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

Merger: De-parameterize alert messages #46

Merged
merged 1 commit into from
Dec 27, 2012
Merged

Merger: De-parameterize alert messages #46

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
20 changes: 11 additions & 9 deletions merger/src/main/java/com/metamx/druid/merger/coordinator/RemoteTaskRunner.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -211,10 +211,10 @@ public String apply(@Nullable WorkerWrapper input)
} else {
Duration durSinceLastTerminate = new Duration(new DateTime(), lastTerminateTime);
if (durSinceLastTerminate.isLongerThan(config.getMaxScalingDuration())) {
log.makeAlert(
"It has been %d millis since last scheduled termination but nodes remain",
durSinceLastTerminate.getMillis()
).emit();
log.makeAlert("Worker node termination taking too long")
.addData("millisSinceLastTerminate", durSinceLastTerminate.getMillis())
.addData("terminatingCount", currentlyTerminating.size())
.emit();
}

log.info(
Expand Down Expand Up @@ -330,7 +330,9 @@ private void retryTask(
log.info("Registering retry for failed task[%s]", task.getId());

if (retryPolicy.hasExceededRetryThreshold()) {
log.makeAlert("Task [%s] has failed[%d] times, giving up!", task.getId(), retryPolicy.getNumRetries())
log.makeAlert("Task exceeded maximum retry count")
.addData("task", task.getId())
.addData("retryCount", retryPolicy.getNumRetries())
.emit();
return;
}
Expand Down Expand Up @@ -542,10 +544,10 @@ public boolean apply(WorkerWrapper input)
} else {
Duration durSinceLastProvision = new Duration(new DateTime(), lastProvisionTime);
if (durSinceLastProvision.isLongerThan(config.getMaxScalingDuration())) {
log.makeAlert(
"It has been %d millis since last scheduled provision but nodes remain",
durSinceLastProvision.getMillis()
).emit();
log.makeAlert("Worker node provisioning taking too long")
.addData("millisSinceLastProvision", durSinceLastProvision.getMillis())
.addData("provisioningCount", currentlyProvisioning.size())
.emit();
}

log.info(
Expand Down
22 changes: 6 additions & 16 deletions merger/src/main/java/com/metamx/druid/merger/coordinator/exec/TaskConsumer.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,11 +20,9 @@
package com.metamx.druid.merger.coordinator.exec;

import com.google.common.base.Throwables;
import com.google.common.collect.ImmutableMap;
import com.google.common.collect.ImmutableSet;
import com.metamx.common.lifecycle.LifecycleStart;
import com.metamx.common.lifecycle.LifecycleStop;
import com.metamx.common.logger.Logger;
import com.metamx.druid.client.DataSegment;
import com.metamx.druid.merger.common.TaskStatus;
import com.metamx.druid.merger.common.task.Task;
Expand All @@ -35,12 +33,9 @@
import com.metamx.druid.merger.coordinator.TaskRunner;
import com.metamx.druid.merger.coordinator.VersionedTaskWrapper;
import com.metamx.emitter.EmittingLogger;
import com.metamx.emitter.service.AlertEvent;
import com.metamx.emitter.service.ServiceEmitter;
import com.metamx.emitter.service.ServiceMetricEvent;

import java.util.concurrent.ExecutorService;

public class TaskConsumer implements Runnable
{
private final TaskQueue queue;
Expand Down Expand Up @@ -242,17 +237,12 @@ public void notify(final TaskStatus statusFromRunner)
emitter.emit(builder.build("indexer/segment/bytes", bytes));

if (status.isFailure()) {
emitter.emit(
new AlertEvent.Builder().build(
String.format("Failed to index: %s", task.getDataSource()),
ImmutableMap.<String, Object>builder()
.put("task", task.getId())
.put("type", task.getType().toString())
.put("dataSource", task.getDataSource())
.put("interval", task.getInterval())
.build()
)
);
log.makeAlert("Failed to index")
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is probably the only one of these that probably doesn't have to be de-parameterized. It can be nice to know the data source in the subject.

.addData("task", task.getId())
.addData("type", task.getType().toString())
.addData("dataSource", task.getDataSource())
.addData("interval", task.getInterval())
.emit();
}

log.info(
Expand Down