/usr/share/heartbeat/cts/CM_LinuxHAv2.py is in heartbeat 1:3.0.5-3ubuntu2.
This file is owned by root:root, with mode 0o644.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 | #!/usr/bin/python
'''CTS: Cluster Testing System: LinuxHA v2 dependent modules...
'''
__copyright__='''
Author: Huang Zhen <zhenhltc@cn.ibm.com>
Copyright (C) 2004 International Business Machines
Additional Audits, Revised Start action, Default Configuration:
Copyright (C) 2004 Andrew Beekhof <andrew@beekhof.net>
'''
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 2
# of the License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
import os,sys,CTS,CTSaudits,CTStests, warnings
from CTS import *
from CM_hb import HeartbeatCM
from CTSaudits import ClusterAudit
from CTStests import *
from CIB import *
try:
from xml.dom.minidom import *
except ImportError:
sys.__stdout__.write("Python module xml.dom.minidom not found\n")
sys.__stdout__.write("Please install python-xml or similar before continuing\n")
sys.__stdout__.flush()
sys.exit(1)
#######################################################################
#
# LinuxHA v2 dependent modules
#
#######################################################################
class LinuxHAv2(HeartbeatCM):
'''
The linux-ha version 2 cluster manager class.
It implements the things we need to talk to and manipulate
linux-ha version 2 clusters
'''
def __init__(self, Environment, randseed=None):
HeartbeatCM.__init__(self, Environment, randseed=randseed)
self.clear_cache = 0
self.cib_installed = 0
self.config = None
self.cluster_monitor = 0
self.use_short_names = 1
self.update({
"Name" : "linux-ha-v2",
"DeadTime" : 300,
"StartTime" : 300, # Max time to start up
"StableTime" : 30,
"StartCmd" : "/etc/init.d/heartbeat start > /dev/null 2>&1",
"StopCmd" : "/etc/init.d/heartbeat stop > /dev/null 2>&1",
"ElectionCmd" : "/usr/sbin/crmadmin -E %s",
"StatusCmd" : "/usr/sbin/crmadmin -S %s 2>/dev/null",
"EpocheCmd" : "/usr/sbin/ccm_tool -e",
"QuorumCmd" : "/usr/sbin/ccm_tool -q",
"CibQuery" : "/usr/sbin/cibadmin -Ql",
"ParitionCmd" : "/usr/sbin/ccm_tool -p",
"IsRscRunning" : "/usr/sbin/lrmadmin -E %s monitor 0 0 EVERYTIME 2>/dev/null|grep return",
"ExecuteRscOp" : "/usr/sbin/lrmadmin -n %s -E %s %s 0 %d EVERYTIME 2>/dev/null",
"CIBfile" : "%s:/var/lib/heartbeat/crm/cib.xml",
"TmpDir" : "/tmp",
"BreakCommCmd2" : "/usr/share/heartbeat/TestHeartbeatComm break-communication %s>/dev/null 2>&1",
