Simple console tracing

packages/cli/src/lib/defaults/infra-modules/tracer/alerts.yml

@@ -0,0 +1,11 @@
+groups:
+- name: ExampleCPULoadGroup
+  rules:
+  - alert: HighCpuLoad
+    expr: system_cpu_load_average_1m > 0.1
+    for: 0m
+    labels:
+      severity: warning
+    annotations:
+      summary: High CPU load
+      description: "CPU load is > 0.1\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

packages/cli/src/lib/defaults/infra-modules/tracer/clickhouse-users.xml

@@ -0,0 +1,123 @@
+<?xml version="1.0"?>
+<clickhouse>
+    <!-- See also the files in users.d directory where the settings can be overridden. -->
+
+    <!-- Profiles of settings. -->
+    <profiles>
+        <!-- Default settings. -->
+        <default>
+            <!-- Maximum memory usage for processing single query, in bytes. -->
+            <max_memory_usage>10000000000</max_memory_usage>
+
+            <!-- How to choose between replicas during distributed query processing.
+                 random - choose random replica from set of replicas with minimum number of errors
+                 nearest_hostname - from set of replicas with minimum number of errors, choose replica
+                  with minimum number of different symbols between replica's hostname and local hostname
+                  (Hamming distance).
+                 in_order - first live replica is chosen in specified order.
+                 first_or_random - if first replica one has higher number of errors, pick a random one from replicas with minimum number of errors.
+            -->
+            <load_balancing>random</load_balancing>
+        </default>
+
+        <!-- Profile that allows only read queries. -->
+        <readonly>
+            <readonly>1</readonly>
+        </readonly>
+    </profiles>
+
+    <!-- Users and ACL. -->
+    <users>
+        <!-- If user name was not specified, 'default' user is used. -->
+        <default>
+            <!-- See also the files in users.d directory where the password can be overridden.
+
+                 Password could be specified in plaintext or in SHA256 (in hex format).
+
+                 If you want to specify password in plaintext (not recommended), place it in 'password' element.
+                 Example: <password>qwerty</password>.
+                 Password could be empty.
+
+                 If you want to specify SHA256, place it in 'password_sha256_hex' element.
+                 Example: <password_sha256_hex>65e84be33532fb784c48129675f9eff3a682b27168c0ea744b2cf58ee02337c5</password_sha256_hex>
+                 Restrictions of SHA256: impossibility to connect to ClickHouse using MySQL JS client (as of July 2019).
+
+                 If you want to specify double SHA1, place it in 'password_double_sha1_hex' element.
+                 Example: <password_double_sha1_hex>e395796d6546b1b65db9d665cd43f0e858dd4303</password_double_sha1_hex>
+
+                 If you want to specify a previously defined LDAP server (see 'ldap_servers' in the main config) for authentication,
+                  place its name in 'server' element inside 'ldap' element.
+                 Example: <ldap><server>my_ldap_server</server></ldap>
+
+                 If you want to authenticate the user via Kerberos (assuming Kerberos is enabled, see 'kerberos' in the main config),
+                  place 'kerberos' element instead of 'password' (and similar) elements.
+                 The name part of the canonical principal name of the initiator must match the user name for authentication to succeed.
+                 You can also place 'realm' element inside 'kerberos' element to further restrict authentication to only those requests
+                  whose initiator's realm matches it.
+                 Example: <kerberos />
+                 Example: <kerberos><realm>EXAMPLE.COM</realm></kerberos>
+
+                 How to generate decent password:
+                 Execute: PASSWORD=$(base64 < /dev/urandom | head -c8); echo "$PASSWORD"; echo -n "$PASSWORD" | sha256sum | tr -d '-'
+                 In first line will be password and in second - corresponding SHA256.
+
+                 How to generate double SHA1:
+                 Execute: PASSWORD=$(base64 < /dev/urandom | head -c8); echo "$PASSWORD"; echo -n "$PASSWORD" | sha1sum | tr -d '-' | xxd -r -p | sha1sum | tr -d '-'
+                 In first line will be password and in second - corresponding double SHA1.
+            -->
+            <password></password>
+
+            <!-- List of networks with open access.
+
+                 To open access from everywhere, specify:
+                    <ip>::/0</ip>
+
+                 To open access only from localhost, specify:
+                    <ip>::1</ip>
+                    <ip>127.0.0.1</ip>
+
+                 Each element of list has one of the following forms:
+                 <ip> IP-address or network mask. Examples: 213.180.204.3 or 10.0.0.1/8 or 10.0.0.1/255.255.255.0
+                     2a02:6b8::3 or 2a02:6b8::3/64 or 2a02:6b8::3/ffff:ffff:ffff:ffff::.
+                 <host> Hostname. Example: server01.clickhouse.com.
+                     To check access, DNS query is performed, and all received addresses compared to peer address.
+                 <host_regexp> Regular expression for host names. Example, ^server\d\d-\d\d-\d\.clickhouse\.com$
+                     To check access, DNS PTR query is performed for peer address and then regexp is applied.
+                     Then, for result of PTR query, another DNS query is performed and all received addresses compared to peer address.
+                     Strongly recommended that regexp is ends with $
+                 All results of DNS requests are cached till server restart.
+            -->
+            <networks>
+                <ip>::/0</ip>
+            </networks>
+
+            <!-- Settings profile for user. -->
+            <profile>default</profile>
+
+            <!-- Quota for user. -->
+            <quota>default</quota>
+
+            <!-- User can create other users and grant rights to them. -->
+            <!-- <access_management>1</access_management> -->
+        </default>
+    </users>
+
+    <!-- Quotas. -->
+    <quotas>
+        <!-- Name of quota. -->
+        <default>
+            <!-- Limits for time interval. You could specify many intervals with different limits. -->
+            <interval>
+                <!-- Length of interval. -->
+                <duration>3600</duration>
+
+                <!-- No limits. Just calculate resource usage for time interval. -->
+                <queries>0</queries>
+                <errors>0</errors>
+                <result_rows>0</result_rows>
+                <read_rows>0</read_rows>
+                <execution_time>0</execution_time>
+            </interval>
+        </default>
+    </quotas>
+</clickhouse>

