Examples with BadVersionException org.apache.zookeeper.KeeperException.BadVersionException used on opensource projects

Example 1 with BadVersionException

use of org.apache.zookeeper.KeeperException.BadVersionException in project accumulo by apache.

the class ZooReaderWriterTest method testMutateWithBadVersion.

@Test
public void testMutateWithBadVersion() throws Exception {
    final String path = "/foo";
    final byte[] value = new byte[] { 0 };
    final List<ACL> acls = Collections.emptyList();
    final byte[] mutatedBytes = new byte[] { 1 };
    Mutator mutator = new Mutator() {

        @Override
        public byte[] mutate(byte[] currentValue) throws Exception {
            return mutatedBytes;
        }
    };
    Method getDataMethod = ZooReaderWriter.class.getMethod("getData", String.class, boolean.class, Stat.class);
    zrw = EasyMock.createMockBuilder(ZooReaderWriter.class).addMockedMethods("getRetryFactory", "getZooKeeper").addMockedMethod(getDataMethod).createMock();
    EasyMock.expect(zrw.getRetryFactory()).andReturn(retryFactory).anyTimes();
    EasyMock.expect(zrw.getZooKeeper()).andReturn(zk).anyTimes();
    Stat stat = new Stat();
    zk.create(path, value, acls, CreateMode.PERSISTENT);
    EasyMock.expectLastCall().andThrow(new NodeExistsException()).once();
    EasyMock.expect(zrw.getData(path, false, stat)).andReturn(new byte[] { 3 }).times(2);
    // BadVersionException should retry
    EasyMock.expect(zk.setData(path, mutatedBytes, 0)).andThrow(new BadVersionException());
    // Let 2nd setData succeed
    EasyMock.expect(zk.setData(path, mutatedBytes, 0)).andReturn(null);
    EasyMock.replay(zk, zrw, retryFactory, retry);
    Assert.assertArrayEquals(new byte[] { 1 }, zrw.mutate(path, value, acls, mutator));
    EasyMock.verify(zk, zrw, retryFactory, retry);
}

Example 2 with BadVersionException

use of org.apache.zookeeper.KeeperException.BadVersionException in project commons by twitter.

the class ZooKeeperUtilsTest method testMagicVersionNumberAllowsUnconditionalUpdate.

@Test
public void testMagicVersionNumberAllowsUnconditionalUpdate() throws Exception {
    String nodePath = "/foo";
    ZooKeeperClient zkClient = createZkClient();
    zkClient.get().create(nodePath, "init".getBytes(), ZooDefs.Ids.OPEN_ACL_UNSAFE, CreateMode.PERSISTENT);
    Stat initStat = new Stat();
    byte[] initialData = zkClient.get().getData(nodePath, false, initStat);
    assertArrayEquals("init".getBytes(), initialData);
    // bump the version
    Stat rev1Stat = zkClient.get().setData(nodePath, "rev1".getBytes(), initStat.getVersion());
    try {
        zkClient.get().setData(nodePath, "rev2".getBytes(), initStat.getVersion());
        fail("expected correct version to be required");
    } catch (BadVersionException e) {
    // expected
    }
    // expect using the correct version to work
    Stat rev2Stat = zkClient.get().setData(nodePath, "rev2".getBytes(), rev1Stat.getVersion());
    assertNotEqual(ZooKeeperUtils.ANY_VERSION, rev2Stat.getVersion());
    zkClient.get().setData(nodePath, "force-write".getBytes(), ZooKeeperUtils.ANY_VERSION);
    Stat forceWriteStat = new Stat();
    byte[] forceWriteData = zkClient.get().getData(nodePath, false, forceWriteStat);
    assertArrayEquals("force-write".getBytes(), forceWriteData);
    assertTrue(forceWriteStat.getVersion() > rev2Stat.getVersion());
    assertNotEqual(ZooKeeperUtils.ANY_VERSION, forceWriteStat.getVersion());
}

Example 3 with BadVersionException

use of org.apache.zookeeper.KeeperException.BadVersionException in project helios by spotify.

the class ZooKeeperMasterModel method updateDeploymentGroupHosts.

