| 摘要 |
<p>Disclosed is a method for backing up data in a Hadoop cluster, the method comprising: acquiring various application capability values of each compute node; determining from the various application capability values an application capability value having the greatest effect on the processing efficiency of the data blocks to be adjusted, and the number N of backup data blocks to be adjusted, N being an integer greater than 1; determining the first N available compute nodes of the compute nodes having the greatest effect and the greatest application capability value; and backing up the data blocks to be adjusted to the determined first N available compute nodes. The method of an embodiment of the present invention backs up data blocks to the compute nodes having the strongest data block processing capability, thus improving data processing efficiency.</p> |
