summaryrefslogtreecommitdiffstats
path: root/extras
diff options
context:
space:
mode:
authorFlorian Haas <florian@hastexo.com>2012-02-20 16:25:43 +0100
committerAnand Avati <avati@redhat.com>2012-10-24 17:46:48 -0700
commit61c1d77f220e36af7feec14ae072d2f6e3230cf0 (patch)
treeaebf1d4d55d47334f0f6c7b90142351554676a7e /extras
parent0d868525d2d6e33761842e0e134eb59475c6c2bb (diff)
Add OCF compliant resource agents for glusterd and volumes
These resource agents plug glusterd into Open Cluster Framework (OCF) compliant cluster resource managers, like Pacemaker. The glusterd RA is fairly trivial; it simply manages the glusterd daemon like any upstart or systemd job would, except that Pacemaker can do it in a cluster-aware fashion. The volume RA is a bit more involved; It starts a volume and monitors individual brick's daemons in a cluster aware fashion, recovering bricks when their processes fail. Note that this does NOT imply people would deploy GlusterFS servers in pairs, or anything of that nature. Pacemaker has the ability to deploy cluster resources as clones, meaning glusterd and volumes would be configured as follows in a Pacemaker cluster: primitive p_glusterd ocf:glusterfs:glusterd \ op monitor interval="30" primitive p_volume_demo ocf:glusterfs:volume \ params volname="demo" \ op monitor interval="10" clone cl_glusterd p_glusterd \ meta interleave="true" clone cl_volume_demo p_volume_demo \ meta interleave="true" ordered="true" colocation c_volume_on_glusterd inf: cl_volume_demo cl_glusterd order o_glusterd_before_volume 0: cl_glusterd cl_volume_demo The cluster status then looks as follows (in a 4-node cluster; note the configuration above could be applied, unchanged, to a cluster of any number of nodes): ============ Last updated: Fri Mar 30 10:54:50 2012 Last change: Thu Mar 29 17:20:17 2012 via crmd on gluster02.h Stack: openais Current DC: gluster03.h - partition with quorum Version: 1.1.6-3.el6-a02c0f19a00c1eb2527ad38f146ebc0834814558 4 Nodes configured, 4 expected votes 8 Resources configured. ============ Online: [ gluster02.h gluster03.h gluster04.h gluster01.h ] Clone Set: cl_glusterd [p_glusterd] Started: [ gluster02.h gluster03.h gluster04.h gluster01.h ] Clone Set: cl_volume_demo [p_volume_demo] Started: [ gluster01.h gluster02.h gluster03.h gluster04.h ] This is also a way of providing automatic glusterd and brick recovery in systems where neither upstart nor systemd are available. Change-Id: Ied46657bdfd2dd72dc97cf41b0eb7adcecacd18f BUG: 869559 Signed-off-by: Florian Haas <florian@hastexo.com> Reviewed-on: http://review.gluster.org/3043 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
Diffstat (limited to 'extras')
-rw-r--r--extras/Makefile.am2
-rw-r--r--extras/ocf/Makefile.am13
-rwxr-xr-xextras/ocf/glusterd.in212
-rwxr-xr-xextras/ocf/volume.in246
4 files changed, 472 insertions, 1 deletions
diff --git a/extras/Makefile.am b/extras/Makefile.am
index 525482e089e..ccc732f097d 100644
--- a/extras/Makefile.am
+++ b/extras/Makefile.am
@@ -3,7 +3,7 @@ docdir = $(datadir)/doc/glusterfs/
EditorModedir = $(docdir)/
EditorMode_DATA = glusterfs-mode.el glusterfs.vim
-SUBDIRS = init.d benchmarking hook-scripts
+SUBDIRS = init.d benchmarking hook-scripts ocf
confdir = $(sysconfdir)/glusterfs
conf_DATA = glusterfs-logrotate
diff --git a/extras/ocf/Makefile.am b/extras/ocf/Makefile.am
new file mode 100644
index 00000000000..2d7410099e0
--- /dev/null
+++ b/extras/ocf/Makefile.am
@@ -0,0 +1,13 @@
+EXTRA_DIST = glusterd.in volume.in
+
+if WITH_OCF
+# The root of the OCF resource agent hierarchy
+# Per the OCF standard, it's always "lib",
+# not "lib64" (even on 64-bit platforms).
