/usr/lib/python2.7/dist-packages/cts/CM_ais.py is in pacemaker 1.1.10+git20130802-1ubuntu2.4.
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 | '''CTS: Cluster Testing System: AIS dependent modules...
'''
__copyright__='''
Copyright (C) 2007 Andrew Beekhof <andrew@suse.de>
'''
#
# 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., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
import os, sys, warnings
from cts.CTSvars import *
from cts.CM_lha import crm_lha
from cts.CTS import Process
#######################################################################
#
# LinuxHA v2 dependent modules
#
#######################################################################
class crm_ais(crm_lha):
'''
The crm version 3 cluster manager class.
It implements the things we need to talk to and manipulate
crm clusters running on top of openais
'''
def __init__(self, Environment, randseed=None):
crm_lha.__init__(self, Environment, randseed=randseed)
self.update({
"Name" : "crm-ais",
"EpocheCmd" : "crm_node -e --openais",
"QuorumCmd" : "crm_node -q --openais",
"ParitionCmd" : "crm_node -p --openais",
"Pat:They_stopped" : "%s crmd.*Node %s\[.*state is now lost",
"Pat:ChildExit" : "Child process .* exited",
# Bad news Regexes. Should never occur.
"BadRegexes" : (
r" trace:",
r"error:",
r"crit:",
r"ERROR:",
r"CRIT:",
r"Shutting down...NOW",
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|warn).*Ignoring HA message.*vote.*not in our membership list",
r"pengine.*Attempting recovery of resource",
r"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":global_timer_callback",
r"Faking parameter digest creation",
r"Parameters to .* action changed:",
r"Parameters to .* changed",
r"Child process .* terminated with signal",
r"LogActions: Recover",
r"rsyslogd.* imuxsock lost .* messages from pid .* due to rate-limiting",
r"Peer is not part of our cluster",
r"We appear to be in an election loop",
r"Unknown node -> we will not deliver message",
r"crm_write_blackbox",
r"pacemakerd.*Could not connect to Cluster Configuration Database API",
r"Recieving messages from a node we think is dead",
r"share the same cluster nodeid",
r"share the same name",
#r"crm_ipc_send:.*Request .* failed",
#r"crm_ipc_send:.*Sending to .* is disabled until pending reply is recieved",
# Not inherently bad, but worth tracking
#r"No need to invoke the TE",
#r"ping.*: DEBUG: Updated connected = 0",
#r"Digest mis-match:",
r"te_graph_trigger: Transition failed: terminated",
#r"Executing .* fencing operation",
#r"fence_pcmk.* Call to fence",
#r"fence_pcmk",
r"cman killed by node",
r"Election storm",
r"stalled the FSA with pending inputs",
),
})
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 [
r"crm_mon:",
r"crmadmin:",
r"update_trace_data",
r"async_notify: strange, client not found",
r"Parse error: Ignoring unknown option .*nodename",
r"error: log_operation: Operation 'reboot' .* with device 'FencingFail' returned:",
r"Child process .* terminated with signal 9",
]
return []
def NodeUUID(self, node):
return node
def ais_components(self):
fullcomplist = {}
self.complist = []
self.common_ignore = [
"Pending action:",
"error: crm_log_message_adv:",
"error: MSG: No message to dump",
"resources were active at shutdown",
"pending LRM operations at shutdown",
"Lost connection to the CIB service",
"Connection to the CIB terminated...",
"Sending message to CIB service FAILED",
"apply_xml_diff: Diff application failed!",
"crmd.*Action A_RECOVER .* not supported",
"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.",
"error: attrd_connection_destroy: Lost connection to attrd",
"info: te_fence_node: Executing .* fencing operation",
"crm_write_blackbox:",
# "error: native_create_actions: Resource .*stonith::.* is active on 2 nodes attempting recovery",
# "error: process_pe_message: Transition .* ERRORs found during PE processing",
]
