Skip to content
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

STORM-4154 - fix: Nimbus downtime during topology deployment #3833

Merged
merged 2 commits into from
Jan 14, 2025
Merged

STORM-4154 - fix: Nimbus downtime during topology deployment #3833

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2602253
fix: Nimbus downtime during topology deployment
DiogoP98 Jan 13, 2025
bdc3a13
add tests for method
DiogoP98 Jan 13, 2025
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
14 changes: 8 additions & 6 deletions storm-server/src/main/java/org/apache/storm/daemon/nimbus/Nimbus.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -308,7 +308,7 @@ public static List<ACL> getNimbusAcls(Map<String, Object> conf) {
NIMBUS_SUBJECT.getPrincipals().add(new NimbusPrincipal());
NIMBUS_SUBJECT.setReadOnly();
}

private static final TopologyStateTransition NOOP_TRANSITION = (arg, nimbus, topoId, base) -> null;
private static final TopologyStateTransition INACTIVE_TRANSITION = (arg, nimbus, topoId, base) -> Nimbus.make(TopologyStatus.INACTIVE);
private static final TopologyStateTransition ACTIVE_TRANSITION = (arg, nimbus, topoId, base) -> Nimbus.make(TopologyStatus.ACTIVE);
Expand Down Expand Up @@ -3218,7 +3218,7 @@ private CommonTopoInfo getCommonTopoInfo(String topoId, String operation) throws
ret.allComponents = new HashSet<>(ret.taskToComponent.values());
return ret;
}

@VisibleForTesting
public boolean awaitLeadership(long timeout, TimeUnit timeUnit) throws InterruptedException {
return leaderElector.awaitLeadership(timeout, timeUnit);
Expand Down Expand Up @@ -4109,6 +4109,8 @@ public void createStateInZookeeper(String key) throws TException {
state.setupBlob(key, ni, getVersionForKey(key, ni, zkClient));
}
LOG.debug("Created state in zookeeper {} {} {}", state, store, ni);
} catch (KeyNotFoundException e) {
LOG.warn("Key not found while creating state in zookeeper - key: " + key, e);
} catch (Exception e) {
LOG.warn("Exception while creating state in zookeeper - key: " + key, e);
if (e instanceof TException) {
Expand Down Expand Up @@ -5313,7 +5315,7 @@ private static class CommonTopoInfo {
private static class ClusterSummaryMetrics implements MetricSet {
private static final String SUMMARY = "summary";
private final Map<String, com.codahale.metrics.Metric> metrics = new HashMap<>();

public com.codahale.metrics.Metric put(String key, com.codahale.metrics.Metric value) {
return metrics.put(MetricRegistry.name(SUMMARY, key), value);
}
Expand All @@ -5323,12 +5325,12 @@ public Map<String, com.codahale.metrics.Metric> getMetrics() {
return metrics;
}
}

private class ClusterSummaryMetricSet implements Runnable {
private static final int CACHING_WINDOW = 5;

private final ClusterSummaryMetrics clusterSummaryMetrics = new ClusterSummaryMetrics();

private final Function<String, Histogram> registerHistogram = (name) -> {
//This histogram reflects the data distribution across only one ClusterSummary, i.e.,
// data distribution across all entities of a type (e.g., data from all nimbus/topologies) at one moment.
Expand Down