| 摘要 |
The present invention provides a distributed computing system which includes: multiple slave units which distribute and store multiple data blocks, a master unit which divides one data into the data blocks, supplies each of the data blocks to at least one slave unit, manages the distribution storage information of the data blocks, and processes an access request to data by a client, and an optimization unit which produces a target value to set an operation environment which represents target performance by repetitively changing each value of one or more performance parameter values of the slave units and the master unit until the operation environment to represent each target performance of the slave units and the master unit is set. According to an embodiment of the present invention, the burden of a system administrator is reduced and big data is quickly and efficiently processed. |
