feat: Add k8s distro to pipelines

.github/workflows/ci-base.yaml

@@ -1,4 +1,4 @@
-name: 🧩 CI Base
+name: 🧩 CI | Base
 
 on:
   workflow_call:

.github/workflows/ci-nightly.yaml

@@ -20,8 +20,9 @@ jobs:
     strategy:
       matrix:
         distribution:
-          - nr-otel-collector
-          - nrdot-collector-host
+#          - nr-otel-collector
+#          - nrdot-collector-host
+          - nrdot-collector-k8s
     uses: ./.github/workflows/ci-base.yaml
     with:
       nightly: true
@@ -46,8 +47,9 @@ jobs:
     strategy:
       matrix:
         distribution:
-          - nr-otel-collector
-          - nrdot-collector-host
+#          - nr-otel-collector
+#          - nrdot-collector-host
+          - nrdot-collector-k8s
     steps:
       - name: Checkout
         uses: actions/checkout@v4

.github/workflows/ci.yaml

@@ -18,6 +18,7 @@ jobs:
         distribution:
           - nr-otel-collector
           - nrdot-collector-host
+          - nrdot-collector-k8s
     uses: ./.github/workflows/ci-base.yaml
     with:
       distribution: ${{ matrix.distribution }}

Makefile

@@ -16,7 +16,7 @@ TOOLS_BIN_NAMES := $(addprefix $(TOOLS_BIN_DIR)/, $(notdir $(shell echo $(TOOLS_
 GO_LICENCE_DETECTOR        := $(TOOLS_BIN_DIR)/go-licence-detector
 GO_LICENCE_DETECTOR_CONFIG   := $(SRC_ROOT)/internal/assets/license/rules.json
 
-DISTRIBUTIONS ?= "nr-otel-collector,nrdot-collector-host"
+DISTRIBUTIONS ?= "nr-otel-collector,nrdot-collector-host,nrdot-collector-k8s"
 
 ci: check build licenses-check
 check: ensure-goreleaser-up-to-date

cmd/goreleaser/internal/configure.go

@@ -44,7 +44,7 @@ var (
 	NightlyImagePrefixes = []string{EnvRegistry}
 
 	Architectures      = []string{"amd64", "arm64"}
-	DefaultConfigDists = map[string]bool{LegacyDistro: true, HostDistro: true}
+	DefaultConfigDists = map[string]bool{LegacyDistro: true, HostDistro: true, K8sDistro: true}
 	K8sDockerSkipArchs = map[string]bool{"arm": true, "386": true}
 	K8sGoos            = []string{"linux"}
 	K8sArchs           = []string{"amd64", "arm64"}

distributions/nrdot-collector-k8s/.goreleaser-nightly.yaml

@@ -1,5 +1,7 @@
 version: 2
 project_name: nrdot-collector-releases-nightly
+release:
+  disable: "true"
 builds:
   - id: nrdot-collector-k8s
     goos:
@@ -38,6 +40,8 @@ dockers:
     image_templates:
       - '{{ .Env.REGISTRY }}/nrdot-collector-k8s:{{ .Version }}-nightly-amd64'
       - '{{ .Env.REGISTRY }}/nrdot-collector-k8s:nightly-amd64'
+    extra_files:
+      - config.yaml
     build_flag_templates:
       - --pull
       - --platform=linux/amd64
@@ -54,6 +58,8 @@ dockers:
     image_templates:
       - '{{ .Env.REGISTRY }}/nrdot-collector-k8s:{{ .Version }}-nightly-arm64'
       - '{{ .Env.REGISTRY }}/nrdot-collector-k8s:nightly-arm64'
+    extra_files:
+      - config.yaml
     build_flag_templates:
       - --pull
       - --platform=linux/arm64
@@ -82,9 +88,3 @@ signs:
       - ${artifact}
     signature: ${artifact}.sig
     artifacts: all
-    certificate: ${artifact}.pem
-docker_signs:
-  - args:
-      - sign
-      - ${artifact}
-    artifacts: all

distributions/nrdot-collector-k8s/.goreleaser.yaml

@@ -1,5 +1,7 @@
 version: 2
 project_name: nrdot-collector-releases
+release:
+  disable: "true"
 builds:
   - id: nrdot-collector-k8s
     goos:
@@ -38,6 +40,8 @@ dockers:
     image_templates:
       - newrelic/nrdot-collector-k8s:{{ .Version }}-amd64
       - newrelic/nrdot-collector-k8s:latest-amd64
+    extra_files:
+      - config.yaml
     build_flag_templates:
       - --pull
       - --platform=linux/amd64
@@ -54,6 +58,8 @@ dockers:
     image_templates:
       - newrelic/nrdot-collector-k8s:{{ .Version }}-arm64
       - newrelic/nrdot-collector-k8s:latest-arm64
+    extra_files:
+      - config.yaml
     build_flag_templates:
       - --pull
       - --platform=linux/arm64
@@ -86,9 +92,3 @@ signs:
       - ${artifact}
     signature: ${artifact}.sig
     artifacts: all
-    certificate: ${artifact}.pem
-docker_signs:
-  - args:
-      - sign
-      - ${artifact}
-    artifacts: all