packages/cli/src/lib/defaults/infra-modules/tracer/docker-compose.yaml

@@ -0,0 +1,70 @@
+version: "2.4"
+
+services:
+  clickhouse:
+    image: clickhouse/clickhouse-server:22.4.5-alpine
+    tty: true
+    volumes:
+      - ./clickhouse-config.xml:/etc/clickhouse-server/config.xml
+      - ./clickhouse-users.xml:/etc/clickhouse-server/users.xml
+      - ./data/clickhouse/:/var/lib/clickhouse/
+    restart: on-failure
+    logging:
+      options:
+        max-size: 50m
+        max-file: "3"
+    healthcheck:
+      test: ["CMD", "wget", "--spider", "-q", "localhost:8123/ping"]
+      interval: 30s
+      timeout: 5s
+      retries: 3
+
+  query-service:
+    image: signoz/query-service:0.10.0
+    container_name: query-service
+    command: ["-config=/root/config/prometheus.yml"]
+    volumes:
+      - ./prometheus.yml:/root/config/prometheus.yml
+      - ./dashboards:/root/config/dashboards
+      - ./data/signoz/:/var/lib/signoz/
+    environment:
+      - ClickHouseUrl=tcp://clickhouse:9000/?database=signoz_traces
+      - STORAGE=clickhouse
+      - GODEBUG=netdns=go
+      - TELEMETRY_ENABLED=true
+      - DEPLOYMENT_TYPE=docker-standalone-amd
+    restart: on-failure
+    healthcheck:
+      test: ["CMD", "wget", "--spider", "-q", "localhost:8080/api/v1/version"]
+      interval: 30s
+      timeout: 5s
+      retries: 3
+    depends_on:
+      clickhouse:
+        condition: service_healthy
+
+  frontend:
+    image: signoz/frontend:0.10.0
+    container_name: frontend
+    restart: on-failure
+    depends_on:
+      - query-service
+    ports:
+      - "3301:3301"
+    volumes:
+      - ./nginx-config.conf:/etc/nginx/conf.d/default.conf
+
+  otel-collector:
+    image: signoz/otelcontribcol:0.45.1-1.1
+    command: ["--config=/etc/otel-collector-config.yaml"]
+    volumes:
+      - ./otel-collector-config.yaml:/etc/otel-collector-config.yaml
+    environment:
+      - OTEL_RESOURCE_ATTRIBUTES=host.name=signoz-host,os.type=linux
+    ports:
+      - "4318:4318"     # OTLP HTTP receiver
+    mem_limit: 2000m
+    restart: on-failure
+    depends_on:
+      clickhouse:
+        condition: service_healthy

packages/cli/src/lib/defaults/infra-modules/tracer/nginx-config.conf

@@ -0,0 +1,42 @@
+server {
+    listen       3301;
+    server_name  _;
+
+    gzip on;
+    gzip_static on;    
+    gzip_types text/plain text/css application/json application/x-javascript text/xml application/xml application/xml+rss text/javascript;
+    gzip_proxied  any;
+    gzip_vary on;
+    gzip_comp_level 6;
+    gzip_buffers 16 8k;
+    gzip_http_version 1.1;
+
+    # to handle uri issue 414 from nginx
+    client_max_body_size 24M;
+
+    large_client_header_buffers 8 16k;
+
+    location / {
+        if ( $uri = '/index.html' ) {
+            add_header Cache-Control no-store always;
+        }
+        root   /usr/share/nginx/html;
+        index  index.html index.htm;
+        try_files $uri $uri/ /index.html;
+    }
+
+    #location /api/alertmanager {
+    #    proxy_pass http://alertmanager:9093/api/v2;
+    #}
+
+    location /api {
+        proxy_pass http://query-service:8080/api;
+    }
+
+    # redirect server error pages to the static page /50x.html
+    #
+    error_page   500 502 503 504  /50x.html;
+    location = /50x.html {
+        root   /usr/share/nginx/html;
+    }
+}

