You are here

Migration Process

Compute Canada has begun one of the biggest advanced research computing renewals in Canada’s history. Funding from the Canada Foundation for Innovation (CFI) and provincial partners is being used to replace several ageing systems with four new national systems that will consolidate resources and centralize services. For more information on the national migration process and the latest update to the technology refresh program, please visit the Compute Canada website

This page provides details specifically about migrating users and data off WestGrid’s legacy systems including any action WestGrid users need to take.

Thank you in advance for your patience during this migration period. We are working hard to limit the extent of disruptions or impacts to your research during this transition. If you have questions or concerns about any aspect of this migration process, please contact support@westgrid.ca

Table of Contents:

WestGrid Systems Defunding Schedule

*** Note“Defunded” means that the system is no longer funded, operated or maintained as part of Compute Canada’s national cyberinfrastructure platform, which is funded through the Canada Foundation for Innovation’s (CFI) Major Science Initiatives (MSI) program. After this time the system is no longer available for use by Compute Canada or WestGrid users.

Once a system has been defunded, local institutions may choose to keep a system running, at their own cost and discretion. This may result in usage limited to a certain group of users (e.g. only those from the local institution).

Users are encouraged to contact the Site Lead of the defunded system for further information.***

 

Legacy Systems to be Defunded in 2017

System(s) & Location Migration Period Defunding Date Data Deletion
Date
ACTION REQUIRED...
Silo
(University of Saskatchewan)
Complete March 31, 2017 March 24, 2017 Complete. No action required.

User Migration off the Silo system was handled by WestGrid / Compute Canada staff.
Nestor & Hermes
(University of Victoria)
Complete June 1, 2017 July 31, 2017 Complete. No action required.  UVic researchers should dontact sysadmin@uvic.ca for local use policies.
Breezy & Lattice
(University of Calgary)
August 1-31, 2017 Aug 31, 2017 Sept 30, 2017 Complete. No action required. 

UofC researchers should contact support@hpc.ucalgary.ca for local use policies.
Hungabee & Jasper
(University of Alberta)
Sept 1 - 30, 2017 Sept 30, 2017 Oct 1, 2017 Complete. No action required. 

UofA researchers should contact research.support@ualberta.ca for local use policies.
Bugaboo Simon Fraser University Dec 31, 2017 Dec 31, 2017 Wait for further instruction from the WestGrid Support Team. If you have questions, email support@westgrid.ca.


Users are asked to move their data to a new system during the Migration Period listed above and BEFORE the Defunding Date.

Any remaining data WILL BE DELETED from the system by the Data Deletion Date listed in the table above. Please refer to our Data Storage Policies for more information. Users should ensure they take the appropriate steps to comply with any data management requirements their institution or project may require.

Legacy Systems to be Defunded in 2018

System(s) Institution / Location Defunding Date What To Do...
Grex University of Manitoba Mar. 31, 2018 Wait for further instruction from the WestGrid Support Team. If you have questions, email support@westgrid.ca
Orcinus University of British Columbia Mar. 31, 2018 Wait for further instruction from the WestGrid Support Team. If you have questions, email support@westgrid.ca.

Note: Limited warranty support after January 1, 2017. See below for details.
Parallel University of Calgary Mar. 31, 2018 Wait for further instruction from the WestGrid Support Team. If you have questions, email support@westgrid.ca.

 

RAC 2017 Allocations

The RAC 2017 allocations were implemented on WestGrid systems and the new Cedar system on June 30, 2017. Users should see their jobs running with their RAC 2017 priorities. WestGrid systems scheduled for defunding in 2017 were not allocated, and will remain with their RAC 2016 priorities until they are defunded/offline.

RAC 2018 Allocations

All RAC 2018 allocations will be implemented on the new systems. If you have already migrated to Cedar or Graham, please mention this in your RAC 2018 application so that we can try to get you on a system you are already familiar with. Please note, if you elect to Fast Track and your allocation is on a to-be-defunded legacy system, your 2018 allocation will be moved to a new system.

Do I Need to Migrate?

Any user of a system in the first table above (Legacy Systems to be Defunded in 2017) will need to move any stored data and/or compute use to another system BEFORE the listed defunding date if they are not affiliated with the host site. **Please move your data well in advance of the defunding date to avoid network bottlenecks with file transfers.**

Please refer to https://docs.computecanada.ca/wiki/WestGrid_Legacy_Systems_Migration for detailed instructions and recommendations for each of the to-be-defunded systems.

We strongly recommend users make backup copies of important data as soon as the new National Data Cyberinfrastructure becomes available.

How to Migrate your Data

To move your data off a system, follow these instructions: 

  1. Delete any unneeded files.
  2. Prepare your data for transfer by archiving and compressing files.
  3. Read detailed recommendations on where to go for each of the to-be-defunded systems.
  4. Refer to the General Directives for Migration page on the Compute Canada Documentation Wiki for step-by-step instructions of how to transfer your data. 
  5. Email support@westgrid.ca to notify us when you have moved your data. 

