HP XC System Software Installation Guide Version 4.0

}
+ south2 {
lnets o2ib0
o2ib0 172.22.0.201
role ost
+ ib {
cards MT25208
}
}
}
You can also use the /usr/sbin/sfsmount command on client nodes to obtain the NIDs
configured on SFS G3.0-0 servers:
# sfsmount -X http://MGS_host_name/hptc_cluster /hptc_cluster
2. Confirm that the file system is mounted:
# mount
3. When you have verified that the /hptc_cluster file system has been mounted, unmount
it:
# sfsumount /hptc_cluster
4. Repeat the mount test for each file system you intend to mount on the client nodes. When
you have finished verifying that each file system can be mounted, proceed to Section 5.7.1.3.4
(page 84) to create the /etc/sfstab.proto file.
5.7.1.3.4 Step 4: Create the /etc/sfstab.proto File
The SFS service uses the /etc/sfstab.proto file to mount Lustre file systems at boot time.
Create an /etc/sfstab.proto file as follows:
1. If an /etc/sfstab file exists on the head node, delete it
# rm /etc/sfstab
2. Stop the SFS service:
# service sfs stop
3. Use a text editor to create and populate the /etc/sfstab.proto file according to the
guidelines described in the remainder of this section.
Example 5-1 contains a sample of an /etc/sfstab.proto file. The format and syntax of the
/etc/sfstab.proto file is described in Chapter 4 of the HP StorageWorks Scalable File Share
System User Guide for Version 2.2.
Example 5-1 Sample /etc/sfstab.proto File
lnet://nid1@o2ib0,nid2@o2ib0:/hptc_cluster /hptc_cluster sfs
server=MGS_host_name,fs=hptc_cluster,_netdev,rw,flock 0 0
In addition to the general description of the /etc/sfstab.proto file in the SFS documentation,
specific rules apply to HP XC systems. To ensure correct and optimal operation of your HP
XCcluster, you must observe the following rules:
If the /hptc_cluster file system is stored on the SFS server, it must be mounted in
foreground mode; that is, do not use the bg (background) mount option. This applies to all
nodes including the head node. This means that when a node has booted, the
/hptc_cluster file system will always be mounted on the node.
The head node must mount all other file systems (that is, with the exception of the
/hptc_cluster file system) using the bg mount option. This means that the head node
will always boot even if some file systems are not in the started state.
84 Setting Up the Environment