Skip to content

Describe STALE_STATE_CONFIG in ClusterFormationFH #53878

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.

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
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@
import org.elasticsearch.common.transport.TransportAddress;
import org.elasticsearch.common.unit.TimeValue;
import org.elasticsearch.common.util.concurrent.AbstractRunnable;
import org.elasticsearch.gateway.GatewayMetaState;
import org.elasticsearch.threadpool.ThreadPool;
import org.elasticsearch.threadpool.ThreadPool.Names;

Expand Down Expand Up @@ -206,7 +207,12 @@ private String describeQuorum(VotingConfiguration votingConfiguration) {
assert requiredNodes <= realNodeIds.size() : nodeIds;

if (nodeIds.size() == 1) {
return "a node with id " + realNodeIds;
if (nodeIds.contains(GatewayMetaState.STALE_STATE_CONFIG_NODE_ID)) {
return "one or more nodes that have already participated as master-eligible nodes in the cluster but this node was " +
"not master-eligible the last time it joined the cluster";
} else {
return "a node with id " + realNodeIds;
}
} else if (nodeIds.size() == 2) {
return "two nodes with ids " + realNodeIds;
} else {
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -78,6 +78,13 @@
*/
public class GatewayMetaState implements Closeable {

/**
* Fake node ID for a voting configuration written by a master-ineligible data node to indicate that its on-disk state is potentially
* stale (since it is written asynchronously after application, rather than before acceptance). This node ID means that if the node is
* restarted as a master-eligible node then it does not win any elections until it has received a fresh cluster state.
*/
public static final String STALE_STATE_CONFIG_NODE_ID = "STALE_STATE_CONFIG";

// Set by calling start()
private final SetOnce<PersistedState> persistedState = new SetOnce<>();

Expand Down Expand Up @@ -360,7 +367,7 @@ protected void doRun() {
}

static final CoordinationMetaData.VotingConfiguration staleStateConfiguration =
new CoordinationMetaData.VotingConfiguration(Collections.singleton("STALE_STATE_CONFIG"));
new CoordinationMetaData.VotingConfiguration(Collections.singleton(STALE_STATE_CONFIG_NODE_ID));

static ClusterState resetVotingConfiguration(ClusterState clusterState) {
CoordinationMetaData newCoordinationMetaData = CoordinationMetaData.builder(clusterState.coordinationMetaData())
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@
import org.elasticsearch.cluster.node.DiscoveryNodes;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.common.transport.TransportAddress;
import org.elasticsearch.gateway.GatewayMetaState;
import org.elasticsearch.test.ESTestCase;

import java.util.Arrays;
Expand Down Expand Up @@ -395,5 +396,14 @@ public void testDescriptionAfterBootstrapping() {
"have discovered [] which is not a quorum; " +
"discovery will continue using [] from hosts providers and [" + otherMasterNode + ", " + localNode +
"] from last-known cluster state; node term 0, last-accepted version 0 in term 0")));

assertThat(new ClusterFormationState(Settings.EMPTY, state(localNode, GatewayMetaState.STALE_STATE_CONFIG_NODE_ID), emptyList(),
emptyList(), 0L, electionStrategy).getDescription(),
is("master not discovered or elected yet, an election requires one or more nodes that have already participated as " +
"master-eligible nodes in the cluster but this node was not master-eligible the last time it joined the cluster, " +
"have discovered [] which is not a quorum; " +
"discovery will continue using [] from hosts providers and [" + localNode +
"] from last-known cluster state; node term 0, last-accepted version 0 in term 0"));

}
}