Skip to content
Merged
Show file tree
Hide file tree
Changes from 4 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 @@ -51,7 +51,7 @@ public final class RouterMetrics {
private MutableGaugeInt numAppsFailedRetrieved;
@Metric("# of multiple applications reports failed to be retrieved")
private MutableGaugeInt numMultipleAppsFailedRetrieved;
@Metric("# of applicationAttempt reports failed to be retrieved")
@Metric("# of getApplicationAttempts failed to be retrieved")
private MutableGaugeInt numAppAttemptsFailedRetrieved;
@Metric("# of getClusterMetrics failed to be retrieved")
private MutableGaugeInt numGetClusterMetricsFailedRetrieved;
Expand All @@ -63,6 +63,12 @@ public final class RouterMetrics {
private MutableGaugeInt numGetLabelsToNodesFailedRetrieved;
@Metric("# of getClusterNodeLabels failed to be retrieved")
private MutableGaugeInt numGetClusterNodeLabelsFailedRetrieved;
@Metric("# of getApplicationAttemptReports failed to be retrieved")
private MutableGaugeInt numAppAttemptReportFailedRetrieved;
@Metric("# of getQueueUserAcls failed to be retrieved")
private MutableGaugeInt numGetQueueUserAclsFailedRetrieved;
@Metric("# of getContainerReport failed to be retrieved")
private MutableGaugeInt numGetContainerReportFailedRetrieved;

// Aggregate metrics are shared, and don't have to be looked up per call
@Metric("Total number of successful Submitted apps and latency(ms)")
Expand Down Expand Up @@ -90,6 +96,12 @@ public final class RouterMetrics {
private MutableRate totalSucceededGetLabelsToNodesRetrieved;
@Metric("Total number of successful Retrieved getClusterNodeLabels and latency(ms)")
private MutableRate totalSucceededGetClusterNodeLabelsRetrieved;
@Metric("Total number of successful Retrieved getApplicationAttemptReport and latency(ms)")
private MutableRate totalSucceededAppAttemptReportRetrieved;
@Metric("Total number of successful Retrieved getQueueUserAcls and latency(ms)")
private MutableRate totalSucceededGetQueueUserAclsRetrieved;
@Metric("Total number of successful Retrieved getContainerReport and latency(ms)")
private MutableRate totalSucceededGetContainerReportRetrieved;

/**
* Provide quantile counters for all latencies.
Expand All @@ -105,6 +117,9 @@ public final class RouterMetrics {
private MutableQuantiles getNodeToLabelsLatency;
private MutableQuantiles getLabelToNodesLatency;
private MutableQuantiles getClusterNodeLabelsLatency;
private MutableQuantiles getApplicationAttemptsLatency;
private MutableQuantiles getQueueUserAclsLatency;
private MutableQuantiles getContainerReportLatency;

private static volatile RouterMetrics INSTANCE = null;
private static MetricsRegistry registry;
Expand Down Expand Up @@ -147,6 +162,18 @@ private RouterMetrics() {
getClusterNodeLabelsLatency =
registry.newQuantiles("getClusterNodeLabelsLatency",
"latency of get cluster node labels", "ops", "latency", 10);

getApplicationAttemptsLatency =
registry.newQuantiles("getApplicationAttemptsLatency",
"latency of get application attempts", "ops", "latency", 10);

getQueueUserAclsLatency =
registry.newQuantiles("getQueueUserAclsLatency",
"latency of get queue user acls", "ops", "latency", 10);

getContainerReportLatency =
registry.newQuantiles("getContainerReportLatency",
"latency of get container report", "ops", "latency", 10);
}

public static RouterMetrics getMetrics() {
Expand Down Expand Up @@ -223,6 +250,21 @@ public long getNumSucceededGetClusterNodeLabelsRetrieved(){
return totalSucceededGetClusterNodeLabelsRetrieved.lastStat().numSamples();
}

@VisibleForTesting
public long getNumSucceededAppAttemptReportRetrieved(){
return totalSucceededAppAttemptReportRetrieved.lastStat().numSamples();
}

@VisibleForTesting
public long getNumSucceededGetQueueUserAclsRetrieved(){
Comment thread
goiri marked this conversation as resolved.
return totalSucceededGetQueueUserAclsRetrieved.lastStat().numSamples();
}

