68 lines
74 KiB
XML
68 lines
74 KiB
XML
<?xml version="1.0" encoding="UTF-8"?>
|
|
<zabbix_export><version>7.4</version><template_groups><template_group><uuid>a571c0d144b14fd4a87a9d9b2aa9fcd6</uuid><name>Templates/Applications</name></template_group></template_groups><templates><template><uuid>32a39c8aca9445df862e9f3e1369c19a</uuid><template>Nvidia by Zabbix agent 2</template><name>Nvidia by Zabbix agent 2</name><description>This template is designed for Nvidia GPU monitoring and doesn't require any external scripts.
|
|
1. Setup and configure Zabbix agent 2 compiled with the Nvidia monitoring plugin.
|
|
2. Create a host with Zabbix agent interface and attach the template to it.
|
|
All Nvidia GPUs will be discovered. Set filters with macros if you want to override default filter parameters.
|
|
|
|
You can discuss this template or leave feedback on our forum https://www.zabbix.com/forum/zabbix-suggestions-and-feedback.
|
|
|
|
Generated by official Zabbix template tool "Templator"</description><vendor><name>Zabbix</name><version>7.2-1</version></vendor><groups><group><name>Templates/Applications</name></group></groups><items><item><uuid>ac18129f78a54a2e95d1d48630e0eab2</uuid><name>Number of devices</name><key>nvml.device.count</key><delay>1h</delay><description>Retrieves the number of compute devices in the system. A compute device is a single GPU.
|
|
For all Nvidia products.</description><preprocessing><step><type>DISCARD_UNCHANGED_HEARTBEAT</type><parameters><parameter>1d</parameter></parameters></step></preprocessing><tags><tag><tag>component</tag><value>nvidia</value></tag></tags><triggers><trigger><uuid>92b64a9d2e87418a99cd2ca814a2deac</uuid><expression>change(/Nvidia by Zabbix agent 2/nvml.device.count) <> 0</expression><name>Nvidia: Number of devices has changed</name><event_name>Nvidia: Number of devices on {HOST.HOST} has changed.</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>WARNING</priority><description>Number of devices has changed. Check if this was intentional.</description><manual_close>YES</manual_close><tags><tag><tag>scope</tag><value>notice</value></tag></tags></trigger></triggers></item><item><uuid>afe2ea47c42f4992851f02b31efd8225</uuid><name>Get devices</name><key>nvml.device.get</key><delay>1h</delay><history>0</history><value_type>TEXT</value_type><description>Retrieves a list of Nvidia devices in the system.</description><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>component</tag><value>raw</value></tag></tags></item><item><uuid>824a7555809f4e23b2f7fa72aff28a0c</uuid><name>Driver version</name><key>nvml.system.driver.version</key><delay>1h</delay><value_type>CHAR</value_type><description>Retrieves the version of the system's graphics driver.
|
|
For all Nvidia products.</description><preprocessing><step><type>DISCARD_UNCHANGED_HEARTBEAT</type><parameters><parameter>1d</parameter></parameters></step></preprocessing><tags><tag><tag>component</tag><value>nvidia</value></tag></tags><triggers><trigger><uuid>da8538e357a044ee8ebea1d6d4077ffd</uuid><expression>change(/Nvidia by Zabbix agent 2/nvml.system.driver.version) <> 0</expression><name>Nvidia: Driver version has changed</name><event_name>Nvidia: Driver version on {HOST.HOST} has changed.</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>INFO</priority><description>Driver version has changed.
|
|
Check the Nvidia website for the specific driver version: https://www.nvidia.com/en-us/drivers/</description><manual_close>YES</manual_close><tags><tag><tag>scope</tag><value>notice</value></tag></tags></trigger></triggers></item><item><uuid>8e54cc700a9147baa5f18aa286c47205</uuid><name>NVML library version</name><key>nvml.version</key><delay>1h</delay><value_type>CHAR</value_type><description>Retrieves the version of the NVML library.
|
|
For all Nvidia products.</description><preprocessing><step><type>DISCARD_UNCHANGED_HEARTBEAT</type><parameters><parameter>1d</parameter></parameters></step></preprocessing><tags><tag><tag>component</tag><value>nvidia</value></tag></tags><triggers><trigger><uuid>1f04a31c99954172a69f2c8529b429ff</uuid><expression>change(/Nvidia by Zabbix agent 2/nvml.version) <> 0</expression><name>Nvidia: NVML library has changed</name><event_name>Nvidia: NVML library on {HOST.HOST} has changed.</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>INFO</priority><description>NVML library version has changed.
|
|
Check the changelog for details: https://docs.nvidia.com/deploy/nvml-api/change-log.html</description><manual_close>YES</manual_close><tags><tag><tag>scope</tag><value>notice</value></tag></tags></trigger></triggers></item></items><discovery_rules><discovery_rule><uuid>bb7ede7d50f0427aaa043c59ee706c09</uuid><name>GPU Discovery</name><type>DEPENDENT</type><key>nvml.device.discovery</key><filter><evaltype>AND</evaltype><conditions><condition><macro>{#NAME}</macro><value>{$NVIDIA.NAME.MATCHES}</value></condition><condition><macro>{#NAME}</macro><value>{$NVIDIA.NAME.NOT_MATCHES}</value><operator>NOT_MATCHES_REGEX</operator></condition><condition><macro>{#UUID}</macro><value>{$NVIDIA.UUID.MATCHES}</value></condition><condition><macro>{#UUID}</macro><value>{$NVIDIA.UUID.NOT_MATCHES}</value><operator>NOT_MATCHES_REGEX</operator></condition></conditions></filter><description>Nvidia GPU discovery in the system.</description><item_prototypes><item_prototype><uuid>cf631ee2b8d9494e81eef3e9e0bddf80</uuid><name>[{#UUID}]: Decoder utilization</name><key>nvml.device.decoder.utilization["{#UUID}"]</key><units>%</units><description>Retrieves the current utilization for the Decoder.
|
|
For Nvidia Kepler or newer fully supported devices.</description><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags><trigger_prototypes><trigger_prototype><uuid>6b41ac763eab4e83b69e1e28ec01db3d</uuid><expression>min(/Nvidia by Zabbix agent 2/nvml.device.decoder.utilization["{#UUID}"],3m) > {$NVIDIA.DECODER.UTIL.CRIT}</expression><name>Nvidia: [{#UUID}]: Decoder utilization exceeded critical threshold</name><event_name>Nvidia: [{#UUID}]: Decoder utilization ({ITEM.VALUE1}) exceeded critical threshold ({$NVIDIA.DECODER.UTIL.CRIT} %)</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>AVERAGE</priority><description>[{#UUID}]: Decoder utilization is very high. It may indicate abnormal behavior/activity. Change corresponding macro in case of false-positive.</description><tags><tag><tag>scope</tag><value>performance</value></tag></tags></trigger_prototype><trigger_prototype><uuid>4cc20329b01543f7b0ef9b3a00dbff07</uuid><expression>min(/Nvidia by Zabbix agent 2/nvml.device.decoder.utilization["{#UUID}"],3m) > {$NVIDIA.DECODER.UTIL.WARN}</expression><name>Nvidia: [{#UUID}]: Decoder utilization exceeded warning threshold</name><event_name>Nvidia: [{#UUID}]: Decoder utilization ({ITEM.VALUE1}) exceeded warning threshold ({$NVIDIA.DECODER.UTIL.WARN} %)</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>WARNING</priority><description>[{#UUID}]: Decoder utilization is high. It may indicate abnormal behavior/activity. Change corresponding macro in case of false-positive.</description><dependencies><dependency><name>Nvidia: [{#UUID}]: Decoder utilization exceeded critical threshold</name><expression>min(/Nvidia by Zabbix agent 2/nvml.device.decoder.utilization["{#UUID}"],3m) > {$NVIDIA.DECODER.UTIL.CRIT}</expression></dependency></dependencies><tags><tag><tag>scope</tag><value>performance</value></tag></tags></trigger_prototype></trigger_prototypes></item_prototype><item_prototype><uuid>71cabb57ad9b43c39ff05d56f753b2c1</uuid><name>[{#UUID}]: Encoder average FPS</name><type>DEPENDENT</type><key>nvml.device.encoder.stats.fps["{#UUID}"]</key><units>!fps</units><description>Retrieves the trailing average FPS of all active encoder sessions for a given device.
|
|
For Nvidia Maxwell or newer fully supported devices.</description><preprocessing><step><type>JSONPATH</type><parameters><parameter>$.average_fps</parameter></parameters></step></preprocessing><master_item><key>nvml.device.encoder.stats.get["{#UUID}"]</key></master_item><tags><tag><tag>component</tag><value>encoder</value></tag><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>cc4ff50ff1ed4c6d92ccb24f205b65c5</uuid><name>[{#UUID}]: Encoder stats</name><key>nvml.device.encoder.stats.get["{#UUID}"]</key><history>0</history><value_type>TEXT</value_type><description>Retrieves the current encoder statistics for a given device.
