refactor(keel): use SpinnakerRetrofitErrorHandler with KeelService

This PR lays the foundational work for upgrading the retrofit version to 2.x, specifically focusing on refactoring the exception handling for KeelService The tests modified as part of this PR will verify the new changes with the scenarios:- Reading the Http error response body and building the TaskResult by instantiating SpringHttpError. Note, there's a behaviour change on the Task Results error message format when KeelService API throws any 4xx/5xx http errors with empty error body. - On any 4xx http errors with empty error body: before: 11:56:19.324 [Test worker] ERROR com.netflix.spinnaker.orca.keel.task.ImportDeliveryConfigTask - {message=Non-retryable HTTP response 400 received from downstream service: HTTP 400 http://localhost:62130/delivery-configs/: 400 Bad Request} after: 12:00:02.018 [Test worker] ERROR com.netflix.spinnaker.orca.keel.task.ImportDeliveryConfigTask - {message=Non-retryable HTTP response 400 received from downstream service: HTTP 400 http://localhost:62275/delivery-configs/: Status: 400, URL: http://localhost:62275/delivery-configs/, Message: Bad Request} - On any 5xx http errors with empty error body: before: TaskResult(status=RUNNING, context={repoType=stash, projectKey=SPKR, repositorySlug=keeldemo, directory=., manifest=spinnaker.yml, ref=refs/heads/master, attempt=2, maxRetries=5, errorFromLastAttempt=Retryable HTTP response 500 received from downstream service: HTTP 500 http://localhost:65311/delivery-configs/: 500 Server Error}, outputs={}) after: TaskResult(status=RUNNING, context={repoType=stash, projectKey=SPKR, repositorySlug=keeldemo, directory=., manifest=spinnaker.yml, ref=refs/heads/master, attempt=1, maxRetries=5, errorFromLastAttempt=Retryable HTTP response 500 received from downstream service: HTTP 500 http://localhost:49862/delivery-configs/: Status: 500, URL: http://localhost:49862/delivery-configs/, Message: Server Error}, outputs={})
spinnaker · Feb 23, 2024 · f7a03fb · f7a03fb
1 parent 6ff93fb
commit f7a03fb
Show file tree

Hide file tree

Showing 5 changed files with 115 additions and 2 deletions.
diff --git a/...rc/main/groovy/com/netflix/spinnaker/orca/applications/tasks/DeleteApplicationTask.groovy b/...rc/main/groovy/com/netflix/spinnaker/orca/applications/tasks/DeleteApplicationTask.groovy
@@ -18,6 +18,8 @@ package com.netflix.spinnaker.orca.applications.tasks
 
 import com.fasterxml.jackson.databind.ObjectMapper
 import com.netflix.spinnaker.kork.dynamicconfig.DynamicConfigService
+import com.netflix.spinnaker.kork.retrofit.exceptions.SpinnakerHttpException
+import com.netflix.spinnaker.kork.retrofit.exceptions.SpinnakerServerException
 import com.netflix.spinnaker.orca.api.pipeline.TaskResult
 import com.netflix.spinnaker.orca.api.pipeline.models.ExecutionStatus
 import com.netflix.spinnaker.orca.front50.Front50Service
@@ -93,6 +95,15 @@ class DeleteApplicationTask extends AbstractFront50Task {
       }
       log.error("Could not delete application", e)
       return TaskResult.builder(ExecutionStatus.TERMINAL).outputs(outputs).build()
+    } catch (SpinnakerHttpException httpException){
+      if (httpException.responseCode == 404) {
+        return TaskResult.SUCCEEDED
+      }
+      log.error("Could not delete application", httpException)
+      return TaskResult.builder(ExecutionStatus.TERMINAL).outputs(outputs).build()
+    } catch (SpinnakerServerException serverException) {
+      log.error("Could not delete application", serverException)
+      return TaskResult.builder(ExecutionStatus.TERMINAL).outputs(outputs).build()
     }
     return TaskResult.builder(ExecutionStatus.SUCCEEDED).outputs(outputs).build()
   }

diff --git a/orca-keel/orca-keel.gradle b/orca-keel/orca-keel.gradle
@@ -24,6 +24,7 @@ dependencies {
   implementation("com.fasterxml.jackson.module:jackson-module-kotlin")
   implementation("org.springframework:spring-web")
   implementation("org.springframework.boot:spring-boot-autoconfigure")
+  implementation("io.spinnaker.kork:kork-retrofit")
 
   testImplementation("com.fasterxml.jackson.module:jackson-module-kotlin")
   testImplementation("dev.minutest:minutest")

