Implement drive health check for thinkpad

CLAUDE.md

@@ -2,4 +2,4 @@
 
 - This is my nix configuration system. Whenever you need to introduce update to my config, remember to check the current config.
 - After you introduce updates, remember to reflect those updates in the readme, should they bring any changes.
-- Do not add the shebang when writing shell scripts
+- Never write shebang in any context unless specifically requested

hosts/nixos/hs/disk-health.nix

@@ -18,32 +18,64 @@
     # Global smartd options
     extraOptions = [ "-A /var/log/smartd/" "-i 600" ];
     
+    # Disable default notifications
+    notifications = {
+      mail.enable = false;
+      x11.enable = false;
+      test = false;
+    };
+    
     # Device-specific monitoring configurations
     devices = [
       # ZFS Mirror drives (NVMe SSDs) - more frequent monitoring
       {
         device = "/dev/disk/by-id/ata-ZHITAI_SC001_XT_1000GB_ZTB401TAB244431J4R";
-        options = "-d auto -a -o on -S on -s (S/../.././02|L/../../6/03) -m exec=/home/yanlin/.config/nix/scripts/disk-health-smartd-alert.sh";
+        options = "-d auto -a -o on -S on -s (S/../.././02|L/../../6/03) -M exec ${pkgs.writeShellScript "smartd-notify-hs-zfs1" ''
+          export SMARTD_DEVICE="$SMARTD_DEVICE"
+          export SMARTD_FAILTYPE="$SMARTD_FAILTYPE"
+          export SMARTD_MESSAGE="$SMARTD_MESSAGE"
+          /home/yanlin/.config/nix/scripts/disk-health-smartd-alert.sh Ac9qKFH5cA.7Yly ZFS_Mirror_1
+        ''}";
       }
       {
         device = "/dev/disk/by-id/ata-ZHITAI_SC001_XT_1000GB_ZTB401TAB244431KEG";
-        options = "-d auto -a -o on -S on -s (S/../.././02|L/../../6/03) -m exec=/home/yanlin/.config/nix/scripts/disk-health-smartd-alert.sh";
+        options = "-d auto -a -o on -S on -s (S/../.././02|L/../../6/03) -M exec ${pkgs.writeShellScript "smartd-notify-hs-zfs2" ''
+          export SMARTD_DEVICE="$SMARTD_DEVICE"
+          export SMARTD_FAILTYPE="$SMARTD_FAILTYPE"
+          export SMARTD_MESSAGE="$SMARTD_MESSAGE"
+          /home/yanlin/.config/nix/scripts/disk-health-smartd-alert.sh Ac9qKFH5cA.7Yly ZFS_Mirror_2
+        ''}";
       }
       
       # Data drives (12TB HDDs) - standard monitoring
       {
         device = "/dev/disk/by-id/ata-HGST_HUH721212ALE604_5PK2N4GB";
-        options = "-d auto -a -o on -S on -s (S/../.././02|L/../../7/03) -W 4,45,55 -m exec=/home/yanlin/.config/nix/scripts/disk-health-smartd-alert.sh";
+        options = "-d auto -a -o on -S on -s (S/../.././02|L/../../7/03) -W 4,45,55 -M exec ${pkgs.writeShellScript "smartd-notify-hs-data1" ''
+          export SMARTD_DEVICE="$SMARTD_DEVICE"
+          export SMARTD_FAILTYPE="$SMARTD_FAILTYPE"
+          export SMARTD_MESSAGE="$SMARTD_MESSAGE"
+          /home/yanlin/.config/nix/scripts/disk-health-smartd-alert.sh Ac9qKFH5cA.7Yly Data_Drive_1_12TB
+        ''}";
       }
       {
         device = "/dev/disk/by-id/ata-HGST_HUH721212ALE604_5PJ7Z3LE";
-        options = "-d auto -a -o on -S on -s (S/../.././02|L/../../7/03) -W 4,45,55 -m exec=/home/yanlin/.config/nix/scripts/disk-health-smartd-alert.sh";
+        options = "-d auto -a -o on -S on -s (S/../.././02|L/../../7/03) -W 4,45,55 -M exec ${pkgs.writeShellScript "smartd-notify-hs-data2" ''
+          export SMARTD_DEVICE="$SMARTD_DEVICE"
+          export SMARTD_FAILTYPE="$SMARTD_FAILTYPE"
+          export SMARTD_MESSAGE="$SMARTD_MESSAGE"
+          /home/yanlin/.config/nix/scripts/disk-health-smartd-alert.sh Ac9qKFH5cA.7Yly Data_Drive_2_12TB
+        ''}";
       }
       
