Merge pull request #223 from sysdiglabs/staging

Staging Y22W23

apps/haproxy.yaml

@@ -7,6 +7,7 @@ keywords:
   - Available
 availableVersions: 
   - '2.1'
+  - '2.3'
 shortDescription: "HAProxy is a free, open source load balancer"
 description: |
   HAProxy is free, open source software that provides a high availability load balancer and proxy server for TCP and HTTP-based applications that spreads requests across multiple servers.

apps/php-fpm.yaml

@@ -0,0 +1,15 @@
+---
+apiVersion: v1
+kind: App
+name: "php-fpm"
+keywords:
+  - PHP
+  - Available
+availableVersions:
+  - '7.2'
+shortDescription: "PHP-FPM (FastCGI Process Manager) is an alternative PHP FastCGI implementation with some additional features useful for sites of any size, especially busier sites."
+description: |
+  PHP-FPM (FastCGI Process Manager) is an alternative PHP FastCGI implementation with some additional features useful for sites of any size, especially busier sites.
+icon: https://raw.githubusercontent.com/sysdiglabs/promcat-resources/master/apps/images/PHP-FPM.svg
+website: https://www.php.net/manual/en/book.fpm.php
+available: true

resources/cassandra/INSTALL.md

@@ -11,7 +11,7 @@ spec:
     spec:
       containers:
       - name: cassandra-exporter
-        image: gcr.io/mateo-burillo-ns/promcat-cassandra-exporter:latest
+        image: quay.io/sysdig/promcat-cassandra-exporter:v0.9.10
         imagePullPolicy: Always
         volumeMounts:
           - mountPath: /var/lib/cassandra

resources/cassandra/include/patch.yaml

@@ -7,7 +7,7 @@ spec:
     spec:
       containers:
       - name: cassandra-exporter
-        image: gcr.io/mateo-burillo-ns/promcat-cassandra-exporter:latest
+        image: quay.io/sysdig/promcat-cassandra-exporter:v0.9.10
         imagePullPolicy: Always
         volumeMounts:
           - mountPath: /var/lib/cassandra

resources/haproxy-ingress/ALERTS.md

@@ -1,21 +1,25 @@
 # Alerts
-## UpTimeLessThan1Hour
-This alert detects when all of the instances of the ingress controller have an uptime of less tha 1 hour.
+## [Haproxy-Ingress] Uptime less than 1 hour
+This alert detects when all of the instances of the ingress controller have an uptime of less than 1 hour.
 
-## FrontendDown
+## [Haproxy-Ingress] Frontend Down
 This alert detects when a frontend has all of its instances down for more than 10 minutes.
 
-## BackendDown
+## [Haproxy-Ingress] Backend Down
 This alert detects when a backend has all of its instances down for more than 10 minutes.
 
-## HighSessionsUsage
+## [Haproxy-Ingress] High Sessions Usage
 This alert triggers when the backend sessions overpass the 85% of the sessions capacity for 10 minutes.
 
-## HigErrorRate
-This alert triggers when the is an error rate over 15% for over 10 minutes in a proxy.
+## [Haproxy-Ingress] High Error Rate
+This alert triggers when there is an error rate over 15% for over 10 minutes in a proxy.
 
-## HighRequestDeniedRate and HighResponseDeniedRate
-These alerts detect when there is a denied rate of requests or responses over 10% for over 10 minutes in a proxy.
+## [Haproxy-Ingress] High Request Denied Rate
+These alerts detect when there is a denied rate of requests over 10% for over 10 minutes in a proxy.
 
-## HighResponseTime
+## [Haproxy-Ingress] High Response Denied Rate
+These alerts detect when there is a denied rate of responses over 10% for over 10 minutes in a proxy.
+
+## [Haproxy-Ingress] High Response Rate
 This alert triggers when a proxy has a mean response time higher than 250ms for over 10 minutes.
+

