Infrastructure renewal: Difference between revisions

From Alliance Doc
Jump to navigation Jump to search
(remove duplicate list of systems affected)
(mention space and power to explain outages)
Line 10: Line 10:
* Improved reliability
* Improved reliability


This new infrastructure will better support your research and computational tasks, providing a better performing and more efficient environment for your work.
This new infrastructure will better support your research and computational tasks, providing a better-performing and more efficient environment for your work.


The systems being replaced are [[Arbutus]], [[Béluga]], [[Cedar]], [[Graham]] and [[Niagara]]. The new systems will be broadly comparable to the old systems, but with very significantly increased capacity.
The systems being replaced are [[Arbutus]], [[Béluga]], [[Cedar]], [[Graham]] and [[Niagara]]. The new systems will be broadly comparable to the old systems, but with significantly increased capacity.


= Outages during the transition =
= Outages during the transition =
This renewal, while very welcome, will be implemented during an intense period in the winter of 2024-2025. All systems will experience significant outages when the new systems are installed and users transitioned. Each site will develop a transition plan for their new systems. We expect to hear more details in the Autumn and will continue to update this landing page as those details become known.  
This renewal will be implemented during an intense period in the winter of 2024-2025. Constraints on space and electrical power mean that there will have to be service outages during the installation and transition to the new systems. Each site will develop a transition plan for their new system. We expect to hear more details in the autumn and will continue to update this landing page as those details become known.  


{{Callout
{{Callout
   |title=Important information
   |title=Important information
   |content=
   |content=
There will be outages Winter 2024 and Spring 2025. No details yet, but we recommend that researchers consider the possibility of such outages when planning research programs, graduate examinations, etc., for next winter and spring.
There will be outages in the winter of 2024/25 and spring of 2025. No details yet, but we recommend that researchers consider the possibility of such outages when planning research programs, graduate examinations, etc., for next winter and spring.
}}
}}



Revision as of 18:17, 12 September 2024


This article is a draft

This is not a complete article: This is a draft, a work in progress that is intended to be published into an article, which may or may not be ready for inclusion in the main wiki. It should not necessarily be considered factual or authoritative.




Welcome to the ARC/Cloud renewal transition documentation for the Digital Research Alliance of Canada (the Alliance). This is the primary source for users with questions about the upgrade of our HPC/Cloud infrastructure. The upgrade will replace the nearly 80% of our current HPC and Community Cloud equipment which is approaching end-of-life.

What's coming in 2025?[edit]

In 2023, The Digital Research Alliance of Canada was given formal approval and funding for a complete replacement of ageing national systems. The new equipment will offer:

  • Increased processing capacity
  • Increased storage capacity
  • Improved reliability

This new infrastructure will better support your research and computational tasks, providing a better-performing and more efficient environment for your work.

The systems being replaced are Arbutus, Béluga, Cedar, Graham and Niagara. The new systems will be broadly comparable to the old systems, but with significantly increased capacity.

Outages during the transition[edit]

This renewal will be implemented during an intense period in the winter of 2024-2025. Constraints on space and electrical power mean that there will have to be service outages during the installation and transition to the new systems. Each site will develop a transition plan for their new system. We expect to hear more details in the autumn and will continue to update this landing page as those details become known.


Important information

There will be outages in the winter of 2024/25 and spring of 2025. No details yet, but we recommend that researchers consider the possibility of such outages when planning research programs, graduate examinations, etc., for next winter and spring.


What we know so far[edit]

We'll keep this table updated regularly as we move through the acquisition, installation, and migration phases. Please be aware that all dates are subject to change.

Current Status Sep 3, 2024: Currently all sites have completed various Requests for Proposal, and are working with the vendors on deliverables and purchase orders. This means that we do not yet have specific delivery and installation schedules. Current system status will still be available at status.alliancecan.ca (for old and new systems)
Specifications The sites are negotiating with various vendors, but we expect the new systems to be installed during Winter 2025, with a reasonable expectation that they will be in production and available to users in early Summer 2025. Currently the sites are not yet in a position to provide detailed technical specifications of the new systems. Generally, the new systems will be similar in architecture to the old systems but with considerably increased capacity and performance. For instance, we expect to have fewer compute nodes, but each node will have a very significant increase in the number of cores due to modern multi-core CPUs
Timeline The sites are negotiating with various vendors, but we are expecting the new systems to be installed during Winter 2025, with a reasonable expectation that they will be in production and available to users in early Summer 2025

RAC allocation policy and renewals[edit]

The RAC allocation policy and renewals will be affected by this transition, but we are not changing the normal RAC process. Expect to see the usual announcements for the competition in September 2024. We expect to implement the 2025/26 allocations on the new machines when they become available so there may be some delay in RAC implementation. Detailed updates to follow. See RAC documentation available here.

System-specific updates[edit]

Arbutus[edit]

Coming soon

Béluga[edit]

Coming soon

Cedar and Cedar Cloud[edit]

Coming soon

Graham and Graham Cloud[edit]

Coming soon

Niagara[edit]

Coming soon

Frequently asked questions[edit]

As we work on finalizing the details, here are a few key points to keep in mind.

Light-bulb.pngWe are committed to providing the most up-to-date information. Please check back regularly as this section will be updated frequently to reflect any new developments


Will data be copied to the new systems?[edit]

Data migration to the new systems is a site responsibility. Each site will let you know exactly what to do once the details are finalized.

When will outages occur?[edit]

Each site will have their own schedule for outages as the new equipment is installed and transitioned. Specific outages will as usual be described on the status pages (https://status.alliancecan.ca). We will also provide more general updates through this wiki page as we know more, probably in early Autumn 2024. We will also periodically send system emails with updates and outage notices.

Who should I contact for questions about the transition?[edit]

Contact our Technical support

Will my jobs/applications run without change on the new system?[edit]

Generally yes, but with new CPUs and GPUs some codes may need recompiling or reconfiguring. More details will be provided during the transition.

Will the software from the old systems still be available?[edit]

Yes, our standard software environment will be available on the new systems.

Will there be staggered outages?[edit]

We will do our best to limit overlapping outages, but we are very constrained by delivery schedules and funding deadlines so there will probably be periods when many of our systems are simultaneously out. We’ll communicate all outages as early as possible.