feat: point release for telemetry module beta roll out

2024-07-16 13:32:36 +00:00 · 2024-07-16 13:32:36 +00:00 · 4b349aac76
commit 4b349aac76
parent f1f196c860
7 changed files with 160 additions and 27 deletions
--- a/admin/libhelm.sh
+++ b/admin/libhelm.sh
@ -158,9 +158,10 @@ function _helm() {
  local namespace="$(yq eval '.spec.destination.namespace' $WORKDIR/kubezero/templates/${module}.yaml)"

  targetRevision=""
+  if [ -z "$LOCAL_DEV" ]; then
    _version="$(yq eval '.spec.source.targetRevision' $WORKDIR/kubezero/templates/${module}.yaml)"
-
    [ -n "$_version" ] && targetRevision="--version $_version"
+  fi

  yq eval '.spec.source.helm.values' $WORKDIR/kubezero/templates/${module}.yaml > $WORKDIR/values.yaml

--- a/charts/kubezero-telemetry/Chart.yaml
+++ b/charts/kubezero-telemetry/Chart.yaml
@ -2,7 +2,7 @@ apiVersion: v2
 name: kubezero-telemetry
 description: KubeZero Umbrella Chart for OpenTelemetry, Jaeger etc.
 type: application
-version: 0.3.3
+version: 0.4.0
 home: https://kubezero.com
 icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
 keywords:
@ -10,6 +10,7 @@ keywords:
  - otel
  - OpenTelemetry
  - jaeger
+  - dataprepper
 maintainers:
  - name: Stefan Reimer
    email: stefan@zero-downtime.net
@ -21,6 +22,10 @@ dependencies:
    version: 0.97.1
    repository: https://open-telemetry.github.io/opentelemetry-helm-charts
    condition: opentelemetry-collector.enabled
+  - name: data-prepper
+    version: 0.1.0
+    repository: https://opensearch-project.github.io/helm-charts/
+    condition: data-prepper.enabled
  - name: jaeger
    version: 3.1.1
    repository: https://jaegertracing.github.io/helm-charts
--- a/charts/kubezero-telemetry/README.md
+++ b/charts/kubezero-telemetry/README.md
@ -1,6 +1,6 @@
 # kubezero-telemetry

-![Version: 0.3.3](https://img.shields.io/badge/Version-0.3.3-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square)
+![Version: 0.4.0](https://img.shields.io/badge/Version-0.4.0-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square)

 KubeZero Umbrella Chart for OpenTelemetry, Jaeger etc.

@ -23,6 +23,7 @@ Kubernetes: `>= 1.26.0`
 | https://fluent.github.io/helm-charts | fluentd | 0.5.2 |
 | https://jaegertracing.github.io/helm-charts | jaeger | 3.1.1 |
 | https://open-telemetry.github.io/opentelemetry-helm-charts | opentelemetry-collector | 0.97.1 |
+| https://opensearch-project.github.io/helm-charts/ | data-prepper | 0.1.0 |

