diff --git a/python/pacemaker/_cts/cib.py b/python/pacemaker/_cts/cib.py index fce4298cc7..f272e4707c 100644 --- a/python/pacemaker/_cts/cib.py +++ b/python/pacemaker/_cts/cib.py @@ -1,424 +1,424 @@ """ CIB generator for Pacemaker's Cluster Test Suite (CTS) """ __all__ = ["ConfigFactory"] __copyright__ = "Copyright 2008-2023 the Pacemaker project contributors" __license__ = "GNU General Public License version 2 or later (GPLv2+) WITHOUT ANY WARRANTY" import warnings import tempfile from pacemaker.buildoptions import BuildOptions from pacemaker._cts.cibxml import Alerts, Clone, Expression, FencingTopology, Group, Nodes, OpDefaults, Option, Resource, Rule from pacemaker._cts.network import next_ip class CIB: """ A class for generating, representing, and installing a CIB file onto cluster nodes """ def __init__(self, cm, version, factory, tmpfile=None): """ Create a new CIB instance Arguments: cm -- A ClusterManager instance version -- The schema syntax version factory -- A ConfigFactory instance tmpfile -- Where to store the CIB, or None to use a new tempfile """ # pylint: disable=invalid-name self._cib = None self._cm = cm self._counter = 1 self._factory = factory self._num_nodes = 0 self.version = version if not tmpfile: warnings.filterwarnings("ignore") # pylint: disable=consider-using-with f = tempfile.NamedTemporaryFile(delete=True) f.close() tmpfile = f.name warnings.resetwarnings() self._factory.tmpfile = tmpfile def _show(self): """ Query a cluster node for its generated CIB; log and return the result """ output = "" (_, result) = self._factory.rsh(self._factory.target, "HOME=/root CIB_file=%s cibadmin -Ql" % self._factory.tmpfile, verbose=1) for line in result: output += line self._factory.debug("Generated Config: %s" % line) return output def new_ip(self, name=None): """ Generate an IP resource for the next available IP address, optionally specifying the resource's name. """ if self._cm.Env["IPagent"] == "IPaddr2": ip = next_ip(self._cm.Env["IPBase"]) if not name: if ":" in ip: (_, _, suffix) = ip.rpartition(":") name = "r%s" % suffix else: name = "r%s" % ip r = Resource(self._factory, name, self._cm.Env["IPagent"], "ocf") r["ip"] = ip if ":" in ip: r["cidr_netmask"] = "64" r["nic"] = "eth0" else: r["cidr_netmask"] = "32" else: if not name: name = "r%s%d" % (self._cm.Env["IPagent"], self._counter) self._counter += 1 r = Resource(self._factory, name, self._cm.Env["IPagent"], "ocf") r.add_op("monitor", "5s") return r def get_node_id(self, node_name): """ Check the cluster configuration for the node ID for the given node_name """ # We can't account for every possible configuration, # so we only return a node ID if: # * The node is specified in /etc/corosync/corosync.conf # with "ring0_addr:" equal to node_name and "nodeid:" # explicitly specified. # In all other cases, we return 0. node_id = 0 # awkward command: use } as record separator # so each corosync.conf "object" is one record; # match the "node {" record that has "ring0_addr: node_name"; # then print the substring of that record after "nodeid:" (rc, output) = self._factory.rsh(self._factory.target, r"""awk -v RS="}" """ r"""'/^(\s*nodelist\s*{)?\s*node\s*{.*(ring0_addr|name):\s*%s(\s+|$)/""" r"""{gsub(/.*nodeid:\s*/,"");gsub(/\s+.*$/,"");print}' %s""" % (node_name, BuildOptions.COROSYNC_CONFIG_FILE), verbose=1) if rc == 0 and len(output) == 1: try: node_id = int(output[0]) except ValueError: node_id = 0 return node_id def install(self, target): """ Generate a CIB file and install it to the given cluster node """ old = self._factory.tmpfile # Force a rebuild self._cib = None self._factory.tmpfile = "%s/cib.xml" % BuildOptions.CIB_DIR self.contents(target) self._factory.rsh(self._factory.target, "chown %s %s" % (BuildOptions.DAEMON_USER, self._factory.tmpfile)) self._factory.tmpfile = old def contents(self, target): """ Generate a complete CIB file """ # fencing resource if self._cib: return self._cib if