#!/bin/sh
#
#
#	HealthLUSTRE OCF RA that utilizes the lustre /proc/fs/lustre/health_check 
#

# License:      GNU General Public License (GPL)v2
# Description:  Manages ZFS and Lustre on a shared storage
# Written by:   Gabriele Paciucci
# Release Date: 01 June 2016
# Release Version: 0.97

# Copyright (c) 2009 Andrew Beekhof

# Copyright © 2016, Intel Corporation


#
# This program is free software; you can redistribute it and/or modify
# it under the terms of version 2 of the GNU General Public License as
# published by the Free Software Foundation.
#
# This program is distributed in the hope that it would be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
#
# Further, this software is distributed without any warranty that it is
# free of the rightful claim of any third person regarding infringement
# or the like.  Any license provided herein, whether implied or
# otherwise, applies only to this software file.  Patent licenses, if
# any, provided herein do not apply to combinations of this program with
# other software, or any other product whatsoever.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write the Free Software Foundation,
# Inc., 59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
#

#######################################################################
# Initialization:

: ${OCF_FUNCTIONS=${OCF_ROOT}/resource.d/heartbeat/.ocf-shellfuncs}
. ${OCF_FUNCTIONS}
: ${__OCF_ACTION=$1}

#######################################################################

meta_data() {
	cat <<END
<?xml version="1.0"?>
<!DOCTYPE resource-agent SYSTEM "ra-api-1.dtd">
<resource-agent name="healthLUSTRE">
<version>1.0</version>

<longdesc lang="en">
Every time the monitor action is run, this resource agent records (in the CIB) the current number of healthy lustre server
</longdesc>
<shortdesc lang="en">lustre servers healthy</shortdesc>

<parameters>

<parameter name="pidfile" unique="0">
<longdesc lang="en">PID file</longdesc>
<shortdesc lang="en">PID file</shortdesc>
<content type="string" default="$HA_VARRUN/healthLUSTRE-${OCF_RESOURCE_INSTANCE}" />
</parameter>

<parameter name="dampen" unique="0">
<longdesc lang="en">
The time to wait (dampening) further changes occur
</longdesc>
<shortdesc lang="en">Dampening interval</shortdesc>
<content type="integer" default="5s"/>
</parameter>


<parameter name="name" unique="0">
<longdesc lang="en">
The name of the attributes to set.  This is the name to be used in the constraints.
</longdesc>
<shortdesc lang="en">Attribute name</shortdesc>
<content type="string" default="lustred"/>
</parameter>



<parameter name="debug" unique="0">
<longdesc lang="en">
Enables to use default attrd_updater verbose logging on every call.
</longdesc>
<shortdesc lang="en">Verbose logging</shortdesc>
<content type="string" default="false"/>
</parameter>

</parameters>

<actions>
<action name="start"   timeout="60" />
<action name="stop"    timeout="20" />
<action name="reload"  timeout="100" />
<action name="monitor" depth="0"  timeout="60" interval="10"/>
<action name="meta-data"  timeout="5" />
<action name="validate-all"  timeout="30" />
</actions>
</resource-agent>
END
}

#######################################################################

lustre_conditional_log() {
    level=$1; shift 
    if [ ${OCF_RESKEY_debug} = "true" ]; then
	ocf_log $level "$*"
    fi
}

lustre_usage() {
	cat <<END
usage: $0 {start|stop|monitor|migrate_to|migrate_from|validate-all|meta-data}

Expects to have a fully populated OCF RA-compliant environment set.
END
}

lustre_start() {
    lustre_monitor
    if [ $? =  $OCF_SUCCESS ]; then
	return $OCF_SUCCESS
    fi
    touch ${OCF_RESKEY_pidfile}
    lustre_update
}

lustre_stop() {

	rm -f ${OCF_RESKEY_pidfile}
    
    attrd_updater -D -n $OCF_RESKEY_name -d $OCF_RESKEY_dampen $attrd_options
    
    return $OCF_SUCCESS
}

lustre_monitor() {
    if [ -f ${OCF_RESKEY_pidfile} ]; then
	lustre_update
        if [ $? -eq 0 ]; then
            return $OCF_SUCCESS
        fi
        return $OCF_ERR_GENERIC
    fi
    return $OCF_NOT_RUNNING
}

# we worked on this later
#ping_validate() {
    # Is the state directory writable? 
#    state_dir=`dirname "$OCF_RESKEY_pidfile"`
#    touch "$state_dir/$$"
#    if [ $? != 0 ]; then
#	ocf_log err "Invalid location for 'state': $state_dir is not writable"
#	return $OCF_ERR_ARGS
#    fi
#    rm "$state_dir/$$"

# Pidfile better be an absolute path
#    case $OCF_RESKEY_pidfile in
#	/*) ;;
#	*) ocf_log warn "You should use an absolute path for pidfile not: $OCF_RESKEY_pidfile" ;;
#    esac
    
