Examples with MismatchingStoreIdException org.neo4j.kernel.impl.store.MismatchingStoreIdException used on opensource projects

Example 6 with MismatchingStoreIdException

use of org.neo4j.kernel.impl.store.MismatchingStoreIdException in project neo4j by neo4j.

the class HighAvailabilityModeSwitcherTest method shouldNotResetAvailableMasterURIIfElectionResultReceived.

@Test
public void shouldNotResetAvailableMasterURIIfElectionResultReceived() throws Throwable {
    /*
         * It is possible that a masterIsElected nulls out the current available master URI in the HAMS. That can
         * be a problem if handing the mIE event is concurrent with an ongoing switch which re-runs because
         * the store was incompatible or a log was missing. In such a case it will find a null master URI on
         * rerun and it will fail.
         */
    // Given
    SwitchToSlaveCopyThenBranch switchToSlave = mock(SwitchToSlaveCopyThenBranch.class);
    // The fist run through switchToSlave
    final CountDownLatch firstCallMade = new CountDownLatch(1);
    // The second run through switchToSlave
    final CountDownLatch secondCallMade = new CountDownLatch(1);
    // The latch for waiting for the masterIsElected to come through
    final CountDownLatch waitForSecondMessage = new CountDownLatch(1);
    HighAvailabilityModeSwitcher toTest = new HighAvailabilityModeSwitcher(switchToSlave, mock(SwitchToMaster.class), mock(Election.class), mock(ClusterMemberAvailability.class), mock(ClusterClient.class), storeSupplierMock(), new InstanceId(1), new ComponentSwitcherContainer(), neoStoreDataSourceSupplierMock(), NullLogService.getInstance());
    URI uri1 = URI.create("ha://server1");
    toTest.init();
    toTest.start();
    toTest.listeningAt(URI.create("ha://server3?serverId=3"));
    when(switchToSlave.switchToSlave(any(LifeSupport.class), any(URI.class), any(URI.class), any(CancellationRequest.class))).thenAnswer(invocation -> {
        firstCallMade.countDown();
        waitForSecondMessage.await();
        throw new MismatchingStoreIdException(StoreId.DEFAULT, StoreId.DEFAULT);
    }).thenAnswer(invocation -> {
        secondCallMade.countDown();
        return URI.create("ha://server3");
    });
    // When
    // The first message goes through, start the first run
    toTest.masterIsAvailable(new HighAvailabilityMemberChangeEvent(PENDING, TO_SLAVE, new InstanceId(1), uri1));
    // Wait for it to be processed but get just before the exception
    firstCallMade.await();
    // It is just about to throw the exception, i.e. rerun. Send in the event
    toTest.masterIsElected(new HighAvailabilityMemberChangeEvent(TO_SLAVE, TO_SLAVE, new InstanceId(1), null));
    // Allow to continue and do the second run
    waitForSecondMessage.countDown();
    // Wait for the call to finish
    secondCallMade.await();
    // Then
    verify(switchToSlave, times(2)).switchToSlave(any(LifeSupport.class), any(URI.class), eq(uri1), any(CancellationRequest.class));
}

Example 7 with MismatchingStoreIdException

use of org.neo4j.kernel.impl.store.MismatchingStoreIdException in project neo4j by neo4j.

the class SwitchToSlaveBranchThenCopy method checkDataConsistency.

void checkDataConsistency(MasterClient masterClient, TransactionIdStore txIdStore, StoreId storeId, URI masterUri, URI me, CancellationRequest cancellationRequest) throws Throwable {
    try {
        userLog.info("Checking store consistency with master");
        checkMyStoreIdAndMastersStoreId(storeId, masterUri, resolver);
        checkDataConsistencyWithMaster(masterUri, masterClient, storeId, txIdStore);
        userLog.info("Store is consistent");
    } catch (StoreUnableToParticipateInClusterException upe) {
        userLog.info("The store is inconsistent. Will treat it as branched and fetch a new one from the master");
        msgLog.warn("Current store is unable to participate in the cluster; fetching new store from master", upe);
        try {
            stopServicesAndHandleBranchedStore(config.get(HaSettings.branched_data_policy));
        } catch (IOException e) {
            msgLog.warn("Failed while trying to handle branched data", e);
        }
        throw upe;
    } catch (MismatchingStoreIdException e) {
        userLog.info("The store does not represent the same database as master. Will remove and fetch a new one from " + "master");
        if (txIdStore.getLastCommittedTransactionId() == BASE_TX_ID) {
            msgLog.warn("Found and deleting empty store with mismatching store id", e);
            stopServicesAndHandleBranchedStore(BranchedDataPolicy.keep_none);
            throw e;
        }
        msgLog.error("Store cannot participate in cluster due to mismatching store IDs", e);
        throw new ForeignStoreException(e.getExpected(), e.getEncountered());
    }
}

Example 8 with MismatchingStoreIdException

use of org.neo4j.kernel.impl.store.MismatchingStoreIdException in project neo4j by neo4j.

the class BackupService method incrementalWithContext.