resources/haproxy-ingress/INSTALLv2.3.md

@@ -0,0 +1,32 @@
+# Adding HAProxy Ingress 
+To install the HAProxy, you can use the [official Helm chart](https://github.com/haproxytech/helm-charts):
+```sh
+helm repo add haproxytech https://haproxytech.github.io/helm-charts
+helm repo update
+```
+
+# Install k8s HAProxy ingress controller and configuring Prometheus metrics
+This command will install haproxy-ingress helm chart with prometheus metrics and haproxy stats enabled
+```
+helm install haproxy-ingress haproxy-ingress/haproxy-ingress \
+--set-string "controller.stats.enabled = true" \
+--set-string "controller.metrics.enabled = true"
+```
+
+Metrics will be exposed via 9101 port and /metrics path
+
+# Pod and metrics check
+
+To get the pods of the ingress:
+```
+kubectl get pods -l app.kubernetes.io/instance=haproxy-ingress -n haproxy-ingress
+```
+Port forward 9101 to your localhost
+
+```
+kubectl port-forward -n haproxy-ingress pod-name 9101:9101
+```
+To count the metrics of a pod: 
+```
+curl 'http://localhost:9101/metrics' | grep -v "# HELP\|# TYPE" | wc -l
+```

resources/haproxy-ingress/alerts.yaml

@@ -4,66 +4,75 @@ app: HAProxy Ingress
 version: 1.0.0
 appVersion:
 - '2.1'
+- '2.3'
 descriptionFile: ALERTS.md
 configurations:
 - kind: Prometheus
   data: |
     groups:
-    - name: HAProxy-Ingress
+    - name: Haproxy-Ingress
       rules:
-      - alert: UpTimeLessThan1Hour
-        expr: max(time() - haproxy_process_start_time_seconds) < 3600
-        for: 10m
-        labels:
-          severity: page
-        annotations:
-          summary: Up Time of less than 1 hour
-      - alert: FrontendDown
-        expr: count by (proxy) (haproxy_frontend_status == 1) == 0
-        for: 10m
-        labels:
-          severity: page
-        annotations:
-          summary: Frontend down {{$labels.proxy}}
-      - alert: BackendDown
-        expr: sum by (proxy) (haproxy_backend_status==1) == 0
-        for: 10m
-        labels:
-          severity: page
-        annotations:
-          summary: No backend instances found for the proxy {{$labels.proxy}}
-      - alert: HighSessionsUsage
-        expr: max by (proxy)(rate(haproxy_backend_sessions_total[5m]) / haproxy_backend_limit_sessions) >0.85
-        for: 10m
-        labels:
-          severity: page
-        annotations:
-          summary: Low number of sessions available in proxy {{$labels.proxy}}
-      - alert: HigErrorRate
-        expr: sum by (proxy)(rate(haproxy_backend_http_responses_total{code!="2xx"}[5m])) / sum by (proxy)(rate(haproxy_backend_http_responses_total[5m])) > 0.15
-        for: 10m
-        labels:
-          severity: page
-        annotations:
-          summary: High HTTP error rate in proxy {{$labels.proxy}}
-      - alert: HighRequestDeniedRate
-        expr: sum by (proxy) (rate(haproxy_backend_requests_denied_total[5m])) / sum by (proxy)(rate(haproxy_backend_http_requests_total[5m])) > 0.15
-        for: 10m
-        labels:
-          severity: page
-        annotations:
-          summary: High request denied error rate in proxy {{$labels.proxy}}
-      - alert: HighResponseDeniedRate
-        expr: sum by (proxy) (rate(haproxy_backend_responses_denied_total[5m])) / sum by (proxy)(rate(haproxy_backend_http_responses_total[5m])) > 0.15
-        for: 10m
-        labels:
-          severity: page
-        annotations:
-          summary: High responses denied rate in proxy {{$labels.proxy}}
-      - alert: HighResponseTime
-        expr: max by (proxy) (haproxy_backend_response_time_average_seconds)> 0.25
-        for: 10m
-        labels:
-          severity: page
-        annotations:
-          summary: High response time in proxy {{$labels.proxy}}
+        - alert: '[Haproxy-Ingress] Uptime less than 1 hour'
+          expr: |
+            max(time() - haproxy_process_start_time_seconds) < 3600
+          for: 10m
+          labels:
+            severity: critical
+          annotations:
+            description: This alert detects when all of the instances of the ingress controller have an uptime of less than 1 hour.
+        - alert: '[Haproxy-Ingress] Frontend Down'
+          expr: |
+            count by (proxy) (haproxy_frontend_status == 1) == 0
+          for: 10m
+          labels:
+            severity: critical
+          annotations:
+            description: This alert detects when a frontend has all of its instances down for more than 10 minutes.
+        - alert: '[Haproxy-Ingress] Backend Down'
+          expr: |
+            sum by (proxy) (haproxy_backend_status == 1) == 0
+          for: 10m
+          labels:
+            severity: critical
+          annotations:
+            description: This alert detects when a backend has all of its instances down for more than 10 minutes.
+        - alert: '[Haproxy-Ingress] High Sessions Usage'
+          expr: |
+            max by (proxy)(rate(haproxy_backend_sessions_total[5m]) / haproxy_backend_limit_sessions) >0.85
+          for: 10m
+          labels:
+            severity: critical
+          annotations:
+            description: This alert triggers when the backend sessions overpass the 85% of the sessions capacity for 10 minutes.
+        - alert: '[Haproxy-Ingress] High Error Rate'
+          expr: |
+            sum by (proxy)(rate(haproxy_backend_http_responses_total{code!="2xx"}[5m])) / sum by (proxy)(rate(haproxy_backend_http_responses_total[5m])) > 0.15
+          for: 10m
+          labels:
+            severity: critical
+          annotations:
+            description: This alert triggers when there is an error rate over 15% for over 10 minutes in a proxy.
+        - alert: '[Haproxy-Ingress] High Request Denied Rate'
+          expr: |
+            sum by (proxy) (rate(haproxy_backend_requests_denied_total[5m])) / sum by (proxy)(rate(haproxy_backend_http_requests_total[5m])) > 0.15
+          for: 10m
+          labels:
+            severity: critical
+          annotations:
+            description: These alerts detect when there is a denied rate of requests over 10% for over 10 minutes in a proxy.
+        - alert: '[Haproxy-Ingress] High Response Denied Rate'
+          expr: |
+            sum by (proxy) (rate(haproxy_backend_responses_denied_total[5m])) / sum by (proxy)(rate(haproxy_backend_http_responses_total[5m])) > 0.15
+          for: 10m
+          labels:
+            severity: critical
+          annotations:
+            description: These alerts detect when there is a denied rate of responses over 10% for over 10 minutes in a proxy.
+        - alert: '[Haproxy-Ingress] High Response Rate'
+          expr: |
+            max by (proxy) (haproxy_backend_response_time_average_seconds)> 0.25
+          for: 10m
+          labels:
+            severity: critical
+          annotations:
+            description: This alert triggers when a proxy has a mean response time higher than 250ms for over 10 minutes.

