Initial version

README.md

@@ -0,0 +1,2 @@
+# prometheus_hands-on
+Just a simple repository with the aim of demonstrating the concepts of Prometheus.

alertmanager/config.yml

@@ -0,0 +1,15 @@
+route:
+  receiver: 'default'
+  routes:
+  - match:
+      alertname: healthchecks watchdog
+    receiver: healthchecks.io
+    group_wait: 0s
+    group_interval: 1m
+    repeat_interval: 6m
+
+receivers:
+  - name: 'default'
+  - name: healthchecks.io
+    webhook_configs:
+    - url: https://hc-ping.com/840c3490-a705-4f23-801b-43462657752e

blackbox/blackbox.yml

@@ -0,0 +1,14 @@
+#Example
+#https://github.com/prometheus/blackbox_exporter/blob/master/example.yml
+modules:
+  http_2xx:
+    prober: http
+    timeout: 10s
+    http:
+      valid_http_versions: ["HTTP/1.1", "HTTP/2"]
+      valid_status_codes: [200]
+      method: GET
+      no_follow_redirects: false
+      fail_if_ssl: false
+      preferred_ip_protocol: "ip4"
+      ip_protocol_fallback: false

demo/Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3
+
+WORKDIR /usr/src/app
+
+COPY demo.py .
+
+RUN pip install prometheus_client
+
+EXPOSE 8001
+EXPOSE 8002
+
+CMD [ "python", "./demo.py" ]

demo/demo.py

@@ -0,0 +1,37 @@
+#!/usr/bin/env python
+# coding:utf-8
+'''Exemplo de instrumentação do Prometheus.'''
+
+import http.server
+import random
+import time
+from prometheus_client import start_http_server
+from prometheus_client import Counter
+from prometheus_client import Gauge
+
+SUM = Counter('demo_sum', 'Sum Demo requests duration.')
+REQUESTS = Counter('demo_count', 'Count Demo requests.')
+EXCEPTIONS = Counter('demo_exceptions_count', 'Exceptions serving Demo.')
+LAST = Gauge('demo_last_time_seconds', 'The last time a Demo was served.')
+
+class MyHandler(http.server.BaseHTTPRequestHandler):
+    '''Classe de exemplo.'''
+
+    def do_GET(self):
+        '''Função com todos os exemplos propostos.'''
+        rand = random.randrange(10)
+        time.sleep(rand)
+        SUM.inc(rand)
+        REQUESTS.inc()
+        with EXCEPTIONS.count_exceptions():
+            if random.random() < 0.2:
+                raise Exception
+        self.send_response(200)
+        self.end_headers()
+        self.wfile.write(bytes("Hello World (after %ss)" % rand, "utf-8"))
+        LAST.set_to_current_time()
+
+if __name__ == "__main__":
+    start_http_server(8001)
+    SERVER = http.server.HTTPServer(('', 8002), MyHandler)
+    SERVER.serve_forever()

