mirror of
https://github.com/samber/awesome-prometheus-alerts.git
synced 2026-06-26 11:27:00 +08:00
Update rules.yml
This commit is contained in:
Samuel Berthe
GitHub
parent
50232ace9c
commit
d7e969cfd2
1 changed files with 77 additions and 76 deletions
153
_data/rules.yml
153
_data/rules.yml
|
|
@ -1405,6 +1405,83 @@ groups:
|
||||||
query: 'solr_collections_live_nodes < 2'
|
query: 'solr_collections_live_nodes < 2'
|
||||||
severity: critical
|
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
|
- name: Reverse proxies and load balancers
|
||||||
services:
|
services:
|
||||||
- name: Nginx
|
- name: Nginx
|
||||||
|
|
@ -2717,79 +2794,3 @@ groups:
|
||||||
description: UPS load is > 80%
|
description: UPS load is > 80%
|
||||||
query: 'apcupsd_ups_load_percent > 80'
|
query: 'apcupsd_ups_load_percent > 80'
|
||||||
severity: warning
|
severity: warning
|
||||||
|
|
||||||
- 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."
|
|
||||||
Loading…
Reference in a new issue