RAID Configuration and Disk Health Monitoring: smartctl Guide

# Ubuntu/Debian
sudo apt update
sudo apt install mdadm -y

# CentOS/AlmaLinux
sudo dnf install mdadm -y

# List existing disks
lsblk
fdisk -l

# View disk information
sudo fdisk -l /dev/sdb
sudo fdisk -l /dev/sdc

# Clear existing RAID signatures if present
sudo mdadm --zero-superblock /dev/sdb
sudo mdadm --zero-superblock /dev/sdc

# Create RAID 1 array
sudo mdadm --create /dev/md0 \
  --level=1 \
  --raid-devices=2 \
  /dev/sdb /dev/sdc

# Confirm creation (type yes)
# Monitor RAID status
watch cat /proc/mdstat

# Check completion status
cat /proc/mdstat

# Create RAID 5 array (3 disks)
sudo mdadm --create /dev/md0 \
  --level=5 \
  --raid-devices=3 \
  /dev/sdb /dev/sdc /dev/sdd

# Add a hot spare disk
sudo mdadm --create /dev/md0 \
  --level=5 \
  --raid-devices=3 \
  --spare-devices=1 \
  /dev/sdb /dev/sdc /dev/sdd /dev/sde

# Update mdadm.conf
sudo mdadm --detail --scan | sudo tee -a /etc/mdadm/mdadm.conf

# Update initramfs
sudo update-initramfs -u

# View RAID status
sudo mdadm --detail /dev/md0

# Create ext4 filesystem
sudo mkfs.ext4 /dev/md0

# Create mount point
sudo mkdir /mnt/raid

# Mount
sudo mount /dev/md0 /mnt/raid

# Add to /etc/fstab for persistent mounting
echo '/dev/md0 /mnt/raid ext4 defaults 0 0' | sudo tee -a /etc/fstab

# View RAID status
sudo mdadm --detail /dev/md0

# List all RAID arrays
cat /proc/mdstat

# Mark a disk as failed
sudo mdadm /dev/md0 --fail /dev/sdb

# Remove failed disk
sudo mdadm /dev/md0 --remove /dev/sdb

# Add new disk
sudo mdadm /dev/md0 --add /dev/sdb

# Stop RAID
sudo mdadm --stop /dev/md0

# Start RAID
sudo mdadm --assemble /dev/md0

# Ubuntu/Debian
sudo apt install smartmontools -y

# CentOS/AlmaLinux
sudo dnf install smartmontools -y

# View disk information
sudo smartctl -i /dev/sda

# Check SMART status
sudo smartctl -H /dev/sda
# Output: SMART overall-health self-assessment test result: PASSED

# View all SMART data
sudo smartctl -a /dev/sda

# Short summary
sudo smartctl -s on -a /dev/sda

# Short test (1-2 minutes)
sudo smartctl -t short /dev/sda

# Long test (several hours)
sudo smartctl -t long /dev/sda

# View test results
sudo smartctl -l selftest /dev/sda

# Check test progress
sudo smartctl -a /dev/sda | grep -i "test"

# View attributes
sudo smartctl -A /dev/sda

# NVMe disk information
sudo smartctl -i /dev/nvme0

# NVMe SMART data
sudo smartctl -a /dev/nvme0

# NVMe health status
sudo smartctl -H /dev/nvme0

# Edit configuration file
sudo nano /etc/smartd.conf

# Monitor all disks, send email on issues
DEFAULTS -a -o on -S on -n standby,q -s (S/../.././02|L/../../6/03) -m admin@rexe.tr -M exec /usr/share/smartmontools/smartd-runner

# Monitor specific disks
/dev/sda -a -o on -S on -m admin@rexe.tr
/dev/sdb -a -o on -S on -m admin@rexe.tr

# Auto-detect all disks
DEVICESCAN -a -o on -S on -m admin@rexe.tr

# Enable smartd service
sudo systemctl enable --now smartd

# Check status
sudo systemctl status smartd

# Test configuration
sudo smartd -q onecheck

# Quick health check for all disks
for disk in /dev/sd[a-z]; do
  echo "=== $disk ==="
  sudo smartctl -H $disk 2>/dev/null | grep -E "PASSED|FAILED|result"
done

# Check disk temperature
sudo smartctl -A /dev/sda | grep -i temperature

# Check disk operating hours
sudo smartctl -A /dev/sda | grep Power_On_Hours

# View error logs
sudo smartctl -l error /dev/sda

# Get disk info in JSON format
sudo smartctl -j -a /dev/sda

# Check SMART status of disks in RAID array
sudo mdadm --detail /dev/md0 | grep -E "State|Active|Failed"

# Check health of each disk in RAID
for disk in /dev/sdb /dev/sdc /dev/sdd; do
  echo "=== $disk ==="
  sudo smartctl -H $disk
done

# Monitor RAID events
sudo mdadm --monitor --scan --daemonise

# RAID email notification
sudo nano /etc/mdadm/mdadm.conf
# Add line: MAILADDR admin@rexe.tr