+ocfdir = $(prefix)/lib/ocf
+
+# The ceph provider directory
+radir = $(ocfdir)/resource.d/$(PACKAGE_NAME)
+
+ra_SCRIPTS = glusterd volume
+endif
diff --git a/extras/ocf/glusterd.in b/extras/ocf/glusterd.in
new file mode 100755
index 00000000000..c119a285d32
--- /dev/null
+++ b/extras/ocf/glusterd.in
@@ -0,0 +1,212 @@
+#!/bin/sh
+#
+# glusterd
+#
+# Description: Manages a glusterd server as a (typically cloned)
+# HA resource
+#
+# Authors: Florian Haas (hastexo Professional Services GmbH)
+#
+# License: GNU General Public License (GPL)
+
+#######################################################################
+# Initialization:
+
+: ${OCF_FUNCTIONS_DIR=${OCF_ROOT}/lib/heartbeat}
+. ${OCF_FUNCTIONS_DIR}/ocf-shellfuncs
+
+# Convenience variables
+# When sysconfdir and localstatedir aren't passed in as
+# configure flags, they're defined in terms of prefix
+prefix=@prefix@
+#######################################################################
+
+
+OCF_RESKEY_binary_default="glusterd"
+OCF_RESKEY_pid_default="@localstatedir@/run/glusterd.pid"
+OCF_RESKEY_socket_default=""
+OCF_RESKEY_additional_parameters_default=""
+
+: ${OCF_RESKEY_binary=${OCF_RESKEY_binary_default}}
+: ${OCF_RESKEY_pid=${OCF_RESKEY_pid_default}}
+
+glusterd_meta_data() {
+ cat <<EOF
+<?xml version="1.0"?>
+<!DOCTYPE resource-agent SYSTEM "ra-api-1.dtd">
+<resource-agent name="glusterd" version="0.1">
+ <version>0.1</version>
+ <longdesc lang="en">
+ </longdesc>
+ <shortdesc lang="en">Manages a Gluster server</shortdesc>
+ <parameters>
+ <parameter name="binary">
+ <longdesc lang="en">
+ Name of the glusterd executable. Specify a full absolute
+ path if the binary is not in your \$PATH.
+ </longdesc>
+ <shortdesc lang="en">glusterd executable</shortdesc>
+ <content type="string" default="$OCF_RESKEY_binary_default"/>
+ </parameter>
+ <parameter name="pid">
+ <longdesc lang="en">
+ Path to the glusterd PID file.
+ </longdesc>
+ <shortdesc lang="en">PID file</shortdesc>
+ <content type="string" default="$OCF_RESKEY_pid_default"/>
+ </parameter>
+ <parameter name="socket">
+ <longdesc lang="en">
+ Path to the glusterd UNIX socket file. If unspecified,
+ glusterd will not listen on any socket.
+ </longdesc>
+ <shortdesc lang="en">Socket file</shortdesc>
+ <content type="string"/>
+ </parameter>
+ </parameters>
+ <actions>
+ <action name="start" timeout="20" />
+ <action name="stop" timeout="20" />
+ <action name="monitor" timeout="20" interval="10" />
+ <action name="reload" timeout="20" />
+ <action name="meta-data" timeout="5" />
+ <action name="validate-all" timeout="20" />
+ </actions>
+</resource-agent>
+EOF
+
+}
+
+glusterd_start() {
+ local glusterd_options
+ # exit immediately if configuration is not valid
+ glusterd_validate_all || exit $?
