Cluster Controller at p55cc1

Titan & Pleione resource manager (slurm) upgraded.

Test queue (partition) added to Pleione, maxtime 15 minutes using single dedicated node (pl99).

Problem with pleione nodes 1 & 9 fixed.

Caveat emptor:

The resource manager needs to be upgraded which most probably means that your current jobs will be stopped during the process.

Such upgrade takes place next week without any further notification

Pleione reboot finished, cluster ready to be used.

Both clusters will be rebooted as soon as the queues are flushed. Maxtime is set to one hour.

The new partition 'test' consists of node ti99 only and maxtime is set to 15 minutes.

Pleione has been removed from the Grid usage permanently.

This should not affect your local jobs.

Due to bug in newest kernel the reboot sequence of Pleione & Titan has been cancelled.

Both clusters should operate normally now.

Pleione reboot finished.

Pleione reboot in few minutes due to kernel update.

Titan reboot and upgrade completed.