|
|
For Nvidia Maxwell or newer fully supported devices.</description><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>component</tag><value>raw</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>727e5f7da5394d4191814d5ccb5b6af0</uuid><name>[{#UUID}]: Encoder average latency</name><type>DEPENDENT</type><key>nvml.device.encoder.stats.latency["{#UUID}"]</key><value_type>FLOAT</value_type><units>s</units><description>Retrieves the current encode latency for a given device.
|
|
For Nvidia Maxwell or newer fully supported devices.</description><preprocessing><step><type>JSONPATH</type><parameters><parameter>$.average_latency_ms</parameter></parameters></step><step><type>MULTIPLIER</type><parameters><parameter>0.001</parameter></parameters></step></preprocessing><master_item><key>nvml.device.encoder.stats.get["{#UUID}"]</key></master_item><tags><tag><tag>component</tag><value>encoder</value></tag><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags><trigger_prototypes><trigger_prototype><uuid>c6b3813511454b1eafa69d834dfd8d0c</uuid><expression>last(/Nvidia by Zabbix agent 2/nvml.device.encoder.stats.latency["{#UUID}"]) > (2 * avg(/Nvidia by Zabbix agent 2/nvml.device.encoder.stats.latency["{#UUID}"],3m))</expression><name>Nvidia: [{#UUID}]: Encoder average latency is high</name><event_name>Nvidia: [{#UUID}]: Encoder average latency is 2x higher than usual.</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>WARNING</priority><tags><tag><tag>scope</tag><value>performance</value></tag></tags></trigger_prototype></trigger_prototypes></item_prototype><item_prototype><uuid>4a39249deb40404386492631ce987b19</uuid><name>[{#UUID}]: Encoder sessions</name><type>DEPENDENT</type><key>nvml.device.encoder.stats.sessions["{#UUID}"]</key><description>Retrieves the current count of active encoder sessions for a given device.
|
|
For Nvidia Maxwell or newer fully supported devices.</description><preprocessing><step><type>JSONPATH</type><parameters><parameter>$.session_count</parameter></parameters></step></preprocessing><master_item><key>nvml.device.encoder.stats.get["{#UUID}"]</key></master_item><tags><tag><tag>component</tag><value>encoder</value></tag><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>6cf65da338f64f6c9087f8699c2d71dc</uuid><name>[{#UUID}]: Encoder utilization</name><key>nvml.device.encoder.utilization["{#UUID}"]</key><units>%</units><description>Retrieves the current utilization for the Encoder.
|
|
For Nvidia Kepler or newer fully supported devices.</description><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags><trigger_prototypes><trigger_prototype><uuid>0c7f39babddf49469d46aba48114c45e</uuid><expression>min(/Nvidia by Zabbix agent 2/nvml.device.encoder.utilization["{#UUID}"],3m) > {$NVIDIA.ENCODER.UTIL.CRIT}</expression><name>Nvidia: [{#UUID}]: Encoder utilization exceeded critical threshold</name><event_name>Nvidia: [{#UUID}]: Encoder utilization ({ITEM.VALUE1}) exceeded critical threshold ({$NVIDIA.ENCODER.UTIL.CRIT} %)</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>AVERAGE</priority><description>[{#UUID}]: Encoder utilization is very high. It may indicate abnormal behavior/activity. Change corresponding macro in case of false-positive.</description><tags><tag><tag>scope</tag><value>performance</value></tag></tags></trigger_prototype><trigger_prototype><uuid>e2cb63b538514aa49c163c74b4471a39</uuid><expression>min(/Nvidia by Zabbix agent 2/nvml.device.encoder.utilization["{#UUID}"],3m) > {$NVIDIA.ENCODER.UTIL.WARN}</expression><name>Nvidia: [{#UUID}]: Encoder utilization exceeded warning threshold</name><event_name>Nvidia: [{#UUID}]: Encoder utilization ({ITEM.VALUE1}) exceeded warning threshold ({$NVIDIA.ENCODER.UTIL.WARN} %)</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>WARNING</priority><description>[{#UUID}]: Encoder utilization is high. It may indicate abnormal behavior/activity. Change corresponding macro in case of false-positive.</description><dependencies><dependency><name>Nvidia: [{#UUID}]: Encoder utilization exceeded critical threshold</name><expression>min(/Nvidia by Zabbix agent 2/nvml.device.encoder.utilization["{#UUID}"],3m) > {$NVIDIA.ENCODER.UTIL.CRIT}</expression></dependency></dependencies><tags><tag><tag>scope</tag><value>performance</value></tag></tags></trigger_prototype></trigger_prototypes></item_prototype><item_prototype><uuid>8f992f3cffcc42d5a0f4cac878781457</uuid><name>[{#UUID}]: Energy consumption</name><key>nvml.device.energy.consumption["{#UUID}"]</key><value_type>FLOAT</value_type><units>J</units><description>Retrieves the total energy consumption of this GPU in joules since the last driver reload.
|
|
For Nvidia Volta or newer fully supported devices.</description><preprocessing><step><type>MULTIPLIER</type><parameters><parameter>0.001</parameter></parameters></step></preprocessing><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>c558f53c06b346b8a77b941211797cb2</uuid><name>[{#UUID}]: Memory ECC errors, corrected</name><type>DEPENDENT</type><key>nvml.device.errors.memory.corrected["{#UUID}"]</key><description>Retrieves the count of GPU device memory errors that were corrected. For ECC errors, these are single-bit errors, for Texture memory, these are errors fixed by resend.
|
|
For Nvidia Fermi or newer fully supported devices.</description><preprocessing><step><type>JSONPATH</type><parameters><parameter>$.corrected</parameter></parameters></step></preprocessing><master_item><key>nvml.device.errors.memory["{#UUID}"]</key></master_item><tags><tag><tag>component</tag><value>memory</value></tag><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags><trigger_prototypes><trigger_prototype><uuid>4e42cbee73874ca0a8a054a922128cf7</uuid><expression>change(/Nvidia by Zabbix agent 2/nvml.device.errors.memory.corrected["{#UUID}"]) <> 0</expression><name>Nvidia: [{#UUID}]: Number of corrected memory ECC errors has changed</name><event_name>Nvidia: Number of corrected memory ECC errors on {HOST.HOST} has changed.</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>INFO</priority><description>An increasing number of corrected ECC errors can indicate (but not necessary mean) aging or degrading of memory.</description><manual_close>YES</manual_close><tags><tag><tag>scope</tag><value>notice</value></tag></tags></trigger_prototype></trigger_prototypes></item_prototype><item_prototype><uuid>4daf87d77c5c4950b0e2d51e24afd1a5</uuid><name>[{#UUID}]: Memory ECC errors, uncorrected</name><type>DEPENDENT</type><key>nvml.device.errors.memory.uncorrected["{#UUID}"]</key><description>Retrieves the count of GPU device memory errors that were not corrected. For ECC errors, these are double-bit errors, for Texture memory, these are errors where the resend fails.
|
|
For Nvidia Fermi or newer fully supported devices.</description><preprocessing><step><type>JSONPATH</type><parameters><parameter>$.uncorrected</parameter></parameters></step></preprocessing><master_item><key>nvml.device.errors.memory["{#UUID}"]</key></master_item><tags><tag><tag>component</tag><value>memory</value></tag><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags><trigger_prototypes><trigger_prototype><uuid>c5b2ca940c824f0d98e9aff5a5561a2b</uuid><expression>change(/Nvidia by Zabbix agent 2/nvml.device.errors.memory.uncorrected["{#UUID}"]) <> 0</expression><name>Nvidia: [{#UUID}]: Number of uncorrected memory ECC errors has changed</name><event_name>Nvidia: Number uncorrected of memory ECC errors on {HOST.HOST} has changed.</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>INFO</priority><description>An increasing number of uncorrected ECC errors can indicate potential issues such as: data corruption, system instability, hardware issues</description><manual_close>YES</manual_close><tags><tag><tag>scope</tag><value>notice</value></tag></tags></trigger_prototype></trigger_prototypes></item_prototype><item_prototype><uuid>e97eacb1bef64fdaa7b55883fc37a4a9</uuid><name>[{#UUID}]: Memory ECC errors, get</name><key>nvml.device.errors.memory["{#UUID}"]</key><history>0</history><value_type>TEXT</value_type><description>Retrieves the GPU device memory error counters for the device.
|
|
For Nvidia Fermi or newer fully supported devices.
|
|
Requires NVML_INFOROM_ECC version 2.0 or higher to report aggregate location-based memory error counts. Requires NVML_INFOROM_ECC version 1.0 or higher to report all other memory error counts.
|
|
Only applicable to devices with ECC.
