Skip to content

Commit

Permalink
JMX Metric Insight
Browse files Browse the repository at this point in the history 
Solving  #6131 (JMX Support).
  • Loading branch information
@PeterF778
PeterF778 committed Sep 22, 2022
1 parent 3371d93 commit d496304
Show file tree
Hide file tree
Showing 39 changed files with 3,365 additions and 12 deletions.
29 changes: 17 additions & 12 deletions ...va/io/opentelemetry/instrumentation/javaagent/runtimemetrics/RuntimeMetricsInstaller.java
View file
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@
import io.opentelemetry.instrumentation.runtimemetrics.GarbageCollector;
import io.opentelemetry.instrumentation.runtimemetrics.MemoryPools;
import io.opentelemetry.instrumentation.runtimemetrics.Threads;
import io.opentelemetry.instrumentation.runtimemetrics.jmx.MetricService;
import io.opentelemetry.javaagent.extension.AgentListener;
import io.opentelemetry.sdk.autoconfigure.AutoConfiguredOpenTelemetrySdk;
import io.opentelemetry.sdk.autoconfigure.spi.ConfigProperties;
Expand All @@ -27,21 +28,25 @@ public void afterAgent(AutoConfiguredOpenTelemetrySdk autoConfiguredSdk) {
ConfigProperties config = autoConfiguredSdk.getConfig();

boolean defaultEnabled = config.getBoolean("otel.instrumentation.common.default-enabled", true);
if (!config.getBoolean("otel.instrumentation.runtime-metrics.enabled", defaultEnabled)) {
return;
}
if (config.getBoolean("otel.instrumentation.runtime-metrics.enabled", defaultEnabled)) {

OpenTelemetry openTelemetry = GlobalOpenTelemetry.get();

OpenTelemetry openTelemetry = GlobalOpenTelemetry.get();
BufferPools.registerObservers(openTelemetry);
Classes.registerObservers(openTelemetry);
Cpu.registerObservers(openTelemetry);
MemoryPools.registerObservers(openTelemetry);
Threads.registerObservers(openTelemetry);

BufferPools.registerObservers(openTelemetry);
Classes.registerObservers(openTelemetry);
Cpu.registerObservers(openTelemetry);
MemoryPools.registerObservers(openTelemetry);
Threads.registerObservers(openTelemetry);
if (config.getBoolean(
"otel.instrumentation.runtime-metrics.experimental-metrics.enabled", false)) {
GarbageCollector.registerObservers(openTelemetry);
}
}

if (config.getBoolean(
"otel.instrumentation.runtime-metrics.experimental-metrics.enabled", false)) {
GarbageCollector.registerObservers(openTelemetry);
if (config.getBoolean("otel.jmx.enabled", true)) {
MetricService service = new MetricService(GlobalOpenTelemetry.get(), config);
service.start();
}
}
}
270 changes: 270 additions & 0 deletions instrumentation/runtime-metrics/library/README.md
View file

Large diffs are not rendered by default.

17 changes: 17 additions & 0 deletions instrumentation/runtime-metrics/library/activemq.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
# ActiveMQ Metrics

Here is the list of metrics based on MBeans exposed by ActiveMQ.

| Metric Name | Type | Attributes | Description |
| ---------------- | --------------- | ---------------- | --------------- |
| activemq.ProducerCount | UpDownCounter | destination, broker | The number of producers attached to this destination |
| activemq.ConsumerCount | UpDownCounter | destination, broker | The number of consumers subscribed to this destination |
| activemq.memory.MemoryPercentUsage | Gauge | destination, broker | The percentage of configured memory used |
| activemq.message.QueueSize | UpDownCounter | destination, broker | The current number of messages waiting to be consumed |
| activemq.message.ExpiredCount | Counter | destination, broker | The number of messages not delivered because they expired |
| activemq.message.EnqueueCount | Counter | destination, broker | The number of messages sent to this destination |
| activemq.message.DequeueCount | Counter | destination, broker | The number of messages acknowledged and removed from this destination |
| activemq.message.AverageEnqueueTime | Gauge | destination, broker | The average time a message was held on this destination |
| activemq.connections.CurrentConnectionsCount | UpDownCounter | | The total number of current connections |
| activemq.disc.StorePercentUsage | Gauge | | The percentage of configured disk used for persistent messages |
| activemq.disc.TempPercentUsage | Gauge | | The percentage of configured disk used for non-persistent messages |
4 changes: 4 additions & 0 deletions instrumentation/runtime-metrics/library/build.gradle.kts
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,10 @@ plugins {
}

