<?xml version="1.0" encoding="UTF-8"?>
<zabbix_export>
<version>5.0</version>
<date>2021-09-23T09:16:55Z</date>
<groups>
<group>
<name>Templates Users</name>
</group>
</groups>
<templates>
<template>
<template>Template SMARTMONTOOLS</template>
<name>Template SMARTMONTOOLS</name>
<description>#
# .VERSION
# 0.8
#
# .DESCRIPTION
# Author: Nikitin Maksim
# Github: https://github.com/nikimaxim/zbx-smartmonitor.git
# Note: Zabbix lld for smartctl
#
# .TESTING
# Smartmontools: 7.1 and later
#</description>
<groups>
<group>
<name>Templates Users</name>
</group>
</groups>
<applications>
<application>
<name>SMART monitoring (smartctl)</name>
</application>
</applications>
<items>
<item>
<name>Smartctl version</name>
<key>smartctl.version</key>
<delay>1h</delay>
<trends>0</trends>
<value_type>CHAR</value_type>
<applications>
<application>
<name>SMART monitoring (smartctl)</name>
</application>
</applications>
<triggers>
<trigger>
<expression>{diff()}=1</expression>
<name>Version of smartctl was changed on {HOST.NAME}</name>
<priority>INFO</priority>
</trigger>
</triggers>
</item>
</items>
<discovery_rules>
<discovery_rule>
<name>Smartctl storage discovery</name>
<key>storage.discovery</key>
<delay>12h</delay>
<filter>
<conditions>
<condition>
<macro>{#STORAGE.SMART}</macro>
<value>1</value>
<formulaid>A</formulaid>
</condition>
</conditions>
</filter>
<item_prototypes>
<item_prototype>
<name>{#STORAGE.NAME}: Error сount</name>
<type>DEPENDENT</type>
<key>storage.error["{#STORAGE.CMD}"]</key>
<delay>0</delay>
<trends>0</trends>
<value_type>CHAR</value_type>
<description>HDD
SSD
NVME</description>
<applications>
<application>
<name>SMART monitoring (smartctl)</name>
</application>
</applications>
<preprocessing>
<step>
<type>JAVASCRIPT</type>
<params>if (value.search("No Errors Logged") != -1) {
return "No Errors Logged"
} else if (value.search("ATA Error Count:") != -1) {
return value.match(/(?:ATA Error Count:).+\b([0-9]+)/i)[1]
} else {
return "Not supported"
}
</params>
</step>
</preprocessing>
<master_item>
<key>storage.get["{#STORAGE.CMD}"]</key>
</master_item>
<trigger_prototypes>
<trigger_prototype>
<expression>{str(No Errors Logged)}=0 and {str(Not supported)}=0</expression>
<name>{#STORAGE.NAME}: SMART error status is not "No Errors Logged"</name>
<priority>AVERAGE</priority>
<manual_close>YES</manual_close>
</trigger_prototype>
</trigger_prototypes>
</item_prototype>
<item_prototype>
<name>{#STORAGE.NAME}: Smartctl</name>
<key>storage.get["{#STORAGE.CMD}"]</key>
<delay>1h;10m/1-7,08:00-21:00</delay>
<history>30d</history>
<trends>0</trends>
<value_type>TEXT</value_type>
<applications>
<application>
<name>SMART monitoring (smartctl)</name>
</application>
</applications>
<preprocessing>
<step>
<type>JAVASCRIPT</type>
<params>return value.replace(/\s\(.+\)|\s\[.+\]|[\u00A0]/g, '') // Deleting data in brackets and spaces</params>
</step>
</preprocessing>
<trigger_prototypes>
<trigger_prototype>
<expression>{str("FAILING_NOW")}=1</expression>
<name>{#STORAGE.NAME}: One or more SMART attributes are "FAILING_NOW"</name>
<priority>AVERAGE</priority>
<manual_close>YES</manual_close>
<dependencies>
<dependency>
<name>{#STORAGE.NAME}: SMART test status is "FAILED"</name>
<expression>{Template SMARTMONTOOLS:storage.health["{#STORAGE.CMD}"].str("FAILED!")}=1</expression>
