From the Linux kernel-parameters.txt I have seen that it is possible to change the NFS pool behaviour to have the nfsd threads bound to NUMA zones. The parameter in question is
sunrpc.pool_mode
and can be set to pernode
for NUMA affinity. There is also a note about NICs and their interrupts.
Depending on how many NICs you have and where their interrupts are bound, this option will affect which CPUs will do NFS serving.
I am not sure what how to understand this. Does it mean that if you e.g. have a 2-node NUMA system with 1 NIC, only the NFS threads that are bound to same the NUMA node as the NICs interrupts will be active and serving requests?
Hope someone already made some experience with this.
Thomas