Uredi

Supported metrics for Microsoft.Storage/contextCaches/contextCacheContainers

The following table lists the metrics available for the Microsoft.Storage/contextCaches/contextCacheContainers resource type.

Table headings

  • Metric - The metric display name as it appears in the Azure portal.
  • Name in Rest API - Metric name as referred to in the REST API.
  • Advanced platform metrics - A premium, paid tier of platform metrics in Azure Monitor that provide more granular observability for Azure resources.
  • Unit - Unit of measure.
  • Aggregation - The default aggregation type. Valid values: Average, Minimum, Maximum, Total, Count.
  • Dimensions - Dimensions available for the metric.
  • Time Grains - Intervals at which the metric is sampled. For example, PT1M indicates that the metric is sampled every minute, PT30M every 30 minutes, PT1H every hour, and so on.
  • DS Export - Shows whether the metric is exportable to Azure Monitor Logs via Diagnostic Settings.

For information on exporting metrics, see - Metrics export using data collection rules and Create diagnostic settings in Azure Monitor.

For information on metric retention, see Azure Monitor Metrics overview.

Category: Latency

Metric Name in REST API Advanced platform metrics Unit Aggregation Dimensions Time Grains DS Export
Lookup latency

End-to-end latency of Lookup requests. Only successful requests with a bounded latency are included.
LookupLatency No MilliSeconds Average, Minimum, Maximum, Total (Sum), Count providerName, modelName PT1M Yes
Read latency

End-to-end latency of StreamingRead requests. Only successful requests with a bounded latency are included.
ReadLatency No MilliSeconds Average, Minimum, Maximum, Total (Sum), Count providerName, modelName PT1M Yes
Write latency

End-to-end latency of Write requests. Only successful requests with a bounded latency are included.
WriteLatency No MilliSeconds Average, Minimum, Maximum, Total (Sum), Count providerName, modelName PT1M Yes

Category: Traffic

Metric Name in REST API Advanced platform metrics Unit Aggregation Dimensions Time Grains DS Export
Cache hit rate

Percentage of prompt tokens served from cache (token-weighted). Derived as CacheHitCount / (CacheHitCount + CacheMissCount) x 100 over successful Lookups.
CacheHitRate No Percent Average, Minimum, Maximum providerName, modelName PT1M Yes
Read tokens per minute

StreamingRead throughput in tokens per minute. Derived as sum(ReadSize) over 1-minute windows grouped by container.
ReadTpm No Count Average, Minimum, Maximum providerName, modelName PT1M Yes
Write tokens per minute

Write throughput in tokens per minute. Derived as sum(WriteSize) over 1-minute windows grouped by container.
WriteTpm No Count Average, Minimum, Maximum providerName, modelName PT1M Yes

Next steps