सत्येंद्र नाथ बसु राष्ट्रीय मौलिक विज्ञान केंद्र

सत्येंद्र नाथ बसु राष्ट्रीय मौलिक विज्ञान केंद्र

S. N. Bose National Centre for Basic Sciences

Facilities

Usage Policy | High Performance Computing

1. General conditions of use

Use of HPCs resources is subject to the Rules of the S. N. Bose National Centre for Basic Sciences, Kolkata. The Usage Rules of the Computer Services Cell (CSC) and the Privacy Policies provided by the S.N. Bose National Centre for Basic Sciences, Computer Services Cell (CSC). All users agree to abide by these rules.

2. Costs overview

This Service, designed for groups which require large amounts of computer time.Amount paid will be converted into core hour credits. These credits will be divided over an agreed time period and allocated to specific accounting periods; thus the number of core hours used is defined at the start of the usage agreement.

The Current usage fees are:
  • Rs 5.16 per CPU Core hour
  • Rs 5.16 per GB Core per month

3. Storage policies

User space is limited on the home directory file system (/home) to 40 GB per user. The contents of this file system are backed up daily, meaning that damaged or accidentally deleted files can be restored (with certain restrictions and for a limited amount of time).The amount of space currently being used can be seen via the command quota.

4. Payment

Payment can be made in four ways: (i) Cash, and (iv) Net Banking (NEFT).

  • Cash: Cash can be directly submitted to Computer Services Cell In-Charge, before starting the project.
  • Net Banking (NEFT): Net Banking facility also available for the account of S. N. Bose National Centre for Basic Sciences, Kolkata.

A requisition form and 100% payment (Cash, and Net Banking (NEFT - National Electronic Funds Transfer)) should be submitted at least 15 days prior to starting the project.

4.1. Qualified Users

Accounts will be granted to only faculty or researcher consistent with the priorities set for the use of centre HPC resources. HPC usage will be tracked by association with the principal investigator for which access has been approved and granted.

4.2 Obtaining an Account

Account requests can be made only through a peer-reviewed proposal system. The Proposal should be on the official letterhead:

  • Details of specific facility needs
  • A persuasive narrative describing your work.

Account requests associated with an established Principle Investigator will be subject to approval by that investigator with official letterhead

A unique group name will be created for the external user and associated user.

5. Connecting

  • Only SSH connections are allowed. This also includes SFTP
  • Only SSH is supported.
5.1. Connecting from Windows

You will want to use an SSH client like one of these:

  • PuTTY
  • SecureCRT
5.2. Connecting from OS X / Linux / Other OS

You should probably just use the included SSH client

6. Logging In

After your account is created, you can connect using your credentials. You can test your account using the provide credentials.

7. Moving files to/from the cluster

Since you can connect via SSH, you can use the sftp or scp commands to upload/download files to login. On Windows, you can use software like FileZilla or WS_FTP. On OS X users can useFetch or Cyberduck. Linux and other unix like OS just use the included sftp or scp commands.

8. Running jobs on the cluster

There are two types of jobs: batch and parallel. You can start by reading the the man page for 'qsub'

9. Running batch jobs

Use 'qsub'. This will allocate one slot on the cluster and request 2GB RAM by default. See the bottom of the qsub man page for an example. Check how much memory your job uses. You can try running it in an interactive session first, or run just one job and see its peak memory usage after it's done. We have different size nodes, so for a 4GB node with 4 slots, you don't want to use more than 1GB per slot. For an 8GB node with 4 slots, you don't want to use more than 2GB per slot, and so on. Make sure your submitted job doesn't use too much memory or it can crash the node. See HPC:que

10. Running parallel jobs

Use 'qsub' with the '-pe' parameter. Using the '-pe' parameter allows you to request more than one slot per job. We have several different "parallel environments" defined, they differ in how the slots are allocated. If you want your slots on the same node, use '-pe DJ'. If you want your slots spread across nodes, use '-pe make'

11. Running OpenMPI jobs

Contact snbhpc@bose.res.in with any questions

12. Job duration

We don't currently have any limit on job duration. But we recommend you try to keep your job duration to under a day or two. Jobs that run longer than that are more likely to be affected by intermittent problems. When jobs fail, you typically have to re-run them. So try to split them into many small chunks (but not too many).

13. Data Backups

Write to snbhpc@bose.res.in about data backups.

