Editing Introduction to a Self Managed Life: a 13 hour & 28 minute presentation by FUTO software (section)

== Step 2: Creating Complete ZFS Monitoring Script with Logging ==

<span id="create-log-directory"></span>
==== 2.1 Create Log Directory ====

<pre>sudo mkdir -p /var/log/zfs-monitor
sudo chown root:root /var/log/zfs-monitor
sudo chmod 755 /var/log/zfs-monitor</pre>
<span id="make-the-monitoring-script"></span>
==== 2.2 Make the Monitoring Script ====

<pre>sudo -u root nano /root/zfs_health_check.sh</pre>
Copy and paste this complete script:

<pre>#!/bin/bash

# Configuration
EMAIL=&quot;l.a.rossmann@gmail.com&quot;
HOSTNAME=$(hostname)
LOG_FILE=&quot;/var/log/zfs-monitor/health_check.log&quot;
LOG_MAX_SIZE=$((10 * 1024 * 1024))  # 10MB in bytes

# Email configuration
FROM_EMAIL=&quot;yourdriveisdead@stevesavers.com&quot;
FROM_NAME=&quot;Steve&quot;
REPLY_TO=&quot;Steve &lt;steve@stevesavers.com&gt;&quot;  # Use a more consistent Reply-To address
RETURN_PATH=&quot;bounce@stevesavers.com&quot;  # A safe Return-Path address to handle bounces properly

# Create required directories
mkdir -p &quot;$(dirname &quot;$LOG_FILE&quot;)&quot;

# Initialize error log
errors=&quot;&quot;

# Logging functions
rotate_log() {
    if [ -f &quot;$LOG_FILE&quot; ] &amp;&amp; [ $(stat -f%z &quot;$LOG_FILE&quot; 2&gt;/dev/null || stat -c%s &quot;$LOG_FILE&quot;) -gt &quot;$LOG_MAX_SIZE&quot; ]; then
        mv &quot;$LOG_FILE&quot; &quot;$LOG_FILE.old&quot;
    fi
}

log_message() {
    echo -e &quot;[$(date '+%Y-%m-%d %H:%M:%S')] $1&quot; | tee -a &quot;$LOG_FILE&quot;
}

log_error() {
    local message=&quot;$1&quot;
    errors=&quot;${errors}\n$message&quot;
    log_message &quot;ERROR: $message&quot;
}

# Check overall pool status
check_pool_status() {
    while IFS= read -r pool; do
        status=$(zpool status &quot;$pool&quot;)
        
        # Check for common failure keywords
        if echo &quot;$status&quot; | grep -E &quot;DEGRADED|FAULTED|OFFLINE|UNAVAIL|REMOVED|FAIL|DESTROYED|SUSPENDED&quot; &gt; /dev/null; then
            log_error &quot;ALERT: Pool $pool is not healthy:\n$status&quot;
        fi
        
        # Check for errors
        if echo &quot;$status&quot; | grep -v &quot;No known data errors&quot; | grep -i &quot;errors:&quot; &gt; /dev/null; then
            log_error &quot;ALERT: Pool $pool has errors:\n$status&quot;
        fi
        
        # Check scrub status
        if echo &quot;$status&quot; | grep &quot;scan&quot; | grep -E &quot;scrub canceled|scrub failed&quot; &gt; /dev/null; then
            log_error &quot;ALERT: Pool $pool has unusual scrub status:\n$(echo &quot;$status&quot; | grep &quot;scan&quot;)&quot;
        fi
    done &lt; &lt;(zpool list -H -o name)
}

# Check individual device status
check_devices() {
    while IFS= read -r pool; do
        devices=$(zpool status &quot;$pool&quot; | awk '/ONLINE|DEGRADED|FAULTED|OFFLINE|UNAVAIL|REMOVED/ {print $1,$2}')
        
        echo &quot;$devices&quot; | while read -r device state; do
            if [ &quot;$state&quot; != &quot;ONLINE&quot; ] &amp;&amp; [ &quot;$device&quot; != &quot;pool&quot; ] &amp;&amp; [ &quot;$device&quot; != &quot;mirror&quot; ] &amp;&amp; [ &quot;$device&quot; != &quot;raidz1&quot; ] &amp;&amp; [ &quot;$device&quot; != &quot;raidz2&quot; ]; then
                log_error &quot;ALERT: Device $device in pool $pool is $state&quot;
            fi
        done
    done &lt; &lt;(zpool list -H -o name)
}

