Apache Flink has recently become popular as an open source framework with powerful stream and batch processing. It provides the following benefits:

• It has an actual stream processing engine: This engine can approximate batch processing, rather than the other way around. It supports event and out-of-order processing in the DataStream API, based on the dataflow model. 
• Better memory management: Apache Flink has explicit memory management that gets rid of occasional spikes, such as the one found in the Spark framework.
• Speed: It manages faster speeds by allowing for iterative processing to take place on the same node, rather than having the cluster run the nodes independently. Its performance can be further tuned by tweaking it to reprocess only the part of the data that has changed, rather than the entire set. It offers up to a five-fold boost in speed, as compared to the standard processing algorithm.
• Less configuration: It requires less configuration, as compared to state-of-the-art applications. Apache Flink has elegant and fluent APIs in Java and Scala. 
• Integrations: It has better integration with YARN, HDFS, HBase, and other components of the Apache Hadoop ecosystem.