target: self._factory.target = target self._factory.rsh(self._factory.target, "HOME=/root cibadmin --empty %s > %s" % (self.version, self._factory.tmpfile)) self._num_nodes = len(self._cm.Env["nodes"]) no_quorum = "stop" if self._num_nodes < 3: no_quorum = "ignore" self._factory.log("Cluster only has %d nodes, configuring: no-quorum-policy=ignore" % self._num_nodes) # We don't need a nodes section unless we add attributes stn = None # Fencing resource # Define first so that the shell doesn't reject every update if self._cm.Env["DoFencing"]: # Define the "real" fencing device st = Resource(self._factory, "Fencing", self._cm.Env["stonith-type"], "stonith") # Set a threshold for unreliable stonith devices such as the vmware one st.add_meta("migration-threshold", "5") st.add_op("monitor", "120s", timeout="120s") st.add_op("stop", "0", timeout="60s") st.add_op("start", "0", timeout="60s") # For remote node tests, a cluster node is stopped and brought back up # as a remote node with the name "remote-OLDNAME". To allow fencing # devices to fence these nodes, create a list of all possible node names. all_node_names = [ prefix+n for n in self._cm.Env["nodes"] for prefix in ('', 'remote-') ] # Add all parameters specified by user entries = self._cm.Env["stonith-params"].split(',') for entry in entries: try: (name, value) = entry.split('=', 1) except ValueError: print("Warning: skipping invalid fencing parameter: %s" % entry) continue # Allow user to specify "all" as the node list, and expand it here if name in [ "hostlist", "pcmk_host_list" ] and value == "all": value = ' '.join(all_node_names) st[name] = value st.commit() # Test advanced fencing logic stf_nodes = [] stt_nodes = [] attr_nodes = {} # Create the levels stl = FencingTopology(self._factory) for node in self._cm.Env["nodes"]: # Remote node tests will rename the node remote_node = "remote-%s" % node # Randomly assign node to a fencing method ftype = self._cm.Env.random_gen.choice(["levels-and", "levels-or ", "broadcast "]) # For levels-and, randomly choose targeting by node name or attribute by = "" if ftype == "levels-and": node_id = self.get_node_id(node) if node_id == 0 or self._cm.Env.random_gen.choice([True, False]): by = " (by name)" else: attr_nodes[node] = node_id by = " (by attribute)" self._cm.log(" - Using %s fencing for node: %s%s" % (ftype, node, by)) if ftype == "levels-and": # If targeting by name, add a topology level for this node if node not in attr_nodes: stl.level(1, node, "FencingPass,Fencing") # Always target remote nodes by name, otherwise we would need to add # an attribute to the remote node only during remote tests (we don't # want nonexistent remote nodes showing up in the non-remote tests). # That complexity is not worth the effort. stl.level(1, remote_node, "FencingPass,Fencing") # Add the node (and its remote equivalent) to the list of levels-and nodes. stt_nodes.extend([node, remote_node]) elif ftype == "levels-or ": for n in [ node, remote_node ]: stl.level(1, n, "FencingFail") stl.level(2, n, "Fencing") stf_nodes.extend([node, remote_node]) # If any levels-and nodes were targeted by attribute, # create the attributes and a level for the attribute. if attr_nodes: stn = Nodes(self._factory) for (node_name, node_id) in attr_nodes.items(): stn.add_node(node_name, node_id, { "cts-fencing" : "levels-and" }) stl.level(1, None, "FencingPass,Fencing", "cts-fencing", "levels-and") # Create a Dummy agent that always passes for levels-and if stt_nodes: stt = Resource(self._factory, "FencingPass", "fence_dummy", "stonith") stt["pcmk_host_list"] = " ".join(stt_nodes) # Wait this many seconds before doing anything, handy for letting disks get flushed too stt["random_sleep_range"] = "30" stt["mode"] = "pass" stt.commit() # Create a Dummy agent that always fails for levels-or if stf_nodes: stf = Resource(self._factory, "FencingFail", "fence_dummy", "stonith") stf["pcmk_host_list"] = " ".join(stf_nodes) # Wait