diff --git a/cts/cts-fencing.in b/cts/cts-fencing.in index f43640b4b2..2074f8739f 100644 --- a/cts/cts-fencing.in +++ b/cts/cts-fencing.in @@ -1,1681 +1,1710 @@ #!@PYTHON@ """ Regression tests for Pacemaker's fencer """ __copyright__ = "Copyright 2012-2022 the Pacemaker project contributors" __license__ = "GNU General Public License version 2 or later (GPLv2+) WITHOUT ANY WARRANTY" import io import os import psutil import re import sys import subprocess import shlex import time import tempfile import signal # Where to find test binaries # Prefer the source tree if available BUILD_DIR = "@abs_top_builddir@" SCHEMA_DIR = "@CRM_SCHEMA_DIRECTORY@" COROSYNC_CONF = "@PCMK__COROSYNC_CONF@" TEST_DIR = sys.path[0] AUTOGEN_COROSYNC_TEMPLATE = """ totem { version: 2 cluster_name: cts-fencing crypto_cipher: none crypto_hash: none transport: udp } nodelist { node { nodeid: 1 name: %s ring0_addr: 127.0.0.1 } } logging { debug: off to_syslog: no to_stderr: no to_logfile: yes logfile: %s } """ # These values must be kept in sync with include/crm/crm.h class CrmExit(object): OK = 0 ERROR = 1 INVALID_PARAM = 2 UNIMPLEMENT_FEATURE = 3 INSUFFICIENT_PRIV = 4 NOT_INSTALLED = 5 NOT_CONFIGURED = 6 NOT_RUNNING = 7 USAGE = 64 DATAERR = 65 NOINPUT = 66 NOUSER = 67 NOHOST = 68 UNAVAILABLE = 69 SOFTWARE = 70 OSERR = 71 OSFILE = 72 CANTCREAT = 73 IOERR = 74 TEMPFAIL = 75 PROTOCOL = 76 NOPERM = 77 CONFIG = 78 FATAL = 100 PANIC = 101 DISCONNECT = 102 SOLO = 103 DIGEST = 104 NOSUCH = 105 QUORUM = 106 UNSAFE = 107 EXISTS = 108 MULTIPLE = 109 OLD = 110 TIMEOUT = 124 MAX = 255 def update_path(): """ Set the PATH environment variable appropriately for the tests """ new_path = os.environ['PATH'] if os.path.exists("%s/cts-fencing.in" % TEST_DIR): print("Running tests from the source tree: %s (%s)" % (BUILD_DIR, TEST_DIR)) # For pacemaker-fenced and cts-fence-helper new_path = "%s/daemons/fenced:%s" % (BUILD_DIR, new_path) new_path = "%s/tools:%s" % (BUILD_DIR, new_path) # For stonith_admin new_path = "%s/cts/support:%s" % (BUILD_DIR, new_path) # For cts-support else: print("Running tests from the install tree: @CRM_DAEMON_DIR@ (not %s)" % TEST_DIR) # For pacemaker-fenced, cts-fence-helper, and cts-support new_path = "@CRM_DAEMON_DIR@:%s" % (new_path) print('Using PATH="{}"'.format(new_path)) os.environ['PATH'] = new_path def find_validator(rng_file): if os.access("/usr/bin/xmllint", os.X_OK): if rng_file == None: return ["xmllint", "-"] else: return ["xmllint", "--relaxng", rng_file, "-"] else: return None def rng_directory(): if "PCMK_schema_directory" in os.environ: return os.environ["PCMK_schema_directory"] elif os.path.exists("%s/cts-fencing.in" % TEST_DIR): return "xml" else: return SCHEMA_DIR def pipe_communicate(pipes, check_stderr=False, stdin=None): """ Get text output from pipes """ if stdin is not None: pipe_outputs = pipes.communicate(input=stdin.encode()) else: pipe_outputs = pipes.communicate() output = pipe_outputs[0].decode(sys.stdout.encoding) if check_stderr: output = output + pipe_outputs[1].decode(sys.stderr.encoding) return output def output_from_command(command): """ Execute command and return its standard output """ test = subprocess.Popen(shlex.split(command), stdout=subprocess.PIPE) test.wait() return pipe_communicate(test).split("\n") def localname(): """ Return the uname of the local host """ our_uname = output_from_command("uname -n") if our_uname: our_uname = our_uname[0] else: our_uname = "localhost" return our_uname def killall(process_names=[], terminate=False): """ Kill all instances of every process in a list """ if not process_names: return procs = [] for proc in psutil.process_iter(["name"]): if proc.info["name"] in process_names: procs.append(proc) if terminate: for proc in procs: proc.terminate() gone, alive = psutil.wait_procs(procs, timeout=3) procs = alive for proc in procs: proc.kill() def is_proc_running(process_name): """ Check whether a process with a given name is running """ for proc in psutil.process_iter(["name"]): if proc.info["name"] == process_name: return True return False def exit_if_proc_running(process_name): """ Exit with error if a given process is running """ if is_proc_running(process_name): print("Error: %s is already running!" % process_name) print("Run %s only when the cluster is stopped." % sys.argv[0]) sys.exit(CrmExit.ERROR) class TestError(Exception): """ Base class for exceptions in this module """ pass class ExitCodeError(TestError): """ Exception raised when command exit status is unexpected """ def __init__(self, exit_code): self.exit_code = exit_code def __str__(self): return repr(self.exit_code) class OutputNotFoundError(TestError): """ Exception raised when command output does not contain wanted string """ def __init__(self, output): self.output = output def __str__(self): return repr(self.output) class OutputFoundError(TestError): """ Exception raised when command output contains unwanted string """ def __init__(self, output): self.output = output def __str__(self): return repr(self.output) class XmlValidationError(TestError): """ Exception raised when xmllint fails """ def __init__(self, output): self.output = output def __str__(self): return repr(self.output) class Test(object): """ Executor for a single test """ def __init__(self, name, description, verbose=0, with_cpg=0, timeout=2, force_wait=0, logdir="/tmp"): self.name = name self.description = description self.cmds = [] self.verbose = verbose self.timeout = timeout self.force_wait = force_wait self.logpath = os.path.join(logdir, "pacemaker-fenced.log") self.result_txt = "" self.cmd_tool_output = "" self.result_exitcode = CrmExit.OK if with_cpg: self.stonith_options = "-c" self.enable_corosync = 1 else: self.stonith_options = "-s" self.enable_corosync = 0 self.stonith_process = None self.stonith_output = "" self.stonith_patterns = [] self.negative_stonith_patterns = [] self.executed = 0 def __new_cmd(self, cmd, args, exitcode, stdout_match="", no_wait=0, stdout_negative_match="", kill=None, validate=True, check_rng=True, check_stderr=True): """ Add a command to be executed as part of this test """ self.cmds.append( { "cmd" : cmd, "kill" : kill, "args" : args, "expected_exitcode" : exitcode, "stdout_match" : stdout_match, "stdout_negative_match" : stdout_negative_match, "no_wait" : no_wait, "validate" : validate, "check_rng" : check_rng, "check_stderr" : check_stderr, } ) def start_environment(self): """ Prepare the host for executing a test """ # Make sure we are in full control killall(["pacemakerd", "pacemaker-fenced"]) if self.verbose: self.stonith_options = self.stonith_options + " -V" print("Starting pacemaker-fenced with %s" % self.stonith_options) if os.path.exists(self.logpath): os.remove(self.logpath) cmd = "pacemaker-fenced %s -l %s" % (self.stonith_options, self.logpath) self.stonith_process = subprocess.Popen(shlex.split(cmd)) logfile = None init_time = time.time() update_time = init_time while True: time.sleep(0.1) if self.force_wait == 0 and logfile == None \ and os.path.exists(self.logpath): logfile = io.open(self.logpath, 'rt', encoding = "ISO-8859-1") if self.force_wait == 0 and logfile != None: for line in logfile.readlines(): if "successfully started" in line: return now = time.time() if self.timeout > 0 and (now - init_time) >= self.timeout: if self.force_wait == 0: print("\tDaemon pacemaker-fenced doesn't seem to have been initialized within %fs." "\n\tConsider specifying a longer '--timeout' value." %(self.timeout)) return if self.verbose and (now - update_time) >= 5: print("Waiting for pacemaker-fenced to be initialized: %fs ..." %(now - init_time)) update_time = now def clean_environment(self): """ Clean up the host after executing a test """ if self.stonith_process: if self.stonith_process.poll() == None: self.stonith_process.terminate() self.stonith_process.wait() else: return_code = { getattr(signal, _signame): _signame for _signame in dir(signal) if _signame.startswith('SIG') and not _signame.startswith("SIG_") }.get(-self.stonith_process.returncode, "RET=%d" % (self.stonith_process.returncode)) msg = "FAILURE - '%s' failed. pacemaker-fenced abnormally exited during test (%s)." self.result_txt = msg % (self.name, return_code) self.result_exitcode = CrmExit.ERROR self.stonith_output = "" self.stonith_process = None # the default for utf-8 encoding would error out if e.g. memory corruption # makes fenced output any kind of 8 bit value - while still interesting # for debugging and we'd still like the regression-test to go over the # full set of test-cases logfile = io.open(self.logpath, 'rt', encoding = "ISO-8859-1") for line in logfile.readlines(): self.stonith_output = self.stonith_output + line if self.verbose: print("Daemon Output Start") print(self.stonith_output) print("Daemon Output End") def add_stonith_log_pattern(self, pattern): """ Add a log pattern to expect from this test """ self.stonith_patterns.append(pattern) def add_stonith_neg_log_pattern(self, pattern): """ Add a log pattern that should not occur with this test """ self.negative_stonith_patterns.append(pattern) def add_cmd(self, cmd, args, validate=True, check_rng=True, check_stderr=True): """ Add a simple command to be executed as part of this test """ self.__new_cmd(cmd, args, CrmExit.OK, "", validate=validate, check_rng=check_rng, check_stderr=check_stderr) def add_cmd_no_wait(self, cmd, args): """ Add a simple command to be executed (without waiting) as part of this test """ self.__new_cmd(cmd, args, CrmExit.OK, "", 1) def add_cmd_check_stdout(self, cmd, args, match, no_match=""): """ Add a simple command with expected output to be executed as part of this test """ self.__new_cmd(cmd, args, CrmExit.OK, match, 0, no_match) def add_expected_fail_cmd(self, cmd, args, exitcode=CrmExit.ERROR): """ Add a command to be executed as part of this test and expected to fail """ self.__new_cmd(cmd, args, exitcode, "") def get_exitcode(self): """ Return the exit status of the last test execution """ return self.result_exitcode def print_result(self, filler): """ Print the result of the last test execution """ print("%s%s" % (filler, self.result_txt)) def run_cmd(self, args): """ Execute a command as part of this test """ cmd = shlex.split(args['args']) cmd.insert(0, args['cmd']) if self.verbose: print("\n\nRunning: "+" ".join(cmd)) test = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) if args['kill']: if self.verbose: print("Also running: "+args['kill']) subprocess.Popen(shlex.split(args['kill'])) if args['no_wait'] == 0: test.wait() else: return CrmExit.OK output = pipe_communicate(test, check_stderr=args['check_stderr']) if self.verbose: print(output) if test.returncode != args['expected_exitcode']: raise ExitCodeError(test.returncode) if (args['stdout_match'] != "" and re.search(args['stdout_match'], output) is None): raise OutputNotFoundError(output) if (args['stdout_negative_match'] != "" and re.search(args['stdout_negative_match'], output) is not None): raise OutputFoundError(output) if args['validate']: if args['check_rng']: rng_file = rng_directory() + "/api/api-result.rng" else: rng_file = None cmd = find_validator(rng_file) if not cmd: return if self.verbose: print("\nRunning: "+" ".join(cmd)) validator = subprocess.Popen(cmd, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE) output = pipe_communicate(validator, check_stderr=True, stdin=output) if self.verbose: print(output) if validator.returncode != 0: raise XmlValidationError(output) def count_negative_matches(self, outline): """ Return 1 if a line matches patterns that shouldn't have occurred """ count = 0 for line in self.negative_stonith_patterns: if outline.count(line): count = 1 if self.verbose: print("This pattern should not have matched = '%s" % (line)) return count def match_stonith_patterns(self): """ Check test output for expected patterns """ negative_matches = 0 cur = 0 pats = self.stonith_patterns total_patterns = len(self.stonith_patterns) if len(self.stonith_patterns) == 0 and len(self.negative_stonith_patterns) == 0: return for line in self.stonith_output.split("\n"): negative_matches = negative_matches + self.count_negative_matches(line) if len(pats) == 0: continue cur = -1 for pat in pats: cur = cur + 1 if line.count(pats[cur]): del pats[cur] break if len(pats) > 0 or negative_matches: if self.verbose: for pat in pats: print("Pattern Not Matched = '%s'" % pat) msg = "FAILURE - '%s' failed. %d patterns out of %d not matched. %d negative matches." self.result_txt = msg % (self.name, len(pats), total_patterns, negative_matches) self.result_exitcode = CrmExit.ERROR def set_error(self, step, cmd): """ Record failure of this test """ msg = "FAILURE - '%s' failed at step %d. Command: %s %s" self.result_txt = msg % (self.name, step, cmd['cmd'], cmd['args']) self.result_exitcode = CrmExit.ERROR def run(self): """ Execute this test. """ res = 0 i = 1 self.start_environment() if self.verbose: print("\n--- START TEST - %s" % self.name) self.result_txt = "SUCCESS - '%s'" % (self.name) self.result_exitcode = CrmExit.OK for cmd in self.cmds: try: self.run_cmd(cmd) except ExitCodeError as e: print("Step %d FAILED - command returned %s, expected %d" % (i, e, cmd['expected_exitcode'])) self.set_error(i, cmd); break except OutputNotFoundError as e: print("Step %d FAILED - '%s' was not found in command output: %s" % (i, cmd['stdout_match'], e)) self.set_error(i, cmd); break except OutputFoundError as e: print("Step %d FAILED - '%s' was found in command output: %s" % (i, cmd['stdout_negative_match'], e)) self.set_error(i, cmd); break except XmlValidationError as e: print("Step %d FAILED - xmllint failed: %s" % (i, e)) self.set_error(i, cmd); break if self.verbose: print("Step %d SUCCESS" % (i)) i = i + 1 self.clean_environment() if self.result_exitcode == CrmExit.OK: self.match_stonith_patterns() print(self.result_txt) if self.verbose: print("--- END TEST - %s\n" % self.name) self.executed = 1 return res class Tests(object): """ Collection of all fencing regression tests """ def __init__(self, verbose=0, timeout=2, force_wait=0, logdir="/tmp"): self.tests = [] self.verbose = verbose self.timeout = timeout self.force_wait = force_wait self.logdir = logdir self.autogen_corosync_cfg = not os.path.exists(COROSYNC_CONF) def new_test(self, name, description, with_cpg=0): """ Create a named test """ test = Test(name, description, self.verbose, with_cpg, self.timeout, self.force_wait, self.logdir) self.tests.append(test) return test def print_list(self): """ List all registered tests """ print("\n==== %d TESTS FOUND ====" % (len(self.tests))) print("%35s - %s" % ("TEST NAME", "TEST DESCRIPTION")) print("%35s - %s" % ("--------------------", "--------------------")) for test in self.tests: print("%35s - %s" % (test.name, test.description)) print("==== END OF LIST ====\n") def start_corosync(self): """ Start the corosync process """ if self.verbose: print("Starting corosync") test = subprocess.Popen("corosync", stdout=subprocess.PIPE) test.wait() time.sleep(10) def run_single(self, name): """ Run a single named test """ for test in self.tests: if test.name == name: test.run() break def run_tests_matching(self, pattern): """ Run all tests whose name matches a pattern """ for test in self.tests: if test.name.count(pattern) != 0: test.run() def run_cpg_only(self): """ Run all corosync-enabled tests """ for test in self.tests: if test.enable_corosync: test.run() def run_no_cpg(self): """ Run all standalone tests """ for test in self.tests: if not test.enable_corosync: test.run() def run_tests(self): """ Run all tests """ for test in self.tests: test.run() def exit(self): """ Exit (with error status code if any test failed) """ for test in self.tests: if test.executed == 0: continue if test.get_exitcode() != CrmExit.OK: sys.exit(CrmExit.ERROR) sys.exit(CrmExit.OK) def print_results(self): """ Print summary of results of executed tests """ failures = 0 success = 0 print("\n\n======= FINAL RESULTS ==========") print("\n--- FAILURE RESULTS:") for test in self.tests: if test.executed == 0: continue if test.get_exitcode() != CrmExit.OK: failures = failures + 1 test.print_result(" ") else: success = success + 1 if failures == 0: print(" None") print("\n--- TOTALS\n Pass:%d\n Fail:%d\n" % (success, failures)) def build_api_sanity_tests(self): """ Register tests to verify basic API usage """ verbose_arg = "" if self.verbose: verbose_arg = "-V" test = self.new_test("standalone_low_level_api_test", "Sanity test client api in standalone mode.") test.add_cmd("cts-fence-helper", "-t %s" % (verbose_arg), validate=False) test = self.new_test("cpg_low_level_api_test", "Sanity test client api using mainloop and cpg.", 1) test.add_cmd("cts-fence-helper", "-m %s" % (verbose_arg), validate=False) def build_custom_timeout_tests(self): """ Register tests to verify custom timeout usage """ # custom timeout without topology test = self.new_test("cpg_custom_timeout_1", "Verify per device timeouts work as expected without using topology.", 1) test.add_cmd('stonith_admin', '--output-as=xml -R false1 -a fence_dummy -o "mode=fail" -o "pcmk_host_list=node1 node2 node3"') test.add_cmd('stonith_admin', '--output-as=xml -R true1 -a fence_dummy -o "mode=pass" -o "pcmk_host_list=node3" -o "pcmk_off_timeout=1"') test.add_cmd('stonith_admin', '--output-as=xml -R false2 -a fence_dummy -o "mode=fail" -o "pcmk_host_list=node3" -o "pcmk_off_timeout=4"') test.add_cmd("stonith_admin", "--output-as=xml -F node3 -t 5") # timeout is 5+1+4 = 10 test.add_stonith_log_pattern("Total timeout set to 12") # custom timeout _WITH_ topology test = self.new_test("cpg_custom_timeout_2", "Verify per device timeouts work as expected _WITH_ topology.", 1) test.add_cmd('stonith_admin', '--output-as=xml -R false1 -a fence_dummy -o "mode=fail" -o "pcmk_host_list=node1 node2 node3"') test.add_cmd('stonith_admin', '--output-as=xml -R true1 -a fence_dummy -o "mode=pass" -o "pcmk_host_list=node3" -o "pcmk_off_timeout=1"') test.add_cmd('stonith_admin', '--output-as=xml -R false2 -a fence_dummy -o "mode=fail" -o "pcmk_host_list=node3" -o "pcmk_off_timeout=4000"') test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 1 -v false1") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 2 -v true1") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 3 -v false2") test.add_cmd("stonith_admin", "--output-as=xml -F node3 -t 5") # timeout is 5+1+4000 = 4006 test.add_stonith_log_pattern("Total timeout set to 4807") def build_fence_merge_tests(self): """ Register tests to verify when fence operations should be merged """ ### Simple test that overlapping fencing operations get merged test = self.new_test("cpg_custom_merge_single", "Verify overlapping identical fencing operations are merged, no fencing levels used.", 1) test.add_cmd("stonith_admin", "--output-as=xml -R false1 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node3\" ") test.add_cmd("stonith_admin", "--output-as=xml -R false2 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node3\"") test.add_cmd_no_wait("stonith_admin", "--output-as=xml -F node3 -t 10") test.add_cmd("stonith_admin", "--output-as=xml -F node3 -t 10") ### one merger will happen test.add_stonith_log_pattern("Merging fencing action 'off' targeting node3 originating from client") ### the pattern below signifies that both the original and duplicate operation completed test.add_stonith_log_pattern("Operation 'off' targeting node3 by ") test.add_stonith_log_pattern("Operation 'off' targeting node3 by ") ### Test that multiple mergers occur test = self.new_test("cpg_custom_merge_multiple", "Verify multiple overlapping identical fencing operations are merged", 1) test.add_cmd("stonith_admin", "--output-as=xml -R false1 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"delay=2\" -o \"pcmk_host_list=node3\" ") test.add_cmd("stonith_admin", "--output-as=xml -R false2 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node3\"") test.add_cmd_no_wait("stonith_admin", "--output-as=xml -F node3 -t 10") test.add_cmd_no_wait("stonith_admin", "--output-as=xml -F node3 -t 10") test.add_cmd_no_wait("stonith_admin", "--output-as=xml -F node3 -t 10") test.add_cmd_no_wait("stonith_admin", "--output-as=xml -F node3 -t 10") test.add_cmd("stonith_admin", "--output-as=xml -F node3 -t 10") ### 4 mergers should occur test.add_stonith_log_pattern("Merging fencing action 'off' targeting node3 originating from client") test.add_stonith_log_pattern("Merging fencing action 'off' targeting node3 originating from client") test.add_stonith_log_pattern("Merging fencing action 'off' targeting node3 originating from client") test.add_stonith_log_pattern("Merging fencing action 'off' targeting node3 originating from client") ### the pattern below signifies that both the original and duplicate operation completed test.add_stonith_log_pattern("Operation 'off' targeting node3 by ") test.add_stonith_log_pattern("Operation 'off' targeting node3 by ") test.add_stonith_log_pattern("Operation 'off' targeting node3 by ") test.add_stonith_log_pattern("Operation 'off' targeting node3 by ") test.add_stonith_log_pattern("Operation 'off' targeting node3 by ") ### Test that multiple mergers occur with topologies used test = self.new_test("cpg_custom_merge_with_topology", "Verify multiple overlapping identical fencing operations are merged with fencing levels.", 1) test.add_cmd("stonith_admin", "--output-as=xml -R false1 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node3\" ") test.add_cmd("stonith_admin", "--output-as=xml -R false2 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node3\"") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 1 -v false1") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 1 -v false2") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 2 -v true1") test.add_cmd_no_wait("stonith_admin", "--output-as=xml -F node3 -t 10") test.add_cmd_no_wait("stonith_admin", "--output-as=xml -F node3 -t 10") test.add_cmd_no_wait("stonith_admin", "--output-as=xml -F node3 -t 10") test.add_cmd_no_wait("stonith_admin", "--output-as=xml -F node3 -t 10") test.add_cmd("stonith_admin", "--output-as=xml -F node3 -t 10") ### 4 mergers should occur test.add_stonith_log_pattern("Merging fencing action 'off' targeting node3 originating from client") test.add_stonith_log_pattern("Merging fencing action 'off' targeting node3 originating from client") test.add_stonith_log_pattern("Merging fencing action 'off' targeting node3 originating from client") test.add_stonith_log_pattern("Merging fencing action 'off' targeting node3 originating from client") ### the pattern below signifies that both the original and duplicate operation completed test.add_stonith_log_pattern("Operation 'off' targeting node3 by ") test.add_stonith_log_pattern("Operation 'off' targeting node3 by ") test.add_stonith_log_pattern("Operation 'off' targeting node3 by ") test.add_stonith_log_pattern("Operation 'off' targeting node3 by ") test.add_stonith_log_pattern("Operation 'off' targeting node3 by ") def build_fence_no_merge_tests(self): """ Register tests to verify when fence operations should not be merged """ test = self.new_test("cpg_custom_no_merge", "Verify differing fencing operations are not merged", 1) test.add_cmd("stonith_admin", "--output-as=xml -R false1 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node3 node2\"") test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node3 node2\" ") test.add_cmd("stonith_admin", "--output-as=xml -R false2 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node3 node2\"") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 1 -v false1") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 1 -v false2") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 2 -v true1") test.add_cmd_no_wait("stonith_admin", "--output-as=xml -F node2 -t 10") test.add_cmd("stonith_admin", "--output-as=xml -F node3 -t 10") test.add_stonith_neg_log_pattern("Merging fencing action 'off' targeting node3 originating from client") def build_standalone_tests(self): """ Register a grab bag of tests that can be executed in standalone or corosync mode """ test_types = [ { "prefix" : "standalone", "use_cpg" : 0, }, { "prefix" : "cpg", "use_cpg" : 1, }, ] # test what happens when all devices timeout for test_type in test_types: test = self.new_test("%s_fence_multi_device_failure" % test_type["prefix"], "Verify that all devices timeout, a fencing failure is returned.", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R false1 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R false2 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R false3 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node1 node2 node3\"") if test_type["use_cpg"] == 1: test.add_expected_fail_cmd("stonith_admin", "--output-as=xml -F node3 -t 2", CrmExit.TIMEOUT) test.add_stonith_log_pattern("Total timeout set to 7") else: test.add_expected_fail_cmd("stonith_admin", "--output-as=xml -F node3 -t 2", CrmExit.ERROR) test.add_stonith_log_pattern("targeting node3 using false1 returned ") test.add_stonith_log_pattern("targeting node3 using false2 returned ") test.add_stonith_log_pattern("targeting node3 using false3 returned ") # test what happens when multiple devices can fence a node, but the first device fails. for test_type in test_types: test = self.new_test("%s_fence_device_failure_rollover" % test_type["prefix"], "Verify that when one fence device fails for a node, the others are tried.", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R false1 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R false2 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -F node3 -t 5") if test_type["use_cpg"] == 1: test.add_stonith_log_pattern("Total timeout set to 18") # test what happens when we try to use a missing fence-agent. for test_type in test_types: test = self.new_test("%s_fence_missing_agent" % test_type["prefix"], "Verify proper error-handling when using a non-existent fence-agent.", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_missing -o \"mode=pass\" -o \"pcmk_host_list=node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R true2 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node2\"") test.add_expected_fail_cmd("stonith_admin", "--output-as=xml -F node3 -t 5", CrmExit.NOSUCH) test.add_cmd("stonith_admin", "--output-as=xml -F node2 -t 5") # simple topology test for one device for test_type in test_types: if test_type["use_cpg"] == 0: continue test = self.new_test("%s_topology_simple" % test_type["prefix"], "Verify all fencing devices at a level are used.", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R true -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 1 -v true") test.add_cmd("stonith_admin", "--output-as=xml -F node3 -t 5") test.add_stonith_log_pattern("Total timeout set to 6") test.add_stonith_log_pattern("targeting node3 using true returned 0") # add topology, delete topology, verify fencing still works for test_type in test_types: if test_type["use_cpg"] == 0: continue test = self.new_test("%s_topology_add_remove" % test_type["prefix"], "Verify fencing occurrs after all topology levels are removed", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R true -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 1 -v true") test.add_cmd("stonith_admin", "--output-as=xml -d node3 -i 1") test.add_cmd("stonith_admin", "--output-as=xml -F node3 -t 5") test.add_stonith_log_pattern("Total timeout set to 6") test.add_stonith_log_pattern("targeting node3 using true returned 0") # test what happens when the first fencing level has multiple devices. for test_type in test_types: if test_type["use_cpg"] == 0: continue test = self.new_test("%s_topology_device_fails" % test_type["prefix"], "Verify if one device in a level fails, the other is tried.", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R false -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R true -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 1 -v false") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 2 -v true") test.add_cmd("stonith_admin", "--output-as=xml -F node3 -t 20") test.add_stonith_log_pattern("Total timeout set to 48") test.add_stonith_log_pattern("targeting node3 using false returned 1") test.add_stonith_log_pattern("targeting node3 using true returned 0") # test what happens when the first fencing level fails. for test_type in test_types: if test_type["use_cpg"] == 0: continue test = self.new_test("%s_topology_multi_level_fails" % test_type["prefix"], "Verify if one level fails, the next leve is tried.", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R true2 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R true3 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R true4 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R false1 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R false2 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 1 -v false1") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 1 -v true1") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 2 -v true2") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 2 -v false2") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 3 -v true3") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 3 -v true4") test.add_cmd("stonith_admin", "--output-as=xml -F node3 -t 3") test.add_stonith_log_pattern("Total timeout set to 21") test.add_stonith_log_pattern("targeting node3 using false1 returned 1") test.add_stonith_log_pattern("targeting node3 using false2 returned 1") test.add_stonith_log_pattern("targeting node3 using true3 returned 0") test.add_stonith_log_pattern("targeting node3 using true4 returned 0") # test what happens when the first fencing level had devices that no one has registered for test_type in test_types: if test_type["use_cpg"] == 0: continue test = self.new_test("%s_topology_missing_devices" % test_type["prefix"], "Verify topology can continue with missing devices.", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R true2 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R true3 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R true4 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R false2 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 1 -v false1") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 1 -v true1") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 2 -v true2") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 2 -v false2") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 3 -v true3") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 3 -v true4") test.add_cmd("stonith_admin", "--output-as=xml -F node3 -t 5") # Test what happens if multiple fencing levels are defined, and then the first one is removed. for test_type in test_types: if test_type["use_cpg"] == 0: continue test = self.new_test("%s_topology_level_removal" % test_type["prefix"], "Verify level removal works.", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R true2 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R true3 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R true4 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R false1 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R false2 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 1 -v false1") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 1 -v true1") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 2 -v true2") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 2 -v false2") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 3 -v true3") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 3 -v true4") # Now remove level 2, verify none of the devices in level two are hit. test.add_cmd("stonith_admin", "--output-as=xml -d node3 -i 2") test.add_cmd("stonith_admin", "--output-as=xml -F node3 -t 20") test.add_stonith_log_pattern("Total timeout set to 96") test.add_stonith_log_pattern("targeting node3 using false1 returned 1") test.add_stonith_neg_log_pattern("targeting node3 using false2 returned ") test.add_stonith_log_pattern("targeting node3 using true3 returned 0") test.add_stonith_log_pattern("targeting node3 using true4 returned 0") # Test targeting a topology level by node name pattern. for test_type in test_types: if test_type["use_cpg"] == 0: continue test = self.new_test("%s_topology_level_pattern" % test_type["prefix"], "Verify targeting topology by node name pattern works.", test_type["use_cpg"]) test.add_cmd("stonith_admin", """--output-as=xml -R true -a fence_dummy -o "mode=pass" -o "pcmk_host_list=node1 node2 node3" """) test.add_cmd("stonith_admin", """--output-as=xml -r '@node.