distributions/nrdot-collector-k8s/Dockerfile

@@ -8,6 +8,8 @@ USER ${USER_UID}
 
 COPY --from=certs /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/ca-certificates.crt
 COPY --chmod=755 nrdot-collector-k8s /nrdot-collector-k8s
+COPY config.yaml /etc/nrdot-collector-k8s/config.yaml
 ENTRYPOINT ["/nrdot-collector-k8s"]
+CMD ["--config", "/etc/nrdot-collector-k8s/config.yaml"]
 # `4137` and `4318`: OTLP
 EXPOSE 4317 4318

distributions/nrdot-collector-k8s/config.yaml

@@ -0,0 +1,242 @@
+extensions:
+  health_check:
+
+receivers:
+  otlp:
+    protocols:
+      grpc:
+      http:
+
+  hostmetrics:
+    # Default collection interval is 60s. Lower if you need finer granularity.
+    collection_interval: 60s
+    scrapers:
+      cpu:
+        metrics:
+          system.cpu.time:
+            enabled: false
+          system.cpu.utilization:
+            enabled: true
+      load:
+      memory:
+        metrics:
+          system.memory.utilization:
+            enabled: true
+      paging:
+        metrics:
+          system.paging.utilization:
+            enabled: false
+          system.paging.faults:
+            enabled: false
+      filesystem:
+        metrics:
+          system.filesystem.utilization:
+            enabled: true
+      disk:
+        metrics:
+          system.disk.merged:
+            enabled: false
+          system.disk.pending_operations:
+            enabled: false
+          system.disk.weighted_io_time:
+            enabled: false
+      network:
+        metrics:
+          system.network.connections:
+            enabled: false
+      # Uncomment to enable process metrics, which can be noisy but valuable.
+      # processes:
+      # process:
+      #  metrics:
+      #    process.cpu.utilization:
+      #      enabled: true
+      #    process.cpu.time:
+      #      enabled: false
+
+  filelog:
+    include:
+      - /var/log/alternatives.log
+      - /var/log/cloud-init.log
+      - /var/log/auth.log
+      - /var/log/dpkg.log
+      - /var/log/syslog
+      - /var/log/messages
+      - /var/log/secure
+      - /var/log/yum.log
+
+processors:
+  # group system.cpu metrics by cpu
+  metricstransform:
+    transforms:
+      - include: system.cpu.utilization
+        action: update
+        operations:
+          - action: aggregate_labels
+            label_set: [ state ]
+            aggregation_type: mean
+      - include: system.paging.operations
+        action: update
+        operations:
+          - action: aggregate_labels
+            label_set: [ direction ]
+            aggregation_type: sum
+  # remove system.cpu metrics for states
+  filter/exclude_cpu_utilization:
+    metrics:
+      datapoint:
+        - 'metric.name == "system.cpu.utilization" and attributes["state"] == "interrupt"'
+        - 'metric.name == "system.cpu.utilization" and attributes["state"] == "nice"'
+        - 'metric.name == "system.cpu.utilization" and attributes["state"] == "softirq"'
+  filter/exclude_memory_utilization:
+    metrics:
+      datapoint:
+        - 'metric.name == "system.memory.utilization" and attributes["state"] == "slab_unreclaimable"'
+        - 'metric.name == "system.memory.utilization" and attributes["state"] == "inactive"'
+        - 'metric.name == "system.memory.utilization" and attributes["state"] == "cached"'
+        - 'metric.name == "system.memory.utilization" and attributes["state"] == "buffered"'
+        - 'metric.name == "system.memory.utilization" and attributes["state"] == "slab_reclaimable"'
+  filter/exclude_memory_usage:
+    metrics:
+      datapoint:
+        - 'metric.name == "system.memory.usage" and attributes["state"] == "slab_unreclaimable"'
+        - 'metric.name == "system.memory.usage" and attributes["state"] == "inactive"'
+  filter/exclude_filesystem_utilization:
+    metrics:
+      datapoint:
+        - 'metric.name == "system.filesystem.utilization" and attributes["type"] == "squashfs"'
+  filter/exclude_filesystem_usage:
+    metrics:
+      datapoint:
+        - 'metric.name == "system.filesystem.usage" and attributes["type"] == "squashfs"'
+        - 'metric.name == "system.filesystem.usage" and attributes["state"] == "reserved"'
+  filter/exclude_filesystem_inodes_usage:
+    metrics:
+      datapoint:
+        - 'metric.name == "system.filesystem.inodes.usage" and attributes["type"] == "squashfs"'
+        - 'metric.name == "system.filesystem.inodes.usage" and attributes["state"] == "reserved"'
+  filter/exclude_system_disk:
+    metrics:
+      datapoint:
+        - 'metric.name == "system.disk.operations" and IsMatch(attributes["device"], "^loop.*") == true'
+        - 'metric.name == "system.disk.merged" and IsMatch(attributes["device"], "^loop.*") == true'
+        - 'metric.name == "system.disk.io" and IsMatch(attributes["device"], "^loop.*") == true'
+        - 'metric.name == "system.disk.io_time" and IsMatch(attributes["device"], "^loop.*") == true'
+        - 'metric.name == "system.disk.operation_time" and IsMatch(attributes["device"], "^loop.*") == true'
+  filter/exclude_system_paging:
+    metrics:
+      datapoint:
+        - 'metric.name == "system.paging.usage" and attributes["state"] == "cached"'
+        - 'metric.name == "system.paging.operations" and attributes["type"] == "cached"'
+  filter/exclude_network:
+    metrics:
+      datapoint:
+        - 'IsMatch(metric.name, "^system.network.*") == true and attributes["device"] == "lo"'
+
+  attributes/exclude_system_paging:
+    include:
+      match_type: strict
+      metric_names:
+        - system.paging.operations
+    actions:
+      - key: type
+        action: delete
+
+  cumulativetodelta:
+
+  transform/host:
+    metric_statements:
+      - context: metric
+        statements:
+          - set(description, "")
+          - set(unit, "")
+
+  transform:
+    trace_statements:
+      - context: span
+        statements:
+          - truncate_all(attributes, 4095)
+          - truncate_all(resource.attributes, 4095)
+    log_statements:
+      - context: log
+        statements:
+          - truncate_all(attributes, 4095)
+          - truncate_all(resource.attributes, 4095)
+
+  # used to prevent out of memory situations on the collector
+  memory_limiter:
+    check_interval: 1s
+    limit_mib: ${NEW_RELIC_MEMORY_LIMIT_MIB}
+
+  batch:
+
+  resourcedetection:
+    detectors: ["system"]
+    system:
+      hostname_sources: ["os"]
+      resource_attributes:
+        host.id:
+          enabled: true
+
+  resourcedetection/cloud:
+    detectors: ["gcp", "ec2", "azure"]
+    timeout: 2s
+    ec2:
+      resource_attributes:
+        host.name:
+          enabled: false
+
+  # Gives OTEL_RESOURCE_ATTRIBUTES precedence over other sources.
+  # host.id is set from env whenever the collector is orchestrated by NR Agents.
+  resourcedetection/env:
+    detectors: ["env"]
+    timeout: 2s
+    override: true
+
+exporters:
+  debug:
+  otlphttp:
+    endpoint: ${OTEL_EXPORTER_OTLP_ENDPOINT}
+    headers:
+      api-key: ${NEW_RELIC_LICENSE_KEY}
+
+service:
+  pipelines:
+    metrics/host:
+      receivers: [hostmetrics]
+      processors:
+        - memory_limiter
+        - metricstransform
+        - filter/exclude_cpu_utilization
+        - filter/exclude_memory_utilization
+        - filter/exclude_memory_usage
+        - filter/exclude_filesystem_utilization
+        - filter/exclude_filesystem_usage
+        - filter/exclude_filesystem_inodes_usage
+        - filter/exclude_system_disk
+        - filter/exclude_network
+        - attributes/exclude_system_paging
+        - transform/host
+        - resourcedetection
+        - resourcedetection/cloud
+        - resourcedetection/env
+        - cumulativetodelta
+        - batch
+      exporters: [debug, otlphttp]
+    logs/host:
+      receivers: [filelog]
+      processors: [transform, resourcedetection, resourcedetection/cloud, resourcedetection/env, batch]
+      exporters: [debug, otlphttp]
+    traces:
+      receivers: [otlp]
+      processors: [transform, resourcedetection, resourcedetection/cloud, resourcedetection/env, batch]
+      exporters: [debug, otlphttp]
+    metrics:
+      receivers: [otlp]
+      processors: [transform, resourcedetection, resourcedetection/cloud, resourcedetection/env, batch]
+      exporters: [debug, otlphttp]
+    logs:
+      receivers: [otlp]
+      processors: [transform, resourcedetection, resourcedetection/cloud, resourcedetection/env, batch]
+      exporters: [debug, otlphttp]
+
+  extensions: [health_check]