/usr/lib/ocf/resource.d/heartbeat/rabbitmq-cluster is in resource-agents 1:4.0.0~rc1-4.
This file is owned by root:root, with mode 0o755.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 | #!/bin/sh
#
# Copyright (c) 2014 David Vossel <davidvossel@gmail.com>
# All Rights Reserved.
#
# 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:
: ${OCF_FUNCTIONS_DIR=${OCF_ROOT}/lib/heartbeat}
. ${OCF_FUNCTIONS_DIR}/ocf-shellfuncs
#######################################################################
RMQ_SERVER=/usr/sbin/rabbitmq-server
RMQ_CTL=/usr/sbin/rabbitmqctl
RMQ_DATA_DIR="/var/lib/rabbitmq/mnesia"
RMQ_PID_DIR="/var/run/rabbitmq"
RMQ_PID_FILE="/var/run/rabbitmq/rmq.pid"
RMQ_LOG_DIR="/var/log/rabbitmq"
NODENAME=$(ocf_local_nodename)
# this attr represents the current active local rmq node name.
# when rmq stops or the node is fenced, this attr disappears
RMQ_CRM_ATTR_COOKIE="rmq-node-attr-${OCF_RESOURCE_INSTANCE}"
# this attr represents the last known active local rmq node name
# when rmp stops or the node is fenced, the attr stays forever so
# we can continue to map an offline pcmk node to it's rmq node name
# equivalent.
RMQ_CRM_ATTR_COOKIE_LAST_KNOWN="rmq-node-attr-last-known-${OCF_RESOURCE_INSTANCE}"
meta_data() {
cat <<END
<?xml version="1.0"?>
<!DOCTYPE resource-agent SYSTEM "ra-api-1.dtd">
<resource-agent name="rabbitmq-cluster">
<version>1.0</version>
<longdesc lang="en">
Starts cloned rabbitmq cluster instance
</longdesc>
<shortdesc lang="en">rabbitmq clustered</shortdesc>
<parameters>
<parameter name="set_policy" unique="1">
<longdesc lang="en">
Policy string to pass to 'rabbitmqctl set_policy' right after bootstrapping the first rabbitmq instance.
</longdesc>
<shortdesc lang="en">rabbitmqctl set_policy args</shortdesc>
<content type="string" default="" />
</parameter>
</parameters>
<actions>
<action name="start" timeout="100" />
<action name="stop" timeout="90" />
<action name="monitor" timeout="40" interval="10" depth="0" />
<action name="meta-data" timeout="10" />
<action name="validate-all" timeout="20" />
</actions>
</resource-agent>
END
}
#######################################################################
rmq_usage() {
cat <<END
usage: $0 {start|stop|monitor|notify|validate-all|meta-data}
Expects to have a fully populated OCF RA-compliant environment set.
END
}
rmq_wipe_data()
{
rm -rf $RMQ_DATA_DIR > /dev/null 2>&1
}
rmq_local_node()
{
local node_name=$(rabbitmqctl status 2>&1 | sed -n -e "s/^.*[S|s]tatus of node \(.*\)\s.*$/\1/p" | tr -d "'")
if [ -z "$node_name" ]; then
node_name=$(cat /etc/rabbitmq/rabbitmq-env.conf 2>/dev/null | grep "\s*RABBITMQ_NODENAME=" | awk -F= '{print $2}')
fi
echo "$node_name"
}
rmq_join_list()
{
cibadmin -Q --xpath "//node_state[@crmd='online']//nvpair[@name='$RMQ_CRM_ATTR_COOKIE']" | grep "$RMQ_CRM_ATTR_COOKIE" | sed -n -e "s/^.*value=.\(.*\)\".*$/\1/p"
}
rmq_write_nodename()
{
local node_name=$(rmq_local_node)
if [ -z "$node_name" ]; then
ocf_log err "Failed to determine rabbitmq node name, exiting"
exit $OCF_ERR_GENERIC
fi
# store the pcmknode to rmq node mapping as a transient attribute. This allows
# us to retrieve the join list with a simple xpath.
${HA_SBIN_DIR}/crm_attribute -N $NODENAME -l reboot --name "$RMQ_CRM_ATTR_COOKIE" -v "$node_name"
# the pcmknode to rmq node mapping as a permanent attribute as well. this lets
# us continue to map offline nodes to their equivalent rmq node name
${HA_SBIN_DIR}/crm_attribute -N $NODENAME -l forever --name "$RMQ_CRM_ATTR_COOKIE_LAST_KNOWN" -v "$node_name"
}
rmq_delete_nodename()
{
# remove node-name
${HA_SBIN_DIR}/crm_attribute -N $NODENAME -l reboot --name "$RMQ_CRM_ATTR_COOKIE" -D
}
prepare_dir () {
if [ ! -d ${1} ] ; then
mkdir -p ${1}
chown -R rabbitmq:rabbitmq ${1}
chmod 755 ${1}
fi
}
remove_pid () {
rm -f ${RMQ_PID_FILE} > /dev/null 2>&1
}
rmq_monitor() {
local rc
$RMQ_CTL cluster_status > /dev/null 2>&1
rc=$?