*' -i 1 -v true""") test.add_cmd("stonith_admin", "--output-as=xml -F node3 -t 5") test.add_stonith_log_pattern("targeting node3 using true returned 0") # test allowing commas and semicolons as delimiters in pcmk_host_list for test_type in test_types: test = self.new_test("%s_host_list_delimiters" % test_type["prefix"], "Verify commas and semicolons can be used as pcmk_host_list delimiters", test_type["use_cpg"]) test.add_cmd("stonith_admin", """--output-as=xml -R true1 -a fence_dummy -o "mode=pass" -o "pcmk_host_list=node1,node2,node3" """) test.add_cmd("stonith_admin", """--output-as=xml -R true2 -a fence_dummy -o "mode=pass" -o "pcmk_host_list=pcmk1;pcmk2;pcmk3" """) test.add_cmd("stonith_admin", "stonith_admin --output-as=xml -F node2 -t 5") test.add_cmd("stonith_admin", "stonith_admin --output-as=xml -F pcmk3 -t 5") test.add_stonith_log_pattern("targeting node2 using true1 returned 0") test.add_stonith_log_pattern("targeting pcmk3 using true2 returned 0") # test the stonith builds the correct list of devices that can fence a node. for test_type in test_types: test = self.new_test("%s_list_devices" % test_type["prefix"], "Verify list of devices that can fence a node is correct", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R true2 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R true3 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd_check_stdout("stonith_admin", "--output-as=xml -l node1 -V", "true2", "true1") test.add_cmd_check_stdout("stonith_admin", "--output-as=xml -l node1 -V", "true3", "true1") # simple test of device monitor for test_type in test_types: test = self.new_test("%s_monitor" % test_type["prefix"], "Verify device is reachable", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R false1 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node3\"") test.add_cmd("stonith_admin", "--output-as=xml -Q true1") test.add_cmd("stonith_admin", "--output-as=xml -Q false1") test.add_expected_fail_cmd("stonith_admin", "--output-as=xml -Q true2", CrmExit.NOSUCH) # Verify monitor occurs for duration of timeout period on failure for test_type in test_types: test = self.new_test("%s_monitor_timeout" % test_type["prefix"], "Verify monitor uses duration of timeout period given.", test_type["use_cpg"]) test.add_cmd("stonith_admin", '--output-as=xml -R true1 -a fence_dummy -o "mode=fail" -o "monitor_mode=fail" -o "pcmk_host_list=node3"') test.add_expected_fail_cmd("stonith_admin", "--output-as=xml -Q true1 -t 5", CrmExit.ERROR) test.add_stonith_log_pattern("Attempt 2 to execute") # Verify monitor occurs for duration of timeout period on failure, but stops at max retries for test_type in test_types: test = self.new_test("%s_monitor_timeout_max_retries" % test_type["prefix"], "Verify monitor retries until max retry value or timeout is hit.", test_type["use_cpg"]) test.add_cmd("stonith_admin", '--output-as=xml -R true1 -a fence_dummy -o "mode=fail" -o "monitor_mode=fail" -o "pcmk_host_list=node3"') test.add_expected_fail_cmd("stonith_admin", "--output-as=xml -Q true1 -t 15", CrmExit.ERROR) test.add_stonith_log_pattern("Attempted to execute agent fence_dummy (list) the maximum number of times") # simple register test for test_type in test_types: test = self.new_test("%s_register" % test_type["prefix"], "Verify devices can be registered and un-registered", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node3\"") test.add_cmd("stonith_admin", "--output-as=xml -Q true1") test.add_cmd("stonith_admin", "--output-as=xml -D true1") test.add_expected_fail_cmd("stonith_admin", "--output-as=xml -Q true1", CrmExit.NOSUCH) # simple reboot test for test_type in test_types: test = self.new_test("%s_reboot" % test_type["prefix"], "Verify devices can be rebooted", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node3\"") test.add_cmd("stonith_admin", "--output-as=xml -B node3 -t 5") test.add_cmd("stonith_admin", "--output-as=xml -D true1") test.add_expected_fail_cmd("stonith_admin", "--output-as=xml -Q true1", CrmExit.NOSUCH) # test fencing history. for test_type in test_types: if test_type["use_cpg"] == 0: continue test = self.new_test("%s_fence_history" % test_type["prefix"], "Verify last fencing operation is returned.", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node3\"") test.add_cmd("stonith_admin", "--output-as=xml -F node3 -t 5 -V") test.add_cmd_check_stdout("stonith_admin", "--output-as=xml -H node3", 'action="off" target="node3" .* status="success"') # simple test of dynamic list query for test_type in test_types: test = self.new_test("%s_dynamic_list_query" % test_type["prefix"], "Verify dynamic list of fencing devices can be retrieved.", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o mode=pass -o mock_dynamic_hosts=fake_port_1") test.add_cmd("stonith_admin", "--output-as=xml -R true2 -a fence_dummy -o mode=pass -o mock_dynamic_hosts=fake_port_1") test.add_cmd("stonith_admin", "--output-as=xml -R true3 -a fence_dummy -o mode=pass -o mock_dynamic_hosts=fake_port_1") test.add_cmd_check_stdout("stonith_admin", "--output-as=xml -l fake_port_1", 'count="3"') # fence using dynamic list query for test_type in test_types: test = self.new_test("%s_fence_dynamic_list_query" % test_type["prefix"], "Verify dynamic list of fencing devices can be retrieved.", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o mode=pass -o mock_dynamic_hosts=fake_port_1") test.add_cmd("stonith_admin", "--output-as=xml -R true2 -a fence_dummy -o mode=pass -o mock_dynamic_hosts=fake_port_1") test.add_cmd("stonith_admin", "--output-as=xml -R true3 -a fence_dummy -o mode=pass -o mock_dynamic_hosts=fake_port_1") test.add_cmd("stonith_admin", "--output-as=xml -F fake_port_1 -t 5 -V") # simple test of query using status action for test_type in test_types: test = self.new_test("%s_status_query" % test_type["prefix"], "Verify dynamic list of fencing devices can be retrieved.", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_check=status\"") test.add_cmd("stonith_admin", "--output-as=xml -R true2 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_check=status\"") test.add_cmd("stonith_admin", "--output-as=xml -R true3 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_check=status\"") test.add_cmd_check_stdout("stonith_admin", "--output-as=xml -l fake_port_1", 'count="3"') # test what happens when no reboot action is advertised for test_type in test_types: test = self.new_test("%s_no_reboot_support" % test_type["prefix"], "Verify reboot action defaults to off when no reboot action is advertised by agent.", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy_no_reboot -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -B node1 -t 5 -V") test.add_stonith_log_pattern("does not support reboot") test.add_stonith_log_pattern("using true1 returned 0") # make sure reboot is used when reboot action is advertised for test_type in test_types: test = self.new_test("%s_with_reboot_support" % test_type["prefix"], "Verify reboot action can be used when metadata advertises it.", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -B node1 -t 5 -V") test.add_stonith_neg_log_pattern("does not advertise support for 'reboot', performing 'off'") test.add_stonith_log_pattern("using true1 returned 0") # make sure requested fencing delay is applied only for the first device in the first level # make sure static delay from pcmk_delay_base is added for test_type in test_types: if test_type["use_cpg"] == 0: continue test = self.new_test("%s_topology_delay" % test_type["prefix"], "Verify requested fencing delay is applied only for the first device in the first level and pcmk_delay_base is added.", test_type["use_cpg"]) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\" -o \"pcmk_delay_base=1\"") test.add_cmd("stonith_admin", "--output-as=xml -R false1 -a fence_dummy -o \"mode=fail\" -o \"pcmk_host_list=node1 node2 node3\" -o \"pcmk_delay_base=1\"") test.add_cmd("stonith_admin", "--output-as=xml -R true2 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -R true3 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=node1 node2 node3\"") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 1 -v true1") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 1 -v false1") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 2 -v true2") test.add_cmd("stonith_admin", "--output-as=xml -r node3 -i 2 -v true3") test.add_cmd("stonith_admin", "--output-as=xml -F node3 --delay 1") test.add_stonith_log_pattern("Delaying 'off' action targeting node3 using true1 for 2s | timeout=120s requested_delay=1s base=1s max=1s") test.add_stonith_log_pattern("Delaying 'off' action targeting node3 using false1 for 1s | timeout=120s requested_delay=0s base=1s max=1s") test.add_stonith_neg_log_pattern("Delaying 'off' action targeting node3 using true2") test.add_stonith_neg_log_pattern("Delaying 'off' action targeting node3 using true3") def build_nodeid_tests(self): """ Register tests that use a corosync node id """ our_uname = localname() ### verify nodeid is supplied when nodeid is in the metadata parameters test = self.new_test("cpg_supply_nodeid", "Verify nodeid is given when fence agent has nodeid as parameter", 1) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=%s\"" % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -F %s -t 3" % (our_uname)) test.add_stonith_log_pattern("as nodeid with fence action 'off' targeting %s" % (our_uname)) ### verify nodeid is _NOT_ supplied when nodeid is not in the metadata parameters test = self.new_test("cpg_do_not_supply_nodeid", "Verify nodeid is _NOT_ given when fence agent does not have nodeid as parameter", 1) # use a host name that won't be in corosync.conf test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=regr-test\"") test.add_cmd("stonith_admin", "--output-as=xml -F regr-test -t 3") test.add_stonith_neg_log_pattern("as nodeid with fence action 'off' targeting regr-test") ### verify nodeid use doesn't explode standalone mode test = self.new_test("standalone_do_not_supply_nodeid", "Verify nodeid in metadata parameter list doesn't kill standalone mode", 0) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=%s\"" % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -F %s -t 3" % (our_uname)) test.add_stonith_neg_log_pattern("as nodeid with fence action 'off' targeting %s" % (our_uname)) def build_unfence_tests(self): """ Register tests that verify unfencing """ our_uname = localname() ### verify unfencing using automatic unfencing test = self.new_test("cpg_unfence_required_1", "Verify require unfencing on all devices when automatic=true in agent's metadata", 1) test.add_cmd('stonith_admin', '--output-as=xml -R true1 -a fence_dummy_auto_unfence -o "mode=pass" -o "pcmk_host_list=%s"' % (our_uname)) test.add_cmd('stonith_admin', '--output-as=xml -R true2 -a fence_dummy_auto_unfence -o "mode=pass" -o "pcmk_host_list=%s"' % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -U %s -t 3" % (our_uname)) # both devices should be executed test.add_stonith_log_pattern("using true1 returned 0") test.add_stonith_log_pattern("using true2 returned 0") ### verify unfencing using automatic unfencing fails if any of the required agents fail test = self.new_test("cpg_unfence_required_2", "Verify require unfencing on all devices when automatic=true in agent's metadata", 1) test.add_cmd('stonith_admin', '--output-as=xml -R true1 -a fence_dummy_auto_unfence -o "mode=pass" -o "pcmk_host_list=%s"' % (our_uname)) test.add_cmd('stonith_admin', '--output-as=xml -R true2 -a fence_dummy_auto_unfence -o "mode=fail" -o "pcmk_host_list=%s"' % (our_uname)) test.add_expected_fail_cmd("stonith_admin", "--output-as=xml -U %s -t 6" % (our_uname), CrmExit.ERROR) ### verify unfencing using automatic devices with topology test = self.new_test("cpg_unfence_required_3", "Verify require unfencing on all devices even when at different topology levels", 1) test.add_cmd('stonith_admin', '--output-as=xml -R true1 -a fence_dummy_auto_unfence -o "mode=pass" -o "pcmk_host_list=%s node3"' % (our_uname)) test.add_cmd('stonith_admin', '--output-as=xml -R true2 -a fence_dummy_auto_unfence -o "mode=pass" -o "pcmk_host_list=%s node3"' % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -r %s -i 1 -v true1" % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -r %s -i 2 -v true2" % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -U %s -t 3" % (our_uname)) test.add_stonith_log_pattern("using true1 returned 0") test.add_stonith_log_pattern("using true2 returned 0") ### verify unfencing using automatic devices with topology test = self.new_test("cpg_unfence_required_4", "Verify all required devices are executed even with topology levels fail.", 1) test.add_cmd('stonith_admin', '--output-as=xml -R true1 -a fence_dummy_auto_unfence -o "mode=pass" -o "pcmk_host_list=%s node3"' % (our_uname)) test.add_cmd('stonith_admin', '--output-as=xml -R true2 -a fence_dummy_auto_unfence -o "mode=pass" -o "pcmk_host_list=%s node3"' % (our_uname)) test.add_cmd('stonith_admin', '--output-as=xml -R true3 -a fence_dummy_auto_unfence -o "mode=pass" -o "pcmk_host_list=%s node3"' % (our_uname)) test.add_cmd('stonith_admin', '--output-as=xml -R true4 -a fence_dummy_auto_unfence -o "mode=pass" -o "pcmk_host_list=%s node3"' % (our_uname)) test.add_cmd('stonith_admin', '--output-as=xml -R false1 -a fence_dummy -o "mode=fail" -o "pcmk_host_list=%s node3"' % (our_uname)) test.add_cmd('stonith_admin', '--output-as=xml -R false2 -a fence_dummy -o "mode=fail" -o "pcmk_host_list=%s node3"' % (our_uname)) test.add_cmd('stonith_admin', '--output-as=xml -R false3 -a fence_dummy -o "mode=fail" -o "pcmk_host_list=%s node3"' % (our_uname)) test.add_cmd('stonith_admin', '--output-as=xml -R false4 -a fence_dummy -o "mode=fail" -o "pcmk_host_list=%s node3"' % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -r %s -i 1 -v true1" % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -r %s -i 1 -v false1" % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -r %s -i 2 -v false2" % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -r %s -i 2 -v true2" % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -r %s -i 2 -v false3" % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -r %s -i 2 -v true3" % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -r %s -i 3 -v false4" % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -r %s -i 4 -v true4" % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -U %s -t 3" % (our_uname)) test.add_stonith_log_pattern("using true1 returned 0") test.add_stonith_log_pattern("using true2 returned 0") test.add_stonith_log_pattern("using true3 returned 0") test.add_stonith_log_pattern("using true4 returned 0") def build_unfence_on_target_tests(self): """ Register tests that verify unfencing that runs on the target """ our_uname = localname() ### verify unfencing using on_target device test = self.new_test("cpg_unfence_on_target_1", "Verify unfencing with on_target = true", 1) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=%s\"" % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -U %s -t 3" % (our_uname)) test.add_stonith_log_pattern("(on) to be executed on target") ### verify failure of unfencing using on_target device test = self.new_test("cpg_unfence_on_target_2", "Verify failure unfencing with on_target = true", 1) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=%s node_fake_1234\"" % (our_uname)) test.add_expected_fail_cmd("stonith_admin", "--output-as=xml -U node_fake_1234 -t 3", CrmExit.NOSUCH) test.add_stonith_log_pattern("(on) to be executed on target") ### verify unfencing using on_target device with topology test = self.new_test("cpg_unfence_on_target_3", "Verify unfencing with on_target = true using topology", 1) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=%s node3\"" % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -R true2 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=%s node3\"" % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -r %s -i 1 -v true1" % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -r %s -i 2 -v true2" % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -U %s -t 3" % (our_uname)) test.add_stonith_log_pattern("(on) to be executed on target") ### verify unfencing using on_target device with topology fails when target node doesn't exist test = self.new_test("cpg_unfence_on_target_4", "Verify unfencing failure with on_target = true using topology", 1) test.add_cmd("stonith_admin", "--output-as=xml -R true1 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=%s node_fake\"" % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -R true2 -a fence_dummy -o \"mode=pass\" -o \"pcmk_host_list=%s node_fake\"" % (our_uname)) test.add_cmd("stonith_admin", "--output-as=xml -r node_fake -i 1 -v true1") test.add_cmd("stonith_admin", "--output-as=xml -r node_fake -i 2 -v true2") test.add_expected_fail_cmd("stonith_admin", "--output-as=xml -U node_fake -t 3", CrmExit.NOSUCH) test.add_stonith_log_pattern("(on) to be executed on target") def build_remap_tests(self): """ Register tests that verify remapping of reboots to off-on """ test = self.new_test("cpg_remap_simple", "Verify sequential topology reboot is remapped to all-off-then-all-on", 1) test.add_cmd("stonith_admin", """--output-as=xml -R true1 -a fence_dummy -o "mode=pass" -o "pcmk_host_list=node_fake" """ """-o "pcmk_off_timeout=1" -o "pcmk_reboot_timeout=10" """) test.add_cmd("stonith_admin", """--output-as=xml -R true2 -a fence_dummy -o "mode=pass" -o "pcmk_host_list=node_fake" """ """-o "pcmk_off_timeout=2" -o "pcmk_reboot_timeout=20" """) test.add_cmd("stonith_admin", "--output-as=xml -r node_fake -i 1 -v true1 -v true2") test.add_cmd("stonith_admin", "--output-as=xml -B node_fake -t 5") test.add_stonith_log_pattern("Remapping multiple-device reboot targeting node_fake") # timeout should be sum of off timeouts (1+2=3), not reboot timeouts (10+20=30) test.add_stonith_log_pattern("Total timeout set to 3 for peer's fencing targeting node_fake") test.add_stonith_log_pattern("perform 'off' action targeting node_fake using true1") test.add_stonith_log_pattern("perform 'off' action targeting node_fake using true2") test.add_stonith_log_pattern("Remapped 'off' targeting node_fake complete, remapping to 'on'") # fence_dummy sets "on" as an on_target action test.add_stonith_log_pattern("Ignoring true1 'on' failure (no capable peers) targeting node_fake") test.add_stonith_log_pattern("Ignoring true2 'on' failure (no capable peers) targeting node_fake") test.add_stonith_log_pattern("Undoing remap of reboot targeting node_fake") + test = self.new_test("cpg_remap_simple_off", + "Verify sequential topology reboot skips 'on' if " + "pcmk_reboot_action=off or agent doesn't support " + "'on'", 1) + test.add_cmd("stonith_admin", + "--output-as=xml -R true1 -a fence_dummy -o mode=pass " + "-o pcmk_host_list=node_fake -o pcmk_off_timeout=1 " + "-o pcmk_reboot_timeout=10 -o pcmk_reboot_action=off") + test.add_cmd("stonith_admin", + "--output-as=xml -R true2 -a fence_dummy_no_on " + "-o mode=pass -o pcmk_host_list=node_fake " + "-o pcmk_off_timeout=2 -o pcmk_reboot_timeout=20") + test.add_cmd("stonith_admin", + "--output-as=xml -r node_fake -i 1 -v true1 -v true2") + test.add_cmd("stonith_admin", "--output-as=xml -B node_fake -t 5") + test.add_stonith_log_pattern("Remapping multiple-device reboot targeting node_fake") + # timeout should be sum of off timeouts (1+2=3), not reboot timeouts (10+20=30) + test.add_stonith_log_pattern("Total timeout set to 3 for peer's fencing targeting node_fake") + test.add_stonith_log_pattern("perform 'off' action targeting node_fake using true1") + test.add_stonith_log_pattern("perform 'off' action targeting node_fake using true2") + test.add_stonith_log_pattern("Remapped 'off' targeting node_fake complete, remapping to 'on'") + # "on" should be skipped + test.add_stonith_log_pattern("Not turning node_fake back on using " + "true1 because the device is configured " + "to stay off") + test.add_stonith_log_pattern("Not turning node_fake back on using true2" + " because the agent doesn't support 'on'") + test.add_stonith_log_pattern("Undoing remap of reboot targeting node_fake") + test = self.new_test("cpg_remap_automatic", "Verify remapped topology reboot skips automatic 'on'", 1) test.add_cmd("stonith_admin", """--output-as=xml -R true1 -a fence_dummy_auto_unfence """ """-o "mode=pass" -o "pcmk_host_list=node_fake" """) test.add_cmd("stonith_admin", """--output-as=xml -R true2 -a fence_dummy_auto_unfence """ """-o "mode=pass" -o "pcmk_host_list=node_fake" """) test.add_cmd("stonith_admin", "--output-as=xml -r node_fake -i 1 -v true1 -v true2") test.add_cmd("stonith_admin", "--output-as=xml -B node_fake -t 5") test.add_stonith_log_pattern("Remapping multiple-device reboot targeting node_fake") test.add_stonith_log_pattern("perform 'off' action targeting node_fake using true1") test.add_stonith_log_pattern("perform 'off' action targeting node_fake using true2") test.add_stonith_log_pattern("Remapped 'off' targeting node_fake complete, remapping to 'on'") test.add_stonith_log_pattern("Undoing remap of reboot targeting node_fake") test.add_stonith_neg_log_pattern("perform 'on' action targeting node_fake using") test.add_stonith_neg_log_pattern("'on' failure") test = self.new_test("cpg_remap_complex_1", "Verify remapped topology reboot in second level works if non-remapped first level fails", 1) test.add_cmd("stonith_admin", """--output-as=xml -R false1 -a fence_dummy -o "mode=fail" -o "pcmk_host_list=node_fake" """) test.add_cmd("stonith_admin", """--output-as=xml -R true1 -a fence_dummy -o "mode=pass" -o "pcmk_host_list=node_fake" """) test.add_cmd("stonith_admin", """--output-as=xml -R true2 -a fence_dummy -o "mode=pass" -o "pcmk_host_list=node_fake" """) test.add_cmd("stonith_admin", "--output-as=xml -r node_fake -i 1 -v false1") test.add_cmd("stonith_admin", "--output-as=xml -r node_fake -i 2 -v true1 -v true2") test.add_cmd("stonith_admin", "--output-as=xml -B node_fake -t 5") test.add_stonith_log_pattern("perform 'reboot' action targeting node_fake using false1") test.add_stonith_log_pattern("Remapping multiple-device reboot targeting node_fake") test.add_stonith_log_pattern("perform 'off' action targeting node_fake using true1") test.add_stonith_log_pattern("perform 'off' action targeting node_fake using true2") test.add_stonith_log_pattern("Remapped 'off' targeting node_fake complete, remapping to 'on'") test.add_stonith_log_pattern("Ignoring true1 'on' failure (no capable peers) targeting node_fake") test.add_stonith_log_pattern("Ignoring true2 'on' failure (no capable peers) targeting node_fake") test.add_stonith_log_pattern("Undoing remap of reboot targeting node_fake") test = self.new_test("cpg_remap_complex_2", "Verify remapped topology reboot failure in second level proceeds to third level", 1) test.add_cmd("stonith_admin", """--output-as=xml -R false1 -a fence_dummy -o "mode=fail" -o "pcmk_host_list=node_fake" """) test.add_cmd("stonith_admin", """--output-as=xml -R false2 -a fence_dummy -o "mode=fail" -o "pcmk_host_list=node_fake" """) test.add_cmd("stonith_admin", """--output-as=xml -R true1 -a fence_dummy -o "mode=pass" -o "pcmk_host_list=node_fake" """) test.add_cmd("stonith_admin", """--output-as=xml -R true2 -a fence_dummy -o "mode=pass" -o "pcmk_host_list=node_fake" """) test.add_cmd("stonith_admin", """--output-as=xml -R true3 -a fence_dummy -o "mode=pass" -o "pcmk_host_list=node_fake" """) test.add_cmd("stonith_admin", "--output-as=xml -r node_fake -i 1 -v false1") test.add_cmd("stonith_admin", "--output-as=xml -r node_fake -i 2 -v true1 -v false2 -v true3") test.add_cmd("stonith_admin", "--output-as=xml -r node_fake -i 3 -v true2") test.add_cmd("stonith_admin", "--output-as=xml -B node_fake -t 5") test.add_stonith_log_pattern("perform 'reboot' action targeting node_fake using false1") test.add_stonith_log_pattern("Remapping multiple-device reboot targeting node_fake") test.add_stonith_log_pattern("perform 'off' action targeting node_fake using true1") test.add_stonith_log_pattern("perform 'off' action targeting node_fake using false2") test.add_stonith_log_pattern("Attempted to execute agent fence_dummy (off) the maximum number of times") test.add_stonith_log_pattern("Undoing remap of reboot targeting node_fake") test.add_stonith_log_pattern("perform 'reboot' action targeting node_fake using true2") test.add_stonith_neg_log_pattern("node_fake with true3") def build_query_tests(self): """ run stonith_admin --metadata for the fence_dummy agent and check command output """ test = self.new_test("get_metadata", "Run stonith_admin --metadata for the fence_dummy agent", 1) test.add_cmd_check_stdout("stonith_admin", "--output-as=xml -a fence_dummy --metadata", '/dev/null 2>/dev/null if [ $? -eq 0 ]; then DATA_DIR="$(dirname "$(readlink -e "$0")")" else DATA_DIR="$(dirname "$0")" fi fi usage() { echo "Error:" "$@" echo "$USAGE_TEXT" exit $CRM_EX_USAGE } must_be_root() { if ! [ "$(id -u)" = "0" ]; then usage "this command must be run as root" return $CRM_EX_ERROR fi return $CRM_EX_OK } support_uninstall() { must_be_root || return $CRM_EX_ERROR if [ -e "$UNIT_DIR/$DUMMY_DAEMON_UNIT" ]; then echo "Removing $UNIT_DIR/$DUMMY_DAEMON_UNIT ..." rm -f "$UNIT_DIR/$DUMMY_DAEMON_UNIT" systemctl daemon-reload # Ignore failure fi if [ -e "$RUNTIME_UNIT_DIR/$COROSYNC_RUNTIME_UNIT" ]; then echo "Removing $RUNTIME_UNIT_DIR/$COROSYNC_RUNTIME_UNIT ..." rm -rf "$RUNTIME_UNIT_DIR/$COROSYNC_RUNTIME_UNIT" systemctl daemon-reload # Ignore failure fi for FILE in \ "$LIBEXEC_DIR/$DUMMY_DAEMON" \ "$UPSTART_DIR/$UPSTART_DUMMY" \ "$PCMK__FENCE_BINDIR/$FENCE_DUMMY" \ "$INIT_DIR/$LSB_DUMMY" do if [ -e "$FILE" ]; then echo "Removing $FILE ..." rm -f "$FILE" fi done for ALIAS in $FENCE_DUMMY_ALIASES; do \ - FILE="$PCMK__FENCE_BINDIR/$ALIAS" + FILE="$PCMK__FENCE_BINDIR/fence_dummy_$ALIAS" if [ -L "$FILE" ] || [ -e "$FILE" ]; then echo "Removing $FILE ..." rm -f "$FILE" fi done return $CRM_EX_OK } support_install() { support_uninstall || return $CRM_EX_ERROR cd "$DATA_DIR" || return $CRM_EX_ERROR if [ -d "$UNIT_DIR" ]; then echo "Installing $DUMMY_DAEMON ..." mkdir -p "$LIBEXEC_DIR" install -m 0755 "$DUMMY_DAEMON" "$LIBEXEC_DIR" || return $CRM_EX_ERROR echo "Installing $DUMMY_DAEMON_UNIT ..." install -m 0644 "$DUMMY_DAEMON_UNIT" "$UNIT_DIR" || return $CRM_EX_ERROR systemctl daemon-reload # Ignore failure fi if [ -d "$RUNTIME_UNIT_DIR" ]; then echo "Installing $COROSYNC_RUNTIME_CONF to $RUNTIME_UNIT_DIR/$COROSYNC_RUNTIME_UNIT ..." mkdir -p "$RUNTIME_UNIT_DIR/$COROSYNC_RUNTIME_UNIT" install -m 0644 "$COROSYNC_RUNTIME_CONF" "$RUNTIME_UNIT_DIR/$COROSYNC_RUNTIME_UNIT" || return $CRM_EX_ERROR systemctl daemon-reload # Ignore failure fi echo "Installing $FENCE_DUMMY to $PCMK__FENCE_BINDIR ..." mkdir -p "$PCMK__FENCE_BINDIR" install -m 0755 "$FENCE_DUMMY" "$PCMK__FENCE_BINDIR" || return $CRM_EX_ERROR for alias in $FENCE_DUMMY_ALIASES; do \ - echo "Installing $alias to $PCMK__FENCE_BINDIR ..." - ln -s "$FENCE_DUMMY" "$PCMK__FENCE_BINDIR/$alias" || return $CRM_EX_ERROR + echo "Installing fence_dummy_$alias to $PCMK__FENCE_BINDIR ..." + ln -s "$FENCE_DUMMY" "$PCMK__FENCE_BINDIR/fence_dummy_$alias" + if [ $? -ne 0 ]; then + return $CRM_EX_ERROR + fi done echo "Installing $LSB_DUMMY to $INIT_DIR ..." mkdir -p "$INIT_DIR" install -m 0755 "$LSB_DUMMY" "$INIT_DIR" || return $CRM_EX_ERROR if [ -d "$UPSTART_DIR" ] && [ -f "$UPSTART_DUMMY" ]; then echo "Installing $UPSTART_DUMMY to $UPSTART_DIR ..." install -m 0644 "$UPSTART_DUMMY" "$UPSTART_DIR" || return $CRM_EX_ERROR fi return $CRM_EX_OK } COMMAND="" while [ $# -gt 0 ] ; do case "$1" in --help) echo "$HELP_TEXT" exit $CRM_EX_OK ;; install|uninstall) COMMAND="$1" shift ;; *) usage "unknown option '$1'" ;; esac done case "$COMMAND" in install) support_install ;; uninstall) support_uninstall ;; *) usage "must specify command" ;; esac diff --git a/cts/support/fence_dummy.in b/cts/support/fence_dummy.in index 123cb47d9c..d69c10b995 100644 --- a/cts/support/fence_dummy.in +++ b/cts/support/fence_dummy.in @@ -1,509 +1,514 @@ #!