14. Technical Support

Business Hours: Monday - Friday 9:00am - 5:00pm.

To contact HPC Facility support: snbhpc@bose.res.in

15. Cluster Usage Policies Accessing Cluster

S. N. Bose National Centre for Basic Sciences, Computer Services Cell (CSC) Rights and Responsibilities S.N. Bose National Centre for Basic Sciences, Computer Services Cell (CSC) reserves the right to modify this policy at any time.

  • Systems connected to CSC's resources must be configured according to its security policy.
  • CSC is responsible for supporting only software that it has explicitly agreed to support. The list of supported software will be reviewed periodically and will be posted on the Centre Web site. Requests for new software should be forwarded to the CSC, In-Charge
  • CSC exercises no control over the content of the information passing through CSC's equipment. CSC makes no warranties of any kind for the service it provides
  • CSC will not be responsible for any damage a user, or any other person, suffers in connection with use of CSC's facilities. This includes damages resulting due to delays or service interruptions
  • Effort is made by CSC staff to prevent the loss of data in the event of hardware or software failure, or through human error. In rare cases, it may not be possible to restore the latest version of every data file from backups, and some data may be lost. CSC will not be liable to any person for any loss or corruption of any data, records or information placed on the system. Users agree to indemnify, and save CSC harmless, from all liability in connection therewith
  • CSC will maintain an up-to-date registry of all CSC computer resources, licensed software, and the location of those resources
  • In the event that CSC has actual knowledge, or there are reasonable grounds to believe, that the user may be in violation of any of the restrictions under this policy, CSC shall have the unrestricted right to terminate or suspend the user's rights under this policy
  • CSC's resources must not be applied to unlawful purposes. Use of CSC's resources in violation of applicable law or regulation is prohibited. Such prohibitions include, but are not limited to: data that are threatening, obscene, or defamatory; hate propaganda; data that belong to a third party, and data that are protected by copyright, trade secret, patent, or other intellectual-property laws
  • Each user agrees to indemnify and hold harmless CSC from any claims resulting from user's use of the service
  • CSC reserves the right to refuse extra computing resources to users if their code cannot use the extra resources efficiently. Users are encouraged to attempt problems that require large resources, but the onus is on such users to ensure that their code can use the resources efficiently

16. Access to CSC Facilities

  • Access to CSC is limited to access, and authorized users. All other access is prohibited, unless authorized in advance by the CSC working group committee
  • CSC accounts will terminate when the researcher is no longer a user, or authorized user, of CSC.
  • A user may not permit any other person, including other authorized CSC users, to access CSC facilities through his or her account. Authorization to use CSC resources may not be loaned, or given to others, except for temporary access by CSC staff for the purpose of diagnosis or problem correction
  • Providing false, or misleading, information for the purpose of obtaining access to CSC facilities is a violation of this policy
  • Access to CSC will be denied to users who violate this policy

17. User's Rights and Responsibilities

  • Above all, users are responsible at all times for using the CSC facilities in a manner that is ethical, legal, and consistent with the terms of this policy.
  • Users shall not harass, intimidate or threaten others by means of CSC facilities. Users are responsible for reporting to CSC all instances of harassment, intimidation or threats. Such conduct may constitute a violation of law and is a violation of this policy.
  • Programs, objects, and information created on CSC by a user are the property of the user, subject to the policies of the user's accounts.
  • Files controlled by individual users and residing on CSC, computers are considered to be confidential, whether or not they are accessible by other users.
  • Accounts issued on CSC facilities should not be utilized for e-mail by users unless for systems queries and assistance.
  • Users must not send proprietary or confidential information to any unauthorized party. Lending confidential information to an unauthorized party is a breach of this policy.
  • CSC's facilities are provided to enable users to conduct research. All other use is strictly prohibited unless by approval of CSC Working Group Committee.
  • Although CSC has no obligation whatsoever to monitor, review, inspect, screen, audit or otherwise verify content of the information passing through CSC's facilities, CSC reserves the right to undertake any such activities concerning compliance with this policy.
  • Users are responsible for complying with the CSC security policy. Failure to do so shall constitute a breach of this policy. In particular:
    • Users are responsible for selecting a secure password for their account, and for keeping that password secret at all times. Passwords should be changed regularly. Passwords should not be written down, stored on-line, or given to others. If it is necessary to give the password to support personnel for fixing a problem with the user's machine, the password must be changed as soon as the need for others to know the password is passed.
    • Users are responsible for protecting their own files and data from reading and/or writing by other users, using whatever protection mechanisms are provided or approved by CSC.
    • Users must not transmit confidential information in un-encrypted form over publicly accessible media, e.g., the internet or broadcast mechanisms such as those used for wireless communication. Users who need to send confidential information across public media must contact the CSC In-Charge for an appropriate encryption solution.
    • Users are responsible for reporting any system security violation, or suspected system security violation, to CSC staff immediately

