#! /bin/sh # # Resource Agent for managing the Generic SCSI Target Subsystem # for Linux (SCST) and related daemons. # # License: GNU General Public License (GPL) # (c) 2012-2014 Marc A. Smith # PATH=$PATH:/usr/local/sbin # Initialization : ${OCF_FUNCTIONS_DIR=${OCF_ROOT}/lib/heartbeat} . ${OCF_FUNCTIONS_DIR}/ocf-shellfuncs #MODULES="scst qla2x00tgt iscsi_scst ib_srpt \ #scst_disk scst_vdisk scst_tape scst_changer fcst" MODULES="scst iscsi_scst scst_disk scst_vdisk" SCST_CFG="/etc/scst.conf" PRE_SCST_CONF="/etc/pre-scst_xtra_conf" POST_SCST_CONF="/etc/post-scst_xtra_conf" SCST_SYSFS="/sys/kernel/scst_tgt" ALUA_STATES="active nonoptimized standby unavailable offline transitioning" NO_CLOBBER="/tmp/scst_ra-no_clobber" # For optional SCST modules if [ -f "/lib/modules/$(uname -r)/extra/ocs_fc_scst.ko" ]; then MODULES="${MODULES} ocs_fc_scst" fi if [ -f "/lib/modules/$(uname -r)/extra/chfcoe.ko" ]; then MODULES="${MODULES} chfcoe" fi scst_start() { # Exit immediately if configuration is not valid scst_validate_all || exit ${?} # If resource is already running, bail out early if scst_monitor; then ocf_log info "Resource is already running." return ${OCF_SUCCESS} fi # If our pre-SCST file exists, run it if [ -f "${PRE_SCST_CONF}" ]; then ocf_log info "Pre-SCST user config. file found; running..." ocf_run -warn sh "${PRE_SCST_CONF}" fi # Load all modules ocf_log info "Loading kernel modules..." for i in ${MODULES}; do ocf_log debug "scst_start() -> Module: ${i}" if [ -d /sys/module/${i} ]; then ocf_log warn "The ${i} module is already loaded!" else ocf_run modprobe ${i} || exit ${OCF_ERR_GENERIC} fi done # Start the daemons ocf_log info "Starting daemons..." if pidof iscsi-scstd > /dev/null 2>&1; then ocf_log warn "The iscsi-scstd daemon is already running!" else ocf_run iscsi-scstd || exit ${OCF_ERR_GENERIC} fi if pidof lldpad > /dev/null 2>&1; then ocf_log warn "The lldpad daemon is already running!" else ocf_run lldpad -d || exit ${OCF_ERR_GENERIC} fi #if pidof fcoemon > /dev/null 2>&1; then # ocf_log warn "The fcoemon daemon is already running!" #else # ocf_run fcoemon -s || exit ${OCF_ERR_GENERIC} #fi # Configure SCST if [ -f "${SCST_CFG}" ]; then ocf_log info "Applying SCST configuration..." ocf_run scstadmin -config "${SCST_CFG}" # Prevent scst_stop() from clobbering the configuration file if [ ${?} -ne 0 ]; then ocf_log err "Something is wrong with the SCST configuration!" ocf_run touch "${NO_CLOBBER}" exit ${OCF_ERR_GENERIC} else if [ -f "${NO_CLOBBER}" ]; then ocf_run rm -f "${NO_CLOBBER}" fi fi fi # If our post-SCST file exists, run it if [ -f "${POST_SCST_CONF}" ]; then ocf_log info "Post-SCST user config. file found; running..." ocf_run -warn sh "${POST_SCST_CONF}" fi # If we are using ALUA, be sure we are using the "Slave" state initially if ocf_is_true ${OCF_RESKEY_alua}; then check_alua # Set the local target group ALUA state ocf_log debug "scst_start() -> Setting target group" \ "'${OCF_RESKEY_local_tgt_grp}' ALUA state to" \ "'${OCF_RESKEY_s_alua_state}'..." ocf_run scstadmin -noprompt -set_tgrp_attr \ ${OCF_RESKEY_local_tgt_grp} -dev_group \ ${OCF_RESKEY_device_group} -attributes \ state\=${OCF_RESKEY_s_alua_state} || exit ${OCF_ERR_GENERIC} # For now, we simply assume the other node is the Master ocf_log debug "scst_start() -> Setting target group" \ "'${OCF_RESKEY_remote_tgt_grp}' ALUA state to" \ "'${OCF_RESKEY_m_alua_state}'..." ocf_run scstadmin -noprompt -set_tgrp_attr \ ${OCF_RESKEY_remote_tgt_grp} -dev_group \ ${OCF_RESKEY_device_group} -attributes \ state\=${OCF_RESKEY_m_alua_state} || exit ${OCF_ERR_GENERIC} fi # Make sure the resource started correctly while ! scst_monitor; do ocf_log debug "scst_start() -> Resource has not started yet, waiting..." sleep 1 done # Only return $OCF_SUCCESS if _everything_ succeeded as expected return ${OCF_SUCCESS} } scst_stop() { # Exit immediately if configuration is not valid scst_validate_all || exit ${?} # Check the current resource state scst_monitor local rc=${?} case "${rc}" in "${OCF_SUCCESS}") # Currently running; normal, expected behavior ocf_log info "Resource is currently running." ;; "${OCF_RUNNING_MASTER}") # Running as a Master; need to demote before stopping ocf_log info "Resource is currently running as Master." scst_demote || ocf_log warn "Demote failed, trying to stop anyway..." ;; "${OCF_NOT_RUNNING}") # Currently not running; nothing to do ocf_log info "Resource is already stopped." return ${OCF_SUCCESS} ;; esac # Save the SCST configuration, just in case ocf_log info "Saving SCST configuration..." if [ -f "${NO_CLOBBER}" ]; then ocf_log warn "The '${NO_CLOBBER}' file exists," \ "not writing configuration!" else ocf_run scstadmin -force -nonkey -write_config \ ${SCST_CFG} || exit ${OCF_ERR_GENERIC} fi # Stop all of the daemons and wait for each ocf_log info "Stopping daemons..." #for i in "fcoemon lldpad iscsi-scstd"; do for i in "lldpad iscsi-scstd"; do pidof ${i} > /dev/null 2>&1 if [ ${?} -ne 0 ]; then ocf_log warn "The ${i} daemon is not running!" continue fi ocf_log debug "scst_stop() -> Sending the TERM signal to ${i}..." ocf_run killall -TERM ${i} || exit ${OCF_ERR_GENERIC} while pidof ${i} > /dev/null 2>&1; do ocf_log debug "scst_stop() -> The ${i} daemon is" \ "still running, waiting..." sleep 1 done done # Unload the modules (in reverse) ocf_log info "Unloading kernel modules..." for i in $(echo ${MODULES} | tr ' ' '\n' | tac | tr '\n' ' '); do ocf_log debug "scst_stop() -> Module: ${i}" if [ -d /sys/module/${i} ]; then ocf_run rmmod -w ${i} || exit ${OCF_ERR_GENERIC} else ocf_log warn "The ${i} module is not loaded!" fi done # Make sure the resource stopped correctly while scst_monitor; do ocf_log debug "scst_stop() -> Resource has not stopped yet, waiting..." sleep 1 done # Only return $OCF_SUCCESS if _everything_ succeeded as expected return ${OCF_SUCCESS} } scst_monitor() { # Exit immediately if configuration is not valid scst_validate_all || exit ${?