Versions Compared

Old Version 6

changes.mady.by.user Unknown User (kelveny)

Saved on

compared with

New Version 7

changes.mady.by.user Unknown User (kelveny)

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Code Block
    protected HashMap<String, PowerState> sync() {
    	return getVmStates();
    }

The schema change to add VM power state support is shown below.

...

Currently, state transition handling always happens at in-place context, for example, when management server receives hypervisor VM state report, the handling of the report is processed within the context, even if there may be another thread that is handling user request on the same VM. Although we try to coordinate by checking the state of the VM, by simplify failing it with concurrent-access exception.  

About in-place handling style, following code snaplet shows an example.

Code Block
    
    protected Command compareState(long hostId, VMInstanceVO vm, final AgentVmInfo info, final boolean fullSync, boolean trackExternalChange) {
        State agentState = info.state;
        final State serverState = vm.getState();
        final String serverName = vm.getInstanceName();

        Command command = null;
        s_logger.debug("VM " + serverName + ": cs state = " + serverState + " and realState = " + agentState);
        if (s_logger.isDebugEnabled()) {
            s_logger.debug("VM " + serverName + ": cs state = " + serverState + " and realState = " + agentState);
        }

        if (agentState == State.Error) {
            agentState = State.Stopped;

            short alertType = AlertManager.ALERT_TYPE_USERVM;
            if (VirtualMachine.Type.DomainRouter.equals(vm.getType())) {
                alertType = AlertManager.ALERT_TYPE_DOMAIN_ROUTER;
            } else if (VirtualMachine.Type.ConsoleProxy.equals(vm.getType())) {
                alertType = AlertManager.ALERT_TYPE_CONSOLE_PROXY;
            } else if (VirtualMachine.Type.SecondaryStorageVm.equals(vm.getType())) {
                alertType = AlertManager.ALERT_TYPE_SSVM;
            }

            HostPodVO podVO = _podDao.findById(vm.getPodIdToDeployIn());
            DataCenterVO dcVO = _dcDao.findById(vm.getDataCenterId());
            HostVO hostVO = _hostDao.findById(vm.getHostId());

            String hostDesc = "name: " + hostVO.getName() + " (id:" + hostVO.getId() + "), availability zone: " + dcVO.getName() + ", pod: " + podVO.getName();
            _alertMgr.sendAlert(alertType, vm.getDataCenterId(), vm.getPodIdToDeployIn(), "VM (name: " + vm.getInstanceName() + ", id: " + vm.getId() + ") stopped on host " + hostDesc
                    + " due to storage failure", "Virtual Machine " + vm.getInstanceName() + " (id: " + vm.getId() + ") running on host [" + vm.getHostId() + "] stopped due to storage failure.");
        }

        if (trackExternalChange) {
            if (serverState == State.Starting) {
                if (vm.getHostId() != null && vm.getHostId() != hostId) {
                    s_logger.info("CloudStack is starting VM on host " + vm.getHostId() + ", but status report comes from a different host " + hostId + ", skip status sync for vm: "
                            + vm.getInstanceName());
                    return null;
                }
            }
            if (vm.getHostId() == null || hostId != vm.getHostId()) {
                try {
                    ItWorkVO workItem = _workDao.findByOutstandingWork(vm.getId(), State.Migrating);
                    if(workItem == null){
                        stateTransitTo(vm, VirtualMachine.Event.AgentReportMigrated, hostId);
                    }
                } catch (NoTransitionException e) {
                }
            }
        }

        // during VM migration time, don't sync state will agent status update
        if (serverState == State.Migrating) {
            s_logger.debug("Skipping vm in migrating state: " + vm);
            return null;
        }

        if (trackExternalChange) {
            if (serverState == State.Starting) {
                if (vm.getHostId() != null && vm.getHostId() != hostId) {
                    s_logger.info("CloudStack is starting VM on host " + vm.getHostId() + ", but status report comes from a different host " + hostId + ", skip status sync for vm: "
                            + vm.getInstanceName());
                    return null;
                }
            }

            if (serverState == State.Running) {
                try {
                    //
                    // we had a bug that sometimes VM may be at Running State
                    // but host_id is null, we will cover it here.
                    // means that when CloudStack DB lost of host information,
                    // we will heal it with the info reported from host
                    //
                    if (vm.getHostId() == null || hostId != vm.getHostId()) {
                        if (s_logger.isDebugEnabled()) {
                            s_logger.debug("detected host change when VM " + vm + " is at running state, VM could be live-migrated externally from host " + vm.getHostId() + " to host " + hostId);
                        }