# Check the host list
#    if [ "x" = "x$OCF_RESKEY_host_list" ]; then 
#
#	ocf_log err "Empty host_list.  Please specify some nodes to ping"
#	exit $OCF_ERR_CONFIGURED
#    fi

#    check_binary ping

#    return $OCF_SUCCESS
#}



lustre_check() {

	active=0

#	added head -1 due the LU-7486 
	l_out=`cat /proc/fs/lustre/health_check | head -1 |grep -w healthy 2>&1`; rc=$?

	case $rc in
	    0) active=`expr $active + 1`;;
	    1) lustre_conditional_log warn "Lustre is not healthy: $l_out";;
	    *) ocf_log err "Unexpected result for '/proc/fs/lustre/health_check' $rc: $l_out";;
	esac
    return $active
}

lustre_update() {
    
	lustre_check
	active=$?

    attrd_updater -n $OCF_RESKEY_name -v $active -d $OCF_RESKEY_dampen $attrd_options
    rc=$?
    case $rc in 
	0) lustre_conditional_log debug "Updated $OCF_RESKEY_name = $active" ;;
	*) ocf_log warn "Could not update $OCF_RESKEY_name = $active: rc=$rc";;
    esac
    if [ $rc -ne 0 ]; then
        return $rc
    fi
    return 0
}

: ${OCF_RESKEY_name:="lustred"}
: ${OCF_RESKEY_dampen:="5s"}
: ${OCF_RESKEY_attempts:="3"}
: ${OCF_RESKEY_debug:="false"}

: ${OCF_RESKEY_CRM_meta_timeout:="20000"}
: ${OCF_RESKEY_CRM_meta_globally_unique:="true"}


# I don't think we need to care about timeout

#integer=`echo ${OCF_RESKEY_timeout} | egrep -o '[0-9]*'`
#case ${OCF_RESKEY_timeout} in
#    *[0-9]ms|*[0-9]msec) OCF_RESKEY_timeout=`expr $integer / 1000`;;
#    *[0-9]m|*[0-9]min) OCF_RESKEY_timeout=`expr $integer \* 60`;;
#    *[0-9]h|*[0-9]hr)  OCF_RESKEY_timeout=`expr $integer \* 60 \* 60`;;
#    *) OCF_RESKEY_timeout=$integer;;
#esac

#if [ -z ${OCF_RESKEY_timeout} ]; then
#    if [ x"$OCF_RESKEY_host_list" != x ]; then
#	host_count=`echo $OCF_RESKEY_host_list | awk '{print NF}'`
#	OCF_RESKEY_timeout=`expr $OCF_RESKEY_CRM_meta_timeout / $host_count / $OCF_RESKEY_attempts`
#	OCF_RESKEY_timeout=`expr $OCF_RESKEY_timeout / 1100` # Convert to seconds and finish 10% early
#    else
#	OCF_RESKEY_timeout=5
#    fi
#fi

#if [ ${OCF_RESKEY_timeout} -lt 1 ]; then
#    OCF_RESKEY_timeout=5
#elif [ ${OCF_RESKEY_timeout} -gt 1000 ]; then
#    # ping actually complains if this value is too high, 5 minutes is plenty
#    OCF_RESKEY_timeout=300
#fi

if [ ${OCF_RESKEY_CRM_meta_globally_unique} = "false" ]; then
    : ${OCF_RESKEY_pidfile:="$HA_VARRUN/healthLUSTRE-${OCF_RESKEY_name}"}
else 
    : ${OCF_RESKEY_pidfile:="$HA_VARRUN/healthLUSTRE-${OCF_RESOURCE_INSTANCE}"}
fi

attrd_options='-q'
if ocf_is_true ${OCF_RESKEY_debug} ; then
    attrd_options=''
fi

# Check the debug option    
    case "${OCF_RESKEY_debug}" in
	true|True|TRUE|1)    OCF_RESKEY_debug=true;;
	false|False|FALSE|0) OCF_RESKEY_debug=false;;
	*)
            ocf_log warn "Value for 'debug' is incorrect. Please specify 'true' or 'false' not: ${OCF_RESKEY_debug}"
	    OCF_RESKEY_debug=false
	    ;;
    esac

case $__OCF_ACTION in
meta-data)	meta_data
		exit $OCF_SUCCESS
		;;
start)		lustre_start;;
stop)		lustre_stop;;
monitor)	lustre_monitor;;
reload)		lustre_start;;
validate-all)	lustre_usage
		exit $OCF_SUCCESS
		;;
usage|help)	lustre_usage
		exit $OCF_SUCCESS
		;;
*)		lustre_usage
		exit $OCF_ERR_UNIMPLEMENTED
		;;
esac
exit $?