|
|
Requires ECC Mode to be enabled.</description><preprocessing><step><type>CHECK_NOT_SUPPORTED</type><parameters><parameter>0</parameter><parameter>The requested operation is not available on target device</parameter></parameters><error_handler>CUSTOM_ERROR</error_handler><error_handler_params>No ECC on the device or ECC mode is turned off.</error_handler_params></step></preprocessing><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>component</tag><value>raw</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>9a7c0d865ff9423b861913b276c2b3f5</uuid><name>[{#UUID}]: Register file errors, corrected</name><type>DEPENDENT</type><key>nvml.device.errors.register.corrected["{#UUID}"]</key><description>Retrieves the count of GPU register file errors that were corrected. For ECC errors, these are single-bit errors, for Texture memory, these are errors fixed by resend.
|
|
For Nvidia Fermi or newer fully supported devices.</description><preprocessing><step><type>JSONPATH</type><parameters><parameter>$.corrected</parameter></parameters></step></preprocessing><master_item><key>nvml.device.errors.register["{#UUID}"]</key></master_item><tags><tag><tag>component</tag><value>memory</value></tag><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags><trigger_prototypes><trigger_prototype><uuid>979bd4cc64294b9aa5d0c452f84cf74a</uuid><expression>change(/Nvidia by Zabbix agent 2/nvml.device.errors.register.corrected["{#UUID}"]) <> 0</expression><name>Nvidia: [{#UUID}]: Number of corrected register file errors has changed</name><event_name>Nvidia: Number corrected of register file errors on {HOST.HOST} has changed.</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>INFO</priority><description>An increasing number of corrected register file errors can indicate (but not necessary mean) wearing, aging or degrading of memory.</description><manual_close>YES</manual_close><tags><tag><tag>scope</tag><value>notice</value></tag></tags></trigger_prototype></trigger_prototypes></item_prototype><item_prototype><uuid>e7a077d0610e407fb49f1ca8d782c81f</uuid><name>[{#UUID}]: Register file errors, uncorrected</name><type>DEPENDENT</type><key>nvml.device.errors.register.uncorrected["{#UUID}"]</key><description>Retrieves the count of GPU register file errors that were not corrected. For ECC errors, these are double-bit errors, for Texture memory, these are errors where the resend fails.
|
|
For Nvidia Fermi or newer fully supported devices.</description><preprocessing><step><type>JSONPATH</type><parameters><parameter>$.uncorrected</parameter></parameters></step></preprocessing><master_item><key>nvml.device.errors.register["{#UUID}"]</key></master_item><tags><tag><tag>component</tag><value>memory</value></tag><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags><trigger_prototypes><trigger_prototype><uuid>7fc8da6cd0624880b9838c23386df758</uuid><expression>change(/Nvidia by Zabbix agent 2/nvml.device.errors.register.uncorrected["{#UUID}"]) <> 0</expression><name>Nvidia: [{#UUID}]: Number of uncorrected register file errors has changed</name><event_name>Nvidia: Number uncorrected of register file errors on {HOST.HOST} has changed.</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>INFO</priority><description>An increasing number of uncorrected register file errors can indicate potential issues such as: data corruption, system instability, hardware degradation.</description><manual_close>YES</manual_close><tags><tag><tag>scope</tag><value>notice</value></tag></tags></trigger_prototype></trigger_prototypes></item_prototype><item_prototype><uuid>07ea4aec260f4850b0c2a59610f703de</uuid><name>[{#UUID}]: Register file errors, get</name><key>nvml.device.errors.register["{#UUID}"]</key><history>0</history><value_type>TEXT</value_type><description>Retrieves the GPU register file error counters for the device.
|
|
For Nvidia Fermi or newer fully supported devices.
|
|
Requires NVML_INFOROM_ECC version 2.0 or higher to report aggregate location-based memory error counts. Requires NVML_INFOROM_ECC version 1.0 or higher to report all other memory error counts.
|
|
Only applicable to devices with ECC.
|
|
Requires ECC Mode to be enabled.</description><preprocessing><step><type>CHECK_NOT_SUPPORTED</type><parameters><parameter>0</parameter><parameter>The requested operation is not available on target device</parameter></parameters><error_handler>CUSTOM_ERROR</error_handler><error_handler_params>No ECC on the device or ECC mode is turned off.</error_handler_params></step></preprocessing><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>component</tag><value>raw</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>49283334edaa4aeb9d63d8f2794c23d7</uuid><name>[{#UUID}]: Fan speed</name><key>nvml.device.fan.speed.avg["{#UUID}"]</key><units>%</units><description>Retrieves the intended operating speed of the specified device fan.
|
|
Note: The reported speed is the intended fan speed. If the fan is physically blocked and unable to spin, the output will not match the actual fan speed.
|
|
For all Nvidia discrete products with dedicated fans.
|
|
The fan speed is expressed as a percentage of the product's maximum noise tolerance fan speed. In certain cases, this value may exceed 100%.</description><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags><trigger_prototypes><trigger_prototype><uuid>3311b17ca4aa4b81a6dd10af744166df</uuid><expression>min(/Nvidia by Zabbix agent 2/nvml.device.fan.speed.avg["{#UUID}"],3m) > {$NVIDIA.FAN.SPEED.CRIT}</expression><name>Nvidia: [{#UUID}]: Fan speed exceeded critical threshold</name><event_name>Nvidia: [{#UUID}]: Fan speed ({ITEM.VALUE1}) exceeded critical threshold ({$NVIDIA.FAN.SPEED.CRIT} %)</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>AVERAGE</priority><description>[{#UUID}]: Fan speed is very high. It may indicate abnormal behavior/activity. Change corresponding macro in case of false-positive.</description><tags><tag><tag>scope</tag><value>performance</value></tag></tags></trigger_prototype><trigger_prototype><uuid>9aed50cb1a4c4cd4b0d6dce570bb33da</uuid><expression>min(/Nvidia by Zabbix agent 2/nvml.device.fan.speed.avg["{#UUID}"],3m) > {$NVIDIA.FAN.SPEED.WARN}</expression><name>Nvidia: [{#UUID}]: Fan speed exceeded warning threshold</name><event_name>Nvidia: [{#UUID}]: Fan speed ({ITEM.VALUE1}) exceeded warning threshold ({$NVIDIA.FAN.SPEED.WARN} %)</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>WARNING</priority><description>[{#UUID}]: Fan speed is high. It may indicate abnormal behavior/activity. Change corresponding macro in case of false-positive.</description><dependencies><dependency><name>Nvidia: [{#UUID}]: Fan speed exceeded critical threshold</name><expression>min(/Nvidia by Zabbix agent 2/nvml.device.fan.speed.avg["{#UUID}"],3m) > {$NVIDIA.FAN.SPEED.CRIT}</expression></dependency></dependencies><tags><tag><tag>scope</tag><value>performance</value></tag></tags></trigger_prototype></trigger_prototypes></item_prototype><item_prototype><uuid>77bce39e010f4d4ab5fc347aebd7e61b</uuid><name>[{#UUID}]: Graphics frequency</name><key>nvml.device.graphics.frequency["{#UUID}"]</key><units>Hz</units><description>Retrieves the current graphics clock speed for the device.
|
|
For Nvidia Fermi or newer fully supported devices.</description><preprocessing><step><type>MULTIPLIER</type><parameters><parameter>1000000</parameter></parameters></step></preprocessing><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>141fe268d32941f19b79472a7e041ff9</uuid><name>[{#UUID}]: BAR1 memory, free</name><type>DEPENDENT</type><key>nvml.device.memory.bar1.free["{#UUID}"]</key><units>B</units><description>Unallocated BAR1 memory on the device.
|
|
For Nvidia Kepler or newer fully supported devices</description><preprocessing><step><type>JSONPATH</type><parameters><parameter>$.free_memory_bytes</parameter></parameters></step></preprocessing><master_item><key>nvml.device.memory.bar1.get["{#UUID}"]</key></master_item><tags><tag><tag>component</tag><value>memory</value></tag><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>da9f4e0ce0af45af9cb414b34932df70</uuid><name>[{#UUID}]: BAR1 memory, get</name><key>nvml.device.memory.bar1.get["{#UUID}"]</key><history>0</history><value_type>TEXT</value_type><description>Gets Total, Available, and Used size of BAR1 memory.
|
|
BAR1 is used to map the FB (device memory) so that it can be directly accessed by the CPU or 3rd party devices (peer-to-peer on the PCIE bus).
|
|
For Nvidia Kepler or newer fully supported devices</description><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>component</tag><value>raw</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>301e573a311d48de876efc3dfe718222</uuid><name>[{#UUID}]: BAR1 memory, total</name><type>DEPENDENT</type><key>nvml.device.memory.bar1.total["{#UUID}"]</key><units>B</units><description>Total BAR1 memory on the device.
