diff --git a/heartbeat/SAPInstance b/heartbeat/SAPInstance index e3fe788ae..26fd54136 100755 --- a/heartbeat/SAPInstance +++ b/heartbeat/SAPInstance @@ -1,1076 +1,1076 @@ #!/bin/sh # # SAPInstance # # Description: Manages a single SAP Instance as a High-Availability # resource. One SAP Instance is defined by one # SAP Instance-Profile. start/stop handles all services # of the START-Profile, status and monitor care only # about essential services. # # Author: Alexander Krauth, June 2006 # Support: linux@sap.com # License: GNU General Public License (GPL) # Copyright: (c) 2006-2008 Alexander Krauth # # An example usage: # See usage() function below for more details... # # OCF instance parameters: # OCF_RESKEY_InstanceName # OCF_RESKEY_DIR_EXECUTABLE (optional, well known directories will be searched by default) # OCF_RESKEY_DIR_PROFILE (optional, well known directories will be searched by default) # OCF_RESKEY_START_PROFILE (optional, well known directories will be searched by default) # OCF_RESKEY_START_WAITTIME (optional, to solve timing problems during J2EE-Addin start) # OCF_RESKEY_AUTOMATIC_RECOVER (optional, automatic startup recovery using cleanipc, default is false) # OCF_RESKEY_MONITOR_SERVICES (optional, default is to monitor critical services only) # OCF_RESKEY_SHUTDOWN_METHOD (optional, defaults to NORMAL, KILL: terminate the SAP instance with OS commands - faster, at your own risk) # OCF_RESKEY_ERS_InstanceName (optional, InstanceName of the ERS instance in a Promotable configuration) # OCF_RESKEY_ERS_START_PROFILE (optional, START_PROFILE of the ERS instance in a Promotable configuration) # OCF_RESKEY_PRE_START_USEREXIT (optional, lists a script which can be executed before the resource is started) # OCF_RESKEY_POST_START_USEREXIT (optional, lists a script which can be executed after the resource is started) # OCF_RESKEY_PRE_STOP_USEREXIT (optional, lists a script which can be executed before the resource is stopped) # OCF_RESKEY_POST_STOP_USEREXIT (optional, lists a script which can be executed after the resource is stopped) # OCF_RESKEY_IS_ERS (needed for ENQ/REPL NW 740) # OCF_RESKEY_MINIMAL_PROBE (optional but needed for simple mount structure architecure) # # TODO: - Option to shutdown sapstartsrv for non-active instances -> that means: do probes only with OS tools (sapinstance_status) # - Option for better standalone enqueue server monitoring, using ensmon (test enque-deque) # - Option for cleanup abandoned enqueue replication tables # ####################################################################### # Initialization: : ${OCF_FUNCTIONS_DIR=${OCF_ROOT}/lib/heartbeat} . ${OCF_FUNCTIONS_DIR}/ocf-shellfuncs # Parameter defaults OCF_RESKEY_InstanceName_default="" OCF_RESKEY_DIR_EXECUTABLE_default="" OCF_RESKEY_DIR_PROFILE_default="" OCF_RESKEY_START_PROFILE_default="" OCF_RESKEY_START_WAITTIME_default="3600" OCF_RESKEY_AUTOMATIC_RECOVER_default="false" OCF_RESKEY_MONITOR_SERVICES_default="disp+work|msg_server|enserver|enrepserver|jcontrol|jstart|enq_server|enq_replicator" OCF_RESKEY_SHUTDOWN_METHOD_default="normal" OCF_RESKEY_ERS_InstanceName_default="" OCF_RESKEY_ERS_START_PROFILE_default="" OCF_RESKEY_PRE_START_USEREXIT_default="" OCF_RESKEY_POST_START_USEREXIT_default="" OCF_RESKEY_PRE_STOP_USEREXIT_default="" OCF_RESKEY_POST_STOP_USEREXIT_default="" OCF_RESKEY_IS_ERS_default="false" OCF_RESKEY_MINIMAL_PROBE_default="false" : ${OCF_RESKEY_InstanceName=${OCF_RESKEY_InstanceName_default}} : ${OCF_RESKEY_DIR_EXECUTABLE=${OCF_RESKEY_DIR_EXECUTABLE_default}} : ${OCF_RESKEY_DIR_PROFILE=${OCF_RESKEY_DIR_PROFILE_default}} : ${OCF_RESKEY_START_PROFILE=${OCF_RESKEY_START_PROFILE_default}} : ${OCF_RESKEY_START_WAITTIME=${OCF_RESKEY_START_WAITTIME_default}} : ${OCF_RESKEY_AUTOMATIC_RECOVER=${OCF_RESKEY_AUTOMATIC_RECOVER_default}} : ${OCF_RESKEY_MONITOR_SERVICES=${OCF_RESKEY_MONITOR_SERVICES_default}} : ${OCF_RESKEY_SHUTDOWN_METHOD=${OCF_RESKEY_SHUTDOWN_METHOD_default}} : ${OCF_RESKEY_ERS_InstanceName=${OCF_RESKEY_ERS_InstanceName_default}} : ${OCF_RESKEY_ERS_START_PROFILE=${OCF_RESKEY_ERS_START_PROFILE_default}} : ${OCF_RESKEY_PRE_START_USEREXIT=${OCF_RESKEY_PRE_START_USEREXIT_default}} : ${OCF_RESKEY_POST_START_USEREXIT=${OCF_RESKEY_POST_START_USEREXIT_default}} : ${OCF_RESKEY_PRE_STOP_USEREXIT=${OCF_RESKEY_PRE_STOP_USEREXIT_default}} : ${OCF_RESKEY_POST_STOP_USEREXIT=${OCF_RESKEY_POST_STOP_USEREXIT_default}} : ${OCF_RESKEY_IS_ERS=${OCF_RESKEY_IS_ERS_default}} : ${OCF_RESKEY_IS_MINIMAL_PROBE=${OCF_RESKEY_IS_MINIMAL_PROBE_default}} ####################################################################### SH=/bin/sh