packages/cli/src/lib/defaults/infra-modules/tracer/otel-collector-config.yaml

@@ -0,0 +1,115 @@
+receivers:
+  opencensus:
+    endpoint: 0.0.0.0:55678
+  otlp/spanmetrics:
+    protocols:
+      grpc:
+        endpoint: localhost:12345
+  otlp:
+    protocols:
+      grpc:
+        endpoint: 0.0.0.0:4317
+      http:
+        endpoint: 0.0.0.0:4318
+        cors:
+          allowed_origins:
+          - http://*
+          - https://*
+  jaeger:
+    protocols:
+      grpc:
+        endpoint: 0.0.0.0:14250
+      thrift_http:
+        endpoint: 0.0.0.0:14268
+      # thrift_compact:
+      #   endpoint: 0.0.0.0:6831
+      # thrift_binary:
+      #   endpoint: 0.0.0.0:6832
+  hostmetrics:
+    collection_interval: 60s
+    scrapers:
+      cpu: {}
+      load: {}
+      memory: {}
+      disk: {}
+      filesystem: {}
+      network: {}
+
+processors:
+  batch:
+    send_batch_size: 10000
+    send_batch_max_size: 11000
+    timeout: 10s
+  signozspanmetrics/prometheus:
+    metrics_exporter: prometheus
+    latency_histogram_buckets: [100us, 1ms, 2ms, 6ms, 10ms, 50ms, 100ms, 250ms, 500ms, 1000ms, 1400ms, 2000ms, 5s, 10s, 20s, 40s, 60s ]
+    dimensions_cache_size: 10000
+    dimensions:
+      - name: service.namespace
+        default: default
+      - name: deployment.environment
+        default: default
+  # memory_limiter:
+  #   # 80% of maximum memory up to 2G
+  #   limit_mib: 1500
+  #   # 25% of limit up to 2G
+  #   spike_limit_mib: 512
+  #   check_interval: 5s
+  #
+  #   # 50% of the maximum memory
+  #   limit_percentage: 50
+  #   # 20% of max memory usage spike expected
+  #   spike_limit_percentage: 20
+  # queued_retry:
+  #   num_workers: 4
+  #   queue_size: 100
+  #   retry_on_failure: true
+  resourcedetection:
+    # Using OTEL_RESOURCE_ATTRIBUTES envvar, env detector adds custom labels.
+    detectors: [env, system] # include ec2 for AWS, gce for GCP and azure for Azure.
+    timeout: 2s
+    override: false
+
+extensions:
+  health_check:
+    endpoint: 0.0.0.0:13133
+  zpages:
+    endpoint: 0.0.0.0:55679
+  pprof:
+    endpoint: 0.0.0.0:1777
+
+exporters:
+  clickhousetraces:
+    datasource: tcp://clickhouse:9000/?database=signoz_traces
+  clickhousemetricswrite:
+    endpoint: tcp://clickhouse:9000/?database=signoz_metrics
+    resource_to_telemetry_conversion:
+      enabled: true
+  prometheus:
+    endpoint: 0.0.0.0:8889
+  # logging: {}
+
+service:
+  telemetry:
+    metrics:
+      address: 0.0.0.0:8888
+  extensions:
+    - health_check
+    - zpages
+    - pprof
+  pipelines:
+    traces:
+      receivers: [jaeger, otlp]
+      processors: [signozspanmetrics/prometheus, batch]
+      exporters: [clickhousetraces]
+    metrics:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [clickhousemetricswrite]
+    metrics/hostmetrics:
+      receivers: [hostmetrics]
+      processors: [resourcedetection, batch]
+      exporters: [clickhousemetricswrite]
+    metrics/spanmetrics:
+      receivers: [otlp/spanmetrics]
+      exporters: [prometheus]

packages/cli/src/lib/defaults/infra-modules/tracer/prometheus.yml

@@ -0,0 +1,24 @@
+# my global config
+global:
+  scrape_interval:     5s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
+  evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
+  # scrape_timeout is set to the global default (10s).
+
+# Alertmanager configuration
+alerting:
+  alertmanagers:
+  - static_configs:
+    - targets:
+      - alertmanager:9093
+
+# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
+rule_files:
+  - 'alerts.yml'
+
+# A scrape configuration containing exactly one endpoint to scrape:
+# Here it's Prometheus itself.
+scrape_configs:
+
+
+remote_read:
+  - url: tcp://clickhouse:9000/?database=signoz_metrics