Looking at nfsstat -s on a too-busy filer:
Server rpc:
TCP:
calls badcalls nullrecv badlen xdrcall
623374644 4294965579 0 0 4294965579
UDP:
calls badcalls nullrecv badlen xdrcall
94335674 2 0 0 2
IPv4:
calls badcalls nullrecv badlen xdrcall
717710318 3 0 0 3
IPv6:
calls badcalls nullrecv badlen xdrcall
0 0 0 0 0
Server nfs:
calls badcalls
717708871 0
Why are IPV4 badcalls and IPV6 badcalls near zero? Shouldn't they be more or less the sum of TCP + UCP badcalls?
Even though badcalls=xdrcalls? (which is interesting by itself and might be the result of a bug in Objectivity and its proprietary brain-damaged NFS stack.)
I don't think this is a counter wrap issue (even though TCP calls seems to have wrapped.)