@PYTHON@ """Dummy fence agent for testing """ __copyright__ = "Copyright 2012-2022 the Pacemaker project contributors" __license__ = "GNU General Public License version 2 or later (GPLv2+) WITHOUT ANY WARRANTY" import io import os import re import sys import time import random import atexit import getopt AGENT_VERSION = "4.1.0" OCF_VERSION = "1.0" SHORT_DESC = "Dummy fence agent" LONG_DESC = """fence_dummy is a fake fencing agent which reports success based on its mode (pass|fail|random) without doing anything.""" # Short options used: difhmnoqsvBDHMRUV ALL_OPT = { "quiet" : { "getopt" : "q", "help" : "", "order" : 50 }, "verbose" : { "getopt" : "v", "longopt" : "verbose", "help" : "-v, --verbose Verbose mode", "required" : "0", "shortdesc" : "Verbose mode", "order" : 51 }, "debug" : { "getopt" : "D:", "longopt" : "debug-file", "help" : "-D, --debug-file=[debugfile] Debugging to output file", "required" : "0", "shortdesc" : "Write debug information to given file", "order" : 52 }, "version" : { "getopt" : "V", "longopt" : "version", "help" : "-V, --version Display version information and exit", "required" : "0", "shortdesc" : "Display version information and exit", "order" : 53 }, "help" : { "getopt" : "h", "longopt" : "help", "help" : "-h, --help Display this help and exit", "required" : "0", "shortdesc" : "Display help and exit", "order" : 54 }, "action" : { "getopt" : "o:", "longopt" : "action", "help" : "-o, --action=[action] Action: validate-all, status, list, reboot (default), off or on", "required" : "1", "shortdesc" : "Fencing Action", "default" : "reboot", "order" : 1 }, "nodename" : { "getopt" : "N:", "longopt" : "nodename", "help" : "-N, --nodename Node name of fence target (ignored)", "required" : "0", "shortdesc" : "The node name of fence target (ignored)", "order" : 2 }, "mode": { "getopt" : "M:", "longopt" : "mode", "required" : "0", "help" : "-M, --mode=(pass|fail|random) Exit status to return for non-monitor operations", "shortdesc" : "Whether fence operations should always pass, always fail, or fail at random", "order" : 3 }, "monitor_mode" : { "getopt" : "m:", "longopt" : "monitor_mode", "help" : "-m, --monitor_mode=(pass|fail|random) Exit status to return for monitor operations", "required" : "0", "shortdesc" : "Whether monitor operations should always pass, always fail, or fail at random", "order" : 3 }, "random_sleep_range": { "getopt" : "R:", "required" : "0", "longopt" : "random_sleep_range", "help" : "-R, --random_sleep_range=[seconds] Sleep between 1 and [seconds] before returning", "shortdesc" : "Wait randomly between 1 and [seconds]", "order" : 3 }, "mock_dynamic_hosts" : { "getopt" : "H:", "longopt" : "mock_dynamic_hosts", "help" : "-H, --mock_dynamic_hosts=[list] What to return when dynamically queried for possible targets", "required" : "0", "shortdesc" : "A list of hosts we can fence", "order" : 3 }, "delay" : { "getopt" : "f:", "longopt" : "delay", "help" : "-f, --delay [seconds] Wait X seconds before fencing is started", "required" : "0", "shortdesc" : "Wait X seconds before fencing is started", "default" : "0", "order" : 3 }, "monitor_delay" : { "getopt" : "d:", "longopt" : "monitor_delay", "help" : "-d, --monitor_delay [seconds] Wait X seconds before monitor completes", "required" : "0", "shortdesc" : "Wait X seconds before monitor completes", "default" : "0", "order" : 3 }, "plug" : { "getopt" : "n:", "longopt" : "plug", "help" : "-n, --plug=[id] Physical plug number on device (ignored)", "required" : "1", "shortdesc" : "Ignored", "order" : 4 }, "port" : { "getopt" : "n:", "longopt" : "plug", "help" : "-n, --plug=[id] Physical plug number on device (ignored)", "required" : "1", "shortdesc" : "Ignored", "order" : 4 }, "switch" : { "getopt" : "s:", "longopt" : "switch", "help" : "-s, --switch=[id] Physical switch number on device (ignored)", "required" : "0", "shortdesc" : "Ignored", "order" : 4 }, "nodeid" : { "getopt" : "i:", "longopt" : "nodeid", "help" : "-i, --nodeid Corosync id of fence target (ignored)", "required" : "0", "shortdesc" : "Ignored", "order" : 4 }, "uuid" : { "getopt" : "U:", "longopt" : "uuid", "help" : "-U, --uuid UUID of the VM to fence (ignored)", "required" : "0", "shortdesc" : "Ignored", "order" : 4 } } auto_unfence = False no_reboot = False +no_on = False def agent(): """ Return name this file was run as. """ return os.path.basename(sys.argv[0]) def fail_usage(message): """ Print a usage message and exit. """ sys.exit("%s\nPlease use '-h' for usage" % message) def show_docs(options): """ Handle informational options (display info and exit). """ device_opt = options["device_opt"] if "-h" in options: usage(device_opt) sys.exit(0) if "-o" in options and options["-o"].lower() == "metadata": if not os.path.exists(__file__ + ".fail"): metadata(device_opt, options) else: os.remove(__file__ + ".fail") sys.exit(0) if "-V" in options: print(AGENT_VERSION) sys.exit(0) def sorted_options(avail_opt): """ Return a list of all options, in their internally specified order. """ sorted_list = [(key, ALL_OPT[key]) for key in avail_opt] sorted_list.sort(key=lambda x: x[1]["order"]) return sorted_list def usage(avail_opt): """ Print a usage message. """ print("Usage:") print("\t" + agent() + " [options]") print("Options:") for dummy, value in sorted_options(avail_opt): if len(value["help"]) != 0: print(" " + value["help"]) def metadata(avail_opt, options): """ Print agent metadata. """ # This log is just for testing handling of stderr output print("asked for fence_dummy metadata", file=sys.stderr) print(""" %s %s """ % (agent(), SHORT_DESC, AGENT_VERSION, OCF_VERSION, LONG_DESC)) for option, dummy in sorted_options(avail_opt): if "shortdesc" in ALL_OPT[option]: print(' ') default = "" default_name_arg = "-" + ALL_OPT[option]["getopt"][:-1] default_name_no_arg = "-" + ALL_OPT[option]["getopt"] if "default" in ALL_OPT[option]: default = 'default="%s"' % str(ALL_OPT[option]["default"]) elif default_name_arg in options: if options[default_name_arg]: try: default = 'default="%s"' % options[default_name_arg] except TypeError: ## @todo/@note: Currently there is no clean way how to handle lists ## we can create a string from it but we can't set it on command line default = 'default="%s"' % str(options[default_name_arg]) elif default_name_no_arg in options: default = 'default="true"' mixed = ALL_OPT[option]["help"] ## split it between option and help text res = re.compile(r"^(.*--\S+)\s+", re.IGNORECASE | re.S).search(mixed) if None != res: mixed = res.group(1) mixed = mixed.replace("<", "<").replace(">", ">") print(' ') if ALL_OPT[option]["getopt"].count(":") > 0: print(' ') else: print(' ') print(' ' + ALL_OPT[option]["shortdesc"] + '') print(' ') print(' \n ') - if auto_unfence: - attr_name = 'automatic' - else: - attr_name = 'on_target' - print(' ') + if not no_on: + if auto_unfence: + attr_name = 'automatic' + else: + attr_name = 'on_target' + print(' ') print(' ') if not no_reboot: print(' ') print(' ') print(' ') print(' ') print(' ') print(' ') print('') def option_longopt(option): """ Return the getopt-compatible long-option name of the given option. """ if ALL_OPT[option]["getopt"].endswith(":"): return ALL_OPT[option]["longopt"] + "=" else: return ALL_OPT[option]["longopt"] def opts_from_command_line(argv, avail_opt): """ Read options from command-line arguments. """ # Prepare list of options for getopt getopt_string = "" longopt_list = [] for k in avail_opt: if k in ALL_OPT: getopt_string += ALL_OPT[k]["getopt"] else: fail_usage("Parse error: unknown option '"+k+"'") if k in ALL_OPT and "longopt" in ALL_OPT[k]: longopt_list.append(option_longopt(k)) try: opt, dummy = getopt.gnu_getopt(argv, getopt_string, longopt_list) except getopt.GetoptError as error: fail_usage("Parse error: " + error.msg) # Transform longopt to short one which are used in fencing agents old_opt = opt opt = {} for old_option in dict(old_opt).keys(): if old_option.startswith("--"): for option in ALL_OPT.keys(): if "longopt" in ALL_OPT[option] and "--" + ALL_OPT[option]["longopt"] == old_option: opt["-" + ALL_OPT[option]["getopt"].rstrip(":")] = dict(old_opt)[old_option] else: opt[old_option] = dict(old_opt)[old_option] # Compatibility Layer (with what? probably not needed for fence_dummy) new_opt = dict(opt) if "-T" in new_opt: new_opt["-o"] = "status" if "-n" in new_opt: new_opt["-m"] = new_opt["-n"] opt = new_opt return opt def opts_from_stdin(avail_opt): """ Read options from standard input. """ opt = {} name = "" for line in sys.stdin.readlines(): line = line.strip() if line.startswith("#") or (len(line) == 0): continue (name, value) = (line + "=").split("=", 1) value = value[:-1] # Compatibility Layer (with what? probably not needed for fence_dummy) if name == "option": name = "action" if name not in avail_opt: print("Parse error: Ignoring unknown option '%s'" % line, file=sys.stderr) continue if ALL_OPT[name]["getopt"].endswith(":"): opt["-"+ALL_OPT[name]["getopt"].rstrip(":")] = value elif value.lower() in ["1", "yes", "on", "true"]: opt["-"+ALL_OPT[name]["getopt"]] = "1" return opt def process_input(avail_opt): """ Set standard environment variables, and parse all options. """ # Set standard environment os.putenv("LANG", "C") os.putenv("LC_ALL", "C") # Read options from command line or standard input if len(sys.argv) > 1: return opts_from_command_line(sys.argv[1:], avail_opt) else: return opts_from_stdin(avail_opt) def atexit_handler(): """ Close stdout on exit. """ try: sys.stdout.close() os.close(1) except IOError: sys.exit("%s failed to close standard output" % agent()) def success_mode(options, option, default_value): """ Return exit code specified by option. """ if option in options: test_value = options[option] else: test_value = default_value if test_value == "pass": exitcode = 0 elif test_value == "fail": exitcode = 1 else: exitcode = random.randint(0, 1) return exitcode def write_options(options): """ Write out all options to debug file. """ try: debugfile = io.open(options["-D"], 'at') debugfile.write("### %s ###\n" % (time.strftime("%Y-%m-%d %H:%M:%S"))) for option in sorted(options): debugfile.write("%s=%s\n" % (option, options[option])) debugfile.write("###\n") debugfile.close() except IOError: pass def main(): """ Make it so! """ global auto_unfence global no_reboot + global no_on # Meta-data can't take parameters, so we simulate different meta-data # behavior based on the executable name (which can be a symbolic link). - if (sys.argv[0].endswith("_auto_unfence")): + if sys.argv[0].endswith("_auto_unfence"): auto_unfence = True - elif (sys.argv[0].endswith("_no_reboot")): + elif sys.argv[0].endswith("_no_reboot"): no_reboot = True + elif sys.argv[0].endswith("_no_on"): + no_on = True device_opt = ALL_OPT.keys() ## Defaults for fence agent atexit.register(atexit_handler) options = process_input(device_opt) options["device_opt"] = device_opt show_docs(options) if "-o" in options: action = options["-o"] else: action = "reboot" # dump input to file if "-D" in options and action != "validate-all": write_options(options) if "-f" in options and action != "validate-all": val = int(options["-f"]) print("delay sleep for %d seconds" % val, file=sys.stderr) time.sleep(val) # random sleep for testing if "-R" in options and action != "validate-all": val = int(options["-R"]) ran = random.randint(1, val) print("random sleep for %d seconds" % ran, file=sys.stderr) time.sleep(ran) if action == "monitor": if "-d" in options: time.sleep(int(options["-d"])) exitcode = success_mode(options, "-m", "pass") elif action == "list": print("fence_dummy action (list) called", file=sys.stderr) if "-H" in options: print(options["-H"]) exitcode = 0 else: print("dynamic hostlist requires mock_dynamic_hosts to be set", file=sys.stderr) exitcode = 1 elif action == "validate-all": if "-f" in options: val = int(options["-f"]) if val > 10: exitcode = 1 else: exitcode = 0 else: exitcode = 1 else: exitcode = success_mode(options, "-M", "random") # Ensure we generate some error output on failure exit. if exitcode == 1: print("simulated %s failure" % action, file=sys.stderr) sys.exit(exitcode) if __name__ == "__main__": main() diff --git a/daemons/fenced/fenced_commands.c b/daemons/fenced/fenced_commands.c index ec80af4247..1cb1f5b1e5 100644 --- a/daemons/fenced/fenced_commands.c +++ b/daemons/fenced/fenced_commands.c @@ -1,3599 +1,3643 @@ /* * Copyright 2009-2022 the Pacemaker project contributors * * The version control history for this file may have further details. * * This source code is licensed under the GNU General Public License version 2 * or later (GPLv2+) WITHOUT ANY WARRANTY. */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include GHashTable *device_list = NULL; GHashTable *topology = NULL; static GList *cmd_list = NULL; static GHashTable *fenced_handlers = NULL; struct device_search_s { /* target of fence action */ char *host; /* requested fence action */ char *action; /* timeout to use if a device is queried dynamically for possible targets */ int per_device_timeout; /* number of registered fencing devices at time of request */ int replies_needed; /* number of device replies received so far */ int replies_received; /* whether the target is eligible to perform requested action (or off) */ bool allow_suicide; /* private data to pass to search callback function */ void *user_data; /* function to call when all replies have been received */ void (*callback) (GList * devices, void *user_data); /* devices capable of performing requested action (or off if remapping) */ GList *capable; /* Whether to perform searches that support the action */ uint32_t support_action_only; }; static gboolean stonith_device_dispatch(gpointer user_data); static void st_child_done(int pid, const pcmk__action_result_t *result, void *user_data); static void stonith_send_reply(xmlNode * reply, int call_options, const char *remote_peer, pcmk__client_t *client); static void search_devices_record_result(struct device_search_s *search, const char *device, gboolean can_fence); static int get_agent_metadata(const char *agent, xmlNode **metadata); static void read_action_metadata(stonith_device_t *device); static enum fenced_target_by unpack_level_kind(const xmlNode *level); typedef struct async_command_s { int id; int pid; int fd_stdout; int options; int default_timeout; /* seconds */ int timeout; /* seconds */ int start_delay; // seconds (-1 means disable static/random fencing delays) int delay_id; char *op; char *origin; char *client; char *client_name; char *remote_op_id; char *target; uint32_t target_nodeid; char *action; char *device; GList *device_list; GList *next_device_iter; // device_list entry for next device to execute void *internal_user_data; void (*done_cb) (int pid, const pcmk__action_result_t *result, void *user_data); guint timer_sigterm; guint timer_sigkill; /*! If the operation timed out, this is the last signal * we sent to the process to get it to terminate */ int last_timeout_signo; stonith_device_t *active_on; stonith_device_t *activating_on; } async_command_t; static xmlNode *construct_async_reply(const async_command_t *cmd, const pcmk__action_result_t *result); static gboolean is_action_required(const char *action, const stonith_device_t *device) { return device && device->automatic_unfencing && pcmk__str_eq(action, "on", pcmk__str_casei); } static int get_action_delay_max(const stonith_device_t *device, const char *action) { const char *value = NULL; int delay_max = 0; if (!pcmk__is_fencing_action(action)) { return 0; } value = g_hash_table_lookup(device->params, PCMK_STONITH_DELAY_MAX); if (value) { delay_max = crm_parse_interval_spec(value) / 1000; } return delay_max; } static int get_action_delay_base(const stonith_device_t *device, const char *action, const char *target) { char *hash_value = NULL; int delay_base = 0; if (!pcmk__is_fencing_action(action)) { return 0; } hash_value = g_hash_table_lookup(device->params, PCMK_STONITH_DELAY_BASE); if (hash_value) { char *value = strdup(hash_value); char *valptr = value; CRM_ASSERT(value != NULL); if (target != NULL) { for (char *val = strtok(value, "; \t"); val != NULL; val = strtok(NULL, "; \t")) { char *mapval = strchr(val, ':'); if (mapval == NULL || mapval[1] == 0) { crm_err("pcmk_delay_base: empty value in mapping", val); continue; } if (mapval != val && strncasecmp(target, val, (size_t)(mapval - val)) == 0) { value = mapval + 1; crm_debug("pcmk_delay_base mapped to %s for %s", value, target); break; } } } if (strchr(value, ':') == 0) { delay_base = crm_parse_interval_spec(value) / 1000; } free(valptr); } return delay_base; } /*! * \internal * \brief Override STONITH timeout with pcmk_*_timeout if available * * \param[in] device STONITH device to use * \param[in] action STONITH action name * \param[in] default_timeout Timeout to use if device does not have * a pcmk_*_timeout parameter for action * * \return Value of pcmk_(action)_timeout if available, otherwise default_timeout * \note For consistency, it would be nice if reboot/off/on timeouts could be * set the same way as start/stop/monitor timeouts, i.e. with an * entry in the fencing resource configuration. However that * is insufficient because fencing devices may be registered directly via * the fencer's register_device() API instead of going through the CIB * (e.g. stonith_admin uses it for its -R option, and the executor uses it * to ensure a device is registered when a command is issued). As device * properties, pcmk_*_timeout parameters can be grabbed by the fencer when * the device is registered, whether by CIB change or API call. */ static int get_action_timeout(const stonith_device_t *device, const char *action, int default_timeout) { if (action && device && device->params) { char buffer[64] = { 0, }; const char *value = NULL; /* If "reboot" was requested but the device does not support it, * we will remap to "off", so check timeout for "off" instead */ if (pcmk__str_eq(action, "reboot", pcmk__str_casei) && !pcmk_is_set(device->flags, st_device_supports_reboot)) { crm_trace("%s doesn't support reboot, using timeout for off instead", device->id); action = "off"; } /* If the device config specified an action-specific timeout, use it */ snprintf(buffer, sizeof(buffer), "pcmk_%s_timeout", action); value = g_hash_table_lookup(device->params, buffer); if (value) { return atoi(value); } } return default_timeout; } /*! * \internal * \brief Get the currently executing device for a fencing operation * * \param[in] cmd Fencing operation to check * * \return Currently executing device for \p cmd if any, otherwise NULL */ static stonith_device_t * cmd_device(const async_command_t *cmd) { if ((cmd == NULL) || (cmd->device == NULL) || (device_list == NULL)) { return NULL; } return g_hash_table_lookup(device_list, cmd->device); } +/*! + * \internal + * \brief Return the configured reboot action for a given device + * + * \param[in] device_id Device ID + * + * \return Configured reboot action for \p device_id + */ +const char * +fenced_device_reboot_action(const char *device_id) +{ + const char *action = NULL; + + if ((device_list != NULL) && (device_id != NULL)) { + stonith_device_t *device = g_hash_table_lookup(device_list, device_id); + + if ((device != NULL) && (device->params != NULL)) { + action = g_hash_table_lookup(device->params, "pcmk_reboot_action"); + } + } + return pcmk__s(action, "reboot"); +} + +/*! + * \internal + * \brief Check whether a given device supports the "on" action + * + * \param[in] device_id Device ID + * + * \return true if \p device_id supports "on", otherwise false + */ +bool +fenced_device_supports_on(const char *device_id) +{ + if ((device_list != NULL) && (device_id != NULL)) { + stonith_device_t *device = g_hash_table_lookup(device_list, device_id); + + if (device != NULL) { + return pcmk_is_set(device->flags, st_device_supports_on); + } + } + return false; +} + static void free_async_command(async_command_t * cmd) { if (!cmd) { return; } if (cmd->delay_id) { g_source_remove(cmd->delay_id); } cmd_list = g_list_remove(cmd_list, cmd); g_list_free_full(cmd->device_list, free); free(cmd->device); free(cmd->action); free(cmd->target); free(cmd->remote_op_id); free(cmd->client); free(cmd->client_name); free(cmd->origin); free(cmd->op); free(cmd); } /*! * \internal * \brief Create a new asynchronous fencing operation from request XML * * \param[in] msg Fencing request XML (from IPC or CPG) * * \return Newly allocated fencing operation on success, otherwise NULL * * \note This asserts on memory errors, so a NULL return indicates an * unparseable message. */ static async_command_t * create_async_command(xmlNode *msg) { xmlNode *op = NULL; async_command_t *cmd = NULL; if (msg == NULL) { return NULL; } op = get_xpath_object("//@" F_STONITH_ACTION, msg, LOG_ERR); if (op == NULL) { return NULL; } cmd = calloc(1, sizeof(async_command_t)); CRM_ASSERT(cmd != NULL); // All messages must include these cmd->action = crm_element_value_copy(op, F_STONITH_ACTION); cmd->op = crm_element_value_copy(msg, F_STONITH_OPERATION); cmd->client = crm_element_value_copy(msg, F_STONITH_CLIENTID); if ((cmd->action == NULL) || (cmd->op == NULL) || (cmd->client == NULL)) { free_async_command(cmd); return NULL; } crm_element_value_int(msg, F_STONITH_CALLID, &(cmd->id)); crm_element_value_int(msg, F_STONITH_CALLOPTS, &(cmd->options)); crm_element_value_int(msg, F_STONITH_DELAY, &(cmd->start_delay)); crm_element_value_int(msg, F_STONITH_TIMEOUT, &(cmd->default_timeout)); cmd->timeout = cmd->default_timeout; cmd->origin = crm_element_value_copy(msg, F_ORIG); cmd->remote_op_id = crm_element_value_copy(msg, F_STONITH_REMOTE_OP_ID); cmd->client_name = crm_element_value_copy(msg, F_STONITH_CLIENTNAME); cmd->target = crm_element_value_copy(op, F_STONITH_TARGET); cmd->device = crm_element_value_copy(op, F_STONITH_DEVICE); cmd->done_cb = st_child_done; // Track in global command list cmd_list = g_list_append(cmd_list, cmd); return cmd; } static int get_action_limit(stonith_device_t * device) { const char *value = NULL; int action_limit = 1; value = g_hash_table_lookup(device->params, PCMK_STONITH_ACTION_LIMIT); if ((value == NULL) || (pcmk__scan_min_int(value, &action_limit, INT_MIN) != pcmk_rc_ok) || (action_limit == 0)) { action_limit = 1; } return action_limit; } static int get_active_cmds(stonith_device_t * device) { int counter = 0; GList *gIter = NULL; GList *gIterNext = NULL; CRM_CHECK(device != NULL, return 0); for (gIter = cmd_list; gIter != NULL; gIter = gIterNext) { async_command_t *cmd = gIter->data; gIterNext = gIter->next; if (cmd->active_on == device) { counter++; } } return counter; } static void fork_cb(int pid, void *user_data) { async_command_t *cmd = (async_command_t *) user_data; stonith_device_t * device = /* in case of a retry we've done the move from activating_on to active_on already */ cmd->activating_on?cmd->activating_on:cmd->active_on; CRM_ASSERT(device); crm_debug("Operation '%s' [%d]%s%s using %s now running with %ds timeout", cmd->action, pid, ((cmd->target == NULL)? "" : " targeting "), pcmk__s(cmd->target, ""), device->id, cmd->timeout); cmd->active_on = device; cmd->activating_on = NULL; } static int get_agent_metadata_cb(gpointer data) { stonith_device_t *device = data; guint period_ms; switch (get_agent_metadata(device->agent, &device->agent_metadata)) { case pcmk_rc_ok: if (device->agent_metadata) { read_action_metadata(device); stonith__device_parameter_flags(&(device->flags), device->id, device->agent_metadata); } return G_SOURCE_REMOVE; case EAGAIN: period_ms = pcmk__mainloop_timer_get_period(device->timer); if (period_ms < 160 * 1000) { mainloop_timer_set_period(device->timer, 2 * period_ms); } return G_SOURCE_CONTINUE; default: return G_SOURCE_REMOVE; } } /*! * \internal * \brief Call a command's action callback for an internal (not library) result * * \param[in,out] cmd Command to report result for * \param[in] execution_status Execution status to use for result * \param[in] exit_status Exit status to use for result * \param[in] exit_reason Exit reason to use for result */ static void report_internal_result(async_command_t *cmd, int exit_status, int execution_status, const char *exit_reason) { pcmk__action_result_t result = PCMK__UNKNOWN_RESULT; pcmk__set_result(&result, exit_status, execution_status, exit_reason); cmd->done_cb(0, &result, cmd); pcmk__reset_result(&result); } static gboolean stonith_device_execute(stonith_device_t * device) { int exec_rc = 0; const char *action_str = NULL; const char *host_arg = NULL; async_command_t *cmd = NULL; stonith_action_t *action = NULL; int active_cmds = 0; int action_limit = 0; GList *gIter = NULL; GList *gIterNext = NULL; CRM_CHECK(device != NULL, return FALSE); active_cmds = get_active_cmds(device); action_limit = get_action_limit(device); if (action_limit > -1 && active_cmds >= action_limit) { crm_trace("%s is over its action limit of %d (%u active action%s)", device->id, action_limit, active_cmds, pcmk__plural_s(active_cmds)); return TRUE; } for (gIter = device->pending_ops; gIter != NULL; gIter = gIterNext) { async_command_t *pending_op = gIter->data; gIterNext = gIter->next; if (pending_op && pending_op->delay_id) { crm_trace("Operation '%s'%s%s using %s was asked to run too early, " "waiting for start delay of %ds", pending_op->action, ((pending_op->target == NULL)? "" : " targeting "), pcmk__s(pending_op->target, ""), device->id, pending_op->start_delay); continue; } device->pending_ops = g_list_remove_link(device->pending_ops, gIter); g_list_free_1(gIter); cmd = pending_op; break; } if (cmd == NULL) { crm_trace("No actions using %s are needed", device->id); return TRUE; } if (pcmk__str_any_of(device->agent, STONITH_WATCHDOG_AGENT, STONITH_WATCHDOG_AGENT_INTERNAL, NULL)) { if (pcmk__is_fencing_action(cmd->action)) { if (node_does_watchdog_fencing(stonith_our_uname)) { pcmk__panic(__func__); goto done; } } else { crm_info("Faking success for %s watchdog operation", cmd->action); report_internal_result(cmd, CRM_EX_OK, PCMK_EXEC_DONE, NULL); goto done; } } #if SUPPORT_CIBSECRETS exec_rc = pcmk__substitute_secrets(device->id, device->params); if (exec_rc != pcmk_rc_ok) { if (pcmk__str_eq(cmd->action, "stop", pcmk__str_casei)) { crm_info("Proceeding with stop operation for %s " "despite being unable to load CIB secrets (%s)", device->id, pcmk_rc_str(exec_rc)); } else { crm_err("Considering %s unconfigured " "because unable to load CIB secrets: %s", device->id, pcmk_rc_str(exec_rc)); report_internal_result(cmd, CRM_EX_ERROR, PCMK_EXEC_NO_SECRETS, "Failed to get CIB secrets"); goto done; } } #endif action_str = cmd->action; if (pcmk__str_eq(cmd->action, "reboot", pcmk__str_casei) && !pcmk_is_set(device->flags, st_device_supports_reboot)) { crm_notice("Remapping 'reboot' action%s%s using %s to 'off' " "because agent '%s' does not support reboot", ((cmd->target == NULL)? "" : " targeting "), pcmk__s(cmd->target, ""), device->id, device->agent); action_str = "off"; } if (pcmk_is_set(device->flags, st_device_supports_parameter_port)) { host_arg = "port"; } else if (pcmk_is_set(device->flags, st_device_supports_parameter_plug)) { host_arg = "plug"; } action = stonith__action_create(device->agent, action_str, cmd->target, cmd->target_nodeid, cmd->timeout, device->params, device->aliases, host_arg); /* for async exec, exec_rc is negative for early error exit otherwise handling of success/errors is done via callbacks */ cmd->activating_on = device; exec_rc = stonith__execute_async(action, (void *)cmd, cmd->done_cb, fork_cb); if (exec_rc < 0) { cmd->activating_on = NULL; cmd->done_cb(0, stonith__action_result(action), cmd); stonith__destroy_action(action); } done: /* Device might get triggered to work by multiple fencing commands * simultaneously. Trigger the device again to make sure any * remaining concurrent commands get executed. */ if (device->pending_ops) { mainloop_set_trigger(device->work); } return TRUE; } static gboolean stonith_device_dispatch(gpointer user_data) { return stonith_device_execute(user_data); } static gboolean start_delay_helper(gpointer data) { async_command_t *cmd = data; stonith_device_t *device = cmd_device(cmd); cmd->delay_id = 0; if (device) { mainloop_set_trigger(device->work); } return FALSE; } static void schedule_stonith_command(async_command_t * cmd, stonith_device_t * device) { int delay_max = 0; int delay_base = 0; int requested_delay = cmd->start_delay; CRM_CHECK(cmd != NULL, return); CRM_CHECK(device != NULL, return); if (cmd->device) { free(cmd->device); } if (device->include_nodeid && (cmd->target != NULL)) { crm_node_t *node = crm_get_peer(0, cmd->target); cmd->target_nodeid = node->id; } cmd->device = strdup(device->id); cmd->timeout = get_action_timeout(device, cmd->action, cmd->default_timeout); if (cmd->remote_op_id) { crm_debug("Scheduling '%s' action%s%s using %s for remote peer %s " "with op id %.8s and timeout %ds", cmd->action, (cmd->target == NULL)? "" : " targeting ", pcmk__s(cmd->target, ""), device->id, cmd->origin, cmd->remote_op_id, cmd->timeout); } else { crm_debug("Scheduling '%s' action%s%s using %s for %s with timeout %ds", cmd->action, (cmd->target == NULL)? "" : " targeting ", pcmk__s(cmd->target, ""), device->id, cmd->client, cmd->timeout); } device->pending_ops = g_list_append(device->pending_ops, cmd); mainloop_set_trigger(device->work); // Value -1 means disable any static/random fencing delays if (requested_delay < 0) { return; } delay_max = get_action_delay_max(device, cmd->action); delay_base = get_action_delay_base(device, cmd->action, cmd->target); if (delay_max == 0) { delay_max = delay_base; } if (delay_max < delay_base) { crm_warn(PCMK_STONITH_DELAY_BASE " (%ds) is larger than " PCMK_STONITH_DELAY_MAX " (%ds) for %s using %s " "(limiting to maximum delay)", delay_base, delay_max, cmd->action, device->id); delay_base = delay_max; } if (delay_max > 0) { // coverity[dont_call] We're not using rand() for security cmd->start_delay += ((delay_max != delay_base)?(rand() % (delay_max - delay_base)):0) + delay_base; } if (cmd->start_delay > 0) { crm_notice("Delaying '%s' action%s%s using %s for %ds " CRM_XS " timeout=%ds requested_delay=%ds base=%ds max=%ds", cmd->action, (cmd->target == NULL)? "" : " targeting ", pcmk__s(cmd->target, ""), device->id, cmd->start_delay, cmd->timeout, requested_delay, delay_base, delay_max); cmd->delay_id = g_timeout_add_seconds(cmd->start_delay, start_delay_helper, cmd); } } static void free_device(gpointer data) { GList *gIter = NULL; stonith_device_t *device = data; g_hash_table_destroy(device->params); g_hash_table_destroy(device->aliases); for (gIter = device->pending_ops; gIter != NULL; gIter = gIter->next) { async_command_t *cmd = gIter->data; crm_warn("Removal of device '%s' purged operation '%s'", device->id, cmd->action); report_internal_result(cmd, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE, "Device was removed before action could be executed"); } g_list_free(device->pending_ops); g_list_free_full(device->targets, free); if (device->timer) { mainloop_timer_stop(device->timer); mainloop_timer_del(device->timer); } mainloop_destroy_trigger(device->work); free_xml(device->agent_metadata); free(device->namespace); if (device->on_target_actions != NULL) { g_string_free(device->on_target_actions, TRUE); } free(device->agent); free(device->id); free(device); } void free_device_list(void) { if (device_list != NULL) { g_hash_table_destroy(device_list); device_list = NULL; } } void init_device_list(void) { if (device_list == NULL) { device_list = pcmk__strkey_table(NULL, free_device); } } static GHashTable * build_port_aliases(const char *hostmap, GList ** targets) { char *name = NULL; int last = 0, lpc = 0, max = 0, added = 0; GHashTable *aliases = pcmk__strikey_table(free, free); if (hostmap == NULL) { return aliases; } max = strlen(hostmap); for (; lpc <= max; lpc++) { switch (hostmap[lpc]) { /* Skip escaped chars */ case '\\': lpc++; break; /* Assignment chars */ case '=': case ':': if (lpc > last) { free(name); name = calloc(1, 1 + lpc - last); memcpy(name, hostmap + last, lpc - last); } last = lpc + 1; break; /* Delimeter chars */ /* case ',': Potentially used to specify multiple ports */ case 0: case ';': case ' ': case '\t': if (name) { char *value = NULL; int k = 0; value = calloc(1, 1 + lpc - last); memcpy(value, hostmap + last, lpc - last); for (int i = 0; value[i] != '\0'; i++) { if (value[i] != '\\') { value[k++] = value[i]; } } value[k] = '\0'; crm_debug("Adding alias '%s'='%s'", name, value); g_hash_table_replace(aliases, name, value); if (targets) { *targets = g_list_append(*targets, strdup(value)); } value = NULL; name = NULL; added++; } else if (lpc > last) { crm_debug("Parse error at offset %d near '%s'", lpc - last, hostmap + last); } last = lpc + 1; break; } if (hostmap[lpc] == 0) { break; } } if (added == 0) { crm_info("No host mappings detected in '%s'", hostmap); } free(name); return aliases; } GHashTable *metadata_cache = NULL; void free_metadata_cache(void) { if (metadata_cache != NULL) { g_hash_table_destroy(metadata_cache); metadata_cache = NULL; } } static void init_metadata_cache(void) { if (metadata_cache == NULL) { metadata_cache = pcmk__strkey_table(free, free); } } int get_agent_metadata(const char *agent, xmlNode ** metadata) { char *buffer = NULL; if (metadata == NULL) { return EINVAL; } *metadata = NULL; if (pcmk__str_eq(agent, STONITH_WATCHDOG_AGENT_INTERNAL, pcmk__str_none)) { return pcmk_rc_ok; } init_metadata_cache(); buffer = g_hash_table_lookup(metadata_cache, agent); if (buffer == NULL) { stonith_t *st = stonith_api_new(); int rc; if (st == NULL) { crm_warn("Could not get agent meta-data: " "API memory allocation failed"); return EAGAIN; } rc = st->cmds->metadata(st, st_opt_sync_call, agent, NULL, &buffer, 10); stonith_api_delete(st); if (rc || !buffer) { crm_err("Could not retrieve metadata for fencing agent %s", agent); return EAGAIN; } g_hash_table_replace(metadata_cache, strdup(agent), buffer); } *metadata = string2xml(buffer); return pcmk_rc_ok; } static gboolean is_nodeid_required(xmlNode * xml) { xmlXPathObjectPtr xpath = NULL; if (stand_alone) { return FALSE; } if (!xml) { return FALSE; } xpath = xpath_search(xml, "//parameter[@name='nodeid']"); if (numXpathResults(xpath) <= 0) { freeXpathObject(xpath); return FALSE; } freeXpathObject(xpath); return TRUE; } static void read_action_metadata(stonith_device_t *device) { xmlXPathObjectPtr xpath = NULL; int max = 0; int lpc = 0; if (device->agent_metadata == NULL) { return; } xpath = xpath_search(device->agent_metadata, "//action"); max = numXpathResults(xpath); if (max <= 0) { freeXpathObject(xpath); return; } for (lpc = 0; lpc < max; lpc++) { const char *action = NULL; xmlNode *match = getXpathResult(xpath, lpc); CRM_LOG_ASSERT(match != NULL); if(match == NULL) { continue; }; action = crm_element_value(match, "name"); if(pcmk__str_eq(action, "list", pcmk__str_casei)) { stonith__set_device_flags(device->flags, device->id, st_device_supports_list); } else if(pcmk__str_eq(action, "status", pcmk__str_casei)) { stonith__set_device_flags(device->flags, device->id, st_device_supports_status); } else