From 382e53b099c76b0a16ac66fda2b1b34847c3e2f6 Mon Sep 17 00:00:00 2001
From: Fulvio Galeazzi <fulvio.galeazzi@garr.it>
Date: Mon, 13 May 2019 14:10:38 +0200
Subject: [PATCH] 2019-05-13: FG; Added GPU monitoring.
---
Any/Sudo/zabbix | 4 +-
GPU/Config/userparameter_nvidia-smi.conf | 9 +
.../userparameter_nvidia-smi.conf.linux | 9 +
.../userparameter_nvidia-smi.conf.windows | 9 +
GPU/README.md | 44 ++
GPU/Script/get_gpus_info.bat | 35 ++
GPU/Script/get_gpus_info.sh | 27 +
GPU/Template/zbx_nvidia-smi-multi-gpu.xml | 587 ++++++++++++++++++
8 files changed, 723 insertions(+), 1 deletion(-)
create mode 100644 GPU/Config/userparameter_nvidia-smi.conf
create mode 100644 GPU/Config/userparameter_nvidia-smi.conf.linux
create mode 100644 GPU/Config/userparameter_nvidia-smi.conf.windows
create mode 100644 GPU/README.md
create mode 100644 GPU/Script/get_gpus_info.bat
create mode 100755 GPU/Script/get_gpus_info.sh
create mode 100644 GPU/Template/zbx_nvidia-smi-multi-gpu.xml
diff --git a/Any/Sudo/zabbix b/Any/Sudo/zabbix
index 2571ccd..464cb03 100644
--- a/Any/Sudo/zabbix
+++ b/Any/Sudo/zabbix
@@ -11,4 +11,6 @@ Cmnd_Alias ZBXSMCLI = /bin/SMcli, /usr/bin/SMcli, /opt/dell/mdstoragemanager/c
Cmnd_Alias ZBXPDNS = /usr/bin/pdns_control, /usr/bin/rec_control
-zabbix ALL = (root) NOPASSWD: ZBXCEPH, ZBXMULTIPATH, ZBXCRMCMD, ZBXHAPROXY, ZBXIPSTATE, ZBXPS, ZBXSMCLI, ZBXPDNS
+Cmnd_Alias ZBXNVIDIA = /usr/bin/nvidia-smi
+
+zabbix ALL = (root) NOPASSWD: ZBXCEPH, ZBXMULTIPATH, ZBXCRMCMD, ZBXHAPROXY, ZBXIPSTATE, ZBXPS, ZBXSMCLI, ZBXPDNS, ZBXNVIDIA
diff --git a/GPU/Config/userparameter_nvidia-smi.conf b/GPU/Config/userparameter_nvidia-smi.conf
new file mode 100644
index 0000000..970f08a
--- /dev/null
+++ b/GPU/Config/userparameter_nvidia-smi.conf
@@ -0,0 +1,9 @@
+UserParameter=gpu.number,/usr/bin/nvidia-smi -L | /usr/bin/wc -l
+UserParameter=gpu.discovery,/etc/zabbix/scripts/get_gpus_info.sh
+UserParameter=gpu.fanspeed[*],nvidia-smi --query-gpu=fan.speed --format=csv,noheader,nounits -i $1 | tr -d "\n"
+UserParameter=gpu.power[*],nvidia-smi --query-gpu=power.draw --format=csv,noheader,nounits -i $1 | tr -d "\n"
+UserParameter=gpu.temp[*],nvidia-smi --query-gpu=temperature.gpu --format=csv,noheader,nounits -i $1 | tr -d "\n"
+UserParameter=gpu.utilization[*],nvidia-smi --query-gpu=utilization.gpu --format=csv,noheader,nounits -i $1 | tr -d "\n"
+UserParameter=gpu.memfree[*],nvidia-smi --query-gpu=memory.free --format=csv,noheader,nounits -i $1 | tr -d "\n"
+UserParameter=gpu.memused[*],nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits -i $1 | tr -d "\n"
+UserParameter=gpu.memtotal[*],nvidia-smi --query-gpu=memory.total --format=csv,noheader,nounits -i $1 | tr -d "\n"
diff --git a/GPU/Config/userparameter_nvidia-smi.conf.linux b/GPU/Config/userparameter_nvidia-smi.conf.linux
new file mode 100644
index 0000000..970f08a
--- /dev/null
+++ b/GPU/Config/userparameter_nvidia-smi.conf.linux
@@ -0,0 +1,9 @@
+UserParameter=gpu.number,/usr/bin/nvidia-smi -L | /usr/bin/wc -l
+UserParameter=gpu.discovery,/etc/zabbix/scripts/get_gpus_info.sh
+UserParameter=gpu.fanspeed[*],nvidia-smi --query-gpu=fan.speed --format=csv,noheader,nounits -i $1 | tr -d "\n"