cib_ignore = [
"lrmd.*error: crm_ipc_read: Connection to stonith-ng failed",
"lrmd.*error: mainloop_gio_callback: Connection to stonith-ng.* closed",
"lrmd.*error: stonith_connection_destroy_cb: LRMD lost STONITH connection",
"lrmd.*error: stonith_connection_failed: STONITH connection failed, finalizing .* pending operations",
]
fullcomplist["cib"] = Process(self, "cib", pats = [
"State transition .* S_RECOVERY",
"Respawning .* crmd",
"Respawning .* attrd",
"error: crm_ipc_read: Connection to cib_.* failed",
"error: mainloop_gio_callback: Connection to cib_.* closed",
"Connection to the CIB terminated...",
"Child process crmd .* exited: Generic Pacemaker error",
"Child process attrd .* exited: Transport endpoint is not connected",
"crmd.*Input I_TERMINATE from do_recover",
"crmd.*I_ERROR.*crmd_cib_connection_destroy",
"crmd.*Could not recover from internal error",
], badnews_ignore = cib_ignore, common_ignore = self.common_ignore)
fullcomplist["lrmd"] = Process(self, "lrmd", pats = [
"State transition .* S_RECOVERY",
"LRM Connection failed",
"Respawning .* crmd",
"error: crm_ipc_read: Connection to lrmd failed",
"error: mainloop_gio_callback: Connection to lrmd.* closed",
"crmd.*I_ERROR.*lrm_connection_destroy",
"Child process crmd .* exited: Generic Pacemaker error",
"crmd.*Input I_TERMINATE from do_recover",
"crmd.* Could not recover from internal error",
], badnews_ignore = self.common_ignore)
fullcomplist["crmd"] = Process(self, "crmd", pats = [
# "WARN: determine_online_status: Node .* is unclean",
# "Scheduling Node .* for STONITH",
# "Executing .* fencing operation",
# Only if the node wasn't the DC: "State transition S_IDLE",
"State transition .* -> S_IDLE",
], badnews_ignore = self.common_ignore)
fullcomplist["attrd"] = Process(self, "attrd", pats = [
], badnews_ignore = self.common_ignore)
fullcomplist["pengine"] = Process(self, "pengine", dc_pats = [
"State transition .* S_RECOVERY",
"Respawning .* crmd",
"Child process crmd .* exited: Generic Pacemaker error",
"crm_ipc_read: Connection to pengine failed",
"error: mainloop_gio_callback: Connection to pengine.* closed",
"crit: pe_ipc_destroy: Connection to the Policy Engine failed",
"crmd.*I_ERROR.*save_cib_contents",
"crmd.*Input I_TERMINATE from do_recover",
"crmd.* Could not recover from internal error",
], badnews_ignore = self.common_ignore)
stonith_ignore = [
"LogActions: Recover Fencing",
"update_failcount: Updating failcount for Fencing",
"error: te_connect_stonith: Sign-in failed: triggered a retry",
"stonith_connection_failed: STONITH connection failed, finalizing .* pending operations.",
"process_lrm_event: LRM operation Fencing.* Error"
]
stonith_ignore.extend(self.common_ignore)
fullcomplist["stonith-ng"] = Process(self, "stonith-ng", process="stonithd", pats = [
"crm_ipc_read: Connection to stonith-ng failed",
"stonith_connection_destroy_cb: LRMD lost STONITH connection",
"mainloop_gio_callback: Connection to stonith-ng.* closed",
"tengine_stonith_connection_destroy: Fencing daemon connection failed",
"crmd.*stonith_api_add_notification: Callback already present",
], badnews_ignore = stonith_ignore)
vgrind = self.Env["valgrind-procs"].split()
for key in fullcomplist.keys():
if self.Env["valgrind-tests"]:
if key in vgrind:
# Processes running under valgrind can't be shot with "killall -9 processname"
self.log("Filtering %s from the component list as it is being profiled by valgrind" % key)
continue
if key == "stonith-ng" and not self.Env["DoFencing"]:
continue
self.complist.append(fullcomplist[key])
#self.complist = [ fullcomplist["pengine"] ]
return self.complist
class crm_whitetank(crm_ais):
'''
The crm version 3 cluster manager class.