</dependency>
</dependencies>
</trigger_prototype>
</trigger_prototypes>
</item_prototype>
<item_prototype>
<name>{#STORAGE.NAME}: Test result</name>
<type>DEPENDENT</type>
<key>storage.health["{#STORAGE.CMD}"]</key>
<delay>0</delay>
<trends>0</trends>
<value_type>CHAR</value_type>
<description>HDD
SSD</description>
<applications>
<application>
<name>SMART monitoring (smartctl)</name>
</application>
</applications>
<preprocessing>
<step>
<type>REGEX</type>
<params>(?:SMART overall-health self-assessment test result:|SMART Health Status:) +\b([\S ]+)
\1</params>
<error_handler>CUSTOM_ERROR</error_handler>
<error_handler_params>Not supported</error_handler_params>
</step>
</preprocessing>
<master_item>
<key>storage.get["{#STORAGE.CMD}"]</key>
</master_item>
<trigger_prototypes>
<trigger_prototype>
<expression>{str("FAILED!")}=1</expression>
<name>{#STORAGE.NAME}: SMART test status is "FAILED"</name>
<priority>AVERAGE</priority>
</trigger_prototype>
</trigger_prototypes>
</item_prototype>
<item_prototype>
<name>{#STORAGE.NAME}: Device model</name>
<type>DEPENDENT</type>
<key>storage.model["{#STORAGE.CMD}"]</key>
<delay>0</delay>
<trends>0</trends>
<value_type>CHAR</value_type>
<description>HDD
SSD
NVME</description>
<applications>
<application>
<name>SMART monitoring (smartctl)</name>
</application>
</applications>
<preprocessing>
<step>
<type>REGEX</type>
<params>(?:Vendor:|Product:|Device [Mm]odel:|Model [Nn]umber:).+ (.+)
\1</params>
<error_handler>CUSTOM_ERROR</error_handler>
<error_handler_params>Not supported</error_handler_params>
</step>
</preprocessing>
<master_item>
<key>storage.get["{#STORAGE.CMD}"]</key>
</master_item>
</item_prototype>
<item_prototype>
<name>{#STORAGE.NAME}: Serial number</name>
<type>DEPENDENT</type>
<key>storage.sn["{#STORAGE.CMD}"]</key>
<delay>0</delay>
<trends>0</trends>
<value_type>CHAR</value_type>
<description>HDD
SSD
NVME</description>
<applications>
<application>
<name>SMART monitoring (smartctl)</name>
</application>
</applications>
<preprocessing>
<step>
<type>REGEX</type>
<params>(?:Serial [Nn]umber:).+ ([\d\w-]+)
\1</params>
<error_handler>CUSTOM_ERROR</error_handler>
<error_handler_params>Not supported</error_handler_params>
</step>
</preprocessing>
<master_item>
<key>storage.get["{#STORAGE.CMD}"]</key>
</master_item>
<trigger_prototypes>
<trigger_prototype>
<expression>{diff()}=1</expression>
<recovery_mode>NONE</recovery_mode>
<name>{#STORAGE.NAME}: Disk has been replaced (new serial number received)</name>
<priority>INFO</priority>
<manual_close>YES</manual_close>
</trigger_prototype>
</trigger_prototypes>
</item_prototype>
<item_prototype>
<name>{#STORAGE.NAME}: ID 05 Reallocated sectors count</name>
<type>DEPENDENT</type>
<key>storage["{#STORAGE.CMD}", 05 Reallocated_Sector_Ct]</key>
<delay>0</delay>
<description>HDD
SSD</description>
<applications>
<application>
<name>SMART monitoring (smartctl)</name>
</application>
</applications>
<preprocessing>
<step>
<type>REGEX</type>
<params>(?:5 Reallocated|Elements in grown defect list:|5 Retired_Block_Count).+ ([0-9]+)
\1</params>
<error_handler>CUSTOM_ERROR</error_handler>
<error_handler_params>Not supported</error_handler_params>
</step>
</preprocessing>
<master_item>