+UserParameter=gpu.power[*],nvidia-smi --query-gpu=power.draw --format=csv,noheader,nounits -i $1 | tr -d "\n"
+UserParameter=gpu.temp[*],nvidia-smi --query-gpu=temperature.gpu --format=csv,noheader,nounits -i $1 | tr -d "\n"
+UserParameter=gpu.utilization[*],nvidia-smi --query-gpu=utilization.gpu --format=csv,noheader,nounits -i $1 | tr -d "\n"
+UserParameter=gpu.memfree[*],nvidia-smi --query-gpu=memory.free --format=csv,noheader,nounits -i $1 | tr -d "\n"
+UserParameter=gpu.memused[*],nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits -i $1 | tr -d "\n"
+UserParameter=gpu.memtotal[*],nvidia-smi --query-gpu=memory.total --format=csv,noheader,nounits -i $1 | tr -d "\n"
diff --git a/GPU/Config/userparameter_nvidia-smi.conf.windows b/GPU/Config/userparameter_nvidia-smi.conf.windows
new file mode 100644
index 0000000..f17cb19
--- /dev/null
+++ b/GPU/Config/userparameter_nvidia-smi.conf.windows
@@ -0,0 +1,9 @@
+UserParameter=gpu.number,"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" -L | find /c /v ""
+UserParameter=gpu.discovery,C:\scripts\get_gpus_info.bat
+UserParameter=gpu.fanspeed[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=fan.speed --format=csv,noheader,nounits -i $1
+UserParameter=gpu.power[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=power.draw --format=csv,noheader,nounits -i $1
+UserParameter=gpu.temp[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=temperature.gpu --format=csv,noheader,nounits -i $1
+UserParameter=gpu.utilization[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=utilization.gpu --format=csv,noheader,nounits -i $1
+UserParameter=gpu.memfree[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=memory.free --format=csv,noheader,nounits -i $1
+UserParameter=gpu.memused[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=memory.used --format=csv,noheader,nounits -i $1
+UserParameter=gpu.memtotal[*],"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" --query-gpu=memory.total --format=csv,noheader,nounits -i $1
diff --git a/GPU/README.md b/GPU/README.md
new file mode 100644
index 0000000..888af9a
--- /dev/null
+++ b/GPU/README.md
@@ -0,0 +1,44 @@
+#
+# This is copied from:
+# https://github.com/plambe/zabbix-nvidia-smi-multi-gpu
+########
+#
+# zabbix-nvidia-smi-multi-gpu
+A zabbix template using nvidia-smi. Works with multiple GPUs on Windows and Linux.
+
+## Features:
+
+- low-level discovery of all the graphics cards
+- item prototypes for:
+ - fan speed
+ - total, free and used memory
+ - power draw in decaWatts (tens of Watts, so that it can fit in the graphs nicely)
+ - temperature
+ - utilization
+- a graph prototype having the fan speed, power draw and temperature in one graph
+- trigger prototypes set at different GPU temperatures
+- a batch script for low-level discovery on Windows
+- a BASH script for low-level discovery on Linux
+
+Events caused by the triggers:
+
+
+And the graphs:
+
+
+This is essentially a multi-GPU rewrite of RichardKav's template, as found here: https://github.com/RichardKav/zabbix-nvidia-smi-integration/
+
+## On Windows:
+
+* Add the contents of the file `userparameter_nvidia-smi.conf.windows` to your zabbix_agentd.conf file.
