zbx_nvidia-smi-multi-gpu.xml

<?xml version="1.0" encoding="UTF-8"?>
<zabbix_export>
    <version>5.0</version>
    <date>2021-09-08T15:47:49Z</date>
    <groups>
        <group>
            <name>Templates</name>
        </group>
    </groups>
    <templates>
        <template>
            <template>Template Nvidia GPUs Performance</template>
            <name>Template Nvidia GPUs Performance</name>
            <groups>
                <group>
                    <name>Templates</name>
                </group>
            </groups>
            <applications>
                <application>
                    <name>Nvidia</name>
                </application>
            </applications>
            <items>
                <item>
                    <name>Number of GPUs</name>
                    <key>gpu.number</key>
                    <delay>30</delay>
                    <value_type>FLOAT</value_type>
                    <description>The number of GPUs present on this system.</description>
                    <applications>
                        <application>
                            <name>Nvidia</name>
                        </application>
                    </applications>
                </item>
            </items>
            <discovery_rules>
                <discovery_rule>
                    <name>GPU discovery</name>
                    <key>gpu.discovery</key>
                    <delay>600</delay>
                    <description>Discovery of graphics cards.</description>
                    <item_prototypes>
                        <item_prototype>
                            <name>GPU [{#GPUINDEX}] Fan Speed</name>
                            <key>gpu.fanspeed[{#GPUINDEX}]</key>
                            <delay>60</delay>
                            <history>7d</history>
                            <units>%</units>
                            <applications>
                                <application>
                                    <name>Nvidia</name>
                                </application>
                            </applications>
                            <preprocessing>
                                <step>
                                    <type>MULTIPLIER</type>
                                    <params>1</params>
                                </step>
                            </preprocessing>
                        </item_prototype>
                        <item_prototype>
                            <name>GPU [{#GPUINDEX}] Memory Free</name>
                            <key>gpu.memfree[{#GPUINDEX}]</key>
                            <delay>60</delay>
                            <history>7d</history>
                            <units>b</units>
                            <applications>
                                <application>
                                    <name>Nvidia</name>
                                </application>
                            </applications>
                            <preprocessing>
                                <step>
                                    <type>MULTIPLIER</type>
                                    <params>1000000</params>
                                </step>
                            </preprocessing>
                        </item_prototype>
                        <item_prototype>
                            <name>GPU [{#GPUINDEX}] Memory Total</name>
                            <key>gpu.memtotal[{#GPUINDEX}]</key>
                            <delay>60</delay>
                            <history>7d</history>
                            <units>b</units>
                            <applications>
                                <application>
                                    <name>Nvidia</name>
                                </application>
                            </applications>
                            <preprocessing>
                                <step>
                                    <type>MULTIPLIER</type>
                                    <params>1000000</params>
                                </step>
                            </preprocessing>
                        </item_prototype>
                        <item_prototype>
                            <name>GPU [{#GPUINDEX}] Memory Used</name>
                            <key>gpu.memused[{#GPUINDEX}]</key>
                            <delay>60</delay>
                            <history>7d</history>
                            <units>b</units>
                            <applications>
                                <application>
                                    <name>Nvidia</name>
                                </application>
                            </applications>
                            <preprocessing>
                                <step>
                                    <type>MULTIPLIER</type>
                                    <params>1000000</params>
                                </step>
                            </preprocessing>
                        </item_prototype>
                        <item_prototype>
                            <name>GPU [{#GPUINDEX}] Power in decaWatts</name>
                            <key>gpu.power[{#GPUINDEX}]</key>
                            <delay>60</delay>
                            <history>7d</history>
                            <value_type>FLOAT</value_type>
                            <units>dW</units>
                            <applications>
                                <application>
                                    <name>Nvidia</name>
                                </application>
                            </applications>
                            <preprocessing>
                                <step>
                                    <type>MULTIPLIER</type>
                                    <params>0.1</params>
                                </step>
                            </preprocessing>
                        </item_prototype>
                        <item_prototype>
                            <name>GPU [{#GPUINDEX}] Temperature</name>
                            <key>gpu.temp[{#GPUINDEX}]</key>
                            <delay>60</delay>
                            <history>7d</history>
                            <value_type>FLOAT</value_type>
                            <units>C</units>
                            <applications>
                                <application>
                                    <name>Nvidia</name>
                                </application>
                            </applications>
                            <trigger_prototypes>
                                <trigger_prototype>
                                    <expression>{last()}&gt;80</expression>
                                    <name>GPU {#GPUINDEX} Temperature is extremely high</name>
                                    <priority>DISASTER</priority>
                                    <description>A GPU's temperature is getting extremely high!</description>
                                </trigger_prototype>
                                <trigger_prototype>
                                    <expression>{last()}&gt;70</expression>
                                    <name>GPU {#GPUINDEX} Temperature is high</name>
                                    <priority>WARNING</priority>
                                    <description>A GPU's temperature is getting high!</description>
                                    <dependencies>
                                        <dependency>
                                            <name>GPU {#GPUINDEX} Temperature is very high</name>
                                            <expression>{Template Nvidia GPUs Performance:gpu.temp[{#GPUINDEX}].last()}&gt;75</expression>
                                        </dependency>
                                    </dependencies>
                                </trigger_prototype>
                                <trigger_prototype>
                                    <expression>{last()}&gt;75</expression>
                                    <name>GPU {#GPUINDEX} Temperature is very high</name>
                                    <priority>HIGH</priority>
                                    <description>A GPU's temperature is getting very high!</description>
                                    <dependencies>
                                        <dependency>
