Merge branch 'otel-logging' into dev

Author: KillianMeersman

.envrc

@@ -0,0 +1 @@
+export OTEL_EXPORTER_OTLP_ENDPOINT="http://localhost:4317"

.services/jaeger/Dockerfile

@@ -0,0 +1,5 @@
+FROM jaegertracing/jaeger:2.5.0
+
+# Copy the configuration file
+COPY config.yaml /etc/jaeger/jaeger-config.yaml
+COPY ui-config.json /etc/jaeger/config-ui.json

.services/jaeger/config.yaml

@@ -0,0 +1,88 @@
+service:
+  extensions: [jaeger_storage, jaeger_query, healthcheckv2]
+  pipelines:
+    traces:
+      receivers: [otlp/jaeger]
+      processors: [batch]
+      exporters: [jaeger_storage_exporter]
+  telemetry:
+    resource:
+      service.name: jaeger
+    # metrics:
+    #   level: detailed
+    #   readers:
+    #     - pull:
+    #         exporter:
+    #           prometheus:
+    #             host: 0.0.0.0
+    #             port: 8888
+    logs:
+      level: info
+    # TODO Initialize telemetry tracer once OTEL released new feature.
+    # https://github.com/open-telemetry/opentelemetry-collector/issues/10663
+
+# ttl:
+#   span_store: 72h
+
+extensions:
+  healthcheckv2:
+    use_v2: true
+    http:
+
+  jaeger_query:
+    storage:
+      traces: traces_elasticsearch
+      traces_archive: traces_elasticsearch
+    ui:
+      config_file: ./etc/jaeger/config-ui.json
+
+  jaeger_storage:
+    backends:
+      traces_elasticsearch:
+        elasticsearch:
+          server_urls:
+            - http://tracing-elasticsearch:9200
+          indices:
+            # Create a single index per day, with 5 shards per index.
+            index_prefix: "jaeger-main"
+            spans:
+              date_layout: "2006-01-02"
+              rollover_frequency: "day"
+              shards: 5
+              replicas: 1
+            services:
+              date_layout: "2006-01-02"
+              rollover_frequency: "day"
+              shards: 5
+              replicas: 1
+            dependencies:
+              date_layout: "2006-01-02"
+              rollover_frequency: "day"
+              shards: 5
+              replicas: 1
+            sampling:
+              date_layout: "2006-01-02"
+              rollover_frequency: "day"
+              shards: 5
+              replicas: 1
+    metric_backends:
+      prometheus_storage:
+        prometheus:
+          endpoint: http://prometheus:9090
+          normalize_calls: true
+          normalize_duration: true
+
+receivers:
+  otlp/jaeger:
+    protocols:
+      http:
+        endpoint: 0.0.0.0:4318
+      grpc:
+        endpoint: 0.0.0.0:4317
+
+processors:
+  batch:
+
+exporters:
+  jaeger_storage_exporter:
+    trace_storage: traces_elasticsearch

.services/jaeger/ui-config.json

@@ -0,0 +1,50 @@
+{
+    "dependencies": {
+        "dagMaxNumServices": 200,
+        "menuEnabled": true
+    },
+    "monitor": {
+        "menuEnabled": true
+    },
+    "archiveEnabled": true,
+    "tracking": {
+        "gaID": "UA-000000-2",
+        "trackErrors": true
+    },
+    "menu": [
+        {
+            "label": "About Jaeger",
+            "items": [
+                {
+                    "label": "GitHub",
+                    "url": "https://github.com/jaegertracing/jaeger"
+                },
+                {
+                    "label": "Docs",
+                    "url": "http://jaeger.readthedocs.io/en/latest/"
+                }
+            ]
+        }
+    ],
+    "search": {
+        "maxLookback": {
+            "label": "2 Days",
+            "value": "2d"
+        },
+        "maxLimit": 1500
+    },
+    "linkPatterns": [
+        {
+            "type": "process",
+            "key": "jaeger.version",
+            "url": "https://github.com/jaegertracing/jaeger-client-java/releases/tag/#{jaeger.version}",
+            "text": "Information about Jaeger release #{jaeger.version}"
+        },
+        {
+            "type": "tags",
+            "key": "uniqueId",
+            "url": "https://mykibana.com/uniqueId=#{uniqueId}&traceId=#{trace.traceID}",
+            "text": "Redirect to kibana to view log"
+        }
+    ]
+}