case "$rc" in
0)
ocf_log debug "RabbitMQ server is running normally"
rmq_write_nodename
return $OCF_SUCCESS
;;
2|68|69|70|75|78)
ocf_log info "RabbitMQ server is not running"
rmq_delete_nodename
return $OCF_NOT_RUNNING
;;
*)
ocf_log err "Unexpected return code from '$RMQ_CTL cluster_status' exit code: $rc"
rmq_delete_nodename
return $OCF_ERR_GENERIC
;;
esac
}
rmq_init_and_wait()
{
local rc
prepare_dir $RMQ_PID_DIR
prepare_dir $RMQ_LOG_DIR
remove_pid
# the server startup script uses this environment variable
export RABBITMQ_PID_FILE="$RMQ_PID_FILE"
setsid sh -c "$RMQ_SERVER > ${RMQ_LOG_DIR}/startup_log 2> ${RMQ_LOG_DIR}/startup_err" &
ocf_log info "Waiting for server to start"
$RMQ_CTL wait $RMQ_PID_FILE
rc=$?
if [ $rc -ne $OCF_SUCCESS ]; then
remove_pid
ocf_log info "rabbitmq-server start failed: $rc"
return $OCF_ERR_GENERIC
fi
rmq_monitor
return $?
}
rmq_set_policy()
{
$RMQ_CTL set_policy "$@" > /dev/null 2>&1
}
rmq_start_first()
{
local rc
ocf_log info "Bootstrapping rabbitmq cluster"
rmq_wipe_data
rmq_init_and_wait
rc=$?
if [ $rc -eq 0 ]; then
rc=$OCF_SUCCESS
ocf_log info "cluster bootstrapped"
if [ -n "$OCF_RESKEY_set_policy" ]; then
# do not quote set_policy, we are passing in arguments
rmq_set_policy $OCF_RESKEY_set_policy > /dev/null 2>&1
if [ $? -ne 0 ]; then
ocf_log err "Failed to set policy: $OCF_RESKEY_set_policy"
rc=$OCF_ERR_GENERIC
else
ocf_log info "Policy set: $OCF_RESKEY_set_policy"
fi
fi
else
ocf_log info "failed to bootstrap cluster. Check SELINUX policy"
rc=$OCF_ERR_GENERIC
fi
return $rc
}
rmq_is_clustered()
{
$RMQ_CTL eval 'rabbit_mnesia:is_clustered().' | grep -q true
}
rmq_join_existing()
{
local join_list="$1"
local rc=$OCF_ERR_GENERIC
ocf_log info "Joining existing cluster with [ $(echo $join_list | tr '\n' ' ') ] nodes."
rmq_init_and_wait
if [ $? -ne 0 ]; then
return $OCF_ERR_GENERIC
fi
if rmq_is_clustered; then
ocf_log info "Successfully re-joined existing rabbitmq cluster automatically"
return $OCF_SUCCESS
fi
# unconditionally join the cluster
$RMQ_CTL stop_app > /dev/null 2>&1
for node in $(echo "$join_list"); do
ocf_log info "Attempting to join cluster with target node $node"
$RMQ_CTL join_cluster $node
if [ $? -eq 0 ]; then
ocf_log info "Joined cluster by connecting to node $node, starting app"
$RMQ_CTL start_app
rc=$?
if [ $rc -ne 0 ]; then
ocf_log err "'$RMQ_CTL start_app' failed"
fi
break;
fi
done
if [ "$rc" -ne 0 ]; then
ocf_log info "Join process incomplete, shutting down."
return $OCF_ERR_GENERIC
fi
ocf_log info "Successfully joined existing rabbitmq cluster"
return $OCF_SUCCESS
}
rmq_forget_cluster_node_remotely() {
local running_cluster_nodes="$1"
local node_to_forget="$2"
ocf_log info "Forgetting $node_to_forget via nodes [ $(echo $running_cluster_nodes | tr '\n' ' ') ]."