this many seconds before doing anything, handy for letting disks get flushed too stf["random_sleep_range"] = "30" stf["mode"] = "fail" stf.commit() # Now commit the levels themselves stl.commit() o = Option(self._factory) o["stonith-enabled"] = self._cm.Env["DoFencing"] o["start-failure-is-fatal"] = "false" o["pe-input-series-max"] = "5000" o["shutdown-escalation"] = "5min" o["batch-limit"] = "10" o["dc-deadtime"] = "5s" o["no-quorum-policy"] = no_quorum o.commit() o = OpDefaults(self._factory) o["timeout"] = "90s" o.commit() # Commit the nodes section if we defined one if stn is not None: stn.commit() # Add an alerts section if possible if self._factory.rsh.exists_on_all(self._cm.Env["notification-agent"], self._cm.Env["nodes"]): alerts = Alerts(self._factory) alerts.add_alert(self._cm.Env["notification-agent"], self._cm.Env["notification-recipient"]) alerts.commit() # Add resources? if self._cm.Env["CIBResource"]: self.add_resources() # generate cib self._cib = self._show() if self._factory.tmpfile != "%s/cib.xml" % BuildOptions.CIB_DIR: self._factory.rsh(self._factory.target, "rm -f %s" % self._factory.tmpfile) return self._cib def add_resources(self): """ Add various resources and their constraints to the CIB """ # Per-node resources for node in self._cm.Env["nodes"]: name = "rsc_%s" % node r = self.new_ip(name) r.prefer(node, "100") r.commit() # Migrator # Make this slightly sticky (since we have no other location constraints) to avoid relocation during Reattach m = Resource(self._factory, "migrator","Dummy", "ocf", "pacemaker") m["passwd"] = "whatever" m.add_meta("resource-stickiness","1") m.add_meta("allow-migrate", "1") m.add_op("monitor", "P10S") m.commit() # Ping the test exerciser p = Resource(self._factory, "ping-1","ping", "ocf", "pacemaker") p.add_op("monitor", "60s") p["host_list"] = self._cm.Env["cts-exerciser"] p["name"] = "connected" p["debug"] = "true" c = Clone(self._factory, "Connectivity", p) c["globally-unique"] = "false" c.commit() # promotable clone resource s = Resource(self._factory, "stateful-1", "Stateful", "ocf", "pacemaker") s.add_op("monitor", "15s", timeout="60s") s.add_op("monitor", "16s", timeout="60s", role="Promoted") ms = Clone(self._factory, "promotable-1", s) ms["promotable"] = "true" ms["clone-max"] = self._num_nodes ms["clone-node-max"] = 1 ms["promoted-max"] = 1 ms["promoted-node-max"] = 1 # Require connectivity to run the promotable clone r = Rule(self._factory, "connected", "-INFINITY", op="or") r.add_child(Expression(self._factory, "m1-connected-1", "connected", "lt", "1")) r.add_child(Expression(self._factory, "m1-connected-2", "connected", "not_defined", None)) ms.prefer("connected", rule=r) ms.commit() # Group Resource g = Group(self._factory, "group-1") g.add_child(self.new_ip()) if self._cm.Env["have_systemd"]: sysd = Resource(self._factory, "petulant", "pacemaker-cts-dummyd@10", "service") sysd.add_op("monitor", "P10S") g.add_child(sysd) else: g.add_child(self.new_ip()) g.add_child(self.new_ip()) # Make group depend on the promotable clone g.after("promotable-1", first="promote", then="start") g.colocate("promotable-1", "INFINITY", withrole="Promoted") g.commit() # LSB resource lsb = Resource(self._factory, "lsb-dummy", "LSBDummy", "lsb") lsb.add_op("monitor", "5s") # LSB with group lsb.after("group-1") lsb.colocate("group-1") lsb.commit() class ConfigFactory: """ Singleton to generate a CIB file for the environment's schema version """ def __init__(self, cm): """ Create a new ConfigFactory instance Arguments: cm -- A ClusterManager instance """ # pylint: disable=invalid-name self._cm = cm self.rsh = self._cm.rsh if not self._cm.Env["ListTests"]: self.target = self._cm.Env["nodes"][0] self.tmpfile = None def log(self, args): """ Log a message """ self._cm.log("cib: %s" % args) def debug(self, args): """ Log a debug message """ self._cm.debug("cib: %s" % args) - def create_config(self, name="pacemaker-1.0"): + def