+* The Windows script get_gpus_info.bat file should be put in C:\scripts\
+* It doesn't have any dependencies, other than having nvidia-smi.exe
+* Of course, it is possible to use other paths, but:
+ * In case you change C:\scripts\, you need to update the "UserParameter=gpu.discovery" line in zabbix_agentd.conf
+ * In case you have installed nvidia-smi.exe in an alternate location, you need to update both the get_gpus_info.bat and the zabbix_agentd.conf
+
+## On Linux:
+
+The following UserParameters need to be added to the zabbix-agent configuration:
+* Add the contents of the file `userparameter_nvidia-smi.conf.linux` to your zabbix_agentd.conf file.
+* The get_gpus_info.sh file should be put in /etc/zabbix/scripts/ and made executable by running ```chmod +x get_gpus_info.sh```
diff --git a/GPU/Script/get_gpus_info.bat b/GPU/Script/get_gpus_info.bat
new file mode 100644
index 0000000..abd2e45
--- /dev/null
+++ b/GPU/Script/get_gpus_info.bat
@@ -0,0 +1,35 @@
+@ECHO OFF
+SETLOCAL ENABLEDELAYEDEXPANSION
+
+echo {
+echo "data":[
+
+SET count=1
+FOR /F "tokens=* USEBACKQ" %%F IN (`"C:\Program Files\NVIDIA Corporation\NVSMI\nvidia-smi.exe" -L`) DO (
+ if !count! GTR 1 echo ,
+
+ SET line=%%F
+ SET var!count!=%%F
+ SET /a count=!count!+1
+ for /f "tokens=1 delims=:" %%A in ('echo %%F') do (
+ for /f "tokens=2 delims= " %%B in ('echo %%A') do (
+ echo|set /p={"{#GPUINDEX}":"
+ echo|set /p=%%B", "
+ )
+ )
+ for /f "tokens=3 delims=:" %%A in ('echo %%F') do (
+ echo|set /p={#GPUUUID}":"
+ for /f "tokens=1 delims= " %%B in ('echo %%A') do (
+ for /f "tokens=1 delims=)" %%C in ('echo %%B') do (
+ echo|set /p=%%C"}
+ )
+ )
+ rem echo|set /p=
+ )
+)
+echo.
+echo ]
+echo }
+
+ENDLOCAL
+
diff --git a/GPU/Script/get_gpus_info.sh b/GPU/Script/get_gpus_info.sh
new file mode 100755
index 0000000..8cc6104
--- /dev/null
+++ b/GPU/Script/get_gpus_info.sh
@@ -0,0 +1,27 @@
+#!/bin/bash
+
+result=$(/usr/bin/nvidia-smi -L)
+first=1
+
+echo "{"
+echo "\"data\":["
+
+while IFS= read -r line
+do
+ if (( "$first" != "1" ))
+ then
+ echo ,
+ fi
+ index=$(echo -n $line | cut -d ":" -f 1 | cut -d " " -f 2)
+ gpuuuid=$(echo -n $line | cut -d ":" -f 3 | tr -d ")" | tr -d " ")
+ echo -n {"\"{#GPUINDEX}"\":\"$index"\", \"{#GPUUUID}"\":\"$gpuuuid\"}
+ if (( "$first" == "1" ))
+ then
+# echo ,
+ first=0
+ fi
+done < <(printf '%s\n' "$result")
+
+echo
+echo "]"
+echo "}"
diff --git a/GPU/Template/zbx_nvidia-smi-multi-gpu.xml b/GPU/Template/zbx_nvidia-smi-multi-gpu.xml
new file mode 100644
index 0000000..7722fd3
--- /dev/null
+++ b/GPU/Template/zbx_nvidia-smi-multi-gpu.xml
@@ -0,0 +1,587 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<zabbix_export>
+ <version>3.0</version>
+ <date>2018-06-05T20:56:12Z</date>
+ <groups>
+ <group>
+ <name>Templates</name>