+
+ # if resource is already running, bail out early
+ if glusterd_monitor; then
+ ocf_log info "Resource is already running"
+ return $OCF_SUCCESS
+ fi
+
+ # actually start up the resource here (make sure to immediately
+ # exit with an $OCF_ERR_ error code if anything goes seriously
+ # wrong)
+ glusterd_options="-p $OCF_RESKEY_pid"
+ if [ -n "$OCF_RESKEY_socket" ]; then
+ glusterd_options="$glusterd_options -S $OCF_RESKEY_socket"
+ fi
+ if [ -n "$OCF_RESKEY_additional_parameters" ]; then
+ glusterd_options="$glusterd_options $OCF_RESKEY_additional_parameters"
+ fi
+
+ ocf_run $OCF_RESKEY_binary $glusterd_options || exit $OCF_ERR_GENERIC
+
+ # After the resource has been started, check whether it started up
+ # correctly. If the resource starts asynchronously, the agent may
+ # spin on the monitor function here -- if the resource does not
+ # start up within the defined timeout, the cluster manager will
+ # consider the start action failed
+ while ! glusterd_monitor; do
+ ocf_log debug "Resource has not started yet, waiting"
+ sleep 1
+ done
+
+ # only return $OCF_SUCCESS if _everything_ succeeded as expected
+ return $OCF_SUCCESS
+}
+
+glusterd_stop() {
+ local rc
+ local pid
+
+ # exit immediately if configuration is not valid
+ glusterd_validate_all || exit $?
+
+ glusterd_monitor
+ rc=$?
+ case "$rc" in
+ "$OCF_SUCCESS")
+ # Currently running. Normal, expected behavior.
+ ocf_log debug "Resource is currently running"
+ ;;
+ "$OCF_NOT_RUNNING")
+ # Currently not running. Nothing to do.
+ ocf_log info "Resource is already stopped"
+ return $OCF_SUCCESS
+ ;;
+ esac
+
+ # actually shut down the resource here (make sure to immediately
+ # exit with an $OCF_ERR_ error code if anything goes seriously
+ # wrong)
+ pid=`cat $OCF_RESKEY_pid`
+ ocf_run kill -s TERM $pid || exit OCF_ERR_GENERIC
+
+ # After the resource has been stopped, check whether it shut down
+ # correctly. If the resource stops asynchronously, the agent may
+ # spin on the monitor function here -- if the resource does not
+ # shut down within the defined timeout, the cluster manager will
+ # consider the stop action failed
+ while glusterd_monitor; do
+ ocf_log debug "Resource has not stopped yet, waiting"
+ sleep 1
+ done
+
+ # only return $OCF_SUCCESS if _everything_ succeeded as expected
+ return $OCF_SUCCESS
+
+}
+
+glusterd_monitor() {
+ local pid
+
+ [ -e $OCF_RESKEY_pid ] || return $OCF_NOT_RUNNING
+
+ pid=`cat $OCF_RESKEY_pid`
+ ocf_run kill -s 0 $pid || return $OCF_NOT_RUNNING
+
+ ocf_log debug "$OCF_RESKEY_binary running with PID $pid"
+ return $OCF_SUCCESS
+}
+
+glusterd_validate_all() {
+ # Test for required binaries
+ check_binary $OCF_RESKEY_binary
+
+ return $OCF_SUCCESS
+}
+
+
+
+# Make sure meta-data and usage always succeed
+case $__OCF_ACTION in
+meta-data) glusterd_meta_data
+ exit $OCF_SUCCESS
+ ;;
+usage|help) glusterd_usage
+ exit $OCF_SUCCESS
+ ;;
+esac
+
+# Anything other than meta-data and usage must pass validation
+glusterd_validate_all || exit $?
+
+# Translate each action into the appropriate function call
+case $__OCF_ACTION in
+start) glusterd_start;;
+stop) glusterd_stop;;
+status|monitor) glusterd_monitor;;
+reload) ocf_log info "Reloading..."
+ glusterd_start
+ ;;
+validate-all) ;;
+notify) exit $OCF_SUCCESS;;
+*) glusterd_usage
+ exit $OCF_ERR_UNIMPLEMENTED
+ ;;
+esac
+rc=$?
