Vijay monitors servers without Datadog

# The 60-second performance overview:
uptime                          # load average
free -h                         # memory
df -h                           # disk
ss -s                           # network connections
ps aux --sort=-%cpu | head -5   # top CPU processes

# All in one line — paste this at the start of every incident:
echo "=CPU=" && uptime && echo "=MEM=" && free -h && echo "=DISK=" && df -h && echo "=TOP=" && ps aux --sort=-%cpu | head -5

sar -u 1 5                      # CPU usage every 1 second, 5 readings
sar -r 1 5                      # memory usage every 1 second
sar -d 1 5                      # disk I/O every 1 second
sar -n DEV 1 5                  # network interface stats

# Historical data (yesterday, last 7 days):
sar -u -f /var/log/sysstat/sa$(date -d yesterday +%d)
# Shows CPU usage for every 10-minute interval yesterday

# Install if not present:
sudo apt install sysstat
sudo systemctl enable sysstat && sudo systemctl start sysstat

curl https://my-netdata.io/kickstart.sh > /tmp/netdata-kickstart.sh
sudo bash /tmp/netdata-kickstart.sh

# Opens at http://YOUR_SERVER_IP:19999
# Shows: CPU, memory, disk, network, processes, containers — everything
# Free, open source, self-hosted

# Quick start with Docker Compose:
mkdir monitoring && cd monitoring
cat > docker-compose.yml << 'EOF'
version: '3'
services:
  prometheus:
    image: prom/prometheus
    ports: ["9090:9090"]
    volumes: ["./prometheus.yml:/etc/prometheus/prometheus.yml"]
  grafana:
    image: grafana/grafana
    ports: ["3000:3000"]
    environment: [GF_SECURITY_ADMIN_PASSWORD=admin]
EOF

cat > prometheus.yml << 'EOF'
scrape_configs:
  - job_name: 'linux'
    static_configs:
      - targets: ['node-exporter:9100']
EOF

docker compose up -d

# Install node_exporter on servers you want to monitor:
wget https://github.com/prometheus/node_exporter/releases/latest/download/node_exporter-linux-amd64.tar.gz
tar xvf node_exporter-linux-amd64.tar.gz
sudo mv node_exporter*/node_exporter /usr/local/bin/
node_exporter &

# Open Grafana at http://localhost:3000
# Add Prometheus as data source (http://prometheus:9090)
# Import dashboard ID 1860 — instant Linux metrics dashboard

docker run -d --restart=always -p 3001:3001 \
    -v uptime-kuma:/app/data \
    --name uptime-kuma louislam/uptime-kuma:1

# Open http://YOUR_SERVER_IP:3001
# Add monitors for your HTTP endpoints, TCP ports, ping checks
# Configure alerts: Telegram bot works great for Indian teams

#!/bin/bash
# /usr/local/bin/health-check — run every 5 minutes via cron

TELEGRAM_TOKEN="your_bot_token"
CHAT_ID="your_chat_id"
HOST=$(hostname)

alert() {
    curl -s -X POST "https://api.telegram.org/bot${TELEGRAM_TOKEN}/sendMessage" \
        -d chat_id="${CHAT_ID}" \
        -d text="⚠️ ${HOST}: $1" > /dev/null
}

# Check disk
DISK=$(df / | awk 'NR==2{print $5}' | tr -d '%')
[ "$DISK" -gt 85 ] && alert "Disk at ${DISK}%"

# Check memory
MEM_FREE=$(free | awk 'NR==2{printf "%.0f", $4/$2*100}')
[ "$MEM_FREE" -lt 10 ] && alert "Memory only ${MEM_FREE}% free"

# Check services
for SVC in nginx myapp postgresql; do
    systemctl is-active --quiet $SVC || alert "$SVC is DOWN"
done

# Add to cron:
# */5 * * * * /usr/local/bin/health-check

# Watch a log for errors and send a Telegram alert:
tail -f /opt/app/logs/app.log | while read line; do
    echo "$line" | grep -q "CRITICAL\|OutOfMemoryError\|FATAL" && \
    curl -s "https://api.telegram.org/bot${TOKEN}/sendMessage" \
        -d chat_id="${CHAT_ID}" -d text="🚨 ${line}" > /dev/null
done