Automatic commit of package [zabbix-agent-addons] release [0.2.172-1].

Created by command:

/usr/bin/tito tag

.tito/packages/zabbix-agent-addons

@@ -1 +1 @@
-0.2.171-1 ./
+0.2.172-1 ./

zabbix-agent-addons.spec

@@ -4,7 +4,7 @@
 
 Summary: Scripts for Zabbix monitoring
 Name: zabbix-agent-addons
-Version: 0.2.171
+Version: 0.2.172
 Release: 1%{?dist}
 Source0: %{name}-%{version}.tar.gz
 BuildArch: noarch
@@ -106,6 +106,16 @@ fi
 %endif
 
 %changelog
+* Thu Dec 21 2023 Daniel Berteaud <dbd@ehtrace.com> 0.2.172-1
+- Add Zabbix template for storageDevices (dbd@ehtrace.com)
+- Read raw value for SSL_Life_Left (dbd@ehtrace.com)
+- Read SSD_Life_Left if available (dbd@ehtrace.com)
+- /dev/bus/0 might not exist but can be queried (dbd@ehtrace.com)
+- Report more info from some NVMe (dbd@ehtrace.com)
+- Adjust default values for stor dev (dbd@ehtrace.com)
+- Fix UserParam (dbd@ehtrace.com)
+- Add new script for smart monitoring (dbd@ehtrace.com)
+
 * Tue Sep 19 2023 Daniel Berteaud <dbd@ehtrace.com> 0.2.171-1
 - Ignore samba NT_STATUS_PROTOCOL_UNREACHABLE errors (dbd@ehtrace.com)
 

zabbix_conf/smart.conf

@@ -5,3 +5,7 @@ UserParameter=hardware.disk.smart.discovery,/usr/bin/sudo /var/lib/zabbix/bin/di
 # Takes two args: the drives to check, and the value to get
 # eg: hardward.disk.smart[/dev/sda,Reallocated_Sector_Ct]
 UserParameter=hardware.disk.smart[*],/usr/bin/sudo /var/lib/zabbix/bin/check_smart_sudo $1 $2
+
+# New smart disk discovery/monitoring
+UserParameter=stor.dev.discovery[*],/usr/bin/sudo /var/lib/zabbix/bin/disco_stor_dev_sudo
+UserParameter=stor.dev.info[*],/usr/bin/sudo /var/lib/zabbix/bin/check_stor_dev_sudo --dev "$1" --type "$2"

