Skip to content

Wait for blackholed connection before discovery #44077

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jul 9, 2019
Merged

Wait for blackholed connection before discovery #44077

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4952735
Wait for blackholed connection before discovery
DaveCTurner Jul 8, 2019
ce20f05
Merge branch 'master' into 2019-07-08-more-time-for-discovery-44073
DaveCTurner Jul 9, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 7 additions & 6 deletions server/src/main/java/org/elasticsearch/discovery/HandshakingTransportAddressConnector.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,23 +70,24 @@ public HandshakingTransportAddressConnector(Settings settings, TransportService
@Override
public void connectToRemoteMasterNode(TransportAddress transportAddress, ActionListener<DiscoveryNode> listener) {
transportService.getThreadPool().generic().execute(new AbstractRunnable() {
private final AbstractRunnable thisConnectionAttempt = this;

@Override
protected void doRun() {

// TODO if transportService is already connected to this address then skip the handshaking

final DiscoveryNode targetNode = new DiscoveryNode("", transportAddress.toString(),
UUIDs.randomBase64UUID(Randomness.get()), // generated deterministically for reproducible tests
transportAddress.address().getHostString(), transportAddress.getAddress(), transportAddress, emptyMap(),
emptySet(), Version.CURRENT.minimumCompatibilityVersion());

logger.trace("[{}] opening probe connection", this);
logger.trace("[{}] opening probe connection", thisConnectionAttempt);
transportService.openConnection(targetNode,
ConnectionProfile.buildSingleChannelProfile(Type.REG, probeConnectTimeout, probeHandshakeTimeout,
TimeValue.MINUS_ONE, null), new ActionListener<>() {
@Override
public void onResponse(Connection connection) {
logger.trace("[{}] opened probe connection", this);
logger.trace("[{}] opened probe connection", thisConnectionAttempt);

// use NotifyOnceListener to make sure the following line does not result in onFailure being called when
// the connection is closed in the onResponse handler
Expand All @@ -96,7 +97,7 @@ public void onResponse(Connection connection) {
protected void innerOnResponse(DiscoveryNode remoteNode) {
try {
// success means (amongst other things) that the cluster names match
logger.trace("[{}] handshake successful: {}", this, remoteNode);
logger.trace("[{}] handshake successful: {}", thisConnectionAttempt, remoteNode);
IOUtils.closeWhileHandlingException(connection);

if (remoteNode.equals(transportService.getLocalNode())) {
Expand All @@ -109,7 +110,7 @@ protected void innerOnResponse(DiscoveryNode remoteNode) {
transportService.connectToNode(remoteNode, new ActionListener<Void>() {
@Override
public void onResponse(Void ignored) {
logger.trace("[{}] full connection successful: {}", this, remoteNode);
logger.trace("[{}] full connection successful: {}", thisConnectionAttempt, remoteNode);
listener.onResponse(remoteNode);
}

Expand All @@ -129,7 +130,7 @@ protected void innerOnFailure(Exception e) {
// we opened a connection and successfully performed a low-level handshake, so we were definitely
// talking to an Elasticsearch node, but the high-level handshake failed indicating some kind of
// mismatched configurations (e.g. cluster name) that the user should address
logger.warn(new ParameterizedMessage("handshake failed for [{}]", this), e);
logger.warn(new ParameterizedMessage("handshake failed for [{}]", thisConnectionAttempt), e);
IOUtils.closeWhileHandlingException(connection);
listener.onFailure(e);
}
Expand Down
4 changes: 3 additions & 1 deletion ...ork/src/main/java/org/elasticsearch/cluster/coordination/AbstractCoordinatorTestCase.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -121,6 +121,7 @@
import static org.elasticsearch.gateway.GatewayService.STATE_NOT_RECOVERED_BLOCK;
import static org.elasticsearch.node.Node.NODE_NAME_SETTING;
import static org.elasticsearch.transport.TransportService.NOOP_TRANSPORT_INTERCEPTOR;
import static org.elasticsearch.transport.TransportSettings.CONNECT_TIMEOUT;
import static org.hamcrest.Matchers.empty;
import static org.hamcrest.Matchers.equalTo;
import static org.hamcrest.Matchers.greaterThan;
Expand Down Expand Up @@ -556,7 +557,8 @@ void bootstrapIfNecessary() {
if (clusterNodes.stream().allMatch(ClusterNode::isNotUsefullyBootstrapped)) {
assertThat("setting initial configuration may fail with disconnected nodes", disconnectedNodes, empty());
assertThat("setting initial configuration may fail with blackholed nodes", blackholedNodes, empty());
runFor(defaultMillis(DISCOVERY_FIND_PEERS_INTERVAL_SETTING) * 2, "discovery prior to setting initial configuration");
runFor(defaultMillis(CONNECT_TIMEOUT) + // may be in a prior connection attempt which has been blackholed
defaultMillis(DISCOVERY_FIND_PEERS_INTERVAL_SETTING) * 2, "discovery prior to setting initial configuration");
final ClusterNode bootstrapNode = getAnyBootstrappableNode();
bootstrapNode.applyInitialConfiguration();
} else {
Expand Down