} # Check if SCST is loaded local rc if [ -e "${SCST_SYSFS}/version" ]; then ocf_log debug "scst_monitor() -> SCST version:" \ "$(cat ${SCST_SYSFS}/version)" ocf_log debug "scst_monitor() -> Resource is running." crm_master -l reboot -v 100 rc=${OCF_SUCCESS} else ocf_log debug "scst_monitor() -> Resource is not running." crm_master -l reboot -D rc=${OCF_NOT_RUNNING} return ${rc} fi # If we are using ALUA, then we can test if we are Master or not if ocf_is_true ${OCF_RESKEY_alua}; then dev_grp_path="${SCST_SYSFS}/device_groups/${OCF_RESKEY_device_group}" tgt_grp_path="${dev_grp_path}/target_groups/${OCF_RESKEY_local_tgt_grp}" tgt_grp_state="$(head -1 ${tgt_grp_path}/state)" ocf_log debug "scst_monitor() -> SCST local target" \ "group state: ${tgt_grp_state}" if [ "x${tgt_grp_state}" = "x${OCF_RESKEY_m_alua_state}" ]; then rc=${OCF_RUNNING_MASTER} fi fi return ${rc} } scst_validate_all() { # Test for required binaries check_binary scstadmin # There can only be one instance of SCST running per node if [ ! -z "${OCF_RESKEY_CRM_meta_clone_node_max}" ] && [ "${OCF_RESKEY_CRM_meta_clone_node_max}" -ne 1 ]; then ocf_log err "The 'clone-node-max' parameter must equal '1'." exit ${OCF_ERR_CONFIGURED} fi # If ALUA support is enabled, we need to check the parameters if ocf_is_true ${OCF_RESKEY_alua}; then # Make sure they are set to something if [ -z "${OCF_RESKEY_device_group}" ]; then ocf_log err "The 'device_group' parameter is not set!" exit ${OCF_ERR_CONFIGURED} fi if [ -z "${OCF_RESKEY_local_tgt_grp}" ]; then ocf_log err "The 'local_tgt_grp' parameter is not set!" exit ${OCF_ERR_CONFIGURED} fi if [ -z "${OCF_RESKEY_remote_tgt_grp}" ]; then ocf_log err "The 'remote_tgt_grp' parameter is not set!" exit ${OCF_ERR_CONFIGURED} fi if [ -z "${OCF_RESKEY_m_alua_state}" ]; then ocf_log err "The 'm_alua_state' parameter is not set!" exit ${OCF_ERR_CONFIGURED} fi if [ -z "${OCF_RESKEY_s_alua_state}" ]; then ocf_log err "The 's_alua_state' parameter is not set!" exit ${OCF_ERR_CONFIGURED} fi # Currently, we only support using one Master with this RA if [ ! -z "${OCF_RESKEY_CRM_meta_master_max}" ] && [ "${OCF_RESKEY_CRM_meta_master_max}" -ne 1 ]; then ocf_log err "The 'master-max' parameter must equal '1'." exit ${OCF_ERR_CONFIGURED} fi if [ ! -z "${OCF_RESKEY_CRM_meta_master_node_max}" ] && [ "${OCF_RESKEY_CRM_meta_master_node_max}" -ne 1 ]; then ocf_log err "The 'master-node-max' parameter must equal '1'." exit ${OCF_ERR_CONFIGURED} fi fi return ${OCF_SUCCESS} } scst_meta_data() { cat <<-EOF 0.1 The SCST OCF resource agent for ESOS; includes SCST ALUA support. SCST OCF RA script for ESOS. Use to enable/disable updating ALUA status in SCST. The 'alua' parameter. The name of the SCST device group (used with ALUA support). The 'device_group' parameter. The name of the SCST local target group (used with ALUA support). The 'local_tgt_grp' parameter. The name of the SCST remote target group (used with ALUA support). The 'remote_tgt_grp' parameter. The ALUA state (eg, active) for a Master node (used with ALUA support). The 'm_alua_state' parameter. The ALUA state (eg, nonoptimized) for a Slave node (used with ALUA support). The 's_alua_state' parameter. EOF } scst_usage() { echo "usage: ${0} {start|stop|monitor|validate-all|promote|demote|reload|notify|meta-data}" echo "" echo "Expects to have a fully populated OCF RA-compliant environment set." } scst_promote() { # Exit immediately if configuration is not valid scst_validate_all || exit ${?} # Test the resource's current state scst_monitor local rc=${?