       # Parity drive (16TB HDD) - enhanced monitoring due to criticality
       {
         device = "/dev/disk/by-id/ata-ST16000NM000J-2TW103_WRS0F8BE";
-        options = "-d auto -a -o on -S on -s (S/../.././02|L/../../1/03) -W 2,45,55 -m exec=/home/yanlin/.config/nix/scripts/disk-health-smartd-alert.sh";
+        options = "-d auto -a -o on -S on -s (S/../.././02|L/../../1/03) -W 2,45,55 -M exec ${pkgs.writeShellScript "smartd-notify-hs-parity" ''
+          export SMARTD_DEVICE="$SMARTD_DEVICE"
+          export SMARTD_FAILTYPE="$SMARTD_FAILTYPE"
+          export SMARTD_MESSAGE="$SMARTD_MESSAGE"
+          /home/yanlin/.config/nix/scripts/disk-health-smartd-alert.sh Ac9qKFH5cA.7Yly Parity_Drive_16TB
+        ''}";
       }
     ];
   };
@@ -56,14 +88,17 @@
       after = [ "multi-user.target" ];
       serviceConfig = {
         Type = "oneshot";
-        ExecStart = "${pkgs.bash}/bin/bash /home/yanlin/.config/nix/scripts/daily-smart-report.sh";
+        ExecStart = "${pkgs.bash}/bin/bash /home/yanlin/.config/nix/scripts/daily-smart-report.sh Ac9qKFH5cA.7Yly";
         User = "root";
         StandardOutput = "journal";
         StandardError = "journal";
         # Add timeout to prevent hanging
         TimeoutStartSec = "300";  # 5 minutes max
-        # Set PATH to include system binaries for smartctl and curl
+        # Set PATH and SMART_DRIVES environment variables
-        Environment = "PATH=/run/current-system/sw/bin";
+        Environment = [
+          "PATH=/run/current-system/sw/bin"
+          "SMART_DRIVES=/dev/disk/by-id/ata-ZHITAI_SC001_XT_1000GB_ZTB401TAB244431J4R:ZFS Mirror 1;/dev/disk/by-id/ata-ZHITAI_SC001_XT_1000GB_ZTB401TAB244431KEG:ZFS Mirror 2;/dev/disk/by-id/ata-HGST_HUH721212ALE604_5PK2N4GB:Data Drive 1 (12TB);/dev/disk/by-id/ata-HGST_HUH721212ALE604_5PJ7Z3LE:Data Drive 2 (12TB);/dev/disk/by-id/ata-ST16000NM000J-2TW103_WRS0F8BE:Parity Drive (16TB)"
+        ];
         # Allow access to block devices for SMART commands
         DeviceAllow = [ "/dev/disk/by-id/* rw" "/dev/sd* rw" "/dev/nvme* rw" "char-* rw" "block-* rw" ];
         DevicePolicy = "closed";

