For some time, Microsoft did not offer a solution for processing big data in cloud environments. SQL Server is good for storage, but its ability to analyze terabytes of data is limited. Hadoop, which was designed for this purpose, is written in Java and was not available to .NET developers. So, Microsoft launched the Hadoop on Windows Azure service to make it possible to distribute the load and speed up big data computations.
For the research, we created eight types of queries in both languages and measured how fast they were processed. Since we wanted to test how the system would handle big data, we downloaded information on US Air Carrier Flight Delays from Windows Azure Marketplace and generated a data set of 9.15 GB.
The evaluation reveals how additional grouping parameters of the query and type of an arithmetic operation affect the throughput. It also shows the dependency between the number of MapReduce tasks and the speed of calculations. In addition, the paper contains conclusions on how the HDFS block size (8 MB, 64 MB, and 256 MB) influences performance. You will find two tables and three graphs with the findings.