From d38c580556cd41086a8553b8e9a34fa91fba4195 Mon Sep 17 00:00:00 2001
From: Vibhu Pandey <vibhupandey28@gmail.com>
Date: Thu, 19 Sep 2024 19:41:02 +0530
Subject: [PATCH] fix(k8s-infra): enable k8sattributes to match other
 information (#488)

## Summary
#### **New Features**
- Introduced a new `k8snode` detector to add k8s.node.uid for
hostmetrics.
- Updated logging configuration to the new streamlined container parser
for better maintainability.

#### **Fixes**
- The removal of k8s.pod.uid and k8s.pod.ip attributes and the inclusion
of k8s.node.name attribute instead should resolve the interference issue
with the k8sprocessor and improve its ability to match and enrich
telemetry data accurately.

#### **Chores**
- Incremented Helm chart version and OpenTelemetry collector image
version for new features and improvements.
---
 charts/k8s-infra/Chart.yaml                   |  4 +-
 charts/k8s-infra/templates/_config.tpl        |  4 +
 .../templates/otel-agent/daemonset.yaml       |  2 +-
 charts/k8s-infra/values.yaml                  | 95 ++-----------------
 4 files changed, 17 insertions(+), 88 deletions(-)

diff --git a/charts/k8s-infra/Chart.yaml b/charts/k8s-infra/Chart.yaml
index 03e3fe2b..6aa9841f 100644
--- a/charts/k8s-infra/Chart.yaml
+++ b/charts/k8s-infra/Chart.yaml
@@ -2,8 +2,8 @@ apiVersion: v2
 name: k8s-infra
 description: Helm chart for collecting metrics and logs in K8s
 type: application
-version: 0.11.11
-appVersion: "0.88.0"
+version: 0.11.12
+appVersion: "0.109.0"
 home: https://signoz.io
 icon: https://signoz.io/img/SigNozLogo-orange.svg
 keywords:
diff --git a/charts/k8s-infra/templates/_config.tpl b/charts/k8s-infra/templates/_config.tpl
index 20fc1076..6a7dbec1 100644
--- a/charts/k8s-infra/templates/_config.tpl
+++ b/charts/k8s-infra/templates/_config.tpl
@@ -364,6 +364,10 @@ processors:
   resourcedetection/internal:
     detectors:
       - env
+      - k8snode
+    k8snode:
+      node_from_env_var: K8S_NODE_NAME
+      auth_type: serviceAccount
     timeout: {{ .Values.presets.resourceDetectionInternal.timeout }}
     override: {{ .Values.presets.resourceDetectionInternal.override }}
 {{- end }}
diff --git a/charts/k8s-infra/templates/otel-agent/daemonset.yaml b/charts/k8s-infra/templates/otel-agent/daemonset.yaml
index c53f5aa6..35ad201c 100644
--- a/charts/k8s-infra/templates/otel-agent/daemonset.yaml
+++ b/charts/k8s-infra/templates/otel-agent/daemonset.yaml
@@ -99,7 +99,7 @@ spec:
             - name: SIGNOZ_COMPONENT
               value: {{ default "otel-agent" .Values.otelAgent.name }}
             - name: OTEL_RESOURCE_ATTRIBUTES
-              {{- $attribs := "signoz.component=$(SIGNOZ_COMPONENT),k8s.cluster.name=$(K8S_CLUSTER_NAME),k8s.pod.uid=$(K8S_POD_UID),k8s.pod.ip=$(K8S_POD_IP)" }}
+              {{- $attribs := "signoz.component=$(SIGNOZ_COMPONENT),k8s.cluster.name=$(K8S_CLUSTER_NAME),k8s.node.name=$(K8S_NODE_NAME)" }}
               {{- if .Values.presets.resourceDetection.envResourceAttributes }}
               {{- $attribs = printf "%s,%s" $attribs .Values.presets.resourceDetection.envResourceAttributes }}
               {{- end }}
diff --git a/charts/k8s-infra/values.yaml b/charts/k8s-infra/values.yaml
index 67021893..bfaa427b 100644
--- a/charts/k8s-infra/values.yaml
+++ b/charts/k8s-infra/values.yaml
@@ -123,88 +123,8 @@ presets:
       containers: []
       additionalInclude: []
     operators:
-      # Find out which format is used by kubernetes
-      - type: router
-        id: get-format
-        routes:
-          - output: parser-docker
-            expr: 'body matches "^\\{"'
-          - output: parser-crio
