From e0c16e19afec4adc4101bc2fdd5acbb69c8c43cd Mon Sep 17 00:00:00 2001 From: jedarden Date: Tue, 21 Apr 2026 13:03:13 -0400 Subject: [PATCH] feat(bd-f4p): add OTLP/gRPC receiver on :4317 Add full OTLP/gRPC receiver terminating LogsService, TraceService, and MetricsService Export RPCs. Decoded protobuf records are normalized via the shared Normalizer pipeline and emitted as LogEvents on the event bus. - gRPC server via @grpc/grpc-js with protobufjs codec - Protobuf definitions for all three OTLP collector services - enrichRecord() merges scope/resource attributes for normalizer - extractDataPoints() handles gauge, sum, and histogram metrics - Integration tests with real gRPC client/server round-trip Co-Authored-By: Claude Opus 4.7 --- .../collector/logs/v1/logs_service.proto | 79 ++ .../metrics/v1/metrics_service.proto | 79 ++ .../collector/trace/v1/trace_service.proto | 79 ++ .../proto/common/v1/common.proto | 81 ++ protos/opentelemetry/proto/logs/v1/logs.proto | 227 ++++++ .../proto/metrics/v1/metrics.proto | 714 ++++++++++++++++++ .../proto/resource/v1/resource.proto | 37 + .../opentelemetry/proto/trace/v1/trace.proto | 357 +++++++++ src/otlpGrpcReceiver.test.ts | 206 +++++ src/otlpGrpcReceiver.ts | 328 ++++++++ 10 files changed, 2187 insertions(+) create mode 100644 protos/opentelemetry/proto/collector/logs/v1/logs_service.proto create mode 100644 protos/opentelemetry/proto/collector/metrics/v1/metrics_service.proto create mode 100644 protos/opentelemetry/proto/collector/trace/v1/trace_service.proto create mode 100644 protos/opentelemetry/proto/common/v1/common.proto create mode 100644 protos/opentelemetry/proto/logs/v1/logs.proto create mode 100644 protos/opentelemetry/proto/metrics/v1/metrics.proto create mode 100644 protos/opentelemetry/proto/resource/v1/resource.proto create mode 100644 protos/opentelemetry/proto/trace/v1/trace.proto create mode 100644 src/otlpGrpcReceiver.test.ts create mode 100644 src/otlpGrpcReceiver.ts diff --git a/protos/opentelemetry/proto/collector/logs/v1/logs_service.proto b/protos/opentelemetry/proto/collector/logs/v1/logs_service.proto new file mode 100644 index 0000000..8260d8a --- /dev/null +++ b/protos/opentelemetry/proto/collector/logs/v1/logs_service.proto @@ -0,0 +1,79 @@ +// Copyright 2020, OpenTelemetry Authors +// +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +syntax = "proto3"; + +package opentelemetry.proto.collector.logs.v1; + +import "opentelemetry/proto/logs/v1/logs.proto"; + +option csharp_namespace = "OpenTelemetry.Proto.Collector.Logs.V1"; +option java_multiple_files = true; +option java_package = "io.opentelemetry.proto.collector.logs.v1"; +option java_outer_classname = "LogsServiceProto"; +option go_package = "go.opentelemetry.io/proto/otlp/collector/logs/v1"; + +// Service that can be used to push logs between one Application instrumented with +// OpenTelemetry and an collector, or between an collector and a central collector (in this +// case logs are sent/received to/from multiple Applications). +service LogsService { + // For performance reasons, it is recommended to keep this RPC + // alive for the entire life of the application. + rpc Export(ExportLogsServiceRequest) returns (ExportLogsServiceResponse) {} +} + +message ExportLogsServiceRequest { + // An array of ResourceLogs. + // For data coming from a single resource this array will typically contain one + // element. Intermediary nodes (such as OpenTelemetry Collector) that receive + // data from multiple origins typically batch the data before forwarding further and + // in that case this array will contain multiple elements. + repeated opentelemetry.proto.logs.v1.ResourceLogs resource_logs = 1; +} + +message ExportLogsServiceResponse { + // The details of a partially successful export request. + // + // If the request is only partially accepted + // (i.e. when the server accepts only parts of the data and rejects the rest) + // the server MUST initialize the `partial_success` field and MUST + // set the `rejected_` with the number of items it rejected. + // + // Servers MAY also make use of the `partial_success` field to convey + // warnings/suggestions to senders even when the request was fully accepted. + // In such cases, the `rejected_` MUST have a value of `0` and + // the `error_message` MUST be non-empty. + // + // A `partial_success` message with an empty value (rejected_ = 0 and + // `error_message` = "") is equivalent to it not being set/present. Senders + // SHOULD interpret it the same way as in the full success case. + ExportLogsPartialSuccess partial_success = 1; +} + +message ExportLogsPartialSuccess { + // The number of rejected log records. + // + // A `rejected_` field holding a `0` value indicates that the + // request was fully accepted. + int64 rejected_log_records = 1; + + // A developer-facing human-readable message in English. It should be used + // either to explain why the server rejected parts of the data during a partial + // success or to convey warnings/suggestions during a full success. The message + // should offer guidance on how users can address such issues. + // + // error_message is an optional field. An error_message with an empty value + // is equivalent to it not being set. + string error_message = 2; +} diff --git a/protos/opentelemetry/proto/collector/metrics/v1/metrics_service.proto b/protos/opentelemetry/proto/collector/metrics/v1/metrics_service.proto new file mode 100644 index 0000000..dd48f1a --- /dev/null +++ b/protos/opentelemetry/proto/collector/metrics/v1/metrics_service.proto @@ -0,0 +1,79 @@ +// Copyright 2019, OpenTelemetry Authors +// +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +syntax = "proto3"; + +package opentelemetry.proto.collector.metrics.v1; + +import "opentelemetry/proto/metrics/v1/metrics.proto"; + +option csharp_namespace = "OpenTelemetry.Proto.Collector.Metrics.V1"; +option java_multiple_files = true; +option java_package = "io.opentelemetry.proto.collector.metrics.v1"; +option java_outer_classname = "MetricsServiceProto"; +option go_package = "go.opentelemetry.io/proto/otlp/collector/metrics/v1"; + +// Service that can be used to push metrics between one Application +// instrumented with OpenTelemetry and a collector, or between a collector and a +// central collector. +service MetricsService { + // For performance reasons, it is recommended to keep this RPC + // alive for the entire life of the application. + rpc Export(ExportMetricsServiceRequest) returns (ExportMetricsServiceResponse) {} +} + +message ExportMetricsServiceRequest { + // An array of ResourceMetrics. + // For data coming from a single resource this array will typically contain one + // element. Intermediary nodes (such as OpenTelemetry Collector) that receive + // data from multiple origins typically batch the data before forwarding further and + // in that case this array will contain multiple elements. + repeated opentelemetry.proto.metrics.v1.ResourceMetrics resource_metrics = 1; +} + +message ExportMetricsServiceResponse { + // The details of a partially successful export request. + // + // If the request is only partially accepted + // (i.e. when the server accepts only parts of the data and rejects the rest) + // the server MUST initialize the `partial_success` field and MUST + // set the `rejected_` with the number of items it rejected. + // + // Servers MAY also make use of the `partial_success` field to convey + // warnings/suggestions to senders even when the request was fully accepted. + // In such cases, the `rejected_` MUST have a value of `0` and + // the `error_message` MUST be non-empty. + // + // A `partial_success` message with an empty value (rejected_ = 0 and + // `error_message` = "") is equivalent to it not being set/present. Senders + // SHOULD interpret it the same way as in the full success case. + ExportMetricsPartialSuccess partial_success = 1; +} + +message ExportMetricsPartialSuccess { + // The number of rejected data points. + // + // A `rejected_` field holding a `0` value indicates that the + // request was fully accepted. + int64 rejected_data_points = 1; + + // A developer-facing human-readable message in English. It should be used + // either to explain why the server rejected parts of the data during a partial + // success or to convey warnings/suggestions during a full success. The message + // should offer guidance on how users can address such issues. + // + // error_message is an optional field. An error_message with an empty value + // is equivalent to it not being set. + string error_message = 2; +} diff --git a/protos/opentelemetry/proto/collector/trace/v1/trace_service.proto b/protos/opentelemetry/proto/collector/trace/v1/trace_service.proto new file mode 100644 index 0000000..d6fe67f --- /dev/null +++ b/protos/opentelemetry/proto/collector/trace/v1/trace_service.proto @@ -0,0 +1,79 @@ +// Copyright 2019, OpenTelemetry Authors +// +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +syntax = "proto3"; + +package opentelemetry.proto.collector.trace.v1; + +import "opentelemetry/proto/trace/v1/trace.proto"; + +option csharp_namespace = "OpenTelemetry.Proto.Collector.Trace.V1"; +option java_multiple_files = true; +option java_package = "io.opentelemetry.proto.collector.trace.v1"; +option java_outer_classname = "TraceServiceProto"; +option go_package = "go.opentelemetry.io/proto/otlp/collector/trace/v1"; + +// Service that can be used to push spans between one Application instrumented with +// OpenTelemetry and a collector, or between a collector and a central collector (in this +// case spans are sent/received to/from multiple Applications). +service TraceService { + // For performance reasons, it is recommended to keep this RPC + // alive for the entire life of the application. + rpc Export(ExportTraceServiceRequest) returns (ExportTraceServiceResponse) {} +} + +message ExportTraceServiceRequest { + // An array of ResourceSpans. + // For data coming from a single resource this array will typically contain one + // element. Intermediary nodes (such as OpenTelemetry Collector) that receive + // data from multiple origins typically batch the data before forwarding further and + // in that case this array will contain multiple elements. + repeated opentelemetry.proto.trace.v1.ResourceSpans resource_spans = 1; +} + +message ExportTraceServiceResponse { + // The details of a partially successful export request. + // + // If the request is only partially accepted + // (i.e. when the server accepts only parts of the data and rejects the rest) + // the server MUST initialize the `partial_success` field and MUST + // set the `rejected_` with the number of items it rejected. + // + // Servers MAY also make use of the `partial_success` field to convey + // warnings/suggestions to senders even when the request was fully accepted. + // In