job to another JobManager in case the original JobManager disappears. • Flink relies on Apache ZooKeeper for high-availability • coordination and consensus services, e.g. leader election • The JobManager required metadata, such as the application’s JAR file, into a remote persistent storage system • Zookeeper also holds state handles and checkpoint locations 5 JobManager failures ??? Vasiliki Kalavri The new JobManager performs the following steps: 1. It requests the storage locations from ZooKeeper to fetch the JobGraph, the JAR file, and the state handles of the last checkpoint from remote

18 20:43 flink-scala_2.12-1.15.2.jar # -rw-r--r-- 1 dianfu staff 10M 10 18 20:43 flink-shaded-zookeeper-3.5.9.jar # -rw-r--r-- 1 dianfu staff 15M 10 18 20:43 flink-table-api-java-uber-1.15.2.jar # -rw-r--r-- 19 16:02 flink-scala_2.12-1.15.2.jar -rw-r--r-- 1 duanchen staff 10M Oct 19 16:02 flink-shaded-zookeeper-3.5.9.jar -rw-r--r-- 1 duanchen staff 15M Oct 19 16:02 flink-table-api-java-uber-1.15.2.jar -rw-r--r--

18 20:43 flink-scala_2.12-1.15.2.jar # -rw-r--r-- 1 dianfu staff 10M 10 18 20:43 flink-shaded-zookeeper-3.5.9.jar # -rw-r--r-- 1 dianfu staff 15M 10 18 20:43 flink-table-api-java-uber-1.15.2.jar # -rw-r--r-- 19 16:02 flink-scala_2.12-1.15.2.jar -rw-r--r-- 1 duanchen staff 10M Oct 19 16:02 flink-shaded-zookeeper-3.5.9.jar -rw-r--r-- 1 duanchen staff 15M Oct 19 16:02 flink-table-api-java-uber-1.15.2.jar -rw-r--r--