dependencies {
implementation("org.yaml:snakeyaml:1.30")

compileOnly("io.opentelemetry:opentelemetry-sdk-extension-autoconfigure")

testImplementation("io.opentelemetry:opentelemetry-sdk-metrics")
testImplementation(project(":testing-common"))
}
15 changes: 15 additions & 0 deletions instrumentation/runtime-metrics/library/hadoop.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
# Hadoop Metrics

Here is the list of metrics based on MBeans exposed by Hadoop.

| Metric Name | Type | Attributes | Description |
|-----------------------------------|---------------|------------------|-------------------------------------------------------|
| hadoop.capacity.CapacityUsed | UpDownCounter | node_name | Current used capacity across all data nodes |
| hadoop.capacity.CapacityTotal | UpDownCounter | node_name | Current raw capacity of data nodes |
| hadoop.block.BlocksTotal | UpDownCounter | node_name | Current number of allocated blocks in the system |
| hadoop.block.MissingBlocks | UpDownCounter | node_name | Current number of missing blocks |
| hadoop.block.CorruptBlocks | UpDownCounter | node_name | Current number of blocks with corrupt replicas |
| hadoop.volume.VolumeFailuresTotal | UpDownCounter | node_name | Total number of volume failures across all data nodes |
| hadoop.file.FilesTotal | UpDownCounter | node_name | Current number of files and directories |
| hadoop.file.TotalLoad | UpDownCounter | node_name | Current number of connection |
| hadoop.datanode.Count | UpDownCounter | node_name, state | The Number of data nodes |
16 changes: 16 additions & 0 deletions instrumentation/runtime-metrics/library/jetty.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
# Jetty Metrics

Here is the list of metrics based on MBeans exposed by Jetty.

| Metric Name | Type | Attributes | Description |
|--------------------------------|---------------|--------------|------------------------------------------------------|
| jetty.session.sessionsCreated | Counter | resource | The number of sessions established in total |
| jetty.session.sessionTimeTotal | UpDownCounter | resource | The total time sessions have been active |
| jetty.session.sessionTimeMax | UpDownCounter | resource | The maximum amount of time a session has been active |
| jetty.session.sessionTimeMean | Gauge | resource | The mean time sessions remain active |
| jetty.threads.busyThreads | UpDownCounter | | The current number of busy threads |
| jetty.threads.idleThreads | UpDownCounter | | The current number of idle threads |
| jetty.threads.maxThreads | UpDownCounter | | The maximum number of threads in the pool |
| jetty.threads.queueSize | UpDownCounter | | The current number of threads in the queue |
| jetty.io.selectCount | Counter | resource, id | The number of select calls |
| jetty.logging.LoggerCount | UpDownCounter | | The number of registered loggers by name |
32 changes: 32 additions & 0 deletions instrumentation/runtime-metrics/library/kafka-broker.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,32 @@
# Kafka Broker Metrics