hosts/nixos/hs/home.nix

@@ -9,7 +9,7 @@
   # hs-specific home configuration
   programs.zsh.shellAliases = {
       # Disk health monitoring
-      smart-report = "sudo /home/yanlin/.config/nix/scripts/daily-smart-report.sh";
+      smart-report = "sudo SMART_DRIVES='/dev/disk/by-id/ata-ZHITAI_SC001_XT_1000GB_ZTB401TAB244431J4R:ZFS Mirror 1;/dev/disk/by-id/ata-ZHITAI_SC001_XT_1000GB_ZTB401TAB244431KEG:ZFS Mirror 2;/dev/disk/by-id/ata-HGST_HUH721212ALE604_5PK2N4GB:Data Drive 1 (12TB);/dev/disk/by-id/ata-HGST_HUH721212ALE604_5PJ7Z3LE:Data Drive 2 (12TB);/dev/disk/by-id/ata-ST16000NM000J-2TW103_WRS0F8BE:Parity Drive (16TB)' /home/yanlin/.config/nix/scripts/daily-smart-report.sh Ac9qKFH5cA.7Yly";
       move-inbox = "cp -rl /mnt/storage/Media/downloads/.inbox/* /mnt/storage/Media/downloads/inbox && chown -R yanlin:users /mnt/storage/Media/downloads/inbox";
   };
 

hosts/nixos/thinkpad/disk-health.nix

@@ -0,0 +1,123 @@
+{ config, lib, pkgs, ... }:
+
+{
+  # Simplified disk health monitoring for ThinkPad laptop
+  # Single NVMe SSD monitoring with laptop-friendly settings
+
+  # Package requirements
+  environment.systemPackages = with pkgs; [
+    smartmontools
+    curl         # For Gotify notifications
+  ];
+
+  # Smartd configuration for laptop NVMe SSD  
+  services.smartd = {
+    enable = true;
+    autodetect = false;  # Explicit configuration
+    
+    # Global smartd options
+    extraOptions = [ "-A /var/log/smartd/" "-i 900" ];  # Check every 15 minutes
+    
+    # Disable default notifications
+    notifications = {
+      mail.enable = false;
+      x11.enable = false;
+      test = false;
+    };
+    
+    # Single NVMe drive monitoring with all options inline
+    devices = [
+      {
+        device = "/dev/nvme0n1";
+        options = "-d nvme -a -o on -S on -s (S/../.././03|L/../../7/04) -W 4,60,70 -M exec ${pkgs.writeShellScript "smartd-notify-thinkpad" ''
+          export SMARTD_DEVICE="$SMARTD_DEVICE"
+          export SMARTD_FAILTYPE="$SMARTD_FAILTYPE"
+          export SMARTD_MESSAGE="$SMARTD_MESSAGE"
+          /home/yanlin/.config/nix/scripts/disk-health-smartd-alert.sh AieM4SJHFcyl7TC System_SSD_ThinkPad
+        ''}";
+      }
+    ];
+  };
+
+  # Daily SMART report service
+  systemd.services = {
+    daily-smart-report = {
+      description = "Daily SMART Health Report for ThinkPad";
+      after = [ "multi-user.target" ];
+      serviceConfig = {
+        Type = "oneshot";
+        ExecStart = "${pkgs.bash}/bin/bash /home/yanlin/.config/nix/scripts/daily-smart-report.sh AieM4SJHFcyl7TC";
+        User = "root";
+        StandardOutput = "journal";
+        StandardError = "journal";
+        TimeoutStartSec = "300";  # 5 minutes max
+        # Environment with single NVMe drive
+        Environment = [
+          "PATH=/run/current-system/sw/bin"
+          "SMART_DRIVES=/dev/nvme0n1:System SSD (ThinkPad)"
+        ];
+        # Allow access to NVMe devices
+        DeviceAllow = [ "/dev/nvme* rw" "char-* rw" "block-* rw" ];
+        DevicePolicy = "closed";
+      };
+    };
+  };
+
+  # Daily SMART report timer - runs at 09:00 (later than server)
+  systemd.timers = {
+    daily-smart-report = {
+      description = "Daily SMART Report Timer for ThinkPad";
+      wantedBy = [ "timers.target" ];
+      timerConfig = {
+        OnCalendar = "09:00:00";  # Later time for laptop
+        Persistent = true;
+        RandomizedDelaySec = "10m";  # Longer randomization for laptop
+      };
+    };
+  };
+
+  # Ensure log directories exist
+  systemd.tmpfiles.rules = [
+    "d /var/log 0755 root root -"
+    "f /var/log/daily-smart-report.log 0644 root root -"
+    "f /var/log/smartd-alerts.log 0644 root root -"
+    "d /var/log/smartd 0755 root root -"
+  ];
+
+  # Enable the timer
+  systemd.targets.timers.wants = [
+    "daily-smart-report.timer"
+  ];
+
+  # Logrotate configuration
+  services.logrotate = {
+    enable = true;
+    settings = {
+      "/var/log/daily-smart-report.log" = {
+        frequency = "weekly";
+        rotate = 4;
+        compress = true;
+        delaycompress = true;
+        missingok = true;
+        notifempty = true;
+        create = "644 root root";
+      };
+      "/var/log/smartd-alerts.log" = {
+        frequency = "weekly";
+        rotate = 4;
+        compress = true;
+        delaycompress = true;
+        missingok = true;
+        notifempty = true;
+        create = "644 root root";
+      };
+    };
+  };
+
+  # Ensure scripts are executable
+  system.activationScripts.disk-health-scripts = ''
+    chmod +x /home/yanlin/.config/nix/scripts/gotify-notify.sh
+    chmod +x /home/yanlin/.config/nix/scripts/disk-health-smartd-alert.sh
+    chmod +x /home/yanlin/.config/nix/scripts/daily-smart-report.sh
+  '';
+}