+ </group>
+ </groups>
+ <templates>
+ <template>
+ <template>Template Nvidia GPUs Performance</template>
+ <name>Template Nvidia GPUs Performance</name>
+ <description/>
+ <groups>
+ <group>
+ <name>Templates</name>
+ </group>
+ </groups>
+ <applications>
+ <application>
+ <name>Nvidia</name>
+ </application>
+ </applications>
+ <items>
+ <item>
+ <name>Number of GPUs</name>
+ <type>0</type>
+ <snmp_community/>
+ <multiplier>0</multiplier>
+ <snmp_oid/>
+ <key>gpu.number</key>
+ <delay>30</delay>
+ <history>90</history>
+ <trends>365</trends>
+ <status>0</status>
+ <value_type>0</value_type>
+ <allowed_hosts/>
+ <units/>
+ <delta>0</delta>
+ <snmpv3_contextname/>
+ <snmpv3_securityname/>
+ <snmpv3_securitylevel>0</snmpv3_securitylevel>
+ <snmpv3_authprotocol>0</snmpv3_authprotocol>
+ <snmpv3_authpassphrase/>
+ <snmpv3_privprotocol>0</snmpv3_privprotocol>
+ <snmpv3_privpassphrase/>
+ <formula>1</formula>
+ <delay_flex/>
+ <params/>
+ <ipmi_sensor/>
+ <data_type>0</data_type>
+ <authtype>0</authtype>
+ <username/>
+ <password/>
+ <publickey/>
+ <privatekey/>
+ <port/>
+ <description>The number of GPUs present on this system.</description>
+ <inventory_link>0</inventory_link>
+ <applications>
+ <application>
+ <name>Nvidia</name>
+ </application>
+ </applications>
+ <valuemap/>
+ <logtimefmt/>
+ </item>
+ </items>
+ <discovery_rules>
+ <discovery_rule>
+ <name>GPU discovery</name>
+ <type>0</type>
+ <snmp_community/>
+ <snmp_oid/>
+ <key>gpu.discovery</key>
+ <delay>600</delay>
+ <status>0</status>
+ <allowed_hosts/>
+ <snmpv3_contextname/>
+ <snmpv3_securityname/>
+ <snmpv3_securitylevel>0</snmpv3_securitylevel>
+ <snmpv3_authprotocol>0</snmpv3_authprotocol>
+ <snmpv3_authpassphrase/>
+ <snmpv3_privprotocol>0</snmpv3_privprotocol>
+ <snmpv3_privpassphrase/>
+ <delay_flex/>
+ <params/>
+ <ipmi_sensor/>
+ <authtype>0</authtype>
+ <username/>
+ <password/>
+ <publickey/>
+ <privatekey/>
+ <port/>
+ <filter>
+ <evaltype>0</evaltype>
+ <formula/>
+ <conditions/>
+ </filter>
+ <lifetime>30</lifetime>
+ <description>Discovery of graphics cards.</description>
+ <item_prototypes>
+ <item_prototype>
+ <name>GPU $1 Fan Speed</name>
+ <type>0</type>
+ <snmp_community/>
+ <multiplier>1</multiplier>
+ <snmp_oid/>
+ <key>gpu.fanspeed[{#GPUINDEX}]</key>
+ <delay>60</delay>
+ <history>7</history>
+ <trends>365</trends>
+ <status>0</status>
+ <value_type>3</value_type>
+ <allowed_hosts/>
+ <units>%</units>
+ <delta>0</delta>
+ <snmpv3_contextname/>
+ <snmpv3_securityname/>
+ <snmpv3_securitylevel>0</snmpv3_securitylevel>
+ <snmpv3_authprotocol>0</snmpv3_authprotocol>
+ <snmpv3_authpassphrase/>
+ <snmpv3_privprotocol>0</snmpv3_privprotocol>
+ <snmpv3_privpassphrase/>
+ <formula>1</formula>
+ <delay_flex/>
+ <params/>
+ <ipmi_sensor/>
+ <data_type>0</data_type>
