Managing Serviceguard Extension for SAP Version B.05.10, December 2012

Livecache Service Monitoring
SAP recommends the use of service monitoring in order to test the runtime availability of liveCache
processes. The monitor, provided with SGeSAP, periodically checks the availability and
responsiveness of the liveCache system. The sanity of the monitor will be ensured by standard
Serviceguard functionality.
The liveCache monitoring program is shipped with SGeSAP in the saplc.mon file. The monitor runs
as a service attached to the lc<LCSID> Serviceguard package.
If the monitor recognizes the liveCache to be unavailable, it will promote the hot standby system
to become the new master. If no hot standby is available, the monitor will try to restart liveCache
on the node it is currently running. If this does not succeed, the runtime operating system resources
of liveCache are cleaned up and another local restart attempt is made. If this still does not bring
liveCache back to work and a failover package with storage option 1,2 or 3 is used, Serviceguard
will switch the package and try to restart the same instance on different hardware.
Monitoring begins with package startup. At this point, the monitor will make sure, that liveCache
is working only up to the point that is specified in lc_startmode (legacy: LCSTARTMODE).
For example, if the mode is set to offline, only the vserver processes will be part of the monitoring.
Still, the monitor detects any manual state change of liveCache. By subsequent manual operations,
liveCache will be entering cold state and finally warm state, which the monitor automatically
detects. As soon as the liveCache reaches the warm state once, the monitoring increases its internal
monitoring level to the same state.
As any SGeSAP package, the liveCache package will skip SAP specific startup steps when during
startup a debug file /var/adm/cmcluster/debug_<packagename > (legacy:
/etc/cmcluster/<LCSID>/debug) is found. This is useful for debugging purposes to allow
access to the log files placed on shared logical volumes if a package does not start up to its full
extend. The liveCache monitor is started regardless of the availability of a debug file. The monitor
will detect the existence of the file and will enter a pause mode until it is removed. This is valid not
only during package startup, but also at runtime. As a consequence, the monitoring of a fully
started package will be paused by the global debug file.
NOTE: Activation of pause mode, state changes of liveCache and liveCache restart attempts get
permanently logged into the standard package logfile
The monitor can also be paused by standard administrative tasks that use the administrative tools
delivered by SAP. Stopping the liveCache using the SAP lcinit shell command or the APO LC10
transaction will send the monitoring into pause mode. This prevents unwanted package failovers
during liveCache administration. Restarting the liveCache in the same way will also trigger
reactivation of the monitoring. The MaxDB Database Manager GUI is not yet cluster-aware and
must not be used to stop liveCache in combination with Serviceguard.
liveCache Installation Step: LC210
Log in on the primary node that has the shared logical volumes mounted .
Create a symbolic link that acts as a hook that informs SAP software where to find the liveCache
monitoring software to allow the prescribed interaction with it. Optionally, you can change the
ownership of the link to sdb:sdba.
ln -s /etc/cmcluster/<LCSID>/saplc.mon /sapdb/<LCSID>/db/sap/lccluster
liveCache Installation Step: LC215
For the following steps the SAPGUI is required. Logon to the APO central instance as user SAP* .
Start transaction/nlc10 and enter LCA for the logical connection.
/nlc10 -> Logical connection -> LCA -> liveCache -> Create/Change/Delete Connection
Change liveCache server name to the virtual IP name for the liveCache (<relocls_s) and save
it. Change the liveCache instance name to <LCSID>. Redo the above steps for LDA.
Livecache Service Monitoring 133