Here is the list of metrics based on MBeans exposed by Kafka broker. <br /><br />
Broker metrics:

| Metric Name | Type | Attributes | Description |
|------------------------------------|---------------|------------|----------------------------------------------------------------------|
| kafka.message.count | Counter | | The number of messages received by the broker |
| kafka.request.count | Counter | type | The number of requests received by the broker |
| kafka.request.failed | Counter | type | The number of requests to the broker resulting in a failure |
| kafka.request.time.total | Counter | type | The total time the broker has taken to service requests |
| kafka.request.time.50p | Gauge | type | The 50th percentile time the broker has taken to service requests |
| kafka.request.time.99p | Gauge | type | The 99th percentile time the broker has taken to service requests |
| kafka.request.queue | UpDownCounter | | Size of the request queue |
| kafka.network.io | Counter | direction | The bytes received or sent by the broker |
| kafka.purgatory.size | UpDownCounter | type | The number of requests waiting in purgatory |
| kafka.partition.count | UpDownCounter | | The number of partitions on the broker |
| kafka.partition.offline | UpDownCounter | | The number of partitions offline |
| kafka.partition.underReplicated | UpDownCounter | | The number of under replicated partitions |
| kafka.isr.operation.count | UpDownCounter | operation | The number of in-sync replica shrink and expand operations |
| kafka.lag.max | Counter | | The max lag in messages between follower and leader replicas |
| kafka.controller.active.count | UpDownCounter | | The number of controllers active on the broker |
| kafka.leaderElection.count | Counter | | The leader election count |
| kafka.leaderElection.unclean.count | Counter | | Unclean leader election count - increasing indicates broker failures |
<br />
Log metrics:

| Metric Name | Type | Attributes | Description |
|---------------------------|---------|------------|----------------------------------|
| kafka.logs.flush.count | Counter | | Log flush count |
| kafka.logs.flush.time.50p | Gauge | | Log flush time - 50th percentile |
| kafka.logs.flush.time.99p | Gauge | | Log flush time - 99th percentile |
28 changes: 28 additions & 0 deletions instrumentation/runtime-metrics/library/kafka-consumer.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
# Kafka Consumer Metrics

Here is the list of metrics based on MBeans exposed by Kafka consumer. <br /><br />

Consumer metrics:

| Metric Name | Type | Attributes | Description |
|---------------------------------------------------|-------|------------------|--------------------------------------------------------------------------------|
| kafka.consumer.all.rebalance-latency-avg | Gauge | client-id | The average time taken for a group to complete a successful rebalance |
| kafka.consumer.all.rebalance-latency-max | Gauge | client-id | The maximum time taken for a group to complete a successful rebalance |
| kafka.consumer.all.rebalance-latency-total | Gauge | client-id | The total time this consumer has spent in successful rebalances since creation |
| kafka.consumer.all.rebalance-rate-per-hour | Gauge | client-id | The number of successful rebalance events per hour |
| kafka.consumer.all.rebalance-total | Gauge | client-id | The total number of successful rebalance events |
| kafka.consumer.all.last-rebalance-seconds-ago | Gauge | client-id | Number of seconds since the last rebalance event |
| kafka.consumer.all.failed-rebalance-rate-per-hour | Gauge | client-id | Number of failed rebalance events per hour |
| kafka.consumer.all.failed-rebalance-total | Gauge | client-id | Total number of failed rebalance events |
| kafka.consumer.all.commit-latency-avg | Gauge | client-id | The average time taken for a commit request |
| kafka.consumer.all.commit-rate | Gauge | client-id | The number of commit calls per second |
| kafka.consumer.all.fetch-rate | Gauge | client-id | The number of fetch requests for all topics per second |
| kafka.consumer.all.fetch-size-avg | Gauge | client-id | The average number of bytes fetched per request for all topics |
| kafka.consumer.all.fetch-latency-avg | Gauge | client-id | The average time taken for a fetch request |
| kafka.consumer.all.fetch-throttle-time-avg | Gauge | client-id | The average throttle time |
| kafka.consumer.all.records-lag-max | Gauge | client-id | Number of messages the consumer lags behind the producer |
| kafka.consumer.all.records-consumed-rate | Gauge | client-id | The average number of records consumed for all topics per second |
| kafka.consumer.all.bytes-consumed-rate | Gauge | client-id | The average number of bytes consumed for all topics per second |
| kafka.consumer.bytes-consumed-rate | Gauge | client-id, topic | The average number of bytes consumed per second |
| kafka.consumer.fetch-size-avg | Gauge | client-id, topic | The average number of bytes fetched per request |
| kafka.consumer.records-consumed-rate | Gauge | client-id, topic | The average number of records consumed per second |
24 changes: 24 additions & 0 deletions instrumentation/runtime-metrics/library/kafka-producer.md
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
# Kafka Producer Metrics