sapinstance_usage() { methods=`sapinstance_methods` methods=`echo $methods | tr ' ' '|'` cat <<-EOF usage: $0 ($methods) $0 manages a SAP Instance as an HA resource. The 'start' operation starts the instance or the ERS instance in a Promotable configuration The 'stop' operation stops the instance The 'status' operation reports whether the instance is running The 'monitor' operation reports whether the instance seems to be working The 'promote' operation starts the primary instance in a Promotable configuration The 'demote' operation stops the primary instance and starts the ERS instance The 'reload' operation allows changed parameters (non-unique only) without restarting the service The 'notify' operation always returns SUCCESS The 'validate-all' operation reports whether the parameters are valid The 'methods' operation reports on the methods $0 supports EOF } sapinstance_meta_data() { cat < 1.0 Usually a SAP system consists of one database and at least one or more SAP instances (sometimes called application servers). One SAP Instance is defined by having exactly one instance profile. The instance profiles can usually be found in the directory /sapmnt/SID/profile. Each instance must be configured as it's own resource in the cluster configuration. The resource agent supports the following SAP versions: - SAP WebAS ABAP Release 6.20 - 7.40 - SAP WebAS Java Release 6.40 - 7.40 - SAP WebAS ABAP + Java Add-In Release 6.20 - 7.40 (Java is not monitored by the cluster in that case) When using a SAP Kernel 6.40 please check and implement the actions from the section "Manual postprocessing" from SAP note 995116 (http://sdn.sap.com). Other versions may also work with this agent, but have not been verified. All operations of the SAPInstance resource agent are done by using the startup framework called SAP Management Console or sapstartsrv that was introduced with SAP kernel release 6.40. Find more information about the SAP Management Console in SAP note 1014480. Using this framework defines a clear interface for the Heartbeat cluster, how it sees the SAP system. The options for monitoring the SAP system are also much better than other methods like just watching the ps command for running processes or doing some pings to the application. sapstartsrv uses SOAP messages to request the status of running SAP processes. Therefore it can actually ask a process itself what it's status is, independent from other problems that might exist at the same time. sapstartsrv knows 4 status colours: - GREEN = everything is fine - YELLOW = something is wrong, but the service is still working - RED = the service does not work - GRAY = the service has not been started The SAPInstance resource agent will interpret GREEN and YELLOW as OK. That means that minor problems will not be reported to the Heartbeat cluster. This prevents the cluster from doing an unwanted failover. The statuses RED and GRAY are reported as NOT_RUNNING to the cluster. Depending on the status the cluster expects from the resource, it will do a restart, failover or just nothing. Manages a SAP instance as an HA resource. The full qualified SAP instance name. e.g. P01_DVEBMGS00_sapp01ci. Usually this is the name of the SAP instance profile. Instance name: SID_INSTANCE_VIR-HOSTNAME The full qualified path where to find sapstartsrv and sapcontrol. Specify this parameter, if you have changed the SAP kernel directory location after the default SAP installation. Path of sapstartsrv and sapcontrol The full qualified path where to find the SAP START profile. Specify this parameter, if you have changed the SAP profile directory location after the default SAP installation. Path of start profile The name of the SAP START profile. Specify this parameter, if you have changed the name of the SAP START profile after the default SAP installation. As SAP release 7.10 does not have a START profile anymore, you need to specify the Instance Profile than. Start profile name After that time in seconds a monitor operation is executed by the resource agent. Does the monitor return SUCCESS, the start ishandled as SUCCESS. This is useful to resolve timing problems with e.g. the J2EE-Addin instance.Usually the resource