Digital Research

alliancecan.ca · Compute, Storage · 2 records · JSON

Digital Research Alliance of Canada — 1 TB default object storage per project, up to 40 TB project / 100 TB nearline via Rapid Access Service Storagecaveatinstitutionno cardRwrite-gated
Digital Research Alliance Computefails: identityemailno cardD

Digital Research Alliance of Canada — 1 TB default object storage per project, up to 40 TB project / 100 TB nearline via Rapid Access Service Storage

caveatinstitutionno cardRwrite-gated

docs.alliancecan.ca/wiki/Arbutus_object_storage · academic · storage/digital-research-alliance-of-canada-1-tb-default-object · JSON · compare

Free tier	'All Arbutus projects are allocated a default 1TB of object storage. If more is required, you can either request an additional 9TB available through our Rapid Access Service. More than 10TB must be requested and allocated under the annual Resource Allocation Competition.' The RAS policy adds: PIs 'can request additional storage resources in any General Purpose cluster without submitting a RAC application, up to a maximum of 40 TB of project storage and 100 TB of nearline storage', with the total across all clusters capped at those numbers. unit TB; metered on stored-bytes
Price	none stated
Per-object cap	not stated
Retention	not stated
Egress	Not metered in any doc I read; OpenStack Swift/S3 serve objects over HTTPS and buckets can be made public.
Identity	institution derived from the record's prose, not from an identity field, and no signup was executed: 1 TB automatic + 9 TB RAS + up to 40 TB project storage per PI by email request. Multiple PIs/institutions each get their own; there is also a separate nearline (HPSS/tape) ceiling o
Limits	write-gated application, up to a maximum of 40 TB of project storage and 100 TB of nearline storage', w source per-object-cap: not documented for Arbutus. Retention: object storage is not backed up — 'management of a project's object storage containers is self-service. This includes operations such as backups because the object store itself is not backed up.' request-rate: not published. Gate: CCDB account (institutional), and storage above 10 TB requires an email to support@tech.alliancecan.ca from a PI.
Binding	write-gated the write is a queue with a person or a rule in it, so the upload rate is set by somebody else
Interface	s3, rclone, cli s3
Tooling	OpenStack Swift or S3 against the Arbutus object store; rclone/swift/s3cmd all work. 'We offer access to the OpenStack Object Store via two different protocols: Swift or Amazon Simple Storage Service (S3). ... object storage containers and objects created with Swift or S3 can be accessed using both protocols.'
Composes with	1 TB automatic + 9 TB RAS + up to 40 TB project storage per PI by email request. Multiple PIs/institutions each get their own; there is also a separate nearline (HPSS/tape) ceiling of 100 TB. This is the strongest nearline number in the survey after NCAR.
Reliability	Not backed up and self-managed; the docs are Anubis-protected (proof-of-work challenge) which also means scraping the current page fails and you must read the archived copy.
Notes	'All Arbutus projects are allocated a default 1TB of object storage. If more is required, you can either request an additional 9TB available through our Rapid Access Service. More than 10TB must be requested and allocated under the annual Resource Allocation Competition.' The RAS policy adds: PIs 'can request additional storage resources in any General Purpose cluster without submitting a RAC application, up to a maximum of 40 TB of project storage and 100 TB of nearline storage', with the total across all clusters capped at those numbers.
Evidence rung	reported One page read moves it to documented.
Checked	2026-10-21 (inherited); stale on 2026-11-04
Parsed numbers	`$.limits[0].value` limit:write-gated 40.0 TB

Evidence (4)

date	source	what it proved
2026-10-21	docs.alliancecan.ca/wiki/Arbutus_object_storage	captured 2024-09-14 via Wayback: 'All Arbutus projects are allocated a default 1TB of object storage... request an additional 9TB available through our Rapid Access Service. More than 10TB must be requested and allocated under the annual Resource Allocation Competition.'
2026-10-21	ualberta-rcg.github.io/ragflow-wiki-data/base/policies/rapid	'up to a maximum of 40 TB of project storage and 100 TB of nearline storage. These resources can be requested all in one cluster or split across multiple ones, but the total amount across all clusters must not exceed 40 TB of project storage or 100 TB of nearline storage.'
2026-10-21	withheld	firecrawl provider -> returns the Wikipedia language-list boilerplate; Wayback capture of the same URL -> also Anubis 'Sad Anubis / Access Denied'. Documented as a challenge-walled host; numbers above come from the 2024-09-14 capture, which predates the wall.
2026-10-21	arbutus.cloud.computecanada.ca/	probe: curl -> 302 (host alive, redirects to auth)

Unknown or withheld values (6)

$.evidence[2].url private-url
$.free_tier.notes process
$.per_object_cap.notes not-extracted
$.per_object_cap.stated not-extracted
$.retention.notes not-extracted
$.retention.stated not-extracted

Digital Research Alliance Compute

fails: identityemailno cardD

alliancecan.ca/en/services/advanced-research-computing/resea · cloud VM · compute/digital-research-alliance · JSON · compare

Free tier	Canada's national platform ran about 233,000 CPU cores, 62,000 virtual CPUs, 2,610 GPUs and 150 PB of storage across Cedar, Graham, Niagara, Beluga and Arbutus. It reserves "a target of 20% for researchers to use through the Rapid Access Service (RAS), which grants all users access to modest quantities of compute, storage and cloud resources as soon as they have a Compute Canada account", against 80% allocated competitively. unit none; metered on wall-clock; kind not stated
Price	none stated
Per-object cap	not applicable
Retention	not applicable
Egress	not stated
Identity	email not published
Binding	none no binding constraint identified
Interface	rest inferred from the tooling the provider documents; not probed
Tooling	not stated
Composes with	not established
Reliability	no reliability event recorded
Notes	no open question recorded
Evidence rung	documented
Checked	2026-10-22 (live); stale on 2026-11-21

Evidence (4)

date	source	what it proved
2026-10-22	alliancecan.ca/en/services/advanced-research-computing/resea	"approximately 233,000 CPU cores, 62,000 virtual CPUs, 2,610 GPUs and 150 PB of storage on Cedar [...] Graham [...] Niagara [...] Beluga [...] and Arbutus", quoted
2026-10-22	alliancecan.ca/en/services/advanced-research-computing/resea	"the CCF reserves a target of 20% for researchers to use through the Rapid Access Service (RAS), which grants all users access to modest quantities of compute, storage and cloud resources as soon as they have a Compute Canada account", quoted
2026-10-22	www.uoguelph.ca/research/alerts/content/digital-research-all	to apply to a Resource Allocation Competition, PIs and Co-PIs must "be a faculty member at a Canadian academic institution" and "have an active Alliance account with an Academic Principal Investigator role", quoted
2026-10-22	alliancecan.ca/en/services/advanced-research-computing/resea	the 2021 competition awarded 40 percent of CPU core years requested, 90 percent of storage and 22 percent of GPUs requested, quoted

More fields (1)

{
 "wave2": {
  "class": null,
  "free_tier_kind": null,
  "shape": null
 }
}

Unknown or withheld values (9)

$.egress.metered egress-unknown
$.egress.terms not-stated
$.identity_cost.detail process
$.per_object_cap.notes process
$.per_object_cap.stated not-applicable
$.reliability_note none-observed
$.retention.notes process
$.retention.stated not-applicable
$.tooling not-stated