@Override
public void updateDeploymentGroupHosts(final String groupName, final List<String> hosts) throws DeploymentGroupDoesNotExistException {
    log.debug("updating deployment-group hosts: name={}", groupName);
    final ZooKeeperClient client = provider.get("updateDeploymentGroupHosts");
    try {
        final DeploymentGroupStatus status = getDeploymentGroupStatus(groupName);
        if (!allowHostChange(status)) {
            return;
        }
        // statusDeploymentGroupRemovedHosts may not exist for deployment groups created before it was
        // introduced.
        client.ensurePathAndSetData(Paths.statusDeploymentGroupRemovedHosts(groupName), Json.asBytesUnchecked(emptyList()));
        final List<String> curHosts = getHosts(client, Paths.statusDeploymentGroupHosts(groupName));
        final List<String> previouslyRemovedHosts = getHosts(client, Paths.statusDeploymentGroupRemovedHosts(groupName));
        final List<String> removedHosts = removedHosts(curHosts, hosts, previouslyRemovedHosts);
        if (hosts.equals(curHosts) && removedHosts.equals(previouslyRemovedHosts)) {
            return;
        }
        log.info("for deployment-group name={}, curHosts={}, new hosts={}, " + "previouslyRemovedHosts={}, derived removedHosts={}", groupName, curHosts, hosts, previouslyRemovedHosts, removedHosts);
        final List<ZooKeeperOperation> ops = Lists.newArrayList();
        ops.add(set(Paths.statusDeploymentGroupHosts(groupName), Json.asBytes(hosts)));
        ops.add(set(Paths.statusDeploymentGroupRemovedHosts(groupName), Json.asBytes(removedHosts)));
        final Node dgn = client.getNode(Paths.configDeploymentGroup(groupName));
        final Integer deploymentGroupVersion = dgn.getStat().getVersion();
        DeploymentGroup deploymentGroup = Json.read(dgn.getBytes(), DeploymentGroup.class);
        List<Map<String, Object>> events = ImmutableList.of();
        if (deploymentGroup.getJobId() != null && updateOnHostChange(deploymentGroup, status)) {
            deploymentGroup = deploymentGroup.toBuilder().setRollingUpdateReason(HOSTS_CHANGED).build();
            // Fail transaction if the deployment group has been updated elsewhere.
            ops.add(check(Paths.configDeploymentGroup(groupName), deploymentGroupVersion));
            // NOTE: If the DG was removed this set() cause the transaction to fail, because
            // removing the DG removes this node. It's *important* that there's an operation that
            // causes the transaction to fail if the DG was removed or we'll end up with
            // inconsistent state.
            ops.add(set(Paths.configDeploymentGroup(deploymentGroup.getName()), deploymentGroup));
            final RollingUpdateOp op = getInitRollingUpdateOps(deploymentGroup, hosts, removedHosts, client);
            ops.addAll(op.operations());
            events = op.events();
        }
        log.info("starting zookeeper transaction for updateDeploymentGroupHosts on deployment-group: " + "name={} jobId={} operations={}", groupName, deploymentGroup.getJobId(), ops);
        client.transaction(ops);
        emitEvents(deploymentGroupEventTopic, events);
    } catch (BadVersionException e) {
        // some other master beat us in processing this host update. not exceptional.
        // ideally we would check the path in the exception, but curator doesn't provide a path
        // for exceptions thrown as part of a transaction.
        log.info("zookeeper transaction for updateDeploymentGroupHosts on deployment-group was " + "processed by another master: name={}", groupName);
    } catch (NoNodeException e) {
        throw new DeploymentGroupDoesNotExistException(groupName, e);
    } catch (KeeperException | IOException e) {
        throw new HeliosRuntimeException("updating deployment group hosts failed", e);
    }
}

Example 4 with BadVersionException

use of org.apache.zookeeper.KeeperException.BadVersionException in project helios by spotify.

the class ZooKeeperMasterModel method rollingUpdateStep.

