html email

scripts/disk-health-check.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 # server-health-check.sh — Argento health monitoring
 # Checks: SMART disk health, ZFS pool status, disk space
-# Outputs to stdout by default, or sends email with --email.
+# Outputs plain text to stdout by default, or sends an HTML email with --email.
 # Use --error-only to suppress output when everything is healthy.
 #
 # Usage:
@@ -37,6 +37,28 @@ done
 PROBLEMS=""
 STATUS=""
 
+# HTML table rows for the email body, built alongside the plain-text STATUS.
+# Styles are inlined on every element because most mail clients strip
+# <style> blocks. nowrap keeps device paths and sizes from wrapping.
+TH='style="padding:2px 10px;text-align:left;border-bottom:1px solid #ccc;white-space:nowrap"'
+TD='style="padding:2px 10px;text-align:left;white-space:nowrap"'
+TDR='style="padding:2px 10px;text-align:right;white-space:nowrap"'
+TABLE='style="border-collapse:collapse;margin:4px 0 16px"'
+HTML_SATA=""
+HTML_NVME=""
+HTML_ZFS=""
+HTML_SPACE=""
+
+# Green for healthy, red for anything else. UNKNOWN is amber because it
+# means smartctl couldn't read the device, not that the device failed.
+state_html() {
+    case "$1" in
+        PASSED|ONLINE) printf '<span style="color:#1a7f37;font-weight:bold">%s</span>' "$1" ;;
+        UNKNOWN)       printf '<span style="color:#9a6700;font-weight:bold">%s</span>' "$1" ;;
+        *)             printf '<span style="color:#cf222e;font-weight:bold">%s</span>' "$1" ;;
+    esac
+}
+
 # ─── SMART Disk Health (SATA/SAS) ───────────────────────────────
 STATUS+="SMART (SATA):\n"
 for disk in /dev/sd?; do
@@ -50,11 +72,15 @@ for disk in /dev/sd?; do
     temp=$(smartctl -A "$disk" 2>/dev/null | awk '$1 == 194 || $1 == 190 {print $10; exit}') || true
     temp="${temp:-?}"
     hours=$(smartctl -A "$disk" 2>/dev/null | awk '$1 == 9 {print $10; exit}') || true
+    # Some Seagates report attribute 9 raw as "11170h+42m+51.807s" —
+    # keep only the whole hours.
+    hours=${hours%%[^0-9]*}
     hours="${hours:-?}"
     model=$(smartctl -i "$disk" 2>/dev/null | awk -F': +' '/Device Model|Model Number/{print $2; exit}') || true
     model="${model:-unknown}"
 
     STATUS+="  $disk ($model): $health, ${temp}C, ${hours}h\n"
+    HTML_SATA+="<tr><td $TD>$disk</td><td $TD>$model</td><td $TD>$(state_html "$health")</td><td $TDR>${temp}C</td><td $TDR>${hours}h</td></tr>"$'\n'
 
     if [ "$health" != "PASSED" ] && [ "$health" != "UNKNOWN" ]; then
         PROBLEMS+="[SMART] $disk: overall health check FAILED ($health)\n"
@@ -93,14 +119,18 @@ for disk in /dev/nvme[0-9]*; do
     health="${health:-UNKNOWN}"
     model=$(smartctl -i "$ns" 2>/dev/null | awk -F': +' '/Model Number/{print $2; exit}') || true
     model="${model:-unknown}"
+    # smartctl prints "38 Celsius" — keep just the number to match the SATA column
     temp=$(smartctl -A "$ns" 2>/dev/null | awk -F': +' '/Temperature:/{print $2; exit}') || true
+    temp=${temp%% *}
     temp="${temp:-?}"
-    hours=$(smartctl -A "$ns" 2>/dev/null | awk -F': +' '/Power On Hours/{print $2; exit}') || true
+    # strip thousands separator ("9,852")
+    hours=$(smartctl -A "$ns" 2>/dev/null | awk -F': +' '/Power On Hours/{print $2; exit}' | tr -d ',') || true
     hours="${hours:-?}"
     # NVMe percentage used — 100% means full rated write endurance consumed
     pct_used=$(smartctl -A "$ns" 2>/dev/null | awk -F': +' '/Percentage Used/{print $2; exit}' | tr -d '%') || true
 
-    STATUS+="  $ns ($model): $health, ${temp}, ${hours}h\n"
+    STATUS+="  $ns ($model): $health, ${temp}C, ${hours}h\n"
+    HTML_NVME+="<tr><td $TD>$ns</td><td $TD>$model</td><td $TD>$(state_html "$health")</td><td $TDR>${temp}C</td><td $TDR>${hours}h</td></tr>"$'\n'
 
     if [ "$health" != "PASSED" ] && [ "$health" != "UNKNOWN" ]; then
         PROBLEMS+="[SMART] $ns: overall health check FAILED ($health)\n"
@@ -116,9 +146,14 @@ STATUS+="\nZFS Pools:\n"
 while IFS= read -r pool; do
     [ -n "$pool" ] || continue
     state=$(zpool list -H -o health "$pool" 2>/dev/null) || true
+    state="${state:-UNKNOWN}"
     pool_info=$(zpool list -H -o name,size,alloc,free,cap "$pool" 2>/dev/null) || true
     STATUS+="  $pool_info  $state\n"
 