resources/haproxy-ingress/dashboardsv2.3.yaml

@@ -0,0 +1,50 @@
+apiVersion: v1
+kind: Dashboard
+app: HAProxy Ingress
+version: 1.0.0
+appVersion:
+- '2.3'
+configurations:
+- name: HAProxy K8s Ingress Overview
+  kind: Sysdig
+  image: haproxy-ingress/images/haproxy-sysdig-ingress-overview-2.3.png
+  description: |
+    This dashboard offers information on:
+    * Up Time
+    * Instances
+    * Frontend OK
+    * Frontend FULL
+    * Frontend STOPPED
+    * Backend DOWN
+    * Connections and Sessions
+    * SSL Connections
+    * Active Jobs
+    * Request and Response Errors
+    * Tasks
+    * Active and Connected Peers
+    * Process Run Queue
+    * Connection ans Session Denied
+    * Frontend Bytes In
+    * Frontend Connections
+    * Frontend Bytes Out
+    * Frontend Requests (TCP and HTTP)
+  file: include/dashboard-Sysdig-HAProxy-K8s-Ingress-Overview-2.3.json
+- name: HAProxy Proxy Golden Signals
+  kind: Sysdig
+  image: haproxy-ingress/images/haproxy-sysdig-proxy-golden-signals-2.3.png
+  description: |
+    This dashboard has the option to select a proxy and offers information on:
+    * Instances UP
+    * Instances Down
+    * Sessions Usage
+    * Queued Requests
+    * HTTP Error Rate
+    * Denial Rate
+    * HTTP Error by Code
+    * Data Transfers Aborted
+    * Mean Response Time
+    * Mean Connect and Queue Time
+    * Throughput
+    * IOPS
+    * Request and Response Size
+  file: include/dashboard-Sysdig-HAProxy-Proxy-Golden-Signals-2.3.json

resources/haproxy-ingress/description.yaml

@@ -4,4 +4,5 @@ app: HAProxy Ingress
 version: 1.0.0
 appVersion:
 - '2.1'
+- '2.3'
 descriptionFile: README.md