From 38aa6664b8bfff5ee4f61ad230880f624fedf705 Mon Sep 17 00:00:00 2001 From: Rogee Date: Tue, 7 Jan 2025 15:50:11 +0800 Subject: [PATCH] feat: add otel --- .../project/providers/otel/config.go.tpl | 27 + .../project/providers/otel/docker/-env.tpl | 30 + .../otel/docker/docker-compose.yaml.tpl | 153 + .../otel/docker/grafana/grafana.ini.tpl | 1170 ++++++ .../provisioning/dashboards/demo.yaml.tpl | 14 + .../dashboards/demo/demo-dashboard.json.tpl | 1076 ++++++ .../demo/exemplars-dashboard.json.tpl | 435 +++ ...opentelemetry-collector-data-flow.json.tpl | 2320 ++++++++++++ .../demo/opentelemetry-collector.json.tpl | 3239 +++++++++++++++++ .../demo/spanmetrics-dashboard.json.tpl | 1012 +++++ .../provisioning/datasources/default.yaml.tpl | 21 + .../provisioning/datasources/jaeger.yaml.tpl | 13 + .../datasources/opensearch.yaml.tpl | 20 + .../otelcol-config-extras.yml.tpl | 18 + .../otel-collector/otelcol-config.yml.tpl | 128 + .../prometheus/prometheus-config.yaml.tpl | 27 + .../project/providers/otel/provider.go.tpl | 120 + 17 files changed, 9823 insertions(+) create mode 100644 templates/project/providers/otel/config.go.tpl create mode 100644 templates/project/providers/otel/docker/-env.tpl create mode 100644 templates/project/providers/otel/docker/docker-compose.yaml.tpl create mode 100644 templates/project/providers/otel/docker/grafana/grafana.ini.tpl create mode 100644 templates/project/providers/otel/docker/grafana/provisioning/dashboards/demo.yaml.tpl create mode 100644 templates/project/providers/otel/docker/grafana/provisioning/dashboards/demo/demo-dashboard.json.tpl create mode 100644 templates/project/providers/otel/docker/grafana/provisioning/dashboards/demo/exemplars-dashboard.json.tpl create mode 100644 templates/project/providers/otel/docker/grafana/provisioning/dashboards/demo/opentelemetry-collector-data-flow.json.tpl create mode 100644 templates/project/providers/otel/docker/grafana/provisioning/dashboards/demo/opentelemetry-collector.json.tpl create mode 100644 templates/project/providers/otel/docker/grafana/provisioning/dashboards/demo/spanmetrics-dashboard.json.tpl create mode 100644 templates/project/providers/otel/docker/grafana/provisioning/datasources/default.yaml.tpl create mode 100644 templates/project/providers/otel/docker/grafana/provisioning/datasources/jaeger.yaml.tpl create mode 100644 templates/project/providers/otel/docker/grafana/provisioning/datasources/opensearch.yaml.tpl create mode 100644 templates/project/providers/otel/docker/otel-collector/otelcol-config-extras.yml.tpl create mode 100644 templates/project/providers/otel/docker/otel-collector/otelcol-config.yml.tpl create mode 100644 templates/project/providers/otel/docker/prometheus/prometheus-config.yaml.tpl create mode 100644 templates/project/providers/otel/provider.go.tpl diff --git a/templates/project/providers/otel/config.go.tpl b/templates/project/providers/otel/config.go.tpl new file mode 100644 index 0000000..d1a9249 --- /dev/null +++ b/templates/project/providers/otel/config.go.tpl @@ -0,0 +1,27 @@ +package otel + +import ( + "git.ipao.vip/rogeecn/atom/container" + "git.ipao.vip/rogeecn/atom/utils/opt" +) + +const DefaultPrefix = "OTEL" + +func DefaultProvider() container.ProviderContainer { + return container.ProviderContainer{ + Provider: Provide, + Options: []opt.Option{ + opt.Prefix(DefaultPrefix), + }, + } +} + +type Config struct { + ServiceName string + Version string + Env string + + EndpointGRPC string + EndpointHTTP string + Token string +} diff --git a/templates/project/providers/otel/docker/-env.tpl b/templates/project/providers/otel/docker/-env.tpl new file mode 100644 index 0000000..7a96191 --- /dev/null +++ b/templates/project/providers/otel/docker/-env.tpl @@ -0,0 +1,30 @@ +# Dependent images +GRAFANA_IMAGE=docker.hub.ipao.vip/grafana/grafana:11.4.0 +JAEGERTRACING_IMAGE=docker.hub.ipao.vip/jaegertracing/all-in-one:1.64.0 +OPENSEARCH_IMAGE=docker.hub.ipao.vip/opensearchproject/opensearch:2.18.0 +COLLECTOR_CONTRIB_IMAGE=docker-ghcr.hub.ipao.vip/open-telemetry/opentelemetry-collector-releases/opentelemetry-collector-contrib:0.116.1 +PROMETHEUS_IMAGE=docker-quay.hub.ipao.vip/prometheus/prometheus:v3.0.1 + +# OpenTelemetry Collector +HOST_FILESYSTEM=/ +DOCKER_SOCK=/var/run/docker.sock +OTEL_COLLECTOR_HOST=otel-collector +OTEL_COLLECTOR_PORT_GRPC=4317 +OTEL_COLLECTOR_PORT_HTTP=4318 +OTEL_COLLECTOR_CONFIG=./otel-collector/otelcol-config.yml +OTEL_COLLECTOR_CONFIG_EXTRAS=./otel-collector/otelcol-config-extras.yml +OTEL_EXPORTER_OTLP_ENDPOINT=http://${OTEL_COLLECTOR_HOST}:${OTEL_COLLECTOR_PORT_GRPC} +PUBLIC_OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=http://localhost:8080/otlp-http/v1/traces + +# Grafana +GRAFANA_SERVICE_PORT=3000 +GRAFANA_SERVICE_HOST=grafana + +# Jaeger +JAEGER_SERVICE_PORT=16686 +JAEGER_SERVICE_HOST=jaeger + +# Prometheus +PROMETHEUS_SERVICE_PORT=9090 +PROMETHEUS_SERVICE_HOST=prometheus +PROMETHEUS_ADDR=${PROMETHEUS_SERVICE_HOST}:${PROMETHEUS_SERVICE_PORT} diff --git a/templates/project/providers/otel/docker/docker-compose.yaml.tpl b/templates/project/providers/otel/docker/docker-compose.yaml.tpl new file mode 100644 index 0000000..cdbe983 --- /dev/null +++ b/templates/project/providers/otel/docker/docker-compose.yaml.tpl @@ -0,0 +1,153 @@ +# Copyright The OpenTelemetry Authors +# SPDX-License-Identifier: Apache-2.0 + +x-default-logging: &logging + driver: "json-file" + options: + max-size: "5m" + max-file: "2" + tag: "{{.Name}}" + +networks: + default: + name: opentelemetry-demo + driver: bridge + +services: + # ******************** + # Telemetry Components + # ******************** + # Jaeger + jaeger: + image: ${JAEGERTRACING_IMAGE} + container_name: jaeger + command: + - "--memory.max-traces=5000" + - "--query.base-path=/jaeger/ui" + - "--prometheus.server-url=http://${PROMETHEUS_ADDR}" + - "--prometheus.query.normalize-calls=true" + - "--prometheus.query.normalize-duration=true" + deploy: + resources: + limits: + memory: 400M + restart: unless-stopped + ports: + - "${JAEGER_SERVICE_PORT}:${JAEGER_SERVICE_PORT}" # Jaeger UI + # - "${OTEL_COLLECTOR_PORT_GRPC}" + environment: + - METRICS_STORAGE_TYPE=prometheus + logging: *logging + + # Grafana + grafana: + image: ${GRAFANA_IMAGE} + container_name: grafana + deploy: + resources: + limits: + memory: 100M + restart: unless-stopped + environment: + - "GF_INSTALL_PLUGINS=grafana-opensearch-datasource" + volumes: + - ./grafana/grafana.ini:/etc/grafana/grafana.ini + - ./grafana/provisioning/:/etc/grafana/provisioning/ + ports: + - "${GRAFANA_SERVICE_PORT}:${GRAFANA_SERVICE_PORT}" + logging: *logging + + # OpenTelemetry Collector + otel-collector: + image: ${COLLECTOR_CONTRIB_IMAGE} + container_name: otel-collector + deploy: + resources: + limits: + memory: 200M + restart: unless-stopped + command: + [ + "--config=/etc/otelcol-config.yml", + "--config=/etc/otelcol-config-extras.yml", + ] + user: 0:0 + volumes: + - ${HOST_FILESYSTEM}:/hostfs:ro + - ${DOCKER_SOCK}:/var/run/docker.sock:ro + - ${OTEL_COLLECTOR_CONFIG}:/etc/otelcol-config.yml + - ${OTEL_COLLECTOR_CONFIG_EXTRAS}:/etc/otelcol-config-extras.yml + ports: + - "${OTEL_COLLECTOR_PORT_GRPC}:${OTEL_COLLECTOR_PORT_GRPC}" + - "${OTEL_COLLECTOR_PORT_HTTP}:${OTEL_COLLECTOR_PORT_HTTP}" + depends_on: + jaeger: + condition: service_started + opensearch: + condition: service_healthy + logging: *logging + environment: + - ENVOY_PORT + - HOST_FILESYSTEM + - OTEL_COLLECTOR_HOST + - OTEL_COLLECTOR_PORT_GRPC + - OTEL_COLLECTOR_PORT_HTTP + + # Prometheus + prometheus: + image: ${PROMETHEUS_IMAGE} + container_name: prometheus + command: + - --web.console.templates=/etc/prometheus/consoles + - --web.console.libraries=/etc/prometheus/console_libraries + - --storage.tsdb.retention.time=1h + - --config.file=/etc/prometheus/prometheus-config.yaml + - --storage.tsdb.path=/prometheus + - --web.enable-lifecycle + - --web.route-prefix=/ + - --web.enable-otlp-receiver + - --enable-feature=exemplar-storage + volumes: + - ./prometheus/prometheus-config.yaml:/etc/prometheus/prometheus-config.yaml + deploy: + resources: + limits: + memory: 300M + restart: unless-stopped + ports: + - "${PROMETHEUS_SERVICE_PORT}:${PROMETHEUS_SERVICE_PORT}" + logging: *logging + + # OpenSearch + opensearch: + image: ${OPENSEARCH_IMAGE} + container_name: opensearch + deploy: + resources: + limits: + memory: 1G + restart: unless-stopped + environment: + - cluster.name=demo-cluster + - node.name=demo-node + - bootstrap.memory_lock=true + - discovery.type=single-node + - OPENSEARCH_JAVA_OPTS=-Xms300m -Xmx300m + - DISABLE_INSTALL_DEMO_CONFIG=true + - DISABLE_SECURITY_PLUGIN=true + ulimits: + memlock: + soft: -1 + hard: -1 + nofile: + soft: 65536 + hard: 65536 + ports: + - "9200:9200" + healthcheck: + test: curl -s http://localhost:9200/_cluster/health | grep -E '"status":"(green|yellow)"' + start_period: 10s + interval: 5s + timeout: 10s + retries: 10 + logging: *logging diff --git a/templates/project/providers/otel/docker/grafana/grafana.ini.tpl b/templates/project/providers/otel/docker/grafana/grafana.ini.tpl new file mode 100644 index 0000000..c21262f --- /dev/null +++ b/templates/project/providers/otel/docker/grafana/grafana.ini.tpl @@ -0,0 +1,1170 @@ +##################### Grafana Configuration Example ##################### +# +# Everything has defaults so you only need to uncomment things you want to +# change + +# possible values : production, development +;app_mode = production + +# instance name, defaults to HOSTNAME environment variable value or hostname if HOSTNAME var is empty +;instance_name = ${HOSTNAME} + +# force migration will run migrations that might cause dataloss +;force_migration = false + +#################################### Paths #################################### +[paths] +# Path to where grafana can store temp files, sessions, and the sqlite3 db (if that is used) +;data = /var/lib/grafana + +# Temporary files in `data` directory older than given duration will be removed +;temp_data_lifetime = 24h + +# Directory where grafana can store logs +;logs = /var/log/grafana + +# Directory where grafana will automatically scan and look for plugins +;plugins = /var/lib/grafana/plugins + +# folder that contains provisioning config files that grafana will apply on startup and while running. +provisioning = /etc/grafana/provisioning + +#################################### Server #################################### +[server] +# Protocol (http, https, h2, socket) +protocol = http + +# The ip address to bind to, empty will bind to all interfaces +;http_addr = + +# The http port to use +http_port = 3000 + +# The public facing domain name used to access grafana from a browser +domain = localhost + +# Redirect to correct domain if host header does not match domain +# Prevents DNS rebinding attacks +;enforce_domain = false + +# The full public facing url you use in browser, used for redirects and emails +# If you use reverse proxy and sub path specify full url (with sub path) +root_url = %(protocol)s://%(domain)s:3000/grafana/ + +# Serve Grafana from subpath specified in `root_url` setting. By default it is set to `false` for compatibility reasons. +serve_from_sub_path = true + +# Log web requests +;router_logging = false + +# the path relative working path +;static_root_path = public + +# enable gzip +;enable_gzip = false + +# https certs & key file +;cert_file = +;cert_key = + +# Unix socket path +;socket = + +# CDN Url +;cdn_url = + +# Sets the maximum time using a duration format (5s/5m/5ms) before timing out read of an incoming request and closing idle connections. +# `0` means there is no timeout for reading the request. +;read_timeout = 0 + +#################################### Database #################################### +[database] +# You