.services/loki/Dockerfile

@@ -0,0 +1,6 @@
+FROM grafana/loki:3
+
+# Copy the configuration file
+COPY config.yaml config.yaml
+
+EXPOSE 3100/tcp

.services/loki/README.md

@@ -0,0 +1,31 @@
+# Loki log collector & database
+
+Loki is a log collector & storage engine, consisting of multiple different processes.
+To make deployment easy, every process is contained in the same binary and can be enabled individually using the `-target=` flag. Targets may be listed using the `-list-targets` flag.
+
+## Simple scalable deployment
+
+See https://grafana.com/docs/loki/latest/get-started/deployment-modes/#simple-scalable.
+
+Loki’s simple scalable deployment mode separates execution paths into read, write, and backend targets. These targets can be scaled independently, letting you customize your Loki deployment to meet your business needs for log ingestion and log query so that your infrastructure costs better match how you use Loki.
+
+The simple scalable deployment mode can scale up to a few TBs of logs per day, however if you go much beyond this, the microservices mode will be a better choice for most users.
+
+The three execution paths in simple scalable mode are each activated by appending the following arguments to Loki on startup:
+
+    -target=write - The write target is stateful and is controlled by a Kubernetes StatefulSet. It contains the following components:
+        Distributor
+        Ingester
+    -target=read - The read target is stateless and can be run as a Kubernetes Deployment that can be scaled automatically (Note that in the official helm chart it is currently deployed as a stateful set). It contains the following components:
+        Query Frontend
+        Querier
+    -target=backend - The backend target is stateful, and is controlled by a Kubernetes StatefulSet. Contains the following components:
+        Compactor
+        Index Gateway
+        Query Scheduler
+        Ruler
+        Bloom Planner (experimental)
+        Bloom Builder (experimental)
+        Bloom Gateway (experimental)
+
+The simple scalable deployment mode requires a reverse proxy to be deployed in front of Loki, to direct client API requests to either the read or write nodes. The Loki Helm chart includes a default reverse proxy configuration, using Nginx.

.services/loki/config.yaml

@@ -0,0 +1,75 @@
+# For reference, see https://grafana.com/docs/loki/latest/configuration/
+
+auth_enabled: false
+
+server:
+  http_listen_port: 3100
+
+common:
+  instance_addr: 127.0.0.1
+  path_prefix: /loki
+  storage:
+    filesystem:
+      chunks_directory: /loki/chunks
+      rules_directory: /loki/rules
+  replication_factor: 1
+  ring:
+    kvstore:
+      store: inmemory
+
+limits_config:
+  # Allow user to send structured metadata in push payload.
+  # Necessary for OTLP push.
+  allow_structured_metadata: true
+
+schema_config:
+  configs:
+    - from: 2020-10-24
+      store: tsdb
+      object_store: filesystem
+      schema: v13
+      index:
+        prefix: index_
+        period: 24h
+
+block_builder:
+  chunk_target_size: 1MB
+  max_chunk_age: 3h
+
+ingester:
+  chunk_idle_period: 3h
+
+storage_config:
+  filesystem:
+    directory: /loki/chunks/
+
+distributor:
+  # Promote the following labels coming from OpenTelemetry input to be indexed.
+  # Only indexed labels can be filtered on.
+  # See https://grafana.com/docs/loki/latest/get-started/labels/#default-labels-for-opentelemetry.
+  otlp_config:
+    default_resource_attributes_as_index_labels:
+      - service.name
+      - environment
+      - deploy.environment
+      - k8s.pod.name
+      - k8s.deployment.name
+      - k8s.daemonset.name
+      - k8s.statefulset.name
+      - k8s.namespace.name
+      - k8s.job.name
+
+ruler:
+  alertmanager_url: http://localhost:9093
+# By default, Loki will send anonymous, but uniquely-identifiable usage and configuration
+# analytics to Grafana Labs. These statistics are sent to https://stats.grafana.org/
+#
+# Statistics help us better understand how Loki is used, and they show us performance
+# levels for most users. This helps us prioritize features and documentation.
+# For more information on what's sent, look at
+# https://github.com/grafana/loki/blob/main/pkg/usagestats/stats.go
+# Refer to the buildReport method to see what goes into a report.
+#
+# If you would like to disable reporting, uncomment the following lines:
+#analytics:
+#  reporting_enabled: false