such cases, the `rejected_` MUST have a value of `0` and + // the `error_message` MUST be non-empty. + // + // A `partial_success` message with an empty value (rejected_ = 0 and + // `error_message` = "") is equivalent to it not being set/present. Senders + // SHOULD interpret it the same way as in the full success case. + ExportTracePartialSuccess partial_success = 1; +} + +message ExportTracePartialSuccess { + // The number of rejected spans. + // + // A `rejected_` field holding a `0` value indicates that the + // request was fully accepted. + int64 rejected_spans = 1; + + // A developer-facing human-readable message in English. It should be used + // either to explain why the server rejected parts of the data during a partial + // success or to convey warnings/suggestions during a full success. The message + // should offer guidance on how users can address such issues. + // + // error_message is an optional field. An error_message with an empty value + // is equivalent to it not being set. + string error_message = 2; +} diff --git a/protos/opentelemetry/proto/common/v1/common.proto b/protos/opentelemetry/proto/common/v1/common.proto new file mode 100644 index 0000000..ff8a21a --- /dev/null +++ b/protos/opentelemetry/proto/common/v1/common.proto @@ -0,0 +1,81 @@ +// Copyright 2019, OpenTelemetry Authors +// +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +syntax = "proto3"; + +package opentelemetry.proto.common.v1; + +option csharp_namespace = "OpenTelemetry.Proto.Common.V1"; +option java_multiple_files = true; +option java_package = "io.opentelemetry.proto.common.v1"; +option java_outer_classname = "CommonProto"; +option go_package = "go.opentelemetry.io/proto/otlp/common/v1"; + +// AnyValue is used to represent any type of attribute value. AnyValue may contain a +// primitive value such as a string or integer or it may contain an arbitrary nested +// object containing arrays, key-value lists and primitives. +message AnyValue { + // The value is one of the listed fields. It is valid for all values to be unspecified + // in which case this AnyValue is considered to be "empty". + oneof value { + string string_value = 1; + bool bool_value = 2; + int64 int_value = 3; + double double_value = 4; + ArrayValue array_value = 5; + KeyValueList kvlist_value = 6; + bytes bytes_value = 7; + } +} + +// ArrayValue is a list of AnyValue messages. We need ArrayValue as a message +// since oneof in AnyValue does not allow repeated fields. +message ArrayValue { + // Array of values. The array may be empty (contain 0 elements). + repeated AnyValue values = 1; +} + +// KeyValueList is a list of KeyValue messages. We need KeyValueList as a message +// since `oneof` in AnyValue does not allow repeated fields. Everywhere else where we need +// a list of KeyValue messages (e.g. in Span) we use `repeated KeyValue` directly to +// avoid unnecessary extra wrapping (which slows down the protocol). The 2 approaches +// are semantically equivalent. +message KeyValueList { + // A collection of key/value pairs of key-value pairs. The list may be empty (may + // contain 0 elements). + // The keys MUST be unique (it is not allowed to have more than one + // value with the same key). + repeated KeyValue values = 1; +} + +// KeyValue is a key-value pair that is used to store Span attributes, Link +// attributes, etc. +message KeyValue { + string key = 1; + AnyValue value = 2; +} + +// InstrumentationScope is a message representing the instrumentation scope information +// such as the fully qualified name and version. +message InstrumentationScope { + // An empty instrumentation scope name means the name is unknown. + string name = 1; + string version = 2; + + // Additional attributes that describe the scope. [Optional]. + // Attribute keys MUST be unique (it is not allowed to have more than one + // attribute with the same key). + repeated KeyValue attributes = 3; + uint32 dropped_attributes_count = 4; +} diff --git a/protos/opentelemetry/proto/logs/v1/logs.proto b/protos/opentelemetry/proto/logs/v1/logs.proto new file mode 100644 index 0000000..261d229 --- /dev/null +++ b/protos/opentelemetry/proto/logs/v1/logs.proto @@ -0,0 +1,227 @@ +// Copyright 2020, OpenTelemetry Authors +// +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +syntax = "proto3"; + +package opentelemetry.proto.logs.v1; + +import "opentelemetry/proto/common/v1/common.proto"; +import "opentelemetry/proto/resource/v1/resource.proto"; + +option csharp_namespace = "OpenTelemetry.Proto.Logs.V1"; +option java_multiple_files = true; +option java_package = "io.opentelemetry.proto.logs.v1"; +option java_outer_classname = "LogsProto"; +option go_package = "go.opentelemetry.io/proto/otlp/logs/v1"; + +// LogsData represents the logs data that can be stored in a persistent storage, +// OR can be embedded by other protocols that transfer OTLP logs data but do not +// implement the OTLP protocol. +// +// The main difference between this message and collector protocol is that +// in this message there will not be any "control" or "metadata" specific to +// OTLP protocol. +// +// When new fields are added into this message, the OTLP request MUST be updated +// as well. +message LogsData { + // An array of ResourceLogs. + // For data coming from a single resource this array will typically contain + // one element. Intermediary nodes that receive data from multiple origins + // typically batch the data before forwarding further and in that case this + // array will contain multiple elements. + repeated ResourceLogs resource_logs = 1; +} + +// A collection of ScopeLogs from a Resource. +message ResourceLogs { + reserved 1000; + + // The resource for the logs in this message. + // If this field is not set then resource info is unknown. + opentelemetry.proto.resource.v1.Resource resource = 1; + + // A list of ScopeLogs that originate from a resource. + repeated ScopeLogs scope_logs = 2; + + // The Schema URL, if known. This is the identifier of the Schema that the resource data + // is recorded in. Notably, the last part of the URL path is the version number of the + // schema: http[s]://server[:port]/path/. To learn more about Schema URL see + // https://opentelemetry.io/docs/specs/otel/schemas/#schema-url + // This schema_url applies to the data in the "resource" field. It does not apply + // to the data in the "scope_logs" field which have their own schema_url field. + string schema_url = 3; +} + +// A collection of Logs produced by a Scope. +message ScopeLogs { + // The instrumentation scope information for the logs in this message. + // Semantically when InstrumentationScope isn't set, it is equivalent with + // an empty instrumentation scope name (unknown). + opentelemetry.proto.common.v1.InstrumentationScope scope = 1; + + // A list of log records. + repeated LogRecord log_records = 2; + + // The Schema URL, if known. This is the identifier of the Schema that the log data + // is recorded in. Notably, the last part of the URL path is the version number of the + // schema: http[s]://server[:port]/path/. To learn more about Schema URL see + // https://opentelemetry.io/docs/specs/otel/schemas/#schema-url + // This schema_url applies to all logs in the "logs" field. + string schema_url = 3; +} + +// Possible values for LogRecord.SeverityNumber. +enum SeverityNumber { + // UNSPECIFIED is the default SeverityNumber, it MUST NOT be used. + SEVERITY_NUMBER_UNSPECIFIED = 0; + SEVERITY_NUMBER_TRACE = 1; + SEVERITY_NUMBER_TRACE2 = 2; + SEVERITY_NUMBER_TRACE3 = 3; + SEVERITY_NUMBER_TRACE4 = 4; + SEVERITY_NUMBER_DEBUG = 5; + SEVERITY_NUMBER_DEBUG2 = 6; + SEVERITY_NUMBER_DEBUG3 = 7; + SEVERITY_NUMBER_DEBUG4 = 8; + SEVERITY_NUMBER_INFO = 9; + SEVERITY_NUMBER_INFO2 = 10; + SEVERITY_NUMBER_INFO3 = 11; + SEVERITY_NUMBER_INFO4 = 12; + SEVERITY_NUMBER_WARN = 13; + SEVERITY_NUMBER_WARN2 = 14; + SEVERITY_NUMBER_WARN3 = 15; + SEVERITY_NUMBER_WARN4 = 16; + SEVERITY_NUMBER_ERROR = 17; + SEVERITY_NUMBER_ERROR2 = 18; + SEVERITY_NUMBER_ERROR3 = 19; + SEVERITY_NUMBER_ERROR4 = 20; + SEVERITY_NUMBER_FATAL = 21; + SEVERITY_NUMBER_FATAL2 = 22; + SEVERITY_NUMBER_FATAL3 = 23; + SEVERITY_NUMBER_FATAL4 = 24; +} + +// LogRecordFlags represents constants used to interpret the +// LogRecord.flags field, which is protobuf 'fixed32' type and is to +// be used as bit-fields. Each non-zero value defined in this enum is +// a bit-mask. To extract the bit-field, for example, use an +// expression like: +// +// (logRecord.flags & LOG_RECORD_FLAGS_TRACE_FLAGS_MASK) +// +enum LogRecordFlags { + // The zero value for the enum. Should not be used for comparisons. + // Instead use bitwise "and" with the appropriate mask as shown above. + LOG_RECORD_FLAGS_DO_NOT_USE = 0; + + // Bits 0-7 are used for trace flags. + LOG_RECORD_FLAGS_TRACE_FLAGS_MASK = 0x000000FF; + + // Bits 8-31 are reserved for future use. +} + +// A log record according to OpenTelemetry Log Data Model: +// https://github.com/open-telemetry/oteps/blob/main/text/logs/0097-log-data-model.md +message LogRecord { + reserved 4; + + // time_unix_nano is the time when the event occurred. + // Value is UNIX Epoch time in nanoseconds since 00:00:00 UTC on 1 January 1970. + // Value of 0 indicates unknown or missing timestamp. + fixed64 time_unix_nano = 1; + + // Time when the event was observed by the collection system. + // For events that originate in OpenTelemetry (e.g. using OpenTelemetry Logging SDK) + // this timestamp is typically set at the generation time and is equal to Timestamp. + // For events originating externally and collected by OpenTelemetry (e.g. using + // Collector) this is the time when OpenTelemetry's code observed the event measured + // by the clock of the OpenTelemetry code. This field MUST be set once the event is + // observed by OpenTelemetry. + // + // For converting OpenTelemetry log data to formats that support only one timestamp or + // when receiving OpenTelemetry log data by recipients that support only one timestamp + // internally the following logic is recommended: + // - Use time_unix_nano if it is present, otherwise use observed_time_unix_nano. + // + // Value is UNIX Epoch time in nanoseconds since 00:00:00 UTC on 1 January 1970. + // Value of 0 indicates unknown or missing timestamp. + fixed64 observed_time_unix_nano = 11; + + // Numerical value of the severity, normalized to values described in Log Data Model. + // [Optional]. + SeverityNumber severity_number = 2; + + // The severity text (also known as log level). The original string representation as + // it is known at the source. [Optional]. + string severity_text = 3; + + // A value containing the body of the log record. Can be for example a human-readable + // string message (including multi-line) describing the event in a free form or it can + // be a structured data composed of arrays and maps of other values. [Optional]. + opentelemetry.proto.common.v1.AnyValue body = 5; + + // Additional attributes that describe the specific event occurrence. [Optional]. + // Attribute keys MUST be unique (it is not allowed to have more than one + // attribute with the same key). + repeated opentelemetry.proto.common.v1.KeyValue attributes = 6; + uint32 dropped_attributes_count = 7; + + // Flags, a bit field. 