Site Navgation
- Molecular Science Computing
- Chinook Supercomputer
- MSC User Policies
- Molecular Science Software Suite
- Graphics and Visualization Lab
Molecular Science Computing User Policies
1.0 Support Policies1.1 Contacting MSC Support Staff
1.1.1 Required citation In the event of a problem, contact the MSC Support staff:
- Monday - Friday:7:30am - 5pm, PST
- EMSL Acknowledgement
- e-mail MSC
- Emergencies only: 509-371-6100
2.1 Acknowledgement of EMSL in published work
2.1.1 Required citation Any use of the computing resources of the MSC must be properly acknowledged in publications using the following citation: (http://www.emsl.pnl.gov/root/publications/acknowledgement/)
2.2 MSC Lack-of-Use policy2.2.1 The purpose of this policy is to ensure the efficient use of MSC computing resources, MSC management will be monitoring all computer project accounts frequently.
2.2.2 Project Inactivity Any projects that have had no usage (computer time used) for two months will be notified for lack-of-use.
- Only the project's principle investigator will receive a lack-of-use message.
- Upon receipt of the first message the project PI will have to provide an explanation for the lack-of-use and why the project should be allowed to continue.
- If no justification is received within a month, and a second lack-of-use notice is sent, the project allocation will be withdrawn and all account access will be terminated for that specific project.
2.2.3 User Inactivity
- Users who no longer have active project accounts will be notified that their accounts will be closed, and given 30 days to save their files from Chinook directories.
- After an additional 30 days, their accounts will be closed, and the account's home directory deleted unless they become participants on an active project account.
3.1 Disk usage
3.1.1 Purpose of this policy is to define the uses of the files systems available at the MSC. The MSC provides users with four disk storage options:
- <local>/scratch, /dtemp, /home and NWfs file systems.
- The /scratch directories are intended for storage of programs and data while a job is running. After termination the entirety of /scratch will be deleted and all data will be unrecoverable.
- The /dtemp directory is intended to be a staging area for launching jobs. As the name implies, /dtemp is for temporary storage of executables and data.
- The /home directory is intended for storage of data and executables while the user has a active MSC project. After a project terminates, the disk space will be reclaimed according to the MSC policy described below.
- The NWfs file system is intended for long term data storage.
3.1.2 Jobs must be run from /dtemp or /scratch. Jobs running from the /home file system can cause system degradation either because too many files are being accessed simultaneously or by exceeding disk storage capacity.
3.1.3 The /dtemp file system is for temporary storage. The MSC will periodically delete "stale" files from the /dtemp subdirectories. A "stale" file is one that has not been accessed within the last 60 days. For longer term storage of important files, the user should move them from /dtemp to NWfs (www.emsl.pnl.gov/capabilities/computing/howto/nwfs_policies.jsp).
3.1.4 Do not submit jobs from /home Jobs running from the /home file system can cause system degradation either because too many files are being accessed simultaneously or by exceeding disk storage capacity.
3.1.5 Appropriate use of /home
- The /home directory is a shared resource without enforced quotas. When excessive amounts of disk space is used, those who are using the most space will be asked to reduce their use to some value.
- Repeated excessive use of disk space can lead to loss of system privileges. This directory is not a permanent storage system. Files to be saved should be stored on your local machine or on the NWfs file storage system. (http://www.emsl.pnl.gov/capabilities/computing/howto/nwfs_policies.jsp)
4.1 Job Submission Policy
4.1.1 The primary objective of EMSL's Molecular Science Computing capability is to provide teraflop computing resources for large scale computational needs associated with environmental problems as given in the Mission Statement of our sponsor (http://www.science.doe.gov/ober/ober_top.html), the Office of Biological & Environmental Research (http://www.science.doe.gov/Program_Offices/BER.htm). The job scheduling policy has been established to provide higher priorities to large jobs that cannot be run on local clusters or other HPC systems not designed for computational chemistry code. To maximize system flexibility, all batch jobs are submitted in identical fashion. The job scheduler controls the allocation of compute nodes to the users job and will place the job in one of seven available queues: tiny, small, medium, large, and extra-large (xl). This allocation is governed by a number of queue constraints. All queue constraint values must be satisfied or the job will go into "BatchHold" until deleted. For information on MSC User policies, please see User Policies
4.1.2 Job Policy Constraints: The total number of jobs a person can have running depends on Chinook user activity. While busy with many users:
- The maximum number of Active jobs in the Running state: 3
- The maximum number of Eligible jobs in the Idle state: 15
- The maximum number of Blocked jobs in the Idle state: 500
- Maximum number of nodes per job: 1100 (8800 processor-cores)
- Minimum number of nodes per job: 1 (for test or interactive purposes only)
