NFS random write

In Figure 1 a random-write FIO workload is running against a file system using NFS-connected shares. The workload is scaled from 1 to 128 jobs running on the KVM guest. The storage space is provided from the protocol server contributing an additional 64 GiB of page cache.

Throughput peaks at 8 jobs and decreases with the increasing amount of FIO jobs. CPU peaks just under 1 CPU. The CPU cost increases with two or more jobs and levels out with 32 or more jobs, as shown in the constant throughput-per-CPU chart.