mirror of
https://github.com/samber/awesome-prometheus-alerts.git
synced 2026-06-22 01:17:19 +08:00
feat: adding hadoop jmx exporter (#391)
* adding hadoop exporter * added hadoop rules with jmx exporter * added hadoop rules with jmx exporter * Update rules.yml --------- Co-authored-by: Samuel Berthe <dev@samuel-berthe.fr>
This commit is contained in:
Vicky Wilson Jacob
GitHub
parent
32a097836a
commit
7a8f883df6
2 changed files with 179 additions and 0 deletions
|
|
@ -1405,6 +1405,83 @@ groups:
|
|||
query: 'solr_collections_live_nodes < 2'
|
||||
severity: critical
|
||||
|
||||
- name: Hadoop
|
||||
exporters:
|
||||
- name: hadoop/jmx_exporter
|
||||
slug: jmx_exporter
|
||||
doc_url: https://github.com/prometheus/jmx_exporter
|
||||
rules:
|
||||
# Alert rule for NameNode availability
|
||||
- name: Hadoop Name Node Down
|
||||
query: up{job="hadoop-namenode"} == 0
|
||||
for: 5m
|
||||
severity: critical
|
||||
description: "The Hadoop NameNode service is unavailable."
|
||||
|
||||
# Alert rule for ResourceManager availability
|
||||
- name: Hadoop Resource Manager Down
|
||||
query: up{job="hadoop-resourcemanager"} == 0
|
||||
for: 5m
|
||||
severity: critical
|
||||
description: "The Hadoop ResourceManager service is unavailable."
|
||||
|
||||
# Alert rule for DataNode status
|
||||
- name: Hadoop Data Node Out Of Service
|
||||
query: hadoop_datanode_last_heartbeat == 0
|
||||
for: 10m
|
||||
severity: warning
|
||||
description: "The Hadoop DataNode is not sending heartbeats."
|
||||
|
||||
# Alert rule for low HDFS disk space
|
||||
- name: Hadoop HDFS Disk Space Low
|
||||
query: (hadoop_hdfs_bytes_total - hadoop_hdfs_bytes_used) / hadoop_hdfs_bytes_total < 0.1
|
||||
for: 15m
|
||||
severity: warning
|
||||
description: "Available HDFS disk space is running low."
|
||||
|
||||
# Alert rule for excessive MapReduce task failures
|
||||
- name: Hadoop Map Reduce Task Failures
|
||||
query: hadoop_mapreduce_task_failures_total > 100
|
||||
for: 10m
|
||||
severity: critical
|
||||
description: "There is an unusually high number of MapReduce task failures."
|
||||
|
||||
# Alert rule for high ResourceManager memory usage
|
||||
- name: Hadoop Resource Manager Memory High
|
||||
query: hadoop_resourcemanager_memory_bytes / hadoop_resourcemanager_memory_max_bytes > 0.8
|
||||
for: 15m
|
||||
severity: warning
|
||||
description: "The Hadoop ResourceManager is approaching its memory limit."
|
||||
|
||||
# Alert rule for high YARN container allocation failures
|
||||
- name: Hadoop YARN Container Allocation Failures
|
||||
query: hadoop_yarn_container_allocation_failures_total > 10
|
||||
for: 10m
|
||||
severity: warning
|
||||
description: "There is a significant number of YARN container allocation failures."
|
||||
|
||||
# Alert rule for excessive HBase region server region count
|
||||
- name: Hadoop HBase Region Count High
|
||||
query: hadoop_hbase_region_count > 5000
|
||||
for: 15m
|
||||
severity: warning
|
||||
description: "The HBase cluster has an unusually high number of regions."
|
||||
|
||||
# Alert rule for low HBase region server heap space
|
||||
- name: Hadoop HBase Region Server Heap Low
|
||||
query: hadoop_hbase_region_server_heap_bytes / hadoop_hbase_region_server_max_heap_bytes < 0.2
|
||||
for: 10m
|
||||
severity: critical
|
||||
description: "HBase Region Servers are running low on heap space."