can configure the database connection by specifying type, host, name, user and password +# as separate properties or as on string using the url properties. + +# Either "mysql", "postgres" or "sqlite3", it's your choice +;type = sqlite3 +;host = 127.0.0.1:3306 +;name = grafana +;user = root +# If the password contains # or ; you have to wrap it with triple quotes. Ex """#password;""" +;password = + +# Use either URL or the previous fields to configure the database +# Example: mysql://user:secret@host:port/database +;url = + +# For "postgres" only, either "disable", "require" or "verify-full" +;ssl_mode = disable + +# Database drivers may support different transaction isolation levels. +# Currently, only "mysql" driver supports isolation levels. +# If the value is empty - driver's default isolation level is applied. +# For "mysql" use "READ-UNCOMMITTED", "READ-COMMITTED", "REPEATABLE-READ" or "SERIALIZABLE". +;isolation_level = + +;ca_cert_path = +;client_key_path = +;client_cert_path = +;server_cert_name = + +# For "sqlite3" only, path relative to data_path setting +;path = grafana.db + +# Max idle conn setting default is 2 +;max_idle_conn = 2 + +# Max conn setting default is 0 (mean not set) +;max_open_conn = + +# Connection Max Lifetime default is 14400 (means 14400 seconds or 4 hours) +;conn_max_lifetime = 14400 + +# Set to true to log the sql calls and execution times. +;log_queries = + +# For "sqlite3" only. cache mode setting used for connecting to the database. (private, shared) +;cache_mode = private + +# For "mysql" only if lockingMigration feature toggle is set. How many seconds to wait before failing to lock the database for the migrations, default is 0. +;locking_attempt_timeout_sec = 0 + +################################### Data sources ######################### +[datasources] +# Upper limit of data sources that Grafana will return. This limit is a temporary configuration and it will be deprecated when pagination will be introduced on the list data sources API. +;datasource_limit = 5000 + +#################################### Cache server ############################# +[remote_cache] +# Either "redis", "memcached" or "database" default is "database" +;type = database + +# cache connectionstring options +# database: will use Grafana primary database. +# redis: config like redis server e.g. `addr=127.0.0.1:6379,pool_size=100,db=0,ssl=false`. Only addr is required. ssl may be 'true', 'false', or 'insecure'. +# memcache: 127.0.0.1:11211 +;connstr = + +#################################### Data proxy ########################### +[dataproxy] + +# This enables data proxy logging, default is false +;logging = false + +# How long the data proxy waits to read the headers of the response before timing out, default is 30 seconds. +# This setting also applies to core backend HTTP data sources where query requests use an HTTP client with timeout set. +;timeout = 30 + +# How long the data proxy waits to establish a TCP connection before timing out, default is 10 seconds. +;dialTimeout = 10 + +# How many seconds the data proxy waits before sending a keepalive probe request. +;keep_alive_seconds = 30 + +# How many seconds the data proxy waits for a successful TLS Handshake before timing out. +;tls_handshake_timeout_seconds = 10 + +# How many seconds the data proxy will wait for a server's first response headers after +# fully writing the request headers if the request has an "Expect: 100-continue" +# header. A value of 0 will result in the body being sent immediately, without +# waiting for the server to approve. +;expect_continue_timeout_seconds = 1 + +# Optionally limits the total number of connections per host, including connections in the dialing, +# active, and idle states. On limit violation, dials will block. +# A value of zero (0) means no limit. +;max_conns_per_host = 0 + +# The maximum number of idle connections