Abstract: Hadoop Remote Procedure Call (RPC) is increasingly used in many data centers of known technology companies such as Facebook and Yahoo together with other data center middleware centers like MapReduce, HDFS and Hbase.Due to its simplicity, efficiency, high performance use of RPC systems, it is essential to achieve dense data storage and low latency and high throughput. This thesis describes how to improve data storage, throughput, and latency performance for big data. These systems are becoming increasingly data-intensive due to the explosion of data and the need to process it, so storage management is critical to application performance in such data-intensive computing systems. Scientific applications in critical areas are becoming increasingly data-intensive. As data volumes continue to grow, the movement of data from memory to storage systems has become a critical performance bottleneck for many data-intensive stores.