-
|
How much effort is required to deploy your own REF environment? |
Beta Was this translation helpful? Give feedback.
Replies: 1 comment
-
|
This depends on how you want to run it. For example, on ESGF they use Kubernetes as it is well supported although it would need a Dev-Ops team to implement in your institute. The REF does not require huge amounts of compute; hundreds not thousands of core hours. Some modelling centres are running local copies on their own HPC’s but this can require work-arounds as each HPC system is different. Currently, the API’s are pointing to the AFT REF version, so there would need to be some discussion of requirements. |
Beta Was this translation helpful? Give feedback.
This depends on how you want to run it. For example, on ESGF they use Kubernetes as it is well supported although it would need a Dev-Ops team to implement in your institute. The REF does not require huge amounts of compute; hundreds not thousands of core hours. Some modelling centres are running local copies on their own HPC’s but this can require work-arounds as each HPC system is different. Currently, the API’s are pointing to the AFT REF version, so there would need to be some discussion of requirements.