Daily Bulletin Archive

Jan. 5, 2018

Two new Cheyenne batch queues, premium and standby, are now available to users. The queues are very similar to the Yellowstone queues with the same names.

Jobs submitted to the premium queue are dispatched for execution at a higher priority than other queues available to most users and will be charged at 1.5 times the rate of jobs in the regular queue.

Running jobs in the standby queue is allowed only for exhausted Cheyenne project allocations. Jobs submitted to other queues when an allocation is exhausted are rejected and the user is notified to resubmit the job to the standby queue. Those jobs are dispatched at the lowest priority level and do not incur charges.

Please see Job-submission queues and charges for more complete information on Cheyenne’s batch queues.

Jan. 4, 2018

A recording of the December 19 tutorial, “How to access Geyser and Caldera from Cheyenne,” is now available on the CISL web site. See the course page to review the presentation and download the slides.

The 55-minute tutorial covers how to start interactive jobs and batch jobs with the Slurm scheduler, performing graphically intensive tasks on Geyser, and considerations when using Cheyenne and Geyser/Caldera together in a workflow.

Jan. 3, 2018

The Cheyenne, Geyser and Caldera systems are expected to remain offline throughout today, January 3, as the NCAR-Wyoming Supercomputing Center (NWSC) facility continues to recover from the December 30 power outage.

Power has been restored to the NWSC and CISL staff have begun extensive hardware and system software testing to ensure that the systems were not damaged as a result of the sudden loss of power. Every effort is being made to restore Cheyenne, Geyser and Caldera as soon as possible.

CISL will inform users through the Notifier service of any significant updates and when the systems are restored. We apologize to all users for the inconvenience this will cause, and we thank you for your patience.

Also be aware that, as planned, the Yellowstone system has been powered down permanently.

Jan. 2, 2018

Scheduled Downtime: Cheyenne, Geyser and Caldera: Tuesday Jan. 2, 6 am to 6 pm

No downtime: GLADE and HPSS

Dec. 31, 2017

The Yellowstone supercomputing cluster will be decommissioned on December 31, 2017. The system will be powered down on that date and no longer available to users.

The Geyser and Caldera clusters will remain in production until the end of 2018. Users can learn about how to access those systems from the Cheyenne cluster in training sessions are scheduled for December 4 and 19. See Training: How to access Geyser and Caldera from Cheyenne for more details and how to register.

Users who have not already done so are strongly encouraged to migrate their work to Cheyenne as soon as possible to avoid unnecessary interruptions. Documentation available to help with the transition includes this Quick start overview, procedures and scripts for running jobs, and this recorded tutorial. For help in migrating job scripts or rebuilding executables, please contact cislhelp@ucar.edu.

It is not necessary to copy or move files to HPSS or to another disk space to ensure that they are available from Cheyenne after Yellowstone’s decommissioning. All files in the GLADE system file spaces—home, scratch, work, and project—are accessible via Cheyenne already. Copying or archiving files unnecessarily will waste expensive tapes and valuable disk space while increasing use of your allocation.

See our allocations documentation if you do not already have a Cheyenne allocation. University users who want to convert an existing Yellowstone allocation to a Cheyenne allocation should email that request to cislhelp@ucar.edu.

Dec. 27, 2017

CISL has resolved some issues that prevented the Systems Accounting Manager (SAM) from updating allocation usage records for several days recently. All records should be up to date and available now in SAM.

Dec. 22, 2017

University users who would like to have their unused Yellowstone allocations transferred to Cheyenne should make their requests well before the end of the year, when the Yellowstone system is decommissioned and the allocations expire on December 31.

The CISL Help Desk will be closed for the holidays on Monday, December 25, and Monday, January 1. Please send your allocation transfer requests to cislhelp@ucar.edu before Christmas to be sure the resources are available on Cheyenne on January 1.

Dec. 19, 2017

Cheyenne users can now run jobs on the Geyser and Caldera clusters via the Slurm job scheduling system. To learn how, refer to the online documentation and consider attending one of the training sessions that are scheduled for December 4 and 19. See Training: How to access Geyser and Caldera from Cheyenne for more details and how to register.

Approximately half of the Geyser and Caldera nodes are accessible from Cheyenne. The remaining nodes will remain accessible from Yellowstone until the end of this month when Yellowstone will be decommissioned. Shortly after January 1 all of Geyser and Caldera will be available from Cheyenne.

Dec. 18, 2017

No Downtime: Yellowstone, Cheyenne, Geyser_Caldera, GLADE and HPSS

Dec. 18, 2017

The CISL User Services Section will present an in-person and online tutorial at 9 a.m. MST Tuesday, December 19, on how to run jobs on the Geyser and Caldera clusters from the Cheyenne HPC system. The Yellowstone system is being decommissioned December 31, but Geyser and Caldera will remain in production throughout 2018.

The 45-minute tutorial will cover submission and monitoring of jobs with the Slurm scheduler, running an interactive job, performing graphically intensive tasks on Geyser, and considerations when using Cheyenne and Geyser/Caldera together in a workflow. The session will include time for questions.

Register to attend in person at NCAR’s Mesa Lab in Boulder or via webcast by selecting a link below:

Attend in person (Chapman Room, ML245, space is limited)

Attend webcast