|
||||
|
||||
# Alert rule for high HBase Write Requests latency
|
||||
- name: Hadoop HBase Write Requests Latency High
|
||||
query: hadoop_hbase_write_requests_latency_seconds > 0.5
|
||||
for: 10m
|
||||
severity: warning
|
||||
description: "HBase Write Requests are experiencing high latency."
|
||||
|
||||
|
||||
- name: Reverse proxies and load balancers
|
||||
services:
|
||||
- name: Nginx
|
||||
|
|
|
|||
102
dist/rules/hadoop/hadoop-jmx-exporter.yml
vendored
Normal file
102
dist/rules/hadoop/hadoop-jmx-exporter.yml
vendored
Normal file
|
|
@ -0,0 +1,102 @@
|
|||
groups:
|
||||
- name: HadoopAlerts
|
||||
rules:
|
||||
# Alert rule for NameNode availability
|
||||
- alert: HadoopNameNodeDown
|
||||
expr: up{job="hadoop-namenode"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Hadoop NameNode is down"
|
||||
description: "The Hadoop NameNode service is unavailable."
|
||||
|
||||
# Alert rule for ResourceManager availability
|
||||
- alert: HadoopResourceManagerDown
|
||||
expr: up{job="hadoop-resourcemanager"} == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Hadoop ResourceManager is down"
|
||||
description: "The Hadoop ResourceManager service is unavailable."
|
||||
|
||||
# Alert rule for DataNode status
|
||||
- alert: HadoopDataNodeOutOfService
|
||||
expr: hadoop_datanode_last_heartbeat == 0
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Hadoop DataNode is out of service"
|
||||
description: "The Hadoop DataNode is not sending heartbeats."
|
||||
|
||||
# Alert rule for low HDFS disk space
|
||||
- alert: HadoopHDFSDiskSpaceLow
|
||||
expr: (hadoop_hdfs_bytes_total - hadoop_hdfs_bytes_used) / hadoop_hdfs_bytes_total < 0.1
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Low HDFS Disk Space"
|
||||
description: "Available HDFS disk space is running low."
|
||||
|
||||
# Alert rule for excessive MapReduce task failures
|
||||
- alert: HadoopMapReduceTaskFailures
|
||||
expr: hadoop_mapreduce_task_failures_total > 100
|
||||
for: 10m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Excessive MapReduce Task Failures"
|
||||
description: "There is an unusually high number of MapReduce task failures."
|
||||
|
||||
# Alert rule for high ResourceManager memory usage
|
||||
- alert: HadoopResourceManagerMemoryHigh
|
||||
expr: hadoop_resourcemanager_memory_bytes / hadoop_resourcemanager_memory_max_bytes > 0.8
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "High ResourceManager Memory Usage"
|
||||
description: "The Hadoop ResourceManager is approaching its memory limit."
|
||||
|
||||
# Alert rule for high YARN container allocation failures
|
||||
- alert: HadoopYARNContainerAllocationFailures
|
||||
expr: hadoop_yarn_container_allocation_failures_total > 10
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "High YARN Container Allocation Failures"
|
||||
description: "There is a significant number of YARN container allocation failures."
|
||||
|
||||
# Alert rule for excessive HBase region server region count
|
||||
- alert: HadoopHBaseRegionCountHigh
|
||||
expr: hadoop_hbase_region_count > 5000
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Excessive HBase Region Count"
|
||||
description: "The HBase cluster has an unusually high number of regions."
|
||||
|
||||
# Alert rule for low HBase region server heap space
|
||||
- alert: HadoopHBaseRegionServerHeapLow
|
||||
expr: hadoop_hbase_region_server_heap_bytes / hadoop_hbase_region_server_max_heap_bytes < 0.2
|
||||
for: 10m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Low HBase Region Server Heap Space"
|
||||
description: "HBase Region Servers are running low on heap space."
|
||||
|
||||
# Alert rule for high HBase Write Requests latency
|
||||
- alert: HadoopHBaseWriteRequestsLatencyHigh
|
||||
expr: hadoop_hbase_write_requests_latency_seconds > 0.5
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "High HBase Write Requests Latency"
|
||||
description: "HBase Write Requests are experiencing high latency."
|
||||
Loading…
Reference in a new issue