[GitHub] [arrow-ballista] andygrove commented on a diff in pull request #261: Task level retry and Stage level retry

[GitBox]

andygrove commented on code in PR #261:
URL: https://github.com/apache/arrow-ballista/pull/261#discussion_r984067609


##########
ballista/rust/core/proto/ballista.proto:
##########
@@ -424,54 +424,87 @@ message ExecutionGraph {
   uint64 output_partitions = 5;
   repeated PartitionLocation output_locations = 6;
   string scheduler_id = 7;
+  uint32 tid_gen = 8;
+  repeated StageAttempts failed_attempts = 9;
+}
+
+message StageAttempts {
+  uint32 stage_id = 1;
+  repeated uint32 stage_attempt_num = 2;
 }
 
 message ExecutionGraphStage {
   oneof StageType {
       UnResolvedStage unresolved_stage = 1;
       ResolvedStage resolved_stage = 2;
-      CompletedStage completed_stage = 3;
+      SuccessfulStage successful_stage = 3;
       FailedStage failed_stage = 4;
   }
 }
 
 message UnResolvedStage {
-  uint64 stage_id = 1;
-  PhysicalHashRepartition output_partitioning = 2;
-  repeated uint32 output_links = 3;
-  repeated  GraphStageInput inputs = 4;
-  bytes plan = 5;
-}
-
-message ResolvedStage {
-  uint64 stage_id = 1;
-  uint32 partitions = 2;
+  uint32 stage_id = 1;
+  uint32 stage_attempt_num = 2;
   PhysicalHashRepartition output_partitioning = 3;
   repeated uint32 output_links = 4;
   repeated  GraphStageInput inputs = 5;
   bytes plan = 6;
+  repeated string last_attempt_failure_reasons = 7;
 }
 
-message CompletedStage {
-  uint64 stage_id = 1;
-  uint32 partitions = 2;
-  PhysicalHashRepartition output_partitioning = 3;
-  repeated uint32 output_links = 4;
-  repeated  GraphStageInput inputs = 5;
-  bytes plan = 6;
-  repeated TaskStatus task_statuses = 7;
-  repeated OperatorMetricsSet stage_metrics = 8;
+message ResolvedStage {
+  uint32 stage_id = 1;
+  uint32 stage_attempt_num = 2;
+  uint32 partitions = 3;
+  PhysicalHashRepartition output_partitioning = 4;
+  repeated uint32 output_links = 5;
+  repeated  GraphStageInput inputs = 6;
+  bytes plan = 7;
+  repeated string last_attempt_failure_reasons = 8;
+}
+
+message SuccessfulStage {
+  uint32 stage_id = 1;
+  uint32 stage_attempt_num = 2;
+  uint32 partitions = 3;
+  PhysicalHashRepartition output_partitioning = 4;
+  repeated uint32 output_links = 5;
+  repeated  GraphStageInput inputs = 6;
+  bytes plan = 7;
+  repeated TaskInfo task_infos = 8;
+  repeated OperatorMetricsSet stage_metrics = 9;
 }
 
 message FailedStage {
-  uint64 stage_id = 1;
-  uint32 partitions = 2;
-  PhysicalHashRepartition output_partitioning = 3;
-  repeated uint32 output_links = 4;
-  bytes plan = 5;
-  repeated TaskStatus task_statuses = 6;
-  repeated OperatorMetricsSet stage_metrics = 7;
-  string error_message = 8;
+  uint32 stage_id = 1;
+  uint32 stage_attempt_num = 2;
+  uint32 partitions = 3;

Review Comment:
   Same issue here with changing tag numbers.



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: github-unsubscr...@arrow.apache.org

For queries about this service, please contact Infrastructure at:
us...@infra.apache.org