@Override
public void rollingUpdateStep() {
    final ZooKeeperClient client = provider.get("rollingUpdateStep");
    final Map<String, VersionedValue<DeploymentGroupTasks>> tasksMap = getDeploymentGroupTasks(client);
    for (final Map.Entry<String, VersionedValue<DeploymentGroupTasks>> entry : tasksMap.entrySet()) {
        final String deploymentGroupName = entry.getKey();
        final VersionedValue<DeploymentGroupTasks> versionedTasks = entry.getValue();
        final DeploymentGroupTasks tasks = versionedTasks.value();
        final int taskIndex = tasks.getTaskIndex();
        log.info("rolling-update step on deployment-group {}. Doing taskIndex {} of {}: {}. ", deploymentGroupName, taskIndex, tasks.getRolloutTasks().size(), tasks.getRolloutTasks().get(taskIndex));
        try {
            final RollingUpdateOpFactory opFactory = new RollingUpdateOpFactory(tasks, DEPLOYMENT_GROUP_EVENT_FACTORY);
            final RolloutTask task = tasks.getRolloutTasks().get(taskIndex);
            final RollingUpdateOp op = processRollingUpdateTask(client, opFactory, task, tasks.getDeploymentGroup());
            if (!op.operations().isEmpty()) {
                final List<ZooKeeperOperation> ops = Lists.newArrayList();
                ops.add(check(Paths.statusDeploymentGroupTasks(deploymentGroupName), versionedTasks.version()));
                ops.addAll(op.operations());
                log.info("rolling-update step on deployment-group: name={}, zookeeper operations={}", deploymentGroupName, ops);
                try {
                    client.transaction(ops);
                    emitEvents(deploymentGroupEventTopic, op.events());
                } catch (BadVersionException e) {
                    // some other master beat us in processing this rolling update step. not exceptional.
                    // ideally we would check the path in the exception, but curator doesn't provide a path
                    // for exceptions thrown as part of a transaction.
                    log.info("rolling-update step on deployment-group was processed by another master" + ": name={}, zookeeper operations={}", deploymentGroupName, ops);
                } catch (KeeperException e) {
                    log.error("rolling-update on deployment-group {} failed. {}", deploymentGroupName, e.getMessage(), e);
                }
            }
        } catch (final Exception e) {
            log.error("error processing rolling update step for {}", deploymentGroupName, e);
        }
    }
}

Example 5 with BadVersionException

use of org.apache.zookeeper.KeeperException.BadVersionException in project Saturn by vipshop.

the class ShardingService method shardingIfNecessary.