for running_cluster_node in $running_cluster_nodes; do
rabbitmqctl -n $running_cluster_node forget_cluster_node $node_to_forget
if [ $? = 0 ]; then
ocf_log info "Succeeded forgetting $node_to_forget via $running_cluster_node."
return
else
ocf_log err "Failed to forget node $node_to_forget via $running_cluster_node."
fi
done
}
rmq_notify() {
node_list="${OCF_RESKEY_CRM_meta_notify_stop_uname}"
mode="${OCF_RESKEY_CRM_meta_notify_type}-${OCF_RESKEY_CRM_meta_notify_operation}"
# When notifications are on, this agent is going to "forget" nodes once they
# leave the cluster. This is thought to resolve some issues where rabbitmq
# blocks trying to sync with an offline node after a fencing action occurs.
if ! [ "${mode}" = "post-stop" ]; then
return $OCF_SUCCESS
fi
rmq_monitor
if [ $? -ne $OCF_SUCCESS ]; then
# only run forget when we are for sure active
return $OCF_SUCCESS
fi
# forget each stopped rmq instance in the provided pcmk node in the list.
for node in $(echo "$node_list"); do
local rmq_node="$(${HA_SBIN_DIR}/crm_attribute -N $node -l forever --query --name $RMQ_CRM_ATTR_COOKIE_LAST_KNOWN -q)"
if [ -z "$rmq_node" ]; then
ocf_log warn "Unable to map pcmk node $node to a known rmq node."
continue
fi
ocf_log notice "Forgetting stopped node $rmq_node"
$RMQ_CTL forget_cluster_node $rmq_node
if [ $? -ne 0 ]; then
ocf_log warn "Unable to forget offline node $rmq_node."
fi
done
return $OCF_SUCCESS
}
rmq_start() {
local join_list=""
local rc
rmq_monitor
if [ $? -eq $OCF_SUCCESS ]; then
return $OCF_SUCCESS
fi
join_list=$(rmq_join_list)
# No join list means no active instances are up. This instance
# is the first, so it needs to bootstrap the rest
if [ -z "$join_list" ]; then
rmq_start_first
rc=$?
return $rc
fi
# first try to join without wiping mnesia data
rmq_join_existing "$join_list"
if [ $? -ne 0 ]; then
ocf_log info "node failed to join, wiping data directory and trying again"
local local_rmq_node="$(${HA_SBIN_DIR}/crm_attribute -N $NODENAME -l forever --query --name $RMQ_CRM_ATTR_COOKIE_LAST_KNOWN -q)"
# if the graceful join fails, use the hammer and reset all the data.
rmq_stop
rmq_wipe_data
rmq_forget_cluster_node_remotely "$join_list" "$local_rmq_node"
rmq_join_existing "$join_list"
rc=$?
# Restore users and users' permissions (if any)
BaseDataDir=`dirname $RMQ_DATA_DIR`
if [ -f $BaseDataDir/users.erl ] ; then
rabbitmqctl eval "
%% Run only if Mnesia is ready.
lists:any(fun({mnesia,_,_}) -> true; ({_,_,_}) -> false end, application:which_applications()) andalso
begin
[WildPattern] = ets:select(mnesia_gvar, [ { {{rabbit_user, wild_pattern}, '\\\$1'}, [], ['\\\$1'] } ]),
%% Read users first
{ok, [Users]} = file:consult(\"$BaseDataDir/users.erl\"),
Upgrade = fun
({internal_user, A, B, C}) -> {internal_user, A, B, C, rabbit_password_hashing_md5};
({internal_user, A, B, C, D}) -> {internal_user, A, B, C, D}
end,
Downgrade = fun
({internal_user, A, B, C}) -> {internal_user, A, B, C};
({internal_user, A, B, C, rabbit_password_hashing_md5}) -> {internal_user, A, B, C};
%% Incompatible scheme, so we will loose user's password ('B' value) during conversion.
%% Unfortunately, this case will require manual intervention - user have to run:
%% rabbitmqctl change_password <A> <somenewpassword>
({internal_user, A, B, C, _}) -> {internal_user, A, B, C}
end,
case WildPattern of
%% Version < 3.6.0
{internal_user,'_','_','_'} ->
lists:foreach(fun(X) -> mnesia:dirty_write(rabbit_user, Downgrade(X)) end, Users);
%% Version >= 3.6.0
{internal_user,'_','_','_','_'} ->
lists:foreach(fun(X) -> mnesia:dirty_write(rabbit_user, Upgrade(X)) end, Users)
end,
ok = file:delete(\"$BaseDataDir/users.erl\")
end.
