While guaranteeing the strictness of the file system, there is a lot of performance involved. The performance is not as good as I expected. It's not the functionality here but the performance level. It won't be a problem if it's twice as fast.

Even though its stability has room for improvement, I would recommend it to my bigger customers.

The only problem is the current performance of the individual nodes. As a sale-out solution with integrated load-balancing functions, performance is in principle not a problem at all. Capacity and performance are linearly scalable over the number of nodes in the cluster. An increase in the performance of the individual nodes in future releases would be desirable.

Its read performance can be improved. It is just slow in comparison to other file systems, but a lot of it also has to do with the fact that they have a limited number of spindles under each node.