/**
     * Performs an incremental backup based off the given context. This means
     * receiving and applying selectively (i.e. irrespective of the actual state
     * of the target db) a set of transactions starting at the desired txId and
     * spanning up to the latest of the master
     *
     * @param targetDb The database that contains a previous full copy
     * @param context The context, containing transaction id to start streaming transaction from
     * @return A backup context, ready to perform
     */
private BackupOutcome incrementalWithContext(String sourceHostNameOrIp, int sourcePort, GraphDatabaseAPI targetDb, long timeout, RequestContext context) throws IncrementalBackupNotPossibleException {
    DependencyResolver resolver = targetDb.getDependencyResolver();
    ProgressTxHandler handler = new ProgressTxHandler();
    TransactionCommittingResponseUnpacker unpacker = new TransactionCommittingResponseUnpacker(resolver, DEFAULT_BATCH_SIZE, 0);
    Monitors monitors = resolver.resolveDependency(Monitors.class);
    LogProvider logProvider = resolver.resolveDependency(LogService.class).getInternalLogProvider();
    BackupClient client = new BackupClient(sourceHostNameOrIp, sourcePort, null, logProvider, targetDb.storeId(), timeout, unpacker, monitors.newMonitor(ByteCounterMonitor.class, BackupClient.class), monitors.newMonitor(RequestMonitor.class, BackupClient.class), new VersionAwareLogEntryReader<>());
    try (Lifespan lifespan = new Lifespan(unpacker, client)) {
        try (Response<Void> response = client.incrementalBackup(context)) {
            unpacker.unpackResponse(response, handler);
        }
    } catch (MismatchingStoreIdException e) {
        throw new RuntimeException(DIFFERENT_STORE, e);
    } catch (RuntimeException | IOException e) {
        if (e.getCause() != null && e.getCause() instanceof MissingLogDataException) {
            throw new IncrementalBackupNotPossibleException(TOO_OLD_BACKUP, e.getCause());
        }
        if (e.getCause() != null && e.getCause() instanceof ConnectException) {
            throw new RuntimeException(e.getMessage(), e.getCause());
        }
        throw new RuntimeException("Failed to perform incremental backup.", e);
    } catch (Throwable throwable) {
        throw new RuntimeException("Unexpected error", throwable);
    }
    return new BackupOutcome(handler.getLastSeenTransactionId(), true);
}

Example 9 with MismatchingStoreIdException

use of org.neo4j.kernel.impl.store.MismatchingStoreIdException in project neo4j by neo4j.

the class HighAvailabilityModeSwitcher method switchToSlave.

private void switchToSlave() {
    /*
         * This is purely defensive and should never trigger. There was a race where the switch to slave task would
         * start after this instance was elected master and the task would constantly try to change as slave
         * for itself, never cancelling. This now should not be possible, since we cancel the task and wait for it
         * to complete, all in a single thread executor. However, this is a check worth doing because if this
         * condition slips through via some other code path it can cause trouble.
         */
    if (getServerId(availableMasterId).equals(instanceId)) {
        msgLog.error("I (" + me + ") tried to switch to slave for myself as master (" + availableMasterId + ")");
        return;
    }
    final AtomicLong wait = new AtomicLong();
    final CancellationHandle cancellationHandle = new CancellationHandle();
    startModeSwitching(new Runnable() {

        @Override
        public void run() {
            if (currentTargetState != HighAvailabilityMemberState.TO_SLAVE) {
                // Already switched - this can happen if a second master becomes available while waiting
                return;
            }
            if (cancellationHandle.cancellationRequested()) {
                msgLog.info("Switch to slave cancelled on start.");
                return;
            }
            componentSwitcher.switchToSlave();
            try {
                if (cancellationHandle.cancellationRequested()) {
                    msgLog.info("Switch to slave cancelled before ha communication started.");
                    return;
                }
                haCommunicationLife.shutdown();
                haCommunicationLife = new LifeSupport();
                // it is important for availableMasterId to be re-read on every attempt so that
                // slave switching would not result in an infinite loop with wrong/stale availableMasterId
                URI resultingSlaveHaURI = switchToSlave.switchToSlave(haCommunicationLife, me, availableMasterId, cancellationHandle);
                if (resultingSlaveHaURI == null) {
                    /*
                         * null slave uri means the task was cancelled. The task then must simply terminate and
                         * have no side effects.
                         */
                    msgLog.info("Switch to slave is effectively cancelled");
                } else {
                    slaveHaURI = resultingSlaveHaURI;
                    canAskForElections.set(true);
                }
            } catch (HighAvailabilityStoreFailureException e) {
                userLog.error("UNABLE TO START UP AS SLAVE: %s", e.getMessage());
                msgLog.error("Unable to start up as slave", e);
                clusterMemberAvailability.memberIsUnavailable(SLAVE);
                ClusterClient clusterClient = HighAvailabilityModeSwitcher.this.clusterClient;
                try {
                    // TODO I doubt this actually works
                    clusterClient.leave();
                    clusterClient.stop();
                    haCommunicationLife.shutdown();
                } catch (Throwable t) {
                    msgLog.error("Unable to stop cluster client", t);
                }
                modeSwitcherExecutor.schedule(this, 5, TimeUnit.SECONDS);
            } catch (MismatchingStoreIdException e) {
                // Try again immediately, the place that threw it have already treated the db
                // as branched and so a new attempt will have this slave copy a new store from master.
                run();
            } catch (Throwable t) {
                msgLog.error("Error while trying to switch to slave", t);
                // Try again later
                // Exponential backoff
                wait.set(1 + wait.get() * 2);
                // Wait maximum 5 minutes
                wait.set(Math.min(wait.get(), 5 * 60));
                modeSwitcherFuture = modeSwitcherExecutor.schedule(this, wait.get(), TimeUnit.SECONDS);
                msgLog.info("Attempting to switch to slave in %ds", wait.get());
            }
        }
    }, cancellationHandle);
}