 ## Values

@ -33,12 +34,13 @@ Kubernetes: `>= 1.26.0`
 | fluent-bit.config.flushInterval | int | `5` |  |
 | fluent-bit.config.input.memBufLimit | string | `"16MB"` |  |
 | fluent-bit.config.input.refreshInterval | int | `5` |  |
-| fluent-bit.config.inputs | string | `"[INPUT]\n    Name tail\n    Path /var/log/containers/*.log\n    # Exclude ourselves to current error spam, https://github.com/fluent/fluent-bit/issues/5769\n    Exclude_Path *logging-fluent-bit*\n    multiline.parser cri\n    Tag cri.*\n    Skip_Long_Lines On\n    Skip_Empty_Lines On\n    DB /var/log/flb_kube.db\n    DB.Sync Normal\n    DB.locking true\n    # Buffer_Max_Size 1M\n    {{- with .Values.config.input }}\n    Mem_Buf_Limit {{ default \"16MB\" .memBufLimit }}\n    Refresh_Interval {{ default 5 .refreshInterval }}\n    {{- end }}\n"` |  |
+| fluent-bit.config.inputs | string | `"[INPUT]\n    Name tail\n    Path /var/log/containers/*.log\n    # Exclude ourselves to current error spam, https://github.com/fluent/fluent-bit/issues/5769\n    # Todo: Rather limit / filter spam message than exclude all together -> ideally locally, next dataprepper\n    Exclude_Path *logging-fluent-bit*\n    multiline.parser cri\n    Tag cri.*\n    Skip_Long_Lines On\n    Skip_Empty_Lines On\n    DB /var/log/flb_kube.db\n    DB.Sync Normal\n    DB.locking true\n    # Buffer_Max_Size 1M\n    {{- with .Values.config.input }}\n    Mem_Buf_Limit {{ .memBufLimit }}\n    Refresh_Interval {{ .refreshInterval }}\n    {{- end }}\n\n[INPUT]\n    Name opentelemetry\n    Tag otel\n"` |  |
 | fluent-bit.config.logLevel | string | `"info"` |  |
 | fluent-bit.config.output.host | string | `"telemetry-fluentd"` |  |
 | fluent-bit.config.output.sharedKey | string | `"secretref+k8s://v1/Secret/kube-system/kubezero-secrets/telemetry.fluentd.source.sharedKey"` |  |
 | fluent-bit.config.output.tls | bool | `false` |  |
-| fluent-bit.config.outputs | string | `"[OUTPUT]\n    Match *\n    Name forward\n    Host {{ .Values.config.output.host }}\n    Port 24224\n    Shared_Key {{ .Values.config.output.sharedKey }}\n    tls {{ ternary \"on\" \"off\" .Values.config.output.tls }}\n    Send_options true\n    Require_ack_response true\n"` |  |
+| fluent-bit.config.output_otel.host | string | `"telemetry-opentelemetry-collector"` |  |
+| fluent-bit.config.outputs | string | `"[OUTPUT]\n    Match kube.*\n    Name forward\n    Host {{ .Values.config.output.host }}\n    Port 24224\n    Shared_Key {{ .Values.config.output.sharedKey }}\n    tls {{ ternary \"on\" \"off\" .Values.config.output.tls }}\n    Send_options true\n    Require_ack_response true\n\n[OUTPUT]\n    Name opentelemetry\n    Match otel\n    Host {{ .Values.config.output_otel.host }}\n    Port 4318\n    #Metrics_uri /v1/metrics\n    Traces_uri   /v1/traces\n    #Logs_uri    /v1/logs\n"` |  |
 | fluent-bit.config.service | string | `"[SERVICE]\n    Flush {{ .Values.config.flushInterval }}\n    Daemon Off\n    Log_Level {{ .Values.config.logLevel }}\n    Parsers_File parsers.conf\n    Parsers_File custom_parsers.conf\n    HTTP_Server On\n    HTTP_Listen 0.0.0.0\n    HTTP_Port {{ .Values.service.port }}\n    Health_Check On\n"` |  |
 | fluent-bit.daemonSetVolumeMounts[0].mountPath | string | `"/var/log"` |  |
 | fluent-bit.daemonSetVolumeMounts[0].name | string | `"varlog"` |  |
@ -49,10 +51,15 @@ Kubernetes: `>= 1.26.0`
 | fluent-bit.daemonSetVolumes[1].hostPath.path | string | `"/var/lib/containers/logs"` |  |
 | fluent-bit.daemonSetVolumes[1].name | string | `"newlog"` |  |
 | fluent-bit.enabled | bool | `false` |  |
+| fluent-bit.extraPorts[0].containerPort | int | `4318` |  |
+| fluent-bit.extraPorts[0].name | string | `"otel"` |  |
+| fluent-bit.extraPorts[0].port | int | `4318` |  |
+| fluent-bit.extraPorts[0].protocol | string | `"TCP"` |  |
 | fluent-bit.luaScripts."kubezero.lua" | string | `"function nest_k8s_ns(tag, timestamp, record)\n    if not record['kubernetes']['namespace_name'] then\n        return 0, 0, 0\n    end\n    new_record = {}\n    for key, val in pairs(record) do\n        if key == 'kube' then\n            new_record[key] = {}\n            new_record[key][record['kubernetes']['namespace_name']] = record[key]\n        else\n            new_record[key] = record[key]\n        end\n    end\n    return 1, timestamp, new_record\nend\n"` |  |
 | fluent-bit.resources.limits.memory | string | `"128Mi"` |  |
 | fluent-bit.resources.requests.cpu | string | `"20m"` |  |
 | fluent-bit.resources.requests.memory | string | `"48Mi"` |  |
+| fluent-bit.service.internalTrafficPolicy | string | `"Local"` |  |
 | fluent-bit.serviceMonitor.enabled | bool | `false` |  |
 | fluent-bit.testFramework.enabled | bool | `false` |  |
 | fluent-bit.tolerations[0].effect | string | `"NoSchedule"` |  |
@ -100,9 +107,6 @@ Kubernetes: `>= 1.26.0`
 | fluentd.volumes[0].secret.items[0].path | string | `"ca.crt"` |  |
 | fluentd.volumes[0].secret.secretName | string | `"telemetry-nodes-http-tls"` |  |
 | jaeger.agent.enabled | bool | `false` |  |
-| jaeger.collector.enabled | bool | `false` |  |
-| jaeger.collector.extraEnv[0].name | string | `"ES_TAGS_AS_FIELDS_ALL"` |  |
-| jaeger.collector.extraEnv[0].value | string | `"true"` |  |
 | jaeger.collector.service.otlp.grpc.name | string | `"otlp-grpc"` |  |
 | jaeger.collector.service.otlp.grpc.port | int | `4317` |  |
 | jaeger.collector.service.otlp.http.name | string | `"otlp-http"` |  |
@ -130,12 +134,8 @@ Kubernetes: `>= 1.26.0`
 | opensearch.nodeSets | list | `[]` |  |
 | opensearch.prometheus | bool | `false` |  |
 | opensearch.version | string | `"2.15.0"` |  |
