Hi,
On Fri, Nov 07, 2008 at 04:17:58PM +0000, Igor Neves wrote:
> Hi,
>
> I'm writing this email to both lists, to let the community know this too.
> It's possible to add this code with all the other OCF scripts?
Sure. A few notes on the scripts.
ejabberd:
1.
# * OCF_RESKEY_waitup
# * OCF_RESKEY_waitdown
You can remove these two: the best practice is that the RA keeps
trying in a loop and we let the administrator configure timeouts
in the CIB.
2. In check_ejabberd_running this test is necessary (should be
done in the validate action):
if [ -f "$EJABBERDCTL" ]; then
3. In check_msn_tranport_running the last if-else is not
necessary (superfluous). But you should check if the pid file
exists before kill.
4. You should invoke _validate for all actions. Move the
meta-data, usage, and help up, so that you have two sets of
actions and validate in between. See other RAs.
5. Not sure, but it looks like the monitor operation is not
correct. Shouldn't it check both ejabberd and the msn_transport?
There's also a typo: search for "tranport".
6. In validate, if the required program's missing (*ctl), you
should exit with OCF_ERR_INSTALLED.
7. Drop the ocf_log info message from validate: it will be
annoying.
Did you use ocf-tester to test the RA?
No time now to check the other RA. Tomorrow probably.
Many thanks for the contribution.
Cheers,
Dejan
> My English it's not great, and I'm not a guru, if I make mistake somewhere
> please tell where, so I can correct.
>
> The OCF script are attached and all have the copyright stuff. If something
> it's missing about authorizations, please tell me.
>
> Thanks,
>
> --
> Igor Neves <[EMAIL PROTECTED]>
> 3GNTW - Tecnologias de Informa??o, Lda
>
> SIP/JID/MSN: [EMAIL PROTECTED] Mobile Phone: 00351914503611
> Local Phone: 00351252377120
>
>
> #!/bin/sh
> #
> # CGatePro OCF resource agent
> #
> # Description: Manages a CGatePro High-Availability Resource
> #
> # Author: Igor Neves <igor AT 3gnt DOT net>
> # <neves DOT igor AT gmail DOT com>
> # License: GNU General Public License (GPL)
> #
> # Copyright: (C) 2008 3GNTW - Tecnologias de Informacao, Lda
> # All Rights Reserved.
> #
> # OCF parameters:
> # * OCF_RESKEY_basefolder
> # * OCF_RESKEY_application
> # * OCF_RESKEY_waitdown
> # * OCF_RESKEY_waitup
> # * OCF_RESKEY_supplyparams
> #
> #################################################################
> # Source ocf shell functions
> . ${OCF_ROOT}/resource.d/heartbeat/.ocf-shellfuncs
>
> # Variable configuration
> #################################################################
> # Who much time (in sec) we will wait until check if CGatePro its UP
> # (default: 10sec)
> CGPRO_WAIT_UP="$OCF_RESKEY_waitup"
>
> # Who much time (in sec) we will wait until check if CGatePro its DOWN
> # (default: 10sec)
> CGPRO_WAIT_DOWN="$OCF_RESKEY_waitdown"
>
> # Directory where all the cgpro apps live
> APPLICATION="$OCF_RESKEY_application"
>
> # All my data and configuration directory
> BASEFOLDER="$OCF_RESKEY_basefolder"
>
> # Extra params
> SUPPLPARAMS="$OCF_RESKEY_supplyparams"
>
> # CGPRO lock file
> CGATE_LOCK_FILE="/var/lock/subsys/CommuniGate"
>
> #################################################################
> # Internal functions
>
> # Check if this use exists, if ok return 0
> check_user ()
> {
> # arg1 should be the username
> ID="$1"
>
> id "$ID" 2>/dev/null
> if [ "$?" = "0" ]; then
> return 0
> else
> return 1
> fi
> }
>
> # Check if CGatePro it's running
> check_cgpro_lock ()
> {
> # lets see if there is any lock file
> # we should return 1, if there is no lock file
> if [ -f "/var/lock/subsys/CommuniGate" ]; then
> return 0;
> else
> return 1;
> fi
> }
>
> # Check if the is any cgpro running
> check_cgpro_running ()
> {
>
> if [ -f "/var/CommuniGate/ProcessID" ]; then
> PID=`cat /var/CommuniGate/ProcessID`
>
> kill -0 $PID 1> /dev/null 2> /dev/null
>
> if [ "$?" = "0" ]; then
> return 0
> else
> ocf_log info "CGatePro not running, removing old PID file"
> rm -f "/var/CommuniGate/ProcessID"
> return 1
> fi
> else
> return 1
> fi
>
> }
>
> #################################################################
> # Main functions
>
> # show how to use this script
> _usage ()
> {
> cat <<END
> usage: $0 {start|stop|status|monitor|meta-data|validate-all}
>
> Expects to have a fully populated OCF RA-compliant environment set.