create_config(self, name="pacemaker-%s" % BuildOptions.CIB_SCHEMA_VERSION): """ Return a CIB object for the given schema version """ return CIB(self._cm, name, self) diff --git a/python/pacemaker/_cts/environment.py b/python/pacemaker/_cts/environment.py index 2dfbae4a27..56246abea4 100644 --- a/python/pacemaker/_cts/environment.py +++ b/python/pacemaker/_cts/environment.py @@ -1,645 +1,646 @@ """ Test environment classes for Pacemaker's Cluster Test Suite (CTS) """ __all__ = ["EnvFactory"] __copyright__ = "Copyright 2014-2023 the Pacemaker project contributors" __license__ = "GNU General Public License version 2 or later (GPLv2+) WITHOUT ANY WARRANTY" import argparse import os import random import socket import sys import time +from pacemaker.buildoptions import BuildOptions from pacemaker._cts.logging import LogFactory from pacemaker._cts.remote import RemoteFactory from pacemaker._cts.watcher import LogKind class Environment: """ A class for managing the CTS environment, consisting largely of processing and storing command line parameters """ # pylint doesn't understand that self._rsh is callable (it stores the # singleton instance of RemoteExec, as returned by the getInstance method # of RemoteFactory). It's possible we could fix this with type annotations, # but those were introduced with python 3.5 and we only support python 3.4. # I think we could also fix this by getting rid of the getInstance methods, # but that's a project for another day. For now, just disable the warning. # pylint: disable=not-callable def __init__(self, args): """ Create a new Environment instance. This class can be treated kind of like a dictionary due to the presence of typical dict functions like __contains__, __getitem__, and __setitem__. However, it is not a dictionary so do not rely on standard dictionary behavior. Arguments: args -- A list of command line parameters, minus the program name. If None, sys.argv will be used. """ self.data = {} self._nodes = [] # Set some defaults before processing command line arguments. These are # either not set by any command line parameter, or they need a default # that can't be set in add_argument. self["DeadTime"] = 300 self["StartTime"] = 300 self["StableTime"] = 30 self["tests"] = [] self["IPagent"] = "IPaddr2" self["DoFencing"] = True self["ClobberCIB"] = False self["CIBfilename"] = None self["CIBResource"] = False self["LogWatcher"] = LogKind.ANY self["node-limit"] = 0 self["scenario"] = "random" self.random_gen = random.Random() self._logger = LogFactory() self._rsh = RemoteFactory().getInstance() self._target = "localhost" self._seed_random() self._parse_args(args) if not self["ListTests"]: self._validate() self._discover() def _seed_random(self, seed=None): """ Initialize the random number generator with the given seed, or use the current time if None """ if not seed: seed = int(time.time()) self["RandSeed"] = seed self.random_gen.seed(str(seed)) def dump(self): """ Print the current environment """ keys = [] for key in list(self.data.keys()): keys.append(key) keys.sort() for key in keys: s = "Environment[%s]" % key self._logger.debug("{key:35}: {val}".format(key=s, val=str(self[key]))) def keys(self): """ Return a list of all environment keys stored in this instance """ return list(self.data.keys()) def __contains__(self, key): """ Does the given environment key exist? """ if key == "nodes": return True return key in self.data def __getitem__(self, key): """ Return the given environment key, or None if it does not exist """ if str(key) == "0": raise ValueError("Bad call to 'foo in X', should reference 'foo in X.keys()' instead") if key == "nodes": return self._nodes if key == "Name": return self._get_stack_short() return self.data.get(key) def __setitem__(self, key, value): """ Set the given environment key to the given value, overriding any previous value """ if key == "Stack": self._set_stack(value) elif key == "node-limit": self.data[key] = value self._filter_nodes() elif key == "nodes": self._nodes = [] for node in value: # I don't think I need the IP address, etc. but this validates # the node name against /etc/hosts and/or DNS, so it's a # GoodThing(tm). try: n = node.strip() socket.gethostbyname_ex(n) self._nodes.append(n) except: self._logger.log("%s not found in DNS... aborting" % node) raise self._filter_nodes() else: self.data[key] = value def random_node(self): """ Choose a random node from the cluster """ return self.random_gen.choice(self["nodes"]) def get(self, key, default=None): """ Return the value for key if key is in the environment, else default """ if key == "nodes": return self._nodes return self.data.get(key, default) def _set_stack(self, name): """ Normalize the given cluster stack name """ if name in ["corosync", "cs", "mcp"]: self.data["Stack"] = "corosync 2+" else: raise ValueError("Unknown stack: %s" % name) def _get_stack_short(self): """ Return the short name for the currently set cluster stack """ if "Stack" not in self.data: return "unknown" if self.data["Stack"] == "corosync 2+": return "crm-corosync" LogFactory().log("Unknown stack: %s" % self["stack"]) raise ValueError("Unknown stack: %s" % self["stack"]) def _detect_systemd(self): """ Detect whether systemd is in use on the target node """ if "have_systemd" not in self.data: (rc, _) = self._rsh(self._target, "systemctl list-units", verbose=0) self["have_systemd"] = rc == 0 def _detect_syslog(self): """ Detect the syslog variant in use on the target node """ if "syslogd" not in self.data: if self["have_systemd"]: # Systemd (_, lines) = self._rsh(self._target, r"systemctl list-units | grep syslog.*\.service.*active.*running | sed 's:.service.*::'", verbose=1) self["syslogd"] = lines[0].strip() else: # SYS-V (_, lines) = self._rsh(self._target, "chkconfig --list | grep syslog.*on | awk '{print $1}' | head -n 1", verbose=1) self["syslogd"] = lines[0].strip() if "syslogd" not in self.data or not self["syslogd"]: # default self["syslogd"] = "rsyslog" def disable_service(self, node, service): """ Disable the given service on the given node """ if self["have_systemd"]: # Systemd (rc, _) = self._rsh(node, "systemctl disable %s" % service) return rc # SYS-V (rc, _) = self._rsh(node, "chkconfig %s off" % service) return rc def enable_service(self, node, service): """ Enable the given service on the given node """ if self["have_systemd"]: # Systemd (rc, _) = self._rsh(node, "systemctl enable %s" % service) return rc # SYS-V (rc, _) = self._rsh(node, "chkconfig %s on" % service) return rc def service_is_enabled(self, node, service): """ Is the given service enabled on the given node? """ if self["have_systemd"]: # Systemd # With "systemctl is-enabled", we should check if the service is # explicitly "enabled" instead of the return code. For example it returns # 0 if the service is "static" or "indirect", but they don't really count # as "enabled". (rc, _) = self._rsh(node, "systemctl is-enabled %s | grep enabled" % service) return rc == 0 # SYS-V (rc, _) = self._rsh(node, "chkconfig --list | grep -e %s.*on" % service) return rc == 0 def _detect_at_boot(self): """ Detect if the cluster starts at boot """ if "at-boot" not in self.data: self["at-boot"] = self.service_is_enabled(self._target, "corosync") \ or self.service_is_enabled(self._target, "pacemaker") def _detect_ip_offset(self): """ Detect the offset for IPaddr resources """ if self["CIBResource"] and "IPBase" not in self.data: (_, lines) = self._rsh(self._target, "ip addr | grep inet | grep -v -e link -e inet6 -e '/32' -e ' lo' | awk '{print $2}'", verbose=0) network = lines[0].strip() (_, lines) = self._rsh(self._target, "nmap -sn -n %s | grep 'scan report' | awk '{print $NF}' | sed 's:(::' | sed 's:)::' | sort -V | tail -n 1" % network, verbose=0) try: self["IPBase"] = lines[0].strip() except (IndexError, TypeError): self["IPBase"] = None if not self["IPBase"]: self["IPBase"] = " fe80::1234:56:7890:1000" self._logger.log("Could not determine an offset for IPaddr resources. Perhaps nmap is not installed on the nodes.") self._logger.log("Defaulting to '%s', use --test-ip-base to override" % self["IPBase"]) return # pylint thinks self["IPBase"] is a list, not a string, which causes it # to error out because a list doesn't have split(). # pylint: disable=no-member if int(self["IPBase"].split('.')