Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[INTERNAL] Open Telemetry: Adds documentation with details #4944

Merged
merged 7 commits into from
Jan 8, 2025
Merged
Show file tree
Hide file tree
Changes from 2 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
86 changes: 51 additions & 35 deletions Microsoft.Azure.Cosmos/src/Resource/ClientContextCore.cs
Original file line number Diff line number Diff line change
Expand Up @@ -532,17 +532,21 @@ private async Task<TResult> RunWithDiagnosticsHelperAsync<TResult>(
// Checks if OpenTelemetry is configured for this operation and either Trace or Metrics are enabled by customer
if (isOtelCompatibleOperation)
{
// Extracts and records telemetry data from the result of the operation.
OpenTelemetryAttributes otelAttributes = openTelemetry?.GetAttributes(result);

// Records the telemetry attributes for Distributed Tracing (if enabled) and Metrics
recorder.Record(otelAttributes);
RecordMetrics(getOperationName,
this.client.Endpoint,
containerName,
databaseName,
requestOptions,
attributes: otelAttributes);
using (ITrace telemetryTrace = trace.StartChild("Recording Telemetry"))
sourabh1007 marked this conversation as resolved.
Show resolved Hide resolved
{
// Extracts and records telemetry data from the result of the operation.
OpenTelemetryAttributes otelAttributes = openTelemetry?.GetAttributes(result);

// Records the telemetry attributes for Distributed Tracing (if enabled) and Metrics
recorder.Record(otelAttributes);
RecordMetrics(getOperationName,
this.client.Endpoint,
containerName,
databaseName,
requestOptions,
attributes: otelAttributes,
trace: telemetryTrace);
}
}

return result;
Expand All @@ -551,13 +555,17 @@ private async Task<TResult> RunWithDiagnosticsHelperAsync<TResult>(
{
if (isOtelCompatibleOperation)
{
recorder.MarkFailed(cosmosException);
RecordMetrics(getOperationName,
gatewayEndpoint,
containerName,
databaseName,
requestOptions,
cosmosException: cosmosException);
using (ITrace telemetryTrace = trace.StartChild("Recording Telemetry"))
{
recorder.MarkFailed(cosmosException);
RecordMetrics(getOperationName,
gatewayEndpoint,
containerName,
databaseName,
requestOptions,
cosmosException: cosmosException,
trace: telemetryTrace);
}
}

throw cosmosException; // Rethrow after recording telemetry
Expand Down Expand Up @@ -613,24 +621,32 @@ private static void RecordMetrics(Func<string> getOperationName,
string databaseName,
RequestOptions requestOptions,
OpenTelemetryAttributes attributes = null,
Exception cosmosException = null)
Exception cosmosException = null,
ITrace trace = null)
{
// Records telemetry data
CosmosDbOperationMeter.RecordTelemetry(getOperationName: getOperationName,
accountName: accountName,
containerName: containerName,
databaseName: databaseName,
attributes: attributes,
operationMetricsOptions: requestOptions?.OperationMetricsOptions,
ex: cosmosException);

CosmosDbNetworkMeter.RecordTelemetry(getOperationName: getOperationName,
accountName: accountName,
containerName: containerName,
databaseName: databaseName,
attributes: attributes,
networkMetricsOptions: requestOptions?.NetworkMetricsOptions,
ex: cosmosException);
try
{
// Records telemetry data
CosmosDbOperationMeter.RecordTelemetry(getOperationName: getOperationName,
accountName: accountName,
containerName: containerName,
databaseName: databaseName,
attributes: attributes,
operationMetricsOptions: requestOptions?.OperationMetricsOptions,
ex: cosmosException);

CosmosDbNetworkMeter.RecordTelemetry(getOperationName: getOperationName,
accountName: accountName,
containerName: containerName,
databaseName: databaseName,
attributes: attributes,
networkMetricsOptions: requestOptions?.NetworkMetricsOptions,
ex: cosmosException);
}
catch (Exception ex)
{
trace?.AddDatum("Exception", ex.ToString());
}
}

private async Task<ResponseMessage> ProcessResourceOperationAsBulkStreamAsync(
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -102,34 +102,27 @@ internal static void RecordTelemetry(
return;
}

try
Func<KeyValuePair<string, object>[]> dimensionsFunc = () =>
DimensionPopulator.PopulateOperationMeterDimensions(
getOperationName(),
containerName,
databaseName,
accountName,
attributes,
ex,
operationMetricsOptions);