|
|
For Nvidia Kepler or newer fully supported devices</description><preprocessing><step><type>JSONPATH</type><parameters><parameter>$.total_memory_bytes</parameter></parameters></step></preprocessing><master_item><key>nvml.device.memory.bar1.get["{#UUID}"]</key></master_item><tags><tag><tag>component</tag><value>memory</value></tag><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags><trigger_prototypes><trigger_prototype><uuid>da69286b1c4f428d8a9da0d77d5a9057</uuid><expression>change(/Nvidia by Zabbix agent 2/nvml.device.memory.bar1.total["{#UUID}"]) <> 0</expression><name>Nvidia: [{#UUID}]: Total BAR1 memory has changed</name><event_name>Nvidia: Total BAR1 memory on {HOST.HOST} has changed.</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>WARNING</priority><description>Total BAR1 memory has changed. This could mean possible memory degradation, hardware configuration changes, or memory reservation by system or software.</description><manual_close>YES</manual_close><tags><tag><tag>scope</tag><value>notice</value></tag></tags></trigger_prototype></trigger_prototypes></item_prototype><item_prototype><uuid>afd6bbb5c6584e328cf37a6584970c2d</uuid><name>[{#UUID}]: BAR1 memory, used</name><type>DEPENDENT</type><key>nvml.device.memory.bar1.used["{#UUID}"]</key><units>B</units><description>Allocated used BAR1 memory on the device.
|
|
For Nvidia Kepler or newer fully supported devices</description><preprocessing><step><type>JSONPATH</type><parameters><parameter>$.used_memory_bytes</parameter></parameters></step></preprocessing><master_item><key>nvml.device.memory.bar1.get["{#UUID}"]</key></master_item><tags><tag><tag>component</tag><value>memory</value></tag><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>fbef18bb0f4d466bbdcd859e7198f144</uuid><name>[{#UUID}]: FB memory, free</name><type>DEPENDENT</type><key>nvml.device.memory.fb.free["{#UUID}"]</key><units>B</units><description>Unallocated memory on the device.
|
|
For all Nvidia products.</description><preprocessing><step><type>JSONPATH</type><parameters><parameter>$.free_memory_bytes</parameter></parameters></step></preprocessing><master_item><key>nvml.device.memory.fb.get["{#UUID}"]</key></master_item><tags><tag><tag>component</tag><value>memory</value></tag><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>cad7ac51204847e2a00a8a594a7ffecc</uuid><name>[{#UUID}]: FB memory, get</name><key>nvml.device.memory.fb.get["{#UUID}"]</key><history>0</history><value_type>TEXT</value_type><description>Retrieves the amount of used, free, reserved, and total memory available on the device.
|
|
For all Nvidia products.
|
|
Enabling ECC reduces the amount of total available memory due to the extra required parity bits. Under WDDM, most of the device memory is allocated and managed on startup by Windows.
|
|
Under Linux and Windows TCC, the reported amount of used memory is equal to the sum of memory allocated by all active channels on the device.</description><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>component</tag><value>raw</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>d30fba06739c4353bf8b39014da65b21</uuid><name>[{#UUID}]: FB memory, reserved</name><type>DEPENDENT</type><key>nvml.device.memory.fb.reserved["{#UUID}"]</key><units>B</units><description>Memory reserved for system use (driver or firmware) on the device.
|
|
For all Nvidia products.</description><preprocessing><step><type>JSONPATH</type><parameters><parameter>$.reserved_memory_bytes</parameter></parameters><error_handler>CUSTOM_ERROR</error_handler><error_handler_params>NVML library too old to support this metric.</error_handler_params></step></preprocessing><master_item><key>nvml.device.memory.fb.get["{#UUID}"]</key></master_item><tags><tag><tag>component</tag><value>memory</value></tag><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>c67a14cb463e40289500c88d7f9e0997</uuid><name>[{#UUID}]: FB memory, total</name><type>DEPENDENT</type><key>nvml.device.memory.fb.total["{#UUID}"]</key><units>B</units><description>Total physical memory on the device.
|
|
For all Nvidia products.</description><preprocessing><step><type>JSONPATH</type><parameters><parameter>$.total_memory_bytes</parameter></parameters></step></preprocessing><master_item><key>nvml.device.memory.fb.get["{#UUID}"]</key></master_item><tags><tag><tag>component</tag><value>memory</value></tag><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags><trigger_prototypes><trigger_prototype><uuid>945579a20b8e4983a07719f1b7ace8e2</uuid><expression>change(/Nvidia by Zabbix agent 2/nvml.device.memory.fb.total["{#UUID}"]) <> 0</expression><name>Nvidia: [{#UUID}]: Total FB memory has changed</name><event_name>Nvidia: Total FB memory on {HOST.HOST} has changed.</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>WARNING</priority><description>Total FB memory has changed. This could mean possible memory degradation, hardware configuration changes, or memory reservation by system or software.</description><manual_close>YES</manual_close><tags><tag><tag>scope</tag><value>notice</value></tag></tags></trigger_prototype></trigger_prototypes></item_prototype><item_prototype><uuid>c4b9a7593e6d4433b9021c9e3656ed41</uuid><name>[{#UUID}]: FB memory, used</name><type>DEPENDENT</type><key>nvml.device.memory.fb.used["{#UUID}"]</key><units>B</units><description>Allocated memory on the device.
|
|
For all Nvidia products.</description><preprocessing><step><type>JSONPATH</type><parameters><parameter>$.used_memory_bytes</parameter></parameters></step></preprocessing><master_item><key>nvml.device.memory.fb.get["{#UUID}"]</key></master_item><tags><tag><tag>component</tag><value>memory</value></tag><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>78918ce1cbae45bdb3a0773f3bf9bd14</uuid><name>[{#UUID}]: Memory frequency</name><key>nvml.device.memory.frequency["{#UUID}"]</key><units>Hz</units><description>Retrieves the current memory clock speed for the device.
|
|
For Nvidia Fermi or newer fully supported devices.</description><preprocessing><step><type>MULTIPLIER</type><parameters><parameter>1000000</parameter></parameters></step></preprocessing><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>88f5cf58ce5043b8b3f71e57eff67340</uuid><name>[{#UUID}]: PCIe utilization, Rx</name><type>DEPENDENT</type><key>nvml.device.pci.utilization.rx.rate["{#UUID}"]</key><units>bps</units><description>The PCIe Rx (receive) throughput over a 20ms interval on the device.
|
|
For Nvidia Maxwell or newer fully supported devices.</description><preprocessing><step><type>JSONPATH</type><parameters><parameter>$.rx_rate_kb_s</parameter></parameters></step><step><type>MULTIPLIER</type><parameters><parameter>1024</parameter></parameters></step></preprocessing><master_item><key>nvml.device.pci.utilization["{#UUID}"]</key></master_item><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>256d8cd75fb14382ae79a32ab8cc0b13</uuid><name>[{#UUID}]: PCIe utilization, Tx</name><type>DEPENDENT</type><key>nvml.device.pci.utilization.tx.rate["{#UUID}"]</key><units>bps</units><description>The PCIe Tx (transmit) throughput over a 20ms interval on the device.
|
|
For Nvidia Maxwell or newer fully supported devices.</description><preprocessing><step><type>JSONPATH</type><parameters><parameter>$.tx_rate_kb_s</parameter></parameters></step><step><type>MULTIPLIER</type><parameters><parameter>1024</parameter></parameters></step></preprocessing><master_item><key>nvml.device.pci.utilization["{#UUID}"]</key></master_item><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>35d9d7075294487f9bd2f47f4be66dea</uuid><name>[{#UUID}]: PCIe utilization, get</name><key>nvml.device.pci.utilization["{#UUID}"]</key><history>0</history><value_type>TEXT</value_type><description>Retrieves PCIe utilization information.
|
|
For Nvidia Maxwell or newer fully supported devices.</description><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>component</tag><value>raw</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>5a97162894064078ad8913d647dbf76e</uuid><name>[{#UUID}]: Performance state</name><key>nvml.device.performance.state["{#UUID}"]</key><description>Retrieves the current performance state for the device.
|
|
For Nvidia Fermi or newer fully supported devices.</description><valuemap><name>Performance state</name></valuemap><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>6b99a9e1c5b841059f0e62b04001c82d</uuid><name>[{#UUID}]: Power limit</name><key>nvml.device.power.limit["{#UUID}"]</key><delay>1h</delay><value_type>FLOAT</value_type><units>watts</units><description>Retrieves the power management limit associated with this device.
|
|
For Nvidia Fermi or newer fully supported devices.
|
|
The power limit defines the upper boundary for the card's power draw. If the card's total power draw reaches this limit, the power management algorithm kicks in.