if(pcmk__str_eq(action, "reboot", pcmk__str_casei)) { stonith__set_device_flags(device->flags, device->id, st_device_supports_reboot); } else if (pcmk__str_eq(action, "on", pcmk__str_casei)) { /* "automatic" means the cluster will unfence node when it joins */ /* "required" is a deprecated synonym for "automatic" */ if (pcmk__xe_attr_is_true(match, "automatic") || pcmk__xe_attr_is_true(match, "required")) { device->automatic_unfencing = TRUE; } stonith__set_device_flags(device->flags, device->id, st_device_supports_on); } if ((action != NULL) && pcmk__xe_attr_is_true(match, "on_target")) { pcmk__add_word(&(device->on_target_actions), 64, action); } } freeXpathObject(xpath); } /*! * \internal * \brief Set a pcmk_*_action parameter if not already set * * \param[in,out] params Device parameters * \param[in] action Name of action * \param[in] value Value to use if action is not already set */ static void map_action(GHashTable *params, const char *action, const char *value) { char *key = crm_strdup_printf("pcmk_%s_action", action); if (g_hash_table_lookup(params, key)) { crm_warn("Ignoring %s='%s', see %s instead", STONITH_ATTR_ACTION_OP, value, key); free(key); } else { crm_warn("Mapping %s='%s' to %s='%s'", STONITH_ATTR_ACTION_OP, value, key, value); g_hash_table_insert(params, key, strdup(value)); } } /*! * \internal * \brief Create device parameter table from XML * * \param[in] name Device name (used for logging only) * \param[in] dev XML containing device parameters */ static GHashTable * xml2device_params(const char *name, const xmlNode *dev) { GHashTable *params = xml2list(dev); const char *value; /* Action should never be specified in the device configuration, * but we support it for users who are familiar with other software * that worked that way. */ value = g_hash_table_lookup(params, STONITH_ATTR_ACTION_OP); if (value != NULL) { crm_warn("%s has '%s' parameter, which should never be specified in configuration", name, STONITH_ATTR_ACTION_OP); if (*value == '\0') { crm_warn("Ignoring empty '%s' parameter", STONITH_ATTR_ACTION_OP); } else if (strcmp(value, "reboot") == 0) { crm_warn("Ignoring %s='reboot' (see stonith-action cluster property instead)", STONITH_ATTR_ACTION_OP); } else if (strcmp(value, "off") == 0) { map_action(params, "reboot", value); } else { map_action(params, "off", value); map_action(params, "reboot", value); } g_hash_table_remove(params, STONITH_ATTR_ACTION_OP); } return params; } static const char * target_list_type(stonith_device_t * dev) { const char *check_type = NULL; check_type = g_hash_table_lookup(dev->params, PCMK_STONITH_HOST_CHECK); if (check_type == NULL) { if (g_hash_table_lookup(dev->params, PCMK_STONITH_HOST_LIST)) { check_type = "static-list"; } else if (g_hash_table_lookup(dev->params, PCMK_STONITH_HOST_MAP)) { check_type = "static-list"; } else if (pcmk_is_set(dev->flags, st_device_supports_list)) { check_type = "dynamic-list"; } else if (pcmk_is_set(dev->flags, st_device_supports_status)) { check_type = "status"; } else { check_type = PCMK__VALUE_NONE; } } return check_type; } static stonith_device_t * build_device_from_xml(xmlNode *dev) { const char *value; stonith_device_t *device = NULL; char *agent = crm_element_value_copy(dev, "agent"); CRM_CHECK(agent != NULL, return device); device = calloc(1, sizeof(stonith_device_t)); CRM_CHECK(device != NULL, {free(agent); return device;}); device->id = crm_element_value_copy(dev, XML_ATTR_ID); device->agent = agent; device->namespace = crm_element_value_copy(dev, "namespace"); device->params = xml2device_params(device->id, dev); value = g_hash_table_lookup(device->params, PCMK_STONITH_HOST_LIST); if (value) { device->targets = stonith__parse_targets(value); } value = g_hash_table_lookup(device->params, PCMK_STONITH_HOST_MAP); device->aliases = build_port_aliases(value, &(device->targets)); value = target_list_type(device); if (!pcmk__str_eq(value, "static-list", pcmk__str_casei) && device->targets) { /* Other than "static-list", dev-> targets is unnecessary. */ g_list_free_full(device->targets, free); device->targets = NULL; } switch (get_agent_metadata(device->agent, &device->agent_metadata)) { case pcmk_rc_ok: if (device->agent_metadata) { read_action_metadata(device); stonith__device_parameter_flags(&(device->flags), device->id, device->agent_metadata); } break; case EAGAIN: if (device->timer == NULL) { device->timer = mainloop_timer_add("get_agent_metadata", 10 * 1000, TRUE, get_agent_metadata_cb, device); } if (!mainloop_timer_running(device->timer)) { mainloop_timer_start(device->timer); } break; default: break; } value = g_hash_table_lookup(device->params, "nodeid"); if (!value) { device->include_nodeid = is_nodeid_required(device->agent_metadata); } value = crm_element_value(dev, "rsc_provides"); if (pcmk__str_eq(value, PCMK__VALUE_UNFENCING, pcmk__str_casei)) { device->automatic_unfencing = TRUE; } if (is_action_required("on", device)) { crm_info("Fencing device '%s' requires unfencing", device->id); } if (device->on_target_actions != NULL) { crm_info("Fencing device '%s' requires actions (%s) to be executed " "on target", device->id, (const char *) device->on_target_actions->str); } device->work = mainloop_add_trigger(G_PRIORITY_HIGH, stonith_device_dispatch, device); /* TODO: Hook up priority */ return device; } static void schedule_internal_command(const char *origin, stonith_device_t * device, const char *action, const char *target, int timeout, void *internal_user_data, void (*done_cb) (int pid, const pcmk__action_result_t *result, void *user_data)) { async_command_t *cmd = NULL; cmd = calloc(1, sizeof(async_command_t)); cmd->id = -1; cmd->default_timeout = timeout ? timeout : 60; cmd->timeout = cmd->default_timeout; cmd->action = strdup(action); pcmk__str_update(&cmd->target, target); cmd->device = strdup(device->id); cmd->origin = strdup(origin); cmd->client = strdup(crm_system_name); cmd->client_name = strdup(crm_system_name); cmd->internal_user_data = internal_user_data; cmd->done_cb = done_cb; /* cmd, not internal_user_data, is passed to 'done_cb' as the userdata */ schedule_stonith_command(cmd, device); } // Fence agent status commands use custom exit status codes enum fence_status_code { fence_status_invalid = -1, fence_status_active = 0, fence_status_unknown = 1, fence_status_inactive = 2, }; static void status_search_cb(int pid, const pcmk__action_result_t *result, void *user_data) { async_command_t *cmd = user_data; struct device_search_s *search = cmd->internal_user_data; stonith_device_t *dev = cmd_device(cmd); gboolean can = FALSE; free_async_command(cmd); if (!dev) { search_devices_record_result(search, NULL, FALSE); return; } mainloop_set_trigger(dev->work); if (result->execution_status != PCMK_EXEC_DONE) { crm_warn("Assuming %s cannot fence %s " "because status could not be executed: %s%s%s%s", dev->id, search->host, pcmk_exec_status_str(result->execution_status), ((result->exit_reason == NULL)? "" : " ("), ((result->exit_reason == NULL)? "" : result->exit_reason), ((result->exit_reason == NULL)? "" : ")")); search_devices_record_result(search, dev->id, FALSE); return; } switch (result->exit_status) { case fence_status_unknown: crm_trace("%s reported it cannot fence %s", dev->id, search->host); break; case fence_status_active: case fence_status_inactive: crm_trace("%s reported it can fence %s", dev->id, search->host); can = TRUE; break; default: crm_warn("Assuming %s cannot fence %s " "(status returned unknown code %d)", dev->id, search->host, result->exit_status); break; } search_devices_record_result(search, dev->id, can); } static void dynamic_list_search_cb(int pid, const pcmk__action_result_t *result, void *user_data) { async_command_t *cmd = user_data; struct device_search_s *search = cmd->internal_user_data; stonith_device_t *dev = cmd_device(cmd); gboolean can_fence = FALSE; free_async_command(cmd); /* Host/alias must be in the list output to be eligible to be fenced * * Will cause problems if down'd nodes aren't listed or (for virtual nodes) * if the guest is still listed despite being moved to another machine */ if (!dev) { search_devices_record_result(search, NULL, FALSE); return; } mainloop_set_trigger(dev->work); if (pcmk__result_ok(result)) { crm_info("Refreshing target list for %s", dev->id); g_list_free_full(dev->targets, free); dev->targets = stonith__parse_targets(result->action_stdout); dev->targets_age = time(NULL); } else if (dev->targets != NULL) { if (result->execution_status == PCMK_EXEC_DONE) { crm_info("Reusing most recent target list for %s " "because list returned error code %d", dev->id, result->exit_status); } else { crm_info("Reusing most recent target list for %s " "because list could not be executed: %s%s%s%s", dev->id, pcmk_exec_status_str(result->execution_status), ((result->exit_reason == NULL)? "" : " ("), ((result->exit_reason == NULL)? "" : result->exit_reason), ((result->exit_reason == NULL)? "" : ")")); } } else { // We have never successfully executed list if (result->execution_status == PCMK_EXEC_DONE) { crm_warn("Assuming %s cannot fence %s " "because list returned error code %d", dev->id, search->host, result->exit_status); } else { crm_warn("Assuming %s cannot fence %s " "because list could not be executed: %s%s%s%s", dev->id, search->host, pcmk_exec_status_str(result->execution_status), ((result->exit_reason == NULL)? "" : " ("), ((result->exit_reason == NULL)? "" : result->exit_reason), ((result->exit_reason == NULL)? "" : ")")); } /* Fall back to pcmk_host_check="status" if the user didn't explicitly * specify "dynamic-list". */ if (g_hash_table_lookup(dev->params, PCMK_STONITH_HOST_CHECK) == NULL) { crm_notice("Switching to pcmk_host_check='status' for %s", dev->id); g_hash_table_replace(dev->params, strdup(PCMK_STONITH_HOST_CHECK), strdup("status")); } } if (dev->targets) { const char *alias = g_hash_table_lookup(dev->aliases, search->host); if (!alias) { alias = search->host; } if (pcmk__str_in_list(alias, dev->targets, pcmk__str_casei)) { can_fence = TRUE; } } search_devices_record_result(search, dev->id, can_fence); } /*! * \internal * \brief Returns true if any key in first is not in second or second has a different value for key */ static int device_params_diff(GHashTable *first, GHashTable *second) { char *key = NULL; char *value = NULL; GHashTableIter gIter; g_hash_table_iter_init(&gIter, first); while (g_hash_table_iter_next(&gIter, (void **)&key, (void **)&value)) { if(strstr(key, "CRM_meta") == key) { continue; } else if(strcmp(key, "crm_feature_set") == 0) { continue; } else { char *other_value = g_hash_table_lookup(second, key); if (!other_value || !pcmk__str_eq(other_value, value, pcmk__str_casei)) { crm_trace("Different value for %s: %s != %s", key, other_value, value); return 1; } } } return 0; } /*! * \internal * \brief Checks to see if an identical device already exists in the device_list */ static stonith_device_t * device_has_duplicate(const stonith_device_t *device) { stonith_device_t *dup = g_hash_table_lookup(device_list, device->id); if (!dup) { crm_trace("No match for %s", device->id); return NULL; } else if (!pcmk__str_eq(dup->agent, device->agent, pcmk__str_casei)) { crm_trace("Different agent: %s != %s", dup->agent, device->agent); return NULL; } /* Use calculate_operation_digest() here? */ if (device_params_diff(device->params, dup->params) || device_params_diff(dup->params, device->params)) { return NULL; } crm_trace("Match"); return dup; } int stonith_device_register(xmlNode *dev, gboolean from_cib) { stonith_device_t *dup = NULL; stonith_device_t *device = build_device_from_xml(dev); guint ndevices = 0; int rv = pcmk_ok; CRM_CHECK(device != NULL, return -ENOMEM); /* do we have a watchdog-device? */ if (pcmk__str_eq(device->id, STONITH_WATCHDOG_ID, pcmk__str_none) || pcmk__str_any_of(device->agent, STONITH_WATCHDOG_AGENT, STONITH_WATCHDOG_AGENT_INTERNAL, NULL)) do { if (stonith_watchdog_timeout_ms <= 0) { crm_err("Ignoring watchdog fence device without " "stonith-watchdog-timeout set."); rv = -ENODEV; /* fall through to cleanup & return */ } else if (!pcmk__str_any_of(device->agent, STONITH_WATCHDOG_AGENT, STONITH_WATCHDOG_AGENT_INTERNAL, NULL)) { crm_err("Ignoring watchdog fence device with unknown " "agent '%s' unequal '" STONITH_WATCHDOG_AGENT "'.", device->agent?device->agent:""); rv = -ENODEV; /* fall through to cleanup & return */ } else if (!pcmk__str_eq(device->id, STONITH_WATCHDOG_ID, pcmk__str_none)) { crm_err("Ignoring watchdog fence device " "named %s !='"STONITH_WATCHDOG_ID"'.", device->id?device->id:""); rv = -ENODEV; /* fall through to cleanup & return */ } else { if (pcmk__str_eq(device->agent, STONITH_WATCHDOG_AGENT, pcmk__str_none)) { /* this either has an empty list or the targets configured for watchdog-fencing */ g_list_free_full(stonith_watchdog_targets, free); stonith_watchdog_targets = device->targets; device->targets = NULL; } if (node_does_watchdog_fencing(stonith_our_uname)) { g_list_free_full(device->targets, free); device->targets = stonith__parse_targets(stonith_our_uname); g_hash_table_replace(device->params, strdup(PCMK_STONITH_HOST_LIST), strdup(stonith_our_uname)); /* proceed as with any other stonith-device */ break; } crm_debug("Skip registration of watchdog fence device on node not in host-list."); /* cleanup and fall through to more cleanup and return */ device->targets = NULL; stonith_device_remove(device->id, from_cib); } free_device(device); return rv; } while (0); dup = device_has_duplicate(device); if (dup) { ndevices = g_hash_table_size(device_list); crm_debug("Device '%s' already in device list (%d active device%s)", device->id, ndevices, pcmk__plural_s(ndevices)); free_device(device); device = dup; dup = g_hash_table_lookup(device_list, device->id); dup->dirty = FALSE; } else { stonith_device_t *old = g_hash_table_lookup(device_list, device->id); if (from_cib && old && old->api_registered) { /* If the cib is writing over an entry that is shared with a stonith client, * copy any pending ops that currently exist on the old entry to the new one. * Otherwise the pending ops will be reported as failures */ crm_info("Overwriting existing entry for %s from CIB", device->id); device->pending_ops = old->pending_ops; device->api_registered = TRUE; old->pending_ops = NULL; if (device->pending_ops) { mainloop_set_trigger(device->work); } } g_hash_table_replace(device_list, device->id, device); ndevices = g_hash_table_size(device_list); crm_notice("Added '%s' to device list (%d active device%s)", device->id, ndevices, pcmk__plural_s(ndevices)); } if (from_cib) { device->cib_registered = TRUE; } else { device->api_registered = TRUE; } return pcmk_ok; } void stonith_device_remove(const char *id, bool from_cib) { stonith_device_t *device = g_hash_table_lookup(device_list, id); guint ndevices = 0; if (!device) { ndevices = g_hash_table_size(device_list); crm_info("Device '%s' not found (%d active device%s)", id, ndevices, pcmk__plural_s(ndevices)); return; } if (from_cib) { device->cib_registered = FALSE; } else { device->verified = FALSE; device->api_registered = FALSE; } if (!device->cib_registered && !device->api_registered) { g_hash_table_remove(device_list, id); ndevices = g_hash_table_size(device_list); crm_info("Removed '%s' from device list (%d active device%s)", id, ndevices, pcmk__plural_s(ndevices)); } else { crm_trace("Not removing '%s' from device list (%d active) because " "still registered via:%s%s", id, g_hash_table_size(device_list), (device->cib_registered? " cib" : ""), (device->api_registered? " api" : "")); } } /*! * \internal * \brief Return the number of stonith levels registered for a node * * \param[in] tp Node's topology table entry * * \return Number of non-NULL levels in topology entry * \note This function is used only for log messages. */ static int count_active_levels(const stonith_topology_t *tp) { int lpc = 0; int count = 0; for (lpc = 0; lpc < ST_LEVEL_MAX; lpc++) { if (tp->levels[lpc] != NULL) { count++; } } return count; } static void free_topology_entry(gpointer data) { stonith_topology_t *tp = data; int lpc = 0; for (lpc = 0; lpc < ST_LEVEL_MAX; lpc++) { if (tp->levels[lpc] != NULL) { g_list_free_full(tp->levels[lpc], free); } } free(tp->target); free(tp->target_value); free(tp->target_pattern); free(tp->target_attribute); free(tp); } void free_topology_list(void) { if (topology != NULL) { g_hash_table_destroy(topology); topology = NULL; } } void init_topology_list(void) { if (topology == NULL) { topology = pcmk__strkey_table(NULL, free_topology_entry); } } char * stonith_level_key(const xmlNode *level, enum fenced_target_by mode) { if (mode == fenced_target_by_unknown) { mode = unpack_level_kind(level); } switch (mode) { case fenced_target_by_name: return crm_element_value_copy(level, XML_ATTR_STONITH_TARGET); case fenced_target_by_pattern: return crm_element_value_copy(level, XML_ATTR_STONITH_TARGET_PATTERN); case fenced_target_by_attribute: return crm_strdup_printf("%s=%s", crm_element_value(level, XML_ATTR_STONITH_TARGET_ATTRIBUTE), crm_element_value(level, XML_ATTR_STONITH_TARGET_VALUE)); default: return crm_strdup_printf("unknown-%s", ID(level)); } } /*! * \internal * \brief Parse target identification from topology level XML * * \param[in] level Topology level XML to parse * * \return How to identify target of \p level */ static int unpack_level_kind(const xmlNode *level) { if (crm_element_value(level, XML_ATTR_STONITH_TARGET) != NULL) { return fenced_target_by_name; } if (crm_element_value(level, XML_ATTR_STONITH_TARGET_PATTERN) != NULL) { return fenced_target_by_pattern; } if (!stand_alone /* if standalone, there's no attribute manager */ && (crm_element_value(level, XML_ATTR_STONITH_TARGET_ATTRIBUTE) != NULL) && (crm_element_value(level, XML_ATTR_STONITH_TARGET_VALUE) != NULL)) { return fenced_target_by_attribute; } return fenced_target_by_unknown; } static stonith_key_value_t * parse_device_list(const char *devices) { int lpc = 0; int max = 0; int last = 0; stonith_key_value_t *output = NULL; if (devices == NULL) { return output; } max = strlen(devices); for (lpc = 0; lpc <= max; lpc++) { if (devices[lpc] == ',' || devices[lpc] == 0) { char *line = strndup(devices + last, lpc - last); output = stonith_key_value_add(output, NULL, line); free(line); last = lpc + 1; } } return output; } /*! * \internal * \brief Unpack essential information from topology request XML * * \param[in] xml Request XML to search * \param[out] mode If not NULL, where to store level kind * \param[out] target If not NULL, where to store representation of target * \param[out] id If not NULL, where to store level number * \param[out] desc If not NULL, where to store log-friendly level description * * \return Topology level XML from within \p xml, or NULL if not found * \note The caller is responsible for freeing \p *target and \p *desc if set. */ static xmlNode * unpack_level_request(xmlNode *xml, enum fenced_target_by *mode, char **target, int *id, char **desc) { enum fenced_target_by local_mode = fenced_target_by_unknown; char *local_target = NULL; int local_id = 0; /* The level element can be the top element or lower. If top level, don't * search by xpath, because it might give multiple hits if the XML is the * CIB. */ if ((xml != NULL) && !pcmk__str_eq(TYPE(xml), XML_TAG_FENCING_LEVEL, pcmk__str_none)) { xml = get_xpath_object("//" XML_TAG_FENCING_LEVEL, xml, LOG_WARNING); } if (xml == NULL) { if (desc != NULL) { *desc = crm_strdup_printf("missing"); } } else { local_mode = unpack_level_kind(xml); local_target = stonith_level_key(xml, local_mode); crm_element_value_int(xml, XML_ATTR_STONITH_INDEX, &local_id); if (desc != NULL) { *desc = crm_strdup_printf("%s[%d]", local_target, local_id); } } if (mode != NULL) { *mode = local_mode; } if (id != NULL) { *id = local_id; } if (target != NULL) { *target = local_target; } else { free(local_target); } return xml; } /*! * \internal * \brief Register a fencing topology level for a target * * Given an XML request specifying the target name, level index, and device IDs * for the level, this will create an entry for the target in the global topology * table if one does not already exist, then append the specified device IDs to * the entry's device list for the specified level. * * \param[in] msg XML request for STONITH level registration * \param[out] desc If not NULL, set to string representation "TARGET[LEVEL]" * \param[out] result Where to set result of registration */ void fenced_register_level(xmlNode *msg, char **desc, pcmk__action_result_t *result) { int id = 0; xmlNode *level; enum fenced_target_by mode; char *target; stonith_topology_t *tp; stonith_key_value_t *dIter = NULL; stonith_key_value_t *devices = NULL; CRM_CHECK((msg != NULL) && (result != NULL), return); level = unpack_level_request(msg, &mode, &target, &id, desc); if (level == NULL) { fenced_set_protocol_error(result); return; } // Ensure an ID was given (even the client API adds an ID) if (pcmk__str_empty(ID(level))) { crm_warn("Ignoring registration for topology level without ID"); free(target); crm_log_xml_trace(level, "Bad level"); pcmk__format_result(result, CRM_EX_INVALID_PARAM, PCMK_EXEC_INVALID, "Topology level is invalid without ID"); return; } // Ensure a valid target was specified if (mode == fenced_target_by_unknown) { crm_warn("Ignoring registration for topology level '%s' " "without valid target", ID(level)); free(target); crm_log_xml_trace(level, "Bad level"); pcmk__format_result(result, CRM_EX_INVALID_PARAM, PCMK_EXEC_INVALID, "Invalid target for topology level '%s'", ID(level)); return; } // Ensure level ID is in allowed range if ((id <= 0) || (id >= ST_LEVEL_MAX)) { crm_warn("Ignoring topology registration for %s with invalid level %d", target, id); free(target); crm_log_xml_trace(level, "Bad level"); pcmk__format_result(result, CRM_EX_INVALID_PARAM, PCMK_EXEC_INVALID, "Invalid level number '%s' for topology level '%s'", pcmk__s(crm_element_value(level, XML_ATTR_STONITH_INDEX), ""), ID(level)); return; } /* Find or create topology table entry */ tp = g_hash_table_lookup(topology, target); if (tp == NULL) { tp = calloc(1, sizeof(stonith_topology_t)); if (tp == NULL) { pcmk__set_result(result, CRM_EX_ERROR, PCMK_EXEC_ERROR, strerror(ENOMEM)); free(target); return; } tp->kind = mode; tp->target = target; tp->target_value = crm_element_value_copy(level, XML_ATTR_STONITH_TARGET_VALUE); tp->target_pattern = crm_element_value_copy(level, XML_ATTR_STONITH_TARGET_PATTERN); tp->target_attribute = crm_element_value_copy(level, XML_ATTR_STONITH_TARGET_ATTRIBUTE); g_hash_table_replace(topology, tp->target, tp); crm_trace("Added %s (%d) to the topology (%d active entries)", target, (int) mode, g_hash_table_size(topology)); } else { free(target); } if (tp->levels[id] != NULL) { crm_info("Adding to the existing %s[%d] topology entry", tp->target, id); } devices = parse_device_list(crm_element_value(level, XML_ATTR_STONITH_DEVICES)); for (dIter = devices; dIter; dIter = dIter->next) { const char *device = dIter->value; crm_trace("Adding device '%s' for %s[%d]", device, tp->target, id); tp->levels[id] = g_list_append(tp->levels[id], strdup(device)); } stonith_key_value_freeall(devices, 1, 1); { int nlevels = count_active_levels(tp); crm_info("Target %s has %d active fencing level%s", tp->target, nlevels, pcmk__plural_s(nlevels)); } pcmk__set_result(result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); } /*! * \internal * \brief Unregister a fencing topology level for a target * * Given an XML request specifying the target name and level index (or 0 for all * levels), this will remove any corresponding entry for the target from the * global topology table. * * \param[in] msg XML request for STONITH level registration * \param[out] desc If not NULL, set to string representation "TARGET[LEVEL]" * \param[out] result Where to set result of unregistration */ void fenced_unregister_level(xmlNode *msg, char **desc, pcmk__action_result_t *result) { int id = -1; stonith_topology_t *tp; char *target; xmlNode *level = NULL; CRM_CHECK(result != NULL, return); level = unpack_level_request(msg, NULL, &target, &id, desc); if (level == NULL) { fenced_set_protocol_error(result); return; } // Ensure level ID is in allowed range if ((id < 0) || (id >= ST_LEVEL_MAX)) { crm_warn("Ignoring topology unregistration for %s with invalid level %d", target, id); free(target); crm_log_xml_trace(level, "Bad level"); pcmk__format_result(result, CRM_EX_INVALID_PARAM, PCMK_EXEC_INVALID, "Invalid level number '%s' for topology level %s", pcmk__s(crm_element_value(level, XML_ATTR_STONITH_INDEX), ""), // Client API doesn't add ID to unregistration XML pcmk__s(ID(level), "")); return; } tp = g_hash_table_lookup(topology, target); if (tp == NULL) { guint nentries = g_hash_table_size(topology); crm_info("No fencing topology found for %s (%d active %s)", target, nentries, pcmk__plural_alt(nentries, "entry", "entries")); } else if (id == 0 && g_hash_table_remove(topology, target)) { guint nentries = g_hash_table_size(topology); crm_info("Removed all fencing topology entries related to %s " "(%d active %s remaining)", target, nentries, pcmk__plural_alt(nentries, "entry", "entries")); } else if (tp->levels[id] != NULL) { guint nlevels; g_list_free_full(tp->levels[id], free); tp->levels[id] = NULL; nlevels = count_active_levels(tp); crm_info("Removed level %d from fencing topology for %s " "(%d active level%s remaining)", id, target, nlevels, pcmk__plural_s(nlevels)); } free(target); pcmk__set_result(result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); } static char * list_to_string(GList *list, const char *delim, gboolean terminate_with_delim) { int max = g_list_length(list); size_t delim_len = delim?strlen(delim):0; size_t alloc_size = 1 + (max?((max-1+(terminate_with_delim?1:0))*delim_len):0); char *rv; GList *gIter; for (gIter = list; gIter != NULL; gIter = gIter->next) { const char *value = (const char *) gIter->data; alloc_size += strlen(value); } rv = calloc(alloc_size, sizeof(char)); if (rv) { char *pos = rv; const char *lead_delim = ""; for (gIter = list; gIter != NULL; gIter = gIter->next) { const char *value = (const char *) gIter->data; pos = &pos[sprintf(pos, "%s%s", lead_delim, value)]; lead_delim = delim; } if (max && terminate_with_delim) { sprintf(pos, "%s", delim); } } return rv; } /*! * \internal * \brief Execute a fence agent action directly (and asynchronously) * * Handle a STONITH_OP_EXEC API message by scheduling a requested agent action * directly on a specified device. Only list, monitor, and status actions are * expected to use this call, though it should work with any agent command. * * \param[in] msg Request XML specifying action * \param[out] result Where to store result of action * * \note If the action is monitor, the device must be registered via the API * (CIB registration is not sufficient), because monitor should not be * possible unless the device is "started" (API registered). */ static void execute_agent_action(xmlNode *msg, pcmk__action_result_t *result) { xmlNode *dev = get_xpath_object("//" F_STONITH_DEVICE, msg, LOG_ERR); xmlNode *op = get_xpath_object("//@" F_STONITH_ACTION, msg, LOG_ERR); const char *id = crm_element_value(dev, F_STONITH_DEVICE); const char *action = crm_element_value(op, F_STONITH_ACTION); async_command_t *cmd = NULL; stonith_device_t *device = NULL; if ((id == NULL) || (action == NULL)) { crm_info("Malformed API action request: device %s, action %s", (id? id : "not specified"), (action? action : "not specified")); fenced_set_protocol_error(result); return; } if (pcmk__str_eq(id, STONITH_WATCHDOG_ID, pcmk__str_none)) { // Watchdog agent actions are implemented internally if (stonith_watchdog_timeout_ms <= 0) { pcmk__set_result(result, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE, "Watchdog fence device not configured"); return; } else if (pcmk__str_eq(action, "list", pcmk__str_casei)) { pcmk__set_result(result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); pcmk__set_result_output(result, list_to_string(stonith_watchdog_targets, "\n", TRUE), NULL); return; } else if (pcmk__str_eq(action, "monitor", pcmk__str_casei)) { pcmk__set_result(result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); return; } } device = g_hash_table_lookup(device_list, id); if (device == NULL) { crm_info("Ignoring API '%s' action request because device %s not found", action, id); pcmk__format_result(result, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE, "'%s' not found", id); return; } else if (!device->api_registered && !strcmp(action, "monitor")) { // Monitors may run only on "started" (API-registered) devices crm_info("Ignoring API '%s' action request because device %s not active", action, id); pcmk__format_result(result, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE, "'%s' not active", id); return; } cmd = create_async_command(msg); if (cmd == NULL) { crm_log_xml_warn(msg, "invalid"); fenced_set_protocol_error(result); return; } schedule_stonith_command(cmd, device); pcmk__set_result(result, CRM_EX_OK, PCMK_EXEC_PENDING, NULL); } static void search_devices_record_result(struct device_search_s *search, const char *device, gboolean can_fence) { search->replies_received++; if (can_fence && device) { if (search->support_action_only != st_device_supports_none) { stonith_device_t *dev = g_hash_table_lookup(device_list, device); if (dev && !pcmk_is_set(dev->flags, search->support_action_only)) { return; } } search->capable = g_list_append(search->capable, strdup(device)); } if (search->replies_needed == search->replies_received) { guint ndevices = g_list_length(search->capable); crm_debug("Search found %d device%s that can perform '%s' targeting %s", ndevices, pcmk__plural_s(ndevices), (search->action? search->action : "unknown action"), (search->host? search->host : "any node")); search->callback(search->capable, search->user_data); free(search->host); free(search->action); free(search); } } /*! * \internal * \brief Check whether the local host is allowed to execute a fencing action * * \param[in] device Fence device to check * \param[in] action Fence action to check * \param[in] target Hostname of fence target * \param[in] allow_suicide Whether self-fencing is allowed for this operation * * \return TRUE if local host is allowed to execute action, FALSE otherwise */ static gboolean localhost_is_eligible(const stonith_device_t *device, const char *action, const char *target, gboolean allow_suicide) { gboolean localhost_is_target = pcmk__str_eq(target, stonith_our_uname, pcmk__str_casei); if ((device != NULL) && (action != NULL) && (device->on_target_actions != NULL) && (strstr((const char*) device->on_target_actions->str, action) != NULL)) { if (!localhost_is_target) { crm_trace("Operation '%s' using %s can only be executed for local " "host, not %s", action, device->id, target); return FALSE; } } else if (localhost_is_target && !allow_suicide) { crm_trace("'%s' operation does not support self-fencing", action); return FALSE; } return TRUE; } static void can_fence_host_with_device(stonith_device_t * dev, struct device_search_s *search) { gboolean can = FALSE; const char *check_type = NULL; const char *host = search->host; const char *alias = NULL; CRM_LOG_ASSERT(dev != NULL); if (dev == NULL) { goto search_report_results; } else if (host == NULL) { can = TRUE; goto search_report_results; } /* Short-circuit query if this host is not allowed to perform the action */ if (pcmk__str_eq(search->action, "reboot", pcmk__str_casei)) { /* A "reboot" *might* get remapped to "off" then "on", so short-circuit * only if all three are disallowed. If only one or two are disallowed, * we'll report that with the results. We never allow suicide for * remapped "on" operations because the host is off at that point. */ if (!localhost_is_eligible(dev, "reboot", host, search->allow_suicide) && !localhost_is_eligible(dev, "off", host, search->allow_suicide) && !localhost_is_eligible(dev, "on", host, FALSE)) { goto search_report_results; } } else if (!localhost_is_eligible(dev, search->action, host, search->allow_suicide)) { goto search_report_results; } alias = g_hash_table_lookup(dev->aliases, host); if (alias == NULL) { alias = host; } check_type = target_list_type(dev); if (pcmk__str_eq(check_type, PCMK__VALUE_NONE, pcmk__str_casei)) { can = TRUE; } else if (pcmk__str_eq(check_type, "static-list", pcmk__str_casei)) { /* Presence in the hostmap is sufficient * Only use if all hosts on which the device can be active can always fence all listed hosts */ if (pcmk__str_in_list(host, dev->targets, pcmk__str_casei)) { can = TRUE; } else if (g_hash_table_lookup(dev->params, PCMK_STONITH_HOST_MAP) && g_hash_table_lookup(dev->aliases, host)) { can = TRUE; } } else if (pcmk__str_eq(check_type, "dynamic-list", pcmk__str_casei)) { time_t now = time(NULL); if (dev->targets == NULL || dev->targets_age + 60 < now) { int device_timeout = get_action_timeout(dev, "list", search->per_device_timeout); if (device_timeout > search->per_device_timeout) { crm_notice("Since the pcmk_list_timeout(%ds) parameter of %s is larger than stonith-timeout(%ds), timeout may occur", device_timeout, dev->id, search->per_device_timeout); } crm_trace("Running '%s' to check whether %s is eligible to fence %s (%s)", check_type, dev->id, search->host, search->action); schedule_internal_command(__func__, dev, "list", NULL, search->per_device_timeout, search, dynamic_list_search_cb); /* we'll respond to this search request async in the cb */ return; } if (pcmk__str_in_list(alias, dev->targets, pcmk__str_casei)) { can = TRUE; } } else if (pcmk__str_eq(check_type, "status", pcmk__str_casei)) { int device_timeout = get_action_timeout(dev, check_type, search->per_device_timeout); if (device_timeout > search->per_device_timeout) { crm_notice("Since the pcmk_status_timeout(%ds) parameter of %s is larger than stonith-timeout(%ds), timeout may occur", device_timeout, dev->id, search->per_device_timeout); } crm_trace("Running '%s' to check whether %s is eligible to fence %s (%s)", check_type, dev->id, search->host, search->action); schedule_internal_command(__func__, dev, "status", search->host, search->per_device_timeout, search, status_search_cb); /* we'll respond to this search request async in the cb */ return; } else { crm_err("Invalid value for " PCMK_STONITH_HOST_CHECK ": %s", check_type); check_type = "Invalid " PCMK_STONITH_HOST_CHECK; } if (pcmk__str_eq(host, alias, pcmk__str_casei)) { crm_info("%s is%s eligible to fence (%s) %s: %s", dev->id, (can? "" : " not"), search->action, host, check_type); } else { crm_info("%s is%s eligible to fence (%s) %s (aka. '%s'): %s", dev->id, (can? "" : " not"), search->action, host, alias, check_type); } search_report_results: search_devices_record_result(search, dev ? dev->id : NULL, can); } static void search_devices(gpointer key, gpointer value, gpointer user_data) { stonith_device_t *dev = value; struct device_search_s *search = user_data; can_fence_host_with_device(dev, search); } #define DEFAULT_QUERY_TIMEOUT 20 static void get_capable_devices(const char *host, const char *action, int timeout, bool suicide, void *user_data, void (*callback) (GList * devices, void *user_data), uint32_t support_action_only) { struct device_search_s *search; guint ndevices = g_hash_table_size(device_list); if (ndevices == 0) { callback(NULL, user_data); return; } search = calloc(1, sizeof(struct device_search_s)); if (!search) { crm_crit("Cannot search for capable fence devices: %s", strerror(ENOMEM)); callback(NULL, user_data); return; } pcmk__str_update(&search->host, host); pcmk__str_update(&search->action, action); search->per_device_timeout = timeout; search->allow_suicide = suicide; search->callback = callback; search->user_data = user_data; search->support_action_only = support_action_only; /* We are guaranteed this many replies, even if a device is * unregistered while the search is in progress. */ search->replies_needed = ndevices; crm_debug("Searching %d device%s to see which can execute '%s' targeting %s", ndevices, pcmk__plural_s(ndevices), (search->action? search->action : "unknown action"), (search->host? search->host : "any node")); g_hash_table_foreach(device_list, search_devices, search); } struct st_query_data { xmlNode *reply; char *remote_peer; char *client_id; char *target; char *action; int call_options; }; /*! * \internal * \brief Add action-specific attributes to query reply XML * * \param[in,out] xml XML to add attributes to * \param[in] action Fence action * \param[in] device Fence device * \param[in] target Fence target */ static void add_action_specific_attributes(xmlNode *xml, const char *action, const stonith_device_t *device, const char *target) { int action_specific_timeout; int delay_max; int delay_base; CRM_CHECK(xml && action && device, return); if (is_action_required(action, device)) { crm_trace("Action '%s' is required using %s", action, device->id); crm_xml_add_int(xml, F_STONITH_DEVICE_REQUIRED, 1); } action_specific_timeout = get_action_timeout(device, action, 0); if (action_specific_timeout) { crm_trace("Action '%s' has timeout %dms using %s", action, action_specific_timeout, device->id); crm_xml_add_int(xml, F_STONITH_ACTION_TIMEOUT, action_specific_timeout); } delay_max = get_action_delay_max(device, action); if (delay_max > 0) { crm_trace("Action '%s' has maximum random delay %dms using %s", action, delay_max, device->id); crm_xml_add_int(xml, F_STONITH_DELAY_MAX, delay_max / 1000); } delay_base = get_action_delay_base(device, action, target); if (delay_base > 0) { crm_xml_add_int(xml, F_STONITH_DELAY_BASE, delay_base / 1000); } if ((delay_max > 0) && (delay_base == 0)) { crm_trace("Action '%s' has maximum random delay %dms using %s", action, delay_max, device->id); } else if ((delay_max == 0) && (delay_base > 0)) { crm_trace("Action '%s' has a static delay of %dms using %s", action, delay_base, device->id); } else if ((delay_max > 0) && (delay_base > 0)) { crm_trace("Action '%s' has a minimum delay of %dms and a randomly chosen " "maximum delay of %dms using %s", action, delay_base, delay_max, device->id); } } /*! * \internal * \brief Add "disallowed" attribute to query reply XML if appropriate * * \param[in,out] xml XML to add attribute to * \param[in] action Fence action * \param[in] device Fence device * \param[in] target Fence target * \param[in] allow_suicide Whether self-fencing is allowed */ static void add_disallowed(xmlNode *xml, const char *action, const stonith_device_t *device, const char *target, gboolean allow_suicide) { if (!localhost_is_eligible(device, action, target, allow_suicide)) { crm_trace("Action '%s' using %s is disallowed for local host", action, device->id); pcmk__xe_set_bool_attr(xml, F_STONITH_ACTION_DISALLOWED, true); } } /*! * \internal * \brief Add child element with action-specific values to query reply XML * * \param[in,out] xml XML to add attribute to * \param[in] action Fence action * \param[in] device Fence device * \param[in] target Fence target * \param[in] allow_suicide Whether self-fencing is allowed */ static void add_action_reply(xmlNode *xml, const char *action, const stonith_device_t *device, const char *target, gboolean allow_suicide) { xmlNode *child = create_xml_node(xml, F_STONITH_ACTION); crm_xml_add(child, XML_ATTR_ID, action); add_action_specific_attributes(child, action, device, target); add_disallowed(child, action, device, target, allow_suicide); } static void stonith_query_capable_device_cb(GList * devices, void *user_data) { struct st_query_data *query = user_data; int available_devices = 0; xmlNode *dev = NULL; xmlNode *list = NULL; GList *lpc = NULL; pcmk__client_t *client = NULL; if (query->client_id != NULL) { client = pcmk__find_client_by_id(query->client_id); if ((client == NULL) && (query->remote_peer == NULL)) { crm_trace("Skipping reply to %s: no longer a client", query->client_id); goto done; } } /* Pack the results into XML */ list = create_xml_node(NULL, __func__); crm_xml_add(list, F_STONITH_TARGET, query->target); for (lpc = devices; lpc != NULL; lpc = lpc->next) { stonith_device_t *device = g_hash_table_lookup(device_list, lpc->data); const char *action = query->action; if (!device) { /* It is possible the device got unregistered while * determining who can fence the target */ continue; } available_devices++; dev = create_xml_node(list, F_STONITH_DEVICE); crm_xml_add(dev, XML_ATTR_ID, device->id); crm_xml_add(dev, "namespace", device->namespace); crm_xml_add(dev, "agent", device->agent); crm_xml_add_int(dev, F_STONITH_DEVICE_VERIFIED, device->verified); crm_xml_add_int(dev, F_STONITH_DEVICE_SUPPORT_FLAGS, device->flags); /* If the originating fencer wants to reboot the node, and we have a * capable device that doesn't support "reboot", remap to "off" instead. */ if (!pcmk_is_set(device->flags, st_device_supports_reboot) && pcmk__str_eq(query->action, "reboot", pcmk__str_casei)) { crm_trace("%s doesn't support reboot, using values for off instead", device->id); action = "off"; } /* Add action-specific values if available */ add_action_specific_attributes(dev, action, device, query->target); if (pcmk__str_eq(query->action, "reboot", pcmk__str_casei)) { /* A "reboot" *might* get remapped to "off" then "on", so after * sending the "reboot"-specific values in the main element, we add * sub-elements for "off" and "on" values. * * We short-circuited earlier if "reboot", "off" and "on" are all * disallowed for the local host. However if only one or two are * disallowed, we send back the results and mark which ones are * disallowed. If "reboot" is disallowed, this might cause problems * with older fencer versions, which won't check for it. Older * versions will ignore "off" and "on", so they are not a problem. */ add_disallowed(dev, action, device, query->target, pcmk_is_set(query->call_options, st_opt_allow_suicide)); add_action_reply(dev, "off", device, query->target, pcmk_is_set(query->call_options, st_opt_allow_suicide)); add_action_reply(dev, "on", device, query->target, FALSE); } /* A query without a target wants device parameters */ if (query->target == NULL) { xmlNode *attrs = create_xml_node(dev, XML_TAG_ATTRS); g_hash_table_foreach(device->params, hash2field, attrs); } } crm_xml_add_int(list, F_STONITH_AVAILABLE_DEVICES, available_devices); if (query->target) { crm_debug("Found %d matching device%s for target '%s'", available_devices, pcmk__plural_s(available_devices), query->target); } else { crm_debug("%d device%s installed", available_devices, pcmk__plural_s(available_devices)); } if (list != NULL) { crm_log_xml_trace(list, "Add query results"); add_message_xml(query->reply, F_STONITH_CALLDATA, list); } stonith_send_reply(query->reply, query->call_options, query->remote_peer, client); done: free_xml(query->reply); free(query->remote_peer); free(query->client_id); free(query->target); free(query->action); free(query); free_xml(list); g_list_free_full(devices, free); } /*! * \internal * \brief Log the result of an asynchronous command * * \param[in] cmd Command the result is for * \param[in] result Result of command * \param[in] pid Process ID of command, if available * \param[in] next Alternate device that will be tried if command failed * \param[in] op_merged Whether this command was merged with an earlier one */ static void log_async_result(const async_command_t *cmd, const pcmk__action_result_t *result, int pid, const char *next, bool op_merged) { int log_level = LOG_ERR; int output_log_level = LOG_NEVER; guint devices_remaining = g_list_length(cmd->next_device_iter); GString *msg = g_string_sized_new(80); // Reasonable starting size // Choose log levels appropriately if we have a result if (pcmk__result_ok(result)) { log_level = (cmd->target == NULL)? LOG_DEBUG : LOG_NOTICE; if ((result->action_stdout != NULL) && !pcmk__str_eq(cmd->action, "metadata", pcmk__str_casei)) { output_log_level = LOG_DEBUG; } next = NULL; } else { log_level = (cmd->target == NULL)? LOG_NOTICE : LOG_ERR; if ((result->action_stdout != NULL) && !pcmk__str_eq(cmd->action, "metadata", pcmk__str_casei)) { output_log_level = LOG_WARNING; } } // Build the log message piece by piece pcmk__g_strcat(msg, "Operation '", cmd->action, "' ", NULL); if (pid != 0) { g_string_append_printf(msg, "[%d] ", pid); } if (cmd->target != NULL) { pcmk__g_strcat(msg, "targeting ", cmd->target, " ", NULL); } if (cmd->device != NULL) { pcmk__g_strcat(msg, "using ", cmd->device, " ", NULL); } // Add exit status or execution status as appropriate if (result->execution_status == PCMK_EXEC_DONE) { g_string_append_printf(msg, "returned %d", result->exit_status); } else { pcmk__g_strcat(msg, "could not be executed: ", pcmk_exec_status_str(result->execution_status), NULL); } // Add exit reason and next device if appropriate if (result->exit_reason != NULL) { pcmk__g_strcat(msg, " (", result->exit_reason, ")", NULL); } if (next != NULL) { pcmk__g_strcat(msg, ", retrying with ", next, NULL); } if (devices_remaining > 0) { g_string_append_printf(msg, " (%u device%s remaining)", (unsigned int) devices_remaining, pcmk__plural_s(devices_remaining)); } g_string_append_printf(msg, " " CRM_XS " %scall %d from %s", (op_merged? "merged " : ""), cmd->id, cmd->client_name); // Log the result do_crm_log(log_level, "%s", msg->str); g_string_free(msg, TRUE); // Log the output (which may have multiple lines), if appropriate if (output_log_level != LOG_NEVER) { char *prefix = crm_strdup_printf("%s[%d]", cmd->device, pid); crm_log_output(output_log_level, prefix, result->action_stdout); free(prefix); } } /*! * \internal * \brief Reply to requester after asynchronous command completion * * \param[in] cmd Command that completed * \param[in] result Result of command * \param[in] pid Process ID of command, if available * \param[in] merged If true, command was merged with another, not executed */ static void send_async_reply(const async_command_t *cmd, const pcmk__action_result_t *result, int pid, bool merged) { xmlNode *reply = NULL; pcmk__client_t *client = NULL; CRM_CHECK((cmd != NULL) && (result != NULL), return); log_async_result(cmd, result, pid, NULL, merged); if (cmd->client != NULL) { client = pcmk__find_client_by_id(cmd->client); if ((client == NULL) && (cmd->origin == NULL)) { crm_trace("Skipping reply to %s: no longer a client", cmd->client); return; } } reply = construct_async_reply(cmd, result); if (merged) { pcmk__xe_set_bool_attr(reply, F_STONITH_MERGED, true); } if (!stand_alone && pcmk__is_fencing_action(cmd->action) && pcmk__str_eq(cmd->origin, cmd->target, pcmk__str_casei)) { /* The target was also the originator, so broadcast the result on its * behalf (since it will be unable to). */ crm_trace("Broadcast '%s' result for %s (target was also originator)", cmd->action, cmd->target); crm_xml_add(reply, F_SUBTYPE, "broadcast"); crm_xml_add(reply, F_STONITH_OPERATION, T_STONITH_NOTIFY); send_cluster_message(NULL, crm_msg_stonith_ng, reply, FALSE); } else { // Reply only to the originator stonith_send_reply(reply, cmd->options, cmd->origin, client); } crm_log_xml_trace(reply, "Reply"); free_xml(reply); if (stand_alone) { /* Do notification with a clean data object */ xmlNode *notify_data = create_xml_node(NULL, T_STONITH_NOTIFY_FENCE); stonith__xe_set_result(notify_data, result); crm_xml_add(notify_data, F_STONITH_TARGET, cmd->target); crm_xml_add(notify_data, F_STONITH_OPERATION, cmd->op); crm_xml_add(notify_data, F_STONITH_DELEGATE, "localhost"); crm_xml_add(notify_data, F_STONITH_DEVICE, cmd->device); crm_xml_add(notify_data, F_STONITH_REMOTE_OP_ID, cmd->remote_op_id); crm_xml_add(notify_data, F_STONITH_ORIGIN, cmd->client); fenced_send_notification(T_STONITH_NOTIFY_FENCE, result, notify_data); fenced_send_notification(T_STONITH_NOTIFY_HISTORY, NULL, NULL); } } static void cancel_stonith_command(async_command_t * cmd) { stonith_device_t *device = cmd_device(cmd); if (device) { crm_trace("Cancel scheduled '%s' action using %s", cmd->action, device->id); device->pending_ops = g_list_remove(device->pending_ops, cmd); } } /*! * \internal * \brief Cancel and reply to any duplicates of a just-completed operation * * Check whether any fencing operations are scheduled to do the same thing as * one that just succeeded. If so, rather than performing the same operation * twice, return the result of this operation for all matching pending commands. * * \param[in,out] cmd Fencing operation that just succeeded * \param[in] result Result of \p cmd * \param[in] pid If nonzero, process ID of agent invocation (for logs) * * \note Duplicate merging will do the right thing for either type of remapped * reboot. If the executing fencer remapped an unsupported reboot to off, * then cmd->action will be "reboot" and will be merged with any other * reboot requests. If the originating fencer remapped a topology reboot * to off then on, we will get here once with cmd->action "off" and once * with "on", and they will be merged separately with similar requests. */ static void reply_to_duplicates(async_command_t *cmd, const pcmk__action_result_t *result, int pid) { GList *next = NULL; for (GList *iter = cmd_list; iter != NULL; iter = next) { async_command_t *cmd_other = iter->data; next = iter->next; // We might delete this entry, so grab next now if (cmd == cmd_other) { continue; } /* A pending operation matches if: * 1. The client connections are different. * 2. The target is the same. * 3. The fencing action is the same. * 4. The device scheduled to execute the action is the same. */ if (pcmk__str_eq(cmd->client, cmd_other->client, pcmk__str_casei) || !pcmk__str_eq(cmd->target, cmd_other->target, pcmk__str_casei) || !pcmk__str_eq(cmd->action, cmd_other->action, pcmk__str_casei) || !pcmk__str_eq(cmd->device, cmd_other->device, pcmk__str_casei)) { continue; } crm_notice("Merging fencing action '%s'%s%s originating from " "client %s with identical fencing request from client %s", cmd_other->action, (cmd_other->target == NULL)? "" : " targeting ", pcmk__s(cmd_other->target, ""), cmd_other->client_name, cmd->client_name); // Stop tracking the duplicate, send its result, and cancel it cmd_list = g_list_remove_link(cmd_list, iter); send_async_reply(cmd_other, result, pid, true); cancel_stonith_command(cmd_other); free_async_command(cmd_other); g_list_free_1(iter); } } /*! * \internal * \brief Return the next required device (if any) for an operation * * \param[in,out] cmd Fencing operation that just succeeded * * \return Next device required for action if any, otherwise NULL */ static stonith_device_t * next_required_device(async_command_t *cmd) { for (GList *iter = cmd->next_device_iter; iter != NULL; iter = iter->next) { stonith_device_t *next_device = g_hash_table_lookup(device_list, iter->data); if (is_action_required(cmd->action, next_device)) { /* This is only called for successful actions, so it's OK to skip * non-required devices. */ cmd->next_device_iter = iter->next; return next_device; } } return NULL; } static void st_child_done(int pid, const pcmk__action_result_t *result, void *user_data) { async_command_t *cmd = user_data; stonith_device_t *device = NULL; stonith_device_t *next_device = NULL; CRM_CHECK(cmd != NULL, return); device = cmd_device(cmd); cmd->active_on = NULL; /* The device is ready to do something else now */ if (device) { if (!device->verified && pcmk__result_ok(result) && (pcmk__strcase_any_of(cmd->action, "list", "monitor", "status", NULL))) { device->verified = TRUE; } mainloop_set_trigger(device->work); } if (pcmk__result_ok(result)) { next_device = next_required_device(cmd); } else if ((cmd->next_device_iter != NULL) && !is_action_required(cmd->action, device)) { /* if this device didn't work out, see if there are any others we can try. * if the failed device was 'required', we can't pick another device. */ next_device = g_hash_table_lookup(device_list, cmd->next_device_iter->data); cmd->next_device_iter = cmd->next_device_iter->next; } if (next_device == NULL) { send_async_reply(cmd, result, pid, false); if (pcmk__result_ok(result)) { reply_to_duplicates(cmd, result, pid); } free_async_command(cmd); } else { // This operation requires more fencing log_async_result(cmd, result, pid, next_device->id, false); schedule_stonith_command(cmd, next_device); } } static gint sort_device_priority(gconstpointer a, gconstpointer b) { const stonith_device_t *dev_a = a; const stonith_device_t *dev_b = b; if (dev_a->priority > dev_b->priority) { return -1; } else if (dev_a->priority < dev_b->priority) { return 1; } return 0; } static void stonith_fence_get_devices_cb(GList * devices, void *user_data) { async_command_t *cmd = user_data; stonith_device_t *device = NULL; guint ndevices = g_list_length(devices); crm_info("Found %d matching device%s for target '%s'", ndevices, pcmk__plural_s(ndevices), cmd->target); if (devices != NULL) { /* Order based on priority */ devices = g_list_sort(devices, sort_device_priority); device = g_hash_table_lookup(device_list, devices->data); } if (device == NULL) { // No device found pcmk__action_result_t result = PCMK__UNKNOWN_RESULT; pcmk__format_result(&result, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE, "No device configured for target '%s'", cmd->target); send_async_reply(cmd, &result, 0, false); pcmk__reset_result(&result); free_async_command(cmd); g_list_free_full(devices, free); } else { // Device found, schedule it for fencing cmd->device_list = devices; cmd->next_device_iter = devices->next; schedule_stonith_command(cmd, device); } } /*! * \internal * \brief Execute a fence action via the local node * * \param[in] msg Fencing request * \param[out] result Where to store result of fence action */ static void fence_locally(xmlNode *msg, pcmk__action_result_t *result) { const char *device_id = NULL; stonith_device_t *device = NULL; async_command_t *cmd = NULL; xmlNode *dev = NULL; CRM_CHECK((msg != NULL) && (result != NULL), return); dev = get_xpath_object("//@" F_STONITH_TARGET, msg, LOG_ERR); cmd = create_async_command(msg); if (cmd == NULL) { crm_log_xml_warn(msg, "invalid"); fenced_set_protocol_error(result); return; } device_id = crm_element_value(dev, F_STONITH_DEVICE); if (device_id != NULL) { device = g_hash_table_lookup(device_list, device_id); if (device == NULL) { crm_err("Requested device '%s' is not available", device_id); pcmk__format_result(result, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE, "Requested device '%s' not found", device_id); return; } schedule_stonith_command(cmd, device); } else { const char *host = crm_element_value(dev, F_STONITH_TARGET); if (pcmk_is_set(cmd->options, st_opt_cs_nodeid)) { int nodeid = 0; crm_node_t *node = NULL; pcmk__scan_min_int(host, &nodeid, 0); node = pcmk__search_known_node_cache(nodeid, NULL, CRM_GET_PEER_ANY); if (node != NULL) { host = node->uname; } } /* If we get to here, then self-fencing is implicitly allowed */ get_capable_devices(host, cmd->action, cmd->default_timeout, TRUE, cmd, stonith_fence_get_devices_cb, pcmk__str_eq(cmd->action, "on", pcmk__str_casei)? st_device_supports_on: st_device_supports_none); } pcmk__set_result(result, CRM_EX_OK, PCMK_EXEC_PENDING, NULL); } /*! * \internal * \brief Build an XML reply for a fencing operation * * \param[in] request Request that reply is for * \param[in] data If not NULL, add to reply as call data * \param[in] result Full result of fencing operation * * \return Newly created XML reply * \note The caller is responsible for freeing the result. * \note This has some overlap with construct_async_reply(), but that copies * values from an async_command_t, whereas this one copies them from the * request. */ xmlNode * fenced_construct_reply(const xmlNode *request, xmlNode *data, const pcmk__action_result_t *result) { xmlNode *reply = NULL; reply = create_xml_node(NULL, T_STONITH_REPLY); crm_xml_add(reply, "st_origin", __func__); crm_xml_add(reply, F_TYPE, T_STONITH_NG); stonith__xe_set_result(reply, result); if (request == NULL) { /* Most likely, this is the result of a stonith operation that was * initiated before we came up. Unfortunately that means we lack enough * information to provide clients with a full result. * * @TODO Maybe synchronize this information at start-up? */ crm_warn("Missing request information for client notifications for " "operation with result '%s' (initiated before we came up?)", pcmk_exec_status_str(result->execution_status)); } else { const char *name = NULL; const char *value = NULL; // Attributes to copy from request to reply const char *names[] = { F_STONITH_OPERATION, F_STONITH_CALLID, F_STONITH_CLIENTID, F_STONITH_CLIENTNAME, F_STONITH_REMOTE_OP_ID, F_STONITH_CALLOPTS }; for (int lpc = 0; lpc < PCMK__NELEM(names); lpc++) { name = names[lpc]; value = crm_element_value(request, name); crm_xml_add(reply, name, value); } if (data != NULL) { add_message_xml(reply, F_STONITH_CALLDATA, data); } } return reply; } /*! * \internal * \brief Build an XML reply to an asynchronous fencing command * * \param[in] cmd Fencing command that reply is for * \param[in] result Command result */ static xmlNode * construct_async_reply(const async_command_t *cmd, const pcmk__action_result_t *result) { xmlNode *reply = create_xml_node(NULL, T_STONITH_REPLY); crm_xml_add(reply, "st_origin", __func__); crm_xml_add(reply, F_TYPE, T_STONITH_NG); crm_xml_add(reply, F_STONITH_OPERATION, cmd->op); crm_xml_add(reply, F_STONITH_DEVICE, cmd->device); crm_xml_add(reply, F_STONITH_REMOTE_OP_ID, cmd->remote_op_id); crm_xml_add(reply, F_STONITH_CLIENTID, cmd->client); crm_xml_add(reply, F_STONITH_CLIENTNAME, cmd->client_name); crm_xml_add(reply, F_STONITH_TARGET, cmd->target); crm_xml_add(reply, F_STONITH_ACTION, cmd->op); crm_xml_add(reply, F_STONITH_ORIGIN, cmd->origin); crm_xml_add_int(reply, F_STONITH_CALLID, cmd->id); crm_xml_add_int(reply, F_STONITH_CALLOPTS, cmd->options); stonith__xe_set_result(reply, result); return reply; } bool fencing_peer_active(crm_node_t *peer) { if (peer == NULL) { return FALSE; } else if (peer->uname == NULL) { return FALSE; } else if (pcmk_is_set(peer->processes, crm_get_cluster_proc())) { return TRUE; } return FALSE; } void set_fencing_completed(remote_fencing_op_t *op) { struct timespec tv; qb_util_timespec_from_epoch_get(&tv); op->completed = tv.tv_sec; op->completed_nsec = tv.tv_nsec; } /*! * \internal * \brief Look for alternate node needed if local node shouldn't fence target * * \param[in] target Node that must be fenced * * \return Name of an alternate node that should fence \p target if any, * or NULL otherwise */ static const char * check_alternate_host(const char *target) { if (pcmk__str_eq(target, stonith_our_uname, pcmk__str_casei)) { GHashTableIter gIter; crm_node_t *entry = NULL; g_hash_table_iter_init(&gIter, crm_peer_cache); while (g_hash_table_iter_next(&gIter, NULL, (void **)&entry)) { if (fencing_peer_active(entry) && !pcmk__str_eq(entry->uname, target, pcmk__str_casei)) { crm_notice("Forwarding self-fencing request to %s", entry->uname); return entry->uname; } } crm_warn("Will handle own fencing because no peer can"); } return NULL; } /*! * \internal * \brief Send a reply to a CPG peer or IPC client * * \param[in] reply XML reply to send * \param[in] call_options Send synchronously if st_opt_sync_call is set * \param[in] remote_peer If not NULL, name of peer node to send CPG reply * \param[in,out] client If not NULL, client to send IPC reply */ static void stonith_send_reply(xmlNode *reply, int call_options, const char *remote_peer, pcmk__client_t *client) { CRM_CHECK((reply != NULL) && ((remote_peer != NULL) || (client != NULL)), return); if (remote_peer == NULL) { do_local_reply(reply, client, call_options); } else { send_cluster_message(crm_get_peer(0, remote_peer), crm_msg_stonith_ng, reply, FALSE); } } static void remove_relay_op(xmlNode * request) { xmlNode *dev = get_xpath_object("//@" F_STONITH_ACTION, request, LOG_TRACE); const char *relay_op_id = NULL; const char *op_id = NULL; const char *client_name = NULL; const char *target = NULL; remote_fencing_op_t *relay_op = NULL; if (dev) { target = crm_element_value(dev, F_STONITH_TARGET); } relay_op_id = crm_element_value(request, F_STONITH_REMOTE_OP_ID_RELAY); op_id = crm_element_value(request, F_STONITH_REMOTE_OP_ID); client_name = crm_element_value(request, F_STONITH_CLIENTNAME); /* Delete RELAY operation. */ if (relay_op_id && target && pcmk__str_eq(target, stonith_our_uname, pcmk__str_casei)) { relay_op = g_hash_table_lookup(stonith_remote_op_list, relay_op_id); if (relay_op) { GHashTableIter iter; remote_fencing_op_t *list_op = NULL; g_hash_table_iter_init(&iter, stonith_remote_op_list); /* If the operation to be deleted is registered as a duplicate, delete the registration. */ while (g_hash_table_iter_next(&iter, NULL, (void **)&list_op)) { GList *dup_iter = NULL; if (list_op != relay_op) { for (dup_iter = list_op->duplicates; dup_iter != NULL; dup_iter = dup_iter->next) { remote_fencing_op_t *other = dup_iter->data; if (other == relay_op) { other->duplicates = g_list_remove(other->duplicates, relay_op); break; } } } } crm_debug("Deleting relay op %s ('%s'%s%s for %s), " "replaced by op %s ('%s'%s%s for %s)", relay_op->id, relay_op->action, (relay_op->target == NULL)? "" : " targeting ", pcmk__s(relay_op->target, ""), relay_op->client_name, op_id, relay_op->action, (target == NULL)? "" : " targeting ", pcmk__s(target, ""), client_name); g_hash_table_remove(stonith_remote_op_list, relay_op_id); } } } /*! * \internal * \brief Check whether an API request was sent by a privileged user * * API commands related to fencing configuration may be done only by privileged * IPC users (i.e. root or hacluster), because all other users should go through * the CIB to have ACLs applied. If no client was given, this is a peer request, * which is always allowed. * * \param[in] c IPC client that sent request (or NULL if sent by CPG peer) * \param[in] op Requested API operation (for logging only) * * \return true if sender is peer or privileged client, otherwise false */ static inline bool is_privileged(const pcmk__client_t *c, const char *op) { if ((c == NULL) || pcmk_is_set(c->flags, pcmk__client_privileged)) { return true; } else { crm_warn("Rejecting IPC request '%s' from unprivileged client %s", pcmk__s(op, ""), pcmk__client_name(c)); return false; } } // CRM_OP_REGISTER static xmlNode * handle_register_request(pcmk__request_t *request) { xmlNode *reply = create_xml_node(NULL, "reply"); CRM_ASSERT(request->ipc_client != NULL); crm_xml_add(reply, F_STONITH_OPERATION, CRM_OP_REGISTER); crm_xml_add(reply, F_STONITH_CLIENTID, request->ipc_client->id); pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); pcmk__set_request_flags(request, pcmk__request_reuse_options); return reply; } // STONITH_OP_EXEC static xmlNode * handle_agent_request(pcmk__request_t *request) { execute_agent_action(request->xml, &request->result); if (request->result.execution_status == PCMK_EXEC_PENDING) { return NULL; } return fenced_construct_reply(request->xml, NULL, &request->result); } // STONITH_OP_TIMEOUT_UPDATE static xmlNode * handle_update_timeout_request(pcmk__request_t *request) { const char *call_id = crm_element_value(request->xml, F_STONITH_CALLID); const char *client_id = crm_element_value(request->xml, F_STONITH_CLIENTID); int op_timeout = 0; crm_element_value_int(request->xml, F_STONITH_TIMEOUT, &op_timeout); do_stonith_async_timeout_update(client_id, call_id, op_timeout); pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); return NULL; } // STONITH_OP_QUERY static xmlNode * handle_query_request(pcmk__request_t *request) { int timeout = 0; xmlNode *dev = NULL; const char *action = NULL; const char *target = NULL; const char *client_id = crm_element_value(request->xml, F_STONITH_CLIENTID); struct