if (CosmosDbMeterUtil.TryOperationMetricsValues(attributes, ex, out OperationMetricData value))
{
Func<KeyValuePair<string, object>[]> dimensionsFunc = () =>
DimensionPopulator.PopulateOperationMeterDimensions(
getOperationName(),
containerName,
databaseName,
accountName,
attributes,
ex,
operationMetricsOptions);

if (CosmosDbMeterUtil.TryOperationMetricsValues(attributes, ex, out OperationMetricData value))
{
CosmosDbMeterUtil.RecordHistogramMetric<int>(value.ItemCount, dimensionsFunc, ActualItemHistogram, Convert.ToInt32);
CosmosDbMeterUtil.RecordHistogramMetric<double>(value.RequestCharge, dimensionsFunc, RequestUnitsHistogram);
}

if (CosmosDbMeterUtil.TryGetDiagnostics(attributes, ex, out CosmosTraceDiagnostics diagnostics))
{
CosmosDbMeterUtil.RecordHistogramMetric<double>(value: diagnostics.GetClientElapsedTime(),
dimensionsFunc, RequestLatencyHistogram,
t => ((TimeSpan)t).TotalSeconds);
}
CosmosDbMeterUtil.RecordHistogramMetric<int>(value.ItemCount, dimensionsFunc, ActualItemHistogram, Convert.ToInt32);
CosmosDbMeterUtil.RecordHistogramMetric<double>(value.RequestCharge, dimensionsFunc, RequestUnitsHistogram);
}
catch (Exception exception)

if (CosmosDbMeterUtil.TryGetDiagnostics(attributes, ex, out CosmosTraceDiagnostics diagnostics))
{
DefaultTrace.TraceWarning($"Failed to record telemetry data. {exception.StackTrace}");
CosmosDbMeterUtil.RecordHistogramMetric<double>(value: diagnostics.GetClientElapsedTime(),
dimensionsFunc, RequestLatencyHistogram,
t => ((TimeSpan)t).TotalSeconds);
}
}