                                            <name>GPU {#GPUINDEX} Temperature is extremely high</name>
                                            <expression>{Template Nvidia GPUs Performance:gpu.temp[{#GPUINDEX}].last()}&gt;80</expression>
                                        </dependency>
                                    </dependencies>
                                </trigger_prototype>
                            </trigger_prototypes>
                        </item_prototype>
                        <item_prototype>
                            <name>GPU [{#GPUINDEX}] Decoder Utilization Max</name>
                            <key>gpu.utilization.dec.max[{#GPUINDEX}]</key>
                            <delay>60</delay>
                            <history>7d</history>
                            <units>%</units>
                            <applications>
                                <application>
                                    <name>Nvidia</name>
                                </application>
                            </applications>
                        </item_prototype>
                        <item_prototype>
                            <name>GPU [{#GPUINDEX}] Decoder Utilization Min</name>
                            <key>gpu.utilization.dec.min[{#GPUINDEX}]</key>
                            <delay>60</delay>
                            <history>7d</history>
                            <units>%</units>
                            <applications>
                                <application>
                                    <name>Nvidia</name>
                                </application>
                            </applications>
                        </item_prototype>
                        <item_prototype>
                            <name>GPU [{#GPUINDEX}] Encoder Utilization Max</name>
                            <key>gpu.utilization.enc.max[{#GPUINDEX}]</key>
                            <delay>60</delay>
                            <history>7d</history>
                            <units>%</units>
                            <applications>
                                <application>
                                    <name>Nvidia</name>
                                </application>
                            </applications>
                        </item_prototype>
                        <item_prototype>
                            <name>GPU [{#GPUINDEX}] Encoder Utilization min</name>
                            <key>gpu.utilization.enc.min[{#GPUINDEX}]</key>
                            <delay>60</delay>
                            <history>7d</history>
                            <units>%</units>
                            <applications>
                                <application>
                                    <name>Nvidia</name>
                                </application>
                            </applications>
                        </item_prototype>
                        <item_prototype>
                            <name>GPU [{#GPUINDEX}] Utilization</name>
                            <key>gpu.utilization[{#GPUINDEX}]</key>
                            <delay>60</delay>
                            <history>7d</history>
                            <units>%</units>
                            <applications>
                                <application>
                                    <name>Nvidia</name>
                                </application>
                            </applications>
                        </item_prototype>
                    </item_prototypes>
                    <graph_prototypes>
                        <graph_prototype>
                            <name>GPU {#GPUINDEX} Encoder/Decoder Utilization</name>
                            <graph_items>
                                <graph_item>
                                    <sortorder>1</sortorder>
                                    <drawtype>BOLD_LINE</drawtype>
                                    <color>1A7C11</color>
                                    <item>
                                        <host>Template Nvidia GPUs Performance</host>
                                        <key>gpu.utilization.dec.max[{#GPUINDEX}]</key>
                                    </item>
                                </graph_item>
                                <graph_item>
                                    <sortorder>2</sortorder>
                                    <color>00FF00</color>
                                    <item>
                                        <host>Template Nvidia GPUs Performance</host>
                                        <key>gpu.utilization.dec.min[{#GPUINDEX}]</key>
                                    </item>
                                </graph_item>
                                <graph_item>
                                    <sortorder>3</sortorder>
                                    <drawtype>BOLD_LINE</drawtype>
                                    <color>BF00FF</color>
                                    <item>
                                        <host>Template Nvidia GPUs Performance</host>
                                        <key>gpu.utilization.enc.max[{#GPUINDEX}]</key>
                                    </item>
                                </graph_item>
                                <graph_item>
                                    <sortorder>4</sortorder>
                                    <color>311B92</color>
                                    <item>
                                        <host>Template Nvidia GPUs Performance</host>
                                        <key>gpu.utilization.enc.min[{#GPUINDEX}]</key>
                                    </item>
                                </graph_item>
                            </graph_items>
                        </graph_prototype>
                        <graph_prototype>
                            <name>GPU {#GPUINDEX} Memory</name>
                            <graph_items>
                                <graph_item>
                                    <color>00AA00</color>
                                    <item>
                                        <host>Template Nvidia GPUs Performance</host>
                                        <key>gpu.memfree[{#GPUINDEX}]</key>
                                    </item>
                                </graph_item>
                                <graph_item>
                                    <sortorder>1</sortorder>
                                    <color>0000DD</color>
                                    <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>
                            <graph_items>
                                <graph_item>
                                    <color>1A7C11</color>
                                    <item>
                                        <host>Template Nvidia GPUs Performance</host>
                                        <key>gpu.power[{#GPUINDEX}]</key>
                                    </item>
                                </graph_item>
                                <graph_item>
                                    <sortorder>1</sortorder>
                                    <color>2774A4</color>
                                    <item>
                                        <host>Template Nvidia GPUs Performance</host>
                                        <key>gpu.fanspeed[{#GPUINDEX}]</key>
                                    </item>
                                </graph_item>
                                <graph_item>
                                    <sortorder>2</sortorder>
                                    <color>F63100</color>
                                    <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>
                            <graph_items>
                                <graph_item>
                                    <color>2774A4</color>
                                    <item>
                                        <host>Template Nvidia GPUs Performance</host>
                                        <key>gpu.utilization[{#GPUINDEX}]</key>
                                    </item>
                                </graph_item>
                            </graph_items>
                        </graph_prototype>
                    </graph_prototypes>
                </discovery_rule>
            </discovery_rules>
        </template>
    </templates>
</zabbix_export>