It implements the things we need to talk to and manipulate
crm clusters running on top of openais
'''
def __init__(self, Environment, randseed=None):
crm_ais.__init__(self, Environment, randseed=randseed)
self.update({
"Name" : "crm-whitetank",
"StartCmd" : "service openais start",
"StopCmd" : "service openais stop",
"Pat:We_stopped" : "%s.*openais.*pcmk_shutdown: Shutdown complete",
"Pat:They_stopped" : "%s crmd.*Node %s\[.*state is now lost",
"Pat:They_dead" : "openais:.*Node %s is now: lost",
"Pat:ChildKilled" : "%s openais.*Child process %s terminated with signal 9",
"Pat:ChildRespawn" : "%s openais.*Respawning failed child process: %s",
"Pat:ChildExit" : "Child process .* exited",
})
def Components(self):
self.ais_components()
aisexec_ignore = [
"error: ais_dispatch: Receiving message .* failed",
"crmd.*I_ERROR.*crmd_cib_connection_destroy",
"cib.*error: cib_cs_destroy: AIS connection terminated",
#"crmd.*error: crm_ais_destroy: AIS connection terminated",
"crmd.* Could not recover from internal error",
"crmd.*I_TERMINATE.*do_recover",
"attrd.*attrd_cs_destroy: Lost connection to Corosync service!",
"stonithd.*error: Corosync connection terminated",
]
aisexec_ignore.extend(self.common_ignore)
self.complist.append(Process(self, "aisexec", pats = [
"error: ais_dispatch: AIS connection failed",
"crmd.*error: do_exit: Could not recover from internal error",
"pengine.*Scheduling Node .* for STONITH",
"stonithd.*requests a STONITH operation RESET on node",
"stonithd.*Succeeded to STONITH the node",
], badnews_ignore = aisexec_ignore))
class crm_cs_v0(crm_ais):
'''
The crm version 3 cluster manager class.
It implements the things we need to talk to and manipulate
crm clusters running against version 0 of our plugin
'''
def __init__(self, Environment, randseed=None):
crm_ais.__init__(self, Environment, randseed=randseed)
self.update({
"Name" : "crm-plugin-v0",
"StartCmd" : "service corosync start",
"StopCmd" : "service corosync stop",
# The next pattern is too early
# "Pat:We_stopped" : "%s.*Service engine unloaded: Pacemaker Cluster Manager",
# The next pattern would be preferred, but it doesn't always come out
# "Pat:We_stopped" : "%s.*Corosync Cluster Engine exiting with status",
"Pat:We_stopped" : "%s.*Service engine unloaded: corosync cluster quorum service",
"Pat:They_stopped" : "%s crmd.*Node %s\[.*state is now lost",
"Pat:They_dead" : "corosync:.*Node %s is now: lost",
"Pat:ChildKilled" : "%s corosync.*Child process %s terminated with signal 9",
"Pat:ChildRespawn" : "%s corosync.*Respawning failed child process: %s",
})
def Components(self):
self.ais_components()
corosync_ignore = [
r"error: pcmk_cpg_dispatch: Connection to the CPG API failed: Library error",
r"pacemakerd.*error: pcmk_child_exit: Child process .* exited",
r"cib.*error: cib_cs_destroy: Corosync connection lost",
r"attrd.*error: attrd_cib_connection_destroy: Connection to the CIB terminated",
r"stonith-ng.*error: stonith_peer_cs_destroy: Corosync connection terminated",
r"error: pcmk_child_exit: Child process cib .* exited: Invalid argument",
r"error: pcmk_child_exit: Child process attrd .* exited: Transport endpoint is not connected",
r"error: pcmk_child_exit: Child process crmd .* exited: Link has been severed",
r"lrmd.*error: crm_ipc_read: Connection to stonith-ng failed",
r"lrmd.*error: mainloop_gio_callback: Connection to stonith-ng.* closed",
r"lrmd.*error: stonith_connection_destroy_cb: LRMD lost STONITH connection",
r"crmd.*do_state_transition: State transition .* S_RECOVERY",
r"crmd.*error: do_log: FSA: Input I_ERROR",
r"crmd.*error: do_log: FSA: Input I_TERMINATE",
r"crmd.*error: pcmk_cman_dispatch: Connection to cman failed",
r"crmd.*error: crmd_fast_exit: Could not recover from internal error",
r"error: crm_ipc_read: Connection to cib_shm failed",
r"error: mainloop_gio_callback: Connection to cib_shm.* closed",
]
self.complist.append(Process(self, "corosync", pats = [
r"pacemakerd.*error: cfg_connection_destroy: Connection destroyed",
r"pacemakerd.*error: mcp_cpg_destroy: Connection destroyed",
r"attrd_cs_destroy: Lost connection to Corosync service!",
r"stonith_peer_cs_destroy: Corosync connection terminated",
r"cib_cs_destroy: Corosync connection lost! Exiting.",
r"crmd_(cs|quorum)_destroy: connection terminated",
r"pengine.*Scheduling Node .* for STONITH",
r"tengine_stonith_notify: Peer .* was terminated .*: OK",
], badnews_ignore = corosync_ignore, common_ignore = self.common_ignore))
return self.complist
class crm_cs_v1(crm_cs_v0):
'''
The crm version 3 cluster manager class.
