Tsz-wo Sze created HDDS-2270: -------------------------------- Summary: Avoid buffer copying in ContainerStateMachine.loadSnapshot/persistContainerSet Key: HDDS-2270 URL: https://issues.apache.org/jira/browse/HDDS-2270 Project: Hadoop Distributed Data Store Issue Type: Improvement Components: Ozone Datanode Reporter: Tsz-wo Sze Assignee: Tsz-wo Sze
ContainerStateMachine: - In loadSnapshot(..), it first reads the snapshotFile to a byte[] and then parses it to ContainerProtos.Container2BCSIDMapProto. The buffer copying can be avoided. {code} try (FileInputStream fin = new FileInputStream(snapshotFile)) { byte[] container2BCSIDData = IOUtils.toByteArray(fin); ContainerProtos.Container2BCSIDMapProto proto = ContainerProtos.Container2BCSIDMapProto .parseFrom(container2BCSIDData); ... } {code} - persistContainerSet(..) has similar problem. -- This message was sent by Atlassian Jira (v8.3.4#803005) --------------------------------------------------------------------- To unsubscribe, e-mail: hdfs-dev-unsubscr...@hadoop.apache.org For additional commands, e-mail: hdfs-dev-h...@hadoop.apache.org