"IsIPAddrRscRunning" : "",
"StandbyCmd" : "/usr/sbin/crm_standby -U %s -v %s 2>/dev/null",
"UUIDQueryCmd" : "/usr/sbin/crmadmin -N",
"StandbyQueryCmd" : "/usr/sbin/crm_standby -GQ -U %s 2>/dev/null",
# Patterns to look for in the log files for various occasions...
"Pat:DC_IDLE" : "crmd.*State transition.*-> S_IDLE",
# This wont work if we have multiple partitions
# Use: "Pat:They_started" : "%s crmd:.*State transition.*-> S_NOT_DC",
"Pat:They_started" : "Updating node state to member for %s",
"Pat:We_started" : "%s crmd:.* State transition.*-> S_IDLE",
"Pat:We_stopped" : "heartbeat.*%s.*Heartbeat shutdown complete",
"Pat:Logd_stopped" : "%s logd:.*Exiting write process",
"Pat:They_stopped" : "%s crmd:.*LOST:.* %s ",
"Pat:All_stopped" : "heartbeat.*%s.*Heartbeat shutdown complete",
"Pat:They_dead" : "node %s.*: is dead",
"Pat:TransitionComplete" : "Transition status: Complete: complete",
# Bad news Regexes. Should never occur.
"BadRegexes" : (
r"ERROR:",
r"CRIT:",
r"Shutting down\.",
r"Forcing shutdown\.",
r"Timer I_TERMINATE just popped",
r"input=I_ERROR",
r"input=I_FAIL",
r"input=I_INTEGRATED cause=C_TIMER_POPPED",
r"input=I_FINALIZED cause=C_TIMER_POPPED",
r"input=I_ERROR",
r", exiting\.",
r"WARN.*Ignoring HA message.*vote.*not in our membership list",
r"pengine.*Attempting recovery of resource",
r"tengine.*is taking more than 2x its timeout",
r"Confirm not received from",
r"Welcome reply not received from",
r"Attempting to schedule .* after a stop",
r"Resource .* was active at shutdown",
r"duplicate entries for call_id",
r"Search terminated:",
r"No need to invoke the TE",
r":global_timer_callback",
r"Faking parameter digest creation",
r"Parameters to .* action changed:",
r"Parameters to .* changed",
),
})
del self["Standby"]
if self.Env["DoBSC"]:
del self["Pat:They_stopped"]
del self["Pat:Logd_stopped"]
self.Env["use_logd"] = 0
self.check_transitions = 0
self.check_elections = 0
self.CIBsync = {}
self.default_cts_cib=CIB(self).cib()
self.debug(self.default_cts_cib)
def errorstoignore(self):
# At some point implement a more elegant solution that
# also produces a report at the end
'''Return list of errors which are known and very noisey should be ignored'''
if 1:
return [
"crmadmin:",
"ERROR: Message hist queue is filling up"
]
return []
def install_config(self, node):
if not self.ns.WaitForNodeToComeUp(node):
self.log("Node %s is not up." % node)
return None
if not self.CIBsync.has_key(node) and self.Env["ClobberCIB"] == 1:
self.CIBsync[node] = 1
self.rsh.remote_py(node, "os", "system", "rm -f /var/lib/heartbeat/crm/cib.xml")
self.rsh.remote_py(node, "os", "system", "rm -f /var/lib/heartbeat/crm/cib.xml.sig")
self.rsh.remote_py(node, "os", "system", "rm -f /var/lib/heartbeat/crm/cib.xml.last")
self.rsh.remote_py(node, "os", "system", "rm -f /var/lib/heartbeat/crm/cib.xml.sig.last")
# Only install the CIB on the first node, all the other ones will pick it up from there
if self.cib_installed == 1:
return None
self.cib_installed = 1
if self.Env["CIBfilename"] == None:
self.debug("Installing Generated CIB on node %s" %(node))
warnings.filterwarnings("ignore")
cib_file=os.tmpnam()
warnings.resetwarnings()
os.system("rm -f "+cib_file)
self.debug("Creating new CIB for " + node + " in: " + cib_file)
os.system("echo \'" + self.default_cts_cib + "\' > " + cib_file)
if 0!=self.rsh.echo_cp(None, cib_file, node, "/var/lib/heartbeat/crm/cib.xml"):
raise ValueError("Can not create CIB on %s "%node)
os.system("rm -f "+cib_file)
else:
self.debug("Installing CIB (%s) on node %s" %(self.Env["CIBfilename"], node))
if 0!=self.rsh.cp(self.Env["CIBfilename"], "root@" + (self["CIBfile"]%node)):
raise ValueError("Can not scp file to %s "%node)
self.rsh.remote_py(node, "os", "system", "chown hacluster /var/lib/heartbeat/crm/cib.xml")
def prepare(self):
'''Finish the Initialization process. Prepare to test...'''