It implements the things we need to talk to and manipulate
crm clusters running on top of version 1 of our plugin
'''
def __init__(self, Environment, randseed=None):
crm_cs_v0.__init__(self, Environment, randseed=randseed)
self.update({
"Name" : "crm-plugin-v1",
"StartCmd" : "service corosync start && service pacemaker start",
"StopCmd" : "service pacemaker stop; service corosync stop",
"EpocheCmd" : "crm_node -e",
"QuorumCmd" : "crm_node -q",
"ParitionCmd" : "crm_node -p",
"Pat:We_stopped" : "%s.*Service engine unloaded: corosync cluster quorum service",
"Pat:They_stopped" : "%s crmd.*Node %s\[.*state is now lost",
"Pat:They_dead" : "crmd.*Node %s\[.*state is now lost",
"Pat:ChildKilled" : "%s pacemakerd.*Child process %s terminated with signal 9",
"Pat:ChildRespawn" : "%s pacemakerd.*Respawning failed child process: %s",
})
class crm_mcp(crm_cs_v0):
'''
The crm version 4 cluster manager class.
It implements the things we need to talk to and manipulate
crm clusters running on top of native corosync (no plugins)
'''
def __init__(self, Environment, randseed=None):
crm_cs_v0.__init__(self, Environment, randseed=randseed)
self.update({
"Name" : "crm-mcp",
"StartCmd" : "service corosync start && service pacemaker start",
"StopCmd" : "service pacemaker stop; service corosync stop",
"EpocheCmd" : "crm_node -e",
"QuorumCmd" : "crm_node -q",
"ParitionCmd" : "crm_node -p",
# Close enough... "Corosync Cluster Engine exiting normally" isn't printed
# reliably and there's little interest in doing anything it
"Pat:We_stopped" : "%s.*Unloading all Corosync service engines",
"Pat:They_stopped" : "%s crmd.*Node %s\[.*state is now lost",
"Pat:They_dead" : "crmd.*Node %s\[.*state is now lost",
"Pat:ChildKilled" : "%s pacemakerd.*Child process %s terminated with signal 9",
"Pat:ChildRespawn" : "%s pacemakerd.*Respawning failed child process: %s",
"Pat:InfraUp" : "%s corosync.*Initializing transport",
"Pat:PacemakerUp" : "%s pacemakerd.*Starting Pacemaker",
})
class crm_cman(crm_cs_v0):
'''
The crm version 3 cluster manager class.
It implements the things we need to talk to and manipulate
crm clusters running on top of openais
'''
def __init__(self, Environment, randseed=None):
crm_cs_v0.__init__(self, Environment, randseed=randseed)
self.update({
"Name" : "crm-cman",
"StartCmd" : "service pacemaker start",
"StopCmd" : "service pacemaker stop",
"EpocheCmd" : "crm_node -e --cman",
"QuorumCmd" : "crm_node -q --cman",
"ParitionCmd" : "crm_node -p --cman",
"Pat:We_stopped" : "%s.*Unloading all Corosync service engines",
"Pat:They_stopped" : "%s crmd.*Node %s\[.*state is now lost",
"Pat:They_dead" : "crmd.*Node %s\[.*state is now lost",
"Pat:ChildKilled" : "%s pacemakerd.*Child process %s terminated with signal 9",
"Pat:ChildRespawn" : "%s pacemakerd.*Respawning failed child process: %s",
})
|