Failure to adhere to any of the above provisions constitutes a fundamental and material breach of this policy. Users must notify CSC immediately of any use of CSC's facilities of which the user has actual knowledge that would, or could reasonably be considered to, constitute a violation of this policy. Although CSC's security efforts are consistent with best practice, complete privacy, confidentiality, and security is not guaranteed. Users agree that CSC shall not be responsible, or liable, for any damage that the user may suffer in connection with communication of private, confidential or sensitive information using CSC's equipment.

18. Proper Use

  • CSC facilities are a service provided to external users to conduct research. All users are responsible for seeing that these computing facilities are used in an effective, efficient, ethical, and lawful manner.
  • Many resources, including disk space, CPU cycles, and software licenses, are shared among all users. Users shall not monopolize these resources without prior authorization from the CSC Working Group Committee
  • Users should not load the system in such a way that hinders others from performing useful work
  • For software with a shared license, users should relinquish their licenses when no longer using the license.
  • Users must never leave their login sessions open and unattended.
  • Files controlled by individual users are to be considered as private information, whether or not they are accessible by other users
  • The ability to read a file does not imply permission to read that file.
  • Under no circumstances may a user alter a file that does not belong to him or her without prior permission of the file's owner or other appropriate authority. The ability to alter a file does not imply permission to alter that file.
  • Any access to CSC's records, files, information or other data contained on any database or the CSC, or the use of such records, files, information or such other data when the USER has no proper, contractually related need for such information is prohibited
  • Because the operation of CSC relies on the integrity and trust of its users, users are generally not blocked from perusing and investigating computer systems. Such access must not be abused either by attempting to harm the systems, or by stealing/copying copyrighted or licensed software
  • System-level files (not owned by individuals) may be used and viewed if their access permissions so allow.
  • Most system-level files are part of copyrighted or licensed software, and may not be copied, in whole or in part, except as allowed by the license.
  • The same standards of intellectual honesty and plagiarism apply to software as to other forms of published work.
  • Intentionally making copies of software having a restricted-use license is theft as well as copyright infringement, unless permission to copy the software has been granted by the copyright holder.
  • Deliberate alteration of system-level files is gross misconduct and can lead to termination of any and all use of CSC's facilities.
  • CSC's facilities may not be used for the purpose of making unauthorized connections to, breaking into, or adversely affecting the performance of other systems on any network, whether these systems are CSC-owned or not. The ability to connect to other systems via the network does not imply the right to make use of, or even to connect to these systems, unless properly authorized by the owners of those systems.
  • CSC recognizes the value of computer security for both network operation and product development. Users may not intentionally develop or use programs that
    • Use resources that the user doesn't have the authority to use.
    • Harass, intimidate or threaten other users.
    • Attempt to bypass system security mechanisms, steal passwords or data, or crack passwords
    • Attempt to consume all of an available system resource (memory, swap space, disk space, network bandwidth, dial-up ports, etc.)
    • Replicate themselves, or that attach themselves to other programs, in the manner commonly called worms or viruses
    • Are designed to evade software licensing or copying restrictions
    • Scan the network to identify security holes
    • Block HPC in its attempts to collect information about, and manage its systems and network traffic. Users who believe that they have a legitimate reason to use or develop programs in the above categories to perform their contractual obligations must obtain permission from the CSC Wking Group Committee before developing or using these programs.

19. Copyrighted Material and Software

  • Any software to be installed on any device in CSC must be original and properly licensed from an authenticated source authorized to distribute the software. Software obtained via a public connection (except as specified below), or from unauthenticated sources, may not be used on CSC's equipment.
  • Users who import software will be held fully responsible for all consequences that result from the use of that software. Users hereby indemnify, and save CSC harmless, for all damage, cost, expense, loss and liability arising from all acts and omissions related thereto
  • Copyrighted material must not be knowingly imported, or otherwise copied, without permission from the author. If copyright material is obtained in a manner inconsistent with the rights granted by the author, it must not be stored on CSC-owned resources, and all copies must be destroyed. Failure to adhere to this provision constitutes a material and fundamental breach of this policy. Users hereby agree to indemnify, and save CSC harmless, for all liability in connection therewith
  • Software on CSC's equipment may not be exported from CSC without the permission of the copyright holder.
  • Software licensed for academic non-profit use may not be used for non-academic purposes.
  • It is against this policy to violate the copyrights or patents on computer software. It is against this policy and may be a violation of provincial or federal law to violate software licenses.