+ <authtype>0</authtype>
+ <username/>
+ <password/>
+ <publickey/>
+ <privatekey/>
+ <port/>
+ <description/>
+ <inventory_link>0</inventory_link>
+ <applications>
+ <application>
+ <name>Nvidia</name>
+ </application>
+ </applications>
+ <valuemap/>
+ <logtimefmt/>
+ <application_prototypes/>
+ </item_prototype>
+ <item_prototype>
+ <name>GPU $1 Memory Free</name>
+ <type>0</type>
+ <snmp_community/>
+ <multiplier>0</multiplier>
+ <snmp_oid/>
+ <key>gpu.memfree[{#GPUINDEX}]</key>
+ <delay>60</delay>
+ <history>7</history>
+ <trends>365</trends>
+ <status>0</status>
+ <value_type>3</value_type>
+ <allowed_hosts/>
+ <units>MB</units>
+ <delta>0</delta>
+ <snmpv3_contextname/>
+ <snmpv3_securityname/>
+ <snmpv3_securitylevel>0</snmpv3_securitylevel>
+ <snmpv3_authprotocol>0</snmpv3_authprotocol>
+ <snmpv3_authpassphrase/>
+ <snmpv3_privprotocol>0</snmpv3_privprotocol>
+ <snmpv3_privpassphrase/>
+ <formula>1</formula>
+ <delay_flex/>
+ <params/>
+ <ipmi_sensor/>
+ <data_type>0</data_type>
+ <authtype>0</authtype>
+ <username/>
+ <password/>
+ <publickey/>
+ <privatekey/>
+ <port/>
+ <description/>
+ <inventory_link>0</inventory_link>
+ <applications>
+ <application>
+ <name>Nvidia</name>
+ </application>
+ </applications>
+ <valuemap/>
+ <logtimefmt/>
+ <application_prototypes/>
+ </item_prototype>
+ <item_prototype>
+ <name>GPU $1 Memory Total</name>
+ <type>0</type>
+ <snmp_community/>
+ <multiplier>0</multiplier>
+ <snmp_oid/>
+ <key>gpu.memtotal[{#GPUINDEX}]</key>
+ <delay>60</delay>
+ <history>7</history>
+ <trends>365</trends>
+ <status>0</status>
+ <value_type>3</value_type>
+ <allowed_hosts/>
+ <units>MB</units>
+ <delta>0</delta>
+ <snmpv3_contextname/>
+ <snmpv3_securityname/>
+ <snmpv3_securitylevel>0</snmpv3_securitylevel>
+ <snmpv3_authprotocol>0</snmpv3_authprotocol>
+ <snmpv3_authpassphrase/>
+ <snmpv3_privprotocol>0</snmpv3_privprotocol>
+ <snmpv3_privpassphrase/>
+ <formula>1</formula>
+ <delay_flex/>
+ <params/>
+ <ipmi_sensor/>
+ <data_type>0</data_type>
+ <authtype>0</authtype>
+ <username/>
+ <password/>
+ <publickey/>
+ <privatekey/>
+ <port/>
+ <description/>
+ <inventory_link>0</inventory_link>
+ <applications>
+ <application>
+ <name>Nvidia</name>
+ </application>
+ </applications>
+ <valuemap/>
+ <logtimefmt/>
+ <application_prototypes/>
+ </item_prototype>
+ <item_prototype>
+ <name>GPU $1 Memory Used</name>
+ <type>0</type>
+ <snmp_community/>
+ <multiplier>0</multiplier>
+ <snmp_oid/>
+ <key>gpu.memused[{#GPUINDEX}]</key>
+ <delay>60</delay>
+ <history>7</history>
+ <trends>365</trends>
+ <status>0</status>
+ <value_type>3</value_type>
+ <allowed_hosts/>
+ <units>MB</units>
+ <delta>0</delta>
+ <snmpv3_contextname/>
+ <snmpv3_securityname/>
+ <snmpv3_securitylevel>0</snmpv3_securitylevel>