-            expr: 'body matches "^[^ Z]+ "'
-          - output: parser-containerd
-            expr: 'body matches "^[^ Z]+Z"'
-      # Parse CRI-O format
-      - type: regex_parser
-        id: parser-crio
-        regex: '^(?P<time>[^ Z]+) (?P<stream>stdout|stderr) (?P<logtag>[^ ]*) ?(?P<log>.*)$'
-        output: extract_metadata_from_filepath
-        timestamp:
-          parse_from: attributes.time
-          layout_type: gotime
-          layout: '2006-01-02T15:04:05.000000000-07:00'
-      # Parse CRI-Containerd format
-      - type: regex_parser
-        id: parser-containerd
-        regex: '^(?P<time>[^ ^Z]+Z) (?P<stream>stdout|stderr) (?P<logtag>[^ ]*) ?(?P<log>.*)$'
-        output: extract_metadata_from_filepath
-        timestamp:
-          parse_from: attributes.time
-          layout: '%Y-%m-%dT%H:%M:%S.%LZ'
-      # Parse Docker format
-      - type: json_parser
-        id: parser-docker
-        output: extract_metadata_from_filepath
-        timestamp:
-          parse_from: attributes.time
-          layout: '%Y-%m-%dT%H:%M:%S.%LZ'
-      # Extract metadata from file path
-      - type: regex_parser
-        id: extract_metadata_from_filepath
-        regex: '^.*\/(?P<namespace>[^_]+)_(?P<pod_name>[^_]+)_(?P<uid>[a-f0-9\-]+)\/(?P<container_name>[^\._]+)\/(?P<restart_count>\d+)\.log$'
-        parse_from: attributes["log.file.path"]
-        output: add_cluster_name
-      # Add cluster name attribute from environment variable
-      - id: add_cluster_name
-        type: add
-        field: resource["k8s.cluster.name"]
-        value: EXPR(env("K8S_CLUSTER_NAME"))
-        output: move_stream
-      # Rename attributes
-      - type: move
-        id: move_stream
-        from: attributes.stream
-        to: attributes["log.iostream"]
-        output: move_container_name
-      - type: move
-        id: move_container_name
-        from: attributes.container_name
-        to: resource["k8s.container.name"]
-        output: move_namespace
-      - type: move
-        id: move_namespace
-        from: attributes.namespace
-        to: resource["k8s.namespace.name"]
-        output: move_pod_name
-      - type: move
-        id: move_pod_name
-        from: attributes.pod_name
-        to: resource["k8s.pod.name"]
-        output: move_restart_count
-      - type: move
-        id: move_restart_count
-        from: attributes.restart_count
-        to: resource["k8s.container.restart_count"]
-        output: move_uid
-      - type: move
-        id: move_uid
-        from: attributes.uid
-        to: resource["k8s.pod.uid"]
-        output: move_log
-      # Clean up log body
-      - type: move
-        id: move_log
-        from: attributes.log
-        to: body
+      - id: container-parser
+        type: container
   hostMetrics:
     enabled: true
     collectionInterval: 30s
@@ -262,11 +182,16 @@ presets:
     # -- Which pod/namespace metadata to extract from a list of default metadata fields.
     extractMetadatas:
       - k8s.namespace.name
+      - k8s.deployment.name
+      - k8s.statefulset.name
+      - k8s.daemonset.name
+      - k8s.cronjob.name
+      - k8s.job.name
+      - k8s.node.name
+      - k8s.node.uid
       - k8s.pod.name
       - k8s.pod.uid
       - k8s.pod.start_time
-      - k8s.deployment.name
-      - k8s.node.name
   clusterMetrics:
     enabled: true
     collectionInterval: 30s
@@ -316,7 +241,7 @@ otelAgent:
   image:
     registry: docker.io
     repository: otel/opentelemetry-collector-contrib
-    tag: 0.88.0
+    tag: 0.109.0
     pullPolicy: IfNotPresent
 
   # -- Image Registry Secret Names for OtelAgent.