can't stay one more year like this. There is no more free disk space, but we could take out some from the dCache database and put it into the billing partition. This needs a downtime.
Edit | Attach | Watch | Print version | History: r2 < r1 | Backlinks | Raw View | Raw edit | More topic actions
Topic revision: r2 - 2012-02-01 - PabloFernandez
This site is powered by the TWiki collaboration platform Powered by Perl This site is powered by the TWiki collaboration platformCopyright © 2008-2021 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding TWiki? Send feedback