Server sockets staying in CLOSED for extended periods

[Kevin Oberman]

There has been a long thread on stable about sshd processes being hung due
to sockets remaining in a CLOSED state for extended periods in 10-stable.
This did not seem to be happening with 9.2. (Not sure about 10.0.)

Was here a change in the network stack on 10 that would have kept CLOSED
sockets around for extended intervals? Should sshd processes hang for
extended periods (forever?) unless killed (KILL)?

I also wonder if a daemon process should refuse to exit if a closed socket
remains.

Any suggestions would help. the full thread with a great deal of detail is
in stable with the subject "sshd with zombie process on FreeBSD 10.0-STABLE
- workaround".
-- 
R. Kevin Oberman, Network Engineer, Retired
E-mail: rkoberman at gmail.com