-| opentelemetry-collector.config.exporters.opensearch/trace.http.auth.authenticator | string | `"basicauth/client"` |  |
-| opentelemetry-collector.config.exporters.opensearch/trace.http.endpoint | string | `"https://telemetry:9200"` |  |
-| opentelemetry-collector.config.exporters.opensearch/trace.http.tls.insecure | bool | `false` |  |
-| opentelemetry-collector.config.exporters.opensearch/trace.http.tls.insecure_skip_verify | bool | `true` |  |
-| opentelemetry-collector.config.extensions.basicauth/client.client_auth.password | string | `"admin"` |  |
-| opentelemetry-collector.config.extensions.basicauth/client.client_auth.username | string | `"admin"` |  |
+| opentelemetry-collector.config.exporters.otlp/jaeger.endpoint | string | `"telemetry-jaeger-collector:4317"` |  |
+| opentelemetry-collector.config.exporters.otlp/jaeger.tls.insecure | bool | `true` |  |
 | opentelemetry-collector.config.extensions.health_check.endpoint | string | `"${env:MY_POD_IP}:13133"` |  |
 | opentelemetry-collector.config.extensions.memory_ballast | object | `{}` |  |
 | opentelemetry-collector.config.processors.batch | object | `{}` |  |
@ -146,10 +146,9 @@ Kubernetes: `>= 1.26.0`
 | opentelemetry-collector.config.receivers.zipkin | string | `nil` |  |
 | opentelemetry-collector.config.service.extensions[0] | string | `"health_check"` |  |
 | opentelemetry-collector.config.service.extensions[1] | string | `"memory_ballast"` |  |
-| opentelemetry-collector.config.service.extensions[2] | string | `"basicauth/client"` |  |
 | opentelemetry-collector.config.service.pipelines.logs | string | `nil` |  |
 | opentelemetry-collector.config.service.pipelines.metrics | string | `nil` |  |
-| opentelemetry-collector.config.service.pipelines.traces.exporters[0] | string | `"opensearch/trace"` |  |
+| opentelemetry-collector.config.service.pipelines.traces.exporters[0] | string | `"otlp/jaeger"` |  |
 | opentelemetry-collector.config.service.pipelines.traces.processors[0] | string | `"memory_limiter"` |  |
 | opentelemetry-collector.config.service.pipelines.traces.processors[1] | string | `"batch"` |  |
 | opentelemetry-collector.config.service.pipelines.traces.receivers[0] | string | `"otlp"` |  |
--- a/charts/kubezero-telemetry/values.yaml
+++ b/charts/kubezero-telemetry/values.yaml
@ -1,3 +1,109 @@
+data-prepper:
+  enabled: false
+
+  securityContext:
+    capabilities:
+      drop:
+      - ALL
+    #readOnlyRootFilesystem: true
+    #runAsNonRoot: true
+    #runAsUser: 1000
+
+  pipelineConfig:
+    config:
+      simple-sample-pipeline: null
+      otel-trace-pipeline:
+        workers: 1
+        delay: "100"
+        source:
+          otel_trace_source:
+            ssl: false
+        buffer:
+          bounded_blocking:
+            # default value is 12800
+            #buffer_size: 25600
+            # Default is 200.
+            # Make sure buffer_size >= workers * batch_size
+            #batch_size: 400
+        sink:
+          - pipeline:
+              name: "raw-traces-pipeline"
+          - pipeline:
+              name: "otel-service-map-pipeline"
+      raw-traces-pipeline:
+        workers: 1
+        delay: 3000
+        source:
+          pipeline:
+            name: "otel-trace-pipeline"
+        buffer:
+          bounded_blocking:
+            #buffer_size: 25600
+            #batch_size: 400
+        processor:
+          - otel_traces:
+          - otel_trace_group:
+              hosts: [ "https://telemetry:9200" ]
+              insecure: true
+              username: "admin"
+              password: "admin"
+        sink:
+          - opensearch:
+              hosts: ["https://telemetry:9200"]
+              username: "admin"
+              password: "admin"
+              insecure: true
+              index_type: trace-analytics-raw
+      otel-service-map-pipeline:
+        workers: 1
+        delay: 3000
+        source:
+          pipeline:
+            name: "otel-trace-pipeline"
+        processor:
+          - service_map:
+              # The window duration is the maximum length of time the data prepper stores the most recent trace data to evaluvate service-map relationships.
+              # The default is 3 minutes, this means we can detect relationships between services from spans reported in last 3 minutes.
+              # Set higher value if your applications have higher latency.
+              window_duration: 180
+        buffer:
+            bounded_blocking:
+              #buffer_size: 25600
+              #batch_size: 400
+        sink:
+          - opensearch:
+              hosts: ["https://telemetry:9200"]
+              username: "admin"
+              password: "admin"
+              insecure: true
+              index_type: trace-analytics-service-map
+              #index: otel-v1-apm-span-%{yyyy.MM.dd}
+              #max_retries: 20
+              bulk_size: 4
+
+  config:
+    log4j2-rolling.properties: |
+      status = error
+      dest = err
+      name = PropertiesConfig
+
+      appender.console.type = Console
+      appender.console.name = STDOUT
+      appender.console.layout.type = PatternLayout
+      appender.console.layout.pattern = %d{ISO8601} [%t] %-5p %40C - %m%n
+
+      rootLogger.level = warn
+      rootLogger.appenderRef.stdout.ref = STDOUT
+
+      logger.pipeline.name = org.opensearch.dataprepper.pipeline
+      logger.pipeline.level = info
+
+      logger.parser.name = org.opensearch.dataprepper.parser
+      logger.parser.level = info
+
+      logger.plugins.name = org.opensearch.dataprepper.plugins
+      logger.plugins.level = info
+
 opentelemetry-collector:
  enabled: false