Here is the list of metrics based on MBeans exposed by Kafka producer. <br /><br />

Producer metrics:

| Metric Name | Type | Attributes | Description |
|----------------------------------------------|-------|------------------|--------------------------------------------------------------------------------------|
| kafka.producer.all.batch-size-avg | Gauge | client-id | Average number of bytes sent per partition per request |
| kafka.producer.all.bufferpool-wait-ratio | Gauge | client-id | The fraction of time an appender waits for space allocation |
| kafka.producer.all.compression-rate-avg | Gauge | client-id | Average ratio of the compressed batch size to the uncompressed size |
| kafka.producer.all.io-wait-time-ns-avg | Gauge | client-id | The average time the I/O thread spent waiting for a socket ready for reads or writes |
| kafka.producer.all.outgoing-byte-rate | Gauge | client-id | The average number of outgoing bytes sent per second to all servers |
| kafka.producer.all.produce-throttle-time-avg | Gauge | client-id | Average time a request was throttled by a broker |
| kafka.producer.all.record-queue-time-avg | Gauge | client-id | The average time record batches spent in the send buffer |
| kafka.producer.all.record-retry-rate | Gauge | client-id | The average number of retried record sends per second |
| kafka.producer.all.request-latency-avg | Gauge | client-id | The average request latency |
| kafka.producer.all.request-rate | Gauge | client-id | The average number of requests sent per second |
| kafka.producer.all.response-rate | Gauge | client-id | The average number of response sent per second |
| kafka.producer.byte-rate | Gauge | client-id, topic | The average number of bytes sent per second for a topic |
| kafka.producer.compression-rate | Gauge | client-id, topic | The average compression rate of record batches for a topic |
| kafka.producer.record-error-rate | Gauge | client-id, topic | The average per-second number of record sends that resulted in errors for a topic |
| kafka.producer.record-retry-rate | Gauge | client-id, topic | The average per-second number of retried record sends for a topic |
| kafka.producer.record-send-rate | Gauge | client-id, topic | The average number of records sent per second for a topic |
53 changes: 53 additions & 0 deletions ...rary/src/main/java/io/opentelemetry/instrumentation/runtimemetrics/jmx/AttributeInfo.java
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,53 @@
/*
* Copyright The OpenTelemetry Authors
* SPDX-License-Identifier: Apache-2.0
*/

package io.opentelemetry.instrumentation.runtimemetrics.jmx;

/**
* A class holding relevant information about an MBean atribute which will be used for collecting
* metric values. The info comes directly from the relevant MBeans.
*/
class AttributeInfo {

private boolean usesDoubles;
private String description;

AttributeInfo(Number sampleValue, String description) {
if (sampleValue instanceof Byte
|| sampleValue instanceof Short
|| sampleValue instanceof Integer
|| sampleValue instanceof Long) {
// will use Long values
usesDoubles = false;
} else {
usesDoubles = true;
}
this.description = description;
}

boolean usesDoubleValues() {
return usesDoubles;
}

String getDescription() {
return description;
}

/**
* It is unlikely, but possible, that among the MBeans matching some ObjectName pattern,
* attributes with the same name but different types exist. In such cases we have to use a metric
* type which will be able to handle all of these attributes.
*
* @param other another AttributeInfo apparently for the same MBean attribute, must not be null
*/
void updateFrom(AttributeInfo other) {
if (other.usesDoubleValues()) {
usesDoubles = true;
}
if (description == null) {
description = other.getDescription();
}
}
}
Loading

0 comments on commit d496304

Please sign in to comment.