agent waits until all services are started and the SAP Management Console reports a GREEN status. A double stack installation (ABAP + Java AddIn) consists of an ABAP dispatcher and a JAVA instance. Normally the start of the JAVA instance takes much longer than the start of the ABAP instance. For a JAVA Instance you may need to configure a much higher timeout for the start operation of the resource in Heartbeat. The disadvantage here is, that the discovery of a failed start by the cluster takes longer. Somebody might say: For me it is important, that the ABAP instance is up and running. A failure of the JAVA instance shall not cause a failover of the SAP instance. Actually the SAP MC reports a YELLOW status, if the JAVA instance of a double stack system fails. From the resource agent point of view YELLOW means:everything is OK. Setting START_WAITTIME to a lower value determines the resource agent to check the status of the instance during a start operation after that time. As it would wait normally for a GREEN status, now it reports SUCCESS to the cluster in case of a YELLOW status already after the specified time. That is only useful for double stack systems. Check the successful start after that time (do not wait for J2EE-Addin) The SAPInstance resource agent tries to recover a failed start attempt automatically one time. This is done by killing running instance processes, removing the kill.sap file and executing cleanipc. Sometimes a crashed SAP instance leaves some processes and/or shared memory segments behind. Setting this option to true will try to remove those leftovers during a start operation. That is to reduce manual work for the administrator. Enable or disable automatic startup recovery Within a SAP instance there can be several services. Usually you will find the defined services in the START profile of the related instance (Attention: with SAP Release 7.10 the START profile content was moved to the instance profile). Not all of those services are worth to monitor by the cluster. For example you properly do not like to failover your SAP instance, if the central syslog collector daemon fails. Those services are monitored within the SAPInstance resource agent: - disp+work - msg_server - enserver (ENSA1) - enq_server (ENSA2) - enrepserver (ENSA1) - enq_replicator (ENSA2) - jcontrol - jstart Some other services could be monitored as well. They have to be given with the parameter MONITOR_SERVICES, e.g.: - sapwebdisp - TREXDaemon.x That names match the strings used in the output of the command 'sapcontrol -nr [Instance-Nr] -function GetProcessList'. The default should fit most cases where you want to manage a SAP Instance from the cluster. You may change this with this parameter, if you like to monitor more/less or other services that sapstartsrv supports. You may specify multiple services separated by a | (pipe) sign in this parameter: disp+work|msg_server|enserver Services to monitor Usually a SAP Instance is stopped by the command 'sapcontrol -nr InstanceNr -function Stop'. SHUTDOWN_METHOD=KILL means to kill the SAP Instance using OS commands. SAP processes of the instance are terminated with 'kill -9', shared memory is deleted with 'cleanipc' and the 'kill.sap' file will be deleted. That method is much faster than the graceful stop, but the instance does not have the chance to say goodbye to other SAPinstances in the same system. USE AT YOUR OWN RISK !! Shutdown graceful or kill a SAP instance by terminating the processes. (normal|KILL) Only used in a Promotable resource configuration: The full qualified SAP enqueue replication instance name. e.g. P01_ERS02_sapp01ers. Usually this is the name of the SAP instance profile. The enqueue replication instance must be installed, before you want to configure a promotable cluster resource. The promotable configuration in the cluster must use this properties: clone_max = 2 clone_node_max = 1 master_node_max = 1 master_max = 1 Enqueue replication instance name: SID_INSTANCE_VIR-HOSTNAME Only used in a Promotable resource configuration: The parameter ERS_InstanceName must also be set in this configuration. The name of the SAP START profile. Specify this parameter, if you have changed the name of the SAP START profile after the default SAP installation. As SAP release 7.10 does not have a START profile anymore, you need to specify the Instance Profile than. Enqueue replication