Add retry_on_failure/sending_queue config to values.yaml

CHANGELOG.md

@@ -4,6 +4,10 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 ## Unreleased
 
+### Added
+
+- Add `splunkPlatform.retryOnFailure` and `splunkPlatform.sendingQueue` config options to values.yaml (#460)
+
 ## [0.52.0] - 2022-06-07
 
 ### Changed

helm-charts/splunk-otel-collector/templates/config/_common.tpl

@@ -199,6 +199,15 @@ splunk_hec/platform_logs:
     {{- if .Values.splunkPlatform.caFile }}
     ca_file: /otel/etc/splunk_platform_hec_ca_file
     {{- end }}
+  retry_on_failure:
+    enabled: {{ .Values.splunkPlatform.retryOnFailure.enabled }}
+    initial_interval: {{ .Values.splunkPlatform.retryOnFailure.initialInterval }}
+    max_interval: {{ .Values.splunkPlatform.retryOnFailure.maxInterval }}
+    max_elapsed_time: {{ .Values.splunkPlatform.retryOnFailure.maxElapsedTime }}
+  sending_queue:
+    enabled:  {{ .Values.splunkPlatform.sendingQueue.enabled }}
+    num_consumers: {{ .Values.splunkPlatform.sendingQueue.numConsumers }}
+    queue_size: {{ .Values.splunkPlatform.sendingQueue.queueSize }}
 {{- end }}
 
 {{/*
@@ -226,6 +235,15 @@ splunk_hec/platform_metrics:
     {{- if .Values.splunkPlatform.caFile }}
     ca_file: /otel/etc/splunk_platform_hec_ca_file
     {{- end }}
+  retry_on_failure:
+    enabled: {{ .Values.splunkPlatform.retryOnFailure.enabled }}
+    initial_interval: {{ .Values.splunkPlatform.retryOnFailure.initialInterval }}
+    max_interval: {{ .Values.splunkPlatform.retryOnFailure.maxInterval }}
+    max_elapsed_time: {{ .Values.splunkPlatform.retryOnFailure.maxElapsedTime }}
+  sending_queue:
+    enabled:  {{ .Values.splunkPlatform.sendingQueue.enabled }}
+    num_consumers: {{ .Values.splunkPlatform.sendingQueue.numConsumers }}
+    queue_size: {{ .Values.splunkPlatform.sendingQueue.queueSize }}
 {{- end }}
 
 {{/*

helm-charts/splunk-otel-collector/values.schema.json

@@ -92,6 +92,41 @@
               "type": "boolean"
             }
           }
+        },
+        "retryOnFailure": {
+          "description": "Retry configurations",
+          "type": "object",
+          "additionalProperties": false,
+          "properties": {
+            "enabled": {
+              "type": "boolean"
+            },
+            "initialInterval": {
+              "type": "string"
+            },
+            "maxInterval": {
+              "type": "string"
+            },
+            "maxElapsedTime": {
+              "type": "string"
+            }
+          }
+        },
+        "sendingQueue": {
+          "description": "Batching configurations for logs/traces/metrics",
+          "type": "object",
+          "additionalProperties": false,
+          "properties": {
+            "enabled": {
+              "type": "boolean"
+            },
+            "numConsumers": {
+              "type": "integer"
+            },
+            "queueSize": {
+              "type": "integer"
+            }
+          }
         }
       },
       "anyOf": [

helm-charts/splunk-otel-collector/values.yaml

@@ -75,6 +75,27 @@ splunkPlatform:
     # Boolean for keeping Otel convention fields after renaming it
     keepOtelConvention: true
 
+  # Refer to https://github.com/open-telemetry/opentelemetry-collector/blob/main/exporter/exporterhelper/README.md#configuration
+  # for detailed examples
+  retryOnFailure:
+    enabled: true
+    # Time to wait after the first failure before retrying; ignored if enabled is false
+    initialInterval: 5s
+    # The upper bound on backoff; ignored if enabled is false
+    maxInterval: 30s
+    # The maximum amount of time spent trying to send a batch; ignored if enabled is false
+    maxElapsedTime: 300s
+
+  sendingQueue:
+    enabled: true
+    # Number of consumers that dequeue batches; ignored if enabled is false
+    numConsumers: 10
+    # Maximum number of batches kept in memory before dropping; ignored if enabled is false
+    # User should calculate this as num_seconds * requests_per_second where:
+    #   num_seconds is the number of seconds to buffer in case of a backend outage
+    #   requests_per_second is the average number of requests per seconds.
+    queueSize: 5000
+
 ################################################################################
 # Splunk Observability configuration
 ################################################################################