@VisibleForTesting
public long getNumSucceededGetContainerReportRetrieved(){
return totalSucceededGetContainerReportRetrieved.lastStat().numSamples();
}

@VisibleForTesting
public double getLatencySucceededAppsCreated() {
return totalSucceededAppsCreated.lastStat().mean();
Expand All @@ -240,7 +282,7 @@ public double getLatencySucceededAppsKilled() {

@VisibleForTesting
public double getLatencySucceededGetAppAttemptReport() {
return totalSucceededAppAttemptsRetrieved.lastStat().mean();
return totalSucceededAppAttemptReportRetrieved.lastStat().mean();
}

@VisibleForTesting
Expand Down Expand Up @@ -278,6 +320,21 @@ public double getLatencySucceededGetClusterNodeLabelsRetrieved() {
return totalSucceededGetClusterNodeLabelsRetrieved.lastStat().mean();
}

@VisibleForTesting
public double getLatencySucceededAppAttemptReportRetrieved() {
return totalSucceededAppAttemptReportRetrieved.lastStat().mean();
}

@VisibleForTesting
public double getLatencySucceededGetQueueUserAclsRetrieved() {
return totalSucceededGetQueueUserAclsRetrieved.lastStat().mean();
}

@VisibleForTesting
public double getLatencySucceededGetContainerReportRetrieved() {
return totalSucceededGetContainerReportRetrieved.lastStat().mean();
}

@VisibleForTesting
public int getAppsFailedCreated() {
return numAppsFailedCreated.value();
Expand Down Expand Up @@ -333,6 +390,21 @@ public int getGetClusterNodeLabelsFailedRetrieved() {
return numGetClusterNodeLabelsFailedRetrieved.value();
}

@VisibleForTesting
public int getAppAttemptReportFailedRetrieved() {
return numAppAttemptReportFailedRetrieved.value();
}

@VisibleForTesting
public int getNumGetQueueUserAclsFailedRetrieved() {
return numGetQueueUserAclsFailedRetrieved.value();
}

@VisibleForTesting
public int getNumGetContainerReportFailedRetrieved() {
return numGetContainerReportFailedRetrieved.value();
}

public void succeededAppsCreated(long duration) {
totalSucceededAppsCreated.add(duration);
getNewApplicationLatency.add(duration);
Expand Down Expand Up @@ -360,7 +432,7 @@ public void succeededMultipleAppsRetrieved(long duration) {

public void succeededAppAttemptsRetrieved(long duration) {
totalSucceededAppAttemptsRetrieved.add(duration);
getApplicationAttemptReportLatency.add(duration);
getApplicationAttemptsLatency.add(duration);
}

public void succeededGetClusterMetricsRetrieved(long duration) {
Expand Down Expand Up @@ -388,6 +460,21 @@ public void succeededGetClusterNodeLabelsRetrieved(long duration) {
getClusterNodeLabelsLatency.add(duration);
}

public void succeededAppAttemptReportRetrieved(long duration) {
totalSucceededAppAttemptReportRetrieved.add(duration);
getApplicationAttemptReportLatency.add(duration);
}

public void succeededGetQueueUserAclsRetrieved(long duration) {
totalSucceededGetQueueUserAclsRetrieved.add(duration);
getQueueUserAclsLatency.add(duration);
}

public void succeededGetContainerReportRetrieved(long duration) {
totalSucceededGetContainerReportRetrieved.add(duration);
getContainerReportLatency.add(duration);
}

public void incrAppsFailedCreated() {
numAppsFailedCreated.incr();
}
Expand Down Expand Up @@ -431,4 +518,16 @@ public void incrLabelsToNodesFailedRetrieved() {
public void incrClusterNodeLabelsFailedRetrieved() {
numGetClusterNodeLabelsFailedRetrieved.incr();
}

public void incrAppAttemptReportFailedRetrieved() {
numAppAttemptReportFailedRetrieved.incr();
}

public void incrGetQueueUserAclsFailedRetrieved() {
numGetQueueUserAclsFailedRetrieved.incr();
}

public void incrGetContainerReportFailedRetrieved() {
numGetContainerReportFailedRetrieved.incr();
}
}
Loading