zabbix_scripts/check_stor_dev_sudo

@@ -0,0 +1,120 @@
+#!/usr/bin/perl
+
+use strict;
+use warnings;
+use JSON;
+use Getopt::Long;
+use File::Which;
+
+my $dev    =  undef;
+my $type   = 'auto';
+my $what   = 'json';
+my $pretty = 0;
+
+GetOptions(
+  'device=s' => \$dev,
+  'type=s'   => \$type,
+  'what=s'   => \$what,
+  'pretty'   => \$pretty
+);
+
+if (not defined $dev or $dev !~ m|^/dev/\w+(/\w+)*$|){
+  print "Invalid --device\n";
+  exit 1;
+} elsif ($what !~ m/^\w+$/){
+  print "Invalid --what\n";
+  exit 1;
+} elsif ($type !~ m/^\w+\+*\w+(,\w+)*$/){
+  print "Invalid --type\n";
+  exit 1;
+}
+
+my $json = {
+  temperature_celsius      => 25,
+  power_on_hours           => 0,
+  power_cycle_count        => 0,
+  reallocated_sector_count => 0,
+  current_pending_sector   => 0,
+  offline_uncorrectable    => 0,
+  percent_lifetime_remain  => 100,
+  firmware_version         => 0
+};
+my $smartctl = which('smartctl');
+
+sub print_out {
+  if ($what eq 'json'){
+    print to_json($json, { pretty => $pretty });
+    exit 0;
+  } elsif (defined $json->{$what}){
+    print $json->{$what} . "\n";
+    exit 0;
+  } else {
+    print "ZBX_NOTSUPPORTED\n";
+    exit 1;
+  }
+}
+
+sub get_smart_attr {
+  my $smart = shift;
+  my $attr  = shift;
+
+  if (defined $smart->{ata_smart_attributes}->{table}){
+    foreach (@{$smart->{ata_smart_attributes}->{table}}){
+      if ($_->{name} eq $attr){
+        return $_;
+      }
+    }
+  }
+  return undef;
+}
+
+if (not defined $smartctl){
+  $what = 'error';
+  print_out();
+}
+
+my $data = from_json(qx($smartctl -a $dev -d $type --json=c));
+
+if (defined $data->{temperature}->{current}){
+  $json->{temperature_celsius} = $data->{temperature}->{current};
+}
+
+if (defined $data->{power_on_time}->{hours}){
+  $json->{power_on_hours} = $data->{power_on_time}->{hours};
+}
+
+if (defined $data->{power_cycle_count}){
+  $json->{power_cycle_count} = $data->{power_cycle_count};
+}
+
+if (defined $data->{firmware_version}){
+  $json->{firmware_version} = $data->{firmware_version};
+}
+
+my ($pending, $realloc, $offline, $remain);
+if ($pending = get_smart_attr($data, 'Current_Pending_Sector')){
+  $json->{current_pending_sector} = $pending->{raw}->{value};
+}
+
+if ($realloc = get_smart_attr($data, 'Reallocated_Sector_Ct') || get_smart_attr($data, 'Reallocated_Event_Count')){
+  $json->{reallocated_sector_count} = $realloc->{raw}->{value};
+} elsif (defined $data->{nvme_smart_health_information_log}->{media_errors}){
+  # NMVe can report media error, so report it as reallocated sectors
+  $json->{reallocated_sector_count} = $data->{nvme_smart_health_information_log}->{media_errors};
+}
+
+if ($offline = get_smart_attr($data, 'Offline_Uncorrectable')){
+  $json->{offline_uncorrectable} = $offline->{raw}->{value};
+}
+
+if ($remain = get_smart_attr($data, 'Percent_Lifetime_Remain')){
+  $json->{percent_lifetime_remain} = $remain->{value};
+} elsif ($remain = get_smart_attr($data, 'SSD_Life_Left')){
+  $json->{percent_lifetime_remain} = $remain->{raw}->{value};
+} elsif ($remain = get_smart_attr($data, 'Wear_Leveling_Count')){
+  $json->{percent_lifetime_remain} = $remain->{value};
+} elsif (defined $data->{nvme_smart_health_information_log}->{percentage_used}){
+  # NMVe sometime report the estimated life used, instead of the remaining
+  $json->{percent_lifetime_remain} = 100 - $data->{nvme_smart_health_information_log}->{percentage_used};
+}
+print_out();

zabbix_scripts/disco_stor_dev_sudo

@@ -0,0 +1,61 @@
+#!/usr/bin/perl
+
+use strict;
+use JSON;
+use Getopt::Long;
+use Data::Dumper;
+use File::Which;
+
+my $pretty = 0;
+
+GetOptions(
+  'pretty' => \$pretty
+);
+
+my $smartctl = which('smartctl');
+my $json = [];
+
+sub print_out {
+  print to_json($json, { pretty => $pretty });
+}
+
+if (not defined $smartctl){
+  print_out();
+  exit 0;
+}
+
+my $smart_scan = from_json(qx($smartctl --scan-open --json=c));
+
+if (not defined $smart_scan){
+  print_out();
+  exit 0;
+}
+
+foreach my $device (@{$smart_scan->{devices}}){
+  my ($model, $sn, $has_smart) = "";
+  my $smart_info = from_json(qx($smartctl -i $device->{name} -d $device->{type} --json=c));
+
+  if (defined $smart_info){
+    $model     = $smart_info->{model_name};
+    $sn        = $smart_info->{serial_number};
+    $has_smart = (
+      $smart_info->{in_smartctl_database} or (
+        defined $smart_info->{smart_support} and
+        $smart_info->{smart_support}->{available} and
+        $smart_info->{smart_support}->{enabled}
+      )
+    ) ? 1 : 0;
+  }
+
+  push @{$json}, {
+    '{#STOR_DEV_NAME}'  => $device->{name},
+    '{#STOR_DEV_DESC}'  => $device->{info_name},
+    '{#STOR_DEV_TYPE}'  => $device->{type},
+    '{#STOR_DEV_PROTO}' => $device->{protocol},
+    '{#STOR_DEV_MODEL}' => $model,
+    '{#STOR_DEV_SN}'    => $sn,
+    '{#STOR_DEV_SMART}' => int $has_smart
+  };
+}
+
+print_out();

