[ https://issues.apache.org/jira/browse/CLOUDSTACK-9114?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15050433#comment-15050433 ]
ASF GitHub Bot commented on CLOUDSTACK-9114: -------------------------------------------- Github user wilderrodrigues commented on a diff in the pull request: https://github.com/apache/cloudstack/pull/1198#discussion_r47204055 --- Diff: engine/orchestration/src/org/apache/cloudstack/engine/orchestration/NetworkOrchestrator.java --- @@ -2558,6 +2575,62 @@ public boolean restartNetwork(Long networkId, Account callerAccount, User caller } } + /* If there are redundant routers in the isolated network, we follow the steps to make the network working better + * (1) destroy backup router if exists + * (2) create new backup router + * (3) destroy master router (then the backup will become master) + * (4) create a new router as backup router. + */ + private boolean restartGuestNetworkWithRedundantRouters(NetworkVO network, List<DomainRouterVO> routers, ReservationContext context) throws ResourceUnavailableException, ConcurrentOperationException, InsufficientCapacityException { + Account caller = CallContext.current().getCallingAccount(); + long callerUserId = CallContext.current().getCallingUserId(); + + // check the master and backup redundant state + DomainRouterVO masterRouter = null; + DomainRouterVO backupRouter = null; + if (routers != null && routers.size() == 1) { + masterRouter = routers.get(0); + } if (routers != null && routers.size() == 2) { + DomainRouterVO router1 = routers.get(0); + DomainRouterVO router2 = routers.get(1); + if (router1.getRedundantState() == RedundantState.MASTER || router2.getRedundantState() == RedundantState.BACKUP) { + masterRouter = router1; + backupRouter = router2; + } else if (router1.getRedundantState() == RedundantState.BACKUP || router2.getRedundantState() == RedundantState.MASTER) { + masterRouter = router2; + backupRouter = router1; + } else { // both routers are in UNKNOWN state + masterRouter = router1; + backupRouter = router2; + } + } + + NetworkOfferingVO offering = _networkOfferingDao.findByIdIncludingRemoved(network.getNetworkOfferingId()); + DeployDestination dest = new DeployDestination(_dcDao.findById(network.getDataCenterId()), null, null, null); + List<Provider> providersToImplement = getNetworkProviders(network.getId()); + + // destroy backup router + if (backupRouter != null) { + _routerService.destroyRouter(backupRouter.getId(), caller, callerUserId); + } + // create new backup router + implementNetworkElements(dest, context, network, offering, providersToImplement); + + // destroy master router + if (masterRouter != null) { + try { + Thread.sleep(10000); // wait 10s for the keepalived/conntrackd on backup router --- End diff -- It's a blocking call, you don't need it. Also, the keepalived is started with the kernel module. It would be way easier to prove the behaviour with an automated test. If you don't feel confident with writing the test, I can do it after christmas/new year and change the java code as well. > restartnetwork with cleanup should not update/restart both routers at once > -------------------------------------------------------------------------- > > Key: CLOUDSTACK-9114 > URL: https://issues.apache.org/jira/browse/CLOUDSTACK-9114 > Project: CloudStack > Issue Type: Improvement > Security Level: Public(Anyone can view this level - this is the > default.) > Reporter: Wei Zhou > Assignee: Wei Zhou > > for now, restartnetwork with cleanup will stop both RVRs at first, then start > two new RVRs. > to reduce the downtime of network, we'd better restart the RVRs one by one. -- This message was sent by Atlassian JIRA (v6.3.4#6332)