Where to Migrate?

Detailed recommendations on where to go for each of WestGrid's to-be-defunded systems can be found on the Compute Canada Documentation Wiki. Please Note: The 2017/2018 resource allocation year (April 1, 2017 to March 31, 2018) will be a transition year with a mix of legacy and new systems available for use. 

The table below lists the WestGrid legacy systems which will be available to WestGrid users until March 31, 2018. 

System

Default Storage

Backup policy

Type of jobs

Orcinus

/home: 250 GB per user, 250,000 files


/global/scratch: 500 GB per user, 200,000 files

Backed up



No backup

Orcinus is intended for both serial and parallel applications.

Grex

/home: 30 GB per user, 500,000 files


/global/scratch: 953 GB per GROUP, 1M files/user

Daily backup



No backup. Long-term data retention not guaranteed.

Grex is primarily intended for applications that can take advantage of non-blocking low latency InfiniBand networks and large memory per compute node. It also hosts the WestGrid-wide license for Gaussian computational chemistry software. Grex is a general-use system so no special access requests required for registered WestGrid users.

Parallel

/home: 50GB, 200,00 file limit per directory




/global/scratch: 450 GB, 200,000 files; email support to increase quota

Users are responsible for their own backups.


Files older than 30 days are subject to deletion.

Parallel is intended for multi-node parallel applications that can run in a relatively short time (less than 3 days) and can take advantage of its InfiniBand interconnect or special GPU-based nodes. It can also be used for applications that have license restrictions that prevent them from being run elsewhere.

 

Future Use

Local institutions may choose to keep a defunded system running at their own cost and discretion. However, this may result in usage limited to a certain group of users (e.g. only those from the local institution). Researchers are encouraged to contact their local sites directly for further information:

Data Retention Policy for Defunded Systems

User data on defunded systems will be deleted. Users are responsible for migrating their data to alternate storage. WestGrid will give as much advance notice of data deletion dates as possible, and will notify users of data deletion dates as soon as they become available. WestGrid will keep users of defunded systems informed about timelines for migration, and will provide support for the migration process.  

For defunded systems, the host institution assumes full control of the system, including managing the storage file systems and backups. Users should contact the Site Lead of defunded systems for further information about the host institution’s data retention and deletion policies.

IMPORTANT: Non-local user data on defunded systems will be deleted after the published deletion date. WestGrid has arranged with the host institutions to keep data until the published deletion date, but can make no guarantees about data retention after that date. WestGrid will not retain any long term or back-up copies of user data and as noted above users must arrange for migration of their data. Users should also ensure they take the appropriate steps to comply with any data management requirements their institution or project may require.

Decreased Performance And Limited Support

Please Note: Legacy systems scheduled for defunding are not being maintained under comprehensive vendor support programs due to the prohibitive cost. Only critical components (interconnects and shared storage) are maintained. No new (or replacement) compute nodes will be added which will likely result in a reduced number of available compute nodes and cores over time as components die. We also expect the reliability of these resources to decline and downtime to increase due to additional needs for maintenance and repairs. There may be significant outages. If jobs are lost due to an outage, they will need to be resubmitted. 

Orcinus

As of January 01, 2017 the Orcinus storage system is not under vendor support. Due to the redundant nature of the storage controllers we feel that this is an acceptable risk. Orcinus will be backed up to the new storage system, the National Data Cyberinfrastructure (NDC) located at SFU and Waterloo. There may be some lack of continuity in backups as we transition between legacy and new tape systems, so we recommend users keep their own copies of critical data.  

Getting Started on the New Systems

Compute Canada's new national systems are now available for use. Instructions for logging on and getting started with the systems can be found here. Descriptions of the new systems can be found on the New Systems page of the Compute Canada Documentation Wiki. 

As a rule-of-thumb those users located in the West (Saskatchewan to BC) should choose Cedar-GP2, and the rest should choose Graham-GP3. This has no particular technical justification but does give at least some guidance for the choice. For Cedar-GP2 and Graham-GP3, the parallel filesystems, interconnects and external persistent storage is the same with a slightly different mix of compute nodes.

Note: WestGrid users will need to use their Compute Canada username and password to login to the new systems (the username and password used to log in to ccdb.computecanada.ca). See User Accounts and Groups on the Compute Canada Documentation Wiki for more information.

FAQs

For Frequently Asked Questions (FAQs) about migration, the national systems, and other Compute Canada services, visit the FAQ page on the Compute Canada Documentation Wiki.

Support & Other Links

Please email support@westgrid.ca for general help and questions at any point during the migration process, or refer to the following links for more tools, tips and support related to migration:

Updated 2017-07-25: Changed the quota on Grex. Updated 2017-08-03: Revised the defunding table at the top with new dates and linked everything to the docs wiki pages. Also revised the who needs to migrate section. Updated 2017-10-16: Revised the 2017 defunding table with new dates for Bugaboo.