start profile name The full qualified path where to find a script or program which should be executed before this resource gets started. Path to a pre-start script The full qualified path where to find a script or program which should be executed after this resource got started. Path to a post-start script The full qualified path where to find a script or program which should be executed before this resource gets stopped. Path to a pre-start script The full qualified path where to find a script or program which should be executed after this resource got stopped. Path to a post-start script Only used for ASCS/ERS SAP Netweaver installations without implementing a promotable resource to allow the ASCS to 'find' the ERS running on another cluster node after a resource failure. This parameter should be set to true 'only' for the ERS instance for implementations following the SAP NetWeaver 7.40 HA certification (NW-HA-CLU-740). This includes also systems for NetWeaver less than 7.40, if you like to implement the NW-HA-CLU-740 scenario. Mark SAPInstance as ERS instance Setting MINIMAL_PROBE=true forces the resource agent to do only minimal check during a probe. This is needed for special file system setups. The MINIMAL_PROBE=true is only supported, if requested either by your vendor's support or if described in an architecture document from your HA vendor. Switch probe action from full to minimal check END } # # methods: What methods/operations do we support? # sapinstance_methods() { cat <<-EOF start stop status monitor promote demote reload notify validate-all methods meta-data usage EOF } # # is_clone : find out if we are configured to run in a Master/Slave configuration # is_clone() { if [ -n "$OCF_RESKEY_CRM_meta_clone_max" ] \ && [ "$OCF_RESKEY_CRM_meta_clone_max" -gt 0 ] then if [ "$OCF_RESKEY_CRM_meta_clone_max" -ne 2 ] || \ [ "$OCF_RESKEY_CRM_meta_clone_node_max" -ne 1 ] || \ [ "$OCF_RESKEY_CRM_meta_master_node_max" -ne 1 ] || \ [ "$OCF_RESKEY_CRM_meta_master_max" -ne 1 ] then ocf_log err "Clone options misconfigured. (expect: clone_max=2,clone_node_max=1,master_node_max=1,master_max=1)" exit $OCF_ERR_CONFIGURED fi if [ -z "$OCF_RESKEY_ERS_InstanceName" ] then ocf_log err "In a Master/Slave configuration the ERS_InstanceName parameter is mandatory." exit $OCF_ERR_ARGS fi else return 0 fi return 1 } # # abnormal_end : essential things are missing, but in the natur of a SAP installation - which can be very different # from customer to customer - we cannot handle this always as an error # This would be the case, if the software is installed on shared disks and not visible # to all cluster nodes at all times. # abnormal_end() { local err_msg=$1 ocf_is_probe && { sapinstance_status exit $? } ocf_log err $err_msg if [ "$ACTION" = "stop" ] then cleanup_instance exit $OCF_SUCCESS fi exit $OCF_ERR_CONFIGURED } # # sapinstance_init : Define global variables with default values, if optional parameters are not set # # sapinstance_init() { local myInstanceName="$1" SID=`echo "$myInstanceName" | cut -d_ -f1` InstanceName=`echo "$myInstanceName" | cut -d_ -f2` InstanceNr=`echo "$InstanceName" | sed 's/.*\([0-9][0-9]\)$/\1/'` SAPVIRHOST=`echo "$myInstanceName" | cut -d_ -f3` # make sure that we don't care the content of variable from previous run of sapinstance_init DIR_EXECUTABLE="" SYSTEMCTL="systemctl" # optional OCF parameters, we try to guess which directories are correct if [ -z "$OCF_RESKEY_DIR_EXECUTABLE" ] then if have_binary /usr/sap/$SID/$InstanceName/exe/sapstartsrv && have_binary /usr/sap/$SID/$InstanceName/exe/sapcontrol then DIR_EXECUTABLE="/usr/sap/$SID/$InstanceName/exe" SAPSTARTSRV="/usr/sap/$SID/$InstanceName/exe/sapstartsrv" SAPCONTROL="/usr/sap/$SID/$InstanceName/exe/sapcontrol" elif have_binary /usr/sap/$SID/SYS/exe/run/sapstartsrv && have_binary /usr/sap/$SID/SYS/exe/run/sapcontrol then DIR_EXECUTABLE="/usr/sap/$SID/SYS/exe/run" SAPSTARTSRV="/usr/sap/$SID/SYS/exe/run/sapstartsrv" SAPCONTROL="/usr/sap/$SID/SYS/exe/run/sapcontrol" fi else if have_binary "$OCF_RESKEY_DIR_EXECUTABLE/sapstartsrv" && have_binary "$OCF_RESKEY_DIR_EXECUTABLE/sapcontrol" then DIR_EXECUTABLE="$OCF_RESKEY_DIR_EXECUTABLE" SAPSTARTSRV="$OCF_RESKEY_DIR_EXECUTABLE/sapstartsrv" SAPCONTROL="$OCF_RESKEY_DIR_EXECUTABLE/sapcontrol" fi fi sidadm="`echo $SID | tr '[:upper:]' '[:lower:]'`adm" [ -z "$DIR_EXECUTABLE" ] && abnormal_end "Cannot find sapstartsrv