hosts/nixos/thinkpad/home.nix

@@ -32,6 +32,8 @@
   # For example, laptop-specific aliases or scripts
   
   programs.zsh.shellAliases = {
+    # Disk health monitoring
+    smart-report = "sudo SMART_DRIVES='/dev/nvme0n1:System SSD (ThinkPad)' /home/yanlin/.config/nix/scripts/daily-smart-report.sh AieM4SJHFcyl7TC";
   };
 
   home.packages = with pkgs; [

hosts/nixos/thinkpad/system.nix

@@ -1,6 +1,7 @@
 { config, pkgs, lib, ... }: {
   imports = [
     ./hardware-configuration.nix
+    ./disk-health.nix
     ../../../modules/wireguard.nix
     ../../../modules/borg-server.nix
   ];

scripts/daily-smart-report.sh

@@ -1,5 +1,7 @@
 # Simple daily SMART report script - plain text version
 # Only checks SMART attributes and sends report via Gotify
+# Usage: daily-smart-report.sh <gotify_token>
+# Drive list should be passed via SMART_DRIVES environment variable as "device:name" pairs
 
 set -euo pipefail
 
@@ -7,18 +9,37 @@ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 GOTIFY_SCRIPT="${SCRIPT_DIR}/gotify-notify.sh"
 LOG_FILE="/var/log/daily-smart-report.log"
 
-# Host-specific Gotify configuration
+# Get parameters
-GOTIFY_URL="https://notify.yanlincs.com"
+GOTIFY_TOKEN="${1:-}"
-GOTIFY_TOKEN="Ac9qKFH5cA.7Yly"
 
-# Drive configurations
+# Validate parameters
-declare -A DRIVES=(
+if [[ -z "$GOTIFY_TOKEN" ]]; then
-    ["/dev/disk/by-id/ata-ZHITAI_SC001_XT_1000GB_ZTB401TAB244431J4R"]="ZFS Mirror 1"
+    echo "Error: Gotify token not provided"
-    ["/dev/disk/by-id/ata-ZHITAI_SC001_XT_1000GB_ZTB401TAB244431KEG"]="ZFS Mirror 2"
+    echo "Usage: $0 <gotify_token>"
-    ["/dev/disk/by-id/ata-HGST_HUH721212ALE604_5PK2N4GB"]="Data Drive 1 (12TB)"
+    echo "Drives should be in SMART_DRIVES environment variable"
-    ["/dev/disk/by-id/ata-HGST_HUH721212ALE604_5PJ7Z3LE"]="Data Drive 2 (12TB)"
+    exit 1
-    ["/dev/disk/by-id/ata-ST16000NM000J-2TW103_WRS0F8BE"]="Parity Drive (16TB)"
+fi
-)
+
+# Gotify configuration
+GOTIFY_URL="https://notify.yanlincs.com"
+
+# Parse drive configurations from environment variable
+# SMART_DRIVES format: "device1:name1;device2:name2;..."
+declare -A DRIVES=()
+
+if [[ -n "${SMART_DRIVES:-}" ]]; then
+    IFS=';' read -ra DRIVE_PAIRS <<< "$SMART_DRIVES"
+    for pair in "${DRIVE_PAIRS[@]}"; do
+        IFS=':' read -r device name <<< "$pair"
+        if [[ -n "$device" && -n "$name" ]]; then
+            DRIVES["$device"]="$name"
+        fi
+    done
+else
+    echo "Warning: No drives specified in SMART_DRIVES environment variable"
+    echo "Format: SMART_DRIVES='device1:name1;device2:name2'"
+    exit 1
+fi
 