4.1.3 Jobs must be run from the batch queue rather than the login node.
- Jobs found running in the login node will be terminated by the system administrator and the user will be sent an e-mail message.
- Jobs in the batch queue that have been suspended for more than 12 hours will be deleted. Please be sure to kill or restart jobs before the 12 hours is up.
4.1.4 Job queue default values limit the time a single job with a particular number of nodes can have.
| Queue Name | Number of Nodes in a Single Job | Time Limit | Notes |
|---|---|---|---|
| Extra Large (XL) | 256 - 1100 | 24 wall-clock hours | These jobs (xl) will be placed ahead of the jobs in the queues below, i.e., they will receive highest priority. |
| Large | 128 - 255 | 48 wall-clock hours | These jobs (large) will be placed ahead of the jobs in the queues below, i.e., they will receive higher priority. |
| Normal | 2 - 127 | 48 wall-clock hours | These jobs, medium and small will be used to backfill with the larger queues. |
| Short | 1 - 4 | 30 wall clock minutes | This is a test or interactive queue, with only 16 nodes in this (short) queue. A maximum limit of 4 nodes/job may be used. |
| Long | 2 - 16 | 96 wall clock hours | This is referred to as the "long queue" as it has the most wall clock hours of any queue. |
4.1.5 Jobs larger than 1,100 nodes can be run when needed. We ask that you first contact your Science Point-of-Contact (your PI should know who that is) to make arrangements. Or you may send an e-mail to mscf-consulting@emsl.pnl.gov with details on what is required. Your large job may qualify as a SIGHTS job (see below).
4.1.6 Idle Queue: {This queue has not been implemented on Chinook pending further investigation.}
4.2 Special Purpose Queue (SIGHTS Jobs)4.2.1 The purpose of this policy In addition to the queue limitations mentioned above the users can request access to a special purpose queue called Scientific Impact Generated by High Teraflop Simulations (SIGHTS). The SIGHTS queue is for compute jobs that require resources beyond the normal queue limits for Chinook, and serve uniquely impactful cutting-edge OBER/EMSL mission science opportunities which cannot be performed at any other computing facility. SIGHTS jobs should require the use of 1600 nodes or more, up to Chinook's capacity of 2130 nodes. SIGHTS jobs should not be sent to the Chinook queue until approval is given by the appropriate MSC staff. SIGHTS jobs can be submitted anytime after approval and will be tended by an MSC scientific consultant and operations personnel to improve the chance for successful completion. When a scheduled outage is planned, a SIGHTS request must be submitted by 12 noon on the day before the scheduled outage.
4.2.2 Access to the SIGHTS is by request only and is subject to time availability. All requests are submitted to the MSC consulting group for review. In your request please provide a short (one-two page) description of what you plan to do and how you plan on doing it. If your request is accepted, and you do not have an active EMSL Usage System project, you will need to submit your accepted request to the EMSL User Portal. Then a consultant will be assigned to the job and will work with you to be sure the job is ready. The consultants and operations staff will watch all SIGHTS jobs to be sure they are running correctly. Details about SIGHTS jobs are:
- The minimum number of processor-cores: is 1100 (1 processor core per node)
- There is no time limit but the longer the time, the greater the chance of node failure.
- Job can be started during weekday business Pacific time normal hours.
- There is no cost for SIGHTS jobs. All allocations for the job will be returned to the user.
- The minimum number of Nodes per Job: 1 (for test or interactive purposes only)
- All queue constraint values must be satisfied or the job will go into "BatchHold" until deleted.
4.2.3 To be eligible as a SIGHTS job, the science completed must have a high expectation of being published in a high-impact journal upon successful completion. Time used during the SIGHTS job will not be deducted from your project account.
