National systems

Sharing: Public

Early Draft

Author:CC Migration team

Introduction

TBD - detailed docs for the new systems are being written by the Research Support National Team.

Compute

Name	Description	Approximate Capacity	Availability
CC-Cloud Resources (GP1)	cloud	7,640 cores	In production (integrated with west.cloud)
GP2	general-purpose cluster (serial and small parallel jobs)	25,000 cores	February, 2017
GP3	general-purpose cluster (serial and small parallel jobs)	25,000 cores	May, 2017
LP	a cluster designed for large parallel jobs	60,000 cores	Summer, 2017
Available software

National Storage Infrastructure

The National Storage Infrastructure will have 2 components:

1	Object Storage	A fully distributed object storage system spanning all 4 sites, with geo-redundancy, replication and universal access.
2	Long-term or Nearline File Storage	"Nearline" Long-term file storage sites (similar to Silo) at SFU and the University of Waterloo. Each site will have tape backup.

Type	Location	Capacity	Availability	Comments
Long-term File Storage	Sites at SFU and Waterloo	15 PB each	Interim: Early November (Delayed)	Tape backup Silo replacement Aiming for redundant tape backup across sites
Object Store	All 4 sites	Small to start (A few PB usable)	Late 2016	Fully distributed, redundant object storage Accessible anywhere Allows for redundant, high availability architectures S3 and File interfaces New service aimed at experimental and observational data
Special Purpose	All 4 sites	~3.5 PB	Specialized migration plans	Special purpose for Atlas, LHC, SNO+, CANFAR dCache and other customized configurations

• Patrick Mann (talk) 16:43, 20 October 2016 (UTC) Storage Building Blocks have been delivered and are being installed.
• Patrick Mann (talk) 15:26, 23 September 2016 (UTC) Note that due to Silo decommissioning Dec.31/2016 it will be necessary to provide interim storage while the NSI is developed. See Migration2016:Silo for details.