|
|
This reading is only available if power management mode is supported.</description><preprocessing><step><type>MULTIPLIER</type><parameters><parameter>0.001</parameter></parameters></step></preprocessing><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags><trigger_prototypes><trigger_prototype><uuid>4c821a8812c444eca5e03cc0d223b697</uuid><expression>change(/Nvidia by Zabbix agent 2/nvml.device.power.limit["{#UUID}"]) <> 0</expression><name>Nvidia: [{#UUID}]: Power limit has changed</name><event_name>Nvidia: [{#UUID}]Power limit on {HOST.HOST} has changed.</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>INFO</priority><description>Power limit for the device has changed. Check if this was intentional.</description><manual_close>YES</manual_close><tags><tag><tag>scope</tag><value>notice</value></tag></tags></trigger_prototype></trigger_prototypes></item_prototype><item_prototype><uuid>bb1c7aee478f4ba4b108491532ccd737</uuid><name>[{#UUID}]: Power usage</name><key>nvml.device.power.usage["{#UUID}"]</key><value_type>FLOAT</value_type><units>watts</units><description>Retrieves power usage for this GPU (in watts) and its associated circuitry (e.g. memory).
|
|
For Nvidia Fermi or newer fully supported devices.
|
|
On Fermi and Kepler GPUs, the reading is accurate to within +/- 5% of current power draw. On Ampere (except GA100) or newer GPUs, the API returns power averaged over a 1 second interval. On GA100 and older architectures, instantaneous power is returned.</description><preprocessing><step><type>MULTIPLIER</type><parameters><parameter>0.001</parameter></parameters></step></preprocessing><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>94c121b6588d424f9573f6e1352b5cd4</uuid><name>[{#UUID}]: Serial number</name><key>nvml.device.serial["{#UUID}"]</key><delay>1h</delay><value_type>CHAR</value_type><description>Retrieves the globally unique board serial number associated with this device's board.
|
|
For all products with an inforom.
|
|
This number matches the serial number tag that is physically attached to the board.</description><preprocessing><step><type>CHECK_NOT_SUPPORTED</type><parameters><parameter>0</parameter><parameter>The requested operation is not available on target device</parameter></parameters><error_handler>CUSTOM_ERROR</error_handler><error_handler_params>The device does not support operation to retrieve serial number.</error_handler_params></step></preprocessing><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>6e149695990a46f294361c047f288b80</uuid><name>[{#UUID}]: SM frequency</name><key>nvml.device.sm.frequency["{#UUID}"]</key><units>Hz</units><description>Retrieves the current SM clock speed for the device.
|
|
For Nvidia Fermi or newer fully supported devices.</description><preprocessing><step><type>MULTIPLIER</type><parameters><parameter>1000000</parameter></parameters></step></preprocessing><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>f47e1eed64354c7cb010dea8570c067b</uuid><name>[{#UUID}]: Temperature</name><key>nvml.device.temperature["{#UUID}"]</key><units>C</units><description>Retrieves the current temperature readings for the device, in degrees C.
|
|
For Nvidia all products.</description><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags><trigger_prototypes><trigger_prototype><uuid>563fdb237ef84d51b53d6ce70e9c67ad</uuid><expression>min(/Nvidia by Zabbix agent 2/nvml.device.temperature["{#UUID}"],3m) > {$NVIDIA.TEMPERATURE.CRIT}</expression><name>Nvidia: [{#UUID}]: Temperature exceeded critical threshold</name><event_name>Nvidia: [{#UUID}]: Temperature ({ITEM.VALUE1}) exceeded critical threshold ({$NVIDIA.TEMPERATURE.CRIT} C)</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>AVERAGE</priority><description>[{#UUID}]: Temperature is very high. It may indicate abnormal behavior/activity. Change corresponding macro in case of false-positive.</description><tags><tag><tag>scope</tag><value>performance</value></tag></tags></trigger_prototype><trigger_prototype><uuid>a5d5a632695c415eab61d427f221db93</uuid><expression>min(/Nvidia by Zabbix agent 2/nvml.device.temperature["{#UUID}"],3m) > {$NVIDIA.TEMPERATURE.WARN}</expression><name>Nvidia: [{#UUID}]: Temperature exceeded warning threshold</name><event_name>Nvidia: [{#UUID}]: Temperature ({ITEM.VALUE1}) exceeded warning threshold ({$NVIDIA.TEMPERATURE.WARN} C)</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>WARNING</priority><description>[{#UUID}]: Temperature is high. It may indicate abnormal behavior/activity. Change corresponding macro in case of false-positive.</description><dependencies><dependency><name>Nvidia: [{#UUID}]: Temperature exceeded critical threshold</name><expression>min(/Nvidia by Zabbix agent 2/nvml.device.temperature["{#UUID}"],3m) > {$NVIDIA.TEMPERATURE.CRIT}</expression></dependency></dependencies><tags><tag><tag>scope</tag><value>performance</value></tag></tags></trigger_prototype></trigger_prototypes></item_prototype><item_prototype><uuid>0dce87608aeb4b77b0e0df8baf1b9027</uuid><name>[{#UUID}]: GPU utilization</name><type>DEPENDENT</type><key>nvml.device.utilization.gpu["{#UUID}"]</key><units>%</units><description>Percentage of time over the past sampling period during which one or more kernels were running on the GPU.
|
|
For Nvidia Fermi or newer fully supported devices.</description><preprocessing><step><type>JSONPATH</type><parameters><parameter>$.device</parameter></parameters></step></preprocessing><master_item><key>nvml.device.utilization["{#UUID}"]</key></master_item><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags><trigger_prototypes><trigger_prototype><uuid>fcc330882ac34f59b2277dd4533d66f8</uuid><expression>min(/Nvidia by Zabbix agent 2/nvml.device.utilization.gpu["{#UUID}"],3m) > {$NVIDIA.GPU.UTIL.CRIT}</expression><name>Nvidia: [{#UUID}]: GPU utilization exceeded critical threshold</name><event_name>Nvidia: [{#UUID}]: GPU utilization ({ITEM.VALUE1}) exceeded critical threshold ({$NVIDIA.GPU.UTIL.CRIT} %)</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>AVERAGE</priority><description>[{#UUID}]: GPU utilization is very high. It may indicate abnormal behavior/activity. Change corresponding macro in case of false-positive.</description><tags><tag><tag>scope</tag><value>performance</value></tag></tags></trigger_prototype><trigger_prototype><uuid>ffa0dd66c71e4c8991244e80d8c4c53a</uuid><expression>min(/Nvidia by Zabbix agent 2/nvml.device.utilization.gpu["{#UUID}"],3m) > {$NVIDIA.GPU.UTIL.WARN}</expression><name>Nvidia: [{#UUID}]: GPU utilization exceeded warning threshold</name><event_name>Nvidia: [{#UUID}]: GPU utilization ({ITEM.VALUE1}) exceeded warning threshold ({$NVIDIA.GPU.UTIL.WARN} %)</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>WARNING</priority><description>[{#UUID}]: GPU utilization is high. It may indicate abnormal behavior/activity. Change corresponding macro in case of false-positive.</description><dependencies><dependency><name>Nvidia: [{#UUID}]: GPU utilization exceeded critical threshold</name><expression>min(/Nvidia by Zabbix agent 2/nvml.device.utilization.gpu["{#UUID}"],3m) > {$NVIDIA.GPU.UTIL.CRIT}</expression></dependency></dependencies><tags><tag><tag>scope</tag><value>performance</value></tag></tags></trigger_prototype></trigger_prototypes></item_prototype><item_prototype><uuid>c545a78d63644cefac8de7c1c2cbea9a</uuid><name>[{#UUID}]: Memory utilization</name><type>DEPENDENT</type><key>nvml.device.utilization.memory["{#UUID}"]</key><units>%</units><description>Percentage of time over the past sampling period during which global (device) memory was being read or written.