} case "${rc}" in "${OCF_SUCCESS}") # Running as Slave; normal, expected behavior ocf_log debug "scst_promote() -> Resource is" \ "currently running as Slave." ;; "${OCF_RUNNING_MASTER}") # Already a Master; unexpected, but not a problem ocf_log info "Resource is already running as Master." return ${OCF_SUCCESS} ;; "${OCF_NOT_RUNNING}") # Currently not running; need to start before promoting ocf_log info "Resource is currently not running." scst_start ;; *) # Failed resource; let the cluster manager recover ocf_log err "Unexpected error, cannot promote." exit ${rc} ;; esac # Promote only makes sense if we are using ALUA if ocf_is_true ${OCF_RESKEY_alua}; then check_alua # Set the local target group to the "Master" ALUA state ocf_log debug "scst_promote() -> Setting target group" \ "'${OCF_RESKEY_local_tgt_grp}' ALUA state to" \ "'${OCF_RESKEY_m_alua_state}'..." ocf_run scstadmin -noprompt -set_tgrp_attr \ ${OCF_RESKEY_local_tgt_grp} -dev_group \ ${OCF_RESKEY_device_group} -attributes \ state\=${OCF_RESKEY_m_alua_state} || exit ${OCF_ERR_GENERIC} # Since there can only be one Master, set the remote target group ocf_log debug "scst_promote() -> Setting target group" \ "'${OCF_RESKEY_remote_tgt_grp}' ALUA state to" \ "'${OCF_RESKEY_s_alua_state}'..." ocf_run scstadmin -noprompt -set_tgrp_attr \ ${OCF_RESKEY_remote_tgt_grp} -dev_group \ ${OCF_RESKEY_device_group} -attributes \ state\=${OCF_RESKEY_s_alua_state} || exit ${OCF_ERR_GENERIC} else ocf_log err "The ALUA parameters need to be configured before using MS." exit ${OCF_ERR_CONFIGURED} fi # After the resource has been promoted, check whether the promotion worked while true; do scst_monitor if [ ${?} -eq ${OCF_RUNNING_MASTER} ]; then ocf_log info "Resource was promoted successfully." break else ocf_log debug "scst_promote() -> Resource still" \ "awaiting promotion." sleep 1 fi done # Only return $OCF_SUCCESS if _everything_ succeeded as expected return ${OCF_SUCCESS} } scst_demote() { # Exit immediately if configuration is not valid scst_validate_all || exit ${?} # Test the resource's current state scst_monitor local rc=${?} case "${rc}" in "${OCF_RUNNING_MASTER}") # Running as Master; normal, expected behavior ocf_log debug "scst_demote() -> Resource is" \ "currently running as Master." ;; "${OCF_SUCCESS}") # Already running as Slave; nothing to do ocf_log debug "scst_demote() -> Resource is" \ "currently running as Slave." return ${OCF_SUCCESS} ;; "${OCF_NOT_RUNNING}") # Not running; getting a demote action in this state is unexpected ocf_log err "Resource is currently not running." exit ${OCF_ERR_GENERIC} ;; *) # Failed resource; let the cluster manager recover ocf_log err "Unexpected error, cannot demote." exit ${rc} ;; esac # Demote only makes sense if we are using ALUA if ocf_is_true ${OCF_RESKEY_alua}; then check_alua # Set the local target group to the "Slave" ALUA state ocf_log debug "scst_demote() -> Setting target group" \ "'${OCF_RESKEY_local_tgt_grp}' ALUA state to" \ "'${OCF_RESKEY_s_alua_state}'..." ocf_run scstadmin -noprompt -set_tgrp_attr \ ${OCF_RESKEY_local_tgt_grp} -dev_group \ ${OCF_RESKEY_device_group} -attributes \ state\=${OCF_RESKEY_s_alua_state} || exit ${OCF_ERR_GENERIC} # If