+ <snmpv3_authprotocol>0</snmpv3_authprotocol>
+ <snmpv3_authpassphrase/>
+ <snmpv3_privprotocol>0</snmpv3_privprotocol>
+ <snmpv3_privpassphrase/>
+ <formula>1</formula>
+ <delay_flex/>
+ <params/>
+ <ipmi_sensor/>
+ <data_type>0</data_type>
+ <authtype>0</authtype>
+ <username/>
+ <password/>
+ <publickey/>
+ <privatekey/>
+ <port/>
+ <description/>
+ <inventory_link>0</inventory_link>
+ <applications>
+ <application>
+ <name>Nvidia</name>
+ </application>
+ </applications>
+ <valuemap/>
+ <logtimefmt/>
+ <application_prototypes/>
+ </item_prototype>
+ <item_prototype>
+ <name>GPU $1 Power in decaWatts</name>
+ <type>0</type>
+ <snmp_community/>
+ <multiplier>1</multiplier>
+ <snmp_oid/>
+ <key>gpu.power[{#GPUINDEX}]</key>
+ <delay>60</delay>
+ <history>7</history>
+ <trends>365</trends>
+ <status>0</status>
+ <value_type>0</value_type>
+ <allowed_hosts/>
+ <units>dW</units>
+ <delta>0</delta>
+ <snmpv3_contextname/>
+ <snmpv3_securityname/>
+ <snmpv3_securitylevel>0</snmpv3_securitylevel>
+ <snmpv3_authprotocol>0</snmpv3_authprotocol>
+ <snmpv3_authpassphrase/>
+ <snmpv3_privprotocol>0</snmpv3_privprotocol>
+ <snmpv3_privpassphrase/>
+ <formula>0.1</formula>
+ <delay_flex/>
+ <params/>
+ <ipmi_sensor/>
+ <data_type>0</data_type>
+ <authtype>0</authtype>
+ <username/>
+ <password/>
+ <publickey/>
+ <privatekey/>
+ <port/>
+ <description/>
+ <inventory_link>0</inventory_link>
+ <applications>
+ <application>
+ <name>Nvidia</name>
+ </application>
+ </applications>
+ <valuemap/>
+ <logtimefmt/>
+ <application_prototypes/>
+ </item_prototype>
+ <item_prototype>
+ <name>GPU $1 Temperature</name>
+ <type>0</type>
+ <snmp_community/>
+ <multiplier>0</multiplier>
+ <snmp_oid/>
+ <key>gpu.temp[{#GPUINDEX}]</key>
+ <delay>60</delay>
+ <history>7</history>
+ <trends>365</trends>
+ <status>0</status>
+ <value_type>0</value_type>
+ <allowed_hosts/>
+ <units>C</units>
+ <delta>0</delta>
+ <snmpv3_contextname/>
+ <snmpv3_securityname/>
+ <snmpv3_securitylevel>0</snmpv3_securitylevel>
+ <snmpv3_authprotocol>0</snmpv3_authprotocol>
+ <snmpv3_authpassphrase/>
+ <snmpv3_privprotocol>0</snmpv3_privprotocol>
+ <snmpv3_privpassphrase/>
+ <formula>1</formula>
+ <delay_flex/>
+ <params/>
+ <ipmi_sensor/>
+ <data_type>0</data_type>
+ <authtype>0</authtype>
+ <username/>
+ <password/>
+ <publickey/>
+ <privatekey/>
+ <port/>
+ <description/>
+ <inventory_link>0</inventory_link>
+ <applications>
+ <application>
+ <name>Nvidia</name>
+ </application>
+ </applications>
+ <valuemap/>
+ <logtimefmt/>
+ <application_prototypes/>
+ </item_prototype>
+ <item_prototype>
+ <name>GPU $1 Utilization</name>
+ <type>0</type>
+ <snmp_community/>
+ <multiplier>0</multiplier>
+ <snmp_oid/>
+ <key>gpu.utilization[{#GPUINDEX}]</key>
+ <delay>60</delay>
+ <history>7</history>