> END
> }
>
> # All the verifications we need to do
> _validate()
> {
>
> # verify if exists the binary of cgpro
> if [ ! -f ${APPLICATION}/CommuniGate/CGServer ]; then
> ocf_log err "CommuniGate bin file, was not found in:
> ${APPLICATION}/CommuniGate/CGServer"
> exit $OCF_ERR_GENERIC
> fi
>
> # verify if exists base folder, if not create
> if [ ! -d ${BASEFOLDER} ] ; then
> ocf_log info "We will try to create CGatePRO base folder: ${BASEFOLDER}"
>
> mkdir ${BASEFOLDER} 2> /dev/null
> if [ "$?" = "0" ]; then
> ocf_log info "Base folder created: ${BASEFOLDER}"
>
> if check_user "mail"; then
> chgrp mail ${BASEFOLDER}
> chmod 2770 ${BASEFOLDER}
> else
> ocf_log err "Could not find user <mail>, this use should exist
> to get CGatePro running."
> exit $OCF_ERR_GENERIC
> fi
> else
> ocf_log err "Could not create CGatePro base folder, check your
> configurations or data store location."
> exit $OCF_ERR_GENERIC
> fi
> fi
>
> # verify if there is a lock file
> if check_cgpro_lock; then
> ocf_log warn "We found one old lock file, we will remove it:
> /var/lock/subsys/CommuniGate"
> rm -f "$CGATE_LOCK_FILE"
> fi
>
> # if it gets here, everything its ok
> return $OCF_SUCCESS
> }
>
> ###### start ######
> _start()
> {
>
> # we will now check if there is any cgpro running
> if check_cgpro_running; then
> ocf_log warn "There is already one cgpro running, we will leave it."
> else
> # start the daemon
> ${APPLICATION}/CommuniGate/CGServer --Base ${BASEFOLDER} --Daemon
> ${SUPPLPARAMS}
> fi
>
> # lets give some time to cgpro to get up
> sleep "$CGPRO_WAIT_UP"
>
> # check if CGatePro its already running, if not, we will wait until it goes up
> # we dont need timeout stuff, crm will care of that
> if ! check_cgpro_running; then
> RUNNING=0
> while [ $RUNNING = 0 ]; do
> ocf_log info "CGatePro not running yet, we will wait a litle bit
> more"
> sleep 5
> if check_cgpro_running; then
> RUNNING=1
> fi
> done
> fi
>
> # create the lock file for application
> touch $CGATE_LOCK_FILE
>
> # everything went fine
> return $OCF_SUCCESS
>
> }
>
> ###### stop ######
> _stop()
> {
>
> # check if CGatePro its already running
> if check_cgpro_running; then
> # its running, lets find PID
> CGPRO_PID=""
> if [ -f ${BASEFOLDER}/ProcessID ]; then
> CGPRO_PID=`cat ${BASEFOLDER}/ProcessID`
> else
> CGPRO_PID=`/sbin/pidof CGServer`
> fi
>
> # we have PID, not lets kill it normally
> kill $CGPRO_PID
>
> # lets wait a couple of time, until its down
> sleep $CGPRO_WAIT_DOWN
>
> # now lets check if its really down, if not we will wait a couple
> # we dont need timeout stuff, crm will care of that
> RUNNING=0
> while [ $RUNNING = 0 ]; do
> ocf_log info "CGatePro still running, we will wait a litle bit more"
> sleep 5
> if ! check_cgpro_running; then
> RUNNING=1
> fi
> done
> else
> ocf_log info "CGatePro not running, nothing to stop"
> fi
>
> rm -f $CGATE_LOCK_FILE
>
> return $OCF_SUCCESS
>
> }
>
> # Monitor if CGatePro it's running
> _monitor()
> {
>
> # we will check if CGatePro it's running
> if check_cgpro_running; then
> ocf_log info "CGatePro runnning."
> return $OCF_SUCCESS
> else
> ocf_log warn "CGatePro not runnning."
