due improvements

alertmanager/config.yml

@@ -0,0 +1,10 @@
+route:
+    receiver: 'slack'
+
+receivers:
+    - name: 'slack'
+      slack_configs:
+          - send_resolved: true
+            username: 'sebastian.blasaik'
+            channel: '#channel_name'
+            api_url: 'https://hooks.slack.com/services/'

deploy_all.sh

@@ -1,10 +1,33 @@
+#!/bin/bash
+
+NC='\033[0m'
+
+RED='\033[00;31m'
+GREEN='\033[00;32m'
+YELLOW='\033[00;33m'
+BLUE='\033[00;34m'
+PURPLE='\033[00;35m'
+CYAN='\033[00;36m'
+LIGHTGRAY='\033[00;37m'
+MAGENTA='\033[00;35m'
+LRED='\033[01;31m'
+LGREEN='\033[01;32m'
+LYELLOW='\033[01;33m'
+LBLUE='\033[01;34m'
+LPURPLE='\033[01;35m'
+LCYAN='\033[01;36m'
+WHITE='\033[01;37m'
+
+
+
 ## INSTALL docker-ce
 read -r -p "Do you want to install docker? [y/N] " response
 if [[ "$response" =~ ^([yY][eE][sS]|[yY])+$ ]]
 then
+	logout=1
 	curl -fsSL get.docker.com -o get-docker.sh
 	sudo sh get-docker.sh
-	sudo usermod -aG docker $(whoami)
+	sudo systemctl enable docker
 else
 	echo -e "'no' chosen for docker installation - docker assummed to be already installed"
 fi
@@ -13,18 +36,43 @@ fi
 read -r -p "Do you want to install docker-compose? [y/N] " response
 if [[ "$response" =~ ^([yY][eE][sS]|[yY])+$ ]]
 then
+	logout=1
 	sudo curl -L https://github.com/docker/compose/releases/download/1.21.2/docker-compose-$(uname -s)-$(uname -m) -o /usr/local/bin/docker-compose
 	sudo chmod +x /usr/local/bin/docker-compose
 else
 	echo -e "'no' chosen for docker-compose installation - docker-compose assummed to be already installed"
 fi
 
+## LOGOUT IF NEEDED
+if [[ "$logout" -eq 1 ]]; then
+	if [[ $(whoami) != "root" ]]; then
+		if [[ ! $(groups $(whoami) | egrep -oh 'docker') == "docker" ]]; then
+			echo -e "${BLUE}your login ${YELLOW}$(whoami)${NC}${BLUE} will be added to "docker" group...${NC}"
+			if [[ ! $(cat /etc/group | egrep -oh 'docker:') == "docker:" ]]; then
+				sudo groupadd docker
+				echo -e "${BLUE}creating group: ${YELLOW}docker${NC}${BLUE}${NC}"
+			fi
+			sudo usermod -aG docker $(whoami)
+			echo -e "${BLUE}you need to logout and login again...${NC}"
+			echo -e "${BLUE}start the same script and skip docker related part (answer 'no' two times).${NC}"
+			exit
+		fi
+	fi
+	echo -e "${YELLOW}docker was installed, you need to logout and login${NC}"
+	echo -e "${RED}login again and start deploy script without docker* installation part (answer no)${NC}"
+	exit 0
+fi
+
+
 # START docker-compose
+sudo systemctl restart docker
 docker-compose up -d 
 
 # ADD DATASOURCES AND DASHBOARDS
+sleep 5
+echo "adding datasources..."
+docker exec -it -u 0 grafana /var/lib/grafana/ds/add_datasources.sh
+
 echo "adding dashboards..."
 docker exec -it -u 0 grafana /var/lib/grafana/ds/add_dashboards.sh
 