+ <trends>365</trends>
+ <status>0</status>
+ <value_type>3</value_type>
+ <allowed_hosts/>
+ <units>%</units>
+ <delta>0</delta>
+ <snmpv3_contextname/>
+ <snmpv3_securityname/>
+ <snmpv3_securitylevel>0</snmpv3_securitylevel>
+ <snmpv3_authprotocol>0</snmpv3_authprotocol>
+ <snmpv3_authpassphrase/>
+ <snmpv3_privprotocol>0</snmpv3_privprotocol>
+ <snmpv3_privpassphrase/>
+ <formula>1</formula>
+ <delay_flex/>
+ <params/>
+ <ipmi_sensor/>
+ <data_type>0</data_type>
+ <authtype>0</authtype>
+ <username/>
+ <password/>
+ <publickey/>
+ <privatekey/>
+ <port/>
+ <description/>
+ <inventory_link>0</inventory_link>
+ <applications>
+ <application>
+ <name>Nvidia</name>
+ </application>
+ </applications>
+ <valuemap/>
+ <logtimefmt/>
+ <application_prototypes/>
+ </item_prototype>
+ </item_prototypes>
+ <trigger_prototypes>
+ <trigger_prototype>
+ <expression>{Template Nvidia GPUs Performance:gpu.temp[{#GPUINDEX}].last()}>80</expression>
+ <name>GPU {#GPUINDEX} Temperature is extremely high</name>
+ <url/>
+ <status>0</status>
+ <priority>5</priority>
+ <description>A GPU's temperature is getting extremely high!</description>
+ <type>0</type>
+ <dependencies/>
+ </trigger_prototype>
+ <trigger_prototype>
+ <expression>{Template Nvidia GPUs Performance:gpu.temp[{#GPUINDEX}].last()}>70</expression>
+ <name>GPU {#GPUINDEX} Temperature is high</name>
+ <url/>
+ <status>0</status>
+ <priority>2</priority>
+ <description>A GPU's temperature is getting high!</description>
+ <type>0</type>
+ <dependencies/>
+ </trigger_prototype>
+ <trigger_prototype>
+ <expression>{Template Nvidia GPUs Performance:gpu.temp[{#GPUINDEX}].last()}>75</expression>
+ <name>GPU {#GPUINDEX} Temperature is very high</name>
+ <url/>
+ <status>0</status>
+ <priority>4</priority>
+ <description>A GPU's temperature is getting very high!</description>
+ <type>0</type>
+ <dependencies/>
+ </trigger_prototype>
+ </trigger_prototypes>
+ <graph_prototypes>
+ <graph_prototype>
+ <name>GPU {#GPUINDEX} Memory</name>
+ <width>900</width>
+ <height>200</height>
+ <yaxismin>0.0000</yaxismin>
+ <yaxismax>100.0000</yaxismax>
+ <show_work_period>1</show_work_period>
+ <show_triggers>1</show_triggers>
+ <type>0</type>
+ <show_legend>1</show_legend>
+ <show_3d>0</show_3d>
+ <percent_left>0.0000</percent_left>
+ <percent_right>0.0000</percent_right>
+ <ymin_type_1>0</ymin_type_1>
+ <ymax_type_1>0</ymax_type_1>
+ <ymin_item_1>0</ymin_item_1>
+ <ymax_item_1>0</ymax_item_1>
+ <graph_items>
+ <graph_item>
+ <sortorder>0</sortorder>
+ <drawtype>0</drawtype>
+ <color>00AA00</color>
+ <yaxisside>0</yaxisside>
+ <calc_fnc>2</calc_fnc>
+ <type>0</type>
+ <item>
+ <host>Template Nvidia GPUs Performance</host>
+ <key>gpu.memfree[{#GPUINDEX}]</key>
+ </item>
+ </graph_item>
+ <graph_item>