diff --git a/orca-keel/src/main/kotlin/com/netflix/spinnaker/orca/config/KeelConfiguration.kt b/orca-keel/src/main/kotlin/com/netflix/spinnaker/orca/config/KeelConfiguration.kt
@@ -22,6 +22,7 @@ import com.fasterxml.jackson.module.kotlin.KotlinModule
 import com.jakewharton.retrofit.Ok3Client
 import com.netflix.spinnaker.config.DefaultServiceEndpoint
 import com.netflix.spinnaker.config.okhttp3.OkHttpClientProvider
+import com.netflix.spinnaker.kork.retrofit.exceptions.SpinnakerRetrofitErrorHandler
 import com.netflix.spinnaker.orca.KeelService
 import com.netflix.spinnaker.orca.jackson.OrcaObjectMapper
 import org.springframework.beans.factory.annotation.Value
@@ -60,6 +61,7 @@ class KeelConfiguration {
       .setEndpoint(keelEndpoint)
       .setClient(Ok3Client(clientProvider.getClient(DefaultServiceEndpoint("keel", keelEndpoint.url))))
       .setLogLevel(retrofitLogLevel)
+      .setErrorHandler(SpinnakerRetrofitErrorHandler.getInstance())
       .setConverter(JacksonConverter(keelObjectMapper))
       .build()
       .create(KeelService::class.java)

diff --git a/orca-keel/src/main/kotlin/com/netflix/spinnaker/orca/keel/task/ImportDeliveryConfigTask.kt b/orca-keel/src/main/kotlin/com/netflix/spinnaker/orca/keel/task/ImportDeliveryConfigTask.kt
@@ -19,6 +19,9 @@ package com.netflix.spinnaker.orca.keel.task
 import com.fasterxml.jackson.databind.ObjectMapper
 import com.fasterxml.jackson.module.kotlin.convertValue
 import com.fasterxml.jackson.module.kotlin.readValue
+import com.netflix.spinnaker.kork.retrofit.exceptions.SpinnakerHttpException
+import com.netflix.spinnaker.kork.retrofit.exceptions.SpinnakerNetworkException
+import com.netflix.spinnaker.kork.retrofit.exceptions.SpinnakerServerException
 import com.netflix.spinnaker.kork.web.exceptions.InvalidRequestException
 import com.netflix.spinnaker.orca.KeelService
 import com.netflix.spinnaker.orca.api.pipeline.RetryableTask
@@ -77,6 +80,8 @@ constructor(
       TaskResult.builder(ExecutionStatus.SUCCEEDED).context(emptyMap<String, Any?>()).build()
     } catch (e: RetrofitError) {
       handleRetryableFailures(e, context)
+    } catch (e: SpinnakerServerException) {
+      handleRetryableFailures(e, context)
     } catch (e: Exception) {
       log.error("Unexpected exception while executing {}, aborting.", javaClass.simpleName, e)
       buildError(e.message ?: "Unknown error (${e.javaClass.simpleName})")
@@ -153,6 +158,65 @@ constructor(
       ?: ""}/${context.manifest}@${context.ref}"
   }
 
+  /*
+  * Handle (potentially) all Spinnaker*Exception. Smart casts to the respective type on Http error and/or Network error.
+  * @return default error message on non-http and non-network errors.
+  * */
+  private fun handleRetryableFailures(error: SpinnakerServerException, context: ImportDeliveryConfigContext): TaskResult {
+    return when {
+      error is SpinnakerNetworkException -> {
+        // retry if unable to connect
+        buildRetry(
+          context,
+          "Network error talking to downstream service, attempt ${context.attempt} of ${context.maxRetries}: ${error.networkErrorMessage}"
+        )
+      }
+      error is SpinnakerHttpException -> {
+        handleRetryableFailures(error, context)
+      } else -> {
+        buildRetry(
+          context,
+          "Server error talking to downstream service, attempt ${context.attempt} of ${context.maxRetries}: ${error.serverErrorMessage}"
+        )
+      }
+    }
+  }
+
+  /**
+   * Handle (potentially) retryable failures by looking at the HTTP status code. A few 4xx errors
+   * are handled as special cases to provide more friendly error messages to the UI.
+   */
+  private fun handleRetryableFailures(httpException: SpinnakerHttpException, context: ImportDeliveryConfigContext): TaskResult{
+    return when {
+      httpException.responseCode in 400..499 -> {
+        val responseBody = httpException.responseBody
+        // just give up on 4xx errors, which are unlikely to resolve with retries, but give users a hint about 401
+        // errors from igor/scm, and attempt to parse keel errors (which are typically more informative)
+        buildError(
+          if (httpException.fromIgor && httpException.responseCode == 401) {
+            UNAUTHORIZED_SCM_ACCESS_MESSAGE
+          } else if (httpException.fromKeel && responseBody!=null && responseBody.isNotEmpty()) {
+            // keel's errors should use the standard Spring format
+            try {
+              SpringHttpError(responseBody.get("error") as String, responseBody.get("status") as Int, responseBody.get("message") as? String, Instant.ofEpochMilli(responseBody.get("timestamp") as Long), responseBody.get("details") as? Map<String, Any?>)
+            } catch (_: Exception) {
+              "Non-retryable HTTP response ${httpException.responseCode} received from downstream service: ${httpException.httpErrorMessage}"
+            }
+          } else {
+            "Non-retryable HTTP response ${httpException.responseCode} received from downstream service: ${httpException.httpErrorMessage}"
+          }
+        )
+      }
+      else -> {
+        // retry on other status codes
+        buildRetry(
+          context,
+          "Retryable HTTP response ${httpException.responseCode} received from downstream service: ${httpException.httpErrorMessage}"
+        )
+      }
+    }
+  }
+
   /**
    * Handle (potentially) retryable failures by looking at the retrofit error type or HTTP status code. A few 40x errors
    * are handled as special cases to provide more friendly error messages to the UI.
@@ -240,18 +304,45 @@ constructor(
       "$message: ${cause?.message ?: ""}"
     }
 