> return $OCF_NOT_RUNNING
> fi
>
> }
>
> # Print metadata informations
> _meta_data()
> {
> cat <<END
> <?xml version="1.0"?>
> <!DOCTYPE resource-agent SYSTEM "ra-api-1.dtd">
> <resource-agent name="cgatepro">
> <version>0.1</version>
> <longdesc lang="en">
> OCF script that control cgatepro server, in failover scenario
> </longdesc>
> <shortdesc lang="en">CGatePro server resource script</shortdesc>
>
> <parameters>
>
> <parameter name="basefolder" unique="0" required="1">
> <longdesc lang="en">
> CGatePro BaseFolder, where all your data and configurations will live
> </longdesc>
> <shortdesc lang="en">CGatePro BaseFolder</shortdesc>
> <content type="string" default="/var/CommuniGate"/>
> </parameter>
>
> <parameter name="supplyparams" unique="0" required="1">
> <longdesc lang="en">
> CGatePro Supply Params argument
> </longdesc>
> <shortdesc lang="en">cgatepro supplyparams</shortdesc>
> <content type="string" default=""/>
> </parameter>
>
> <parameter name="application" unique="0" required="1">
> <longdesc lang="en">
> CGatePro Application Path
> </longdesc>
> <shortdesc lang="en">cgatepro app path</shortdesc>
> <content type="string" default="/opt"/>
> </parameter>
>
> <parameter name="waitup" unique="0" required="1">
> <longdesc lang="en">
> How much time will this script wait to check if CGatePro its UP
> </longdesc>
> <shortdesc lang="en">Time UP</shortdesc>
> <content type="integer" default="10"/>
> </parameter>
>
> <parameter name="waitdown" unique="0" required="1">
> <longdesc lang="en">
> How much time will this script wait to check if CGatePro its DOWN
> </longdesc>
> <shortdesc lang="en">Time DOWN</shortdesc>
> <content type="integer" default="10"/>
> </parameter>
>
> </parameters>
>
> <actions>
> <action name="start" timeout="60" />
> <action name="stop" timeout="60" />
> <action name="monitor" timeout="15" interval="300" depth="0"
> start-delay="30"/>
> <action name="meta-data" timeout="5" />
> </actions>
> </resource-agent>
> END
> }
>
> # See how we were called
> #################################################################
>
> case $1 in
>
> meta-data)
> _meta_data
> exit $OCF_SUCCESS
> ;;
> start)
> _validate
> _start
> ;;
> stop)
> _stop
> ;;
> status|monitor)
> _monitor
> ;;
> usage|help)
> _usage
> exit $OCF_SUCCESS
> ;;
> validate-all)
> _validate
> ;;
> *)
> _usage
> exit $OCF_ERR_UNIMPLEMENTED
> ;;
> esac
> exit $?
> #!/bin/sh
> #
> # Description: Manages a ejabberd High-Availability Resource
> #
> # Author: Igor Neves <igor AT 3gnt DOT net>
> # <neves DOT igor AT gmail DOT com>
> # License: GNU General Public License (GPL)
> #
> # Copyright: (C) 2008 3GNTW - Tecnologias de Informacao, Lda
> # All Rights Reserved.
> #
> # OCF parameters:
> # * OCF_RESKEY_ejabberdctl
> # * OCF_RESKEY_waitup
> # * OCF_RESKEY_waitdown
> # * OCF_RESKEY_msntransportenable
> # * OCF_RESKEY_msntransportpath
> #
> # IMPORTANT:
> # - To make msn transport agent working, I changed the first like
> # of 'PyMSNt.py' to: '#!/usr/bin/env /usr/bin/python'
> #
> #################################################################
> # Source ocf shell functions
> . ${OCF_ROOT}/resource.d/heartbeat/.ocf-shellfuncs
>
> # Variable configuration
> #################################################################
> # Path to ejabberdctl file
> EJABBERDCTL="$OCF_RESKEY_ejabberdctl"
>
> # How much time (in sec) we will wait until check if ejabberd its UP
> # (default: 15sec)
> EJABBERD_WAIT_UP="$OCF_RESKEY_waitup"
>
> # How much time (in sec) we will wait until check if ejabberd its DOWN
> # (default: 15sec)
> EJABBERD_WAIT_DOWN="$OCF_RESKEY_waitdown"
>
> # Boolen to enable or disable starting the msn transport
> EJABBERD_MSN_TRANS_ENABLE="$OCF_RESKEY_msntransportenable"
>
> # Path to msn transport agent
> EJABBERD_MSN_TRANS_PATH="$OCF_RESKEY_msntransportpath"
> #################################################################
> # Internal functions
>
> # Check if there is any ejabberd running
> check_ejabberd_running ()
> {
>
> if [ -f "$EJABBERDCTL" ]; then
>
> $EJABBERDCTL status 1>/dev/null 2>/dev/null
>
> if [ "$?" = "0" ]; then
> return 0
> else
> ocf_log info "Ejabberd not running"
> return 1
> fi
> else
> ocf_log err "EjabberdCtl binary not found"
> return 1
> fi
>
> }
>
> # Check if there is any msn transport running
> check_msn_tranport_running ()
> {
> FILE="`/bin/basename $EJABBERD_MSN_TRANS_PATH .py`.pid"
> PATH="`/usr/bin/dirname $EJABBERD_MSN_TRANS_PATH`"
> PID="`/bin/cat $PATH/$FILE`"
>
> kill -0 $PID
>
> if [ "$?" = "0" ]; then
> return 0
> else
> return 1
> fi
>
> }
> #################################################################
> # Main functions
>
> # show how to use this script
> _usage ()
> {
> cat <<END
> usage: $0 {start|stop|status|monitor|meta-data|validate-all}
>
> Expects to have a fully populated OCF RA-compliant environment set.