<key>storage.get["{#STORAGE.CMD}"]</key>
</master_item>
<trigger_prototypes>
<trigger_prototype>
<expression>{diff()}=1</expression>
<recovery_mode>RECOVERY_EXPRESSION</recovery_mode>
<recovery_expression>{last()}=0 or {delta(864000)}=0</recovery_expression>
<name>{#STORAGE.NAME}: SMART reallocated sectors count has been registered</name>
<priority>AVERAGE</priority>
<manual_close>YES</manual_close>
<dependencies>
<dependency>
<name>{#STORAGE.NAME}: SMART test status is "FAILED"</name>
<expression>{Template SMARTMONTOOLS:storage.health["{#STORAGE.CMD}"].str("FAILED!")}=1</expression>
</dependency>
</dependencies>
</trigger_prototype>
</trigger_prototypes>
</item_prototype>
<item_prototype>
<name>{#STORAGE.NAME}: ID 09 Power on hours</name>
<type>DEPENDENT</type>
<key>storage["{#STORAGE.CMD}", 09 Power_On_Hours]</key>
<delay>0</delay>
<units>s</units>
<description>HDD
SSD
NVME</description>
<applications>
<application>
<name>SMART monitoring (smartctl)</name>
</application>
</applications>
<preprocessing>
<step>
<type>REGEX</type>
<params>(?:9 Power_On_Hours|Power On Hours:|[Nn]umber of hours powered up|Accumulated power on time).+ ([0-9]+)
\1</params>
<error_handler>CUSTOM_ERROR</error_handler>
<error_handler_params>Not supported</error_handler_params>
</step>
<step>
<type>MULTIPLIER</type>
<params>3600</params>
<error_handler>CUSTOM_ERROR</error_handler>
<error_handler_params>Not supported</error_handler_params>
</step>
</preprocessing>
<master_item>
<key>storage.get["{#STORAGE.CMD}"]</key>
</master_item>
</item_prototype>
<item_prototype>
<name>{#STORAGE.NAME}: ID 10 Spin retry count</name>
<type>DEPENDENT</type>
<key>storage["{#STORAGE.CMD}", 10 Spin_Retry_Count]</key>
<delay>0</delay>
<description>HDD</description>
<applications>
<application>
<name>SMART monitoring (smartctl)</name>
</application>
</applications>
<preprocessing>
<step>
<type>REGEX</type>
<params>(?:10 Spin_Retry_Count).+ ([0-9]+)
\1</params>
<error_handler>CUSTOM_ERROR</error_handler>
<error_handler_params>Not supported</error_handler_params>
</step>
</preprocessing>
<master_item>
<key>storage.get["{#STORAGE.CMD}"]</key>
</master_item>
<trigger_prototypes>
<trigger_prototype>
<expression>{delta(7d)}>0</expression>
<name>{#STORAGE.NAME}: SMART spin retry count has been registered</name>
<priority>AVERAGE</priority>
<manual_close>YES</manual_close>
</trigger_prototype>
</trigger_prototypes>
</item_prototype>
<item_prototype>
<name>{#STORAGE.NAME}: ID 190/194 Temperature</name>
<type>DEPENDENT</type>
<key>storage["{#STORAGE.CMD}", 190/194 Temperature_Celsius]</key>
<delay>0</delay>
<units>°С</units>
<description>HDD
SSD
NVME</description>
<applications>
<application>
<name>SMART monitoring (smartctl)</name>
</application>
</applications>
<preprocessing>
<step>
<type>REGEX</type>
<params>(?:190 Temperature|190 Airflow_Temperature|194 Temperature|Drive Temperature:|Temperature:).+ \w* (\d+)
\1</params>
<error_handler>CUSTOM_ERROR</error_handler>
<error_handler_params>Not supported</error_handler_params>
</step>
</preprocessing>
<master_item>
<key>storage.get["{#STORAGE.CMD}"]</key>
</master_item>
<trigger_prototypes>
<trigger_prototype>
<expression>{avg(5m)}>{$TEMP_CRIT} and
{last()}<=100</expression>
<recovery_mode>RECOVERY_EXPRESSION</recovery_mode>
