commands.sh

#!/bin/bash
# Commands executed during the lab

# ========================================================================
# Task 1: Install and Configure the Monitoring Stack / Step 1.1: Install InfluxDB
# ========================================================================
sudo apt update
sudo apt install -y wget curl bc ca-certificates
wget https://dl.influxdata.com/influxdb/releases/influxdb2-2.7.4-amd64.deb
sudo apt install -y ./influxdb2-2.7.4-amd64.deb
curl -O https://dl.influxdata.com/influxdb/releases/influxdb2-client-2.7.5-linux-amd64.tar.gz
tar xvf influxdb2-client-2.7.5-linux-amd64.tar.gz
sudo install -m 0755 influx /usr/local/bin/influx
sudo systemctl start influxdb
sudo systemctl enable influxdb

# ========================================================================
# Task 1: Install and Configure the Monitoring Stack / Step 1.2: Initialize InfluxDB
# ========================================================================
export INFLUX_TOKEN="energy-operator-token-1234567890"
influx setup \
  --username admin \
  --password adminpassword123 \
  --token "$INFLUX_TOKEN" \
  --org energyorg \
  --bucket energy_metrics \
  --retention 168h \
  --force
echo 'export INFLUX_TOKEN="energy-operator-token-1234567890"' >> ~/.bashrc
source ~/.bashrc

# ========================================================================
# Task 1: Install and Configure the Monitoring Stack / Step 1.3: Install Telegraf
# ========================================================================
wget https://dl.influxdata.com/telegraf/releases/telegraf_1.29.1-1_amd64.deb
sudo apt install -y ./telegraf_1.29.1-1_amd64.deb

# ========================================================================
# Task 1: Install and Configure the Monitoring Stack / Step 1.4: Configure Telegraf for Energy Metrics Collection
# ========================================================================
sudo nano /etc/telegraf/telegraf.conf

# ========================================================================
# Task 1: Install and Configure the Monitoring Stack / Step 1.5: Create Simulated Energy Data Source
# ========================================================================
sudo nano /usr/local/bin/energy_simulator.sh

# ========================================================================
# Task 1: Install and Configure the Monitoring Stack / Step 1.5: Create Simulated Energy Data Source / Make it executable and run in background
# ========================================================================
sudo chmod +x /usr/local/bin/energy_simulator.sh
sudo touch /var/log/energy_data.log
sudo chmod 644 /var/log/energy_data.log
nohup sudo /usr/local/bin/energy_simulator.sh > /dev/null 2>&1 &

# ========================================================================
# Task 1: Install and Configure the Monitoring Stack / Step 1.6: Start Telegraf
# ========================================================================
sudo systemctl start telegraf
sudo systemctl enable telegraf
sudo systemctl status telegraf --no-pager

# ========================================================================
# Task 1: Install and Configure the Monitoring Stack / Step 1.7: Verify Data Ingestion
# ========================================================================
influx query 'from(bucket: "energy_metrics")
  |> range(start: -5m)
  |> filter(fn: (r) => r._measurement == "energy_consumption")
  |> limit(n: 10)' \
  --org energyorg \
  --token "$INFLUX_TOKEN"

# ========================================================================
# Task 2: Configure Threshold Detection and Alerting / Step 2.1: Install Kapacitor
# ========================================================================
wget https://dl.influxdata.com/kapacitor/releases/kapacitor_1.7.0_amd64.deb
sudo apt install -y ./kapacitor_1.7.0_amd64.deb

# ========================================================================
# Task 2: Configure Threshold Detection and Alerting / Step 2.2: Configure Kapacitor
# ========================================================================
sudo mkdir -p /var/log/kapacitor
sudo chown kapacitor:kapacitor /var/log/kapacitor

# ========================================================================
# Task 2: Configure Threshold Detection and Alerting / Step 2.2: Configure Kapacitor
# ========================================================================
sudo nano /etc/kapacitor/kapacitor.conf

# ========================================================================
# Task 2: Configure Threshold Detection and Alerting / Step 2.2: Configure Kapacitor / Start Kapacitor
# ========================================================================
sudo systemctl start kapacitor
sudo systemctl enable kapacitor
sudo systemctl status kapacitor --no-pager

# ========================================================================
# Task 2: Configure Threshold Detection and Alerting / Step 2.3: Create Threshold Detection Script
# ========================================================================
nano ~/energy_threshold_alert.tick

