From 9b95ecc89f3ef112de28c6561a523759803b3626 Mon Sep 17 00:00:00 2001
From: "Trez.One" <charish.patel@trez.wtf>
Date: Sun, 27 Jul 2025 16:43:47 -0400
Subject: [PATCH] OTEL config overhaul.

---
 .../signoz/otel/otel-collector-config.yaml.j2 | 122 +++++++++++++++++-
 1 file changed, 120 insertions(+), 2 deletions(-)

diff --git a/ansible/app-configs/signoz/otel/otel-collector-config.yaml.j2 b/ansible/app-configs/signoz/otel/otel-collector-config.yaml.j2
index f792d080..c3804694 100644
--- a/ansible/app-configs/signoz/otel/otel-collector-config.yaml.j2
+++ b/ansible/app-configs/signoz/otel/otel-collector-config.yaml.j2
@@ -8,6 +8,104 @@ receivers:
         endpoint: 0.0.0.0:4317
       http:
         endpoint: 0.0.0.0:4318
+  hostmetrics:
+    collection_interval: 60s  # Frequency of metrics collection.
+    scrapers:
+      cpu: {}
+      load: {}
+      memory: {}
+      disk: {}
+      filesystem: {}
+      network: {}
+  docker_stats:
+    endpoint: unix:///var/run/docker.sock
+    collection_interval: 30s
+    timeout: 10s
+    api_version: "1.51"
+    metrics:
+      container.uptime:
+        enabled: true
+      container.restarts:
+        enabled: true
+      container.network.io.usage.rx_errors:
+        enabled: true
+      container.network.io.usage.tx_errors:
+        enabled: true
+      container.network.io.usage.rx_packets:
+        enabled: true
+      container.network.io.usage.tx_packets:
+        enabled: true
+  filelog/nginx-access-logs:
+    include: ["${env:NGINX_ACCESS_LOG_FILE}"]
+    operators:
+      # Parse the default nginx access log format. Nginx defaults to the "combined" log format
+      # $remote_addr - $remote_user [$time_local] "$request" $status $body_bytes_sent "$http_referer" "$http_user_agent"
+      # For more details, see https://nginx.org/en/docs/http/ngx_http_log_module.html
+      - type: regex_parser
+        if: body matches '^(?P<remote_addr>[0-9\\.]+) - (?P<remote_user>[^\\s]+) \\[(?P<ts>.+)\\] "(?P<request_method>\\w+?) (?P<request_path>.+?)" (?P<status>[0-9]+) (?P<body_bytes_sent>[0-9]+) "(?P<http_referrer>.+?)" "(?P<http_user_agent>.+?)"$'
+        parse_from: body
+        parse_to: attributes
+        regex: '^(?P<remote_addr>[0-9\.]+) - (?P<remote_user>[^\s]+) \[(?P<ts>.+)\] "(?P<request_method>\w+?) (?P<request_path>.+?)" (?P<status>[0-9]+) (?P<body_bytes_sent>[0-9]+) "(?P<http_referrer>.+?)" "(?P<http_user_agent>.+?)"$'
+        timestamp:
+          parse_from: attributes.ts
+          layout: "02/Jan/2006:15:04:05 -0700"
+          layout_type: gotime
+        severity:
+          parse_from: attributes.status
+          overwrite_text: true
+          mapping:
+            debug: "1xx"
+            info:
+              - "2xx"
+              - "3xx"
+            warn: "4xx"
+            error: "5xx"
+      - type: remove
+        if: attributes.ts != nil
+        field: attributes.ts
+      - type: add
+        field: attributes.source
+        value: nginx
+
+  filelog/nginx-error-logs:
+    include: ["${env:NGINX_ERROR_LOG_FILE}"]
+    operators:
+      # Parse the default nginx error log format.
+      # YYYY/MM/DD HH:MM:SS [LEVEL] PID#TID: *CID MESSAGE
+      # For more details, see https://github.com/phusion/nginx/blob/master/src/core/ngx_log.c
+      - type: regex_parser
+        if: body matches '^(?P<ts>.+?) \\[(?P<log_level>\\w+)\\] (?P<pid>\\d+)#(?P<tid>\\d+). \\*(?P<cid>\\d+) (?P<message>.+)$'
+        parse_from: body
+        parse_to: attributes
+        regex: '^(?P<ts>.+?) \[(?P<log_level>\w+)\] (?P<pid>\d+)#(?P<tid>\d+). \*(?P<cid>\d+) (?P<message>.+)$'
+        timestamp:
+          parse_from: attributes.ts
+          layout: "2006/01/02 15:04:05"
+          layout_type: gotime
+        severity:
+          parse_from: attributes.log_level
+          overwrite_text: true
+          mapping:
+            debug: "debug"
+            info:
+              - "info"
+              - "notice"
+            warn: "warn"
+            error:
+              - "error"
+              - "crit"
+              - "alert"
+            fatal: "emerg"
+      - type: remove
+        if: attributes.ts != nil
+        field: attributes.ts
+      - type: move
+        if: attributes.message != nil
+        from: attributes.message
+        to: body
+      - type: add
+        field: attributes.source
+        value: nginx
   prometheus:
     config:
       global:
@@ -25,9 +123,21 @@ processors:
     send_batch_max_size: 11000
     timeout: 10s
   resourcedetection:
-    # Using OTEL_RESOURCE_ATTRIBUTES envvar, env detector adds custom labels.
     detectors: [env, system]
+    system:
+      hostname_sources: [os]
+  resourcedetection/env:
+    detectors: [env]
     timeout: 2s
+    override: false
+  resourcedetection/system:
+    detectors: ["system"]
+    system:
+      hostname_sources: ["dns", "os"]
+  resourcedetection/docker:
+    detectors: [env, docker]
+    timeout: 2s
+    override: false
   signozspanmetrics/delta:
     metrics_exporter: clickhousemetricswrite, signozclickhousemetrics
     metrics_flush_interval: 60s
@@ -78,6 +188,10 @@ exporters:
     timeout: 10s
     use_new_schema: true
   # debug: {}
+  otlp/nginx-logs:
+    endpoint: "localhost:4317"
+    tls:
+      insecure: true
 service:
   telemetry:
     logs:
@@ -93,7 +207,11 @@ service:
     metrics:
       receivers: [otlp]
       processors: [batch]
-      exporters: [clickhousemetricswrite, signozclickhousemetrics]
+      exporters: [clickhousemetricswrite, signozclickhousemetrics, resourcedetection/docker, resourcedetection/system]
+    metrics/hostmetrics:
+      receivers: [hostmetrics]
+      processors: [resourcedetection, resource/env]
+      exporters: [otlp]
     metrics/prometheus:
       receivers: [prometheus]
       processors: [batch]