spark-operator/spark-docker/conf/prometheus.yaml

124 lines
4.4 KiB
YAML

#
# Copyright 2018 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# https://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
---
lowercaseOutputName: true
attrNameSnakeCase: true
rules:
# These come from the application driver if it's a streaming application
# Example: default/streaming.driver.com.example.ClassName.StreamingMetrics.streaming.lastCompletedBatch_schedulingDelay
- pattern: metrics<name=(\S+)\.(\S+)\.driver\.(\S+)\.StreamingMetrics\.streaming\.(\S+)><>Value
name: spark_streaming_driver_$4
labels:
app_namespace: "$1"
app_id: "$2"
# These come from the application driver if it's a structured streaming application
# Example: default/sstreaming.driver.spark.streaming.QueryName.inputRate-total
- pattern: metrics<name=(\S+)\.(\S+)\.driver\.spark\.streaming\.(\S+)\.(\S+)><>Value
name: spark_structured_streaming_driver_$4
labels:
app_namespace: "$1"
app_id: "$2"
query_name: "$3"
# These come from the application executors
# Example: default/spark-pi.0.executor.threadpool.activeTasks
- pattern: metrics<name=(\S+)\.(\S+)\.(\S+)\.executor\.(\S+)><>Value
name: spark_executor_$4
type: GAUGE
labels:
app_namespace: "$1"
app_id: "$2"
executor_id: "$3"
# These come from the application driver
# Example: default/spark-pi.driver.DAGScheduler.stage.failedStages
- pattern: metrics<name=(\S+)\.(\S+)\.driver\.(BlockManager|DAGScheduler|jvm)\.(\S+)><>Value
name: spark_driver_$3_$4
type: GAUGE
labels:
app_namespace: "$1"
app_id: "$2"
# These come from the application driver
# Emulate timers for DAGScheduler like messagePRocessingTime
- pattern: metrics<name=(\S+)\.(\S+)\.driver\.DAGScheduler\.(.*)><>Count
name: spark_driver_DAGScheduler_$3_count
type: COUNTER
labels:
app_namespace: "$1"
app_id: "$2"
# HiveExternalCatalog is of type counter
- pattern: metrics<name=(\S+)\.(\S+)\.driver\.HiveExternalCatalog\.(.*)><>Count
name: spark_driver_HiveExternalCatalog_$3_count
type: COUNTER
labels:
app_namespace: "$1"
app_id: "$2"
# These come from the application driver
# Emulate histograms for CodeGenerator
- pattern: metrics<name=(\S+)\.(\S+)\.driver\.CodeGenerator\.(.*)><>Count
name: spark_driver_CodeGenerator_$3_count
type: COUNTER
labels:
app_namespace: "$1"
app_id: "$2"
# These come from the application driver
# Emulate timer (keep only count attribute) plus counters for LiveListenerBus
- pattern: metrics<name=(\S+)\.(\S+)\.driver\.LiveListenerBus\.(.*)><>Count
name: spark_driver_LiveListenerBus_$3_count
type: COUNTER
labels:
app_namespace: "$1"
app_id: "$2"
# Get Gauge type metrics for LiveListenerBus
- pattern: metrics<name=(\S+)\.(\S+)\.driver\.LiveListenerBus\.(.*)><>Value
name: spark_driver_LiveListenerBus_$3
type: GAUGE
labels:
app_namespace: "$1"
app_id: "$2"
# Executors counters
- pattern: metrics<name=(\S+)\.(\S+)\.(.*)\.executor\.(.*)><>Count
name: spark_executor_$4_count
type: COUNTER
labels:
app_namespace: "$1"
app_id: "$2"
executor_id: "$3"
# These come from the application executors
# Example: app-20160809000059-0000.0.jvm.threadpool.activeTasks
- pattern: metrics<name=(\S+)\.(\S+)\.([0-9]+)\.(jvm|NettyBlockTransfer)\.(.*)><>Value
name: spark_executor_$4_$5
type: GAUGE
labels:
app_namespace: "$1"
app_id: "$2"
executor_id: "$3"
- pattern: metrics<name=(\S+)\.(\S+)\.([0-9]+)\.HiveExternalCatalog\.(.*)><>Count
name: spark_executor_HiveExternalCatalog_$4_count
type: COUNTER
labels:
app_namespace: "$1"
app_id: "$2"
executor_id: "$3"
# These come from the application driver
# Emulate histograms for CodeGenerator
- pattern: metrics<name=(\S+)\.(\S+)\.([0-9]+)\.CodeGenerator\.(.*)><>Count
name: spark_executor_CodeGenerator_$4_count
type: COUNTER
labels:
app_namespace: "$1"
app_id: "$2"
executor_id: "$3"