# ========================================================================
# Task 2: Configure Threshold Detection and Alerting / Step 2.4: Define and Enable the Alert Task
# ========================================================================
BUCKET_ID=$(influx bucket list --name energy_metrics --hide-headers | awk 'NR==1 {print $1}')
echo "$BUCKET_ID"
influx v1 dbrp create \
  --db energy_metrics \
  --rp autogen \
  --bucket-id "$BUCKET_ID" \
  --default

# ========================================================================
# Task 2: Configure Threshold Detection and Alerting / Step 2.4: Define and Enable the Alert Task
# ========================================================================
kapacitor define energy_alert \
  -tick ~/energy_threshold_alert.tick \
  -type batch \
  -dbrp energy_metrics.autogen

# ========================================================================
# Task 2: Configure Threshold Detection and Alerting / Step 2.4: Define and Enable the Alert Task
# ========================================================================
kapacitor enable energy_alert

# ========================================================================
# Task 2: Configure Threshold Detection and Alerting / Step 2.4: Define and Enable the Alert Task
# ========================================================================
kapacitor show energy_alert

# ========================================================================
# Task 2: Configure Threshold Detection and Alerting / Step 2.5: Create Alert Log Directory
# ========================================================================
sudo mkdir -p /var/log/kapacitor
sudo chown kapacitor:kapacitor /var/log/kapacitor
sudo systemctl restart kapacitor

# ========================================================================
# Task 2: Configure Threshold Detection and Alerting / Step 2.6: Trigger Test Alerts
# ========================================================================
for i in {1..10}; do
  TIMESTAMP=$(date +%s%N)
  echo "energy_consumption,location=datacenter,rack=A1 power_watts=135i,voltage=120i,current=1.125 ${TIMESTAMP}" | sudo tee -a /var/log/energy_data.log > /dev/null
  sleep 2
done

# ========================================================================
# Task 2: Configure Threshold Detection and Alerting / Step 2.7: Monitor Alerts
# ========================================================================
sudo tail -f /var/log/kapacitor/energy_alerts.log

# ========================================================================
# Task 2: Configure Threshold Detection and Alerting / Step 2.7: Monitor Alerts
# ========================================================================
kapacitor stats general
kapacitor list tasks

# ========================================================================
# Verification / Verify Data Ingestion
# ========================================================================
sudo journalctl -u telegraf -n 50 --no-pager

# ========================================================================
# Verification / Verify Data Ingestion
# ========================================================================
influx query 'from(bucket: "energy_metrics")
  |> range(start: -10m)
  |> filter(fn: (r) => r._measurement == "energy_consumption")
  |> group(columns: ["location"])
  |> count()' \
  --org energyorg \
  --token "$INFLUX_TOKEN"

# ========================================================================
# Verification / Verify Threshold Detection
# ========================================================================
grep -Ei "crit|warn" /var/log/kapacitor/energy_alerts.log

# ========================================================================
# Verification / Verify Threshold Detection
# ========================================================================
kapacitor show energy_alert | grep -A 5 "Status"

# ========================================================================
# Verification / Complete System Check
# ========================================================================
nano ~/verify_lab.sh

# ========================================================================
# Verification / Complete System Check / Make it executable and run it
# ========================================================================
chmod +x ~/verify_lab.sh
~/verify_lab.sh

# ========================================================================
# Troubleshooting Tips / Issue: Telegraf not collecting data
# ========================================================================
telegraf --config /etc/telegraf/telegraf.conf --test
cpu,cpu=cpu-total,host=ip-172-31-10-187 usage_idle=96.2015503875969,usage_user=1.937984496124031,usage_system=1.8604651162790697 1744466268000000000
mem,host=ip-172-31-10-187 used_percent=23.948230127170916,total=4028628992i,available=3064027136i,used=964601856i 1744466268000000000
energy_consumption,host=ip-172-31-10-187,location=datacenter,rack=A1 current=1.125,power_watts=135i,voltage=120i 1744466268000000000

# ========================================================================
# Troubleshooting Tips / Issue: No alerts generated
# ========================================================================
sudo journalctl -u kapacitor -n 100 --no-pager

# ========================================================================
# Troubleshooting Tips / Issue: No alerts generated
# ========================================================================
kapacitor show energy_alert

# ========================================================================
# Troubleshooting Tips / Issue: InfluxDB connection errors
# ========================================================================
sudo systemctl status influxdb --no-pager

# ========================================================================
# Troubleshooting Tips / Issue: InfluxDB connection errors
# ========================================================================
sudo ss -tlnp | grep 8086

# ========================================================================
# Troubleshooting Tips / Issue: InfluxDB connection errors
# ========================================================================
echo "Check token permissions in InfluxDB UI:"
echo "http://localhost:8086"