that Grafana will keep alive. +;max_idle_connections = 100 + +# How many seconds the data proxy keeps an idle connection open before timing out. +;idle_conn_timeout_seconds = 90 + +# If enabled and user is not anonymous, data proxy will add X-Grafana-User header with username into the request, default is false. +;send_user_header = false + +# Limit the amount of bytes that will be read/accepted from responses of outgoing HTTP requests. +;response_limit = 0 + +# Limits the number of rows that Grafana will process from SQL data sources. +;row_limit = 1000000 + +#################################### Analytics #################################### +[analytics] +# Server reporting, sends usage counters to stats.grafana.org every 24 hours. +# No ip addresses are being tracked, only simple counters to track +# running instances, dashboard and error counts. It is very helpful to us. +# Change this option to false to disable reporting. +;reporting_enabled = true + +# The name of the distributor of the Grafana instance. Ex hosted-grafana, grafana-labs +;reporting_distributor = grafana-labs + +# Set to false to disable all checks to https://grafana.com +# for new versions of grafana. The check is used +# in some UI views to notify that a grafana update exists. +# This option does not cause any auto updates, nor send any information +# only a GET request to https://raw.githubusercontent.com/grafana/grafana/main/latest.json to get the latest version. +;check_for_updates = true + +# Set to false to disable all checks to https://grafana.com +# for new versions of plugins. The check is used +# in some UI views to notify that a plugin update exists. +# This option does not cause any auto updates, nor send any information +# only a GET request to https://grafana.com to get the latest versions. +;check_for_plugin_updates = true + +# Google Analytics universal tracking code, only enabled if you specify an id here +;google_analytics_ua_id = + +# Google Tag Manager ID, only enabled if you specify an id here +;google_tag_manager_id = + +# Rudderstack write key, enabled only if rudderstack_data_plane_url is also set +;rudderstack_write_key = + +# Rudderstack data plane url, enabled only if rudderstack_write_key is also set +;rudderstack_data_plane_url = + +# Rudderstack SDK url, optional, only valid if rudderstack_write_key and rudderstack_data_plane_url is also set +;rudderstack_sdk_url = + +# Rudderstack Config url, optional, used by Rudderstack SDK to fetch source config +;rudderstack_config_url = + +# Controls if the UI contains any links to user feedback forms +;feedback_links_enabled = true + +#################################### Security #################################### +[security] +# disable creation of admin user on first start of grafana +;disable_initial_admin_creation = false + +# default admin user, created on startup +;admin_user = admin + +# default admin password, can be changed before first start of grafana, or in profile settings +;admin_password = admin + +# used for signing +;secret_key = SW2YcwTIb9zpOOhoPsMm + +# current key provider used for envelope encryption, default to static value specified by secret_key +;encryption_provider = secretKey.v1 + +# list of configured key providers, space separated (Enterprise only): e.g., awskms.v1 azurekv.v1 +;available_encryption_providers = + +# disable gravatar profile images +;disable_gravatar = false + +# data source proxy whitelist (ip_or_domain:port separated by spaces) +;data_source_proxy_whitelist = + +# disable protection against brute force login attempts +;disable_brute_force_login_protection = false + +# set to true if you host Grafana behind HTTPS. default is false. +;cookie_secure = false + +# set cookie SameSite attribute. defaults to `lax`. can be set to "lax", "strict", "none" and "disabled" +;cookie_samesite = lax + +# set to true if you want to allow browsers to render Grafana in a ,