<recovery_expression>{avg(5m)}<{$TEMP_CRIT}-3</recovery_expression>
<name>{#STORAGE.NAME}: Disk temperature is "CRITICAL"</name>
<priority>AVERAGE</priority>
<manual_close>YES</manual_close>
</trigger_prototype>
<trigger_prototype>
<expression>{avg(5m)}>{$TEMP_WARN}</expression>
<recovery_mode>RECOVERY_EXPRESSION</recovery_mode>
<recovery_expression>{avg(5m)}<{$TEMP_WARN}-3</recovery_expression>
<name>{#STORAGE.NAME}: Disk temperature is "WARNING"</name>
<priority>WARNING</priority>
<manual_close>YES</manual_close>
<dependencies>
<dependency>
<name>{#STORAGE.NAME}: Disk temperature is "CRITICAL"</name>
<expression>{Template SMARTMONTOOLS:storage["{#STORAGE.CMD}", 190/194 Temperature_Celsius].avg(5m)}>{$TEMP_CRIT} and
{Template SMARTMONTOOLS:storage["{#STORAGE.CMD}", 190/194 Temperature_Celsius].last()}<=100</expression>
<recovery_expression>{Template SMARTMONTOOLS:storage["{#STORAGE.CMD}", 190/194 Temperature_Celsius].avg(5m)}<{$TEMP_CRIT}-3</recovery_expression>
</dependency>
</dependencies>
</trigger_prototype>
</trigger_prototypes>
</item_prototype>
<item_prototype>
<name>{#STORAGE.NAME}: ID 197 Current pending sector count</name>
<type>DEPENDENT</type>
<key>storage["{#STORAGE.CMD}", 197 Current_Pending_Sector]</key>
<delay>0</delay>
<description>HDD</description>
<applications>
<application>
<name>SMART monitoring (smartctl)</name>
</application>
</applications>
<preprocessing>
<step>
<type>REGEX</type>
<params>(?:197 Current_Pending_Sector|197\s+\w+_\w+).+ ([0-9]+)
\1</params>
<error_handler>CUSTOM_ERROR</error_handler>
<error_handler_params>Not supported</error_handler_params>
</step>
</preprocessing>
<master_item>
<key>storage.get["{#STORAGE.CMD}"]</key>
</master_item>
<trigger_prototypes>
<trigger_prototype>
<expression>{delta(3d)}>0</expression>
<name>{#STORAGE.NAME}: SMART current pending sector counter has been registered</name>
<priority>WARNING</priority>
<manual_close>YES</manual_close>
<dependencies>
<dependency>
<name>{#STORAGE.NAME}: SMART reallocated sectors count has been registered</name>
<expression>{Template SMARTMONTOOLS:storage["{#STORAGE.CMD}", 05 Reallocated_Sector_Ct].diff()}=1</expression>
<recovery_expression>{Template SMARTMONTOOLS:storage["{#STORAGE.CMD}", 05 Reallocated_Sector_Ct].last()}=0 or {Template SMARTMONTOOLS:storage["{#STORAGE.CMD}", 05 Reallocated_Sector_Ct].delta(864000)}=0</recovery_expression>
</dependency>
<dependency>
<name>{#STORAGE.NAME}: SMART test status is "FAILED"</name>
<expression>{Template SMARTMONTOOLS:storage.health["{#STORAGE.CMD}"].str("FAILED!")}=1</expression>
</dependency>
</dependencies>
</trigger_prototype>
</trigger_prototypes>
</item_prototype>
<item_prototype>
<name>{#STORAGE.NAME}: ID 198 Uncorrectable errors count</name>
<type>DEPENDENT</type>
<key>storage["{#STORAGE.CMD}", 198 Offline_Uncorrectable]</key>
<delay>0</delay>
<description>HDD
SSD</description>
<applications>
<application>
<name>SMART monitoring (smartctl)</name>
</application>
</applications>
<preprocessing>
<step>
<type>REGEX</type>
<params>(?:Offline_Uncorrectable).+ ([0-9]+)
\1</params>
<error_handler>CUSTOM_ERROR</error_handler>
<error_handler_params>Not supported</error_handler_params>
</step>
</preprocessing>
<master_item>
<key>storage.get["{#STORAGE.CMD}"]</key>
