Talk:Running ARC CEs for NeIC Tier 1

The "Requirements for Monitoring" sections is a monitoring-related check-list. If someone feels like adding a more complete description, I suggest adding it at the top of the page. -- Petter Urkedal (talk)

ARC Session dir

Sizing the session dir depends a lot on your specific set-up.

If you have enough space and fast enough local disk you can choose to There are three main setups:

Linked cache files and node scratch

Most data will reside in cache and on the node local disk. Only the requested output files will take up space in your session dir. You should scale the session dir to handle peak load, when jobs finishes. The expected average load is then around 200 GB + 2 G pr job (Caveat emptor. This will depend on your atlas/alice job mix )

The upper limits on used scratch space is at the time of writing 20 GB per ATLAS job and 10 GB per Alice job. Check this link for the current figures: []

Linked cache files and session dir as scratch

In this case you must size the session dir to take the scratch space into account. This means a session dir of at around 10 GB per alice job and 20 G per atlas job. (This can have a huge spread if you are only running single core jobs vs only multi core.) It can be less because of sharing of cached files.

Cache files copied to session dir and session dir as scratch

In this case you are no longer sharing cache and have to have the full job data in session directory. Expect to size the session directory In this case the session dir should be sized as 200 G + 20 G per job if you run Atlas jobs.