+    # zpool -H output is tab-separated
+    IFS=$'\t' read -r p_name p_size p_alloc p_free p_cap <<< "$pool_info" || true
+    HTML_ZFS+="<tr><td $TD>${p_name:-$pool}</td><td $TDR>$p_size</td><td $TDR>$p_alloc</td><td $TDR>$p_free</td><td $TDR>$p_cap</td><td $TD>$(state_html "$state")</td></tr>"$'\n'
+
     if [ "$state" != "ONLINE" ]; then
         PROBLEMS+="[ZFS] Pool '$pool' state: $state\n"
     fi
@@ -155,9 +190,12 @@ while IFS= read -r line; do
     used=$(echo "$line" | awk '{print $3}')
     avail=$(echo "$line" | awk '{print $4}')
     STATUS+="  $mount: ${usage}% (${used}/${size}, ${avail} free)\n"
+    usage_cell="${usage}%"
     if [ "$usage" -gt "$SPACE_THRESHOLD" ] 2>/dev/null; then
         PROBLEMS+="[SPACE] $mount is ${usage}% full\n"
+        usage_cell="<span style=\"color:#cf222e;font-weight:bold\">${usage}%</span>"
     fi
+    HTML_SPACE+="<tr><td $TD>$mount</td><td $TDR>$usage_cell</td><td $TDR>$used</td><td $TDR>$size</td><td $TDR>$avail</td></tr>"$'\n'
 done < <(df -h --output=source,size,used,avail,pcent,target -x tmpfs -x devtmpfs -x overlay -x efivarfs 2>/dev/null | tail -n +2 || true)
 
 # ─── Output ──────────────────────────────────────────────────────
@@ -181,12 +219,47 @@ else
 fi
 
 if [ "$USE_EMAIL" = true ]; then
+    HTML_PROBLEMS=""
+    while IFS= read -r p; do
+        [ -n "$p" ] || continue
+        HTML_PROBLEMS+="<li style=\"color:#cf222e;font-weight:bold;margin:2px 0\">$p</li>"$'\n'
+    done < <(printf '%b' "$PROBLEMS")
+
+    # Built with a newline after each row/section — SMTP caps lines at
+    # ~1000 chars and one giant line can get mangled in transit.
+    HTML_BODY="<div style=\"font-family:Arial,Helvetica,sans-serif;font-size:14px;color:#222\">"$'\n'
+    if [ "$ERROR_ONLY" = true ]; then
+        HTML_BODY+="<p>Health check found issues on <b>$HOSTNAME</b> at $(date):</p>"$'\n'
+        HTML_BODY+="<ul style=\"padding-left:20px\">"$'\n'"$HTML_PROBLEMS</ul>"$'\n'
+    else
+        HTML_BODY+="<p>Health report for <b>$HOSTNAME</b> at $(date):</p>"$'\n'
+        if [ -n "$HTML_PROBLEMS" ]; then
+            HTML_BODY+="<h3 style=\"color:#cf222e\">Issues</h3>"$'\n'
+            HTML_BODY+="<ul style=\"padding-left:20px\">"$'\n'"$HTML_PROBLEMS</ul>"$'\n'
+        fi
+        HTML_BODY+="<h3>SMART (SATA)</h3><table $TABLE>"$'\n'
+        HTML_BODY+="<tr><th $TH>Disk</th><th $TH>Model</th><th $TH>Health</th><th $TH>Temp</th><th $TH>Hours</th></tr>"$'\n'
+        HTML_BODY+="$HTML_SATA</table>"$'\n'
+        HTML_BODY+="<h3>SMART (NVMe)</h3><table $TABLE>"$'\n'
+        HTML_BODY+="<tr><th $TH>Disk</th><th $TH>Model</th><th $TH>Health</th><th $TH>Temp</th><th $TH>Hours</th></tr>"$'\n'
+        HTML_BODY+="$HTML_NVME</table>"$'\n'
+        HTML_BODY+="<h3>ZFS Pools</h3><table $TABLE>"$'\n'
+        HTML_BODY+="<tr><th $TH>Pool</th><th $TH>Size</th><th $TH>Alloc</th><th $TH>Free</th><th $TH>Cap</th><th $TH>State</th></tr>"$'\n'
+        HTML_BODY+="$HTML_ZFS</table>"$'\n'
+        HTML_BODY+="<h3>Disk Space</h3><table $TABLE>"$'\n'
+        HTML_BODY+="<tr><th $TH>Mount</th><th $TH>Used %</th><th $TH>Used</th><th $TH>Size</th><th $TH>Free</th></tr>"$'\n'
+        HTML_BODY+="$HTML_SPACE</table>"$'\n'
+    fi
+    HTML_BODY+="</div>"
+
     {
         echo "Subject: $SUBJECT"
         echo "From: $HOSTNAME <argento@fastmail.com>"
         echo "To: $MAILTO"
+        echo "MIME-Version: 1.0"
+        echo "Content-Type: text/html; charset=utf-8"
         echo ""
-        printf '%b' "$BODY"
+        printf '%s\n' "$HTML_BODY"
     } | sendmail "$MAILTO"
 else
     printf '%b' "$BODY"