8 least significant bits are the trace flags as + // defined in W3C Trace Context specification. 24 most significant bits are reserved + // and must be set to 0. Readers must not assume that 24 most significant bits + // will be zero and must correctly mask the bits when reading 8-bit trace flag (use + // flags & LOG_RECORD_FLAGS_TRACE_FLAGS_MASK). [Optional]. + fixed32 flags = 8; + + // A unique identifier for a trace. All logs from the same trace share + // the same `trace_id`. The ID is a 16-byte array. An ID with all zeroes OR + // of length other than 16 bytes is considered invalid (empty string in OTLP/JSON + // is zero-length and thus is also invalid). + // + // This field is optional. + // + // The receivers SHOULD assume that the log record is not associated with a + // trace if any of the following is true: + // - the field is not present, + // - the field contains an invalid value. + bytes trace_id = 9; + + // A unique identifier for a span within a trace, assigned when the span + // is created. The ID is an 8-byte array. An ID with all zeroes OR of length + // other than 8 bytes is considered invalid (empty string in OTLP/JSON + // is zero-length and thus is also invalid). + // + // This field is optional. If the sender specifies a valid span_id then it SHOULD also + // specify a valid trace_id. + // + // The receivers SHOULD assume that the log record is not associated with a + // span if any of the following is true: + // - the field is not present, + // - the field contains an invalid value. + bytes span_id = 10; + + // A unique identifier of event category/type. + // All events with the same event_name are expected to conform to the same + // schema for both their attributes and their body. + // + // Recommended to be fully qualified and short (no longer than 256 characters). + // + // Presence of event_name on the log record identifies this record + // as an event. + // + // [Optional]. + // + // Status: [Development] + string event_name = 12; +} diff --git a/protos/opentelemetry/proto/metrics/v1/metrics.proto b/protos/opentelemetry/proto/metrics/v1/metrics.proto new file mode 100644 index 0000000..00c5112 --- /dev/null +++ b/protos/opentelemetry/proto/metrics/v1/metrics.proto @@ -0,0 +1,714 @@ +// Copyright 2019, OpenTelemetry Authors +// +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +syntax = "proto3"; + +package opentelemetry.proto.metrics.v1; + +import "opentelemetry/proto/common/v1/common.proto"; +import "opentelemetry/proto/resource/v1/resource.proto"; + +option csharp_namespace = "OpenTelemetry.Proto.Metrics.V1"; +option java_multiple_files = true; +option java_package = "io.opentelemetry.proto.metrics.v1"; +option java_outer_classname = "MetricsProto"; +option go_package = "go.opentelemetry.io/proto/otlp/metrics/v1"; + +// MetricsData represents the metrics data that can be stored in a persistent +// storage, OR can be embedded by other protocols that transfer OTLP metrics +// data but do not implement the OTLP protocol. +// +// MetricsData +// └─── ResourceMetrics +// ├── Resource +// ├── SchemaURL +// └── ScopeMetrics +// ├── Scope +// ├── SchemaURL +// └── Metric +// ├── Name +// ├── Description +// ├── Unit +// └── data +// ├── Gauge +// ├── Sum +// ├── Histogram +// ├── ExponentialHistogram +// └── Summary +// +// The main difference between this message and collector protocol is that +// in this message there will not be any "control" or "metadata" specific to +// OTLP protocol. +// +// When new fields are added into this message, the OTLP request MUST be updated +// as well. +message MetricsData { + // An array of ResourceMetrics. + // For data coming from a single resource this array will typically contain + // one element. Intermediary nodes that receive data from multiple origins + // typically batch the data before forwarding further and in that case this + // array will contain multiple elements. + repeated ResourceMetrics resource_metrics = 1; +} + +// A collection of ScopeMetrics from a Resource. +message ResourceMetrics { + reserved 1000; + + // The resource for the metrics in this message. + // If this field is not set then no resource info is known. + opentelemetry.proto.resource.v1.Resource resource = 1; + + // A list of metrics that originate from a resource. + repeated ScopeMetrics scope_metrics = 2; + + // The Schema URL, if known. This is the identifier of the Schema that the resource data + // is recorded in. Notably, the last part of the URL path is the version number of the + // schema: http[s]://server[:port]/path/. To learn more about Schema URL see + // https://opentelemetry.io/docs/specs/otel/schemas/#schema-url + // This schema_url applies to the data in the "resource" field. It does not apply + // to the data in the "scope_metrics" field which have their own schema_url field. + string schema_url = 3; +} + +// A collection of Metrics produced by an Scope. +message ScopeMetrics { + // The instrumentation scope information for the metrics in this message. + // Semantically when InstrumentationScope isn't set, it is equivalent with + // an empty instrumentation scope name (unknown). + opentelemetry.proto.common.v1.InstrumentationScope scope = 1; + + // A list of metrics that originate from an instrumentation library. + repeated Metric metrics = 2; + + // The Schema URL, if known. This is the identifier of the Schema that the metric data + // is recorded in. Notably, the last part of the URL path is the version number of the + // schema: http[s]://server[:port]/path/. To learn more about Schema URL see + // https://opentelemetry.io/docs/specs/otel/schemas/#schema-url + // This schema_url applies to all metrics in the "metrics" field. + string schema_url = 3; +} + +// Defines a Metric which has one or more timeseries. The following is a +// brief summary of the Metric data model. For more details, see: +// +// https://github.com/open-telemetry/opentelemetry-specification/blob/main/specification/metrics/data-model.md +// +// The data model and relation between entities is shown in the +// diagram below. Here, "DataPoint" is the term used to refer to any +// one of the specific data point value types, and "points" is the term used +// to refer to any one of the lists of points contained in the Metric. +// +// - Metric is composed of a metadata and data. +// - Metadata part contains a name, description, unit. +// - Data is one of the possible types (Sum, Gauge, Histogram, Summary). +// - DataPoint contains timestamps, attributes, and one of the possible value type +// fields. +// +// Metric +// +------------+ +// |name | +// |description | +// |unit | +------------------------------------+ +// |data |---> |Gauge, Sum, Histogram, Summary, ... | +// +------------+ +------------------------------------+ +// +// Data [One of Gauge, Sum, Histogram, Summary, ...] +// +-----------+ +// |... | // Metadata about the Data. +// |points |--+ +// +-----------+ | +// | +---------------------------+ +// | |DataPoint 1 | +// v |+------+------+ +------+ | +// +-----+ ||label |label |...|label | | +// | 1 |-->||value1|value2|...|valueN| | +// +-----+ |+------+------+ +------+ | +// | . | |+-----+ | +// | . | ||value| | +// | . | |+-----+ | +// | . | +---------------------------+ +// | . | . +// | . | . +// | . | . +// | . | +---------------------------+ +// | . | |DataPoint M | +// +-----+ |+------+------+ +------+ | +// | M |-->||label |label |...|label | | +// +-----+ ||value1|value2|...|valueN| | +// |+------+------+ +------+ | +// |+-----+ | +// ||value| | +// |+-----+ | +// +---------------------------+ +// +// Each distinct type of DataPoint represents the output of a specific +// aggregation function, the result of applying the DataPoint's +// associated function of to one or more measurements. +// +// All DataPoint types have three common fields: +// - Attributes includes key-value pairs associated with the data point +// - TimeUnixNano is required, set to the end time of the aggregation +// - StartTimeUnixNano is optional, but strongly encouraged for DataPoints +// having an AggregationTemporality field, as discussed below. +// +// Both TimeUnixNano and StartTimeUnixNano values are expressed as +// UNIX Epoch time in nanoseconds since 00:00:00 UTC on 1 January 1970. +// +// # TimeUnixNano +// +// This field is required, having consistent interpretation across +// DataPoint types. TimeUnixNano is the moment corresponding to when +// the data point's aggregate value was captured. +// +// Data points with the 0 value for TimeUnixNano SHOULD be rejected +// by consumers. +// +// # StartTimeUnixNano +// +// StartTimeUnixNano in general allows detecting when a sequence of +// observations is unbroken. This field indicates to consumers the +// start time for points with cumulative and delta +// AggregationTemporality, and it should be included whenever possible +// to support correct rate calculation. Although it may be omitted +// when the start time is truly unknown, setting StartTimeUnixNano is +// strongly encouraged. +message Metric { + reserved 4, 6, 8; + + // name of the metric. + string name = 1; + + // description of the metric, which can be used in documentation. + string description = 2; + + // unit in which the metric value is reported. Follows the format + // described by http://unitsofmeasure.org/ucum.html. + string unit = 3; + + // Data determines the aggregation type (if any) of the metric, what is the + // reported value type for the data points, as well as the relatationship to + // the time interval over which they are reported. + oneof data { + Gauge gauge = 5; + Sum sum = 7; + Histogram histogram = 9; + ExponentialHistogram exponential_histogram = 10; + Summary summary = 11; + } + + // Additional metadata attributes that describe the metric. [Optional]. + // Attributes are non-identifying. + // Consumers SHOULD NOT need to be aware of these attributes. + // These attributes MAY be used to encode information allowing + // for lossless roundtrip translation to / from another data model. + // Attribute keys MUST be unique (it is not allowed to have more than one + // attribute with the same key). + repeated opentelemetry.proto.common.v1.KeyValue metadata = 12; +} + +// Gauge represents the type of a scalar metric that always exports the +// "current value" for every data point. It should be used for an "unknown" +// aggregation. +// +// A Gauge does not support