User's Guide

Installation Step: IS190
In full CFS environments, this step can be omitted.
If CFS is only used for SAP and not for the database, then the volume group(s) that are required by the
database need to be distributed to all cluster nodes.
Import the shared volume groups using the minor numbers specified in Table 1 - Instance Specific Volume
Groups contained in chapter "Planning the Storage Layout".
The whole volume group distribution should be done using the command line interface. Do not use SAM.
SAM will not create minor numbers in the intended fashion. Specify the device minor numbers explicitly by
creating the group file manually.
On possible failover nodes, for example:
mkdir /dev/vgdb<SID>mknod /dev/vgdb<SID>/group c 64 0x080000
Now you can use vgimport(1m) with the map file created on the primary host during Step IS020.
Installation Step: IS210
Create a local directory for the saposcol temporary data on possible the backup nodes.
For example:
mkdir -p /usr/sap/tmp
Installation Step: IS220
Create a local mount point for each file system that was specified in chapter "Planning the Storage Layout
to have shared disk" or HA NFS" access point
Refer to the tables in chapter 2 for Instance, System and Environment specific volume groups and the
corresponding tables that represent entries for the required database type. Depending on the past usage of
the hosts, some of the directories might already exist.
For non-CFS options only:
su - <sid>admmkdir -p /sapmnt/<SID>mkdir -p /usr/sap/transmkdir -p
/usr/sap/<SID>/<INSTNAME><INSTNR>exit
MAXDB Database Step: SD230
SAPDB database specific:
su - sqd<SID>
mkdir -p /sapdb/programs
mkdir -p /sapdb/data
mkdir -p /usr/spool/sql
exit
Ownership and permissions of these directories should be chosen equally to the already existing directories
on the primary host.
MAXDB Database Step: SD235
For releases starting with MAXDB 7.5: Copy file /etc/opt/sdb to the alternate cluster nodes.
This file contains global path names for the MAXDB instance.
MAXDB Database Step: SD236
For releases starting with MAXDB 7.5:
Verify that the symbolic links listed below in directory/var/spool/sql exist on all cluster nodes running
the database.
Cluster Node Configuration
Repeat the steps in this section for each node of the cluster.
Logon as root.
SGeSAP needs remote login to be enabled on all cluster hosts. The traditional way to achieve this is via
remote shell commands. If security concerns prohibit this, it is also possible to use secure shell access instead.
54 Step-by-Step Cluster Conversion