we're a Slave, we assume the remote side is the Master ocf_log debug "scst_demote() -> Setting target group" \ "'${OCF_RESKEY_remote_tgt_grp}' ALUA state to" \ "'${OCF_RESKEY_m_alua_state}'..." ocf_run scstadmin -noprompt -set_tgrp_attr \ ${OCF_RESKEY_remote_tgt_grp} -dev_group \ ${OCF_RESKEY_device_group} -attributes \ state\=${OCF_RESKEY_m_alua_state} || exit ${OCF_ERR_GENERIC} else ocf_log err "The ALUA parameters need to be configured before using MS." exit ${OCF_ERR_CONFIGURED} fi # After the resource has been demoted, check whether the demotion worked while true; do scst_monitor if [ ${?} -eq ${OCF_RUNNING_MASTER} ]; then ocf_log debug "scst_demote() -> Resource still" \ "awaiting demotion." sleep 1 else ocf_log info "Resource was demoted successfully." break fi done # Only return $OCF_SUCCESS if _everything_ succeeded as expected return ${OCF_SUCCESS} } scst_notify() { # We're currently not using this ocf_log debug "scst_notify() -> Received a" \ "'${OCF_RESKEY_CRM_meta_notify_type}' /" \ "'${OCF_RESKEY_CRM_meta_notify_operation}' notification." return ${OCF_SUCCESS} } check_alua() { # Make sure the directories exist in the SCST sysfs structure if [ ! -d "${SCST_SYSFS}/device_groups/${OCF_RESKEY_device_group}" ]; then ocf_log err "The '${OCF_RESKEY_device_group}' device group does not exist!" exit ${OCF_ERR_INSTALLED} fi target_groups="${SCST_SYSFS}/device_groups/${OCF_RESKEY_device_group}/target_groups" if [ ! -d "${target_groups}/${OCF_RESKEY_local_tgt_grp}" ]; then ocf_log err "The '${OCF_RESKEY_local_tgt_grp}' target group does not exist!" exit ${OCF_ERR_INSTALLED} fi if [ ! -d "${target_groups}/${OCF_RESKEY_remote_tgt_grp}" ]; then ocf_log err "The '${OCF_RESKEY_remote_tgt_grp}' target group does not exist!" exit ${OCF_ERR_INSTALLED} fi # Check that the given ALUA states are valid local valid_m_alua_state=0 local valid_s_alua_state=0 for i in ${ALUA_STATES}; do if [ "x${OCF_RESKEY_m_alua_state}" = "x${i}" ]; then valid_m_alua_state=1 fi if [ "x${OCF_RESKEY_s_alua_state}" = "x${i}" ]; then valid_s_alua_state=1 fi done if [ ${valid_m_alua_state} -eq 0 ]; then ocf_log err "The 'm_alua_state' value is not valid: ${OCF_RESKEY_m_alua_state}" exit ${OCF_ERR_INSTALLED} fi if [ ${valid_s_alua_state} -eq 0 ]; then ocf_log err "The 's_alua_state' value is not valid: ${OCF_RESKEY_s_alua_state}" exit ${OCF_ERR_INSTALLED} fi } # Make sure meta-data and usage always succeed case ${__OCF_ACTION} in meta-data) scst_meta_data exit ${OCF_SUCCESS} ;; usage|help) scst_usage exit ${OCF_SUCCESS} ;; esac # Anything other than meta-data and usage must pass validation scst_validate_all || exit ${?} # Translate each action into the appropriate function call case ${__OCF_ACTION} in start) scst_start ;; stop) scst_stop ;; status|monitor) scst_monitor ;; notify) scst_notify ;; promote) scst_promote ;; demote) scst_demote ;; reload) ocf_log info "Reloading..." scst_start ;; validate-all) ;; migrate_to|migrate_from) scst_usage exit ${OCF_ERR_UNIMPLEMENTED} ;; *) scst_usage exit ${OCF_ERR_UNIMPLEMENTED} ;; esac # Log a debug message and exit rc=${?} ocf_log debug "${OCF_RESOURCE_INSTANCE} ${__OCF_ACTION} returned: ${rc}" exit ${rc}