obsdog

Databricks integration metrics

The official Datadog integration for monitoring Databricks. It collects 16 metrics.

Official summary

Monitor the reliability and cost of your Databricks environment.

Metric types

  • gauge (value at a point in time): 16

Metrics

Descriptions are the official definitions, unedited.

MetricTypeUnit
databricks.model_serving.cpu_usage_percentageAverage CPU utilization used across all replicas during the last minutegaugepercent
databricks.model_serving.gpu_mem_usage_percentage.avgAverage GPU memory usage used across all GPUs during the minutegaugepercent
databricks.model_serving.gpu_mem_usage_percentage.maxMaximum GPU memory usage used across all GPUs during the minutegaugepercent
databricks.model_serving.gpu_mem_usage_percentage.minMinimum GPU memory usage used across all GPUs during the minutegaugepercent
databricks.model_serving.gpu_usage_percentage.avgAverage GPU utilization used across all GPUs during the minutegaugepercent
databricks.model_serving.gpu_usage_percentage.maxMaximum GPU utilization used across all GPUs during the minutegaugepercent
databricks.model_serving.gpu_usage_percentage.minMinimum GPU utilization used across all GPUs during the minutegaugepercent
databricks.model_serving.mem_usage_percentageAverage memory utilization used across all replicas during the last minutegaugepercent
databricks.model_serving.provisioned_concurrent_requests_totalNumber of provisioned concurrency during the last minutegaugerequest
databricks.model_serving.request_4xx_count_totalNumber of 4xx errors during the last minutegaugerequest
databricks.model_serving.request_5xx_count_totalNumber of 5xx errors during the last minutegaugerequest
databricks.model_serving.request_count_totalNumber of requests during the last minutegaugerequest
databricks.model_serving.request_latency_ms.75percentile75th percentile request latency in milliseconds during the minutegaugemillisecond
databricks.model_serving.request_latency_ms.90percentile90th percentile request latency in milliseconds during the minutegaugemillisecond
databricks.model_serving.request_latency_ms.95percentile95th percentile request latency in milliseconds during the minutegaugemillisecond
databricks.model_serving.request_latency_ms.99percentile99th percentile request latency in milliseconds during the minutegaugemillisecond

Official documentation

Official documentation for the Databricks integration

Metric names and descriptions are the official Datadog integration definitions (Copyright Datadog, Inc., BSD-3-Clause), reproduced unedited. The full license terms are on the About page.

Related products

IntegrationsIntegrations are the bundle of entry points that pour data from external systems such as AWS and MySQL into Datadog. Where you configure them splits into two families, the Agent side and the cloud account side, and which one you choose changes both what you can see and how billing is counted.Foundation and data collectionLLM ObservabilityLLM Observability records a single request to an application with an embedded LLM as a trace, tracks the inputs and outputs, tokens, latency, and errors of each model call, and turns response quality into numbers through evaluations. The only thing billed is the LLM span, which represents a model call.APM and tracingInfrastructure MonitoringInfrastructure Monitoring is the product that visualizes the state of servers, containers, and cloud resources at the host level. The host map and process list let you grasp at a glance which host is struggling right now.Infrastructure monitoring

Other Cost Management integrations

LangChain6 metricsOpenAI29 metricsAnthropic Usage and Costs8 metrics