for node in self.Env["nodes"]:
self.ShouldBeStatus[node] = ""
self.StataCM(node)
def test_node_CM(self, node):
'''Report the status of the cluster manager on a given node'''
watchpats = [ ]
watchpats.append("Current ping state: (S_IDLE|S_NOT_DC)")
watchpats.append(self["Pat:They_started"]%node)
idle_watch = CTS.LogWatcher(self["LogFileName"], watchpats)
idle_watch.setwatch()
out=self.rsh.readaline(node, self["StatusCmd"]%node)
ret= (string.find(out, 'ok') != -1)
self.debug("Node %s status: %s" %(node, out))
if not ret:
if self.ShouldBeStatus[node] == self["up"]:
self.log(
"Node status for %s is %s but we think it should be %s"
%(node, self["down"], self.ShouldBeStatus[node]))
self.ShouldBeStatus[node]=self["down"]
return 0
if self.ShouldBeStatus[node] == self["down"]:
self.log(
"Node status for %s is %s but we think it should be %s: %s"
%(node, self["up"], self.ShouldBeStatus[node], out))
self.ShouldBeStatus[node]=self["up"]
# check the output first - because syslog-ng looses messages
if string.find(out, 'S_NOT_DC') != -1:
# Up and stable
return 2
if string.find(out, 'S_IDLE') != -1:
# Up and stable
return 2
# fall back to syslog-ng and wait
if not idle_watch.look():
# just up
self.debug("Warn: Node %s is unstable: %s" %(node, out))
return 1
# Up and stable
return 2
# Is the node up or is the node down
def StataCM(self, node):
'''Report the status of the cluster manager on a given node'''
if self.test_node_CM(node) > 0:
return 1
return None
# Being up and being stable is not the same question...
def node_stable(self, node):
'''Report the status of the cluster manager on a given node'''
if self.test_node_CM(node) == 2:
return 1
self.log("Warn: Node %s not stable" %(node))
return None
def cluster_stable(self, timeout=None):
watchpats = [ ]
watchpats.append("Current ping state: S_IDLE")
watchpats.append(self["Pat:DC_IDLE"])
if timeout == None:
timeout = self["DeadTime"]
idle_watch = CTS.LogWatcher(self["LogFileName"], watchpats, timeout)
idle_watch.setwatch()
any_up = 0
for node in self.Env["nodes"]:
# have each node dump its current state
if self.ShouldBeStatus[node] == self["up"]:
self.rsh.readaline(node, (self["StatusCmd"] %node) )
any_up = 1
if any_up == 0:
self.debug("Cluster is inactive")
return 1
ret = idle_watch.look()
if ret:
self.debug(ret)
return 1
self.log("Warn: Cluster Master not IDLE after %ds" % timeout)
return None
def is_node_dc(self, node, status_line=None):
rc = 0
if not status_line:
status_line = self.rsh.readaline(node, self["StatusCmd"]%node)
if not status_line:
rc = 0
elif string.find(status_line, 'S_IDLE') != -1:
rc = 1
elif string.find(status_line, 'S_INTEGRATION') != -1:
rc = 1
elif string.find(status_line, 'S_FINALIZE_JOIN') != -1:
rc = 1
elif string.find(status_line, 'S_POLICY_ENGINE') != -1:
rc = 1
elif string.find(status_line, 'S_TRANSITION_ENGINE') != -1:
rc = 1
if rc == 1:
self.debug("%s _is_ the DC" % node)
return rc
def active_resources(self, node):
(rc, output) = self.rsh.remote_py(
node, "os", "system", """/usr/sbin/crm_mon -1 | grep "Started %s" """ % node)
resources = []
for line in output:
fields = line.split()
resources.append(fields[0])
return resources
def ResourceOp(self, resource, op, node, interval=0, app="lrmadmin"):
'''
Execute an operation on a resource
'''
self.rsh.readaline(node, self["ExecuteRscOp"]
% (app, resource, op, interval))
return self.rsh.lastrc
def ResourceLocation(self, rid):
ResourceNodes = []
for node in self.Env["nodes"]:
if self.ShouldBeStatus[node] == self["up"]:
if self.ResourceOp(rid, "monitor", node) == 0:
ResourceNodes.append(node)
return ResourceNodes
def isolate_node(self, node, allowlist):
'''isolate the communication between the nodes'''
rc = self.rsh(node, self["BreakCommCmd2"]%allowlist)
if rc == 0:
return 1
else:
self.log("Could not break the communication from node: %s",node)
return None
def Configuration(self):
if self.config:
return self.config.getElementsByTagName('configuration')[0]
warnings.filterwarnings("ignore")
cib_file=os.tmpnam()
warnings.resetwarnings()
os.system("rm -f "+cib_file)
if self.Env["ClobberCIB"] == 1:
if self.Env["CIBfilename"] == None:
self.debug("Creating new CIB in: " + cib_file)
os.system("echo \'"+ self.default_cts_cib +"\' > "+ cib_file)
else:
os.system("cp "+self.Env["CIBfilename"]+" "+cib_file)
else:
if 0 != self.rsh.echo_cp(
self.Env["nodes"][0], "/var/lib/heartbeat/crm/cib.xml", None, cib_file):
raise ValueError("Can not copy file to %s, maybe permission denied"%cib_file)
self.config = parse(cib_file)
os.remove(cib_file)
return self.config.getElementsByTagName('configuration')[0]
def Resources(self):
ResourceList = []
#read resources in cib
configuration = self.Configuration()
resources = configuration.getElementsByTagName('resources')[0]
rscs = configuration.getElementsByTagName('primitive')
incs = configuration.getElementsByTagName('clone')
groups = configuration.getElementsByTagName('group')
for rsc in rscs:
if rsc in resources.childNodes:
ResourceList.append(HAResource(self,rsc))
for grp in groups:
for rsc in rscs:
if rsc in grp.childNodes:
if self.use_short_names:
resource = HAResource(self,rsc)
else:
resource = HAResource(self,rsc,grp.getAttribute('id'))
ResourceList.append(resource)
for inc in incs:
max = 0
inc_name = inc.getAttribute("id")
instance_attributes = inc.getElementsByTagName('instance_attributes')[0]
attributes = instance_attributes.getElementsByTagName('attributes')[0]
nvpairs = attributes.getElementsByTagName('nvpair')
for nvpair in nvpairs:
if nvpair.getAttribute("name") == "clone_max":
max = int(nvpair.getAttribute("value"))
inc_rsc = inc.getElementsByTagName('primitive')[0]
for i in range(0,max):
rsc = HAResource(self,inc_rsc)
rsc.inc_no = i
rsc.inc_name = inc_name
rsc.inc_max = max
if self.use_short_names:
rsc.rid = rsc.rid + ":%d"%i
else:
rsc.rid = inc_name+":"+rsc.rid + ":%d"%i
rsc.Instance = rsc.rid
ResourceList.append(rsc)
return ResourceList
def ResourceGroups(self):
GroupList = []
#read resources in cib
configuration = self.Configuration()
groups = configuration.getElementsByTagName('group')
rscs = configuration.getElementsByTagName('primitive')
for grp in groups:
group = []
GroupList.append(group)
for rsc in rscs:
if rsc in grp.childNodes:
if self.use_short_names:
resource = HAResource(self,rsc)
else:
resource = HAResource(self,rsc,grp.getAttribute('id'))
group.append(resource)
return GroupList
def Dependencies(self):
DependencyList = []
#read dependency in cib
configuration=self.Configuration()
constraints=configuration.getElementsByTagName('constraints')[0]
rsc_to_rscs=configuration.getElementsByTagName('rsc_to_rsc')
for node in rsc_to_rscs:
dependency = {}
dependency["id"]=node.getAttribute('id')
dependency["from"]=node.getAttribute('from')
dependency["to"]=node.getAttribute('to')
dependency["type"]=node.getAttribute('type')
dependency["strength"]=node.getAttribute('strength')
DependencyList.append(dependency)
return DependencyList
def find_partitions(self):
ccm_partitions = []
for node in self.Env["nodes"]:
self.debug("Retrieving partition details for %s" %node)
if self.ShouldBeStatus[node] == self["up"]:
partition = self.rsh.readaline(node, self["ParitionCmd"])
if not partition:
self.log("no partition details for %s" %node)
elif len(partition) > 2:
partition = partition[:-1]
found=0
for a_partition in ccm_partitions:
if partition == a_partition:
found = 1
if found == 0:
self.debug("Adding partition from %s: %s" %(node, partition))
ccm_partitions.append(partition)
else:
self.log("bad partition details for %s" %node)
return ccm_partitions
def HasQuorum(self, node_list):