 main() {
     local report=""

scripts/disk-health-smartd-alert.sh

@@ -1,6 +1,7 @@
 # SMART daemon alert script for Gotify notifications
 # Called by smartd when SMART issues are detected
-# No arguments needed - uses SMARTD_DEVICE environment variable
+# Usage: disk-health-smartd-alert.sh <gotify_token> <drive_name>
+# Uses SMARTD_DEVICE environment variable for device info
 
 set -euo pipefail
 
@@ -8,34 +9,24 @@ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 GOTIFY_SCRIPT="${SCRIPT_DIR}/gotify-notify.sh"
 LOG_FILE="/var/log/smartd-alerts.log"
 
-# Host-specific Gotify configuration
+# Get parameters
-GOTIFY_URL="https://notify.yanlincs.com"
+GOTIFY_TOKEN="${1:-}"
-GOTIFY_TOKEN="Ac9qKFH5cA.7Yly"
+DRIVE_NAME="${2:-}"
 
-# Drive name mapping based on device path
+# Validate parameters
-get_drive_name() {
+if [[ -z "$GOTIFY_TOKEN" ]]; then
-    local device="$1"
+    echo "Error: Gotify token not provided"
-    case "$device" in
+    echo "Usage: $0 <gotify_token> <drive_name>"
-        *"ata-ZHITAI_SC001_XT_1000GB_ZTB401TAB244431J4R"*)
+    exit 1
-            echo "ZFS Mirror 1 (System)"
+fi
-            ;;
+
-        *"ata-ZHITAI_SC001_XT_1000GB_ZTB401TAB244431KEG"*)
+# If drive name not provided, use device path
-            echo "ZFS Mirror 2 (System)"
+if [[ -z "$DRIVE_NAME" ]]; then
-            ;;
+    DRIVE_NAME="${SMARTD_DEVICE:-Unknown Drive}"
-        *"ata-HGST_HUH721212ALE604_5PK2N4GB"*)
+fi
-            echo "Data Drive 1 (12TB)"
+
-            ;;
+# Gotify configuration
-        *"ata-HGST_HUH721212ALE604_5PJ7Z3LE"*)
+GOTIFY_URL="https://notify.yanlincs.com"
-            echo "Data Drive 2 (12TB)"
-            ;;
-        *"ata-ST16000NM000J-2TW103_WRS0F8BE"*)
-            echo "Parity Drive (16TB)"
-            ;;
-        *)
-            echo "Unknown Drive ($device)"
-            ;;
-    esac
-}
 
 log_message() {
     local message="$1"
@@ -48,10 +39,7 @@ send_smartd_alert() {
     local failtype="${SMARTD_FAILTYPE:-unknown}"
     local message="${SMARTD_MESSAGE:-No details provided}"
     
-    local drive_name
+    log_message "SMART alert for $DRIVE_NAME ($device): $failtype - $message"
-    drive_name=$(get_drive_name "$device")
-    
-    log_message "SMART alert for $drive_name ($device): $failtype - $message"
     
     # Determine priority based on failure type
     local priority="high"
@@ -68,7 +56,7 @@ send_smartd_alert() {
     esac
     
     # Create notification message
-    local notification_title="SMART Alert: $drive_name"
+    local notification_title="SMART Alert: $DRIVE_NAME"
     local notification_message="Device: $device
 Failure Type: $failtype
 Details: $message