Skip to content

Allocations on LCRC Computing Resources

Overview of LCRC Clusters

The LCRC operates three distinct clusters, all of which measure allocations in node hours. For an overview on our general guidelines on allocation requests and policies, please visit this link.

Allocations Metrics for Each Cluster

Node Hours

We currently allow for an Overburn of a project allocation. Each allocation is allowed to use 10% over the granted allocation before getting an error message. Once the project allocation is exhausted, the following error message will be displayed when submitting a job:

qsub: Job violates queue and/or server resource limits

Pojects can Request Additional Project Time when > 90% of the initial allocation is exhausted.

Improv and Bebop Clusters

Allocations on Improv and Bebop are provided (and should be requested) in Node Hours. 1 node on Improv has 128 CPU Cores, and 1 node on Bebop has 36 CPU Cores. When requesting or viewing your allocation(s), please take this into consideration. Balances, transactions and other sbank details displayed from sbank commands will update every 5 minutes.

Node Hours = Number of Nodes Used × Time in Hours

  • Number of Nodes Used: The quantity of compute nodes utilized for the job.
  • Time in Hours: The duration for which these nodes are used.

Swing Cluster

Allocations on Swing are provided in Node Hours. However, on Swing, 1 Node Hour equates to 8 GPU Hours.

Allocation Usage and Tracking

General Policies

  • System Error: If a system error occurs that causes a program to crash while it is running, a project won’t be charged for that time. (This policy may be amended in the future in order to promote the use of user-based checkpointing.) The scheduler may or may not deduct the time used from the project’s allocation, depending on how the crash took place. If someone thinks their project should be credited time because of a system crash or other system problem, they should send email to support@lcrc.anl.gov to get that time back into the project.
  • Run Continuation:If a project runs out of allocation time during a run, that run will be allowed to continue to completion.
  • Project Suspension: If a project runs out of allocation time, all users on the project will not be able to run any jobs until time is added again. At the present time, no steps will be taken to stop any jobs associated with that project from running and sitting idle in the job queue.
  • Usage Tracking

Requesting Additional Project Time

When to Request Additional Time

Projects at LCRC may deplete their quarterly time allocation sooner than expected due to unforeseen computational demands or additional case studies. In these instances, Principal Investigators (PIs) have the option to request extra time.

How to Request

PIs can submit requests for additional project time through the LCRC Accounts page by accessing the project management screens. Requests must include proper justification for the additional time needed.

Review Process

  • The LCRC core team convenes every Tuesday to assess time requests for both new and ongoing projects. Additional grants will be decided on following our Mid-Quarter Allocation Policy.

Expiration of Additional Time

PIs should note that any extra time granted but not used within the quarter will expire at the quarter's end. For example, if a PI is allocated an extra 25K node-hours and only utilizes 10K, the remaining 15K node-hours will be forfeited at the quarter's conclusion.

Annual Time Requests for Projects

  • Existing Projects: Time requests for the upcoming fiscal year can be made from the first week of September until October 1st.
  • New Projects: New projects may request time throughout the year for the remaining quarters.
  • Post-October 1st: After October 1st, existing projects can request time for any quarter, but there may be restrictions on the maximum hours granted.

Mid-Quarter Allocations

Mid-Quarter Allocations can be granted for LCRC projects after not previously requesting time or exhausting a current allocation. Principal Investigators (PIs) need to understand the guidelines and requirements for requesting additional computational resources. We have described, in detail, this process on the Managing Projects documentation.