+ <sortorder>1</sortorder>
+ <drawtype>0</drawtype>
+ <color>0000DD</color>
+ <yaxisside>0</yaxisside>
+ <calc_fnc>2</calc_fnc>
+ <type>0</type>
+ <item>
+ <host>Template Nvidia GPUs Performance</host>
+ <key>gpu.memused[{#GPUINDEX}]</key>
+ </item>
+ </graph_item>
+ </graph_items>
+ </graph_prototype>
+ <graph_prototype>
+ <name>GPU {#GPUINDEX} Temperature, Fan Speed and Power</name>
+ <width>900</width>
+ <height>200</height>
+ <yaxismin>0.0000</yaxismin>
+ <yaxismax>100.0000</yaxismax>
+ <show_work_period>1</show_work_period>
+ <show_triggers>1</show_triggers>
+ <type>0</type>
+ <show_legend>1</show_legend>
+ <show_3d>0</show_3d>
+ <percent_left>0.0000</percent_left>
+ <percent_right>0.0000</percent_right>
+ <ymin_type_1>0</ymin_type_1>
+ <ymax_type_1>0</ymax_type_1>
+ <ymin_item_1>0</ymin_item_1>
+ <ymax_item_1>0</ymax_item_1>
+ <graph_items>
+ <graph_item>
+ <sortorder>0</sortorder>
+ <drawtype>0</drawtype>
+ <color>1A7C11</color>
+ <yaxisside>0</yaxisside>
+ <calc_fnc>2</calc_fnc>
+ <type>0</type>
+ <item>
+ <host>Template Nvidia GPUs Performance</host>
+ <key>gpu.power[{#GPUINDEX}]</key>
+ </item>
+ </graph_item>
+ <graph_item>
+ <sortorder>1</sortorder>
+ <drawtype>0</drawtype>
+ <color>2774A4</color>
+ <yaxisside>0</yaxisside>
+ <calc_fnc>2</calc_fnc>
+ <type>0</type>
+ <item>
+ <host>Template Nvidia GPUs Performance</host>
+ <key>gpu.fanspeed[{#GPUINDEX}]</key>
+ </item>
+ </graph_item>
+ <graph_item>
+ <sortorder>2</sortorder>
+ <drawtype>0</drawtype>
+ <color>F63100</color>
+ <yaxisside>0</yaxisside>
+ <calc_fnc>2</calc_fnc>
+ <type>0</type>
+ <item>
+ <host>Template Nvidia GPUs Performance</host>
+ <key>gpu.temp[{#GPUINDEX}]</key>
+ </item>
+ </graph_item>
+ </graph_items>
+ </graph_prototype>
+ <graph_prototype>
+ <name>GPU {#GPUINDEX} Utilization</name>
+ <width>900</width>
+ <height>200</height>
+ <yaxismin>0.0000</yaxismin>
+ <yaxismax>100.0000</yaxismax>
+ <show_work_period>1</show_work_period>
+ <show_triggers>1</show_triggers>
+ <type>0</type>
+ <show_legend>1</show_legend>
+ <show_3d>0</show_3d>
+ <percent_left>0.0000</percent_left>
+ <percent_right>0.0000</percent_right>
+ <ymin_type_1>0</ymin_type_1>
+ <ymax_type_1>0</ymax_type_1>
+ <ymin_item_1>0</ymin_item_1>
+ <ymax_item_1>0</ymax_item_1>
+ <graph_items>
+ <graph_item>
+ <sortorder>0</sortorder>
+ <drawtype>0</drawtype>
+ <color>2774A4</color>
+ <yaxisside>0</yaxisside>
+ <calc_fnc>2</calc_fnc>
+ <type>0</type>
+ <item>
+ <host>Template Nvidia GPUs Performance</host>
+ <key>gpu.utilization[{#GPUINDEX}]</key>
+ </item>
+ </graph_item>
+ </graph_items>
+ </graph_prototype>
+ </graph_prototypes>
+ <host_prototypes/>
+ </discovery_rule>
+ </discovery_rules>
+ <macros/>
+ <templates/>
+ <screens/>
+ </template>
+ </templates>
+</zabbix_export>
--
GitLab