|
|
For Nvidia Fermi or newer fully supported devices.</description><preprocessing><step><type>JSONPATH</type><parameters><parameter>$.memory</parameter></parameters></step></preprocessing><master_item><key>nvml.device.utilization["{#UUID}"]</key></master_item><tags><tag><tag>component</tag><value>memory</value></tag><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags><trigger_prototypes><trigger_prototype><uuid>6e296d7736a2484d8b971e51b306927d</uuid><expression>min(/Nvidia by Zabbix agent 2/nvml.device.utilization.memory["{#UUID}"],3m) > {$NVIDIA.MEMORY.UTIL.CRIT}</expression><name>Nvidia: [{#UUID}]: Memory utilization exceeded critical threshold</name><event_name>Nvidia: [{#UUID}]: Memory utilization ({ITEM.VALUE1}) exceeded critical threshold ({$NVIDIA.MEMORY.UTIL.CRIT} %)</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>AVERAGE</priority><description>[{#UUID}]: Memory utilization is very high. It may indicate abnormal behavior/activity. Change corresponding macro in case of false-positive.</description><tags><tag><tag>scope</tag><value>performance</value></tag></tags></trigger_prototype><trigger_prototype><uuid>722ff2b5a1d94d5f83f2946b04c989ad</uuid><expression>min(/Nvidia by Zabbix agent 2/nvml.device.utilization.memory["{#UUID}"],3m) > {$NVIDIA.MEMORY.UTIL.WARN}</expression><name>Nvidia: [{#UUID}]: Memory utilization exceeded warning threshold</name><event_name>Nvidia: [{#UUID}]: Memory utilization ({ITEM.VALUE1}) exceeded warning threshold ({$NVIDIA.MEMORY.UTIL.WARN} %)</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>WARNING</priority><description>[{#UUID}]: Memory utilization is high. It may indicate abnormal behavior/activity. Change corresponding macro in case of false-positive.</description><dependencies><dependency><name>Nvidia: [{#UUID}]: Memory utilization exceeded critical threshold</name><expression>min(/Nvidia by Zabbix agent 2/nvml.device.utilization.memory["{#UUID}"],3m) > {$NVIDIA.MEMORY.UTIL.CRIT}</expression></dependency></dependencies><tags><tag><tag>scope</tag><value>performance</value></tag></tags></trigger_prototype></trigger_prototypes></item_prototype><item_prototype><uuid>9a3e4972de4d4149bf14512be108179f</uuid><name>[{#UUID}]: Device utilization, get</name><key>nvml.device.utilization["{#UUID}"]</key><history>0</history><value_type>TEXT</value_type><description>Retrieves the current utilization rates for the device's major subsystems.
|
|
For Nvidia Fermi or newer fully supported devices.</description><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>component</tag><value>raw</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype><item_prototype><uuid>91fc19e1784846b7afb982f7ae87439e</uuid><name>[{#UUID}]: Video frequency</name><key>nvml.device.video.frequency["{#UUID}"]</key><units>Hz</units><description>Retrieves the current video encoder/decoder clock speed for the device.
|
|
For Nvidia Fermi or newer fully supported devices.</description><preprocessing><step><type>MULTIPLIER</type><parameters><parameter>1000000</parameter></parameters></step></preprocessing><tags><tag><tag>component</tag><value>nvidia</value></tag><tag><tag>device</tag><value>{#NAME}</value></tag><tag><tag>device</tag><value>{#UUID}</value></tag></tags></item_prototype></item_prototypes><trigger_prototypes><trigger_prototype><uuid>655ad43bd4744909aea3f843db89fe36</uuid><expression>(min(/Nvidia by Zabbix agent 2/nvml.device.power.usage["{#UUID}"],3m) * 100 / last(/Nvidia by Zabbix agent 2/nvml.device.power.limit["{#UUID}"])) > {$NVIDIA.POWER.UTIL.CRIT}</expression><name>Nvidia: [{#UUID}]: Power usage exceeded critical threshold</name><event_name>Nvidia: [{#UUID}]: Power usage ({ITEM.VALUE1}) exceeded critical threshold ({$NVIDIA.POWER.UTIL.CRIT} %)</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>AVERAGE</priority><description>[{#UUID}]: Power usage is very high. It may indicate abnormal behavior/activity. Change corresponding macro in case of false-positive.</description><tags><tag><tag>scope</tag><value>performance</value></tag></tags></trigger_prototype><trigger_prototype><uuid>5ffa7d5f130b4e46936a6f17f7773efe</uuid><expression>(min(/Nvidia by Zabbix agent 2/nvml.device.power.usage["{#UUID}"],3m) * 100 / last(/Nvidia by Zabbix agent 2/nvml.device.power.limit["{#UUID}"])) > {$NVIDIA.POWER.UTIL.WARN}</expression><name>Nvidia: [{#UUID}]: Power usage exceeded warning threshold</name><event_name>Nvidia: [{#UUID}]: Power usage ({ITEM.VALUE1}) exceeded warning threshold ({$NVIDIA.POWER.UTIL.WARN} %)</event_name><opdata>current value: {ITEM.LASTVALUE1}</opdata><priority>WARNING</priority><description>[{#UUID}]: Power usage is high. It may indicate abnormal behavior/activity. Change corresponding macro in case of false-positive.</description><dependencies><dependency><name>Nvidia: [{#UUID}]: Power usage exceeded critical threshold</name><expression>(min(/Nvidia by Zabbix agent 2/nvml.device.power.usage["{#UUID}"],3m) * 100 / last(/Nvidia by Zabbix agent 2/nvml.device.power.limit["{#UUID}"])) > {$NVIDIA.POWER.UTIL.CRIT}</expression></dependency></dependencies><tags><tag><tag>scope</tag><value>performance</value></tag></tags></trigger_prototype></trigger_prototypes><graph_prototypes><graph_prototype><uuid>5d68d70d11454cb5942b251e6d1c2eb3</uuid><name>Nvidia: [{#UUID}]: BAR1 memory</name><type>STACKED</type><ymax_type_1>ITEM</ymax_type_1><ymax_item_1><host>Nvidia by Zabbix agent 2</host><key>nvml.device.memory.bar1.total["{#UUID}"]</key></ymax_item_1><graph_items><graph_item><color>FF0000</color><item><host>Nvidia by Zabbix agent 2</host><key>nvml.device.memory.bar1.used["{#UUID}"]</key></item></graph_item><graph_item><sortorder>1</sortorder><color>76B900</color><item><host>Nvidia by Zabbix agent 2</host><key>nvml.device.memory.bar1.free["{#UUID}"]</key></item></graph_item></graph_items></graph_prototype><graph_prototype><uuid>9e977f8c9d5c4568b2ec57a6aeb03361</uuid><name>Nvidia: [{#UUID}]: Fan speed</name><graph_items><graph_item><color>199C0D</color><item><host>Nvidia by Zabbix agent 2</host><key>nvml.device.fan.speed.avg["{#UUID}"]</key></item></graph_item></graph_items></graph_prototype><graph_prototype><uuid>62d7606507774eee96f0d56fd6d74a6f</uuid><name>Nvidia: [{#UUID}]: FB memory</name><type>STACKED</type><ymax_type_1>ITEM</ymax_type_1><ymax_item_1><host>Nvidia by Zabbix agent 2</host><key>nvml.device.memory.fb.total["{#UUID}"]</key></ymax_item_1><graph_items><graph_item><color>FF0000</color><item><host>Nvidia by Zabbix agent 2</host><key>nvml.device.memory.fb.used["{#UUID}"]</key></item></graph_item><graph_item><sortorder>1</sortorder><color>FF8000</color><item><host>Nvidia by Zabbix agent 2</host><key>nvml.device.memory.fb.reserved["{#UUID}"]</key></item></graph_item><graph_item><sortorder>2</sortorder><color>76B900</color><item><host>Nvidia by Zabbix agent 2</host><key>nvml.device.memory.fb.free["{#UUID}"]</key></item></graph_item></graph_items></graph_prototype><graph_prototype><uuid>93509c440ee446d7b96c407207bcd726</uuid><name>Nvidia: [{#UUID}]: Memory ECC errors</name><graph_items><graph_item><color>76B900</color><item><host>Nvidia by Zabbix agent 2</host><key>nvml.device.errors.memory.corrected["{#UUID}"]</key></item></graph_item><graph_item><sortorder>1</sortorder><color>FF0000</color><item><host>Nvidia by Zabbix agent 2</host><key>nvml.device.errors.memory.uncorrected["{#UUID}"]</key></item></graph_item></graph_items></graph_prototype><graph_prototype><uuid>9acad578a5ee4ce6aeef509d5d08f824</uuid><name>Nvidia: [{#UUID}]: PCIe utilization</name><graph_items><graph_item><color>FF0000</color><item><host>Nvidia by Zabbix agent 2</host><key>nvml.device.pci.utilization.rx.rate["{#UUID}"]</key></item></graph_item><graph_item><sortorder>1</sortorder><color>0040FF</color><item><host>Nvidia by Zabbix agent 2</host><key>nvml.device.pci.utilization.tx.rate["{#UUID}"]</key></item></graph_item></graph_items></graph_prototype><graph_prototype><uuid>7a36984b772d4c3292ca0a8eafbd2c3d</uuid><name>Nvidia: [{#UUID}]: Performance state</name><yaxismax>15</yaxismax><ymin_type_1>FIXED</ymin_type_1><ymax_type_1>FIXED</ymax_type_1><graph_items><graph_item><color>199C0D</color><item><host>Nvidia by Zabbix agent 2</host><key>nvml.device.performance.state["{#UUID}"]</key></item></graph_item></graph_items></graph_prototype><graph_prototype><uuid>08956a3887d14562b2c12a78c7519a23</uuid><name>Nvidia: [{#UUID}]: Power usage</name><ymax_type_1>ITEM</ymax_type_1><ymax_item_1><host>Nvidia by Zabbix agent 2</host><key>nvml.device.power.limit["{#UUID}"]</key></ymax_item_1><graph_items><graph_item><color>199C0D</color><item><host>Nvidia by Zabbix agent 2</host><key>nvml.device.power.usage["{#UUID}"]</key></item></graph_item></graph_items></graph_prototype><graph_prototype><uuid>30a5a91d874847619938568ffa0a7341</uuid><name>Nvidia: [{#UUID}]: Register file errors</name><graph_items><graph_item><color>76B900</color><item><host>Nvidia by Zabbix agent 2</host><key>nvml.device.errors.register.corrected["{#UUID}"]</key></item></graph_item><graph_item><sortorder>1</sortorder><color>FF0000</color><item><host>Nvidia by Zabbix agent 2</host><key>nvml.device.errors.register.uncorrected["{#UUID}"]</key></item></graph_item></graph_items></graph_prototype></graph_prototypes><master_item><key>nvml.device.get</key></master_item><lld_macro_paths><lld_macro_path><lld_macro>{#NAME}</lld_macro><path>$.device_name</path></lld_macro_path><lld_macro_path><lld_macro>{#UUID}</lld_macro><path>$.device_uuid</path></lld_macro_path></lld_macro_paths><preprocessing><step><type>DISCARD_UNCHANGED_HEARTBEAT</type><parameters><parameter>1d</parameter></parameters></step></preprocessing></discovery_rule></discovery_rules><tags><tag><tag>class</tag><value>hardware</value></tag><tag><tag>target</tag><value>nvidia</value></tag></tags><macros><macro><macro>{$NVIDIA.DECODER.UTIL.CRIT}</macro><value>90</value><description>Critical threshold for decoder utilization, in %.