+
+# The resource agent may optionally log a debug message
+ocf_log debug "${OCF_RESOURCE_INSTANCE} $__OCF_ACTION returned $rc"
+exit $rc
diff --git a/extras/ocf/volume.in b/extras/ocf/volume.in
new file mode 100755
index 00000000000..72fd1213af2
--- /dev/null
+++ b/extras/ocf/volume.in
@@ -0,0 +1,246 @@
+#!/bin/sh
+#
+# glusterd
+#
+# Description: Manages a glusterd server as a (typically cloned)
+# HA resource
+#
+# Authors: Florian Haas (hastexo Professional Services GmbH)
+#
+# License: GNU General Public License (GPL)
+
+#######################################################################
+# Initialization:
+
+: ${OCF_FUNCTIONS_DIR=${OCF_ROOT}/lib/heartbeat}
+. ${OCF_FUNCTIONS_DIR}/ocf-shellfuncs
+
+# Convenience variables
+# When sysconfdir and localstatedir aren't passed in as
+# configure flags, they're defined in terms of prefix
+prefix=@prefix@
+SHORTHOSTNAME=`hostname -s`
+#######################################################################
+
+OCF_RESKEY_binary_default="gluster"
+
+: ${OCF_RESKEY_binary=${OCF_RESKEY_binary_default}}
+
+volume_meta_data() {
+ cat <<EOF
+<?xml version="1.0"?>
+<!DOCTYPE resource-agent SYSTEM "ra-api-1.dtd">
+<resource-agent name="volume" version="0.1">
+ <version>0.1</version>
+ <longdesc lang="en">
+Manages a GlusterFS volume and monitors its bricks. When a resource of
+this type is configured as a clone (as is commonly the case), then it
+must have clone ordering enabled.
+ </longdesc>
+ <shortdesc lang="en">Manages a GlusterFS volume</shortdesc>
+ <parameters>
+ <parameter name="volname" required="1">
+ <longdesc lang="en">
+ The name of the volume to manage.
+ </longdesc>
+ <shortdesc lang="en">volume name</shortdesc>
+ <content type="string"/>
+ </parameter>
+ <parameter name="binary">
+ <longdesc lang="en">
+ Name of the gluster executable. Specify a full absolute
+ path if the binary is not in your \$PATH.
+ </longdesc>
+ <shortdesc lang="en">gluster executable</shortdesc>
+ <content type="string" default="$OCF_RESKEY_binary_default"/>
+ </parameter>
+ </parameters>
+ <actions>
+ <action name="start" timeout="20" />
+ <action name="stop" timeout="20" />
+ <action name="monitor" timeout="20" interval="10" />
+ <action name="reload" timeout="20" />
+ <action name="meta-data" timeout="5" />
+ <action name="validate-all" timeout="20" />
+ </actions>
+</resource-agent>
+EOF
+
+}
+
+volume_getdir() {
+ local voldir
+ voldir="@sysconfdir@/glusterd/vols/${OCF_RESKEY_volname}"
+
+ [ -d ${voldir} ] || return 1
+
+ echo "${voldir}"
+ return 0
+}
+
+volume_getbricks() {
+ local infofile
+ local voldir
+ voldir=`volume_getdir`
+ infofile="${voldir}/info"
+
+ [ -e ${infofile} ] || return 1
+
+ echo "`sed -n -e "s/^brick-.\+=${SHORTHOSTNAME}://p" < ${infofile}`"
+ return 0
+}
+
+volume_getpids() {
+ local bricks
+ local piddir
+ local pidfile
+ local infofile
+ local voldir
+
+ voldir=`volume_getdir`
+ bricks=`volume_getbricks`
+ piddir="${voldir}/run"
+
+ for brick in ${bricks}; do
+ pidfile="${piddir}/${SHORTHOSTNAME}${brick}.pid"
+ [ -e $pidfile ] || return 1
+ cat $pidfile
+ done
+
+ return 0
+}
+
+volume_start() {
+ local volume_options
+
+ # exit immediately if configuration is not valid
+ volume_validate_all || exit $?
