search for: sys_sendfile

...set to 2MB and had to forcible set max xmit to 65535, which apparently default to 16K even though the docs say 64K. Writes back to the server seemed faster with max xmit larger and with the 2MB write cache size. Also a few of the return value tests look suspicious about sendfile returning 0 and sys_sendfile returns -1. It's possible that, if I'm reading one man page correctly, that a 0 means a possible EWOULDBLOCK and another offers an EAGAIN on -1 instead of EINTR. I'd be very interested in researching these further, but I have no access to updated man pages for FreeBSD, HP-UX or Solaris...

...ys_acl_to_text': lib/sysacls.c:647: warning: assignment discards qualifiers from pointer target type passdb/pdb_ldap.c: In function `ldapsam_alias_memberships': passdb/pdb_ldap.c:2649: warning: passing arg 5 of `smbldap_search' from incompatible pointer type lib/sendfile.c: In function `sys_sendfile': lib/sendfile.c:164: warning: cast from pointer to integer of different size lib/util_str.c: In function `strstr_m': lib/util_str.c:1322: warning: return discards qualifiers from pointer target type lib/iconv.c: In function `sys_iconv': lib/iconv.c:131: warning: passing arg 2 of `libic...

Two machines (NFS Server: running ZFS / Client: disk-less), both are running FreeBSD r253506. The NFS client starts to deadlock processes within a few hours. It usually gets worse from there on. The processes stay in "D" state. I haven't been able to reproduce it when I want it to happen. I only have to wait a few hours until the deadlocks occur when traffic to the client machine