thinkharderdev commented on code in PR #146:
URL: https://github.com/apache/arrow-ballista/pull/146#discussion_r955332413


##########
ballista/rust/scheduler/src/state/task_manager.rs:
##########
@@ -376,11 +375,78 @@ impl<T: 'static + AsLogicalPlan, U: 'static + 
AsExecutionPlan> TaskManager<T, U>
         .await
     }
 
+    pub(crate) async fn cancel_job(
+        &self,
+        job_id: &str,
+        executor_manager: &ExecutorManager,
+    ) -> Result<()> {
+        let lock = self.state.lock(Keyspace::ActiveJobs, "").await?;
+
+        let running_tasks = self
+            .get_execution_graph(job_id)
+            .await
+            .map(|graph| graph.running_tasks())
+            .unwrap_or_else(|_| vec![]);
+
+        info!(
+            "Cancelling {} running tasks for job {}",
+            running_tasks.len(),
+            job_id
+        );
+
+        self.fail_job_inner(lock, job_id, "Cancelled".to_owned())
+            .await?;
+
+        let mut tasks: HashMap<&str, Vec<protobuf::PartitionId>> = 
Default::default();
+
+        for (partition, executor_id) in &running_tasks {
+            if let Some(parts) = tasks.get_mut(executor_id.as_str()) {
+                parts.push(protobuf::PartitionId {
+                    job_id: job_id.to_owned(),
+                    stage_id: partition.stage_id as u32,
+                    partition_id: partition.partition_id as u32,
+                })
+            } else {
+                tasks.insert(
+                    executor_id.as_str(),
+                    vec![protobuf::PartitionId {
+                        job_id: job_id.to_owned(),
+                        stage_id: partition.stage_id as u32,
+                        partition_id: partition.partition_id as u32,
+                    }],
+                );
+            }
+        }
+
+        for (executor_id, partitions) in tasks {
+            if let Ok(mut client) = 
executor_manager.get_client(executor_id).await {
+                client
+                    .cancel_tasks(CancelTasksParams {
+                        partition_id: partitions,
+                    })
+                    .await?;
+            } else {
+                error!("Failed to get client for executor ID {}", executor_id)
+            }
+        }
+
+        Ok(())
+    }
+

Review Comment:
   @avantgardnerio This is what is happening already. We build a 
`HashMap<ExecutorId, Vec<Task>>` and then call each executor only once with all 
tasks that need to be cancelled on that executor. 



-- 
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: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to