"
fi
if [ -f $BaseDataDir/users_perms.erl ] ; then
rabbitmqctl eval "
%% Run only if Mnesia is ready.
lists:any(fun({mnesia,_,_}) -> true; ({_,_,_}) -> false end, application:which_applications()) andalso
begin
{ok, [UsersPerms]} = file:consult(\"$BaseDataDir/users_perms.erl\"),
lists:foreach(fun(X) -> mnesia:dirty_write(rabbit_user_permission, X) end, UsersPerms),
ok = file:delete(\"$BaseDataDir/users_perms.erl\")
end.
"
fi
if [ $rc -ne 0 ]; then
ocf_log info "node failed to join even after reseting local data. Check SELINUX policy"
return $OCF_ERR_GENERIC
fi
fi
return $OCF_SUCCESS
}
rmq_stop() {
# Backup users and users' permissions
BaseDataDir=`dirname $RMQ_DATA_DIR`
rabbitmqctl eval "
%% Run only if Mnesia is still available.
lists:any(fun({mnesia,_,_}) -> true; ({_,_,_}) -> false end, application:which_applications()) andalso
begin
[WildPattern] = ets:select(mnesia_gvar, [ { {{rabbit_user, wild_pattern}, '\\\$1'}, [], ['\\\$1'] } ]),
Users = case WildPattern of
%% Version < 3.6.0
{internal_user,'_','_','_'} ->
mnesia:dirty_select(rabbit_user, [{ {internal_user, '\\\$1', '_', '_'}, [{'/=', '\\\$1', <<\"guest\">>}], ['\\\$_'] } ]);
%% Version >= 3.6.0
{internal_user,'_','_','_','_'} ->
mnesia:dirty_select(rabbit_user, [{ {internal_user, '\\\$1', '_', '_', '_'}, [{'/=', '\\\$1', <<\"guest\">>}], ['\\\$_'] } ])
end,
Users /= [] andalso file:write_file(\"$BaseDataDir/users.erl\", io_lib:fwrite(\"~p.~n\", [Users])),
UsersPerms = mnesia:dirty_select(rabbit_user_permission, [{{'\\\$1', {'\\\$2', '\\\$3','\\\$4'}, '\\\$5'}, [{'/=', '\\\$3', <<\"guest\">>}], ['\\\$_']}]),
UsersPerms /= [] andalso file:write_file(\"$BaseDataDir/users_perms.erl\", io_lib:fwrite(\"~p.~n\", [UsersPerms]))
end.
"
rmq_monitor
if [ $? -eq $OCF_NOT_RUNNING ]; then
return $OCF_SUCCESS
fi
$RMQ_CTL stop
rc=$?
if [ $rc -ne 0 ]; then
ocf_log err "rabbitmq-server stop command failed: $RMQ_CTL stop, $rc"
return $rc
fi
#TODO add kill logic
stop_wait=1
while [ $stop_wait = 1 ]; do
rmq_monitor
rc=$?
if [ "$rc" -eq $OCF_NOT_RUNNING ]; then
stop_wait=0
break
elif [ "$rc" -ne $OCF_SUCCESS ]; then
ocf_log info "rabbitmq-server stop failed: $rc"
exit $OCF_ERR_GENERIC
fi
sleep 1
done
remove_pid
return $OCF_SUCCESS
}
rmq_validate() {
check_binary $RMQ_SERVER
check_binary $RMQ_CTL
# This resource only makes sense as a clone right now. at some point
# we may want to verify the following.
#TODO verify cloned
#TODO verify ordered=true
# Given that this resource does the cluster join explicitly,
# having a cluster_nodes list in the static config file will
# likely conflict with this agent.
#TODO verify no cluster list in rabbitmq conf
#cat /etc/rabbitmq/rabbitmq.config | grep "cluster_nodes"
return $OCF_SUCCESS
}
case $__OCF_ACTION in
meta-data) meta_data
exit $OCF_SUCCESS
;;
start) rmq_start;;
stop) rmq_stop;;
monitor) rmq_monitor;;
validate-all) rmq_validate;;
notify) rmq_notify;;
usage|help) rmq_usage
exit $OCF_SUCCESS
;;
*) rmq_usage
exit $OCF_ERR_UNIMPLEMENTED
;;
esac
rc=$?
ocf_log debug "${OCF_RESOURCE_INSTANCE} $__OCF_ACTION : $rc"
exit $rc
|