docker-compose.yml

@@ -0,0 +1,103 @@
+version: '3.7'
+
+volumes:
+  alertmanager:
+  grafana:
+  prometheus:
+
+networks:
+  back-tier:
+    driver: bridge
+
+services:
+  prometheus:
+    image: prom/prometheus
+    container_name: prometheus
+    volumes:
+      - ./prometheus/:/etc/prometheus/
+    command:
+      - '--storage.tsdb.path=/prometheus'
+      - '--config.file=/etc/prometheus/prometheus.yml'
+    ports:
+      - 9090:9090
+    networks:
+      - back-tier
+
+  node-exporter:
+    container_name: node-exporter
+    image: prom/node-exporter
+    depends_on:
+      - prometheus
+    volumes:
+      - /proc:/host/proc
+      - /sys:/host/sysfs
+    command:
+      - '--path.procfs=/host/proc'
+      - '--path.sysfs=/host/sysfs'
+      - '--collector.filesystem.ignored-mount-points="^/(sys|proc|dev|host|etc)($$|/)"'
+    ports:
+      - 9100:9100
+    networks:
+      - back-tier
+
+  alertmanager:
+    container_name: alertmanager
+    image: prom/alertmanager
+    volumes:
+      - ./alertmanager/config.yml:/etc/alertmanager/config.yml
+    depends_on:
+      - prometheus
+      - node-exporter
+    command:
+      - '--config.file=/etc/alertmanager/config.yml'
+      - '--storage.path=/alertmanager'
+    ports:
+      - 9093:9093
+    networks:
+      - back-tier
+
+  pushgateway:
+    container_name: pushgateway
+    image: prom/pushgateway
+    depends_on:
+      - prometheus
+      - node-exporter
+      - alertmanager
+    ports:
+      - 9091:9091
+    networks:
+      - back-tier
+
+  blackbox:
+    container_name: blackbox
+    image: prom/blackbox-exporter
+    volumes:
+      - ./blackbox:/config
+    command:
+      - '--config.file=/config/blackbox.yml'
+    depends_on:
+      - prometheus
+      - node-exporter
+      - alertmanager
+      - pushgateway
+    ports:
+      - 9115:9115
+    networks:
+      - back-tier
+
+  demo:
+    container_name: demo
+    build: ./demo/
+    links:
+      - prometheus:prometheus
+    depends_on:
+      - prometheus
+      - node-exporter
+      - alertmanager
+      - pushgateway
+      - blackbox
+    ports:
+      - 8001:8001
+      - 8002:8002
+    networks:
+      - back-tier

prometheus/alert.conf

@@ -0,0 +1,43 @@
+groups:
+- name: prometheus
+  rules:
+  - alert: InstanceIsDown
+    expr: up == 0
+    for: 1m
+    labels:
+      severity: critical
+    annotations:
+      summary: "Instance {{ $labels.instance }} down"
+      description: "Instance {{ $labels.job }} is unavailable."
+  - alert: "HttpStatusCode"
+    expr: probe_http_status_code <= 199 OR probe_http_status_code >= 400
+    for: 5s
+    labels:
+      severity: critical
+    annotations:
+      summary: "HTTP Status Code (instance {{ $labels.instance }})"
+      description: "HTTP status code is not 200-399\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
+  - alert: "SiteIsDown"
+    expr: probe_http_status_code != 200
+    for: 5s
+    labels:
+      severity: high
+    annotations:
+      summary: "Site {{ $labels.instance }} down"
+      description: "Site {{ $labels.job }} is unavailable."
+  - alert: "TooManyHttpStatusCode"
+    expr: count(probe_http_status_code <= 199 or probe_http_status_code >= 400) > 5
+    for: 5s
+    labels:
+      severity: critical
+    annotations:
+      summary: "Too Many HTTP Status Code (instance {{ $labels.instance }})"
+      description: "Too Many HTTP status code is not 200-399\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
+
+  - alert: healthchecks watchdog
+    expr: vector(1)
+    for: 1m
+    labels:
+      severity: none
+    annotations:
+      summary: "Prometheus dead men switch"

prometheus/prometheus.yml

@@ -0,0 +1,48 @@
+global:
+  scrape_interval:     5s # By default, scrape targets every 15 seconds.
+  evaluation_interval: 10s # By default, scrape targets every 15 seconds.
+
+rule_files:
+  - 'alert.conf'
+
+alerting:
+  alertmanagers:
+  - static_configs:
+    - targets:
+      - alertmanager:9093
+
+scrape_configs:
+  - job_name: 'prometheus'
+    static_configs:
+    - targets: [ 'prometheus:9090']
+
+  - job_name: 'node-exporter'
+    static_configs:
+    - targets: [ 'node-exporter:9100']
+
+  - job_name: 'pushgateway'
+    static_configs:
+    - targets: [ 'pushgateway:9091']
+
+  - job_name: 'alertmanager'
+    static_configs:
+    - targets: [ 'alertmanager:9093']
+
+  - job_name: 'demo'
+    static_configs:
+    - targets: [ 'demo:8001']
+
+  - job_name: 'blackbox_http_2xx'
+    metrics_path: /probe
+    params:
+      module: [http_2xx]
+    static_configs:
+      - targets:
+        - https://www.google.com
+    relabel_configs:
+      - source_labels: [__address__]
+        target_label: __param_target
+      - source_labels: [__param_target]
+        target_label: instance
+      - target_label: __address__
+        replacement: blackbox:9115