mirror of
https://github.com/samber/awesome-prometheus-alerts.git
synced 2026-06-26 19:37:27 +08:00
102 lines
No EOL
3.7 KiB
YAML
102 lines
No EOL
3.7 KiB
YAML
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." |