</description></macro><macro><macro>{$NVIDIA.DECODER.UTIL.WARN}</macro><value>80</value><description>Warning threshold for decoder utilization, in %.</description></macro><macro><macro>{$NVIDIA.ENCODER.UTIL.CRIT}</macro><value>90</value><description>Critical threshold for encoder utilization, in %.</description></macro><macro><macro>{$NVIDIA.ENCODER.UTIL.WARN}</macro><value>80</value><description>Warning threshold for encoder utilization, in %.</description></macro><macro><macro>{$NVIDIA.FAN.SPEED.CRIT}</macro><value>90</value><description>Critical threshold for fan speed, in %.</description></macro><macro><macro>{$NVIDIA.FAN.SPEED.WARN}</macro><value>80</value><description>Warning threshold for fan speed, in %.</description></macro><macro><macro>{$NVIDIA.GPU.UTIL.CRIT}</macro><value>90</value><description>Critical threshold for overall GPU utilization, in %.</description></macro><macro><macro>{$NVIDIA.GPU.UTIL.WARN}</macro><value>80</value><description>Warning threshold for overall GPU utilization, in %.</description></macro><macro><macro>{$NVIDIA.MEMORY.UTIL.CRIT}</macro><value>90</value><description>Critical threshold for memory utilization, in %.</description></macro><macro><macro>{$NVIDIA.MEMORY.UTIL.WARN}</macro><value>80</value><description>Warning threshold for memory utilization, in %.</description></macro><macro><macro>{$NVIDIA.NAME.MATCHES}</macro><value>.*</value><description>Filter to include GPUs by name in discovery.</description></macro><macro><macro>{$NVIDIA.NAME.NOT_MATCHES}</macro><value>CHANGE IF NEEDED</value><description>Filter to exclude GPUs by name in discovery.</description></macro><macro><macro>{$NVIDIA.POWER.UTIL.CRIT}</macro><value>90</value><description>Critical threshold for power usage, in %.</description></macro><macro><macro>{$NVIDIA.POWER.UTIL.WARN}</macro><value>80</value><description>Warning threshold for power usage, in %.</description></macro><macro><macro>{$NVIDIA.TEMPERATURE.CRIT}</macro><value>90</value><description>Critical threshold for temperature, in %.</description></macro><macro><macro>{$NVIDIA.TEMPERATURE.WARN}</macro><value>80</value><description>Warning threshold for temperature, in %.</description></macro><macro><macro>{$NVIDIA.UUID.MATCHES}</macro><value>.*</value><description>Filter to include GPUs by UUID in discovery.</description></macro><macro><macro>{$NVIDIA.UUID.NOT_MATCHES}</macro><value>CHANGE IF NEEDED</value><description>Filter to exclude GPUs by UUID in discovery.</description></macro></macros><dashboards><dashboard><uuid>bc2dc6cc58984a20829499823a3c84fa</uuid><name>Nvidia: Overview</name><pages><page><name>Summary</name><widgets><widget><type>svggraph</type><name>GPU utilization</name><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>ds.0.fill</name><value>0</value></field><field><type>STRING</type><name>ds.0.items.0</name><value>*GPU utilization*</value></field><field><type>INTEGER</type><name>ds.0.missingdatafunc</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.transparency</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.width</name><value>3</value></field><field><type>INTEGER</type><name>legend_lines</name><value>10</value></field><field><type>INTEGER</type><name>legend_lines_mode</name><value>1</value></field><field><type>INTEGER</type><name>legend_statistic</name><value>1</value></field><field><type>STRING</type><name>reference</name><value>EBEFB</value></field></fields></widget><widget><type>svggraph</type><name>Temperature</name><y>6</y><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>ds.0.fill</name><value>0</value></field><field><type>STRING</type><name>ds.0.items.0</name><value>*Temperature*</value></field><field><type>INTEGER</type><name>ds.0.missingdatafunc</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.transparency</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.width</name><value>3</value></field><field><type>INTEGER</type><name>legend_lines</name><value>10</value></field><field><type>INTEGER</type><name>legend_lines_mode</name><value>1</value></field><field><type>INTEGER</type><name>legend_statistic</name><value>1</value></field><field><type>STRING</type><name>reference</name><value>ECEEB</value></field></fields></widget><widget><type>svggraph</type><name>Memory utilization</name><x>36</x><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>ds.0.fill</name><value>0</value></field><field><type>STRING</type><name>ds.0.items.0</name><value>*Memory utilization*</value></field><field><type>INTEGER</type><name>ds.0.missingdatafunc</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.transparency</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.width</name><value>3</value></field><field><type>INTEGER</type><name>legend_lines</name><value>10</value></field><field><type>INTEGER</type><name>legend_lines_mode</name><value>1</value></field><field><type>INTEGER</type><name>legend_statistic</name><value>1</value></field><field><type>STRING</type><name>reference</name><value>EBEEB</value></field></fields></widget><widget><type>svggraph</type><name>Power usage</name><x>36</x><y>6</y><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>ds.0.fill</name><value>0</value></field><field><type>STRING</type><name>ds.0.items.0</name><value>*Power usage*</value></field><field><type>INTEGER</type><name>ds.0.missingdatafunc</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.transparency</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.width</name><value>3</value></field><field><type>INTEGER</type><name>legend_lines</name><value>10</value></field><field><type>INTEGER</type><name>legend_lines_mode</name><value>1</value></field><field><type>INTEGER</type><name>legend_statistic</name><value>1</value></field><field><type>STRING</type><name>reference</name><value>ECEDB</value></field></fields></widget></widgets></page><page><name>Frequencies</name><widgets><widget><type>svggraph</type><name>SM frequency</name><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>ds.0.fill</name><value>0</value></field><field><type>STRING</type><name>ds.0.items.0</name><value>*SM frequency*</value></field><field><type>INTEGER</type><name>ds.0.missingdatafunc</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.transparency</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.width</name><value>3</value></field><field><type>INTEGER</type><name>legend_lines</name><value>10</value></field><field><type>INTEGER</type><name>legend_lines_mode</name><value>1</value></field><field><type>INTEGER</type><name>legend_statistic</name><value>1</value></field><field><type>STRING</type><name>reference</name><value>DCBFA</value></field></fields></widget><widget><type>svggraph</type><name>Video frequency</name><y>6</y><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>ds.0.fill</name><value>0</value></field><field><type>STRING</type><name>ds.0.items.0</name><value>*Video frequency*</value></field><field><type>INTEGER</type><name>ds.0.missingdatafunc</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.transparency</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.width</name><value>3</value></field><field><type>INTEGER</type><name>legend_lines</name><value>10</value></field><field><type>INTEGER</type><name>legend_lines_mode</name><value>1</value></field><field><type>INTEGER</type><name>legend_statistic</name><value>1</value></field><field><type>STRING</type><name>reference</name><value>FCACC</value></field></fields></widget><widget><type>svggraph</type><name>Graphics frequency</name><x>36</x><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>ds.0.fill</name><value>0</value></field><field><type>STRING</type><name>ds.0.items.0</name><value>*Graphics frequency*</value></field><field><type>INTEGER</type><name>ds.0.missingdatafunc</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.transparency</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.width</name><value>3</value></field><field><type>INTEGER</type><name>legend_lines</name><value>10</value></field><field><type>INTEGER</type><name>legend_lines_mode</name><value>1</value></field><field><type>INTEGER</type><name>legend_statistic</name><value>1</value></field><field><type>STRING</type><name>reference</name><value>ADAEE</value></field></fields></widget><widget><type>svggraph</type><name>Memory frequency</name><x>36</x><y>6</y><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>ds.0.fill</name><value>0</value></field><field><type>STRING</type><name>ds.0.items.0</name><value>*Memory