[3]) >= 240: self._logger.log("Could not determine an offset for IPaddr resources. Upper bound is too high: %s %s" % (self["IPBase"], self["IPBase"].split('.')[3])) self["IPBase"] = " fe80::1234:56:7890:1000" self._logger.log("Defaulting to '%s', use --test-ip-base to override" % self["IPBase"]) def _filter_nodes(self): """ If --limit-nodes is given, keep that many nodes from the front of the list of cluster nodes and drop the rest """ if self["node-limit"] > 0: if len(self["nodes"]) > self["node-limit"]: # pylint thinks self["node-limit"] is a list even though we initialize # it as an int in __init__ and treat it as an int everywhere. # pylint: disable=bad-string-format-type self._logger.log("Limiting the number of nodes configured=%d (max=%d)" %(len(self["nodes"]), self["node-limit"])) while len(self["nodes"]) > self["node-limit"]: self["nodes"].pop(len(self["nodes"])-1) def _validate(self): """ Were we given all the required command line parameters? """ if not self["nodes"]: raise ValueError("No nodes specified!") def _discover(self): """ Probe cluster nodes to figure out how to log and manage services """ self._target = random.Random().choice(self["nodes"]) exerciser = socket.gethostname() # Use the IP where possible to avoid name lookup failures for ip in socket.gethostbyname_ex(exerciser)[2]: if ip != "127.0.0.1": exerciser = ip break self["cts-exerciser"] = exerciser self._detect_systemd() self._detect_syslog() self._detect_at_boot() self._detect_ip_offset() def _parse_args(self, argv): """ Parse and validate command line parameters, setting the appropriate values in the environment dictionary. If argv is None, use sys.argv instead. """ if not argv: argv = sys.argv[1:] parser = argparse.ArgumentParser(epilog="%s -g virt1 -r --stonith ssh --schema pacemaker-2.0 500" % sys.argv[0]) grp1 = parser.add_argument_group("Common options") grp1.add_argument("-g", "--dsh-group", "--group", metavar="GROUP", dest="group", help="Use the nodes listed in the named DSH group (~/.dsh/groups/$name)") grp1.add_argument("-l", "--limit-nodes", type=int, default=0, metavar="MAX", help="Only use the first MAX cluster nodes supplied with --nodes") grp1.add_argument("--benchmark", action="store_true", help="Add timing information") grp1.add_argument("--list", "--list-tests", action="store_true", dest="list_tests", help="List the valid tests") grp1.add_argument("--nodes", metavar="NODES", help="List of cluster nodes separated by whitespace") grp1.add_argument("--stack", default="corosync", metavar="STACK", help="Which cluster stack is installed") grp2 = parser.add_argument_group("Options that CTS will usually auto-detect correctly") grp2.add_argument("-L", "--logfile", metavar="PATH", help="Where to look for logs from cluster nodes") grp2.add_argument("--at-boot", "--cluster-starts-at-boot", choices=["1", "0", "yes", "no"], help="Does the cluster software start at boot time?") grp2.add_argument("--facility", "--syslog-facility", default="daemon", metavar="NAME", help="Which syslog facility to log to") grp2.add_argument("--ip", "--test-ip-base", metavar="IP", help="Offset for generated IP address resources") grp3 = parser.add_argument_group("Options for release testing") grp3.add_argument("-r", "--populate-resources", action="store_true", help="Generate a sample configuration") grp3.add_argument("--choose", metavar="NAME", help="Run only the named test") grp3.add_argument("--fencing", "--stonith", choices=["1", "0", "yes", "no", "lha", "openstack", "rhcs", "rhevm", "scsi", "ssh", "virt", "xvm"], default="1", help="What