dacort commented on code in PR #34225: URL: https://github.com/apache/airflow/pull/34225#discussion_r1449197109
########## airflow/providers/amazon/aws/links/emr.py: ########## @@ -66,3 +82,98 @@ def get_log_uri( return None log_uri = S3Hook.parse_s3_url(cluster_info["LogUri"]) return "/".join(log_uri) + + +class EmrServerlessLogsLink(BaseAwsLink): + """Helper class for constructing Amazon EMR Serverless Logs Link.""" + + name = "Spark Driver stdout" + key = "emr_serverless_logs" + + def get_link( + self, + operator: BaseOperator, + *, + ti_key: TaskInstanceKey, + ) -> str: + """ + Link to Amazon Web Services Console. + + :param operator: airflow operator + :param ti_key: TaskInstance ID to return link for + :return: link to external system + """ + conf = XCom.get_value(key=self.key, ti_key=ti_key) + if not conf: + return "" + hook = EmrServerlessHook(aws_conn_id=conf.get("conn_id")) + resp = hook.conn.get_dashboard_for_job_run( + applicationId=conf.get("application_id"), jobRunId=conf.get("job_run_id") + ) + o = urlparse(resp["url"]) + return o._replace(path="/logs/SPARK_DRIVER/stdout.gz").geturl() Review Comment: It is, especially given _none_ of the links show up until _all_ of the requests have finished. Some shorter timeouts would likely be good. Another option is handling specific errors (like host not found or connection failed)...but I'd rather have shorter timeouts than trying to catch specific things. -- 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: commits-unsubscr...@airflow.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org