S. N. Bose National Centre for Basic Sciences, Computer Services Cell understands the importance of uninterrupted access to computational and storage resources. As such, CSC will make every effort to meet the response times outlined in the following table. Please understand that some problem resolutions require the involvement of outside vendors, delaying problem resolutions.

Estimated Resolution Response Time

Severity:Critical:

  • Description: Cluster inaccessible, multiple users affected
  • Response: Email announcement
  • Business Hours: 1 hr response

Severity:Moderate:

  • Description: Unable to submit jobs, multiple users affected
  • Response: Email announcement
  • Business Hours: 2 hr response

Severity:Intermediate:

  • Description: Job failure, single user down, others possibly affected
  • Response: Email affected user(s)
  • Business Hours: 4 hr response

Severity:Normal:

  • Description: Support request or degraded operation
  • Response: Email affected user(s)
  • Business Hours: 4 hr response

20. Availability and planned maintenance

General availability

Every reasonable effort will be made to keep our HPC resources available and operational 24 hours per day and 7 days per week. Please note however that although the support personnel will do their best to keep the facility running at all times, we cannot guarantee to promptly resolve problems outside office hours, and during weekends and public holidays. Nevertheless, please notify snbhpc@bose.res.in if issues, whenever they arise.

20.1 Planned maintenance

Occasionally it is necessary as part of maintaining a reliable service to update system software and replace faulty hardware. Sometimes it will be possible to perform these tasks transparently by means of queue reconfiguration in a way that will not disrupt running jobs or interactive use, or significantly inconvenience users. Some tasks however, particularly those affecting storage or login nodes, may require temporary interruption of service. Where possible, maintenance activities involving a level of disruption to service will be scheduled whenever it is urgent. Please note that this does not mean that there will be disruption at this time every week merely that if potentially disruptive maintenance is necessary we will do our best to ensure it takes place during this period, in which case there will be advance notification. Establishing a predictable time slot for planned maintenance has the advantage that users may be confident that `dangerous' changes will not intentionally be undertaken at other times. Unfortunately the potential for unplanned periods of disruption is a fact of life.

20.2 Exceptional maintenance and unplanned disruptions

It may happen that despite best efforts, it becomes necessary to reduce or withdraw service at short notice and/or outside the planned maintenance time slot. This may happen e.g. for environmental reasons, such as air conditioning or power failure, or in an emergency where immediate shutdown is required to save equipment or data. It is hoped that these situations will arise rarely, although it should be noted that power cuts in this part of Cambridge are unfortunately not as rare as one would like. Obviously in such cases service will be restored as rapidly as possible.

21. Additional policies

It should be noted that jobs which require a small number of cores will turn around in a shorter time period; also shorter wall-time jobs will individually turn around faster. However it is most efficient if many small jobs are amalgamated into fewer, larger/longer batch jobs. The usage policy described here will be reviewed periodically and is subject to change.

22. HPC Software

Requests for installation of new software on central HPC cluster systems may be made in writing (e-mail to snbhpc@bose.res.in ) and may be subject to Computer Services Cell Working group's member review. Any request to install software on central HPC systems must include the licensing and operational requirements of that software. Requests to install license-restricted software must include proof of the software's legal license status for use at S.N. Bose National Centre for Basic Sciences, and valid license credentials (if applicable) must be provided to the central HPC staff for their approval before installation can occur. No software will be installed on an HPC cluster without prior proof of license eligibility.

23. Final comments

These usage rules have been constructed in a way that allows for flexibility. For the HPC Service to survive we need to recover costs but at the same time we need to allow users who have limited funding to access the machine on a negotiable basis. Overall we want to provide the best quality of service to all users so please take time to think how we may improve the service you receive and discuss your thoughts and ideas with the CC In-Charge, (snbhpc@bose.res.in ).

Failure to adhere to these provisions represents a fundamental breach of this policy.