and sapcontrol executable, please set DIR_EXECUTABLE parameter!" if [ -z "$OCF_RESKEY_DIR_PROFILE" ] then DIR_PROFILE="/usr/sap/$SID/SYS/profile" else DIR_PROFILE="$OCF_RESKEY_DIR_PROFILE" fi if [ "$myInstanceName" != "$OCF_RESKEY_InstanceName" ] then currentSTART_PROFILE=$OCF_RESKEY_ERS_START_PROFILE else currentSTART_PROFILE=$OCF_RESKEY_START_PROFILE fi if [ -z "$OCF_RESKEY_IS_ERS" ]; then is_ers="no" else is_ers="$OCF_RESKEY_IS_ERS" fi if [ -z "$currentSTART_PROFILE" ] then if [ ! -r "$DIR_PROFILE/START_${InstanceName}_${SAPVIRHOST}" -a -r "$DIR_PROFILE/${SID}_${InstanceName}_${SAPVIRHOST}" ]; then SAPSTARTPROFILE="$DIR_PROFILE/${SID}_${InstanceName}_${SAPVIRHOST}" else SAPSTARTPROFILE="$DIR_PROFILE/START_${InstanceName}_${SAPVIRHOST}" fi else SAPSTARTPROFILE="$currentSTART_PROFILE" fi if [ -z "$OCF_RESKEY_START_WAITTIME" ] then export OCF_RESKEY_START_WAITTIME="${OCF_RESKEY_START_WAITTIME_default}" fi if [ -z "$OCF_RESKEY_MONITOR_SERVICES" ] then export OCF_RESKEY_MONITOR_SERVICES="${OCF_RESKEY_MONITOR_SERVICES_default}" fi # as root user we need the library path to the SAP kernel to be able to call sapcontrol if [ `echo $LD_LIBRARY_PATH | grep -c "^$DIR_EXECUTABLE\>"` -eq 0 ]; then LD_LIBRARY_PATH=$DIR_EXECUTABLE${LD_LIBRARY_PATH:+:}$LD_LIBRARY_PATH export LD_LIBRARY_PATH fi return $OCF_SUCCESS } # # check_systemd_integration : Check, if SAP instance is controlled by systemd unit file SAP_.service # rc == 0 : sap instance is controlled by the unit file (file at least exists) # rc == 1 : sap instance is NOT controlled by the unit file (file does not exist) # check_systemd_integration() { local systemd_unit_name="SAP${SID}_${InstanceNr}" local rc=1 if which "$SYSTEMCTL" 1>/dev/null 2>/dev/null; then if $SYSTEMCTL list-unit-files | \ awk '$1 == service { found=1 } END { if (! found) {exit 1}}' service="${systemd_unit_name}.service"; then rc=0 else rc=1 fi fi return "$rc" } # # check_sapstartsrv : Before using sapcontrol we make sure that the sapstartsrv is running for the correct instance. # We cannot use sapinit and the /usr/sap/sapservices file in case of an enquerep instance, # because then we have two instances with the same instance number. # check_sapstartsrv() { local restart=0 local runninginst="" local chkrc=$OCF_SUCCESS local output="" # check for sapstartsrv/systemd integration if check_systemd_integration; then # do it the systemd way local systemd_unit_name="SAP${SID}_${InstanceNr}" if $SYSTEMCTL status "$systemd_unit_name" 1>/dev/null 2>/dev/null; then ocf_log info "systemd service $systemd_unit_name is active" else ocf_log warn "systemd service $systemd_unit_name is not active, it will be started using systemd" $SYSTEMCTL start "$systemd_unit_name" 1>/dev/null 2>/dev/null # use start, because restart does also stop sap instance fi return 0 else # otherwise continue with old code... if [ ! -S /tmp/.sapstream5${InstanceNr}13 ]; then ocf_log warn "sapstartsrv is not running for instance $SID-$InstanceName (no UDS), it will be started now" restart=1 else output=`$SAPCONTROL -nr $InstanceNr -function ParameterValue INSTANCE_NAME -format script` if [ $? -eq 0 ] then runninginst=`echo "$output" | grep '^0 : ' | cut -d' ' -f3` if [ "$runninginst" != "$InstanceName" ] then ocf_log warn "sapstartsrv is running for instance $runninginst, that service will be killed" restart=1 else output=`$SAPCONTROL -nr $InstanceNr -function AccessCheck Start` if [ $? -ne 0 ]; then ocf_log warn "FAILED : sapcontrol -nr $InstanceNr -function AccessCheck Start (`ls -ld1 /tmp/.sapstream5${InstanceNr}13`)" ocf_log warn "sapstartsrv will be restarted to try to solve this situation, otherwise please check sapstsartsrv setup (SAP Note 927637)" restart=1 fi fi else ocf_log warn "sapstartsrv is not running for instance $SID-$InstanceName, it will be started now" restart=1 fi fi if [ -z "$runninginst" ]; then runninginst=$InstanceName; fi if [ $restart -eq 1 ] then if [ -d /usr/sap/$SID/SYS/profile/ ] then DIR_PROFILE="/usr/sap/$SID/SYS/profile" else abnormal_end "Expected /usr/sap/$SID/SYS/profile/ to be a directory, please set DIR_PROFILE parameter!" fi [ ! -r $SAPSTARTPROFILE ] && abnormal_end "Expected $SAPSTARTPROFILE to be the instance START profile, please set START_PROFILE parameter!" pkill -9 -f "sapstartsrv.