Merge branch 'master' of github.com:samber/awesome-prometheus-alerts

.travis.yml

@@ -0,0 +1,3 @@
+language: node_js
+node_js:
+  - 'node'

README.md

@@ -1,7 +1,7 @@
-# Awesome Prometheus alerting rules [![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/sindresorhus/awesome)
+# Awesome Prometheus alerting rules [![Awesome](https://awesome.re/badge-flat.svg)](https://awesome.re)
 
 <!-- ![Awesome logo](./assets/awesome.png) -->
-<p align="center"> 
+<p align="center">
     <img src="./assets/awesome.png">
 </p>
 
@@ -9,7 +9,12 @@
 
 Collection available here: **[https://awesome-prometheus-alerts.grep.to](https://awesome-prometheus-alerts.grep.to)**
 
-## Content
+## Contents
+
+- [Rules](#rules)
+- [Improvements](#improvements)
+
+## Rules
 
 - [Prometheus](https://awesome-prometheus-alerts.grep.to/rules#prometheus)
 - [Host](https://awesome-prometheus-alerts.grep.to/rules#host)
@@ -41,11 +46,11 @@ Contributions for common alerting rules are most welcome!
 
 [Instructions here](CONTRIBUTING.md)
 
-## Todo
+## Improvements
 
-- Create an alert rule builder in Jekyll for custom alerts (severity, thresholds, instances, ...)
+- Create an alert rule builder in Jekyll for custom alerts (severity, thresholds, instances...)
 
-# License
+## License
 
 [![CC4](https://mirrors.creativecommons.org/presskit/cc.srr.primary.svg)](https://creativecommons.org/licenses/by/4.0/legalcode)
 

_data/rules.yml

@@ -14,27 +14,27 @@ services:
         rules:
           - name: Out of memory
             description: Node memory is filling up (< 10% left)
-            query: '(node_memory_MemFree + node_memory_Cached + node_memory_Buffers) / node_memory_MemTotal * 100 < 10'
+            query: '(node_memory_MemFree_bytes + node_memory_Cached_bytes + node_memory_Buffers_bytes) / node_memory_MemTotal_bytes * 100 < 10'
             severity: warning
           - name: Unusual network throughput in
             description: Host network interfaces are probably receiving too much data (> 100 MB/s)
-            query: 'sum by (instance) (irate(node_network_receive_bytes[2m])) / 1024 / 1024 > 100'
+            query: 'sum by (instance) (irate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100'
             severity: warning
           - name: Unusual network throughput out
             description: Host network interfaces are probably sending too much data (> 100 MB/s)
-            query: 'sum by (instance) (irate(node_network_transmit_bytes[2m])) / 1024 / 1024 > 100'
+            query: 'sum by (instance) (irate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100'
             severity: warning
           - name: Unusual disk read rate
             description: Disk is probably reading too much data (> 50 MB/s)
-            query: 'sum by (instance) (irate(node_disk_bytes_read[2m])) / 1024 / 1024 > 50'
+            query: 'sum by (instance) (irate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50'
             severity: warning
           - name: Unusual disk write rate
             description: Disk is probably writing too much data (> 50 MB/s)
-            query: 'sum by (instance) (irate(node_disk_bytes_written[2m])) / 1024 / 1024 > 50'
+            query: 'sum by (instance) (irate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50'
             severity: warning
           - name: Out of disk space
             description: Disk is almost full (< 10% left)
-            query: 'node_filesystem_free{mountpoint ="/rootfs"} / node_filesystem_size{mountpoint ="/rootfs"} * 100 < 10'
+            query: 'node_filesystem_free_bytes{mountpoint ="/rootfs"} / node_filesystem_size_bytes{mountpoint ="/rootfs"} * 100 < 10'
             severity: warning
           - name: Out of inodes
             description: Disk is almost running out of available inodes (< 10% left)
@@ -42,19 +42,23 @@ services:
             severity: warning
           - name: Unusual disk read latency
             description: Disk latency is growing (read operations > 100ms)
-            query: 'rate(node_disk_read_time_ms[1m]) / rate(node_disk_reads_completed[1m]) > 100'
+            query: 'rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 100'
             severity: warning
           - name: Unusual disk write latency
             description: Disk latency is growing (write operations > 100ms)
-            query: 'rate(node_disk_write_time_ms[1m]) / rate(node_disk_writes_completed[1m]) > 100'
+            query: 'rate(node_disk_write_time_seconds_total[1m]) / rate(node_disk_writes_completed_total[1m]) > 100'
             severity: warning
           - name: CPU load
-            description: CPU load (15m) is high (> 75%)
-            query: 'avg by (instance) (sum by (cpu) (rate(node_cpu{mode!="idle"}[5m]))) * 100 > 75'
+            description: CPU load (15m) is high
+            query: 'node_load15 / (count without (cpu, mode) (node_cpu_seconds_total{mode="system"})) > 2'
             severity: warning
           - name: Context switching
             description: Context switching is growing on node (> 1000 / s)
-            query: 'rate(node_context_switches[5m]) > 1000'
+            query: 'rate(node_context_switches_total[5m]) > 1000'
+            severity: warning
+          - name: Node has swap
+            description: Node has swap
+            query: 'node_memory_SwapTotal_bytes > 0'
             severity: warning
 
   - name: Docker containers

package.json

@@ -0,0 +1,8 @@
+{
+	  "scripts": {
+		    "test": "awesome-lint"
+	  },
+	  "devDependencies": {
+		    "awesome-lint": "*"
+	  }
+}