Narval

From Alliance Doc
Revision as of 17:17, 3 August 2021 by Stubbsda (talk | contribs) (Created page with "=High-performance interconnect= The [InfiniBand] [https://www.nvidia.com/en-us/networking/infiniband/qm8700/ Mellanox HDR] network links together all of the nodes of the clust...")
Jump to navigation Jump to search
Other languages:
Availability: September, 2021
Login node: narval.computecanada.ca
Globus endpoint: computecanada#narval-dtn
Data transfer node (rsync, scp, sftp,...): narval.computecanada.ca

Narval is a general purpose cluster designed for a variety of workloads and situated at the École de technologie supérieure in Montreal. The cluster is named in honour of the St. Lawrence River's Narwhal population.

Site-specific policies

By policy, Narval's compute nodes cannot access the internet. If you need an exception to this rule, contact technical support with information about the IP address, port number(s) and protocol(s) needed as well as the duration and a contact person.

Crontab is not offered on Narval.

Each job on Narval should have a duration of at least one hour (five minutes for test jobs) and a user cannot have more than 1000 jobs, running and queued, at any given moment. The maximum duration for a job on Narval is 7 days (168 hours).

Storage

HOME
Lustre filesystem, ~100 TB of space
  • Location of home directories, each of which has a small fixed quota.
  • You should use the project space for larger storage needs.
  • 50 GB of space and 500K files per user.
  • There is a daily backup of the home directories.
SCRATCH
Lustre filesystem, ~5 PB of space
  • Large space for storing temporary files during computations.
  • No backup system in place.
  • 20 TB of space and 1M files per user.
PROJECT
Lustre filesystem, ~15 PB of space
  • This space is designed for sharing data among the members of a research group and for storing large amounts of data.
  • 1 TB of space and 500K of files per group.
  • There is a daily backup of the project space.

For transferring data via Globus, you should use the endpoint computecanada#beluga-dtn, while for tools like rsync and scp you can use a login node.

High-performance interconnect

The [InfiniBand] Mellanox HDR network links together all of the nodes of the cluster. Each hub of 40 HDR ports (200 Gb/s) can connect up to 66 nodes with HDR100 (100 Gb/s) with 33 HDR links divided in two (2) by special cables. The seven (7) remaining HDR links allow the hub to be connected to a rack containing the seven (7) cental HDR InfiniBand hubs. The islands of nodes are therefore connected by a maximum blocking factor of 33:7 (4.7:1). In contrast, the storage servers are connected by a non-blocking network.

En pratique, les cabinets de Narval contiennent des îlots de 48 ou 56 nœuds CPU réguliers. Il est donc possible d'exécuter des tâches parallèles utilisant jusqu’à 3584 cœurs et une réseautique non bloquante. Pour des tâches plus imposantes ou plus fragmentées sur le réseau, le facteur de blocage est de 4.7:1. L’interconnexion reste malgré tout de haute performance.

Caractéristiques des nœuds

nœuds cœurs mémoire disponible CPU stockage GPU
1109 64 ~256000M 2 x AMD Rome 7532 @ 2.40 GHz 256M cache L3 1 x SSD de 960G -
33 ~2048000M
158 48 ~512000M 2 x AMD Milan 7413 @ 2.65 GHz 128M cache L3 1 x SSD de 3.84T 4 x NVidia A100 (mémoire 40G)