# If we are auditing a partition, then one side will
# have quorum and the other not.
# So the caller needs to tell us which we are checking
# If no value for node_list is specified... assume all nodes
if not node_list:
node_list = self.Env["nodes"]
for node in node_list:
if self.ShouldBeStatus[node] == self["up"]:
quorum = self.rsh.readaline(node, self["QuorumCmd"])
if string.find(quorum, "1") != -1:
return 1
elif string.find(quorum, "0") != -1:
return 0
else:
self.log("WARN: Unexpected quorum test result from "+ node +":"+ quorum)
return 0
def Components(self):
complist = []
common_ignore = [
"Pending action:",
"ERROR: crm_log_message_adv:",
"ERROR: MSG: No message to dump",
"pending LRM operations at shutdown",
"Lost connection to the CIB service",
"Connection to the CIB terminated...",
"Sending message to CIB service FAILED",
"crmd: .*Action A_RECOVER .* not supported",
"ERROR: stonithd_op_result_ready: not signed on",
"send_ipc_message: IPC Channel to .* is not connected",
"unconfirmed_actions: Waiting on .* unconfirmed actions",
"cib_native_msgready: Message pending on command channel",
"crmd:.*do_exit: Performing A_EXIT_1 - forcefully exiting the CRMd",
"verify_stopped: Resource .* was active at shutdown. You may ignore this error if it is unmanaged.",
]
stonith_ignore = [
"ERROR: stonithd_signon: ",
"update_failcount: Updating failcount for child_DoFencing",
"ERROR: te_connect_stonith: Sign-in failed: triggered a retry",
]
stonith_ignore.extend(common_ignore)
complist.append(Process("ccm", 0, [
"State transition S_IDLE",
"CCM connection appears to have failed",
"crmd: .*Action A_RECOVER .* not supported",
"crmd: .*Input I_TERMINATE from do_recover",
"Exiting to recover from CCM connection failure",
"crmd:.*do_exit: Could not recover from internal error",
"crmd: .*I_ERROR.*(ccm_dispatch|crmd_cib_connection_destroy)",
# "WARN: determine_online_status: Node .* is unclean",
# "Scheduling Node .* for STONITH",
# "Executing .* fencing operation",
# "tengine_stonith_callback: .*result=0",
"State transition S_.* -> S_INTEGRATION.*input=I_NODE_JOIN",
"State transition S_STARTING -> S_PENDING",
], [], common_ignore, 1, self))
complist.append(Process("cib", 0, [
"State transition S_IDLE",
"Lost connection to the CIB service",
"Connection to the CIB terminated...",
"crmd: .*Input I_TERMINATE from do_recover",
"crmd: .*I_ERROR.*crmd_cib_connection_destroy",
"crmd:.*do_exit: Could not recover from internal error",
], [], common_ignore, 1, self))
complist.append(Process("lrmd", 0, [
"State transition S_IDLE",
"LRM Connection failed",
"crmd: .*I_ERROR.*lrm_dispatch",
"State transition S_STARTING -> S_PENDING",
".*crmd .*exited with return code 2.",
"crmd: .*Input I_TERMINATE from do_recover",
"crmd:.*do_exit: Could not recover from internal error",
], [], common_ignore, 1, self))
complist.append(Process("crmd", 0, [
# "WARN: determine_online_status: Node .* is unclean",
# "Scheduling Node .* for STONITH",
# "Executing .* fencing operation",
# "tengine_stonith_callback: .*result=0",
"State transition S_IDLE",
"State transition S_STARTING -> S_PENDING",
], [
"tengine: .*ERROR: subsystem_msg_dispatch: The server .* has left us: Shutting down...NOW",
"pengine: .*ERROR: subsystem_msg_dispatch: The server .* has left us: Shutting down...NOW",
], common_ignore, 1, self))
complist.append(Process("pengine", 1, [
"State transition S_IDLE",