# Check capacity threshold (80% by default)
check_capacity() {
    while IFS= read -r pool; do
        capacity=$(zpool list -H -p -o capacity &quot;$pool&quot;)
        if [ &quot;$capacity&quot; -ge 80 ]; then
            log_error &quot;WARNING: Pool $pool is ${capacity}% full&quot;
        fi
    done &lt; &lt;(zpool list -H -o name)
}

# Check dataset properties
check_dataset_properties() {
    while IFS= read -r dataset; do
        # Skip base pools
        if ! echo &quot;$dataset&quot; | grep &quot;/&quot; &gt; /dev/null; then
            continue
        fi
        
        # Check if compression is enabled
        compression=$(zfs get -H compression &quot;$dataset&quot; | awk '{print $3}')
        if [ &quot;$compression&quot; = &quot;off&quot; ]; then
            log_error &quot;WARNING: Compression is disabled on dataset $dataset&quot;
        fi
        
        # Check if dataset is mounted
        mounted=$(zfs get -H mounted &quot;$dataset&quot; | awk '{print $3}')
        if [ &quot;$mounted&quot; = &quot;no&quot; ]; then
            log_error &quot;WARNING: Dataset $dataset is not mounted&quot;
        fi
        
        # Check available space
        available=$(zfs get -H available &quot;$dataset&quot; | awk '{print $3}')
        if [ &quot;$available&quot; = &quot;0&quot; ] || [ &quot;$available&quot; = &quot;0B&quot; ]; then
            log_error &quot;CRITICAL: Dataset $dataset has no available space&quot;
        fi
    done &lt; &lt;(zfs list -H -o name)
}

# Function to send email
send_email() {
    local subject=&quot;$1&quot;
    local content=&quot;$2&quot;
    
    {
        echo &quot;Subject: $subject&quot;
        echo &quot;To: ${EMAIL}&quot;
        echo &quot;From: ${FROM_NAME} &lt;${FROM_EMAIL}&gt;&quot;
        echo &quot;Reply-To: ${REPLY_TO}&quot;
        echo &quot;Return-Path: ${RETURN_PATH}&quot;
        echo &quot;Content-Type: text/plain; charset=UTF-8&quot;
        echo
        echo &quot;$content&quot;
    } | sendmail -t
}

# Main execution
rotate_log
log_message &quot;Starting ZFS health check&quot;

# Run all checks
check_pool_status
check_devices
check_capacity
check_dataset_properties

# Send notification if there are errors
if [ -n &quot;$errors&quot; ]; then
    log_message &quot;Issues detected - sending email alert&quot;
    subject=&quot;Storage Alert: Issues Detected on ${HOSTNAME}&quot;  # Simplified subject line
    content=$(echo -e &quot;ZFS Health Monitor Report from ${HOSTNAME}\n\nThe following issues were detected:${errors}&quot;)
    send_email &quot;$subject&quot; &quot;$content&quot;
else
    log_message &quot;All ZFS checks passed successfully&quot;
fi</pre>
<span id="set-proper-permissions-2"></span>

==== 2.3 Set Proper Permissions ====

<pre>sudo -u root chmod +x /root/zfs_health_check.sh</pre>
<span id="test-the-script"></span>
==== 2.4 Test the Script ====

<pre>sudo /root/zfs_health_check.sh</pre>
<span id="make-sure-logging-works"></span>
==== 2.5 Make sure logging works ====

<pre>tail -f /var/log/zfs-monitor/health_check.log</pre>
<span id="features-of-this-script"></span>
==== 2.6 Features of this Script: ====

* '''Monitoring''':
** It tells you when your pool has issues BEFORE all your drives die
** Device status checks
** Capacity warnings
* '''Email Alerts''':
** Sends when issues are detected
** Includes error information

The script is now ready for cron job configuration and regular use. Cron jobs are tasks we tell the machine to perform at regular intervals, similar to setting a utility bill to autopay.

<span id="step-3-create-cron-job"></span>