Lustre Knowledge Base

This is an inofficial Knowledge Base based on posts on the lustre-discuss mailinglist as the official Knowledge Base is not longer available (moved into the Manual). Please also have a look on the official Knowledge Base, which is part of the Lustre Manual.

What to do when port 988 is already in use?

You've to make sure that the module "ptlrpc" is loaded in the boot process as early as possible before portmapper is able to handle this port to different applications. Then lustre will grab this port. As a hack you can use this small rc script (provided from Ulrich Sibiller on lustre-discuss):

#!/bin/sh
#
# /etc/rc.lustre-reserveport
#
# Load Lustre module ptlrpc early in boot process. This is a hack to prevent
# portmapper from handing out port 988 to different applications before
# Lustre's network layer has a chance to grab it.

case "$1" in
          start|restart|reload)
                  modprobe ptlrpc || :
                  # XXX The above apparently prevents auto-loading of module
                  #     lustre during mount. Force it in now.
                  modprobe lustre || :
                  ;;
          stop)
                  if which lustre_rmmod >/dev/null; then
                          lustre_rmmod
                  fi
                  ;;
esac

exit 0

Which is the IP Address providing the testfs-OST0001 target?

If the hosts are connected via tcp/ip you are able to map the NID to an ip via this command:

lctl get_param osc.${fsname}-${OSTname}*.ost_conn_uuid

An sample output will looks like this

testserver:~# lctl get_param osc.spfs-OST0001-osc-dee0dc00.ost_conn_uuid
osc.spfs-OST0001-osc-dee0dc00.ost_conn_uuid=192.168.1.5@tcp
testserver:~#