".*crmd .*exited with return code 2.",
"crmd: .*Input I_TERMINATE from do_recover",
"crmd:.*do_exit: Could not recover from internal error",
], [], common_ignore, 1, self))
complist.append(Process("tengine", 1, [
"State transition S_IDLE",
".*crmd .*exited with return code 2.",
"crmd: .*Input I_TERMINATE from do_recover",
"crmd:.*do_exit: Could not recover from internal error",
], [], common_ignore, 1, self))
if self.Env["DoFencing"] == 1 :
complist.append(Process("stonithd", 0, [], [
"tengine_stonith_connection_destroy: Fencing daemon has left us",
"Attempting connection to fencing daemon",
"te_connect_stonith: Connected",
], stonith_ignore, 0, self))
# complist.append(Process("heartbeat", 0, [], [], [], None, self))
return complist
def NodeUUID(self, node):
lines = self.rsh.readlines(node, self["UUIDQueryCmd"])
for line in lines:
self.debug("UUIDLine:"+ line)
m = re.search(r'%s.+\((.+)\)' % node, line)
if m:
return m.group(1)
return ""
def StandbyStatus(self, node):
out=self.rsh.readaline(node, self["StandbyQueryCmd"]%node)
if not out:
return "off"
out = out[:-1]
self.debug("Standby result: "+out)
return out
# status == "on" : Enter Standby mode
# status == "off": Enter Active mode
def SetStandbyMode(self, node, status):
current_status = self.StandbyStatus(node)
cmd = self["StandbyCmd"] % (node, status)
ret = self.rsh(node, cmd)
return True
class HAResource(Resource):
def __init__(self, cm, node, group=None):
'''
Get information from xml node
'''
if group == None :
self.rid = str(node.getAttribute('id'))
else :
self.rid = group + ":" + str(node.getAttribute('id'))
self.rclass = str(node.getAttribute('class'))
self.rtype = str(node.getAttribute('type'))
self.inc_name = None
self.inc_no = -1
self.inc_max = -1
self.rparameters = {}
nvpairs = []
list = node.getElementsByTagName('instance_attributes')
if len(list) > 0:
attributes = list[0]
list = attributes.getElementsByTagName('attributes')
if len(list) > 0:
parameters = list[0]
nvpairs = parameters.getElementsByTagName('nvpair')
for nvpair in nvpairs:
name=nvpair.getAttribute('name')
value=nvpair.getAttribute('value')
self.rparameters[name]=value
# This should normally be called first... FIXME!
Resource.__init__(self, cm, self.rtype, self.rid)
# resources that dont need quorum will have:
# <op name="start" prereq="nothing"/>
ops = node.getElementsByTagName('op')
for op in ops:
if op.getAttribute('name') == "start" and op.getAttribute('prereq') == "nothing":
self.needs_quorum = 0
def IsRunningOn(self, nodename):
'''
This member function returns true if our resource is running
on the given node in the cluster.
We call the status operation for the resource script.
'''
rc = self.CM.ResourceOp(self.rid, "monitor", nodename)
return (rc == 0)
def RunningNodes(self):
return self.CM.ResourceLocation(self.rid)
def Start(self, nodename):
'''
This member function starts or activates the resource.
'''
return self.CM.ResourceOp(self.rid, "start", nodename)
def Stop(self, nodename):
'''
This member function stops or deactivates the resource.
'''
return self.CM.ResourceOp(self.rid, "stop", nodename)
def IsWorkingCorrectly(self, nodename):
return self.IsRunningOn(nodename)
#######################################################################
#
# A little test code...
#
# Which you are advised to completely ignore...
#
#######################################################################
if __name__ == '__main__':
pass
|