*$runninginst" # removing the unix domain socket files as they might have wrong permissions # or ownership - they will be recreated by sapstartsrv during next start rm -f /tmp/.sapstream5${InstanceNr}13 rm -f /tmp/.sapstream5${InstanceNr}14 $SAPSTARTSRV pf=$SAPSTARTPROFILE -D -u $sidadm # now make sure the daemon has been started and is able to respond local srvrc=1 while [ $srvrc -eq 1 -a `pgrep -f "sapstartsrv.*$runninginst" | wc -l` -gt 0 ] do sleep 1 $SAPCONTROL -nr $InstanceNr -function GetProcessList > /dev/null 2>&1 srvrc=$? done if [ $srvrc -ne 1 ] then ocf_log info "sapstartsrv for instance $SID-$InstanceName was restarted !" chkrc=$OCF_SUCCESS else ocf_log error "sapstartsrv for instance $SID-$InstanceName could not be started!" chkrc=$OCF_ERR_GENERIC ocf_is_probe && chkrc=$OCF_NOT_RUNNING fi fi return $chkrc fi } # # sapuserexit : Many SAP customers need some additional processes/tools to run their SAP systems. # This specialties do not allow a totally generic SAP cluster resource agent. # Someone should write a resource agent for each additional process you need, if it # is required to monitor that process within the cluster manager. To enable # you to extent this resource agent without developing a new one, this user exit # was introduced. # sapuserexit() { local NAME="$1" local VALUE="$2" if [ -n "$VALUE" ] then if have_binary "$VALUE" then ocf_log info "Calling userexit ${NAME} with customer script file ${VALUE}" "$VALUE" >/dev/null 2>&1 ocf_log info "Exiting userexit ${NAME} with customer script file ${VALUE}, returncode: $?" else ocf_log warn "Attribute ${NAME} is set to ${VALUE}, but this file is not executable" fi fi return 0 } # # cleanup_instance : remove resources (processes and shared memory) from a crashed instance) # cleanup_instance() { pkill -9 -f -U $sidadm $InstanceName ocf_log info "Terminated instance using 'pkill -9 -f -U $sidadm $InstanceName'" # it is necessary to call cleanipc as user sidadm if the system has 'vmcj/enable = ON' set - otherwise SHM-segments in /dev/shm/SAP_ES2* cannot be removed su - $sidadm -c "cleanipc $InstanceNr remove" ocf_log info "Tried to remove shared memory resources using 'cleanipc $InstanceNr remove' as user $sidadm" ocf_run rm -fv /usr/sap/$SID/$InstanceName/work/kill.sap ocf_run rm -fv /usr/sap/$SID/$InstanceName/work/shutdown.sap ocf_run rm -fv /usr/sap/$SID/$InstanceName/data/rslgcpid ocf_run rm -fv /usr/sap/$SID/$InstanceName/data/rslgspid return 0 } # # sapinstance_start : Start the SAP instance # sapinstance_start() { sapuserexit PRE_START_USEREXIT "$OCF_RESKEY_PRE_START_USEREXIT" local rc=$OCF_NOT_RUNNING local output="" local loopcount=0 while [ $loopcount -lt 2 ] do loopcount=$(($loopcount + 1)) check_sapstartsrv rc=$? if [ $rc -eq $OCF_SUCCESS ]; then output=`$SAPCONTROL -nr $InstanceNr -function Start` rc=$? ocf_log info "Starting SAP Instance $SID-$InstanceName: $output" fi if [ $rc -ne 0 ] then ocf_log err "SAP Instance $SID-$InstanceName start failed." return $OCF_ERR_GENERIC fi local startrc=1 while [ $startrc -gt 0 ] do local waittime_start=`date +%s` output=`$SAPCONTROL -nr $InstanceNr -function WaitforStarted $OCF_RESKEY_START_WAITTIME 10` startrc=$? local waittime_stop=`date +%s` if [ $startrc -ne 0 ] then if [ $(($waittime_stop - $waittime_start)) -ge $OCF_RESKEY_START_WAITTIME ] then sapinstance_monitor NOLOG if [ $? -eq $OCF_SUCCESS ] then output="START_WAITTIME ($OCF_RESKEY_START_WAITTIME) has elapsed, but instance monitor returned SUCCESS. Instance considered running." startrc=0; loopcount=2 fi else if [ $loopcount -eq 1 ] && ocf_is_true $OCF_RESKEY_AUTOMATIC_RECOVER then ocf_log warn "SAP Instance $SID-$InstanceName start failed: $output" ocf_log warn "Try to recover $SID-$InstanceName" cleanup_instance else loopcount=2 fi startrc=-1 fi else loopcount=2 fi done done if [ $startrc -eq 0 ] then ocf_log info "SAP Instance $SID-$InstanceName started: $output" rc=$OCF_SUCCESS sapuserexit POST_START_USEREXIT "$OCF_RESKEY_POST_START_USEREXIT" if ocf_is_true $is_ers; then crm_attribute -n runs_ers_${SID} -v 1 -l reboot; fi else ocf_log err "SAP Instance $SID-$InstanceName start failed: $output" rc=$OCF_NOT_RUNNING if ocf_is_true $is_ers; then crm_attribute -n runs_ers_${SID} -v 0 -l reboot; fi fi return $rc } # # sapinstance_recover: Try startup of failed instance by cleaning up resources # sapinstance_recover() { cleanup_instance sapinstance_start return $? } # # sapinstance_stop: Stop the SAP instance # sapinstance_stop() { local output="" local rc sapuserexit