X-Git-Url: https://code.grnet.gr/git/ganeti-local/blobdiff_plain/96fa35c1a35d01a827f1c0e5cffa60fd033f67a6..96d7b4280cf8e0bc9f6b5547fd30bac46b0049f6:/lib/cmdlib.py diff --git a/lib/cmdlib.py b/lib/cmdlib.py index b45a83b..11c98bc 100644 --- a/lib/cmdlib.py +++ b/lib/cmdlib.py @@ -1860,23 +1860,41 @@ def _AssembleInstanceDisks(instance, cfg, ignore_secondaries=False): """ device_info = [] disks_ok = True + iname = instance.name + # With the two passes mechanism we try to reduce the window of + # opportunity for the race condition of switching DRBD to primary + # before handshaking occured, but we do not eliminate it + + # The proper fix would be to wait (with some limits) until the + # connection has been made and drbd transitions from WFConnection + # into any other network-connected state (Connected, SyncTarget, + # SyncSource, etc.) + + # 1st pass, assemble on all nodes in secondary mode for inst_disk in instance.disks: - master_result = None for node, node_disk in inst_disk.ComputeNodeTree(instance.primary_node): cfg.SetDiskID(node_disk, node) - is_primary = node == instance.primary_node - result = rpc.call_blockdev_assemble(node, node_disk, - instance.name, is_primary) + result = rpc.call_blockdev_assemble(node, node_disk, iname, False) if not result: logger.Error("could not prepare block device %s on node %s" - " (is_primary=%s)" % - (inst_disk.iv_name, node, is_primary)) - if is_primary or not ignore_secondaries: + " (is_primary=False, pass=1)" % (inst_disk.iv_name, node)) + if not ignore_secondaries: disks_ok = False - if is_primary: - master_result = result - device_info.append((instance.primary_node, inst_disk.iv_name, - master_result)) + + # FIXME: race condition on drbd migration to primary + + # 2nd pass, do only the primary node + for inst_disk in instance.disks: + for node, node_disk in inst_disk.ComputeNodeTree(instance.primary_node): + if node != instance.primary_node: + continue + cfg.SetDiskID(node_disk, node) + result = rpc.call_blockdev_assemble(node, node_disk, iname, True) + if not result: + logger.Error("could not prepare block device %s on node %s" + " (is_primary=True, pass=2)" % (inst_disk.iv_name, node)) + disks_ok = False + device_info.append((instance.primary_node, inst_disk.iv_name, result)) # leave the disks configured for the primary node # this is a workaround that would be fixed better by @@ -2400,7 +2418,7 @@ class LUQueryInstances(NoHooksLU): This checks that the fields required are valid output fields. """ - self.dynamic_fields = frozenset(["oper_state", "oper_ram"]) + self.dynamic_fields = frozenset(["oper_state", "oper_ram", "status"]) _CheckOutputFields(static=["name", "os", "pnode", "snodes", "admin_state", "admin_ram", "disk_template", "ip", "mac", "bridge", @@ -2457,6 +2475,21 @@ class LUQueryInstances(NoHooksLU): val = None else: val = bool(live_data.get(instance.name)) + elif field == "status": + if instance.primary_node in bad_nodes: + val = "ERROR_nodedown" + else: + running = bool(live_data.get(instance.name)) + if running: + if instance.status != "down": + val = "running" + else: + val = "ERROR_up" + else: + if instance.status != "down": + val = "ERROR_down" + else: + val = "ADMIN_down" elif field == "admin_ram": val = instance.memory elif field == "oper_ram": @@ -3995,7 +4028,7 @@ class LUQueryInstanceData(NoHooksLU): instance = self.cfg.GetInstanceInfo(self.cfg.ExpandInstanceName(name)) if instance is None: raise errors.OpPrereqError("No such instance name '%s'" % name) - self.wanted_instances.append(instance) + self.wanted_instances.append(instance) else: self.wanted_instances = [self.cfg.GetInstanceInfo(name) for name in self.cfg.GetInstanceList()] @@ -4098,7 +4131,7 @@ class LUSetInstanceParms(LogicalUnit): args['memory'] = self.mem if self.vcpus: args['vcpus'] = self.vcpus - if self.do_ip or self.do_bridge: + if self.do_ip or self.do_bridge or self.mac: if self.do_ip: ip = self.ip else: @@ -4107,7 +4140,11 @@ class LUSetInstanceParms(LogicalUnit): bridge = self.bridge else: bridge = self.instance.nics[0].bridge - args['nics'] = [(ip, bridge)] + if self.mac: + mac = self.mac + else: + mac = self.instance.nics[0].mac + args['nics'] = [(ip, bridge, mac)] env = _BuildInstanceHookEnvByObject(self.instance, override=args) nl = [self.sstore.GetMasterNode(), self.instance.primary_node] + list(self.instance.secondary_nodes) @@ -4524,3 +4561,39 @@ class LUDelTags(TagsLU): raise errors.OpRetryError("There has been a modification to the" " config file and the operation has been" " aborted. Please retry.") + +class LUTestDelay(NoHooksLU): + """Sleep for a specified amount of time. + + This LU sleeps on the master and/or nodes for a specified amoutn of + time. + + """ + _OP_REQP = ["duration", "on_master", "on_nodes"] + + def CheckPrereq(self): + """Check prerequisites. + + This checks that we have a good list of nodes and/or the duration + is valid. + + """ + + if self.op.on_nodes: + self.op.on_nodes = _GetWantedNodes(self, self.op.on_nodes) + + def Exec(self, feedback_fn): + """Do the actual sleep. + + """ + if self.op.on_master: + if not utils.TestDelay(self.op.duration): + raise errors.OpExecError("Error during master delay test") + if self.op.on_nodes: + result = rpc.call_test_delay(self.op.on_nodes, self.op.duration) + if not result: + raise errors.OpExecError("Complete failure from rpc call") + for node, node_result in result.items(): + if not node_result: + raise errors.OpExecError("Failure during rpc call to node %s," + " result: %s" % (node, node_result))