different aggregation temporalities. Given the +// aggregation is unknown, points cannot be combined using the same +// aggregation, regardless of aggregation temporalities. Therefore, +// AggregationTemporality is not included. Consequently, this also means +// "StartTimeUnixNano" is ignored for all data points. +message Gauge { + repeated NumberDataPoint data_points = 1; +} + +// Sum represents the type of a scalar metric that is calculated as a sum of all +// reported measurements over a time interval. +message Sum { + repeated NumberDataPoint data_points = 1; + + // aggregation_temporality describes if the aggregator reports delta changes + // since last report time, or cumulative changes since a fixed start time. + AggregationTemporality aggregation_temporality = 2; + + // If "true" means that the sum is monotonic. + bool is_monotonic = 3; +} + +// Histogram represents the type of a metric that is calculated by aggregating +// as a Histogram of all reported measurements over a time interval. +message Histogram { + repeated HistogramDataPoint data_points = 1; + + // aggregation_temporality describes if the aggregator reports delta changes + // since last report time, or cumulative changes since a fixed start time. + AggregationTemporality aggregation_temporality = 2; +} + +// ExponentialHistogram represents the type of a metric that is calculated by aggregating +// as a ExponentialHistogram of all reported double measurements over a time interval. +message ExponentialHistogram { + repeated ExponentialHistogramDataPoint data_points = 1; + + // aggregation_temporality describes if the aggregator reports delta changes + // since last report time, or cumulative changes since a fixed start time. + AggregationTemporality aggregation_temporality = 2; +} + +// Summary metric data are used to convey quantile summaries, +// a Prometheus (see: https://prometheus.io/docs/concepts/metric_types/#summary) +// and OpenMetrics (see: https://github.com/OpenObservability/OpenMetrics/blob/4dbf6075567ab43296eed941037c12951faafb92/protos/prometheus.proto#L45) +// data type. These data points cannot always be merged in a meaningful way. +// While they can be useful in some applications, histogram data points are +// recommended for new applications. +// Summary metrics do not have an aggregation temporality field. This is +// because the count and sum fields of a SummaryDataPoint are assumed to be +// cumulative values. +message Summary { + repeated SummaryDataPoint data_points = 1; +} + +// AggregationTemporality defines how a metric aggregator reports aggregated +// values. It describes how those values relate to the time interval over +// which they are aggregated. +enum AggregationTemporality { + // UNSPECIFIED is the default AggregationTemporality, it MUST not be used. + AGGREGATION_TEMPORALITY_UNSPECIFIED = 0; + + // DELTA is an AggregationTemporality for a metric aggregator which reports + // changes since last report time. Successive metrics contain aggregation of + // values from continuous and non-overlapping intervals. + // + // The values for a DELTA metric are based only on the time interval + // associated with one measurement cycle. There is no dependency on + // previous measurements like is the case for CUMULATIVE metrics. + // + // For example, consider a system measuring the number of requests that + // it receives and reports the sum of these requests every second as a + // DELTA metric: + // + // 1. The system starts receiving at time=t_0. + // 2. A request is received, the system measures 1 request. + // 3. A request is received, the system measures 1 request. + // 4. A request is received, the system measures 1 request. + // 5. The 1 second collection cycle ends. A metric is exported for the + // number of requests received over the interval of time t_0 to + // t_0+1 with a value of 3. + // 6. A request is received, the system measures 1 request. + // 7. A request is received, the system measures 1 request. + // 8. The 1 second collection cycle ends. A metric is exported for the + // number of requests received over the interval of time t_0+1 to + // t_0+2 with a value of 2. + AGGREGATION_TEMPORALITY_DELTA = 1; + + // CUMULATIVE is an AggregationTemporality for a metric aggregator which + // reports changes since a fixed start time. This means that current values + // of a CUMULATIVE metric depend on all previous measurements since the + // start time. Because of this, the sender is required to retain this state + // in some form. If this state is lost or invalidated, the CUMULATIVE metric + // values MUST be reset and a new fixed start time following the last + // reported measurement time sent MUST be used. + // + // For example, consider a system measuring the number of requests that + // it receives and reports the sum of these requests every second as a + // CUMULATIVE metric: + // + // 1. The system starts receiving at time=t_0. + // 2. A request is received, the system measures 1 request. + // 3. A request is received, the system measures 1 request. + // 4. A request is received, the system measures 1 request. + // 5. The 1 second collection cycle ends. A metric is exported for the + // number of requests received over the interval of time t_0 to + // t_0+1 with a value of 3. + // 6. A request is received, the system measures 1 request. + // 7. A request is received, the system measures 1 request. + // 8. The 1 second collection cycle ends. A metric is exported for the + // number of requests received over the interval of time t_0 to + // t_0+2 with a value of 5. + // 9. The system experiences a fault and loses state. + // 10. The system recovers and resumes receiving at time=t_1. + // 11. A request is received, the system measures 1 request. + // 12. The 1 second collection cycle ends. A metric is exported for the + // number of requests received over the interval of time t_1 to + // t_0+1 with a value of 1. + // + // Note: Even though, when reporting changes since last report time, using + // CUMULATIVE is valid, it is not recommended. This may cause problems for + // systems that do not use start_time to determine when the aggregation + // value was reset (e.g. Prometheus). + AGGREGATION_TEMPORALITY_CUMULATIVE = 2; +} + +// DataPointFlags is defined as a protobuf 'uint32' type and is to be used as a +// bit-field representing 32 distinct boolean flags. Each flag defined in this +// enum is a bit-mask. To test the presence of a single flag in the flags of +// a data point, for example, use an expression like: +// +// (point.flags & DATA_POINT_FLAGS_NO_RECORDED_VALUE_MASK) == DATA_POINT_FLAGS_NO_RECORDED_VALUE_MASK +// +enum DataPointFlags { + // The zero value for the enum. Should not be used for comparisons. + // Instead use bitwise "and" with the appropriate mask as shown above. + DATA_POINT_FLAGS_DO_NOT_USE = 0; + + // This DataPoint is valid but has no recorded value. This value + // SHOULD be used to reflect explicitly missing data in a series, as + // for an equivalent to the Prometheus "staleness marker". + DATA_POINT_FLAGS_NO_RECORDED_VALUE_MASK = 1; + + // Bits 2-31 are reserved for future use. +} + +// NumberDataPoint is a single data point in a timeseries that describes the +// time-varying scalar value of a metric. +message NumberDataPoint { + reserved 1; + + // The set of key/value pairs that uniquely identify the timeseries from + // where this point belongs. The list may be empty (may contain 0 elements). + // Attribute keys MUST be unique (it is not allowed to have more than one + // attribute with the same key). + repeated opentelemetry.proto.common.v1.KeyValue attributes = 7; + + // StartTimeUnixNano is optional but strongly encouraged, see the + // the detailed comments above Metric. + // + // Value is UNIX Epoch time in nanoseconds since 00:00:00 UTC on 1 January + // 1970. + fixed64 start_time_unix_nano = 2; + + // TimeUnixNano is required, see the detailed comments above Metric. + // + // Value is UNIX Epoch time in nanoseconds since 00:00:00 UTC on 1 January + // 1970. + fixed64 time_unix_nano = 3; + + // The value itself. A point is considered invalid when one of the recognized + // value fields is not present inside this oneof. + oneof value { + double as_double = 4; + sfixed64 as_int = 6; + } + + // (Optional) List of exemplars collected from + // measurements that were used to form the data point + repeated Exemplar exemplars = 5; + + // Flags that apply to this specific data point. See DataPointFlags + // for the available flags and their meaning. + uint32 flags = 8; +} + +// HistogramDataPoint is a single data point in a timeseries that describes the +// time-varying values of a Histogram. A Histogram contains summary statistics +// for a population of values, it may optionally contain the distribution of +// those values across a set of buckets. +// +// If the histogram contains the distribution of values, then both +// "explicit_bounds" and "bucket counts" fields must be defined. +// If the histogram does not contain the distribution of values, then both +// "explicit_bounds" and "bucket_counts" must be omitted and only "count" and +// "sum" are known. +message HistogramDataPoint { + reserved 1; + + // The set of key/value pairs that uniquely identify the timeseries from + // where this point belongs. The list may be empty (may contain 0 elements). + // Attribute keys MUST be unique (it is not allowed to have more than one + // attribute with the same key). + repeated opentelemetry.proto.common.v1.KeyValue attributes = 9; + + // StartTimeUnixNano is optional but strongly encouraged, see the + // the detailed comments above Metric. + // + // Value is UNIX Epoch time in nanoseconds since 00:00:00 UTC on 1 January + // 1970. + fixed64 start_time_unix_nano = 2; + + // TimeUnixNano is required, see the detailed comments above Metric. + // + // Value is UNIX Epoch time in nanoseconds since 00:00:00 UTC on 1 January + // 1970. + fixed64 time_unix_nano = 3; + + // count is the number of values in the population. Must be non-negative. This + // value must be equal to the sum of the "count" fields in buckets if a + // histogram is provided. + fixed64 count = 4; + + // sum of the values in the population. If count is zero then this field + // must be zero. + // + // Note: Sum should only be filled out when measuring non-negative discrete + // events, and is assumed to be monotonic over the values of these events. + // Negative events *can* be recorded, but sum should not be filled out when + // doing so. This is specifically to enforce compatibility w/ OpenMetrics, + // see: https://github.com/prometheus/OpenMetrics/blob/v1.0.0/specification/OpenMetrics.md#histogram + optional double sum = 5; + + // bucket_counts is an optional field contains the count values of histogram + // for each bucket. + // + // The