fencing agent to use") grp3.add_argument("--once", action="store_true", help="Run all valid tests once") grp4 = parser.add_argument_group("Additional (less common) options") grp4.add_argument("-c", "--clobber-cib", action="store_true", help="Erase any existing configuration") grp4.add_argument("-y", "--yes", action="store_true", dest="always_continue", help="Continue to run whenever prompted") grp4.add_argument("--boot", action="store_true", help="") grp4.add_argument("--cib-filename", metavar="PATH", help="Install the given CIB file to the cluster") grp4.add_argument("--experimental-tests", action="store_true", help="Include experimental tests") grp4.add_argument("--loop-minutes", type=int, default=60, help="") grp4.add_argument("--no-loop-tests", action="store_true", help="Don't run looping/time-based tests") grp4.add_argument("--no-unsafe-tests", action="store_true", help="Don't run tests that are unsafe for use with ocfs2/drbd") grp4.add_argument("--notification-agent", metavar="PATH", default="/var/lib/pacemaker/notify.sh", help="Script to configure for Pacemaker alerts") grp4.add_argument("--notification-recipient", metavar="R", default="/var/lib/pacemaker/notify.log", help="Recipient to pass to alert script") grp4.add_argument("--oprofile", metavar="NODES", help="List of cluster nodes to run oprofile on") grp4.add_argument("--outputfile", metavar="PATH", help="Location to write logs to") grp4.add_argument("--qarsh", action="store_true", help="Use QARSH to access nodes instead of SSH") grp4.add_argument("--schema", metavar="SCHEMA", - default="pacemaker-3.0", + default="pacemaker-%s" % BuildOptions.CIB_SCHEMA_VERSION, help="Create a CIB conforming to the given schema") grp4.add_argument("--seed", metavar="SEED", help="Use the given string as the random number seed") grp4.add_argument("--set", action="append", metavar="ARG", default=[], help="Set key=value pairs (can be specified multiple times)") grp4.add_argument("--stonith-args", metavar="ARGS", default="hostlist=all,livedangerously=yes", help="") grp4.add_argument("--stonith-type", metavar="TYPE", default="external/ssh", help="") grp4.add_argument("--trunc", action="store_true", dest="truncate", help="Truncate log file before starting") grp4.add_argument("--valgrind-procs", metavar="PROCS", default="pacemaker-attrd pacemaker-based pacemaker-controld pacemaker-execd pacemaker-fenced pacemaker-schedulerd", help="Run valgrind against the given space-separated list of processes") grp4.add_argument("--valgrind-tests", action="store_true", help="Include tests using valgrind") grp4.add_argument("--warn-inactive", action="store_true", help="Warn if a resource is assigned to an inactive node") parser.add_argument("iterations", nargs='?', type=int, default=1, help="Number of tests to run") args = parser.parse_args(args=argv) # Set values on this object based on what happened with command line # processing. This has to be done in several blocks. # These values can always be set. They get a default from the add_argument # calls, only do one thing, and they do not have any side effects. self["ClobberCIB"] = args.clobber_cib self["ListTests"] = args.list_tests self["Schema"] = args.schema self["Stack"] = args.stack self["SyslogFacility"] = args.facility self["TruncateLog"] = args.truncate self["at-boot"] = args.at_boot in ["1", "yes"] self["benchmark"] = args.benchmark self["continue"] = args.always_continue self["experimental-tests"] = args.experimental_tests self["iterations"] = args.iterations self["loop-minutes"] = args.loop_minutes self["loop-tests"] = not args.no_loop_tests self["notification-agent"] = args.notification_agent self["notification-recipient"] = args.notification_recipient self["node-limit"] = args.limit_nodes self["stonith-params"] = args.stonith_args self["stonith-type"] = args.stonith_type self["unsafe-tests"] = not