                        stateTransitTo(vm, VirtualMachine.Event.AgentReportMigrated, hostId);
                    }
                } catch (NoTransitionException e) {
                    s_logger.warn(e.getMessage());
                }
            }
        }

        if (agentState == serverState) {
            if (s_logger.isDebugEnabled()) {
                s_logger.debug("Both states are " + agentState + " for " + vm);
            }
            assert (agentState == State.Stopped || agentState == State.Running) : "If the states we send up is changed, this must be changed.";
            if (agentState == State.Running) {
                try {
                    stateTransitTo(vm, VirtualMachine.Event.AgentReportRunning, hostId);
                } catch (NoTransitionException e) {
                    s_logger.warn(e.getMessage());
                }
                // FIXME: What if someone comes in and sets it to stopping? Then
                // what?
                return null;
            }

            s_logger.debug("State matches but the agent said stopped so let's send a cleanup command anyways.");
            return cleanup(vm);
        }

        if (agentState == State.Shutdowned) {
            if (serverState == State.Running || serverState == State.Starting || serverState == State.Stopping) {
                try {
                    advanceStop(vm, true, _accountMgr.getSystemUser(), _accountMgr.getSystemAccount());
                } catch (AgentUnavailableException e) {
                    assert (false) : "How do we hit this with forced on?";
                    return null;
                } catch (OperationTimedoutException e) {
                    assert (false) : "How do we hit this with forced on?";
                    return null;
                } catch (ConcurrentOperationException e) {
                    assert (false) : "How do we hit this with forced on?";
                    return null;
                }
            } else {
                s_logger.debug("Sending cleanup to a shutdowned vm: " + vm.getInstanceName());
                command = cleanup(vm);
            }
        } else if (agentState == State.Stopped) {
            // This state means the VM on the agent was detected previously
            // and now is gone. This is slightly different than if the VM
            // was never completed but we still send down a Stop Command
            // to ensure there's cleanup.
            if (serverState == State.Running) {
                // Our records showed that it should be running so let's restart
                // it.
                _haMgr.scheduleRestart(vm, false);
            } else if (serverState == State.Stopping) {
                _haMgr.scheduleStop(vm, hostId, WorkType.ForceStop);
                s_logger.debug("Scheduling a check stop for VM in stopping mode: " + vm);
            } else if (serverState == State.Starting) {
                s_logger.debug("Ignoring VM in starting mode: " + vm.getInstanceName());
                _haMgr.scheduleRestart(vm, false);
            }
            command = cleanup(vm);
        } else if (agentState == State.Running) {
            if (serverState == State.Starting) {
                if (fullSync) {
                    try {
                        ensureVmRunningContext(hostId, vm, Event.AgentReportRunning);
                    } catch (OperationTimedoutException e) {
                        s_logger.error("Exception during update for running vm: " + vm, e);
                        return null;
                    } catch (ResourceUnavailableException e) {
                        s_logger.error("Exception during update for running vm: " + vm, e);
                        return null;
                    }catch (InsufficientAddressCapacityException e) {
                        s_logger.error("Exception during update for running vm: " + vm, e);
                        return null;
                    }catch (NoTransitionException e) {
                        s_logger.warn(e.getMessage());
                    }
                }
            } else if (serverState == State.Stopping) {
                s_logger.debug("Scheduling a stop command for " + vm);
                _haMgr.scheduleStop(vm, hostId, WorkType.Stop);
            } else {
                s_logger.debug("server VM state " + serverState + " does not meet expectation of a running VM report from agent");

                // just be careful not to stop VM for things we don't handle
                // command = cleanup(vm);
            }
        }
        return command;
    }

In the new design, we will try to serialize activities to the same VM through job facility, since there always be one active operation is in executing, the state transition logic can be simplified. Take the VM migrating case, as it involves with two hosts, in previous model, with VM state report from different hosts, we have to handle it carefully as the host report may come at un-predicted order. 

...