> END
> }
>
> # All the verifications we need to do
> _validate()
> {
>
> # verify if exists the binary of ejabberd
> if [ ! -f "$EJABBERDCTL" ]; then
> ocf_log err "EjabberdCtl, was not found in: $EJABBERDCTL"
> exit $OCF_ERR_GENERIC
> fi
>
> # verify msn transport agent exists if it is enable
> if [ "$EJABBERD_MSN_TRANS_ENABLE" = "1" ]; then
> if [ ! -f "$EJABBERD_MSN_TRANS_PATH" ]; then
> ocf_log err "Ejabberd msn transport agent enable, but transport
> agent binary not found: $EJABBERD_MSN_TRANS_PATH"
> exit $OCF_ERR_GENERIC
> fi
> else
> ocf_log info "Ejabberd msn transport agent disable."
> fi
>
> # if it gets here, everything its ok
> return $OCF_SUCCESS
> }
>
> ###### start ######
> _start()
> {
>
> # we will now check if there is any ejabberd running
> if check_ejabberd_running; then
> ocf_log warn "There is already one ejabberd running, we will leave it."
> else
> # start the daemon
> ${EJABBERDCTL} start
> fi
>
> # lets give some time to ejabberd to get up
> sleep "$EJABBERD_WAIT_UP"
>
> # check if ejabberd its already running, if not, we will wait until it goes up
> # we dont need timeout stuff, crm will care of that
> if ! check_ejabberd_running; then
> RUNNING=0
> while [ $RUNNING = 0 ]; do
> ocf_log info "Ejabberd not running yet, we will wait a litle bit
> more"
> sleep 5
> if check_ejabberd_running; then
> RUNNING=1
> fi
> done
> fi
>
> # Now that ejabberd its running, lets start the transports if enable
> if [ "$EJABBERD_MSN_TRANS_ENABLE" = "1" ]; then
> if check_msn_tranport_running; then
> ocf_log warn "There is already a transport agent running, we will
> not touch it."
> else
> $EJABBERD_MSN_TRANS_PATH
> fi
> fi
>
> # Everything went fine
> return $OCF_SUCCESS
>
> }
>
> ###### stop ######
> _stop()
> {
>
> # check if Ejabberd its already running
> if check_ejabberd_running; then
>
> $EJABBERDCTL stop 1>/dev/null 2>/dev/null
>
> # lets wait a couple of time, until its down
> sleep $EJABBERD_WAIT_DOWN
>
> if check_ejabberd_running; then
> # its still running, lets find PID and kill the m'fucker
> EJ_PID=`/sbin/pidof beam.smp`
>
> # lets se if we have found any PID
> if [ -n "$EJ_PID" ]; then
> kill -9 "$EJ_PID"
> fi
>
> # now lets check if its really down, if not we will wait a couple
> # we dont need timeout stuff, crm will care of that
> RUNNING=0
> while [ $RUNNING = 0 ]; do
> ocf_log info "Ejabberd still running, we will wait a litle bit
> more"
> sleep 5
> if ! check_ejabberd_running; then
> RUNNING=1
> fi
> done
> fi
> else
> ocf_log info "Ejabberd not running, nothing to stop"
> fi
>
> # ejabberd its not running anymore, lets stop all the transports if enable
> if [ "$EJABBERD_MSN_TRANS_ENABLE" = "1" ]; then
> FILE="`/bin/basename $EJABBERD_MSN_TRANS_PATH .py`.pid"
> PATH="`/usr/bin/dirname $EJABBERD_MSN_TRANS_PATH`"
> PID="`/bin/cat $PATH/$FILE`"
>
> if check_msn_tranport_running; then
> kill -9 $PID
> else
> ocf_log info "No msn transport agent running"
> fi
>
> if [ "$PATH" -ne "/" ]; then
> rm $PATH/$LOGFILE
> fi
> fi
>
> return $OCF_SUCCESS
> }
>
> # Monitor if Ejabberd it's running
> _monitor()
> {
>
> # we will check if Ejabberd it's running
> if check_ejabberd_running; then
> ocf_log info "Ejabberd runnning."