PRE_STOP_USEREXIT "$OCF_RESKEY_PRE_STOP_USEREXIT" if [ "$OCF_RESKEY_SHUTDOWN_METHOD" = "KILL" ] then ocf_log info "Stopping SAP Instance $SID-$InstanceName with shutdown method KILL!" cleanup_instance return $OCF_SUCCESS fi check_sapstartsrv rc=$? if [ $rc -eq $OCF_SUCCESS ]; then output=`$SAPCONTROL -nr $InstanceNr -function Stop` rc=$? ocf_log info "Stopping SAP Instance $SID-$InstanceName: $output" fi if [ $rc -eq 0 ] then output=`$SAPCONTROL -nr $InstanceNr -function WaitforStopped 3600 1` if [ $? -eq 0 ] then ocf_log info "SAP Instance $SID-$InstanceName stopped: $output" rc=$OCF_SUCCESS else ocf_log err "SAP Instance $SID-$InstanceName stop failed: $output" rc=$OCF_ERR_GENERIC fi else ocf_log err "SAP Instance $SID-$InstanceName stop failed: $output" rc=$OCF_ERR_GENERIC fi sapuserexit POST_STOP_USEREXIT "$OCF_RESKEY_POST_STOP_USEREXIT" if ocf_is_true $is_ers; then crm_attribute -n runs_ers_${SID} -v 0 -l reboot; fi return $rc } # # sapinstance_monitor: Can the given SAP instance do anything useful? # sapinstance_monitor() { local MONLOG=$1 local rc if ocf_is_probe && ocf_is_true "$OCF_RESKEY_MINIMAL_PROBE"; then # code for minimal probe: # grep for sapstartsrv and maybe also for sapstart # TODO: Do we need to improve this minimal test? if pgrep -f -l "sapstartsrv .*pf=.*${SID}_${InstanceName}_${SAPVIRHOST}"; then rc="$OCF_SUCCESS" elif pgrep -f -l "sapstart .*pf=.*${SID}_${InstanceName}_${SAPVIRHOST}"; then rc="$OCF_SUCCESS" else rc="$OCF_NOT_RUNNING" fi else # standard probe and monitoring code check_sapstartsrv rc=$? fi if [ $rc -eq $OCF_SUCCESS ] then local count=0 local SERVNO local output output=`$SAPCONTROL -nr $InstanceNr -function GetProcessList -format script` # we have to parse the output, because the returncode doesn't tell anything about the instance status for SERVNO in `echo "$output" | grep '^[0-9] ' | cut -d' ' -f1 | sort -u` do local COLOR=`echo "$output" | grep "^$SERVNO dispstatus: " | cut -d' ' -f3` local SERVICE=`echo "$output" | grep "^$SERVNO name: " | cut -d' ' -f3` local STATE=0 local SEARCH case $COLOR in GREEN|YELLOW) STATE=$OCF_SUCCESS;; *) STATE=$OCF_NOT_RUNNING;; esac SEARCH=`echo "$OCF_RESKEY_MONITOR_SERVICES" | sed 's/\+/\\\+/g' | sed 's/\./\\\./g'` if [ `echo "$SERVICE" | egrep -c "$SEARCH"` -eq 1 ] then if [ $STATE -eq $OCF_NOT_RUNNING ] then [ "$MONLOG" != "NOLOG" ] && ocf_log err "SAP instance service $SERVICE is not running with status $COLOR !" rc=$STATE fi count=1 fi done if [ $count -eq 0 -a $rc -eq $OCF_SUCCESS ] then if ocf_is_probe then rc=$OCF_NOT_RUNNING else [ "$MONLOG" != "NOLOG" ] && ocf_log err "The SAP instance does not run any services which this RA could monitor!" rc=$OCF_ERR_GENERIC fi fi fi return $rc } # # sapinstance_status: Lightweight check of SAP instance only with OS tools # sapinstance_status() { local pid local pids [ ! -f "/usr/sap/$SID/$InstanceName/work/kill.sap" ] && return $OCF_NOT_RUNNING - pids=`grep '^kill -[0-9]' /usr/sap/$SID/$InstanceName/work/kill.sap | awk '{print $3}'` + pids=$(awk '$3 ~ "^[0-9]+$" { print $3 }' /usr/sap/$SID/$InstanceName/work/kill.sap) for pid in $pids do [ `pgrep -f -U $sidadm $InstanceName | grep -c $pid` -gt 0 ] && return $OCF_SUCCESS done return $OCF_NOT_RUNNING } # # sapinstance_validate: Check the semantics of the input parameters # sapinstance_validate() { local rc=$OCF_SUCCESS if [ `echo "$SID" | grep -c '^[A-Z][A-Z0-9][A-Z0-9]$'` -ne 1 ] then ocf_log err "Parsing instance profile name: '$SID' is not a valid system ID!" rc=$OCF_ERR_ARGS fi if [ `echo "$InstanceName" | grep -c '^[A-Z].*[0-9][0-9]$'` -ne 1 ] then ocf_log err "Parsing instance profile name: '$InstanceName' is not a valid instance name!" rc=$OCF_ERR_ARGS fi if [ `echo "$InstanceNr" | grep -c '^[0-9][0-9]$'` -ne 1 ] then ocf_log err "Parsing instance profile name: '$InstanceNr' is not a valid instance number!" rc=$OCF_ERR_ARGS fi if [ `echo "$SAPVIRHOST" | grep -c '^[A-Za-z][A-Za-z0-9_-]*$'` -ne 1 ] then ocf_log err "Parsing instance profile name: '$SAPVIRHOST' is not a valid hostname!" rc=$OCF_ERR_ARGS fi return $rc } # # sapinstance_start_clone # sapinstance_start_clone() { sapinstance_init $OCF_RESKEY_ERS_InstanceName ${HA_SBIN_DIR}/crm_master -v 50 -l reboot sapinstance_start return $? } # # sapinstance_stop_clone # sapinstance_stop_clone() { sapinstance_init $OCF_RESKEY_ERS_InstanceName ${HA_SBIN_DIR}/crm_master -v 0 -l reboot sapinstance_stop return $? } # # sapinstance_monitor_clone # sapinstance_monitor_clone() { # first check with the status function (OS tools) if there could be something like a SAP instance running # as we do not know here, if we are in master or slave state we do not want to start our monitoring # agents (sapstartsrv) on the wrong host local rc sapinstance_init $OCF_RESKEY_InstanceName if sapinstance_status; then if sapinstance_monitor; then ${HA_SBIN_DIR}/crm_master -Q -v 100 -l reboot return $OCF_RUNNING_MASTER fi # by nature of the SAP enqueue server we have to make sure # that we do a failover to the slave (enqueue replication server) # in case the enqueue process has failed. We signal this to the # cluster by setting our master preference to a lower value than the slave. ${HA_SBIN_DIR}/crm_master -v 10 -l reboot return $OCF_FAILED_MASTER fi sapinstance_init $OCF_RESKEY_ERS_InstanceName sapinstance_status && sapinstance_monitor rc=$? if [ $rc -eq $OCF_SUCCESS ]; then ${HA_SBIN_DIR}/crm_master -Q -v 100 -l reboot fi return $rc } # # sapinstance_promote_clone: In a Master/Slave configuration get Master by starting the SCS instance and stopping the ERS instance # The order is important here to behave correct from the application levels view # sapinstance_promote_clone() { local rc sapinstance_init $OCF_RESKEY_InstanceName ocf_log info "Promoting $SID-$InstanceName to running Master." sapinstance_start rc=$? if [ $rc -eq $OCF_SUCCESS ]; then sapinstance_init $OCF_RESKEY_ERS_InstanceName sapinstance_stop rc=$? fi return $rc } # # sapinstance_demote_clone: In a Master/Slave configuration get Slave by stopping the SCS instance and starting the ERS instance # sapinstance_demote_clone() { local rc sapinstance_init $OCF_RESKEY_InstanceName ocf_log info "Demoting $SID-$InstanceName to a slave." sapinstance_stop rc=$? if [ $rc -eq $OCF_SUCCESS ]; then sapinstance_init $OCF_RESKEY_ERS_InstanceName sapinstance_start rc=$? fi return $rc } # # sapinstance_notify: Handle master scoring - to make sure a slave gets the next master # sapinstance_notify() { local n_type="$OCF_RESKEY_CRM_meta_notify_type" local n_op="$OCF_RESKEY_CRM_meta_notify_operation" if [ "${n_type}_${n_op}" = "post_promote" ]; then # After promotion of one master in the cluster, we make sure that all clones reset their master # value back to 100. This is because a failed monitor on a master might have degree one clone # instance to score 10. ${HA_SBIN_DIR}/crm_master -v 100 -l reboot elif [ "${n_type}_${n_op}" = "pre_demote" ]; then # if we are a slave and a demote event is announced, make sure we are highest on the list to become master # that is, when a slave resource was started after the promote event of an already running master (e.g. node of slave was down) # We also have to make sure to overrule the globally set resource_stickiness or any fail-count factors => INFINITY local n_uname="$OCF_RESKEY_CRM_meta_notify_demote_uname" if [ ${n_uname} != ${NODENAME} ]; then ${HA_SBIN_DIR}/crm_master -v INFINITY -l reboot fi fi } # # 'main' starts here... # ## GLOBALS SID="" sidadm="" InstanceName="" InstanceNr="" SAPVIRHOST="" DIR_EXECUTABLE="" SAPSTARTSRV="" SAPCONTROL="" DIR_PROFILE="" SAPSTARTPROFILE="" CLONE=0 NODENAME=$(ocf_local_nodename) if ( [ $# -ne 1 ] ) then sapinstance_usage exit $OCF_ERR_ARGS fi ACTION=$1 if [ "$ACTION" = "status" ]; then ACTION=monitor fi # These operations don't require OCF instance parameters to be set case "$ACTION" in usage|methods) sapinstance_$ACTION exit $OCF_SUCCESS;; meta-data) sapinstance_meta_data exit $OCF_SUCCESS;; notify) sapinstance_notify exit $OCF_SUCCESS;; *);; esac if ! ocf_is_root then ocf_log err "$0 must be run as root" exit $OCF_ERR_PERM fi # parameter check if [ -z "$OCF_RESKEY_InstanceName" ] then ocf_log err "Please set OCF_RESKEY_InstanceName to the name to the SAP instance profile!" exit $OCF_ERR_ARGS fi is_clone; CLONE=$? if [ ${CLONE} -eq 1 ] then CLACT=_clone else if [ "$ACTION" = "promote" -o "$ACTION" = "demote" ] then ocf_log err "$ACTION called in a non master/slave environment" exit $OCF_ERR_ARGS fi sapinstance_init $OCF_RESKEY_InstanceName fi # What kind of method was invoked? case "$ACTION" in start|stop|monitor|promote|demote) sapinstance_$ACTION$CLACT exit $?;; validate-all) sapinstance_validate exit $?;; reload ) ocf_log info "reloading SAPInstance parameters" exit $OCF_SUCCESS;; *) sapinstance_methods exit $OCF_ERR_UNIMPLEMENTED;; esac