st_query_data *query = NULL; if (request->peer != NULL) { // Record it for the future notification create_remote_stonith_op(client_id, request->xml, TRUE); } /* Delete the DC node RELAY operation. */ remove_relay_op(request->xml); pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); dev = get_xpath_object("//@" F_STONITH_ACTION, request->xml, LOG_NEVER); if (dev != NULL) { const char *device = crm_element_value(dev, F_STONITH_DEVICE); if (pcmk__str_eq(device, "manual_ack", pcmk__str_casei)) { return NULL; // No query or reply necessary } target = crm_element_value(dev, F_STONITH_TARGET); action = crm_element_value(dev, F_STONITH_ACTION); } crm_log_xml_trace(request->xml, "Query"); query = calloc(1, sizeof(struct st_query_data)); CRM_ASSERT(query != NULL); query->reply = fenced_construct_reply(request->xml, NULL, &request->result); pcmk__str_update(&query->remote_peer, request->peer); pcmk__str_update(&query->client_id, client_id); pcmk__str_update(&query->target, target); pcmk__str_update(&query->action, action); query->call_options = request->call_options; crm_element_value_int(request->xml, F_STONITH_TIMEOUT, &timeout); get_capable_devices(target, action, timeout, pcmk_is_set(query->call_options, st_opt_allow_suicide), query, stonith_query_capable_device_cb, st_device_supports_none); return NULL; } // T_STONITH_NOTIFY static xmlNode * handle_notify_request(pcmk__request_t *request) { const char *flag_name = NULL; CRM_ASSERT(request->ipc_client != NULL); flag_name = crm_element_value(request->xml, F_STONITH_NOTIFY_ACTIVATE); if (flag_name != NULL) { crm_debug("Enabling %s callbacks for client %s", flag_name, pcmk__request_origin(request)); pcmk__set_client_flags(request->ipc_client, get_stonith_flag(flag_name)); } flag_name = crm_element_value(request->xml, F_STONITH_NOTIFY_DEACTIVATE); if (flag_name != NULL) { crm_debug("Disabling %s callbacks for client %s", flag_name, pcmk__request_origin(request)); pcmk__clear_client_flags(request->ipc_client, get_stonith_flag(flag_name)); } pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); pcmk__set_request_flags(request, pcmk__request_reuse_options); return pcmk__ipc_create_ack(request->ipc_flags, "ack", NULL, CRM_EX_OK); } // STONITH_OP_RELAY static xmlNode * handle_relay_request(pcmk__request_t *request) { xmlNode *dev = get_xpath_object("//@" F_STONITH_TARGET, request->xml, LOG_TRACE); crm_notice("Received forwarded fencing request from " "%s %s to fence (%s) peer %s", pcmk__request_origin_type(request), pcmk__request_origin(request), crm_element_value(dev, F_STONITH_ACTION), crm_element_value(dev, F_STONITH_TARGET)); if (initiate_remote_stonith_op(NULL, request->xml, FALSE) == NULL) { fenced_set_protocol_error(&request->result); return fenced_construct_reply(request->xml, NULL, &request->result); } pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_PENDING, NULL); return NULL; } // STONITH_OP_FENCE static xmlNode * handle_fence_request(pcmk__request_t *request) { if ((request->peer != NULL) || stand_alone) { fence_locally(request->xml, &request->result); } else if (pcmk_is_set(request->call_options, st_opt_manual_ack)) { switch (fenced_handle_manual_confirmation(request->ipc_client, request->xml)) { case pcmk_rc_ok: pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); break; case EINPROGRESS: pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_PENDING, NULL); break; default: fenced_set_protocol_error(&request->result); break; } } else { const char *alternate_host = NULL; xmlNode *dev = get_xpath_object("//@" F_STONITH_TARGET, request->xml, LOG_TRACE); const char *target = crm_element_value(dev, F_STONITH_TARGET); const char *action = crm_element_value(dev, F_STONITH_ACTION); const char *device = crm_element_value(dev, F_STONITH_DEVICE); if (request->ipc_client != NULL) { int tolerance = 0; crm_notice("Client %s wants to fence (%s) %s using %s", pcmk__request_origin(request), action, target, (device? device : "any device")); crm_element_value_int(dev, F_STONITH_TOLERANCE, &tolerance); if (stonith_check_fence_tolerance(tolerance, target, action)) { pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); return fenced_construct_reply(request->xml, NULL, &request->result); } alternate_host = check_alternate_host(target); } else { crm_notice("Peer %s wants to fence (%s) '%s' with device '%s'", request->peer, action, target, (device == NULL)? "(any)" : device); } if (alternate_host != NULL) { const char *client_id = NULL; remote_fencing_op_t *op = NULL; if (request->ipc_client->id == 0) { client_id = crm_element_value(request->xml, F_STONITH_CLIENTID); } else { client_id = request->ipc_client->id; } /* Create a duplicate fencing operation to relay with the client ID. * When a query response is received, this operation should be * deleted to avoid keeping the duplicate around. */ op = create_remote_stonith_op(client_id, request->xml, FALSE); crm_xml_add(request->xml, F_STONITH_OPERATION, STONITH_OP_RELAY); crm_xml_add(request->xml, F_STONITH_CLIENTID, request->ipc_client->id); crm_xml_add(request->xml, F_STONITH_REMOTE_OP_ID, op->id); send_cluster_message(crm_get_peer(0, alternate_host), crm_msg_stonith_ng, request->xml, FALSE); pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_PENDING, NULL); } else if (initiate_remote_stonith_op(request->ipc_client, request->xml, FALSE) == NULL) { fenced_set_protocol_error(&request->result); } else { pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_PENDING, NULL); } } if (request->result.execution_status == PCMK_EXEC_PENDING) { return NULL; } return fenced_construct_reply(request->xml, NULL, &request->result); } // STONITH_OP_FENCE_HISTORY static xmlNode * handle_history_request(pcmk__request_t *request) { xmlNode *reply = NULL; xmlNode *data = NULL; stonith_fence_history(request->xml, &data, request->peer, request->call_options); pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); if (!pcmk_is_set(request->call_options, st_opt_discard_reply)) { /* When the local node broadcasts its history, it sets * st_opt_discard_reply and doesn't need a reply. */ reply = fenced_construct_reply(request->xml, data, &request->result); } free_xml(data); return reply; } // STONITH_OP_DEVICE_ADD static xmlNode * handle_device_add_request(pcmk__request_t *request) { const char *op = crm_element_value(request->xml, F_STONITH_OPERATION); xmlNode *dev = get_xpath_object("//" F_STONITH_DEVICE, request->xml, LOG_ERR); if (is_privileged(request->ipc_client, op)) { int rc = stonith_device_register(dev, FALSE); pcmk__set_result(&request->result, ((rc == pcmk_ok)? CRM_EX_OK : CRM_EX_ERROR), stonith__legacy2status(rc), ((rc == pcmk_ok)? NULL : pcmk_strerror(rc))); } else { pcmk__set_result(&request->result, CRM_EX_INSUFFICIENT_PRIV, PCMK_EXEC_INVALID, "Unprivileged users must register device via CIB"); } fenced_send_device_notification(op, &request->result, (dev == NULL)? NULL : ID(dev)); return fenced_construct_reply(request->xml, NULL, &request->result); } // STONITH_OP_DEVICE_DEL static xmlNode * handle_device_delete_request(pcmk__request_t *request) { xmlNode *dev = get_xpath_object("//" F_STONITH_DEVICE, request->xml, LOG_ERR); const char *device_id = crm_element_value(dev, XML_ATTR_ID); const char *op = crm_element_value(request->xml, F_STONITH_OPERATION); if (is_privileged(request->ipc_client, op)) { stonith_device_remove(device_id, false); pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); } else { pcmk__set_result(&request->result, CRM_EX_INSUFFICIENT_PRIV, PCMK_EXEC_INVALID, "Unprivileged users must delete device via CIB"); } fenced_send_device_notification(op, &request->result, device_id); return fenced_construct_reply(request->xml, NULL, &request->result); } // STONITH_OP_LEVEL_ADD static xmlNode * handle_level_add_request(pcmk__request_t *request) { char *desc = NULL; const char *op = crm_element_value(request->xml, F_STONITH_OPERATION); if (is_privileged(request->ipc_client, op)) { fenced_register_level(request->xml, &desc, &request->result); } else { unpack_level_request(request->xml, NULL, NULL, NULL, &desc); pcmk__set_result(&request->result, CRM_EX_INSUFFICIENT_PRIV, PCMK_EXEC_INVALID, "Unprivileged users must add level via CIB"); } fenced_send_level_notification(op, &request->result, desc); free(desc); return fenced_construct_reply(request->xml, NULL, &request->result); } // STONITH_OP_LEVEL_DEL static xmlNode * handle_level_delete_request(pcmk__request_t *request) { char *desc = NULL; const char *op = crm_element_value(request->xml, F_STONITH_OPERATION); if (is_privileged(request->ipc_client, op)) { fenced_unregister_level(request->xml, &desc, &request->result); } else { unpack_level_request(request->xml, NULL, NULL, NULL, &desc); pcmk__set_result(&request->result, CRM_EX_INSUFFICIENT_PRIV, PCMK_EXEC_INVALID, "Unprivileged users must delete level via CIB"); } fenced_send_level_notification(op, &request->result, desc); free(desc); return fenced_construct_reply(request->xml, NULL, &request->result); } // CRM_OP_RM_NODE_CACHE static xmlNode * handle_cache_request(pcmk__request_t *request) { int node_id = 0; const char *name = NULL; crm_element_value_int(request->xml, XML_ATTR_ID, &node_id); name = crm_element_value(request->xml, XML_ATTR_UNAME); reap_crm_member(node_id, name); pcmk__set_result(&request->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); return NULL; } static xmlNode * handle_unknown_request(pcmk__request_t *request) { crm_err("Unknown IPC request %s from %s %s", request->op, pcmk__request_origin_type(request), pcmk__request_origin(request)); pcmk__format_result(&request->result, CRM_EX_PROTOCOL, PCMK_EXEC_INVALID, "Unknown IPC request type '%s' (bug?)", request->op); return fenced_construct_reply(request->xml, NULL, &request->result); } static void fenced_register_handlers(void) { pcmk__server_command_t handlers[] = { { CRM_OP_REGISTER, handle_register_request }, { STONITH_OP_EXEC, handle_agent_request }, { STONITH_OP_TIMEOUT_UPDATE, handle_update_timeout_request }, { STONITH_OP_QUERY, handle_query_request }, { T_STONITH_NOTIFY, handle_notify_request }, { STONITH_OP_RELAY, handle_relay_request }, { STONITH_OP_FENCE, handle_fence_request }, { STONITH_OP_FENCE_HISTORY, handle_history_request }, { STONITH_OP_DEVICE_ADD, handle_device_add_request }, { STONITH_OP_DEVICE_DEL, handle_device_delete_request }, { STONITH_OP_LEVEL_ADD, handle_level_add_request }, { STONITH_OP_LEVEL_DEL, handle_level_delete_request }, { CRM_OP_RM_NODE_CACHE, handle_cache_request }, { NULL, handle_unknown_request }, }; fenced_handlers = pcmk__register_handlers(handlers); } void fenced_unregister_handlers(void) { if (fenced_handlers != NULL) { g_hash_table_destroy(fenced_handlers); fenced_handlers = NULL; } } static void handle_request(pcmk__request_t *request) { xmlNode *reply = NULL; const char *reason = NULL; if (fenced_handlers == NULL) { fenced_register_handlers(); } reply = pcmk__process_request(request, fenced_handlers); if (reply != NULL) { if (pcmk_is_set(request->flags, pcmk__request_reuse_options) && (request->ipc_client != NULL)) { /* Certain IPC-only commands must reuse the call options from the * original request rather than the ones set by stonith_send_reply() * -> do_local_reply(). */ pcmk__ipc_send_xml(request->ipc_client, request->ipc_id, reply, request->ipc_flags); request->ipc_client->request_id = 0; } else { stonith_send_reply(reply, request->call_options, request->peer, request->ipc_client); } free_xml(reply); } reason = request->result.exit_reason; crm_debug("Processed %s request from %s %s: %s%s%s%s", request->op, pcmk__request_origin_type(request), pcmk__request_origin(request), pcmk_exec_status_str(request->result.execution_status), (reason == NULL)? "" : " (", (reason == NULL)? "" : reason, (reason == NULL)? "" : ")"); } static void handle_reply(pcmk__client_t *client, xmlNode *request, const char *remote_peer) { // Copy, because request might be freed before we want to log this char *op = crm_element_value_copy(request, F_STONITH_OPERATION); if (pcmk__str_eq(op, STONITH_OP_QUERY, pcmk__str_none)) { process_remote_stonith_query(request); } else if (pcmk__str_any_of(op, T_STONITH_NOTIFY, STONITH_OP_FENCE, NULL)) { fenced_process_fencing_reply(request); } else { crm_err("Ignoring unknown %s reply from %s %s", pcmk__s(op, "untyped"), ((client == NULL)? "peer" : "client"), ((client == NULL)? remote_peer : pcmk__client_name(client))); crm_log_xml_warn(request, "UnknownOp"); free(op); return; } crm_debug("Processed %s reply from %s %s", op, ((client == NULL)? "peer" : "client"), ((client == NULL)? remote_peer : pcmk__client_name(client))); free(op); } /*! * \internal * \brief Handle a message from an IPC client or CPG peer * * \param[in,out] client If not NULL, IPC client that sent message * \param[in] id If from IPC client, IPC message ID * \param[in] flags Message flags * \param[in,out] message Message XML * \param[in] remote_peer If not NULL, CPG peer that sent message */ void stonith_command(pcmk__client_t *client, uint32_t id, uint32_t flags, xmlNode *message, const char *remote_peer) { int call_options = st_opt_none; bool is_reply = false; CRM_CHECK(message != NULL, return); if (get_xpath_object("//" T_STONITH_REPLY, message, LOG_NEVER) != NULL) { is_reply = true; } crm_element_value_int(message, F_STONITH_CALLOPTS, &call_options); crm_debug("Processing %ssynchronous %s %s %u from %s %s", pcmk_is_set(call_options, st_opt_sync_call)? "" : "a", crm_element_value(message, F_STONITH_OPERATION), (is_reply? "reply" : "request"), id, ((client == NULL)? "peer" : "client"), ((client == NULL)? remote_peer : pcmk__client_name(client))); if (pcmk_is_set(call_options, st_opt_sync_call)) { CRM_ASSERT(client == NULL || client->request_id == id); } if (is_reply) { handle_reply(client, message, remote_peer); } else { pcmk__request_t request = { .ipc_client = client, .ipc_id = id, .ipc_flags = flags, .peer = remote_peer, .xml = message, .call_options = call_options, .result = PCMK__UNKNOWN_RESULT, }; request.op = crm_element_value_copy(request.xml, F_STONITH_OPERATION); CRM_CHECK(request.op != NULL, return); if (pcmk_is_set(request.call_options, st_opt_sync_call)) { pcmk__set_request_flags(&request, pcmk__request_sync); } handle_request(&request); pcmk__reset_request(&request); } } diff --git a/daemons/fenced/fenced_remote.c b/daemons/fenced/fenced_remote.c index 5fc58325d9..2a59376588 100644 --- a/daemons/fenced/fenced_remote.c +++ b/daemons/fenced/fenced_remote.c @@ -1,2416 +1,2446 @@ /* * Copyright 2009-2022 the Pacemaker project contributors * * The version control history for this file may have further details. * * This source code is licensed under the GNU General Public License version 2 * or later (GPLv2+) WITHOUT ANY WARRANTY. */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #define TIMEOUT_MULTIPLY_FACTOR 1.2 /* When one fencer queries its peers for devices able to handle a fencing * request, each peer will reply with a list of such devices available to it. * Each reply will be parsed into a peer_device_info_t, with each device's * information kept in a device_properties_t. */ typedef struct device_properties_s { /* Whether access to this device has been verified */ gboolean verified; /* The remaining members are indexed by the operation's "phase" */ /* Whether this device has been executed in each phase */ gboolean executed[st_phase_max]; /* Whether this device is disallowed from executing in each phase */ gboolean disallowed[st_phase_max]; /* Action-specific timeout for each phase */ int custom_action_timeout[st_phase_max]; /* Action-specific maximum random delay for each phase */ int delay_max[st_phase_max]; /* Action-specific base delay for each phase */ int delay_base[st_phase_max]; /* Group of enum st_device_flags */ uint32_t device_support_flags; } device_properties_t; typedef struct { /* Name of peer that sent this result */ char *host; /* Only try peers for non-topology based operations once */ gboolean tried; /* Number of entries in the devices table */ int ndevices; /* Devices available to this host that are capable of fencing the target */ GHashTable *devices; } peer_device_info_t; GHashTable *stonith_remote_op_list = NULL; extern xmlNode *stonith_create_op(int call_id, const char *token, const char *op, xmlNode * data, int call_options); static void request_peer_fencing(remote_fencing_op_t *op, peer_device_info_t *peer); static void finalize_op(remote_fencing_op_t *op, xmlNode *data, bool dup); static void report_timeout_period(remote_fencing_op_t * op, int op_timeout); static int get_op_total_timeout(const remote_fencing_op_t *op, const peer_device_info_t *chosen_peer); static gint sort_strings(gconstpointer a, gconstpointer b) { return strcmp(a, b); } static void free_remote_query(gpointer data) { if (data != NULL) { peer_device_info_t *peer = data; g_hash_table_destroy(peer->devices); free(peer->host); free(peer); } } void free_stonith_remote_op_list(void) { if (stonith_remote_op_list != NULL) { g_hash_table_destroy(stonith_remote_op_list); stonith_remote_op_list = NULL; } } struct peer_count_data { const remote_fencing_op_t *op; gboolean verified_only; uint32_t support_action_only; int count; }; /*! * \internal * \brief Increment a counter if a device has not been executed yet * * \param[in] key Device ID (ignored) * \param[in] value Device properties * \param[in,out] user_data Peer count data */ static void count_peer_device(gpointer key, gpointer value, gpointer user_data) { device_properties_t *props = (device_properties_t*)value; struct peer_count_data *data = user_data; if (!props->executed[data->op->phase] && (!data->verified_only || props->verified) && ((data->support_action_only == st_device_supports_none) || pcmk_is_set(props->device_support_flags, data->support_action_only))) { ++(data->count); } } /*! * \internal * \brief Check the number of available devices in a peer's query results * * \param[in] op Operation that results are for * \param[in] peer Peer to count * \param[in] verified_only Whether to count only verified devices * \param[in] support_action_only Whether to count only devices that support action * * \return Number of devices available to peer that were not already executed */ static int count_peer_devices(const remote_fencing_op_t *op, const peer_device_info_t *peer, gboolean verified_only, uint32_t support_on_action_only) { struct peer_count_data data; data.op = op; data.verified_only = verified_only; data.support_action_only = support_on_action_only; data.count = 0; if (peer) { g_hash_table_foreach(peer->devices, count_peer_device, &data); } return data.count; } /*! * \internal * \brief Search for a device in a query result * * \param[in] op Operation that result is for * \param[in] peer Query result for a peer * \param[in] device Device ID to search for * * \return Device properties if found, NULL otherwise */ static device_properties_t * find_peer_device(const remote_fencing_op_t *op, const peer_device_info_t *peer, const char *device, uint32_t support_action_only) { device_properties_t *props = g_hash_table_lookup(peer->devices, device); if (props && support_action_only != st_device_supports_none && !pcmk_is_set(props->device_support_flags, support_action_only)) { return NULL; } return (props && !props->executed[op->phase] && !props->disallowed[op->phase])? props : NULL; } /*! * \internal * \brief Find a device in a peer's device list and mark it as executed * * \param[in] op Operation that peer result is for * \param[in,out] peer Peer with results to search * \param[in] device ID of device to mark as done * \param[in] verified_devices_only Only consider verified devices * * \return TRUE if device was found and marked, FALSE otherwise */ static gboolean grab_peer_device(const remote_fencing_op_t *op, peer_device_info_t *peer, const char *device, gboolean verified_devices_only) { device_properties_t *props = find_peer_device(op, peer, device, pcmk__str_eq(op->action, "on", pcmk__str_casei)? st_device_supports_on: st_device_supports_none); if ((props == NULL) || (verified_devices_only && !props->verified)) { return FALSE; } crm_trace("Removing %s from %s (%d remaining)", device, peer->host, count_peer_devices(op, peer, FALSE, st_device_supports_none)); props->executed[op->phase] = TRUE; return TRUE; } static void clear_remote_op_timers(remote_fencing_op_t * op) { if (op->query_timer) { g_source_remove(op->query_timer); op->query_timer = 0; } if (op->op_timer_total) { g_source_remove(op->op_timer_total); op->op_timer_total = 0; } if (op->op_timer_one) { g_source_remove(op->op_timer_one); op->op_timer_one = 0; } } static void free_remote_op(gpointer data) { remote_fencing_op_t *op = data; crm_log_xml_debug(op->request, "Destroying"); clear_remote_op_timers(op); free(op->id); free(op->action); free(op->delegate); free(op->target); free(op->client_id); free(op->client_name); free(op->originator); if (op->query_results) { g_list_free_full(op->query_results, free_remote_query); } if (op->request) { free_xml(op->request); op->request = NULL; } if (op->devices_list) { g_list_free_full(op->devices_list, free); op->devices_list = NULL; } g_list_free_full(op->automatic_list, free); g_list_free(op->duplicates); pcmk__reset_result(&op->result); free(op); } void init_stonith_remote_op_hash_table(GHashTable **table) { if (*table == NULL) { *table = pcmk__strkey_table(NULL, free_remote_op); } } /*! * \internal * \brief Return an operation's originally requested action (before any remap) * * \param[in] op Operation to check * * \return Operation's original action */ static const char * op_requested_action(const remote_fencing_op_t *op) { return ((op->phase > st_phase_requested)? "reboot" : op->action); } /*! * \internal * \brief Remap a "reboot" operation to the "off" phase * * \param[in,out] op Operation to remap */ static void op_phase_off(remote_fencing_op_t *op) { crm_info("Remapping multiple-device reboot targeting %s to 'off' " CRM_XS " id=%.8s", op->target, op->id); op->phase = st_phase_off; /* Happily, "off" and "on" are shorter than "reboot", so we can reuse the * memory allocation at each phase. */ strcpy(op->action, "off"); } /*! * \internal * \brief Advance a remapped reboot operation to the "on" phase * * \param[in,out] op Operation to remap */ static void op_phase_on(remote_fencing_op_t *op) { GList *iter = NULL; crm_info("Remapped 'off' targeting %s complete, " "remapping to 'on' for %s " CRM_XS " id=%.8s", op->target, op->client_name, op->id); op->phase = st_phase_on; strcpy(op->action, "on"); /* Skip devices with automatic unfencing, because the cluster will handle it * when the node rejoins. */ for (iter = op->automatic_list; iter != NULL; iter = iter->next) { GList *match = g_list_find_custom(op->devices_list, iter->data, sort_strings); if (match) { op->devices_list = g_list_remove(op->devices_list, match->data); } } g_list_free_full(op->automatic_list, free); op->automatic_list = NULL; /* Rewind device list pointer */ op->devices = op->devices_list; } /*! * \internal * \brief Reset a remapped reboot operation * * \param[in,out] op Operation to reset */ static void undo_op_remap(remote_fencing_op_t *op) { if (op->phase > 0) { crm_info("Undoing remap of reboot targeting %s for %s " CRM_XS " id=%.8s", op->target, op->client_name, op->id); op->phase = st_phase_requested; strcpy(op->action, "reboot"); } } /*! * \internal * \brief Create notification data XML for a fencing operation result * * \param[in] op Fencer operation that completed * * \return Newly created XML to add as notification data * \note The caller is responsible for freeing the result. */ static xmlNode * fencing_result2xml(const remote_fencing_op_t *op) { xmlNode *notify_data = create_xml_node(NULL, T_STONITH_NOTIFY_FENCE); crm_xml_add_int(notify_data, "state", op->state); crm_xml_add(notify_data, F_STONITH_TARGET, op->target); crm_xml_add(notify_data, F_STONITH_ACTION, op->action); crm_xml_add(notify_data, F_STONITH_DELEGATE, op->delegate); crm_xml_add(notify_data, F_STONITH_REMOTE_OP_ID, op->id); crm_xml_add(notify_data, F_STONITH_ORIGIN, op->originator); crm_xml_add(notify_data, F_STONITH_CLIENTID, op->client_id); crm_xml_add(notify_data, F_STONITH_CLIENTNAME, op->client_name); return notify_data; } /*! * \internal * \brief Broadcast a fence result notification to all CPG peers * * \param[in] op Fencer operation that completed * \param[in] op_merged Whether this operation is a duplicate of another */ void fenced_broadcast_op_result(const remote_fencing_op_t *op, bool op_merged) { static int count = 0; xmlNode *bcast = create_xml_node(NULL, T_STONITH_REPLY); xmlNode *notify_data = fencing_result2xml(op); count++; crm_trace("Broadcasting result to peers"); crm_xml_add(bcast, F_TYPE, T_STONITH_NOTIFY); crm_xml_add(bcast, F_SUBTYPE, "broadcast"); crm_xml_add(bcast, F_STONITH_OPERATION, T_STONITH_NOTIFY); crm_xml_add_int(bcast, "count", count); if (op_merged) { pcmk__xe_set_bool_attr(bcast, F_STONITH_MERGED, true); } stonith__xe_set_result(notify_data, &op->result); add_message_xml(bcast, F_STONITH_CALLDATA, notify_data); send_cluster_message(NULL, crm_msg_stonith_ng, bcast, FALSE); free_xml(notify_data); free_xml(bcast); return; } /*! * \internal * \brief Reply to a local request originator and notify all subscribed clients * * \param[in,out] op Fencer operation that completed * \param[in,out] data Top-level XML to add notification to */ static void handle_local_reply_and_notify(remote_fencing_op_t *op, xmlNode *data) { xmlNode *notify_data = NULL; xmlNode *reply = NULL; pcmk__client_t *client = NULL; if (op->notify_sent == TRUE) { /* nothing to do */ return; } /* Do notification with a clean data object */ crm_xml_add_int(data, "state", op->state); crm_xml_add(data, F_STONITH_TARGET, op->target); crm_xml_add(data, F_STONITH_OPERATION, op->action); reply = fenced_construct_reply(op->request, data, &op->result); crm_xml_add(reply, F_STONITH_DELEGATE, op->delegate); /* Send fencing OP reply to local client that initiated fencing */ client = pcmk__find_client_by_id(op->client_id); if (client == NULL) { crm_trace("Skipping reply to %s: no longer a client", op->client_id); } else { do_local_reply(reply, client, op->call_options); } /* bcast to all local clients that the fencing operation happend */ notify_data = fencing_result2xml(op); fenced_send_notification(T_STONITH_NOTIFY_FENCE, &op->result, notify_data); free_xml(notify_data); fenced_send_notification(T_STONITH_NOTIFY_HISTORY, NULL, NULL); /* mark this op as having notify's already sent */ op->notify_sent = TRUE; free_xml(reply); } /*! * \internal * \brief Finalize all duplicates of a given fencer operation * * \param[in,out] op Fencer operation that completed * \param[in,out] data Top-level XML to add notification to */ static void finalize_op_duplicates(remote_fencing_op_t *op, xmlNode *data) { for (GList *iter = op->duplicates; iter != NULL; iter = iter->next) { remote_fencing_op_t *other = iter->data; if (other->state == st_duplicate) { other->state = op->state; crm_debug("Performing duplicate notification for %s@%s: %s " CRM_XS " id=%.8s", other->client_name, other->originator, pcmk_exec_status_str(op->result.execution_status), other->id); pcmk__copy_result(&op->result, &other->result); finalize_op(other, data, true); } else { // Possible if (for example) it timed out already crm_err("Skipping duplicate notification for %s@%s " CRM_XS " state=%s id=%.8s", other->client_name, other->originator, stonith_op_state_str(other->state), other->id); } } } static char * delegate_from_xml(xmlNode *xml) { xmlNode *match = get_xpath_object("//@" F_STONITH_DELEGATE, xml, LOG_NEVER); if (match == NULL) { return crm_element_value_copy(xml, F_ORIG); } else { return crm_element_value_copy(match, F_STONITH_DELEGATE); } } /*! * \internal * \brief Finalize a peer fencing operation * * Clean up after a fencing operation completes. This function has two code * paths: the executioner uses it to broadcast the result to CPG peers, and then * each peer (including the executioner) uses it to process that broadcast and * notify its IPC clients of the result. * * \param[in,out] op Fencer operation that completed * \param[in,out] data If not NULL, XML reply of last delegated operation * \param[in] dup Whether this operation is a duplicate of another * (in which case, do not broadcast the result) * * \note The operation result should be set before calling this function. */ static void finalize_op(remote_fencing_op_t *op, xmlNode *data, bool dup) { int level = LOG_ERR; const char *subt = NULL; xmlNode *local_data = NULL; gboolean op_merged = FALSE; CRM_CHECK((op != NULL), return); if (op->notify_sent) { // Most likely, this is a timed-out action that eventually completed crm_notice("Operation '%s'%s%s by %s for %s@%s%s: " "Result arrived too late " CRM_XS " id=%.8s", op->action, (op->target? " targeting " : ""), (op->target? op->target : ""), (op->delegate? op->delegate : "unknown node"), op->client_name, op->originator, (op_merged? " (merged)" : ""), op->id); return; } set_fencing_completed(op); clear_remote_op_timers(op); undo_op_remap(op); if (data == NULL) { data = create_xml_node(NULL, "remote-op"); local_data = data; } else if (op->delegate == NULL) { switch (op->result.execution_status) { case PCMK_EXEC_NO_FENCE_DEVICE: break; case PCMK_EXEC_INVALID: if (op->result.exit_status != CRM_EX_EXPIRED) { op->delegate = delegate_from_xml(data); } break; default: op->delegate = delegate_from_xml(data); break; } } if (dup || (crm_element_value(data, F_STONITH_MERGED) != NULL)) { op_merged = true; } /* Tell everyone the operation is done, we will continue * with doing the local notifications once we receive * the broadcast back. */ subt = crm_element_value(data, F_SUBTYPE); if (!dup && !pcmk__str_eq(subt, "broadcast", pcmk__str_casei)) { /* Defer notification until the bcast message arrives */ fenced_broadcast_op_result(op, op_merged); free_xml(local_data); return; } if (pcmk__result_ok(&op->result) || dup || !pcmk__str_eq(op->originator, stonith_our_uname, pcmk__str_casei)) { level = LOG_NOTICE; } do_crm_log(level, "Operation '%s'%s%s by %s for %s@%s%s: %s (%s%s%s) " CRM_XS " id=%.8s", op->action, (op->target? " targeting " : ""), (op->target? op->target : ""), (op->delegate? op->delegate : "unknown node"), op->client_name, op->originator, (op_merged? " (merged)" : ""), crm_exit_str(op->result.exit_status), pcmk_exec_status_str(op->result.execution_status), ((op->result.exit_reason == NULL)? "" : ": "), ((op->result.exit_reason == NULL)? "" : op->result.exit_reason), op->id); handle_local_reply_and_notify(op, data); if (!dup) { finalize_op_duplicates(op, data); } /* Free non-essential parts of the record * Keep the record around so we can query the history */ if (op->query_results) { g_list_free_full(op->query_results, free_remote_query); op->query_results = NULL; } if (op->request) { free_xml(op->request); op->request = NULL; } free_xml(local_data); } /*! * \internal * \brief Finalize a watchdog fencer op after the waiting time expires * * \param[in,out] userdata Fencer operation that completed * * \return G_SOURCE_REMOVE (which tells glib not to restart timer) */ static gboolean remote_op_watchdog_done(gpointer userdata) { remote_fencing_op_t *op = userdata; op->op_timer_one = 0; crm_notice("Self-fencing (%s) by %s for %s assumed complete " CRM_XS " id=%.8s", op->action, op->target, op->client_name, op->id); op->state = st_done; pcmk__set_result(&op->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); finalize_op(op, NULL, false); return G_SOURCE_REMOVE; } static gboolean remote_op_timeout_one(gpointer userdata) { remote_fencing_op_t *op = userdata; op->op_timer_one = 0; crm_notice("Peer's '%s' action targeting %s for client %s timed out " CRM_XS " id=%.8s", op->action, op->target, op->client_name, op->id); pcmk__set_result(&op->result, CRM_EX_ERROR, PCMK_EXEC_TIMEOUT, "Peer did not return fence result within timeout"); // Try another device, if