</master_item>
<trigger_prototypes>
<trigger_prototype>
<expression>{diff()}=1</expression>
<name>{#STORAGE.NAME}: SMART uncorrectable sector count has been registered</name>
<priority>AVERAGE</priority>
<manual_close>YES</manual_close>
<dependencies>
<dependency>
<name>{#STORAGE.NAME}: SMART test status is "FAILED"</name>
<expression>{Template SMARTMONTOOLS:storage.health["{#STORAGE.CMD}"].str("FAILED!")}=1</expression>
</dependency>
</dependencies>
</trigger_prototype>
</trigger_prototypes>
</item_prototype>
<item_prototype>
<name>{#STORAGE.NAME}: ID 199/218 CRC error count</name>
<type>DEPENDENT</type>
<key>storage["{#STORAGE.CMD}", 199/218 UDMA_CRC_Error]</key>
<delay>0</delay>
<description>HDD
SSD
NVME</description>
<applications>
<application>
<name>SMART monitoring (smartctl)</name>
</application>
</applications>
<preprocessing>
<step>
<type>REGEX</type>
<params>(?:199 UDMA_CRC_Error|199 CRC_Error_Count|Non-medium error count:|Media and Data Integrity Errors:|199 SATA_CRC_Error|218 CRC_Error_Count).+ ([0-9]+)
\1</params>
<error_handler>CUSTOM_ERROR</error_handler>
<error_handler_params>Not supported</error_handler_params>
</step>
</preprocessing>
<master_item>
<key>storage.get["{#STORAGE.CMD}"]</key>
</master_item>
<trigger_prototypes>
<trigger_prototype>
<expression>{last()}>100 and {delta(1d)}>0</expression>
<name>{#STORAGE.NAME}: SMART UDMA CRC error count too high has been registered</name>
<priority>AVERAGE</priority>
<manual_close>YES</manual_close>
</trigger_prototype>
</trigger_prototypes>
</item_prototype>
<item_prototype>
<name>{#STORAGE.NAME}: ID 231 SSD life left</name>
<type>DEPENDENT</type>
<key>storage["{#STORAGE.CMD}", 231 SSD_Life_Left]</key>
<delay>0</delay>
<units>%</units>
<description>SSD
NVME</description>
<applications>
<application>
<name>SMART monitoring (smartctl)</name>
</application>
</applications>
<preprocessing>
<step>
<type>REGEX</type>
<params>(?:231 SSD_Life_Left |Available Spare: |231\s+\w+_\w+).+ ([0-9]+)
\1</params>
<error_handler>CUSTOM_ERROR</error_handler>
<error_handler_params>Not supported</error_handler_params>
</step>
<step>
<type>IN_RANGE</type>
<params>0
100</params>
<error_handler>CUSTOM_ERROR</error_handler>
<error_handler_params>Not supported</error_handler_params>
</step>
</preprocessing>
<master_item>
<key>storage.get["{#STORAGE.CMD}"]</key>
</master_item>
<trigger_prototypes>
<trigger_prototype>
<expression>{last()}<=10</expression>
<recovery_mode>RECOVERY_EXPRESSION</recovery_mode>
<recovery_expression>{last()}>10</recovery_expression>
<name>{#STORAGE.NAME}: SMART SSD life left</name>
<priority>AVERAGE</priority>
<manual_close>YES</manual_close>
</trigger_prototype>
</trigger_prototypes>
</item_prototype>
</item_prototypes>
<graph_prototypes>
<graph_prototype>
<name>{#STORAGE.NAME}: Smartctl temperature</name>
<graph_items>
<graph_item>
<color>1A7C11</color>
<item>
<host>Template SMARTMONTOOLS</host>
<key>storage["{#STORAGE.CMD}", 190/194 Temperature_Celsius]</key>
</item>
</graph_item>
</graph_items>
</graph_prototype>
</graph_prototypes>
</discovery_rule>
</discovery_rules>
<macros>
<macro>
<macro>{$TEMP_CRIT}</macro>
<value>65</value>
</macro>
<macro>
<macro>{$TEMP_WARN}</macro>
<value>55</value>
</macro>
</macros>
</template>
</templates>
</zabbix_export>