@@ -256,6 +256,8 @@ We monitor ceph cluster loads via Prometheus/Graphite/Grafana, and here are some
Although the cluster and NLSAS pool coped fine, due to this, we do not recommend running big jobs directly on the NLSAS pool, which should be reserved for long term storage only. Compute jobs should be on faster scratch storage e.g SSD or NVMe.
With its excellent read performance (~41GB/s during the 10n16 test), and adequate write performance (~6.8GB/s), the NLSAS pool makes a good long term storage area, for people to check out their data sets for jobs to be run.
### Networking mismatch
The client nodes we chose all have 1x100Gbe networking which could be too much for the storage nodes on 2x25Gbe. The switches that the client nodes are on are also faster.