@ -17,6 +123,10 @@ opentelemetry-collector:
        endpoint: telemetry-jaeger-collector:4317
        tls:
          insecure: true
+      otlp/data-prepper:
+        endpoint: telemetry-data-prepper:21890
+        tls:
+          insecure: true

    processors:
      batch: {}
@ -45,6 +155,7 @@ opentelemetry-collector:
        traces:
          exporters:
            - otlp/jaeger
+            - otlp/data-prepper
          processors:
            - memory_limiter
            - batch
@ -83,12 +194,9 @@ jaeger:
        grpc:
          name: otlp-grpc
          port: 4317
-   #    http:
-   #      name: otlp-http
-   #      port: 4318
-   #extraEnv:
-   #  - name: ES_TAGS_AS_FIELDS_ALL
-   #    value: "true"
+        http:
+          name: otlp-http
+          port: 4318
    serviceMonitor:
      enabled: false

@ -103,6 +211,9 @@ jaeger:
      cmdlineParams:
        es.tls.enabled: ""
        es.tls.skip-host-verify: ""
+        es.num-replicas: 1
+        es.num-shards: 2
+        #es.tags-as-fields.all: ""

  provisionDataStore:
    cassandra: false
--- a/charts/kubezero/Chart.yaml
+++ b/charts/kubezero/Chart.yaml
@ -2,7 +2,7 @@ apiVersion: v2
 name: kubezero
 description: KubeZero - Root App of Apps chart
 type: application
-version: 1.28.9-1
+version: 1.28.9-2
 home: https://kubezero.com
 icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
 keywords:
--- a/charts/kubezero/templates/telemetry.yaml
+++ b/charts/kubezero/templates/telemetry.yaml
@ -21,6 +21,23 @@ fluentd:
      enabled: {{ .Values.metrics.enabled }}
 {{- end }}

+{{- if index .Values "telemetry" "data-prepper" }}
+data-prepper:
+  {{- with index .Values "telemetry" "data-prepper" }}
+  {{- toYaml . | nindent 2 }}
+  {{- end }}
+{{- end }}
+
+{{- if index .Values "telemetry" "opentelemetry-collector" }}
+opentelemetry-collector:
+  {{- with index .Values "telemetry" "opentelemetry-collector" }}
+  {{- toYaml . | nindent 2 }}
+  {{- end }}
+
+  serviceMonitor:
+    enabled: {{ .Values.metrics.enabled }}
+{{- end }}
+
 {{- if .Values.telemetry.jaeger }}
 jaeger:
  {{- with .Values.telemetry.jaeger }}
--- a/charts/kubezero/values.yaml
+++ b/charts/kubezero/values.yaml
@ -85,12 +85,12 @@ falco:
 telemetry:
  enabled: false
  namespace: telemetry
-  targetRevision: 0.3.0
+  targetRevision: 0.4.0

 operators:
  enabled: false
  namespace: operators
-  targetRevision: 0.1.3
+  targetRevision: 0.1.4

 metrics:
  enabled: false