-echo "adding datasources..."
-docker exec -it -u 0 grafana /var/lib/grafana/ds/add_datasources.sh

docker-compose.yml

@@ -46,11 +46,12 @@ services:
       command: ["bash", "/var/lib/grafana/ds/add_datasources.sh"]
         
   telegraf:
-    image: telegraf:latest
+    image: telegraf:1.6-alpine
     container_name: telegraf
     network_mode: "host"
     volumes:
       - ./telegraf.conf:/etc/telegraf/telegraf.conf:ro
+      - /var/run/utmp:/var/run/utmp:ro
     environment:
       # real influx host
       INFLUXDB_URI: "http://localhost:8086"
@@ -60,8 +61,12 @@ services:
     container_name: prometheus
     volumes:
      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml
+    links:
+      - cadvisor:cadvisor
+      - alertmanager:alertmanager
     networks:
      - private
+     - public
     command: "--config.file=/etc/prometheus/prometheus.yml --storage.tsdb.path=/prometheus"
     ports:
      - 9090:9090
@@ -80,12 +85,41 @@ services:
       - public
       - private
     environment:
-      DOGSNAME:      "Gula&Bodka"
-    command:
-      - "--collector.textfile"
-      - "--collector.textfile.directory=/var/lib/node_exporter/textfile_collector/"
+      PURPOSE:      "PERFORMANCE_MONITORING"
     expose:
       - 9100
     ports:
       - 9100:9100
 
+#
+  cadvisor:
+    image: google/cadvisor:v0.28.3
+    container_name: cadvisor
+    volumes:
+      - /:/rootfs:ro
+      - /var/run:/var/run:rw
+      - /sys:/sys:ro
+      - /var/lib/docker/:/var/lib/docker:ro
+      #- /cgroup:/cgroup:ro #doesn't work on MacOS only for Linux
+    restart: unless-stopped
+    expose:
+      - 8080
+    networks:
+      - private
+      - public
+    labels:
+      org.label-schema.group: "monitoring"
+
+  alertmanager:
+    image: prom/alertmanager
+    container_name: alertmanager
+    ports:
+      - 9093:9093
+    volumes:
+      - ./alertmanager/:/etc/alertmanager/
+    networks:
+      - private
+    restart: unless-stopped
+    command:
+      - '--config.file=/etc/alertmanager/config.yml'
+      - '--storage.path=/alertmanager'

grafana/add_dashboards.sh

@@ -82,7 +82,7 @@ install_dashboards() {
       if grafana_api POST /api/dashboards/db "" "${dashboard}.wrapped"; then
 	echo -e "\n** ${GREEN}installed ok **${NC}"
       else
-        echo -e "\n** ${RED}installation of: ${PURPLE}\"${dashboard}\"${RED} failed **${NC}"
+	echo -e "\n** ${RED}installation of: ${PURPLE}\"${dashboard}\"${RED} failed.**${NC}"
       fi
     fi
   done

prometheus/prometheus.yml

@@ -32,3 +32,15 @@ scrape_configs:
     scrape_interval: "15s"
     static_configs:
       - targets: ['node_exporter:9100']
+
+  - job_name: 'cadvisor'
+    scrape_interval: 5s
+    static_configs:
+      - targets: ['cadvisor:8080']
+
+alerting:
+  alertmanagers:
+  - scheme: http
+    static_configs:
+    - targets:
+      - "alertmanager:9093"

undeploy_all.sh

@@ -13,16 +13,16 @@ do_cleanup () {
 	fi
 
 	
-	read -r -p "Do you want to delete all docker \"bridge\" networks? [y/N] " response
-	if [[ "$response" =~ ^([yY][eE][sS]|[yY])+$ ]]
-	then
-		for n in $(docker network ls | grep "bridge" | awk '/ / { print $1 }'); do
-			echo -e "attempting to delete network: $n"
-			docker network rm $n || echo "cannot remove: $n"
-		done
-	else
-        	echo -e "'no' chosen"
-	fi
+#	read -r -p "Do you want to delete all docker \"bridge\" networks? [y/N] " response
+#	if [[ "$response" =~ ^([yY][eE][sS]|[yY])+$ ]]
+#	then
+#		for n in $(docker network ls | grep "bridge" | awk '/ / { print $1 }'); do
+#			echo -e "attempting to delete network: $n"
+#			docker network rm $n || echo "cannot remove: $n"
+#		done
+#	else
+#        	echo -e "'no' chosen"
+#	fi
 
 	read -r -p "Do you want to delete all docker dangling images? [y/N] " response
 	if [[ "$response" =~ ^([yY][eE][sS]|[yY])+$ ]]