zabbix_templates/Template_HW_storageDevices.yaml

@@ -0,0 +1,195 @@
+zabbix_export:
+  version: '6.0'
+  date: '2023-12-21T14:57:39Z'
+  groups:
+    - uuid: 7df96b18c230490a9a0a9e2307226338
+      name: Templates
+  templates:
+    - uuid: 98cb8260bbeb4a94a8b07b54608521c8
+      template: Template_HW_storageDevices
+      name: Template_HW_storageDevices
+      groups:
+        - name: Templates
+      discovery_rules:
+        - uuid: 12b9a456943f49aca440958063a5bfe2
+          name: 'SMART capable Storage devices discovery'
+          key: 'stor.dev.discovery[smart]'
+          delay: 1h
+          filter:
+            conditions:
+              - macro: '{#STOR_DEV_SMART}'
+                value: ^1$
+                formulaid: A
+          lifetime: 7d
+          item_prototypes:
+            - uuid: 0743506e1c1b49f5b47bd5cef5462c55
+              name: 'Stor dev {#STOR_DEV_SN} ({#STOR_DEV_DESC}): Pending sectors'
+              type: DEPENDENT
+              key: 'stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE},current_pending_sector]'
+              delay: '0'
+              history: 30d
+              value_type: FLOAT
+              units: '!sector(s)'
+              preprocessing:
+                - type: JSONPATH
+                  parameters:
+                    - $.current_pending_sector
+              master_item:
+                key: 'stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE}]'
+              trigger_prototypes:
+                - uuid: 9ffa5efc061542e8a5f227936396e5ab
+                  expression: 'change(/Template_HW_storageDevices/stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE},current_pending_sector])>0'
+                  recovery_mode: NONE
+                  name: '{ITEM.LASTVALUE1} pending on {#STOR_DEV_SN} ({#STOR_DEV_DESC})'
+                  priority: AVERAGE
+                  manual_close: 'YES'
+            - uuid: 3da3d8491a024c7ab4f0bb3fc3887a64
+              name: 'Stor dev {#STOR_DEV_SN} ({#STOR_DEV_DESC}): Firmware version'
+              type: DEPENDENT
+              key: 'stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE},firmware_version]'
+              delay: '0'
+              history: 30d
+              trends: '0'
+              value_type: CHAR
+              preprocessing:
+                - type: JSONPATH
+                  parameters:
+                    - $.firmware_version
+              master_item:
+                key: 'stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE}]'
+            - uuid: 6d4967ca28f549048a507209737fa7bd
+              name: 'Stor dev {#STOR_DEV_SN} ({#STOR_DEV_DESC}): Offline uncorrectable'
+              type: DEPENDENT
+              key: 'stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE},offline_uncorrectable]'
+              delay: '0'
+              history: 30d
+              value_type: FLOAT
+              units: '!sector(s)'
+              preprocessing:
+                - type: JSONPATH
+                  parameters:
+                    - $.offline_uncorrectable
+              master_item:
+                key: 'stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE}]'
+              trigger_prototypes:
+                - uuid: 66c5fc3a96354eb3aae8d5a08eea4544
+                  expression: 'change(/Template_HW_storageDevices/stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE},offline_uncorrectable])>0'
+                  recovery_mode: NONE
+                  name: '{ITEM.LASTVALUE1} offline uncorrectable on {#STOR_DEV_SN} ({#STOR_DEV_DESC})'
+                  priority: HIGH
+                  manual_close: 'YES'
+            - uuid: df1ef0de1bc54200895a5d173a583905
+              name: 'Stor dev {#STOR_DEV_SN} ({#STOR_DEV_DESC}): Percent Lifetime Remain'
+              type: DEPENDENT
+              key: 'stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE},percent_lifetime_remain]'
+              delay: '0'
+              history: 30d
+              value_type: FLOAT
+              units: '%'
+              preprocessing:
+                - type: JSONPATH
+                  parameters:
+                    - $.percent_lifetime_remain
+              master_item:
+                key: 'stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE}]'
+              trigger_prototypes:
+                - uuid: caaa6496f8e941a08f37c8746bb34bc2
+                  expression: 'last(/Template_HW_storageDevices/stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE},percent_lifetime_remain])<{$STOR_LIFETIME_REMAINING_CRITICAL:"{#STOR_DEV_SN}"}'
+                  name: '{ITEM.LASTVALUE1} lifetime remaining for {#STOR_DEV_SN} ({#STOR_DEV_DESC})'
+                  priority: HIGH
+                  manual_close: 'YES'
+                - uuid: 1df675ca6c4649a081ea315599ce4284
+                  expression: 'last(/Template_HW_storageDevices/stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE},percent_lifetime_remain])<{$STOR_LIFETIME_REMAINING_WARN:"{#STOR_DEV_SN}"}'