appropriate request_peer_fencing(op, NULL); return FALSE; } /*! * \internal * \brief Finalize a remote fencer operation that timed out * * \param[in,out] op Fencer operation that timed out * \param[in] reason Readable description of what step timed out */ static void finalize_timed_out_op(remote_fencing_op_t *op, const char *reason) { op->op_timer_total = 0; crm_debug("Action '%s' targeting %s for client %s timed out " CRM_XS " id=%.8s", op->action, op->target, op->client_name, op->id); if (op->phase == st_phase_on) { /* A remapped reboot operation timed out in the "on" phase, but the * "off" phase completed successfully, so quit trying any further * devices, and return success. */ op->state = st_done; pcmk__set_result(&op->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); } else { op->state = st_failed; pcmk__set_result(&op->result, CRM_EX_ERROR, PCMK_EXEC_TIMEOUT, reason); } finalize_op(op, NULL, false); } /*! * \internal * \brief Finalize a remote fencer operation that timed out * * \param[in,out] userdata Fencer operation that timed out * * \return G_SOURCE_REMOVE (which tells glib not to restart timer) */ static gboolean remote_op_timeout(gpointer userdata) { remote_fencing_op_t *op = userdata; if (op->state == st_done) { crm_debug("Action '%s' targeting %s for client %s already completed " CRM_XS " id=%.8s", op->action, op->target, op->client_name, op->id); } else { finalize_timed_out_op(userdata, "Fencing did not complete within a " "total timeout based on the " "configured timeout and retries for " "any devices attempted"); } return G_SOURCE_REMOVE; } static gboolean remote_op_query_timeout(gpointer data) { remote_fencing_op_t *op = data; op->query_timer = 0; if (op->state == st_done) { crm_debug("Operation %.8s targeting %s already completed", op->id, op->target); } else if (op->state == st_exec) { crm_debug("Operation %.8s targeting %s already in progress", op->id, op->target); } else if (op->query_results) { // Query succeeded, so attempt the actual fencing crm_debug("Query %.8s targeting %s complete (state=%s)", op->id, op->target, stonith_op_state_str(op->state)); request_peer_fencing(op, NULL); } else { crm_debug("Query %.8s targeting %s timed out (state=%s)", op->id, op->target, stonith_op_state_str(op->state)); if (op->op_timer_total) { g_source_remove(op->op_timer_total); op->op_timer_total = 0; } finalize_timed_out_op(op, "No capable peers replied to device query " "within timeout"); } return FALSE; } static gboolean topology_is_empty(stonith_topology_t *tp) { int i; if (tp == NULL) { return TRUE; } for (i = 0; i < ST_LEVEL_MAX; i++) { if (tp->levels[i] != NULL) { return FALSE; } } return TRUE; } /*! * \internal * \brief Add a device to an operation's automatic unfencing list * * \param[in,out] op Operation to modify * \param[in] device Device ID to add */ static void add_required_device(remote_fencing_op_t *op, const char *device) { GList *match = g_list_find_custom(op->automatic_list, device, sort_strings); if (!match) { op->automatic_list = g_list_prepend(op->automatic_list, strdup(device)); } } /*! * \internal * \brief Remove a device from the automatic unfencing list * * \param[in,out] op Operation to modify * \param[in] device Device ID to remove */ static void remove_required_device(remote_fencing_op_t *op, const char *device) { GList *match = g_list_find_custom(op->automatic_list, device, sort_strings); if (match) { op->automatic_list = g_list_remove(op->automatic_list, match->data); } } /* deep copy the device list */ static void set_op_device_list(remote_fencing_op_t * op, GList *devices) { GList *lpc = NULL; if (op->devices_list) { g_list_free_full(op->devices_list, free); op->devices_list = NULL; } for (lpc = devices; lpc != NULL; lpc = lpc->next) { op->devices_list = g_list_append(op->devices_list, strdup(lpc->data)); } op->devices = op->devices_list; } /*! * \internal * \brief Check whether a node matches a topology target * * \param[in] tp Topology table entry to check * \param[in] node Name of node to check * * \return TRUE if node matches topology target */ static gboolean topology_matches(const stonith_topology_t *tp, const char *node) { regex_t r_patt; CRM_CHECK(node && tp && tp->target, return FALSE); switch (tp->kind) { case fenced_target_by_attribute: /* This level targets by attribute, so tp->target is a NAME=VALUE pair * of a permanent attribute applied to targeted nodes. The test below * relies on the locally cached copy of the CIB, so if fencing needs to * be done before the initial CIB is received or after a malformed CIB * is received, then the topology will be unable to be used. */ if (node_has_attr(node, tp->target_attribute, tp->target_value)) { crm_notice("Matched %s with %s by attribute", node, tp->target); return TRUE; } break; case fenced_target_by_pattern: /* This level targets node names matching a pattern, so tp->target * (and tp->target_pattern) is a regular expression. */ if (regcomp(&r_patt, tp->target_pattern, REG_EXTENDED|REG_NOSUB)) { crm_info("Bad regex '%s' for fencing level", tp->target); } else { int status = regexec(&r_patt, node, 0, NULL, 0); regfree(&r_patt); if (status == 0) { crm_notice("Matched %s with %s by name", node, tp->target); return TRUE; } } break; case fenced_target_by_name: crm_trace("Testing %s against %s", node, tp->target); return pcmk__str_eq(tp->target, node, pcmk__str_casei); default: break; } crm_trace("No match for %s with %s", node, tp->target); return FALSE; } stonith_topology_t * find_topology_for_host(const char *host) { GHashTableIter tIter; stonith_topology_t *tp = g_hash_table_lookup(topology, host); if(tp != NULL) { crm_trace("Found %s for %s in %d entries", tp->target, host, g_hash_table_size(topology)); return tp; } g_hash_table_iter_init(&tIter, topology); while (g_hash_table_iter_next(&tIter, NULL, (gpointer *) & tp)) { if (topology_matches(tp, host)) { crm_trace("Found %s for %s in %d entries", tp->target, host, g_hash_table_size(topology)); return tp; } } crm_trace("No matches for %s in %d topology entries", host, g_hash_table_size(topology)); return NULL; } /*! * \internal * \brief Set fencing operation's device list to target's next topology level * * \param[in,out] op Remote fencing operation to modify * \param[in] empty_ok If true, an operation without a target (i.e. * queries) or a target without a topology will get a * pcmk_rc_ok return value instead of ENODEV * * \return Standard Pacemaker return value */ static int advance_topology_level(remote_fencing_op_t *op, bool empty_ok) { stonith_topology_t *tp = NULL; if (op->target) { tp = find_topology_for_host(op->target); } if (topology_is_empty(tp)) { return empty_ok? pcmk_rc_ok : ENODEV; } CRM_ASSERT(tp->levels != NULL); stonith__set_call_options(op->call_options, op->id, st_opt_topology); /* This is a new level, so undo any remapping left over from previous */ undo_op_remap(op); do { op->level++; } while (op->level < ST_LEVEL_MAX && tp->levels[op->level] == NULL); if (op->level < ST_LEVEL_MAX) { crm_trace("Attempting fencing level %d targeting %s (%d devices) " "for client %s@%s (id=%.8s)", op->level, op->target, g_list_length(tp->levels[op->level]), op->client_name, op->originator, op->id); set_op_device_list(op, tp->levels[op->level]); // The requested delay has been applied for the first fencing level if (op->level > 1 && op->delay > 0) { op->delay = 0; } if (g_list_next(op->devices_list) && pcmk__str_eq(op->action, "reboot", pcmk__str_casei)) { /* A reboot has been requested for a topology level with multiple * devices. Instead of rebooting the devices sequentially, we will * turn them all off, then turn them all on again. (Think about * switched power outlets for redundant power supplies.) */ op_phase_off(op); } return pcmk_rc_ok; } crm_info("All fencing options targeting %s for client %s@%s failed " CRM_XS " id=%.8s", op->target, op->client_name, op->originator, op->id); return ENODEV; } /*! * \internal * \brief If fencing operation is a duplicate, merge it into the other one * * \param[in,out] op Fencing operation to check */ static void merge_duplicates(remote_fencing_op_t *op) { GHashTableIter iter; remote_fencing_op_t *other = NULL; time_t now = time(NULL); g_hash_table_iter_init(&iter, stonith_remote_op_list); while (g_hash_table_iter_next(&iter, NULL, (void **)&other)) { const char *other_action = op_requested_action(other); if (!strcmp(op->id, other->id)) { continue; // Don't compare against self } if (other->state > st_exec) { crm_trace("%.8s not duplicate of %.8s: not in progress", op->id, other->id); continue; } if (!pcmk__str_eq(op->target, other->target, pcmk__str_casei)) { crm_trace("%.8s not duplicate of %.8s: node %s vs. %s", op->id, other->id, op->target, other->target); continue; } if (!pcmk__str_eq(op->action, other_action, pcmk__str_casei)) { crm_trace("%.8s not duplicate of %.8s: action %s vs. %s", op->id, other->id, op->action, other_action); continue; } if (pcmk__str_eq(op->client_name, other->client_name, pcmk__str_casei)) { crm_trace("%.8s not duplicate of %.8s: same client %s", op->id, other->id, op->client_name); continue; } if (pcmk__str_eq(other->target, other->originator, pcmk__str_casei)) { crm_trace("%.8s not duplicate of %.8s: suicide for %s", op->id, other->id, other->target); continue; } if (!fencing_peer_active(crm_get_peer(0, other->originator))) { crm_notice("Failing action '%s' targeting %s originating from " "client %s@%s: Originator is dead " CRM_XS " id=%.8s", other->action, other->target, other->client_name, other->originator, other->id); crm_trace("%.8s not duplicate of %.8s: originator dead", op->id, other->id); other->state = st_failed; continue; } if ((other->total_timeout > 0) && (now > (other->total_timeout + other->created))) { crm_trace("%.8s not duplicate of %.8s: old (%ld vs. %ld + %d)", op->id, other->id, now, other->created, other->total_timeout); continue; } /* There is another in-flight request to fence the same host * Piggyback on that instead. If it fails, so do we. */ other->duplicates = g_list_append(other->duplicates, op); if (other->total_timeout == 0) { other->total_timeout = op->total_timeout = TIMEOUT_MULTIPLY_FACTOR * get_op_total_timeout(op, NULL); crm_trace("Best guess as to timeout used for %.8s: %d", other->id, other->total_timeout); } crm_notice("Merging fencing action '%s' targeting %s originating from " "client %s with identical request from %s@%s " CRM_XS " original=%.8s duplicate=%.8s total_timeout=%ds", op->action, op->target, op->client_name, other->client_name, other->originator, op->id, other->id, other->total_timeout); report_timeout_period(op, other->total_timeout); op->state = st_duplicate; } } static uint32_t fencing_active_peers(void) { uint32_t count = 0; crm_node_t *entry; GHashTableIter gIter; g_hash_table_iter_init(&gIter, crm_peer_cache); while (g_hash_table_iter_next(&gIter, NULL, (void **)&entry)) { if(fencing_peer_active(entry)) { count++; } } return count; } /*! * \internal * \brief Process a manual confirmation of a pending fence action * * \param[in] client IPC client that sent confirmation * \param[in,out] msg Request XML with manual confirmation * * \return Standard Pacemaker return code */ int fenced_handle_manual_confirmation(const pcmk__client_t *client, xmlNode *msg) { remote_fencing_op_t *op = NULL; xmlNode *dev = get_xpath_object("//@" F_STONITH_TARGET, msg, LOG_ERR); CRM_CHECK(dev != NULL, return EPROTO); crm_notice("Received manual confirmation that %s has been fenced", pcmk__s(crm_element_value(dev, F_STONITH_TARGET), "unknown target")); op = initiate_remote_stonith_op(client, msg, TRUE); if (op == NULL) { return EPROTO; } op->state = st_done; set_fencing_completed(op); op->delegate = strdup("a human"); // For the fencer's purposes, the fencing operation is done pcmk__set_result(&op->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); finalize_op(op, msg, false); /* For the requester's purposes, the operation is still pending. The * actual result will be sent asynchronously via the operation's done_cb(). */ return EINPROGRESS; } /*! * \internal * \brief Create a new remote stonith operation * * \param[in] client ID of local stonith client that initiated the operation * \param[in] request The request from the client that started the operation * \param[in] peer TRUE if this operation is owned by another stonith peer * (an operation owned by one peer is stored on all peers, * but only the owner executes it; all nodes get the results * once the owner finishes execution) */ void * create_remote_stonith_op(const char *client, xmlNode *request, gboolean peer) { remote_fencing_op_t *op = NULL; xmlNode *dev = get_xpath_object("//@" F_STONITH_TARGET, request, LOG_NEVER); int call_options = 0; const char *operation = NULL; init_stonith_remote_op_hash_table(&stonith_remote_op_list); /* If this operation is owned by another node, check to make * sure we haven't already created this operation. */ if (peer && dev) { const char *op_id = crm_element_value(dev, F_STONITH_REMOTE_OP_ID); CRM_CHECK(op_id != NULL, return NULL); op = g_hash_table_lookup(stonith_remote_op_list, op_id); if (op) { crm_debug("Reusing existing remote fencing op %.8s for %s", op_id, ((client == NULL)? "unknown client" : client)); return op; } } op = calloc(1, sizeof(remote_fencing_op_t)); CRM_ASSERT(op != NULL); crm_element_value_int(request, F_STONITH_TIMEOUT, &(op->base_timeout)); // Value -1 means disable any static/random fencing delays crm_element_value_int(request, F_STONITH_DELAY, &(op->delay)); if (peer && dev) { op->id = crm_element_value_copy(dev, F_STONITH_REMOTE_OP_ID); } else { op->id = crm_generate_uuid(); } g_hash_table_replace(stonith_remote_op_list, op->id, op); op->state = st_query; op->replies_expected = fencing_active_peers(); op->action = crm_element_value_copy(dev, F_STONITH_ACTION); op->originator = crm_element_value_copy(dev, F_STONITH_ORIGIN); op->delegate = crm_element_value_copy(dev, F_STONITH_DELEGATE); /* May not be set */ op->created = time(NULL); if (op->originator == NULL) { /* Local or relayed request */ op->originator = strdup(stonith_our_uname); } CRM_LOG_ASSERT(client != NULL); if (client) { op->client_id = strdup(client); } /* For a RELAY operation, set fenced on the client. */ operation = crm_element_value(request, F_STONITH_OPERATION); if (pcmk__str_eq(operation, STONITH_OP_RELAY, pcmk__str_none)) { op->client_name = crm_strdup_printf("%s.%lu", crm_system_name, (unsigned long) getpid()); } else { op->client_name = crm_element_value_copy(request, F_STONITH_CLIENTNAME); } op->target = crm_element_value_copy(dev, F_STONITH_TARGET); op->request = copy_xml(request); /* TODO: Figure out how to avoid this */ crm_element_value_int(request, F_STONITH_CALLOPTS, &call_options); op->call_options = call_options; crm_element_value_int(request, F_STONITH_CALLID, &(op->client_callid)); crm_trace("%s new fencing op %s ('%s' targeting %s for client %s, " "base timeout %d, %u %s expected)", (peer && dev)? "Recorded" : "Generated", op->id, op->action, op->target, op->client_name, op->base_timeout, op->replies_expected, pcmk__plural_alt(op->replies_expected, "reply", "replies")); if (op->call_options & st_opt_cs_nodeid) { int nodeid; crm_node_t *node; pcmk__scan_min_int(op->target, &nodeid, 0); node = pcmk__search_known_node_cache(nodeid, NULL, CRM_GET_PEER_ANY); /* Ensure the conversion only happens once */ stonith__clear_call_options(op->call_options, op->id, st_opt_cs_nodeid); if (node && node->uname) { free(op->target); op->target = strdup(node->uname); } else { crm_warn("Could not expand nodeid '%s' into a host name", op->target); } } /* check to see if this is a duplicate operation of another in-flight operation */ merge_duplicates(op); if (op->state != st_duplicate) { /* kick history readers */ fenced_send_notification(T_STONITH_NOTIFY_HISTORY, NULL, NULL); } /* safe to trim as long as that doesn't touch pending ops */ stonith_fence_history_trim(); return op; } /*! * \internal * \brief Create a peer fencing operation from a request, and initiate it * * \param[in] client IPC client that made request (NULL to get from request) * \param[in] request Request XML * \param[in] manual_ack Whether this is a manual action confirmation * * \return Newly created operation on success, otherwise NULL */ remote_fencing_op_t * initiate_remote_stonith_op(const pcmk__client_t *client, xmlNode *request, gboolean manual_ack) { int query_timeout = 0; xmlNode *query = NULL; const char *client_id = NULL; remote_fencing_op_t *op = NULL; const char *relay_op_id = NULL; const char *operation = NULL; if (client) { client_id = client->id; } else { client_id = crm_element_value(request, F_STONITH_CLIENTID); } CRM_LOG_ASSERT(client_id != NULL); op = create_remote_stonith_op(client_id, request, FALSE); op->owner = TRUE; if (manual_ack) { return op; } CRM_CHECK(op->action, return NULL); if (advance_topology_level(op, true) != pcmk_rc_ok) { op->state = st_failed; } switch (op->state) { case st_failed: // advance_topology_level() exhausted levels pcmk__set_result(&op->result, CRM_EX_ERROR, PCMK_EXEC_ERROR, "All topology levels failed"); crm_warn("Could not request peer fencing (%s) targeting %s " CRM_XS " id=%.8s", op->action, op->target, op->id); finalize_op(op, NULL, false); return op; case st_duplicate: crm_info("Requesting peer fencing (%s) targeting %s (duplicate) " CRM_XS " id=%.8s", op->action, op->target, op->id); return op; default: crm_notice("Requesting peer fencing (%s) targeting %s " CRM_XS " id=%.8s state=%s base_timeout=%d", op->action, op->target, op->id, stonith_op_state_str(op->state), op->base_timeout); } query = stonith_create_op(op->client_callid, op->id, STONITH_OP_QUERY, NULL, op->call_options); crm_xml_add(query, F_STONITH_REMOTE_OP_ID, op->id); crm_xml_add(query, F_STONITH_TARGET, op->target); crm_xml_add(query, F_STONITH_ACTION, op_requested_action(op)); crm_xml_add(query, F_STONITH_ORIGIN, op->originator); crm_xml_add(query, F_STONITH_CLIENTID, op->client_id); crm_xml_add(query, F_STONITH_CLIENTNAME, op->client_name); crm_xml_add_int(query, F_STONITH_TIMEOUT, op->base_timeout); /* In case of RELAY operation, RELAY information is added to the query to delete the original operation of RELAY. */ operation = crm_element_value(request, F_STONITH_OPERATION); if (pcmk__str_eq(operation, STONITH_OP_RELAY, pcmk__str_none)) { relay_op_id = crm_element_value(request, F_STONITH_REMOTE_OP_ID); if (relay_op_id) { crm_xml_add(query, F_STONITH_REMOTE_OP_ID_RELAY, relay_op_id); } } send_cluster_message(NULL, crm_msg_stonith_ng, query, FALSE); free_xml(query); query_timeout = op->base_timeout * TIMEOUT_MULTIPLY_FACTOR; op->query_timer = g_timeout_add((1000 * query_timeout), remote_op_query_timeout, op); return op; } enum find_best_peer_options { /*! Skip checking the target peer for capable fencing devices */ FIND_PEER_SKIP_TARGET = 0x0001, /*! Only check the target peer for capable fencing devices */ FIND_PEER_TARGET_ONLY = 0x0002, /*! Skip peers and devices that are not verified */ FIND_PEER_VERIFIED_ONLY = 0x0004, }; static peer_device_info_t * find_best_peer(const char *device, remote_fencing_op_t * op, enum find_best_peer_options options) { GList *iter = NULL; gboolean verified_devices_only = (options & FIND_PEER_VERIFIED_ONLY) ? TRUE : FALSE; if (!device && pcmk_is_set(op->call_options, st_opt_topology)) { return NULL; } for (iter = op->query_results; iter != NULL; iter = iter->next) { peer_device_info_t *peer = iter->data; crm_trace("Testing result from %s targeting %s with %d device%s: %d %x", peer->host, op->target, peer->ndevices, pcmk__plural_s(peer->ndevices), peer->tried, options); if ((options & FIND_PEER_SKIP_TARGET) && pcmk__str_eq(peer->host, op->target, pcmk__str_casei)) { continue; } if ((options & FIND_PEER_TARGET_ONLY) && !pcmk__str_eq(peer->host, op->target, pcmk__str_casei)) { continue; } if (pcmk_is_set(op->call_options, st_opt_topology)) { if (grab_peer_device(op, peer, device, verified_devices_only)) { return peer; } } else if ((peer->tried == FALSE) && count_peer_devices(op, peer, verified_devices_only, pcmk__str_eq(op->action, "on", pcmk__str_casei)? st_device_supports_on : st_device_supports_none)) { /* No topology: Use the current best peer */ crm_trace("Simple fencing"); return peer; } } return NULL; } static peer_device_info_t * stonith_choose_peer(remote_fencing_op_t * op) { const char *device = NULL; peer_device_info_t *peer = NULL; uint32_t active = fencing_active_peers(); do { if (op->devices) { device = op->devices->data; crm_trace("Checking for someone to fence (%s) %s using %s", op->action, op->target, device); } else { crm_trace("Checking for someone to fence (%s) %s", op->action, op->target); } /* Best choice is a peer other than the target with verified access */ peer = find_best_peer(device, op, FIND_PEER_SKIP_TARGET|FIND_PEER_VERIFIED_ONLY); if (peer) { crm_trace("Found verified peer %s for %s", peer->host, device?device:""); return peer; } if(op->query_timer != 0 && op->replies < QB_MIN(op->replies_expected, active)) { crm_trace("Waiting before looking for unverified devices to fence %s", op->target); return NULL; } /* If no other peer has verified access, next best is unverified access */ peer = find_best_peer(device, op, FIND_PEER_SKIP_TARGET); if (peer) { crm_trace("Found best unverified peer %s", peer->host); return peer; } /* If no other peer can do it, last option is self-fencing * (which is never allowed for the "on" phase of a remapped reboot) */ if (op->phase != st_phase_on) { peer = find_best_peer(device, op, FIND_PEER_TARGET_ONLY); if (peer) { crm_trace("%s will fence itself", peer->host); return peer; } } /* Try the next fencing level if there is one (unless we're in the "on" * phase of a remapped "reboot", because we ignore errors in that case) */ } while ((op->phase != st_phase_on) && pcmk_is_set(op->call_options, st_opt_topology) && (advance_topology_level(op, false) == pcmk_rc_ok)); crm_notice("Couldn't find anyone to fence (%s) %s using %s", op->action, op->target, (device? device : "any device")); return NULL; } static int get_device_timeout(const remote_fencing_op_t *op, const peer_device_info_t *peer, const char *device) { device_properties_t *props; if (!peer || !device) { return op->base_timeout; } props = g_hash_table_lookup(peer->devices, device); if (!props) { return op->base_timeout; } return (props->custom_action_timeout[op->phase]? props->custom_action_timeout[op->phase] : op->base_timeout) + props->delay_max[op->phase]; } struct timeout_data { const remote_fencing_op_t *op; const peer_device_info_t *peer; int total_timeout; }; /*! * \internal * \brief Add timeout to a total if device has not been executed yet * * \param[in] key GHashTable key (device ID) * \param[in] value GHashTable value (device properties) * \param[in,out] user_data Timeout data */ static void add_device_timeout(gpointer key, gpointer value, gpointer user_data) { const char *device_id = key; device_properties_t *props = value; struct timeout_data *timeout = user_data; if (!props->executed[timeout->op->phase] && !props->disallowed[timeout->op->phase]) { timeout->total_timeout += get_device_timeout(timeout->op, timeout->peer, device_id); } } static int get_peer_timeout(const remote_fencing_op_t *op, const peer_device_info_t *peer) { struct timeout_data timeout; timeout.op = op; timeout.peer = peer; timeout.total_timeout = 0; g_hash_table_foreach(peer->devices, add_device_timeout, &timeout); return (timeout.total_timeout? timeout.total_timeout : op->base_timeout); } static int get_op_total_timeout(const remote_fencing_op_t *op, const peer_device_info_t *chosen_peer) { int total_timeout = 0; stonith_topology_t *tp = find_topology_for_host(op->target); if (pcmk_is_set(op->call_options, st_opt_topology) && tp) { int i; GList *device_list = NULL; GList *iter = NULL; GList *auto_list = NULL; if (pcmk__str_eq(op->action, "on", pcmk__str_casei) && op->automatic_list) { auto_list = g_list_copy(op->automatic_list); } /* Yep, this looks scary, nested loops all over the place. * Here is what is going on. * Loop1: Iterate through fencing levels. * Loop2: If a fencing level has devices, loop through each device * Loop3: For each device in a fencing level, see what peer owns it * and what that peer has reported the timeout is for the device. */ for (i = 0; i < ST_LEVEL_MAX; i++) { if (!tp->levels[i]) { continue; } for (device_list = tp->levels[i]; device_list; device_list = device_list->next) { for (iter = op->query_results; iter != NULL; iter = iter->next) { const peer_device_info_t *peer = iter->data; if (auto_list) { GList *match = g_list_find_custom(auto_list, device_list->data, sort_strings); if (match) { auto_list = g_list_remove(auto_list, match->data); } } if (find_peer_device(op, peer, device_list->data, pcmk__str_eq(op->action, "on", pcmk__str_casei)? st_device_supports_on: st_device_supports_none)) { total_timeout += get_device_timeout(op, peer, device_list->data); break; } } /* End Loop3: match device with peer that owns device, find device's timeout period */ } /* End Loop2: iterate through devices at a specific level */ } /*End Loop1: iterate through fencing levels */ //Add only exists automatic_list device timeout if (auto_list) { for (iter = auto_list; iter != NULL; iter = iter->next) { GList *iter2 = NULL; for (iter2 = op->query_results; iter2 != NULL; iter = iter2->next) { peer_device_info_t *peer = iter2->data; if (find_peer_device(op, peer, iter->data, st_device_supports_on)) { total_timeout += get_device_timeout(op, peer, iter->data); break; } } } } g_list_free(auto_list); } else if (chosen_peer) { total_timeout = get_peer_timeout(op, chosen_peer); } else { total_timeout = op->base_timeout; } return total_timeout ? total_timeout : op->base_timeout; } static void report_timeout_period(remote_fencing_op_t * op, int op_timeout) { GList *iter = NULL; xmlNode *update = NULL; const char *client_node = NULL; const char *client_id = NULL; const char *call_id = NULL; if (op->call_options & st_opt_sync_call) { /* There is no reason to report the timeout for a synchronous call. It * is impossible to use the reported timeout to do anything when the client * is blocking for the response. This update is only important for * async calls that require a callback to report the results in. */ return; } else if (!op->request) { return; } crm_trace("Reporting timeout for %s (id=%.8s)", op->client_name, op->id); client_node = crm_element_value(op->request, F_STONITH_CLIENTNODE); call_id = crm_element_value(op->request, F_STONITH_CALLID); client_id = crm_element_value(op->request, F_STONITH_CLIENTID); if (!client_node || !call_id || !client_id) { return; } if (pcmk__str_eq(client_node, stonith_our_uname, pcmk__str_casei)) { // Client is connected to this node, so send update directly to them do_stonith_async_timeout_update(client_id, call_id, op_timeout); return; } /* The client is connected to another node, relay this update to them */ update = stonith_create_op(op->client_callid, op->id, STONITH_OP_TIMEOUT_UPDATE, NULL, 0); crm_xml_add(update, F_STONITH_REMOTE_OP_ID, op->id); crm_xml_add(update, F_STONITH_CLIENTID, client_id); crm_xml_add(update, F_STONITH_CALLID, call_id); crm_xml_add_int(update, F_STONITH_TIMEOUT, op_timeout); send_cluster_message(crm_get_peer(0, client_node), crm_msg_stonith_ng, update, FALSE); free_xml(update); for (iter = op->duplicates; iter != NULL; iter = iter->next) { remote_fencing_op_t *dup = iter->data; crm_trace("Reporting timeout for duplicate %.8s to client %s", dup->id, dup->client_name); report_timeout_period(iter->data, op_timeout); } } /*! * \internal * \brief Advance an operation to the next device in its topology * * \param[in,out] op Fencer operation to advance * \param[in] device ID of device that just completed * \param[in,out] msg If not NULL, XML reply of last delegated operation */ static void advance_topology_device_in_level(remote_fencing_op_t *op, const char *device, xmlNode *msg) { /* Advance to the next device at this topology level, if any */ if (op->devices) { op->devices = op->devices->next; } /* Handle automatic unfencing if an "on" action was requested */ if ((op->phase == st_phase_requested) && pcmk__str_eq(op->action, "on", pcmk__str_casei)) { /* If the device we just executed was required, it's not anymore */ remove_required_device(op, device); /* If there are no more devices at this topology level, run through any * remaining devices with automatic unfencing */ if (op->devices == NULL) { op->devices = op->automatic_list; } } if ((op->devices == NULL) && (op->phase == st_phase_off)) { /* We're done with this level and with required devices, but we had * remapped "reboot" to "off", so start over with "on". If any devices * need to be turned back on, op->devices will be non-NULL after this. */ op_phase_on(op); } // This function is only called if the previous device succeeded pcmk__set_result(&op->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); if (op->devices) { /* Necessary devices remain, so execute the next one */ crm_trace("Next targeting %s on behalf of %s@%s", op->target, op->client_name, op->originator); // The requested delay has been applied for the first device if (op->delay > 0) { op->delay = 0; } request_peer_fencing(op, NULL); } else { /* We're done with all devices and phases, so finalize operation */ crm_trace("Marking complex fencing op targeting %s as complete", op->target); op->state = st_done; finalize_op(op, msg, false); } } static gboolean check_watchdog_fencing_and_wait(remote_fencing_op_t * op) { if (node_does_watchdog_fencing(op->target)) { crm_notice("Waiting %lds for %s to self-fence (%s) for " "client %s " CRM_XS " id=%.8s", (stonith_watchdog_timeout_ms / 1000), op->target, op->action, op->client_name, op->id); op->op_timer_one = g_timeout_add(stonith_watchdog_timeout_ms, remote_op_watchdog_done, op); return TRUE; } else { crm_debug("Skipping fallback to watchdog-fencing as %s is " "not in host-list", op->target); } return FALSE; } /*! * \internal * \brief Ask a peer to execute a fencing operation * * \param[in,out] op Fencing operation to be executed * \param[in,out] peer If NULL or topology is in use, choose best peer to * execute the fencing, otherwise use this peer */ static void request_peer_fencing(remote_fencing_op_t *op, peer_device_info_t *peer) { const char *device = NULL; int timeout; CRM_CHECK(op != NULL, return); crm_trace("Action %.8s targeting %s for %s is %s", op->id, op->target, op->client_name, stonith_op_state_str(op->state)); + + if ((op->phase == st_phase_on) && (op->devices != NULL)) { + /* We are in the "on" phase of a remapped topology reboot. If this + * device has pcmk_reboot_action="off", or doesn't support the "on" + * action, skip it. + * + * We can't check device properties at this point because we haven't + * chosen a peer for this stage yet. Instead, we check the local node's + * knowledge about the device. If different versions of the fence agent + * are installed on different nodes, there's a chance this could be + * mistaken, but the worst that could happen is we don't try turning the + * node back on when we should. + */ + device = op->devices->data; + if (pcmk__str_eq(fenced_device_reboot_action(device), "off", + pcmk__str_none)) { + crm_info("Not turning %s back on using %s because the device is " + "configured to stay off (pcmk_reboot_action='off')", + op->target, device); + advance_topology_device_in_level(op, device, NULL); + return; + } + if (!fenced_device_supports_on(device)) { + crm_info("Not turning %s back on using %s because the agent " + "doesn't support 'on'", op->target, device); + advance_topology_device_in_level(op, device, NULL); + return; + } + } + timeout = op->base_timeout; if ((peer == NULL) && !pcmk_is_set(op->call_options, st_opt_topology)) { peer = stonith_choose_peer(op); } if (!op->op_timer_total) { op->total_timeout = TIMEOUT_MULTIPLY_FACTOR * get_op_total_timeout(op, peer); op->op_timer_total = g_timeout_add(1000 * op->total_timeout, remote_op_timeout, op); report_timeout_period(op, op->total_timeout); crm_info("Total timeout set to %d for peer's fencing targeting %s for %s" CRM_XS "id=%.8s", op->total_timeout, op->target, op->client_name, op->id); } if (pcmk_is_set(op->call_options, st_opt_topology) && op->devices) { /* Ignore the caller's peer preference if topology is in use, because * that peer might not have access to the required device. With * topology, stonith_choose_peer() removes the device from further * consideration, so the timeout must be calculated beforehand. * * @TODO Basing the total timeout on the caller's preferred peer (above) * is less than ideal. */ peer = stonith_choose_peer(op); device = op->devices->data; timeout = get_device_timeout(op, peer, device); } if (peer) { int timeout_one = 0; xmlNode *remote_op = stonith_create_op(op->client_callid, op->id, STONITH_OP_FENCE, NULL, 0); crm_xml_add(remote_op, F_STONITH_REMOTE_OP_ID, op->id); crm_xml_add(remote_op, F_STONITH_TARGET, op->target); crm_xml_add(remote_op, F_STONITH_ACTION, op->action); crm_xml_add(remote_op, F_STONITH_ORIGIN, op->originator); crm_xml_add(remote_op, F_STONITH_CLIENTID, op->client_id); crm_xml_add(remote_op, F_STONITH_CLIENTNAME, op->client_name); crm_xml_add_int(remote_op, F_STONITH_TIMEOUT, timeout); crm_xml_add_int(remote_op, F_STONITH_CALLOPTS, op->call_options); crm_xml_add_int(remote_op, F_STONITH_DELAY, op->delay); if (device) { timeout_one = TIMEOUT_MULTIPLY_FACTOR * get_device_timeout(op, peer, device); crm_notice("Requesting that %s perform '%s' action targeting %s " "using %s " CRM_XS " for client %s (%ds)", peer->host, op->action, op->target, device, op->client_name, timeout_one); crm_xml_add(remote_op, F_STONITH_DEVICE, device); } else { timeout_one = TIMEOUT_MULTIPLY_FACTOR * get_peer_timeout(op, peer); crm_notice("Requesting that %s perform '%s' action targeting %s " CRM_XS " for client %s (%ds, %lds)", peer->host, op->action, op->target, op->client_name, timeout_one, stonith_watchdog_timeout_ms); } op->state = st_exec; if (op->op_timer_one) { g_source_remove(op->op_timer_one); } if (!