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -41,25 +41,26 @@
│ [DistributedTraceId]
│ Redacted To Not Change The Baselines From Run To Run
│ )
└── Execute Next Batch(00000000-0000-0000-0000-000000000000) Batch-Component 00:00:00:000 0.00 milliseconds
├── Create Batch Request(00000000-0000-0000-0000-000000000000) Batch-Component 00:00:00:000 0.00 milliseconds
└── Execute Batch Request(00000000-0000-0000-0000-000000000000) Batch-Component 00:00:00:000 0.00 milliseconds
├── Microsoft.Azure.Cosmos.Handlers.RequestInvokerHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ └── Microsoft.Azure.Cosmos.Handlers.DiagnosticsHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ │ (
│ │ [System Info]
│ │ Redacted To Not Change The Baselines From Run To Run
│ │ )
│ └── Microsoft.Azure.Cosmos.Handlers.TelemetryHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ └── Microsoft.Azure.Cosmos.Handlers.RetryHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ └── Microsoft.Azure.Cosmos.Handlers.RouterHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ └── Microsoft.Azure.Cosmos.Handlers.TransportHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ └── Microsoft.Azure.Documents.ServerStoreModel Transport Request(00000000-0000-0000-0000-000000000000) Transport-Component 00:00:00:000 0.00 milliseconds
│ (
│ [Client Side Request Stats]
│ Redacted To Not Change The Baselines From Run To Run
│ )
└── Create Trace(00000000-0000-0000-0000-000000000000) Batch-Component 00:00:00:000 0.00 milliseconds
├── Execute Next Batch(00000000-0000-0000-0000-000000000000) Batch-Component 00:00:00:000 0.00 milliseconds
│ ├── Create Batch Request(00000000-0000-0000-0000-000000000000) Batch-Component 00:00:00:000 0.00 milliseconds
│ └── Execute Batch Request(00000000-0000-0000-0000-000000000000) Batch-Component 00:00:00:000 0.00 milliseconds
│ ├── Microsoft.Azure.Cosmos.Handlers.RequestInvokerHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ │ └── Microsoft.Azure.Cosmos.Handlers.DiagnosticsHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ │ │ (
│ │ │ [System Info]
│ │ │ Redacted To Not Change The Baselines From Run To Run
│ │ │ )
│ │ └── Microsoft.Azure.Cosmos.Handlers.TelemetryHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ │ └── Microsoft.Azure.Cosmos.Handlers.RetryHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ │ └── Microsoft.Azure.Cosmos.Handlers.RouterHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ │ └── Microsoft.Azure.Cosmos.Handlers.TransportHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ │ └── Microsoft.Azure.Documents.ServerStoreModel Transport Request(00000000-0000-0000-0000-000000000000) Transport-Component 00:00:00:000 0.00 milliseconds
│ │ (
│ │ [Client Side Request Stats]
│ │ Redacted To Not Change The Baselines From Run To Run
│ │ )
│ └── Create Trace(00000000-0000-0000-0000-000000000000) Batch-Component 00:00:00:000 0.00 milliseconds
└── Recording Telemetry(00000000-0000-0000-0000-000000000000) Transport-Component 00:00:00:000 0.00 milliseconds
]]></Text>
<Json><![CDATA[{
"Summary": {},
Expand Down Expand Up @@ -136,6 +137,10 @@
]
}
]
},
{
"name": "Recording Telemetry",
"duration in milliseconds": 0
}
]
}]]></Json><OTelActivities>
Expand Down Expand Up @@ -202,25 +207,26 @@
│ [DistributedTraceId]
│ Redacted To Not Change The Baselines From Run To Run
│ )
└── Execute Next Batch(00000000-0000-0000-0000-000000000000) Batch-Component 00:00:00:000 0.00 milliseconds
├── Create Batch Request(00000000-0000-0000-0000-000000000000) Batch-Component 00:00:00:000 0.00 milliseconds
└── Execute Batch Request(00000000-0000-0000-0000-000000000000) Batch-Component 00:00:00:000 0.00 milliseconds
├── Microsoft.Azure.Cosmos.Handlers.RequestInvokerHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ └── Microsoft.Azure.Cosmos.Handlers.DiagnosticsHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ │ (
│ │ [System Info]
│ │ Redacted To Not Change The Baselines From Run To Run
│ │ )
│ └── Microsoft.Azure.Cosmos.Handlers.TelemetryHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ └── Microsoft.Azure.Cosmos.Handlers.RetryHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ └── Microsoft.Azure.Cosmos.Handlers.RouterHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ └── Microsoft.Azure.Cosmos.Handlers.TransportHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ └── Microsoft.Azure.Documents.ServerStoreModel Transport Request(00000000-0000-0000-0000-000000000000) Transport-Component 00:00:00:000 0.00 milliseconds
│ (
│ [Client Side Request Stats]
│ Redacted To Not Change The Baselines From Run To Run
│ )
└── Create Trace(00000000-0000-0000-0000-000000000000) Batch-Component 00:00:00:000 0.00 milliseconds
├── Execute Next Batch(00000000-0000-0000-0000-000000000000) Batch-Component 00:00:00:000 0.00 milliseconds
│ ├── Create Batch Request(00000000-0000-0000-0000-000000000000) Batch-Component 00:00:00:000 0.00 milliseconds
│ └── Execute Batch Request(00000000-0000-0000-0000-000000000000) Batch-Component 00:00:00:000 0.00 milliseconds
│ ├── Microsoft.Azure.Cosmos.Handlers.RequestInvokerHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ │ └── Microsoft.Azure.Cosmos.Handlers.DiagnosticsHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ │ │ (
│ │ │ [System Info]
│ │ │ Redacted To Not Change The Baselines From Run To Run
│ │ │ )
│ │ └── Microsoft.Azure.Cosmos.Handlers.TelemetryHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ │ └── Microsoft.Azure.Cosmos.Handlers.RetryHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ │ └── Microsoft.Azure.Cosmos.Handlers.RouterHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ │ └── Microsoft.Azure.Cosmos.Handlers.TransportHandler(00000000-0000-0000-0000-000000000000) RequestHandler-Component 00:00:00:000 0.00 milliseconds
│ │ └── Microsoft.Azure.Documents.ServerStoreModel Transport Request(00000000-0000-0000-0000-000000000000) Transport-Component 00:00:00:000 0.00 milliseconds
│ │ (
│ │ [Client Side Request Stats]
│ │ Redacted To Not Change The Baselines From Run To Run
│ │ )
│ └── Create Trace(00000000-0000-0000-0000-000000000000) Batch-Component 00:00:00:000 0.00 milliseconds
└── Recording Telemetry(00000000-0000-0000-0000-000000000000) Transport-Component 00:00:00:000 0.00 milliseconds
]]></Text>
<Json><![CDATA[{
"Summary": {},
Expand Down Expand Up @@ -297,6 +303,10 @@
]
}
]
},
{
"name": "Recording Telemetry",
"duration in milliseconds": 0
}
]
}]]></Json><OTelActivities>
Expand Down
Loading