+                  name: '{ITEM.LASTVALUE1} lifetime remaining for {#STOR_DEV_SN} ({#STOR_DEV_DESC})'
+                  priority: WARNING
+                  manual_close: 'YES'
+                  dependencies:
+                    - name: '{ITEM.LASTVALUE1} lifetime remaining for {#STOR_DEV_SN} ({#STOR_DEV_DESC})'
+                      expression: 'last(/Template_HW_storageDevices/stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE},percent_lifetime_remain])<{$STOR_LIFETIME_REMAINING_CRITICAL:"{#STOR_DEV_SN}"}'
+            - uuid: 70dd4bcd3994423594f7330bbb448038
+              name: 'Stor dev {#STOR_DEV_SN} ({#STOR_DEV_DESC}): Power Cycle Count'
+              type: DEPENDENT
+              key: 'stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE},power_cycle_count]'
+              delay: '0'
+              history: 30d
+              value_type: FLOAT
+              preprocessing:
+                - type: JSONPATH
+                  parameters:
+                    - $.power_cycle_count
+              master_item:
+                key: 'stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE}]'
+            - uuid: f68f569400954636a7e4231c97c57c81
+              name: 'Stor dev {#STOR_DEV_SN} ({#STOR_DEV_DESC}): Power on hours'
+              type: DEPENDENT
+              key: 'stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE},power_on_hours]'
+              delay: '0'
+              history: 30d
+              value_type: FLOAT
+              units: s
+              preprocessing:
+                - type: JSONPATH
+                  parameters:
+                    - $.power_on_hours
+                - type: MULTIPLIER
+                  parameters:
+                    - '3600'
+              master_item:
+                key: 'stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE}]'
+            - uuid: 76e724749c304d7da9c38b81bfb9b711
+              name: 'Stor dev {#STOR_DEV_SN} ({#STOR_DEV_DESC}): Reallocated Sectors'
+              type: DEPENDENT
+              key: 'stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE},reallocated_sector_count]'
+              delay: '0'
+              history: 30d
+              value_type: FLOAT
+              units: '!sector(s)'
+              preprocessing:
+                - type: JSONPATH
+                  parameters:
+                    - $.reallocated_sector_count
+              master_item:
+                key: 'stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE}]'
+              trigger_prototypes:
+                - uuid: f7b3fa0f6a8347e3b67387da531a2d1a
+                  expression: 'change(/Template_HW_storageDevices/stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE},reallocated_sector_count])>0'
+                  recovery_mode: NONE
+                  name: '{ITEM.LASTVALUE1} reallocated on {#STOR_DEV_SN} ({#STOR_DEV_DESC})'
+                  priority: WARNING
+                  manual_close: 'YES'
+                  dependencies:
+                    - name: '{ITEM.LASTVALUE1} reallocated on {#STOR_DEV_SN} ({#STOR_DEV_DESC})'
+                      expression: 'last(/Template_HW_storageDevices/stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE},reallocated_sector_count])>{$STOR_REALLOC_SECTOR_WARN:"{#STOR_DEV_SN}"}'
+                - uuid: 85d6eb29ca7b4175bf8ad15414a44936
+                  expression: 'last(/Template_HW_storageDevices/stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE},reallocated_sector_count])>{$STOR_REALLOC_SECTOR_WARN:"{#STOR_DEV_SN}"}'
+                  name: '{ITEM.LASTVALUE1} reallocated on {#STOR_DEV_SN} ({#STOR_DEV_DESC})'
+                  priority: AVERAGE
+                  manual_close: 'YES'
+            - uuid: 28117d0d998f467ea542821e4a6507c9
+              name: 'Stor dev {#STOR_DEV_SN} ({#STOR_DEV_DESC}): Temperature'
+              type: DEPENDENT
+              key: 'stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE},temperature_celsius]'
+              delay: '0'
+              history: 30d
+              value_type: FLOAT
+              units: °C
+              preprocessing:
+                - type: JSONPATH
+                  parameters:
+                    - $.temperature_celsius
+              master_item:
+                key: 'stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE}]'
+            - uuid: 6d3da698590e43f4be62d5daab7f72f0
+              name: 'Stor dev {#STOR_DEV_SN} ({#STOR_DEV_DESC}) info'
+              key: 'stor.dev.info[{#STOR_DEV_NAME},{#STOR_DEV_TYPE}]'
+              delay: 8m
+              history: '0'
+              trends: '0'
+              value_type: TEXT
+      macros:
+        - macro: '{$STOR_LIFETIME_REMAINING_CRITICAL}'
+          value: '6'
+        - macro: '{$STOR_LIFETIME_REMAINING_WARN}'
+          value: '10'
+        - macro: '{$STOR_REALLOC_SECTOR_WARN}'
+          value: '40'