+
+ # if resource is already running, bail out early
+ if volume_monitor; then
+ ocf_log info "Resource is already running"
+ return $OCF_SUCCESS
+ fi
+
+ # actually start up the resource here
+ ocf_run "$OCF_RESKEY_binary" \
+ volume start "$OCF_RESKEY_volname" force || exit $OCF_ERR_GENERIC
+
+ # After the resource has been started, check whether it started up
+ # correctly. If the resource starts asynchronously, the agent may
+ # spin on the monitor function here -- if the resource does not
+ # start up within the defined timeout, the cluster manager will
+ # consider the start action failed
+ while ! volume_monitor; do
+ ocf_log debug "Resource has not started yet, waiting"
+ sleep 1
+ done
+
+ # only return $OCF_SUCCESS if _everything_ succeeded as expected
+ return $OCF_SUCCESS
+}
+
+volume_stop() {
+ local rc
+ local pid
+
+ # exit immediately if configuration is not valid
+ volume_validate_all || exit $?
+
+ volume_monitor
+ rc=$?
+ case "$rc" in
+ "$OCF_SUCCESS")
+ # Currently running. Normal, expected behavior.
+ ocf_log debug "Resource is currently running"
+ ;;
+ "$OCF_NOT_RUNNING")
+ # Currently not running. Nothing to do.
+ ocf_log info "Resource is already stopped"
+ return $OCF_SUCCESS
+ ;;
+ esac
+
+ # actually shut down the resource here (make sure to immediately
+ # exit with an $OCF_ERR_ error code if anything goes seriously
+ # wrong)
+ pids=`volume_getpids`
+ for pid in $pids; do
+ ocf_run kill -s TERM $pid
+ done
+
+ # After the resource has been stopped, check whether it shut down
+ # correctly. If the resource stops asynchronously, the agent may
+ # spin on the monitor function here -- if the resource does not
+ # shut down within the defined timeout, the cluster manager will
+ # consider the stop action failed
+ while volume_monitor; do
+ ocf_log debug "Resource has not stopped yet, waiting"
+ sleep 1
+ done
+
+ # only return $OCF_SUCCESS if _everything_ succeeded as expected
+ return $OCF_SUCCESS
+
+}
+
+volume_monitor() {
+ local pid
+
+ pids=`volume_getpids` || return $OCF_NOT_RUNNING
+
+ for pid in $pids; do
+ ocf_run kill -s 0 $pid || return $OCF_NOT_RUNNING
+ done
+
+ ocf_log debug "Local bricks for volume ${OCF_RESKEY_volname} running with PIDs $pids"
+ return $OCF_SUCCESS
+}
+
+volume_validate_all() {
+ # Test for configuration errors first
+ if [ -z "${OCF_RESKEY_volname}" ]; then
+ ocf_log err 'Missing required parameter "volname"'
+ return $OCF_ERR_CONFIGURED
+ fi
+
+ # Test for required binaries
+ check_binary $OCF_RESKEY_binary
+
+ return $OCF_SUCCESS
+}
+
+
+
+# Make sure meta-data and usage always succeed
+case $__OCF_ACTION in
+meta-data) volume_meta_data
+ exit $OCF_SUCCESS
+ ;;
+usage|help) volume_usage
+ exit $OCF_SUCCESS
+ ;;
+esac
+
+# Anything other than meta-data and usage must pass validation
+volume_validate_all || exit $?
+
+# Translate each action into the appropriate function call
+case $__OCF_ACTION in
+start) volume_start;;
+stop) volume_stop;;
+status|monitor) volume_monitor;;
+reload) ocf_log info "Reloading..."
+ volume_start
+ ;;
+validate-all) ;;
+notify) exit $OCF_SUCCESS;;
+*) volume_usage
+ exit $OCF_ERR_UNIMPLEMENTED
+ ;;
+esac
+rc=$?
+
+# The resource agent may optionally log a debug message
+ocf_log debug "${OCF_RESOURCE_INSTANCE} $__OCF_ACTION returned $rc"
+exit $rc