/**
 * 如果需要分片且当前节点为主节点, 则作业分片.
 */
public synchronized void shardingIfNecessary() throws JobShuttingDownException {
    if (isShutdown) {
        return;
    }
    GetDataStat getDataStat = null;
    if (getJobNodeStorage().isJobNodeExisted(ShardingNode.NECESSARY)) {
        getDataStat = getNecessaryDataStat();
    }
    // sharding necessary内容为空，或者内容是"0"则返回，否则，需要进行sharding处理
    if (getDataStat == null || SHARDING_UN_NECESSARY.equals(getDataStat.getData())) {
        return;
    }
    // 如果不是leader，则等待leader处理完成（这也是一个死循环，知道满足跳出循环的条件：1. 被shutdown 2. 无须sharding而且不处于processing状态）
    if (blockUntilShardingComplatedIfNotLeader()) {
        return;
    }
    // 如果有作业分片处于running状态则等待（无限期）
    waitingOtherJobCompleted();
    // 建立一个临时节点，标记sharding处理中
    getJobNodeStorage().fillEphemeralJobNode(ShardingNode.PROCESSING, "");
    try {
        // 删除作业下面的所有JobServer的sharding节点
        clearShardingInfo();
        int maxRetryTime = 3;
        int retryCount = 0;
        while (!isShutdown) {
            int version = getDataStat.getVersion();
            // 首先尝试从job/leader/sharding/necessary节点获取，如果失败，会从$SaturnExecutors/sharding/content下面获取
            // key is executor, value is sharding items
            Map<String, List<Integer>> shardingItems = namespaceShardingContentService.getShardContent(jobName, getDataStat.getData());
            try {
                // 所有jobserver的（检查+创建），加上设置sharding necessary内容为0，都是一个事务
                CuratorTransactionFinal curatorTransactionFinal = getJobNodeStorage().getClient().inTransaction().check().forPath("/").and();
                for (Entry<String, List<Integer>> entry : shardingItems.entrySet()) {
                    curatorTransactionFinal.create().forPath(JobNodePath.getNodeFullPath(jobName, ShardingNode.getShardingNode(entry.getKey())), ItemUtils.toItemsString(entry.getValue()).getBytes(StandardCharsets.UTF_8)).and();
                }
                curatorTransactionFinal.setData().withVersion(version).forPath(JobNodePath.getNodeFullPath(jobName, ShardingNode.NECESSARY), SHARDING_UN_NECESSARY.getBytes(StandardCharsets.UTF_8)).and();
                curatorTransactionFinal.commit();
                break;
            } catch (BadVersionException e) {
                LogUtils.warn(log, jobName, "zookeeper bad version exception happens", e);
                if (++retryCount <= maxRetryTime) {
                    LogUtils.info(log, jobName, "bad version because of concurrency, will retry to get shards from sharding/necessary later");
                    // NOSONAR
                    Thread.sleep(200L);
                    getDataStat = getNecessaryDataStat();
                }
            } catch (Exception e) {
                LogUtils.warn(log, jobName, "commit shards failed", e);
                /**
                 * 已知场景：
                 *   异常为NoNodeException，域下作业数量大，业务容器上下线。
                 *   原因是，大量的sharding task导致计算结果有滞后，同时某些server被删除，导致commit失败，报NoNode异常。
                 *
                 * 是否需要重试：
                 *   如果作业一直处于启用状态，necessary最终会被更新正确，这时不需要主动重试。 如果重试，可能导致提前拿到数据，后面再重新拿一次数据，不过也没多大问题。
                 *   如果作业在中途禁用了，那么necessary将不会被更新，这时从necessary拿到的数据是过时的，仍然会commit失败，这时需要从content获取数据来重试。
                 *   如果是其他未知场景导致的commit失败，也是可以尝试从content获取数据来重试。
                 *   所以，为了保险起见，均从content获取数据来重试。
                 */
                if (++retryCount <= maxRetryTime) {
                    LogUtils.info(log, jobName, "unexpected error, will retry to get shards from sharding/content later");
                    // 睡一下，没必要马上重试。减少对zk的压力。
                    // NOSONAR
                    Thread.sleep(500L);
                    /**
                     * 注意：
                     *   data为GET_SHARD_FROM_CONTENT_NODE_FLAG，会从sharding/content下获取数据。
                     *   version使用necessary的version。
                     */
                    getDataStat = new GetDataStat(NamespaceShardingContentService.GET_SHARD_FROM_CONTENT_NODE_FLAG, version);
                }
            }
            if (retryCount > maxRetryTime) {
                LogUtils.warn(log, jobName, "retry time exceed {}, will give up to get shards", maxRetryTime);
                break;
            }
        }
    } catch (Exception e) {
        LogUtils.error(log, jobName, e.getMessage(), e);
    } finally {
        getJobNodeStorage().removeJobNodeIfExisted(ShardingNode.PROCESSING);
    }
}