sum of the bucket_counts must equal the value in the count field. + // + // The number of elements in bucket_counts array must be by one greater than + // the number of elements in explicit_bounds array. + repeated fixed64 bucket_counts = 6; + + // explicit_bounds specifies buckets with explicitly defined bounds for values. + // + // The boundaries for bucket at index i are: + // + // (-infinity, explicit_bounds[i]] for i == 0 + // (explicit_bounds[i-1], explicit_bounds[i]] for 0 < i < size(explicit_bounds) + // (explicit_bounds[i-1], +infinity) for i == size(explicit_bounds) + // + // The values in the explicit_bounds array must be strictly increasing. + // + // Histogram buckets are inclusive of their upper boundary, except the last + // bucket where the boundary is at infinity. This format is intentionally + // compatible with the OpenMetrics histogram definition. + repeated double explicit_bounds = 7; + + // (Optional) List of exemplars collected from + // measurements that were used to form the data point + repeated Exemplar exemplars = 8; + + // Flags that apply to this specific data point. See DataPointFlags + // for the available flags and their meaning. + uint32 flags = 10; + + // min is the minimum value over (start_time, end_time]. + optional double min = 11; + + // max is the maximum value over (start_time, end_time]. + optional double max = 12; +} + +// ExponentialHistogramDataPoint is a single data point in a timeseries that describes the +// time-varying values of a ExponentialHistogram of double values. A ExponentialHistogram contains +// summary statistics for a population of values, it may optionally contain the +// distribution of those values across a set of buckets. +// +message ExponentialHistogramDataPoint { + // The set of key/value pairs that uniquely identify the timeseries from + // where this point belongs. The list may be empty (may contain 0 elements). + // Attribute keys MUST be unique (it is not allowed to have more than one + // attribute with the same key). + repeated opentelemetry.proto.common.v1.KeyValue attributes = 1; + + // StartTimeUnixNano is optional but strongly encouraged, see the + // the detailed comments above Metric. + // + // Value is UNIX Epoch time in nanoseconds since 00:00:00 UTC on 1 January + // 1970. + fixed64 start_time_unix_nano = 2; + + // TimeUnixNano is required, see the detailed comments above Metric. + // + // Value is UNIX Epoch time in nanoseconds since 00:00:00 UTC on 1 January + // 1970. + fixed64 time_unix_nano = 3; + + // count is the number of values in the population. Must be + // non-negative. This value must be equal to the sum of the "bucket_counts" + // values in the positive and negative Buckets plus the "zero_count" field. + fixed64 count = 4; + + // sum of the values in the population. If count is zero then this field + // must be zero. + // + // Note: Sum should only be filled out when measuring non-negative discrete + // events, and is assumed to be monotonic over the values of these events. + // Negative events *can* be recorded, but sum should not be filled out when + // doing so. This is specifically to enforce compatibility w/ OpenMetrics, + // see: https://github.com/prometheus/OpenMetrics/blob/v1.0.0/specification/OpenMetrics.md#histogram + optional double sum = 5; + + // scale describes the resolution of the histogram. Boundaries are + // located at powers of the base, where: + // + // base = (2^(2^-scale)) + // + // The histogram bucket identified by `index`, a signed integer, + // contains values that are greater than (base^index) and + // less than or equal to (base^(index+1)). + // + // The positive and negative ranges of the histogram are expressed + // separately. Negative values are mapped by their absolute value + // into the negative range using the same scale as the positive range. + // + // scale is not restricted by the protocol, as the permissible + // values depend on the range of the data. + sint32 scale = 6; + + // zero_count is the count of values that are either exactly zero or + // within the region considered zero by the instrumentation at the + // tolerated degree of precision. This bucket stores values that + // cannot be expressed using the standard exponential formula as + // well as values that have been rounded to zero. + // + // Implementations MAY consider the zero bucket to have probability + // mass equal to (zero_count / count). + fixed64 zero_count = 7; + + // positive carries the positive range of exponential bucket counts. + Buckets positive = 8; + + // negative carries the negative range of exponential bucket counts. + Buckets negative = 9; + + // Buckets are a set of bucket counts, encoded in a contiguous array + // of counts. + message Buckets { + // Offset is the bucket index of the first entry in the bucket_counts array. + // + // Note: This uses a varint encoding as a simple form of compression. + sint32 offset = 1; + + // bucket_counts is an array of count values, where bucket_counts[i] carries + // the count of the bucket at index (offset+i). bucket_counts[i] is the count + // of values greater than base^(offset+i) and less than or equal to + // base^(offset+i+1). + // + // Note: By contrast, the explicit HistogramDataPoint uses + // fixed64. This field is expected to have many buckets, + // especially zeros, so uint64 has been selected to ensure + // varint encoding. + repeated uint64 bucket_counts = 2; + } + + // Flags that apply to this specific data point. See DataPointFlags + // for the available flags and their meaning. + uint32 flags = 10; + + // (Optional) List of exemplars collected from + // measurements that were used to form the data point + repeated Exemplar exemplars = 11; + + // min is the minimum value over (start_time, end_time]. + optional double min = 12; + + // max is the maximum value over (start_time, end_time]. + optional double max = 13; + + // ZeroThreshold may be optionally set to convey the width of the zero + // region. Where the zero region is defined as the closed interval + // [-ZeroThreshold, ZeroThreshold]. + // When ZeroThreshold is 0, zero count bucket stores values that cannot be + // expressed using the standard exponential formula as well as values that + // have been rounded to zero. + double zero_threshold = 14; +} + +// SummaryDataPoint is a single data point in a timeseries that describes the +// time-varying values of a Summary metric. The count and sum fields represent +// cumulative values. +message SummaryDataPoint { + reserved 1; + + // The set of key/value pairs that uniquely identify the timeseries from + // where this point belongs. The list may be empty (may contain 0 elements). + // Attribute keys MUST be unique (it is not allowed to have more than one + // attribute with the same key). + repeated opentelemetry.proto.common.v1.KeyValue attributes = 7; + + // StartTimeUnixNano is optional but strongly encouraged, see the + // the detailed comments above Metric. + // + // Value is UNIX Epoch time in nanoseconds since 00:00:00 UTC on 1 January + // 1970. + fixed64 start_time_unix_nano = 2; + + // TimeUnixNano is required, see the detailed comments above Metric. + // + // Value is UNIX Epoch time in nanoseconds since 00:00:00 UTC on 1 January + // 1970. + fixed64 time_unix_nano = 3; + + // count is the number of values in the population. Must be non-negative. + fixed64 count = 4; + + // sum of the values in the population. If count is zero then this field + // must be zero. + // + // Note: Sum should only be filled out when measuring non-negative discrete + // events, and is assumed to be monotonic over the values of these events. + // Negative events *can* be recorded, but sum should not be filled out when + // doing so. This is specifically to enforce compatibility w/ OpenMetrics, + // see: https://github.com/prometheus/OpenMetrics/blob/v1.0.0/specification/OpenMetrics.md#summary + double sum = 5; + + // Represents the value at a given quantile of a distribution. + // + // To record Min and Max values following conventions are used: + // - The 1.0 quantile is equivalent to the maximum value observed. + // - The 0.0 quantile is equivalent to the minimum value observed. + // + // See the following issue for more context: + // https://github.com/open-telemetry/opentelemetry-proto/issues/125 + message ValueAtQuantile { + // The quantile of a distribution. Must be in the interval + // [0.0, 1.0]. + double quantile = 1; + + // The value at the given quantile of a distribution. + // + // Quantile values must NOT be negative. + double value = 2; + } + + // (Optional) list of values at different quantiles of the distribution calculated + // from the current snapshot. The quantiles must be strictly increasing. + repeated ValueAtQuantile quantile_values = 6; + + // Flags that apply to this specific data point. See DataPointFlags + // for the available flags and their meaning. + uint32 flags = 8; +} + +// A representation of an exemplar, which is a sample input measurement. +// Exemplars also hold information about the environment when the measurement +// was recorded, for example the span and trace ID of the active span when the +// exemplar was recorded. +message Exemplar { + reserved 1; + + // The set of key/value pairs that were filtered out by the aggregator, but + // recorded alongside the original measurement. Only key/value pairs that were + // filtered out by the aggregator should be included + repeated opentelemetry.proto.common.v1.KeyValue filtered_attributes = 7; + + // time_unix_nano is the exact time when this exemplar was recorded + // + // Value is UNIX Epoch time in nanoseconds since 00:00:00 UTC on 1 January + // 1970. + fixed64 time_unix_nano = 2; + + // The value of the measurement that was recorded. An exemplar is + // considered invalid when one of the recognized value fields is not present + // inside this oneof. + oneof value { + double as_double = 3; + sfixed64 as_int = 6; + } + + // (Optional) Span ID of the exemplar trace. + // span_id may be missing if the measurement is not recorded inside a trace + // or if the trace is not sampled. + bytes span_id = 4; + + // (Optional) Trace ID of the exemplar trace. + // trace_id may be missing if the measurement is not recorded inside a trace + // or if the trace is not sampled. + bytes trace_id = 5; +} diff --git a/protos/opentelemetry/proto/resource/v1/resource.proto b/protos/opentelemetry/proto/resource/v1/resource.proto new file mode 100644 index 0000000..6637560 --- /dev/null +++ b/protos/opentelemetry/proto/resource/v1/resource.proto @@ -0,0 +1,37 @@ +// Copyright 2019, OpenTelemetry Authors +// +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +syntax = "proto3"; + +package opentelemetry.proto.resource.v1; + +import "opentelemetry/proto/common/v1/common.proto"; + +option