args.no_unsafe_tests self["valgrind-procs"] = args.valgrind_procs self["valgrind-tests"] = args.valgrind_tests self["warn-inactive"] = args.warn_inactive # Nodes and groups are mutually exclusive, so their defaults cannot be # set in their add_argument calls. Additionally, groups does more than # just set a value. Here, set nodes first and then if a group is # specified, override the previous nodes value. if args.nodes: self["nodes"] = args.nodes.split(" ") else: self["nodes"] = [] if args.group: self["OutputFile"] = "%s/cluster-%s.log" % (os.environ['HOME'], args.dsh_group) LogFactory().add_file(self["OutputFile"], "CTS") dsh_file = "%s/.dsh/group/%s" % (os.environ['HOME'], args.dsh_group) if os.path.isfile(dsh_file): self["nodes"] = [] with open(dsh_file, "r", encoding="utf-8") as f: for line in f: l = line.strip() if not l.startswith('#'): self["nodes"].append(l) else: print("Unknown DSH group: %s" % args.dsh_group) # Everything else either can't have a default set in an add_argument # call (likely because we don't want to always have a value set for it) # or it does something fancier than just set a single value. However, # order does not matter for these as long as the user doesn't provide # conflicting arguments on the command line. So just do Everything # alphabetically. if args.boot: self["scenario"] = "boot" if args.cib_filename: self["CIBfilename"] = args.cib_filename else: self["CIBfilename"] = None if args.choose: self["scenario"] = "sequence" self["tests"].append(args.choose) if args.fencing: if args.fencing in ["0", "no"]: self["DoFencing"] = False else: self["DoFencing"] = True if args.fencing in ["rhcs", "virt", "xvm"]: self["stonith-type"] = "fence_xvm" elif args.fencing == "scsi": self["stonith-type"] = "fence_scsi" elif args.fencing in ["lha", "ssh"]: self["stonith-params"] = "hostlist=all,livedangerously=yes" self["stonith-type"] = "external/ssh" elif args.fencing == "openstack": self["stonith-type"] = "fence_openstack" print("Obtaining OpenStack credentials from the current environment") self["stonith-params"] = "region=%s,tenant=%s,auth=%s,user=%s,password=%s" % ( os.environ['OS_REGION_NAME'], os.environ['OS_TENANT_NAME'], os.environ['OS_AUTH_URL'], os.environ['OS_USERNAME'], os.environ['OS_PASSWORD'] ) elif args.fencing == "rhevm": self["stonith-type"] = "fence_rhevm" print("Obtaining RHEV-M credentials from the current environment") self["stonith-params"] = "login=%s,passwd=%s,ipaddr=%s,ipport=%s,ssl=1,shell_timeout=10" % ( os.environ['RHEVM_USERNAME'], os.environ['RHEVM_PASSWORD'], os.environ['RHEVM_SERVER'], os.environ['RHEVM_PORT'], ) if args.ip: self["CIBResource"] = True self["ClobberCIB"] = True self["IPBase"] = args.ip if args.logfile: self["LogAuditDisabled"] = True self["LogFileName"] = args.logfile self["LogWatcher"] = LogKind.REMOTE_FILE else: # We can't set this as the default on the parser.add_argument call # for this option because then args.logfile will be set, which means # the above branch will be taken and those other values will also be # set. self["LogFileName"] = "/var/log/messages" if args.once: self["scenario"] = "all-once" if args.oprofile: self["oprofile"] = args.oprofile.split(" ") else: self["oprofile"] = [] if args.outputfile: self["OutputFile"] = args.outputfile LogFactory().add_file(self["OutputFile"]) if args.populate_resources: self["CIBResource"] = True self["ClobberCIB"] = True if args.qarsh: self._rsh.enable_qarsh() for kv in args.set: (name, value) = kv.split("=") self[name] = value print("Setting %s = %s" % (name, value)) class EnvFactory: """ A class for constructing a singleton instance of an Environment object """ instance = None # pylint: disable=invalid-name def getInstance(self, args=None): """ Returns the previously created instance of Environment, or creates a new instance if one does not already exist. """ if not EnvFactory.instance: EnvFactory.instance = Environment(args) return EnvFactory.instance