+  val SpinnakerHttpException.httpErrorMessage: String
+    get() {
+      return "HTTP ${responseCode} ${url}: ${cause?.message ?: message}"
+    }
+
+  val SpinnakerNetworkException.networkErrorMessage: String
+    get() {
+      return "$message: ${cause?.message ?: ""}"
+    }
+
+  val SpinnakerServerException.serverErrorMessage: String
+    get() {
+      return "$message"
+    }
+
   val RetrofitError.fromIgor: Boolean
     get() {
       val parsedUrl = URL(url)
       return parsedUrl.host.contains("igor") || parsedUrl.port == 8085
     }
 
+  val SpinnakerServerException.fromIgor: Boolean
+    get() {
+      val parsedUrl = URL(url)
+      return parsedUrl.host.contains("igor") || parsedUrl.port == 8085
+    }
+
   val RetrofitError.fromKeel: Boolean
     get() {
       val parsedUrl = URL(url)
       return parsedUrl.host.contains("keel") || parsedUrl.port == 8087
     }
 
+  val SpinnakerServerException.fromKeel: Boolean
+    get() {
+      val parsedUrl = URL(url)
+      return parsedUrl.host.contains("keel") || parsedUrl.port == 8087
+    }
+
   data class ImportDeliveryConfigContext(
     var repoType: String? = null,
     var projectKey: String? = null,

diff --git a/...keel/src/test/java/com/netflix/spinnaker/orca/keel/task/ImportDeliveryConfigTaskTest.java b/...keel/src/test/java/com/netflix/spinnaker/orca/keel/task/ImportDeliveryConfigTaskTest.java
@@ -32,6 +32,7 @@
 import com.github.tomakehurst.wiremock.http.Fault;
 import com.github.tomakehurst.wiremock.junit5.WireMockExtension;
 import com.github.tomakehurst.wiremock.junit5.WireMockRuntimeInfo;
+import com.netflix.spinnaker.kork.retrofit.exceptions.SpinnakerRetrofitErrorHandler;
 import com.netflix.spinnaker.okhttp.SpinnakerRequestInterceptor;
 import com.netflix.spinnaker.orca.KeelService;
 import com.netflix.spinnaker.orca.api.pipeline.TaskResult;
@@ -88,6 +89,7 @@ static void setupOnce(WireMockRuntimeInfo wmRuntimeInfo) {
             .setRequestInterceptor(new SpinnakerRequestInterceptor(true))
             .setEndpoint(wmRuntimeInfo.getHttpBaseUrl())
             .setClient(okClient)
+            .setErrorHandler(SpinnakerRetrofitErrorHandler.getInstance())
             .setLogLevel(retrofitLogLevel)
             .setConverter(new JacksonConverter(objectMapper))
             .build()
@@ -197,7 +199,11 @@ public void testTaskResultWhenErrorBodyIsEmpty() {
         String.format(
             "Non-retryable HTTP response %s received from downstream service: %s",
             HttpStatus.BAD_REQUEST.value(),
-            "HTTP 400 " + wireMock.baseUrl() + "/delivery-configs/: 400 Bad Request");
+            "HTTP 400 "
+                + wireMock.baseUrl()
+                + "/delivery-configs/: Status: 400, URL: "
+                + wireMock.baseUrl()
+                + "/delivery-configs/, Message: Bad Request");
 
     var errorMap = new HashMap<>();
     errorMap.put("message", expectedMessage);
@@ -226,7 +232,9 @@ public void testTaskResultWhenHttp5xxErrorIsThrown() {
         "errorFromLastAttempt",
         "Retryable HTTP response 500 received from downstream service: HTTP 500 "
             + wireMock.baseUrl()
-            + "/delivery-configs/: 500 Server Error");
+            + "/delivery-configs/: Status: 500, URL: "
+            + wireMock.baseUrl()
+            + "/delivery-configs/, Message: Server Error");
 
     TaskResult running = TaskResult.builder(ExecutionStatus.RUNNING).context(contextMap).build();