> return $OCF_SUCCESS
> else
> ocf_log warn "Ejabberd not runnning."
> return $OCF_NOT_RUNNING
> fi
>
> if check_msn_tranport_running; then
> ocf_log info "Ejabberd msn transport agent runnning."
> return $OCF_SUCCESS
> else
> ocf_log warn "Ejabberd msn transport agent not runnning."
> return $OCF_NOT_RUNNING
> fi
> }
>
> # Print metadata informations
> _meta_data()
> {
> cat <<END
> <?xml version="1.0"?>
> <!DOCTYPE resource-agent SYSTEM "ra-api-1.dtd">
> <resource-agent name="ejabberd">
> <version>0.1</version>
> <longdesc lang="en">
> OCF script that control ejabberd server, in failover scenario
> </longdesc>
> <shortdesc lang="en">Ejabberd server resource script</shortdesc>
>
> <parameters>
>
> <parameter name="ejabberdctl" unique="0" required="1">
> <longdesc lang="en">
> Ejabberd ctl binary path
> </longdesc>
> <shortdesc lang="en">EjabberdCtl binary path</shortdesc>
> <content type="string" default="/opt/ejabberd/bin/ejabberdctl"/>
> </parameter>
>
> <parameter name="waitup" unique="0" required="1">
> <longdesc lang="en">
> How much time will this script wait to check if CGatePro its UP
> </longdesc>
> <shortdesc lang="en">Time UP</shortdesc>
> <content type="integer" default="15"/>
> </parameter>
>
> <parameter name="waitdown" unique="0" required="1">
> <longdesc lang="en">
> How much time will this script wait to check if CGatePro its DOWN
> </longdesc>
> <shortdesc lang="en">Time DOWN</shortdesc>
> <content type="integer" default="15"/>
> </parameter>
>
> <parameter name="msntransportenable" unique="0" required="1">
> <longdesc lang="en">
> This is a simple boolean value if enable or not the transport agent
> </longdesc>
> <shortdesc lang="en">Enable or Disable MSN transport agent</shortdesc>
> <content type="boolean" default="0"/>
> </parameter>
>
> <parameter name="msntransportpath" unique="0" required="1">
> <longdesc lang="en">
> Path to PyMSNt.py
> </longdesc>
> <shortdesc lang="en">Path to PyMSNt.py</shortdesc>
> <content type="string" default="/opt/pymsnt/PyMSNt.py"/>
> </parameter>
>
> </parameters>
>
> <actions>
> <action name="start" timeout="30" />
> <action name="stop" timeout="30" />
> <action name="monitor" timeout="15" interval="300" depth="0"
> start-delay="30"/>
> <action name="meta-data" timeout="5" />
> </actions>
> </resource-agent>
> END
> }
>
> # See how we were called
> #################################################################
>
> case $1 in
>
> meta-data)
> _meta_data
> exit $OCF_SUCCESS
> ;;
> start)
> _validate
> _start
> ;;
> stop)
> _stop
> ;;
> status|monitor)
> _monitor
> ;;
> usage|help)
> _usage
> exit $OCF_SUCCESS
> ;;
> validate-all)
> _validate
> ;;
> *)
> _usage
> exit $OCF_ERR_UNIMPLEMENTED
> ;;
> esac
> exit $?
> _______________________________________________
> Linux-HA mailing list
> [email protected]
> http://lists.linux-ha.org/mailman/listinfo/linux-ha
> See also: http://linux-ha.org/ReportingProblems
_______________________________________________
Linux-HA mailing list
[email protected]
http://lists.linux-ha.org/mailman/listinfo/linux-ha
See also: http://linux-ha.org/ReportingProblems
