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.

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

feat: Spark benchmark observability #693

Merged
merged 3 commits into from
Nov 1, 2024
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 @@ -47,6 +47,19 @@ spec:
# Logging set to WARN
- "true"
sparkConf:
# Expose Spark metrics for Prometheus
"spark.ui.prometheus.enabled": "true"
"spark.executor.processTreeMetrics.enabled": "true"
"spark.metrics.conf.*.sink.prometheusServlet.class": "org.apache.spark.metrics.sink.PrometheusServlet"
"spark.metrics.conf.driver.sink.prometheusServlet.path": "/metrics/driver/prometheus/"
"spark.metrics.conf.executor.sink.prometheusServlet.path": "/metrics/executors/prometheus/"

# Spark Event logs
"spark.eventLog.enabled": "true"
"spark.eventLog.dir": "s3a://<S3_BUCKET>/spark-event-logs"
"spark.eventLog.rolling.enabled": "true"
"spark.eventLog.rolling.maxFileSize": "64m"

"spark.network.timeout": "2000s"
"spark.executor.heartbeatInterval": "300s"
# AQE
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,19 @@ spec:
# Logging set to WARN
- "true"
sparkConf:
# Expose Spark metrics for Prometheus
"spark.ui.prometheus.enabled": "true"
"spark.executor.processTreeMetrics.enabled": "true"
"spark.metrics.conf.*.sink.prometheusServlet.class": "org.apache.spark.metrics.sink.PrometheusServlet"
"spark.metrics.conf.driver.sink.prometheusServlet.path": "/metrics/driver/prometheus/"
"spark.metrics.conf.executor.sink.prometheusServlet.path": "/metrics/executors/prometheus/"

# Spark Event logs
"spark.eventLog.enabled": "true"
"spark.eventLog.dir": "s3a://<S3_BUCKET>/spark-event-logs"
"spark.eventLog.rolling.enabled": "true"
"spark.eventLog.rolling.maxFileSize": "64m"

"spark.network.timeout": "2000s"
"spark.executor.heartbeatInterval": "300s"
# AQE
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,19 @@ spec:
# Logging set to WARN
- "true"
sparkConf:
# Expose Spark metrics for Prometheus
"spark.ui.prometheus.enabled": "true"
"spark.executor.processTreeMetrics.enabled": "true"
"spark.metrics.conf.*.sink.prometheusServlet.class": "org.apache.spark.metrics.sink.PrometheusServlet"
"spark.metrics.conf.driver.sink.prometheusServlet.path": "/metrics/driver/prometheus/"
"spark.metrics.conf.executor.sink.prometheusServlet.path": "/metrics/executors/prometheus/"

# Spark Event logs
"spark.eventLog.enabled": "true"
"spark.eventLog.dir": "s3a://<S3_BUCKET>/spark-event-logs"
"spark.eventLog.rolling.enabled": "true"
"spark.eventLog.rolling.maxFileSize": "64m"

"spark.executorEnv.JAVA_HOME": "/opt/java/openjdk"
"spark.driverEnv.JAVA_HOME": "/opt/java/openjdk"
"spark.network.timeout": "2000s"
Expand Down
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# Use the official Spark base image with Java 17 and Python 3
FROM apache/spark:3.5.3-scala2.12-java17-python3-ubuntu as tpc-toolkit
FROM apache/spark:3.5.3-scala2.12-java17-python3-ubuntu

# Arguments for version control
ARG HADOOP_VERSION=3.4.1
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -51,6 +51,25 @@ prometheus:
- source_labels: [__meta_kubernetes_endpoint_port_name]
regex: http-metrics
action: keep
# Monitors for Spark Jobs
additionalPodMonitors:
- name: "spark-job-monitoring"
jobLabel: "spark-job-monitoring"
selector:
matchLabels:
spark-role: driver
namespaceSelector:
matchNames:
- spark-team-a
- spark-team-b
- spark-team-c
podMetricsEndpoints:
- port: "spark-ui"
interval: 30s
path: /metrics/driver/prometheus/
- port: "spark-ui"
interval: 30s
path: /metrics/executors/prometheus/

alertmanager:
enabled: false
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,25 @@ prometheus:
- source_labels: [__meta_kubernetes_endpoint_port_name]
regex: http-metrics
action: keep
# Monitors for Spark Jobs
additionalPodMonitors:
- name: "spark-job-monitoring"
jobLabel: "spark-job-monitoring"
selector:
matchLabels:
spark-role: driver
namespaceSelector:
matchNames:
- spark-team-a
- spark-team-b
- spark-team-c
podMetricsEndpoints:
- port: "spark-ui"
interval: 30s
path: /metrics/driver/prometheus/
- port: "spark-ui"
interval: 30s
path: /metrics/executors/prometheus/

alertmanager:
enabled: false
Expand Down
Loading