csharp_namespace = "OpenTelemetry.Proto.Resource.V1"; +option java_multiple_files = true; +option java_package = "io.opentelemetry.proto.resource.v1"; +option java_outer_classname = "ResourceProto"; +option go_package = "go.opentelemetry.io/proto/otlp/resource/v1"; + +// Resource information. +message Resource { + // Set of attributes that describe the resource. + // Attribute keys MUST be unique (it is not allowed to have more than one + // attribute with the same key). + repeated opentelemetry.proto.common.v1.KeyValue attributes = 1; + + // dropped_attributes_count is the number of dropped attributes. If the value is 0, then + // no attributes were dropped. + uint32 dropped_attributes_count = 2; +} diff --git a/protos/opentelemetry/proto/trace/v1/trace.proto b/protos/opentelemetry/proto/trace/v1/trace.proto new file mode 100644 index 0000000..2444285 --- /dev/null +++ b/protos/opentelemetry/proto/trace/v1/trace.proto @@ -0,0 +1,357 @@ +// Copyright 2019, OpenTelemetry Authors +// +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +syntax = "proto3"; + +package opentelemetry.proto.trace.v1; + +import "opentelemetry/proto/common/v1/common.proto"; +import "opentelemetry/proto/resource/v1/resource.proto"; + +option csharp_namespace = "OpenTelemetry.Proto.Trace.V1"; +option java_multiple_files = true; +option java_package = "io.opentelemetry.proto.trace.v1"; +option java_outer_classname = "TraceProto"; +option go_package = "go.opentelemetry.io/proto/otlp/trace/v1"; + +// TracesData represents the traces data that can be stored in a persistent storage, +// OR can be embedded by other protocols that transfer OTLP traces data but do +// not implement the OTLP protocol. +// +// The main difference between this message and collector protocol is that +// in this message there will not be any "control" or "metadata" specific to +// OTLP protocol. +// +// When new fields are added into this message, the OTLP request MUST be updated +// as well. +message TracesData { + // An array of ResourceSpans. + // For data coming from a single resource this array will typically contain + // one element. Intermediary nodes that receive data from multiple origins + // typically batch the data before forwarding further and in that case this + // array will contain multiple elements. + repeated ResourceSpans resource_spans = 1; +} + +// A collection of ScopeSpans from a Resource. +message ResourceSpans { + reserved 1000; + + // The resource for the spans in this message. + // If this field is not set then no resource info is known. + opentelemetry.proto.resource.v1.Resource resource = 1; + + // A list of ScopeSpans that originate from a resource. + repeated ScopeSpans scope_spans = 2; + + // The Schema URL, if known. This is the identifier of the Schema that the resource data + // is recorded in. Notably, the last part of the URL path is the version number of the + // schema: http[s]://server[:port]/path/. To learn more about Schema URL see + // https://opentelemetry.io/docs/specs/otel/schemas/#schema-url + // This schema_url applies to the data in the "resource" field. It does not apply + // to the data in the "scope_spans" field which have their own schema_url field. + string schema_url = 3; +} + +// A collection of Spans produced by an InstrumentationScope. +message ScopeSpans { + // The instrumentation scope information for the spans in this message. + // Semantically when InstrumentationScope isn't set, it is equivalent with + // an empty instrumentation scope name (unknown). + opentelemetry.proto.common.v1.InstrumentationScope scope = 1; + + // A list of Spans that originate from an instrumentation scope. + repeated Span spans = 2; + + // The Schema URL, if known. This is the identifier of the Schema that the span data + // is recorded in. Notably, the last part of the URL path is the version number of the + // schema: http[s]://server[:port]/path/. To learn more about Schema URL see + // https://opentelemetry.io/docs/specs/otel/schemas/#schema-url + // This schema_url applies to all spans and span events in the "spans" field. + string schema_url = 3; +} + +// A Span represents a single operation performed by a single component of the system. +// +// The next available field id is 17. +message Span { + // A unique identifier for a trace. All spans from the same trace share + // the same `trace_id`. The ID is a 16-byte array. An ID with all zeroes OR + // of length other than 16 bytes is considered invalid (empty string in OTLP/JSON + // is zero-length and thus is also invalid). + // + // This field is required. + bytes trace_id = 1; + + // A unique identifier for a span within a trace, assigned when the span + // is created. The ID is an 8-byte array. An ID with all zeroes OR of length + // other than 8 bytes is considered invalid (empty string in OTLP/JSON + // is zero-length and thus is also invalid). + // + // This field is required. + bytes span_id = 2; + + // trace_state conveys information about request position in multiple distributed tracing graphs. + // It is a trace_state in w3c-trace-context format: https://www.w3.org/TR/trace-context/#tracestate-header + // See also https://github.com/w3c/distributed-tracing for more details about this field. + string trace_state = 3; + + // The `span_id` of this span's parent span. If this is a root span, then this + // field must be empty. The ID is an 8-byte array. + bytes parent_span_id = 4; + + // Flags, a bit field. + // + // Bits 0-7 (8 least significant bits) are the trace flags as defined in W3C Trace + // Context specification. To read the 8-bit W3C trace flag, use + // `flags & SPAN_FLAGS_TRACE_FLAGS_MASK`. + // + // See https://www.w3.org/TR/trace-context-2/#trace-flags for the flag definitions. + // + // Bits 8 and 9 represent the 3 states of whether a span's parent + // is remote. The states are (unknown, is not remote, is remote). + // To read whether the value is known, use `(flags & SPAN_FLAGS_CONTEXT_HAS_IS_REMOTE_MASK) != 0`. + // To read whether the span is remote, use `(flags & SPAN_FLAGS_CONTEXT_IS_REMOTE_MASK) != 0`. + // + // When creating span messages, if the message is logically forwarded from another source + // with an equivalent flags fields (i.e., usually another OTLP span message), the field SHOULD + // be copied as-is. If creating from a source that does not have an equivalent flags field + // (such as a runtime representation of an OpenTelemetry span), the high 22 bits MUST + // be set to zero. + // Readers MUST NOT assume that bits 10-31 (22 most significant bits) will be zero. + // + // [Optional]. + fixed32 flags = 16; + + // A description of the span's operation. + // + // For example, the name can be a qualified method name or a file name + // and a line number where the operation is called. A best practice is to use + // the same display name at the same call point in an application. + // This makes it easier to correlate spans in different traces. + // + // This field is semantically required to be set to non-empty string. + // Empty value is equivalent to an unknown span name. + // + // This field is required. + string name = 5; + + // SpanKind is the type of span. Can be used to specify additional relationships between spans + // in addition to a parent/child relationship. + enum SpanKind { + // Unspecified. Do NOT use as default. + // Implementations MAY assume SpanKind to be INTERNAL when receiving UNSPECIFIED. + SPAN_KIND_UNSPECIFIED = 0; + + // Indicates that the span represents an internal operation within an application, + // as opposed to an operation happening at the boundaries. Default value. + SPAN_KIND_INTERNAL = 1; + + // Indicates that the span covers server-side handling of an RPC or other + // remote network request. + SPAN_KIND_SERVER = 2; + + // Indicates that the span describes a request to some remote service. + SPAN_KIND_CLIENT = 3; + + // Indicates that the span describes a producer sending a message to a broker. + // Unlike CLIENT and SERVER, there is often no direct critical path latency relationship + // between producer and consumer spans. A PRODUCER span ends when the message was accepted + // by the broker while the logical processing of the message might span a much longer time. + SPAN_KIND_PRODUCER = 4; + + // Indicates that the span describes consumer receiving a message from a broker. + // Like the PRODUCER kind, there is often no direct critical path latency relationship + // between producer and consumer spans. + SPAN_KIND_CONSUMER = 5; + } + + // Distinguishes between spans generated in a particular context. For example, + // two spans with the same name may be distinguished using `CLIENT` (caller) + // and `SERVER` (callee) to identify queueing latency associated with the span. + SpanKind kind = 6; + + // start_time_unix_nano is the start time of the span. On the client side, this is the time + // kept by the local machine where the span execution starts. On the server side, this + // is the time when the server's application handler starts running. + // Value is UNIX Epoch time in nanoseconds since 00:00:00 UTC on 1 January 1970. + // + // This field is semantically required and it is expected that end_time >= start_time. + fixed64 start_time_unix_nano = 7; + + // end_time_unix_nano is the end time of the span. On the client side, this is the time + // kept by the local machine where the span execution ends. On the server side, this + // is the time when the server application handler stops running. + // Value is UNIX Epoch time in nanoseconds since 00:00:00 UTC on 1 January 1970. + // + // This field is semantically required and it is expected that end_time >= start_time. + fixed64 end_time_unix_nano = 8; + + // attributes is a collection of key/value pairs. Note, global attributes + // like server name can be set using the resource API. Examples of attributes: + // + // "/http/user_agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36" + // "/http/server_latency": 300 + // "example.com/myattribute": true + // "example.com/score": 10.239 + // + // The OpenTelemetry API specification further restricts the allowed value types: + // https://github.com/open-telemetry/opentelemetry-specification/blob/main/specification/common/README.md#attribute + // Attribute keys MUST be unique (it is not allowed to have more than one + // attribute with the same key). + repeated opentelemetry.proto.common.v1.KeyValue attributes = 9; + + // dropped_attributes_count is the number of attributes that were discarded. Attributes + // can be discarded because their keys are too long or because there are too many + // attributes. If this value is 0, then no attributes were dropped. + uint32 dropped_attributes_count = 10; + + // Event is a time-stamped annotation of the span, consisting of user-supplied + // text description and key-value pairs. + message