.services/opentelemetry-collector/Dockerfile

@@ -0,0 +1,8 @@
+FROM otel/opentelemetry-collector-contrib:0.123.0
+
+COPY ./config.yaml /etc/otelcol-contrib/config.yaml
+
+# OTLP gRPC receiver
+EXPOSE 4317
+# OTLP http receiver
+EXPOSE 4318

.services/opentelemetry-collector/config.yaml

@@ -0,0 +1,81 @@
+# Receivers: Where and how do we receive data.
+# =====================================================
+receivers:
+  otlp: # the OTLP receiver the app is sending traces to
+    protocols:
+      grpc:
+        endpoint: 0.0.0.0:4317
+      http:
+        endpoint: 0.0.0.0:4318
+
+# Processors: How do we transform our data?
+# =====================================================
+processors:
+  # Limit memory consumption by dropping telemetry if necessary. Prevents OOM.
+  # See https://github.com/open-telemetry/opentelemetry-collector/blob/main/processor/memorylimiterprocessor/README.md
+  memory_limiter:
+    check_interval: 1s
+    limit_percentage: 75
+    spike_limit_percentage: 20
+
+  # Groups spans from the same trace before sending it on.
+  # Minimizes incomplete traces in downstream collectors.
+  # See https://github.com/open-telemetry/opentelemetry-collector-contrib/blob/main/processor/groupbytraceprocessor/README.md
+  groupbytrace:
+    wait_duration: 5s
+    num_traces: 10000
+    num_workers: 1
+
+  # Batches telemetry before sending it on, making more effective use of the network.
+  # See https://github.com/open-telemetry/opentelemetry-collector/blob/main/processor/batchprocessor/README.md
+  batch:
+    send_batch_size: 8192
+    timeout: 200ms
+    metadata_cardinality_limit: 1000
+
+# Exporters: Where we expose/push our processed data to.
+# =====================================================
+exporters:
+  # Jaeger's OTLP endpoint.
+  otlp/jaeger:
+    endpoint: jaeger:4317
+    tls:
+      insecure: true
+
+  # Loki's OTLPHTTP endpoint.
+  # See https://github.com/open-telemetry/opentelemetry-collector/blob/main/exporter/otlphttpexporter/README.md
+  otlphttp/loki:
+    endpoint: http://loki:3100/otlp
+    tls:
+      insecure: true
+
+  # Push metrics to Prometheus via remote write.
+  # The remote write exporter normalizes names and labels.
+  # See https://github.com/open-telemetry/opentelemetry-collector-contrib/blob/main/pkg/translator/prometheus/README.md
+  prometheusremotewrite:
+    endpoint: http://prometheus:9090/api/v1/write
+    tls:
+      insecure: true
+    target_info:
+      enabled: true
+    resource_to_telemetry_conversion:
+      enabled: true # Convert resource attributes to metric labels
+
+# Service: How do we connect our receivers, processors, and exporters?
+# =====================================================
+service:
+  pipelines:
+    traces:
+      receivers: [otlp]
+      # Export traces to jaeger and an internal exporter named 'spanmetrics'.
+      processors: [memory_limiter, groupbytrace, batch]
+      exporters: [otlp/jaeger]
+    metrics:
+      # Receive metrics from our otlp endpoints.
+      receivers: [otlp]
+      processors: [memory_limiter, batch]
+      exporters: [prometheusremotewrite]
+    logs:
+      receivers: [otlp]
+      processors: [memory_limiter, batch]
+      exporters: [otlphttp/loki]

.services/prometheus/Dockerfile

@@ -0,0 +1,6 @@
+FROM prom/prometheus:main
+
+COPY prometheus.yaml /etc/prometheus/prometheus.yml
+
+VOLUME [ "/prometheus" ]
+CMD [ "--config.file=/etc/prometheus/prometheus.yml", "--storage.tsdb.path=/prometheus", "--web.enable-otlp-receiver", "--web.enable-remote-write-receiver"]