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

Gemfile.lock

@@ -231,7 +231,7 @@ GEM
       jekyll-seo-tag (~> 2.1)
     minitest (5.15.0)
     multipart-post (2.1.1)
-    nokogiri (1.13.6-x86_64-linux)
+    nokogiri (1.13.9-x86_64-linux)
       racc (~> 1.4)
     octokit (4.22.0)
       faraday (>= 0.9)
@@ -273,6 +273,7 @@ GEM
     zeitwerk (2.5.4)
 
 PLATFORMS
+  x86_64-linux
   x86_64-linux-musl
 
 DEPENDENCIES

README.md

@@ -71,7 +71,8 @@ Collection available here: **[https://awesome-prometheus-alerts.grep.to](https:/
 - [Juniper](https://awesome-prometheus-alerts.grep.to/rules#juniper)
 - [CoreDNS](https://awesome-prometheus-alerts.grep.to/rules#coredns)
 - [FreeSwitch](https://awesome-prometheus-alerts.grep.to/rules#freeswitch)
-- [Hashicorp Vault](https://awesome-prometheus-alerts.grep.to/rules#Hashicorp-Vault)
+- [Hashicorp Vault](https://awesome-prometheus-alerts.grep.to/rules#hashicorp-vault)
+- [Cloudflare](https://awesome-prometheus-alerts.grep.to/rules#cloudflare)
 
 #### Other
 

_data/rules.yml

@@ -186,12 +186,12 @@ groups:
                 for: 2m
               - name: Host out of inodes
                 description: Disk is almost running out of available inodes (< 10% left)
-                query: 'node_filesystem_files_free{mountpoint ="/rootfs"} / node_filesystem_files{mountpoint="/rootfs"} * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly{mountpoint="/rootfs"} == 0'
+                query: 'node_filesystem_files_free / node_filesystem_files * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0'
                 severity: warning
                 for: 2m
               - name: Host inodes will fill in 24 hours
                 description: Filesystem is predicted to run out of inodes within the next 24 hours at current write rate
-                query: 'node_filesystem_files_free{mountpoint ="/rootfs"} / node_filesystem_files{mountpoint="/rootfs"} * 100 < 10 and predict_linear(node_filesystem_files_free{mountpoint="/rootfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly{mountpoint="/rootfs"} == 0'
+                query: 'node_filesystem_files_free / node_filesystem_files * 100 < 10 and predict_linear(node_filesystem_files_free[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly == 0'
                 severity: warning
                 for: 2m
               - name: Host unusual disk read latency
@@ -2190,6 +2190,22 @@ groups:
                 severity: warning
                 for: 5m
 
+      - name: Cloudflare
+        exporters:
+          - name: lablabs/cloudflare-exporter
+            slug: lablabs-cloudflare-exporter
+            doc_url: https://github.com/lablabs/cloudflare-exporter
+            rules:
+              - name: Cloudflare http 4xx error rate
+                description: 'Cloudflare high HTTP 4xx error rate (> 5% for domain {{ $labels.zone }})'
+                query: '(sum by(zone) (rate(cloudflare_zone_requests_status{status=~"^4.."}[15m])) / on (zone) sum by (zone) (rate(cloudflare_zone_requests_status[15m]))) * 100 > 5'
+                severity: warning
+              - name: Cloudflare http 5xx error rate
+                description: 'Cloudflare high HTTP 5xx error rate (> 5% for domain {{ $labels.zone }})'
+                query: '(sum by (zone) (rate(cloudflare_zone_requests_status{status=~"^5.."}[5m])) / on (zone) sum by (zone) (rate(cloudflare_zone_requests_status[5m]))) * 100 > 5'
+                severity: critical
+
+
   - name: Other
     services:
       - name: Thanos

dist/rules/cloudflare/lablabs-cloudflare-exporter.yml

@@ -0,0 +1,23 @@
+groups:
+
+- name: LablabsCloudflareExporter
+
+  rules:
+
+    - alert: CloudflareHttp4xxErrorRate
+      expr: '(sum by(zone) (rate(cloudflare_zone_requests_status{status=~"^4.."}[15m])) / on (zone) sum by (zone) (rate(cloudflare_zone_requests_status[15m]))) * 100 > 5'
+      for: 0m
+      labels:
+        severity: warning
+      annotations:
+        summary: Cloudflare http 4xx error rate (instance {{ $labels.instance }})
+        description: "Cloudflare high HTTP 4xx error rate (> 5% for domain {{ $labels.zone }})\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
+
+    - alert: CloudflareHttp5xxErrorRate
+      expr: '(sum by (zone) (rate(cloudflare_zone_requests_status{status=~"^5.."}[5m])) / on (zone) sum by (zone) (rate(cloudflare_zone_requests_status[5m]))) * 100 > 5'
+      for: 0m
+      labels:
+        severity: critical
+      annotations:
+        summary: Cloudflare http 5xx error rate (instance {{ $labels.instance }})
+        description: "Cloudflare high HTTP 5xx error rate (> 5% for domain {{ $labels.zone }})\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

dist/rules/host-and-hardware/node-exporter.yml

@@ -77,7 +77,7 @@ groups:
         description: "Filesystem is predicted to run out of space within the next 24 hours at current write rate\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: HostOutOfInodes
-      expr: 'node_filesystem_files_free{mountpoint ="/rootfs"} / node_filesystem_files{mountpoint="/rootfs"} * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly{mountpoint="/rootfs"} == 0'
+      expr: 'node_filesystem_files_free / node_filesystem_files * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0'
       for: 2m
       labels:
         severity: warning
@@ -86,7 +86,7 @@ groups:
         description: "Disk is almost running out of available inodes (< 10% left)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
 
     - alert: HostInodesWillFillIn24Hours
-      expr: 'node_filesystem_files_free{mountpoint ="/rootfs"} / node_filesystem_files{mountpoint="/rootfs"} * 100 < 10 and predict_linear(node_filesystem_files_free{mountpoint="/rootfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly{mountpoint="/rootfs"} == 0'
+      expr: 'node_filesystem_files_free / node_filesystem_files * 100 < 10 and predict_linear(node_filesystem_files_free[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly == 0'
       for: 2m
       labels:
         severity: warning