Event { + // time_unix_nano is the time the event occurred. + fixed64 time_unix_nano = 1; + + // name of the event. + // This field is semantically required to be set to non-empty string. + string name = 2; + + // attributes is a collection of attribute key/value pairs on the event. + // Attribute keys MUST be unique (it is not allowed to have more than one + // attribute with the same key). + repeated opentelemetry.proto.common.v1.KeyValue attributes = 3; + + // dropped_attributes_count is the number of dropped attributes. If the value is 0, + // then no attributes were dropped. + uint32 dropped_attributes_count = 4; + } + + // events is a collection of Event items. + repeated Event events = 11; + + // dropped_events_count is the number of dropped events. If the value is 0, then no + // events were dropped. + uint32 dropped_events_count = 12; + + // A pointer from the current span to another span in the same trace or in a + // different trace. For example, this can be used in batching operations, + // where a single batch handler processes multiple requests from different + // traces or when the handler receives a request from a different project. + message Link { + // A unique identifier of a trace that this linked span is part of. The ID is a + // 16-byte array. + bytes trace_id = 1; + + // A unique identifier for the linked span. The ID is an 8-byte array. + bytes span_id = 2; + + // The trace_state associated with the link. + string trace_state = 3; + + // attributes is a collection of attribute key/value pairs on the link. + // Attribute keys MUST be unique (it is not allowed to have more than one + // attribute with the same key). + repeated opentelemetry.proto.common.v1.KeyValue attributes = 4; + + // dropped_attributes_count is the number of dropped attributes. If the value is 0, + // then no attributes were dropped. + uint32 dropped_attributes_count = 5; + + // Flags, a bit field. + // + // Bits 0-7 (8 least significant bits) are the trace flags as defined in W3C Trace + // Context specification. To read the 8-bit W3C trace flag, use + // `flags & SPAN_FLAGS_TRACE_FLAGS_MASK`. + // + // See https://www.w3.org/TR/trace-context-2/#trace-flags for the flag definitions. + // + // Bits 8 and 9 represent the 3 states of whether the link is remote. + // The states are (unknown, is not remote, is remote). + // To read whether the value is known, use `(flags & SPAN_FLAGS_CONTEXT_HAS_IS_REMOTE_MASK) != 0`. + // To read whether the link is remote, use `(flags & SPAN_FLAGS_CONTEXT_IS_REMOTE_MASK) != 0`. + // + // Readers MUST NOT assume that bits 10-31 (22 most significant bits) will be zero. + // When creating new spans, bits 10-31 (most-significant 22-bits) MUST be zero. + // + // [Optional]. + fixed32 flags = 6; + } + + // links is a collection of Links, which are references from this span to a span + // in the same or different trace. + repeated Link links = 13; + + // dropped_links_count is the number of dropped links after the maximum size was + // enforced. If this value is 0, then no links were dropped. + uint32 dropped_links_count = 14; + + // An optional final status for this span. Semantically when Status isn't set, it means + // span's status code is unset, i.e. assume STATUS_CODE_UNSET (code = 0). + Status status = 15; +} + +// The Status type defines a logical error model that is suitable for different +// programming environments, including REST APIs and RPC APIs. +message Status { + reserved 1; + + // A developer-facing human readable error message. + string message = 2; + + // For the semantics of status codes see + // https://github.com/open-telemetry/opentelemetry-specification/blob/main/specification/trace/api.md#set-status + enum StatusCode { + // The default status. + STATUS_CODE_UNSET = 0; + // The Span has been validated by an Application developer or Operator to + // have completed successfully. + STATUS_CODE_OK = 1; + // The Span contains an error. + STATUS_CODE_ERROR = 2; + }; + + // The status code. + StatusCode code = 3; +} + +// SpanFlags represents constants used to interpret the +// Span.flags field, which is protobuf 'fixed32' type and is to +// be used as bit-fields. Each non-zero value defined in this enum is +// a bit-mask. To extract the bit-field, for example, use an +// expression like: +// +// (span.flags & SPAN_FLAGS_TRACE_FLAGS_MASK) +// +// See https://www.w3.org/TR/trace-context-2/#trace-flags for the flag definitions. +// +// Note that Span flags were introduced in version 1.1 of the +// OpenTelemetry protocol. Older Span producers do not set this +// field, consequently consumers should not rely on the absence of a +// particular flag bit to indicate the presence of a particular feature. +enum SpanFlags { + // The zero value for the enum. Should not be used for comparisons. + // Instead use bitwise "and" with the appropriate mask as shown above. + SPAN_FLAGS_DO_NOT_USE = 0; + + // Bits 0-7 are used for trace flags. + SPAN_FLAGS_TRACE_FLAGS_MASK = 0x000000FF; + + // Bits 8 and 9 are used to indicate that the parent span or link span is remote. + // Bit 8 (`HAS_IS_REMOTE`) indicates whether the value is known. + // Bit 9 (`IS_REMOTE`) indicates whether the span or link is remote. + SPAN_FLAGS_CONTEXT_HAS_IS_REMOTE_MASK = 0x00000100; + SPAN_FLAGS_CONTEXT_IS_REMOTE_MASK = 0x00000200; + + // Bits 10-31 are reserved for future use. +} diff --git a/src/otlpGrpcReceiver.test.ts b/src/otlpGrpcReceiver.test.ts new file mode 100644 index 0000000..0640320 --- /dev/null +++ b/src/otlpGrpcReceiver.test.ts @@ -0,0 +1,206 @@ +/** + * Integration test for OTLP/gRPC receiver + * + * Starts a real gRPC server, sends OTLP Export requests using a gRPC client, + * and asserts that NeedleEvents arrive on the event bus. + */ + +import { describe, it, expect, beforeAll, afterAll, afterEach } from 'vitest'; +import * as grpc from '@grpc/grpc-js'; +import * as protobuf from 'protobufjs'; +import * as path from 'path'; +import { fileURLToPath } from 'url'; +import { OtlpGrpcReceiver, enrichRecord, extractDataPoints, loadProtoRoot } from './otlpGrpcReceiver.js'; +import { LogEvent } from './types.js'; + +// ── Unit tests for helper functions ─────────────────────────── + +describe('enrichRecord', () => { + it('merges scope and resource attributes into record', () => { + const record = { timeUnixNano: '1709150400000000000' }; + const scope = { name: 'needle', attributes: [ + { key: 'scope_key', value: { stringValue: 'scope_val' } }, + ]}; + const resource = { attributes: [ + { key: 'res_key', value: { stringValue: 'res_val' } }, + ]}; + + const merged = enrichRecord(record, scope, resource); + expect(merged.timeUnixNano).toBe('1709150400000000000'); + + const attrs = merged.attributes as Array<{ key: string }>; + expect(attrs).toHaveLength(2); + expect(attrs[0].key).toBe('res_key'); + expect(attrs[1].key).toBe('scope_key'); + }); + + it('returns record unchanged when no scope/resource', () => { + const record = { timeUnixNano: '123', attributes: [{ key: 'k', value: { stringValue: 'v' } }] }; + const merged = enrichRecord(record); + expect(merged.attributes).toEqual(record.attributes); + }); +}); + +describe('extractDataPoints', () => { + it('extracts data points from gauge metric', () => { + const metric = { + name: 'test_metric', + gauge: { + dataPoints: [ + { timeUnixNano: '1709150400000000000', asDouble: 42.5, attributes: [] }, + ], + }, + }; + const points = extractDataPoints(metric); + expect(points).toHaveLength(1); + expect(points[0].asDouble).toBe(42.5); + }); + + it('extracts data points from sum metric', () => { + const metric = { + name: 'request_count', + sum: { + dataPoints: [ + { timeUnixNano: '1709150400000000000', asInt: '100', attributes: [] }, + ], + }, + }; + const points = extractDataPoints(metric); + expect(points).toHaveLength(1); + expect(points[0].asInt).toBe('100'); + }); + + it('returns empty array for metric with no data points', () => { + expect(extractDataPoints({ name: 'empty' })).toHaveLength(0); + }); +}); + +// ── Integration tests with real gRPC ────────────────────────── + +describe('OtlpGrpcReceiver integration', () => { + let receiver: OtlpGrpcReceiver; + let clientRoot: protobuf.Root; + let client: grpc.Client; + let collectedEvents: LogEvent[]; + let boundPort: number; + + beforeAll(async () => { + clientRoot = await loadProtoRoot(); + }); + + beforeEach(async () => { + collectedEvents = []; + receiver = new OtlpGrpcReceiver({ address: '127.0.0.1:0' }); + receiver.on('event', (event: LogEvent) => { + collectedEvents.push(event); + }); + const addr = await receiver.start(); + boundPort = parseInt(addr.split(':')[1], 10); + + // Create gRPC client + const LogsServiceDef = buildClientServiceDef( + clientRoot, + '/opentelemetry.proto.collector.logs.v1.LogsService/Export', + 'opentelemetry.proto.collector.logs.v1.ExportLogsServiceRequest', + 'opentelemetry.proto.collector.logs.v1.ExportLogsServiceResponse', + ); + client = new grpc.Client( + `127.0.0.1:${boundPort}`, + grpc.credentials.createInsecure(), + ); + }); + + afterEach(async () => { + client.close(); + await receiver.stop(); + }); + + it('accepts a log export and emits a normalized LogEvent', async () => { + const reqType = clientRoot.lookupType('opentelemetry.proto.collector.logs.v1.ExportLogsServiceRequest')!; + const resType = clientRoot.lookupType('opentelemetry.proto.collector.logs.v1.ExportLogsServiceResponse')!; + + const nowNs = String(Date.now() * 1_000_000); + const requestPayload = reqType.create({ + resourceLogs: [{ + scopeLogs: [{ + logRecords: [{ + timeUnixNano: nowNs, + attributes: [ + { key: 'event_type', value: { stringValue: 'worker.started' } }, + { key: 'worker_id', value: { stringValue: 'needle-alpha' } }, + { key: 'session_id', value: { stringValue: 'sess-001' } }, + { key: 'sequence', value: { intValue: 1 } }, + ], + }], + }], + }], + }); + + const requestBytes = Buffer.from(reqType.encode(requestPayload).finish()); + + await new Promise((resolve, reject) => { + client.makeUnaryRequest( + '/opentelemetry.proto.collector.logs.v1.LogsService/Export', + (msg: any) => Buffer.from(reqType.encode(msg).finish()), + (buf: Buffer) => resType.decode(new Uint8Array(buf)) as any, + requestPayload, + (err: grpc.ServiceError | null, resp: any) => { + if (err) reject(err); + else resolve(); + }, + ); + }); + + // Wait for event propagation + await new Promise((r) => setTimeout(r, 100)); + + expect(collectedEvents).toHaveLength(1); + const event = collectedEvents[0]; + expect(event.worker).toBe('needle-alpha'); + expect(event.msg).toBe('worker.started'); + expect(event.session).toBe('sess-001'); + }); + + it('accepts an empty export without error', async () => { + const reqType = clientRoot.lookupType('opentelemetry.proto.collector.logs.v1.ExportLogsServiceRequest')!; + const resType = clientRoot.lookupType('opentelemetry.proto.collector.logs.v1.ExportLogsServiceResponse')!; + + await new Promise((resolve, reject) => { + client.makeUnaryRequest( + '/opentelemetry.proto.collector.logs.v1.LogsService/Export', + (msg: any) => Buffer.from(reqType.encode(msg).finish()), + (buf: Buffer) => resType.decode(new Uint8Array(buf)) as any, + {}, + (err: grpc.ServiceError | null) => { + if (err) reject(err); + else resolve(); + }, + ); + }); + + await new Promise((r) => setTimeout(r, 50)); + expect(collectedEvents).toHaveLength(0); + }); +}); + +// ── Helper: build a minimal client-side MethodDefinition ────── + +function buildClientServiceDef( + root: protobuf.Root, + servicePath: string, + requestFqn: string, + _responseFqn: string, +): grpc.MethodDefinition { + const reqType = root.lookupType(requestFqn); + return { + path: servicePath, + requestStream: false, + responseStream: false, + requestSerialize: (msg: any) => + Buffer.from(reqType.encode(reqType.create(msg)).finish()), + requestDeserialize: (buf: Buffer) => + reqType.toObject(reqType.decode(new Uint8Array(buf)), { longs: String }), + responseSerialize: () => Buffer.alloc(0), + responseDeserialize: () => ({}), + }; +} diff --git a/src/otlpGrpcReceiver.ts b/src/otlpGrpcReceiver.ts new file mode 100644 index 0000000..503aee4 --- /dev/null +++ b/src/otlpGrpcReceiver.ts @@ -0,0 +1,328 @@ +/** + * FABRIC OTLP/gRPC Receiver + * + * Accepts OTLP/gRPC streams on a configurable address (default 0.0.0.0:4317), + * decodes protobuf payloads, and feeds decoded records into the normalizer + * pipeline so they appear alongside JSONL-sourced events. + * + * Terminates all three OTLP collector services: + * - LogsService/Export + * - TraceService/Export + * - MetricsService/Export + */ + +import * as grpc from '@grpc/grpc-js'; +import * as protobuf from 'protobufjs'; +import { fileURLToPath } from 'url'; +import * as path from 'path'; +import { normalizeToLogEvent, NormalizerSource } from './normalizer.js'; +import { LogEvent } from './types.js'; +import { EventEmitter } from 'events'; + +// ── Proto loading ───────────────────────────────────────────── + +let protoRoot: protobuf.Root | null = null; + +export async function loadProtoRoot(): Promise { + if (protoRoot) return protoRoot; + + const __dirname = path.dirname(fileURLToPath(import.meta.url)); + // dist/ in production, src/ during dev — both have the same relative layout + const protoBase = path.resolve(__dirname, '..', 'protos'); + + const root = new protobuf.Root(); + // Proto import paths like "opentelemetry/proto/logs/v1/logs.proto" need to + // resolve from the protos/ root, not relative to the importing file. + root.resolvePath = function (originPath, importPath) { + if (importPath.startsWith('opentelemetry/')) { + return path.join(protoBase, importPath); + } + return protobuf.util.path.resolve(originPath, importPath); + }; + + await protobuf.load( + path.join(protoBase, 'opentelemetry', 'proto', 'collector', 'logs', 'v1', 'logs_service.proto'), + root, + ); + await protobuf.load( + path.join(protoBase, 'opentelemetry', 'proto', 'collector', 'trace', 'v1', 'trace_service.proto'), + root, + ); + await protobuf.load( + path.join(protoBase, 'opentelemetry', 'proto', 'collector', 'metrics', 'v1', 'metrics_service.proto'), + root, + ); + + protoRoot = root; + + return protoRoot; +} + +// ── Helpers ─────────────────────────────────────────────────── + +function lookupType(root: protobuf.Root, fqn: string): protobuf.Type { + const t = root.lookupType(fqn); + if (!t) throw new Error(`protobuf type not found: ${fqn}`); + return t; +} + +/** proto-loader-style plain-object conversion (camelCase, longs→String) */ +const DECODE_OPTS: protobuf.IConversionOptions = { + longs: String, + enums: String, + bytes: String, + defaults: true, + oneofs: true, +}; + +/** Build a grpc.MethodDefinition for a single unary Export RPC. */ +function makeMethod( + root: protobuf.Root, + servicePath: string, + requestFqn: string, + responseFqn: string, +): grpc.MethodDefinition { + const reqType = lookupType(root, requestFqn); + const resType = lookupType(root, responseFqn); + return { + path: servicePath, + requestStream: false, + responseStream: false, + requestSerialize: (msg: any) => + Buffer.from(reqType.encode(reqType.create(msg)).finish()), + requestDeserialize: (buf: Buffer) => + reqType.toObject(reqType.decode(new Uint8Array(buf)), DECODE_OPTS) as any, + responseSerialize: (msg: any) => + Buffer.from(resType.encode(resType.create(msg)).finish()), + responseDeserialize: (buf: Buffer) => + resType.toObject(resType.decode(new Uint8Array(buf)), DECODE_OPTS) as any, + }; +} + +// ── Receiver class ──────────────────────────────────────────── + +export interface OtlpGrpcReceiverOptions { + /** Bind address, e.g. "0.0.0.0:4317" or ":4317". Default ":4317". */ + address?: string; +} + +export class OtlpGrpcReceiver extends EventEmitter { + private address: string; + private server: grpc.Server | null = null; + + constructor(options: OtlpGrpcReceiverOptions = {}) { + super(); + this.address = options.address || ':4317'; + } + + /** + * Start the gRPC server. Resolves with the bound address string + * (useful when binding to port 0). + */ + async start(): Promise { + const root = await loadProtoRoot(); + + // ── Build service definitions ── + + const logsExport = makeMethod( + root, + '/opentelemetry.proto.collector.logs.v1.LogsService/Export', + 'opentelemetry.proto.collector.logs.v1.ExportLogsServiceRequest', + 'opentelemetry.proto.collector.logs.v1.ExportLogsServiceResponse', + ); + const traceExport = makeMethod( + root, + '/opentelemetry.proto.collector.trace.v1.TraceService/Export', + 'opentelemetry.proto.collector.trace.v1.ExportTraceServiceRequest', + 'opentelemetry.proto.collector.trace.v1.ExportTraceServiceResponse', + ); + const metricsExport = makeMethod( + root, + '/opentelemetry.proto.collector.metrics.v1.MetricsService/Export', + 'opentelemetry.proto.collector.metrics.v1.ExportMetricsServiceRequest', + 'opentelemetry.proto.collector.metrics.v1.ExportMetricsServiceResponse', + ); + + // ── Handlers ── + + const handleLogs: grpc.handleUnaryCall = (call, callback) => { + try { + const req = call.request; + for (const rl of req.resourceLogs ?? []) { + for (const sl of rl.scopeLogs ?? []) { + for (const lr of sl.logRecords ?? []) { + // Merge scope/resource attrs into the record so the + // normalizer can find worker_id / session_id etc. + const merged = enrichRecord(lr, sl.scope, rl.resource); + this.pushNormalized(merged, 'otlp-log'); + } + } + } + callback(null, {}); + } catch (err) { + callback(err as Error, null); + } + }; + + const handleTraces: grpc.handleUnaryCall = (call, callback) => { + try { + const req = call.request; + for (const rs of req.resourceSpans ?? []) { + for (const ss of rs.scopeSpans ?? []) { + for (const span of ss.spans ?? []) { + const merged = enrichRecord(span, ss.scope, rs.resource); + this.pushNormalized(merged, 'otlp-span-end'); + // Also emit a span-start event so the timeline shows both + if (span.startTimeUnixNano) { + const startRecord = { ...merged, timeUnixNano: span.startTimeUnixNano }; + this.pushNormalized(startRecord, 'otlp-span-start'); + } + } + } + } + callback(null, {}); + } catch (err) { + callback(err as Error, null); + } + }; + + const handleMetrics: grpc.handleUnaryCall = (call, callback) => { + try { + const req = call.request; + for (const rm of req.resourceMetrics ?? []) { + for (const sm of rm.scopeMetrics ?? []) { + for (const metric of sm.metrics ?? []) { + const dataPoints = extractDataPoints(metric); + for (const dp of dataPoints) { + const merged = enrichRecord( + { ...dp, name: metric.name }, + sm.scope, + rm.resource, + ); + this.pushNormalized(merged, 'otlp-metric'); + } + } + } + } + callback(null, {}); + } catch (err) { + callback(err as Error, null); + } + }; + + // ── Register services ── + + const server = new grpc.Server(); + server.addService({ Export: logsExport }, { Export: handleLogs }); + server.addService({ Export: traceExport }, { Export: handleTraces }); + server.addService({ Export: metricsExport }, { Export: handleMetrics }); + + this.server = server; + + return new Promise((resolve, reject) => { + server.bindAsync(this.address, grpc.ServerCredentials.createInsecure(), (err, port) => { + if (err) { + this.server = null; + reject(err); + return; + } + server.start(); + const boundAddr = `0.0.0.0:${port}`; + this.emit('listening', boundAddr); + resolve(boundAddr); + }); + }); + } + + /** Stop the gRPC server. */ + async stop(): Promise { + if (!this.server) return; + const srv = this.server; + this.server = null; + return new Promise((resolve, reject) => { + srv.tryShutdown((err) => { + if (err) reject(err); + else resolve(); + }); + }); + } + + // ── Private helpers ── + + private pushNormalized(record: unknown, source: NormalizerSource): void { + const event = normalizeToLogEvent(record, source); + if (event) { + this.emit('event', event); + } + } +} + +// ── Pure functions (exported for testing) ───────────────────── + +/** + * Merge scope and resource attributes into a record so the normalizer + * can find worker_id, session_id, etc. regardless of which level they + * appear at in the OTLP hierarchy. + */ +export function enrichRecord( + record: Record, + scope?: Record, + resource?: Record, +): Record { + const merged: Record = { ...record }; + + // Promote scope attributes into the record's attributes + const scopeAttrs = scope?.attributes; + if (Array.isArray(scopeAttrs) && !merged.attributes) { + merged.attributes = scopeAttrs; + } + + // Promote resource attributes into the record's attributes + const resAttrs = resource?.attributes; + if (Array.isArray(resAttrs)) { + const existing = merged.attributes; + if (Array.isArray(existing)) { + merged.attributes = [...resAttrs, ...existing]; + } else { + merged.attributes = resAttrs; + } + } + + return merged; +} + +/** + * Extract flat data-point objects from an OTLP Metric message. + * Handles gauge, sum, and histogram metric types. + */ +export function extractDataPoints( + metric: Record, +): Record[] { + const points: Record[] = []; + + for (const key of ['gauge', 'sum', 'histogram'] as const) { + const container = metric[key] as Record | undefined; + if (!container) continue; + const dps = container.dataPoints as Record[] | undefined; + if (!Array.isArray(dps)) continue; + for (const dp of dps) { + points.push({ ...dp }); + } + } + + return points; +} + +/** + * Create and start an OTLP gRPC receiver, wiring its events to the + * given callbacks. Returns the receiver instance. + */ +export async function startOtlpGrpcReceiver( + address: string, + onEvent: (event: LogEvent) => void, +): Promise { + const receiver = new OtlpGrpcReceiver({ address }); + receiver.on('event', onEvent); + await receiver.start(); + return receiver; +}