(stonith_watchdog_timeout_ms > 0 && ( (pcmk__str_eq(device, STONITH_WATCHDOG_ID, pcmk__str_none)) || (pcmk__str_eq(peer->host, op->target, pcmk__str_casei) && !pcmk__str_eq(op->action, "on", pcmk__str_casei))) && check_watchdog_fencing_and_wait(op))) { /* Some thoughts about self-fencing cases reaching this point: - Actually check in check_watchdog_fencing_and_wait shouldn't fail if STONITH_WATCHDOG_ID is chosen as fencing-device and it being present implies watchdog-fencing is enabled anyway - If watchdog-fencing is disabled either in general or for a specific target - detected in check_watchdog_fencing_and_wait - for some other kind of self-fencing we can't expect a success answer but timeout is fine if the node doesn't come back in between - Delicate might be the case where we have watchdog-fencing enabled for a node but the watchdog-fencing-device isn't explicitly chosen for suicide. Local pe-execution in sbd may detect the node as unclean and lead to timely suicide. Otherwise the selection of stonith-watchdog-timeout at least is questionable. */ op->op_timer_one = g_timeout_add((1000 * timeout_one), remote_op_timeout_one, op); } send_cluster_message(crm_get_peer(0, peer->host), crm_msg_stonith_ng, remote_op, FALSE); peer->tried = TRUE; free_xml(remote_op); return; } else if (op->phase == st_phase_on) { /* A remapped "on" cannot be executed, but the node was already * turned off successfully, so ignore the error and continue. */ crm_warn("Ignoring %s 'on' failure (no capable peers) targeting %s " "after successful 'off'", device, op->target); advance_topology_device_in_level(op, device, NULL); return; } else if (op->owner == FALSE) { crm_err("Fencing (%s) targeting %s for client %s is not ours to control", op->action, op->target, op->client_name); } else if (op->query_timer == 0) { /* We've exhausted all available peers */ crm_info("No remaining peers capable of fencing (%s) %s for client %s " CRM_XS " state=%s", op->action, op->target, op->client_name, stonith_op_state_str(op->state)); CRM_CHECK(op->state < st_done, return); finalize_timed_out_op(op, "All nodes failed, or are unable, to " "fence target"); } else if(op->replies >= op->replies_expected || op->replies >= fencing_active_peers()) { /* if the operation never left the query state, * but we have all the expected replies, then no devices * are available to execute the fencing operation. */ if(stonith_watchdog_timeout_ms > 0 && pcmk__str_eq(device, STONITH_WATCHDOG_ID, pcmk__str_null_matches)) { if (check_watchdog_fencing_and_wait(op)) { return; } } if (op->state == st_query) { crm_info("No peers (out of %d) have devices capable of fencing " "(%s) %s for client %s " CRM_XS " state=%s", op->replies, op->action, op->target, op->client_name, stonith_op_state_str(op->state)); pcmk__reset_result(&op->result); pcmk__set_result(&op->result, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE, NULL); } else { if (pcmk_is_set(op->call_options, st_opt_topology)) { pcmk__reset_result(&op->result); pcmk__set_result(&op->result, CRM_EX_ERROR, PCMK_EXEC_NO_FENCE_DEVICE, NULL); } /* ... else use existing result from previous failed attempt * (topology is not in use, and no devices remain to be attempted). * Overwriting the result with PCMK_EXEC_NO_FENCE_DEVICE would * prevent finalize_op() from setting the correct delegate if * needed. */ crm_info("No peers (out of %d) are capable of fencing (%s) %s " "for client %s " CRM_XS " state=%s", op->replies, op->action, op->target, op->client_name, stonith_op_state_str(op->state)); } op->state = st_failed; finalize_op(op, NULL, false); } else { crm_info("Waiting for additional peers capable of fencing (%s) %s%s%s " "for client %s " CRM_XS " id=%.8s", op->action, op->target, (device? " using " : ""), (device? device : ""), op->client_name, op->id); } } /*! * \internal * \brief Comparison function for sorting query results * * \param[in] a GList item to compare * \param[in] b GList item to compare * * \return Per the glib documentation, "a negative integer if the first value * comes before the second, 0 if they are equal, or a positive integer * if the first value comes after the second." */ static gint sort_peers(gconstpointer a, gconstpointer b) { const peer_device_info_t *peer_a = a; const peer_device_info_t *peer_b = b; return (peer_b->ndevices - peer_a->ndevices); } /*! * \internal * \brief Determine if all the devices in the topology are found or not * * \param[in] op Fencing operation with topology to check */ static gboolean all_topology_devices_found(const remote_fencing_op_t *op) { GList *device = NULL; GList *iter = NULL; device_properties_t *match = NULL; stonith_topology_t *tp = NULL; gboolean skip_target = FALSE; int i; tp = find_topology_for_host(op->target); if (!tp) { return FALSE; } if (pcmk__is_fencing_action(op->action)) { /* Don't count the devices on the target node if we are killing * the target node. */ skip_target = TRUE; } for (i = 0; i < ST_LEVEL_MAX; i++) { for (device = tp->levels[i]; device; device = device->next) { match = NULL; for (iter = op->query_results; iter && !match; iter = iter->next) { peer_device_info_t *peer = iter->data; if (skip_target && pcmk__str_eq(peer->host, op->target, pcmk__str_casei)) { continue; } match = find_peer_device(op, peer, device->data, st_device_supports_none); } if (!match) { return FALSE; } } } return TRUE; } /*! * \internal * \brief Parse action-specific device properties from XML * * \param[in] xml XML element containing the properties * \param[in] peer Name of peer that sent XML (for logs) * \param[in] device Device ID (for logs) * \param[in] action Action the properties relate to (for logs) * \param[in,out] op Fencing operation that properties are being parsed for * \param[in] phase Phase the properties relate to * \param[in,out] props Device properties to update */ static void parse_action_specific(const xmlNode *xml, const char *peer, const char *device, const char *action, remote_fencing_op_t *op, enum st_remap_phase phase, device_properties_t *props) { props->custom_action_timeout[phase] = 0; crm_element_value_int(xml, F_STONITH_ACTION_TIMEOUT, &props->custom_action_timeout[phase]); if (props->custom_action_timeout[phase]) { crm_trace("Peer %s with device %s returned %s action timeout %d", peer, device, action, props->custom_action_timeout[phase]); } props->delay_max[phase] = 0; crm_element_value_int(xml, F_STONITH_DELAY_MAX, &props->delay_max[phase]); if (props->delay_max[phase]) { crm_trace("Peer %s with device %s returned maximum of random delay %d for %s", peer, device, props->delay_max[phase], action); } props->delay_base[phase] = 0; crm_element_value_int(xml, F_STONITH_DELAY_BASE, &props->delay_base[phase]); if (props->delay_base[phase]) { crm_trace("Peer %s with device %s returned base delay %d for %s", peer, device, props->delay_base[phase], action); } /* Handle devices with automatic unfencing */ if (pcmk__str_eq(action, "on", pcmk__str_casei)) { int required = 0; crm_element_value_int(xml, F_STONITH_DEVICE_REQUIRED, &required); if (required) { crm_trace("Peer %s requires device %s to execute for action %s", peer, device, action); add_required_device(op, device); } } /* If a reboot is remapped to off+on, it's possible that a node is allowed * to perform one action but not another. */ if (pcmk__xe_attr_is_true(xml, F_STONITH_ACTION_DISALLOWED)) { props->disallowed[phase] = TRUE; crm_trace("Peer %s is disallowed from executing %s for device %s", peer, action, device); } } /*! * \internal * \brief Parse one device's properties from peer's XML query reply * * \param[in] xml XML node containing device properties * \param[in,out] op Operation that query and reply relate to * \param[in,out] peer Peer's device information * \param[in] device ID of device being parsed */ static void add_device_properties(const xmlNode *xml, remote_fencing_op_t *op, peer_device_info_t *peer, const char *device) { xmlNode *child; int verified = 0; device_properties_t *props = calloc(1, sizeof(device_properties_t)); int flags = st_device_supports_on; /* Old nodes that don't set the flag assume they support the on action */ /* Add a new entry to this peer's devices list */ CRM_ASSERT(props != NULL); g_hash_table_insert(peer->devices, strdup(device), props); /* Peers with verified (monitored) access will be preferred */ crm_element_value_int(xml, F_STONITH_DEVICE_VERIFIED, &verified); if (verified) { crm_trace("Peer %s has confirmed a verified device %s", peer->host, device); props->verified = TRUE; } crm_element_value_int(xml, F_STONITH_DEVICE_SUPPORT_FLAGS, &flags); props->device_support_flags = flags; /* Parse action-specific device properties */ parse_action_specific(xml, peer->host, device, op_requested_action(op), op, st_phase_requested, props); for (child = pcmk__xml_first_child(xml); child != NULL; child = pcmk__xml_next(child)) { /* Replies for "reboot" operations will include the action-specific * values for "off" and "on" in child elements, just in case the reboot * winds up getting remapped. */ if (pcmk__str_eq(ID(child), "off", pcmk__str_casei)) { parse_action_specific(child, peer->host, device, "off", op, st_phase_off, props); } else if (pcmk__str_eq(ID(child), "on", pcmk__str_casei)) { parse_action_specific(child, peer->host, device, "on", op, st_phase_on, props); } } } /*! * \internal * \brief Parse a peer's XML query reply and add it to operation's results * * \param[in,out] op Operation that query and reply relate to * \param[in] host Name of peer that sent this reply * \param[in] ndevices Number of devices expected in reply * \param[in] xml XML node containing device list * * \return Newly allocated result structure with parsed reply */ static peer_device_info_t * add_result(remote_fencing_op_t *op, const char *host, int ndevices, const xmlNode *xml) { peer_device_info_t *peer = calloc(1, sizeof(peer_device_info_t)); xmlNode *child; // cppcheck seems not to understand the abort logic in CRM_CHECK // cppcheck-suppress memleak CRM_CHECK(peer != NULL, return NULL); peer->host = strdup(host); peer->devices = pcmk__strkey_table(free, free); /* Each child element describes one capable device available to the peer */ for (child = pcmk__xml_first_child(xml); child != NULL; child = pcmk__xml_next(child)) { const char *device = ID(child); if (device) { add_device_properties(child, op, peer, device); } } peer->ndevices = g_hash_table_size(peer->devices); CRM_CHECK(ndevices == peer->ndevices, crm_err("Query claimed to have %d device%s but %d found", ndevices, pcmk__plural_s(ndevices), peer->ndevices)); op->query_results = g_list_insert_sorted(op->query_results, peer, sort_peers); return peer; } /*! * \internal * \brief Handle a peer's reply to our fencing query * * Parse a query result from XML and store it in the remote operation * table, and when enough replies have been received, issue a fencing request. * * \param[in] msg XML reply received * * \return pcmk_ok on success, -errno on error * * \note See initiate_remote_stonith_op() for how the XML query was initially * formed, and stonith_query() for how the peer formed its XML reply. */ int process_remote_stonith_query(xmlNode *msg) { int ndevices = 0; gboolean host_is_target = FALSE; gboolean have_all_replies = FALSE; const char *id = NULL; const char *host = NULL; remote_fencing_op_t *op = NULL; peer_device_info_t *peer = NULL; uint32_t replies_expected; xmlNode *dev = get_xpath_object("//@" F_STONITH_REMOTE_OP_ID, msg, LOG_ERR); CRM_CHECK(dev != NULL, return -EPROTO); id = crm_element_value(dev, F_STONITH_REMOTE_OP_ID); CRM_CHECK(id != NULL, return -EPROTO); dev = get_xpath_object("//@" F_STONITH_AVAILABLE_DEVICES, msg, LOG_ERR); CRM_CHECK(dev != NULL, return -EPROTO); crm_element_value_int(dev, F_STONITH_AVAILABLE_DEVICES, &ndevices); op = g_hash_table_lookup(stonith_remote_op_list, id); if (op == NULL) { crm_debug("Received query reply for unknown or expired operation %s", id); return -EOPNOTSUPP; } replies_expected = fencing_active_peers(); if (op->replies_expected < replies_expected) { replies_expected = op->replies_expected; } if ((++op->replies >= replies_expected) && (op->state == st_query)) { have_all_replies = TRUE; } host = crm_element_value(msg, F_ORIG); host_is_target = pcmk__str_eq(host, op->target, pcmk__str_casei); crm_info("Query result %d of %d from %s for %s/%s (%d device%s) %s", op->replies, replies_expected, host, op->target, op->action, ndevices, pcmk__plural_s(ndevices), id); if (ndevices > 0) { peer = add_result(op, host, ndevices, dev); } pcmk__set_result(&op->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); if (pcmk_is_set(op->call_options, st_opt_topology)) { /* If we start the fencing before all the topology results are in, * it is possible fencing levels will be skipped because of the missing * query results. */ if (op->state == st_query && all_topology_devices_found(op)) { /* All the query results are in for the topology, start the fencing ops. */ crm_trace("All topology devices found"); request_peer_fencing(op, peer); } else if (have_all_replies) { crm_info("All topology query replies have arrived, continuing (%d expected/%d received) ", replies_expected, op->replies); request_peer_fencing(op, NULL); } } else if (op->state == st_query) { int nverified = count_peer_devices(op, peer, TRUE, pcmk__str_eq(op->action, "on", pcmk__str_casei)? st_device_supports_on : st_device_supports_none); /* We have a result for a non-topology fencing op that looks promising, * go ahead and start fencing before query timeout */ if ((peer != NULL) && !host_is_target && nverified) { /* we have a verified device living on a peer that is not the target */ crm_trace("Found %d verified device%s", nverified, pcmk__plural_s(nverified)); request_peer_fencing(op, peer); } else if (have_all_replies) { crm_info("All query replies have arrived, continuing (%d expected/%d received) ", replies_expected, op->replies); request_peer_fencing(op, NULL); } else { crm_trace("Waiting for more peer results before launching fencing operation"); } } else if ((peer != NULL) && (op->state == st_done)) { crm_info("Discarding query result from %s (%d device%s): " "Operation is %s", peer->host, peer->ndevices, pcmk__plural_s(peer->ndevices), stonith_op_state_str(op->state)); } return pcmk_ok; } /*! * \internal * \brief Handle a peer's reply to a fencing request * * Parse a fencing reply from XML, and either finalize the operation * or attempt another device as appropriate. * * \param[in] msg XML reply received */ void fenced_process_fencing_reply(xmlNode *msg) { const char *id = NULL; const char *device = NULL; remote_fencing_op_t *op = NULL; xmlNode *dev = get_xpath_object("//@" F_STONITH_REMOTE_OP_ID, msg, LOG_ERR); pcmk__action_result_t result = PCMK__UNKNOWN_RESULT; CRM_CHECK(dev != NULL, return); id = crm_element_value(dev, F_STONITH_REMOTE_OP_ID); CRM_CHECK(id != NULL, return); dev = stonith__find_xe_with_result(msg); CRM_CHECK(dev != NULL, return); stonith__xe_get_result(dev, &result); device = crm_element_value(dev, F_STONITH_DEVICE); if (stonith_remote_op_list) { op = g_hash_table_lookup(stonith_remote_op_list, id); } if ((op == NULL) && pcmk__result_ok(&result)) { /* Record successful fencing operations */ const char *client_id = crm_element_value(dev, F_STONITH_CLIENTID); op = create_remote_stonith_op(client_id, dev, TRUE); } if (op == NULL) { /* Could be for an event that began before we started */ /* TODO: Record the op for later querying */ crm_info("Received peer result of unknown or expired operation %s", id); pcmk__reset_result(&result); return; } pcmk__reset_result(&op->result); op->result = result; // The operation takes ownership of the result if (op->devices && device && !pcmk__str_eq(op->devices->data, device, pcmk__str_casei)) { crm_err("Received outdated reply for device %s (instead of %s) to " "fence (%s) %s. Operation already timed out at peer level.", device, (const char *) op->devices->data, op->action, op->target); return; } if (pcmk__str_eq(crm_element_value(msg, F_SUBTYPE), "broadcast", pcmk__str_casei)) { if (pcmk__result_ok(&op->result)) { op->state = st_done; } else { op->state = st_failed; } finalize_op(op, msg, false); return; } else if (!pcmk__str_eq(op->originator, stonith_our_uname, pcmk__str_casei)) { /* If this isn't a remote level broadcast, and we are not the * originator of the operation, we should not be receiving this msg. */ crm_err("Received non-broadcast fencing result for operation %.8s " "we do not own (device %s targeting %s)", op->id, device, op->target); return; } if (pcmk_is_set(op->call_options, st_opt_topology)) { const char *device = NULL; const char *reason = op->result.exit_reason; /* We own the op, and it is complete. broadcast the result to all nodes * and notify our local clients. */ if (op->state == st_done) { finalize_op(op, msg, false); return; } device = crm_element_value(msg, F_STONITH_DEVICE); if ((op->phase == 2) && !pcmk__result_ok(&op->result)) { /* A remapped "on" failed, but the node was already turned off * successfully, so ignore the error and continue. */ crm_warn("Ignoring %s 'on' failure (%s%s%s) targeting %s " "after successful 'off'", device, pcmk_exec_status_str(op->result.execution_status), (reason == NULL)? "" : ": ", (reason == NULL)? "" : reason, op->target); pcmk__set_result(&op->result, CRM_EX_OK, PCMK_EXEC_DONE, NULL); } else { crm_notice("Action '%s' targeting %s%s%s on behalf of %s@%s: " "%s%s%s%s", op->action, op->target, ((device == NULL)? "" : " using "), ((device == NULL)? "" : device), op->client_name, op->originator, pcmk_exec_status_str(op->result.execution_status), (reason == NULL)? "" : " (", (reason == NULL)? "" : reason, (reason == NULL)? "" : ")"); } if (pcmk__result_ok(&op->result)) { /* An operation completed successfully. Try another device if * necessary, otherwise mark the operation as done. */ advance_topology_device_in_level(op, device, msg); return; } else { /* This device failed, time to try another topology level. If no other * levels are available, mark this operation as failed and report results. */ if (advance_topology_level(op, false) != pcmk_rc_ok) { op->state = st_failed; finalize_op(op, msg, false); return; } } } else if (pcmk__result_ok(&op->result) && (op->devices == NULL)) { op->state = st_done; finalize_op(op, msg, false); return; } else if ((op->result.execution_status == PCMK_EXEC_TIMEOUT) && (op->devices == NULL)) { /* If the operation timed out don't bother retrying other peers. */ op->state = st_failed; finalize_op(op, msg, false); return; } else { /* fall-through and attempt other fencing action using another peer */ } /* Retry on failure */ crm_trace("Next for %s on behalf of %s@%s (result was: %s)", op->target, op->originator, op->client_name, pcmk_exec_status_str(op->result.execution_status)); request_peer_fencing(op, NULL); } gboolean stonith_check_fence_tolerance(int tolerance, const char *target, const char *action) { GHashTableIter iter; time_t now = time(NULL); remote_fencing_op_t *rop = NULL; if (tolerance <= 0 || !stonith_remote_op_list || target == NULL || action == NULL) { return FALSE; } g_hash_table_iter_init(&iter, stonith_remote_op_list); while (g_hash_table_iter_next(&iter, NULL, (void **)&rop)) { if (strcmp(rop->target, target) != 0) { continue; } else if (rop->state != st_done) { continue; /* We don't have to worry about remapped reboots here * because if state is done, any remapping has been undone */ } else if (strcmp(rop->action, action) != 0) { continue; } else if ((rop->completed + tolerance) < now) { continue; } crm_notice("Target %s was fenced (%s) less than %ds ago by %s on behalf of %s", target, action, tolerance, rop->delegate, rop->originator); return TRUE; } return FALSE; } diff --git a/daemons/fenced/pacemaker-fenced.h b/daemons/fenced/pacemaker-fenced.h index 268184e095..0eeaecb798 100644 --- a/daemons/fenced/pacemaker-fenced.h +++ b/daemons/fenced/pacemaker-fenced.h @@ -1,294 +1,297 @@ /* * Copyright 2009-2022 the Pacemaker project contributors * * This source code is licensed under the GNU General Public License version 2 * or later (GPLv2+) WITHOUT ANY WARRANTY. */ #include // uint32_t, uint64_t #include /*! * \internal * \brief Check whether target has already been fenced recently * * \param[in] tolerance Number of seconds to look back in time * \param[in] target Name of node to search for * \param[in] action Action we want to match * * \return TRUE if an equivalent fencing operation took place in the last * \p tolerance seconds, FALSE otherwise */ gboolean stonith_check_fence_tolerance(int tolerance, const char *target, const char *action); typedef struct stonith_device_s { char *id; char *agent; char *namespace; /*! list of actions that must execute on the target node. Used for unfencing */ GString *on_target_actions; GList *targets; time_t targets_age; gboolean has_attr_map; // Whether target's nodeid should be passed as a parameter to the agent gboolean include_nodeid; /* whether the cluster should automatically unfence nodes with the device */ gboolean automatic_unfencing; guint priority; uint32_t flags; // Group of enum st_device_flags GHashTable *params; GHashTable *aliases; GList *pending_ops; mainloop_timer_t *timer; crm_trigger_t *work; xmlNode *agent_metadata; /*! A verified device is one that has contacted the * agent successfully to perform a monitor operation */ gboolean verified; gboolean cib_registered; gboolean api_registered; gboolean dirty; } stonith_device_t; /* These values are used to index certain arrays by "phase". Usually an * operation has only one "phase", so phase is always zero. However, some * reboots are remapped to "off" then "on", in which case "reboot" will be * phase 0, "off" will be phase 1 and "on" will be phase 2. */ enum st_remap_phase { st_phase_requested = 0, st_phase_off = 1, st_phase_on = 2, st_phase_max = 3 }; typedef struct remote_fencing_op_s { /* The unique id associated with this operation */ char *id; /*! The node this operation will fence */ char *target; /*! The fencing action to perform on the target. (reboot, on, off) */ char *action; /*! When was the fencing action recorded (seconds since epoch) */ time_t created; /*! Marks if the final notifications have been sent to local stonith clients. */ gboolean notify_sent; /*! The number of query replies received */ guint replies; /*! The number of query replies expected */ guint replies_expected; /*! Does this node own control of this operation */ gboolean owner; /*! After query is complete, This the high level timer that expires the entire operation */ guint op_timer_total; /*! This timer expires the current fencing request. Many fencing * requests may exist in a single operation */ guint op_timer_one; /*! This timer expires the query request sent out to determine * what nodes are contain what devices, and who those devices can fence */ guint query_timer; /*! This is the default timeout to use for each fencing device if no * custom timeout is received in the query. */ gint base_timeout; /*! This is the calculated total timeout an operation can take before * expiring. This is calculated by adding together all the timeout * values associated with the devices this fencing operation may call */ gint total_timeout; /*! Requested fencing delay. * Value -1 means disable any static/random fencing delays. */ int delay; /*! Delegate is the node being asked to perform a fencing action * on behalf of the node that owns the remote operation. Some operations * will involve multiple delegates. This value represents the final delegate * that is used. */ char *delegate; /*! The point at which the remote operation completed */ time_t completed; //! Group of enum stonith_call_options associated with this operation uint32_t call_options; /*! The current state of the remote operation. This indicates * what stage the op is in, query, exec, done, duplicate, failed. */ enum op_state state; /*! The node that owns the remote operation */ char *originator; /*! The local client id that initiated the fencing request */ char *client_id; /*! The client's call_id that initiated the fencing request */ int client_callid; /*! The name of client that initiated the fencing request */ char *client_name; /*! List of the received query results for all the nodes in the cpg group */ GList *query_results; /*! The original request that initiated the remote stonith operation */ xmlNode *request; /*! The current topology level being executed */ guint level; /*! The current operation phase being executed */ enum st_remap_phase phase; /*! Devices with automatic unfencing (always run if "on" requested, never if remapped) */ GList *automatic_list; /*! List of all devices at the currently executing topology level */ GList *devices_list; /*! Current entry in the topology device list */ GList *devices; /*! List of duplicate operations attached to this operation. Once this operation * completes, the duplicate operations will be closed out as well. */ GList *duplicates; /*! The point at which the remote operation completed(nsec) */ long long completed_nsec; /*! The (potentially intermediate) result of the operation */ pcmk__action_result_t result; } remote_fencing_op_t; void fenced_broadcast_op_result(const remote_fencing_op_t *op, bool op_merged); // Fencer-specific client flags enum st_client_flags { st_callback_unknown = UINT64_C(0), st_callback_notify_fence = (UINT64_C(1) << 0), st_callback_device_add = (UINT64_C(1) << 2), st_callback_device_del = (UINT64_C(1) << 4), st_callback_notify_history = (UINT64_C(1) << 5), st_callback_notify_history_synced = (UINT64_C(1) << 6) }; // How the user specified the target of a topology level enum fenced_target_by { fenced_target_by_unknown = -1, // Invalid or not yet parsed fenced_target_by_name, // By target name fenced_target_by_pattern, // By a pattern matching target names fenced_target_by_attribute, // By a node attribute/value on target }; /* * Complex fencing requirements are specified via fencing topologies. * A topology consists of levels; each level is a list of fencing devices. * Topologies are stored in a hash table by node name. When a node needs to be * fenced, if it has an entry in the topology table, the levels are tried * sequentially, and the devices in each level are tried sequentially. * Fencing is considered successful as soon as any level succeeds; * a level is considered successful if all its devices succeed. * Essentially, all devices at a given level are "and-ed" and the * levels are "or-ed". * * This structure is used for the topology table entries. * Topology levels start from 1, so levels[0] is unused and always NULL. */ typedef struct stonith_topology_s { enum fenced_target_by kind; // How target was specified /*! Node name regex or attribute name=value for which topology applies */ char *target; char *target_value; char *target_pattern; char *target_attribute; /*! Names of fencing devices at each topology level */ GList *levels[ST_LEVEL_MAX]; } stonith_topology_t; void init_device_list(void); void free_device_list(void); void init_topology_list(void); void free_topology_list(void); void free_stonith_remote_op_list(void); void init_stonith_remote_op_hash_table(GHashTable **table); void free_metadata_cache(void); void fenced_unregister_handlers(void); uint64_t get_stonith_flag(const char *name); void stonith_command(pcmk__client_t *client, uint32_t id, uint32_t flags, xmlNode *op_request, const char *remote_peer); int stonith_device_register(xmlNode *msg, gboolean from_cib); void stonith_device_remove(const char *id, bool from_cib); char *stonith_level_key(const xmlNode *msg, int mode); void fenced_register_level(xmlNode *msg, char **desc, pcmk__action_result_t *result); void fenced_unregister_level(xmlNode *msg, char **desc, pcmk__action_result_t *result); stonith_topology_t *find_topology_for_host(const char *host); void do_local_reply(xmlNode *notify_src, pcmk__client_t *client, int call_options); xmlNode *fenced_construct_reply(const xmlNode *request, xmlNode *data, const pcmk__action_result_t *result); void do_stonith_async_timeout_update(const char *client, const char *call_id, int timeout); void fenced_send_notification(const char *type, const pcmk__action_result_t *result, xmlNode *data); void fenced_send_device_notification(const char *op, const pcmk__action_result_t *result, const char *desc); void fenced_send_level_notification(const char *op, const pcmk__action_result_t *result, const char *desc); remote_fencing_op_t *initiate_remote_stonith_op(const pcmk__client_t *client, xmlNode *request, gboolean manual_ack); void fenced_process_fencing_reply(xmlNode *msg); int process_remote_stonith_query(xmlNode * msg); void *create_remote_stonith_op(const char *client, xmlNode * request, gboolean peer); void stonith_fence_history(xmlNode *msg, xmlNode **output, const char *remote_peer, int options); void stonith_fence_history_trim(void); bool fencing_peer_active(crm_node_t *peer); void set_fencing_completed(remote_fencing_op_t * op); int fenced_handle_manual_confirmation(const pcmk__client_t *client, xmlNode *msg); void fencer_metadata(void); +const char *fenced_device_reboot_action(const char *device_id); +bool fenced_device_supports_on(const char *device_id); + gboolean node_has_attr(const char *node, const char *name, const char *value); gboolean node_does_watchdog_fencing(const char *node); static inline void fenced_set_protocol_error(pcmk__action_result_t *result) { pcmk__set_result(result, CRM_EX_PROTOCOL, PCMK_EXEC_INVALID, "Fencer API request missing required information (bug?)"); } extern char *stonith_our_uname; extern gboolean stand_alone; extern GHashTable *device_list; extern GHashTable *topology; extern long stonith_watchdog_timeout_ms; extern GList *stonith_watchdog_targets; extern GHashTable *stonith_remote_op_list;