frequency*</value></field><field><type>INTEGER</type><name>ds.0.missingdatafunc</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.transparency</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.width</name><value>3</value></field><field><type>INTEGER</type><name>legend_lines</name><value>10</value></field><field><type>INTEGER</type><name>legend_lines_mode</name><value>1</value></field><field><type>INTEGER</type><name>legend_statistic</name><value>1</value></field><field><type>STRING</type><name>reference</name><value>DAEBE</value></field></fields></widget></widgets></page><page><name>Memory errors</name><widgets><widget><type>svggraph</type><name>Memory ECC errors, corrected</name><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>ds.0.fill</name><value>0</value></field><field><type>STRING</type><name>ds.0.items.0</name><value>*Memory ECC errors, corrected*</value></field><field><type>INTEGER</type><name>ds.0.transparency</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.width</name><value>3</value></field><field><type>INTEGER</type><name>legend_lines</name><value>10</value></field><field><type>INTEGER</type><name>legend_lines_mode</name><value>1</value></field><field><type>INTEGER</type><name>legend_statistic</name><value>1</value></field><field><type>STRING</type><name>reference</name><value>ECBFB</value></field></fields></widget><widget><type>svggraph</type><name>Register file Errors, corrected</name><y>6</y><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>ds.0.fill</name><value>0</value></field><field><type>STRING</type><name>ds.0.items.0</name><value>*Register file errors, corrected*</value></field><field><type>INTEGER</type><name>ds.0.transparency</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.width</name><value>3</value></field><field><type>INTEGER</type><name>legend_lines</name><value>10</value></field><field><type>INTEGER</type><name>legend_lines_mode</name><value>1</value></field><field><type>INTEGER</type><name>legend_statistic</name><value>1</value></field><field><type>STRING</type><name>reference</name><value>ECBFF</value></field></fields></widget><widget><type>svggraph</type><name>Memory ECC errors, uncorrected</name><x>36</x><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>ds.0.fill</name><value>0</value></field><field><type>STRING</type><name>ds.0.items.0</name><value>*Memory ECC errors, uncorrected*</value></field><field><type>INTEGER</type><name>ds.0.transparency</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.width</name><value>3</value></field><field><type>INTEGER</type><name>legend_lines</name><value>10</value></field><field><type>INTEGER</type><name>legend_lines_mode</name><value>1</value></field><field><type>INTEGER</type><name>legend_statistic</name><value>1</value></field><field><type>STRING</type><name>reference</name><value>EABFF</value></field></fields></widget><widget><type>svggraph</type><name>Register file Errors, uncorrected</name><x>36</x><y>6</y><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>ds.0.fill</name><value>0</value></field><field><type>STRING</type><name>ds.0.items.0</name><value>*Register file errors, uncorrected*</value></field><field><type>INTEGER</type><name>ds.0.transparency</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.width</name><value>3</value></field><field><type>INTEGER</type><name>legend_lines</name><value>10</value></field><field><type>INTEGER</type><name>legend_lines_mode</name><value>1</value></field><field><type>INTEGER</type><name>legend_statistic</name><value>1</value></field><field><type>STRING</type><name>reference</name><value>ECBFA</value></field></fields></widget></widgets></page><page><name>Memory, PCI, fan</name><widgets><widget><type>graphprototype</type><name>BAR1 memory</name><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>columns</name><value>1</value></field><field><type>GRAPH_PROTOTYPE</type><name>graphid.0</name><value><host>Nvidia by Zabbix agent 2</host><name>Nvidia: [{#UUID}]: BAR1 memory</name></value></field><field><type>STRING</type><name>reference</name><value>DCBFB</value></field></fields></widget><widget><type>graphprototype</type><name>PCIe utilization</name><y>6</y><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>columns</name><value>1</value></field><field><type>GRAPH_PROTOTYPE</type><name>graphid.0</name><value><host>Nvidia by Zabbix agent 2</host><name>Nvidia: [{#UUID}]: PCIe utilization</name></value></field><field><type>STRING</type><name>reference</name><value>ACECA</value></field></fields></widget><widget><type>graphprototype</type><name>FB memory</name><x>36</x><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>columns</name><value>1</value></field><field><type>GRAPH_PROTOTYPE</type><name>graphid.0</name><value><host>Nvidia by Zabbix agent 2</host><name>Nvidia: [{#UUID}]: FB memory</name></value></field><field><type>STRING</type><name>reference</name><value>ACDCA</value></field></fields></widget><widget><type>graphprototype</type><name>Fan speed</name><x>36</x><y>6</y><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>columns</name><value>1</value></field><field><type>GRAPH_PROTOTYPE</type><name>graphid.0</name><value><host>Nvidia by Zabbix agent 2</host><name>Nvidia: [{#UUID}]: Fan speed</name></value></field><field><type>STRING</type><name>reference</name><value>ACFCA</value></field></fields></widget></widgets></page><page><name>Encoders</name><widgets><widget><type>svggraph</type><name>Encoder utilization</name><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>ds.0.fill</name><value>0</value></field><field><type>STRING</type><name>ds.0.items.0</name><value>*Encoder utilization*</value></field><field><type>INTEGER</type><name>ds.0.transparency</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.width</name><value>3</value></field><field><type>INTEGER</type><name>legend_lines</name><value>10</value></field><field><type>INTEGER</type><name>legend_lines_mode</name><value>1</value></field><field><type>INTEGER</type><name>legend_statistic</name><value>1</value></field><field><type>STRING</type><name>reference</name><value>ECAFB</value></field></fields></widget><widget><type>svggraph</type><name>Encoder average FPS</name><y>6</y><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>ds.0.fill</name><value>0</value></field><field><type>STRING</type><name>ds.0.items.0</name><value>*Encoder average FPS*</value></field><field><type>INTEGER</type><name>ds.0.transparency</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.width</name><value>3</value></field><field><type>INTEGER</type><name>legend_lines</name><value>10</value></field><field><type>INTEGER</type><name>legend_lines_mode</name><value>1</value></field><field><type>INTEGER</type><name>legend_statistic</name><value>1</value></field><field><type>STRING</type><name>reference</name><value>ECFFF</value></field></fields></widget><widget><type>svggraph</type><name>Encoder sessions</name><x>36</x><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>ds.0.fill</name><value>0</value></field><field><type>STRING</type><name>ds.0.items.0</name><value>*Encoder sessions*</value></field><field><type>INTEGER</type><name>ds.0.transparency</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.width</name><value>3</value></field><field><type>INTEGER</type><name>legend_lines</name><value>10</value></field><field><type>INTEGER</type><name>legend_lines_mode</name><value>1</value></field><field><type>INTEGER</type><name>legend_statistic</name><value>1</value></field><field><type>STRING</type><name>reference</name><value>ECAFF</value></field></fields></widget><widget><type>svggraph</type><name>Encoder average latency</name><x>36</x><y>6</y><width>36</width><height>6</height><fields><field><type>INTEGER</type><name>ds.0.fill</name><value>0</value></field><field><type>STRING</type><name>ds.0.items.0</name><value>*Encoder average latency*</value></field><field><type>INTEGER</type><name>ds.0.transparency</name><value>1</value></field><field><type>INTEGER</type><name>ds.0.width</name><value>3</value></field><field><type>INTEGER</type><name>legend_lines</name><value>10</value></field><field><type>INTEGER</type><name>legend_lines_mode</name><value>1</value></field><field><type>INTEGER</type><name>legend_statistic</name><value>1</value></field><field><type>STRING</type><name>reference</name><value>ECFFA</value></field></fields></widget></widgets></page></pages></dashboard></dashboards><valuemaps><valuemap><uuid>9c9e6145dc87474ba03f16ea73c355d4</uuid><name>Performance state</name><mappings><mapping><value>0</value><newvalue>Maximum</newvalue></mapping><mapping><type>IN_RANGE</type><value>1-4</value><newvalue>High</newvalue></mapping><mapping><type>IN_RANGE</type><value>5-10</value><newvalue>Average</newvalue></mapping><mapping><type>IN_RANGE</type><value>11-14</value><newvalue>Low</newvalue></mapping><mapping><value>15</value><newvalue>Minimum</newvalue></mapping><mapping><value>32</value><newvalue>Unknown</newvalue></mapping></mappings></valuemap></valuemaps></template></templates></zabbix_export>
|