GFS scales by adding ChunkServers to the cluster. The master gradually moves data from existing ChunkServers to the newly added servers. Since the master stores all metadata in memory (for faster operations), GFS is limited by how much memory the master has. At Google, this is not a serious problem in practice as the master maintains less than 64 bytes of metadata for each 64 MB chunk, but as the system has grown in usage, problems have emerged with the centralized master scheme.Despite the separation of control and data flow and the performance optimization of the master, it is emerging as a bottleneck in the design. Despite the reduced amount of metadata (because of the large chunk size), the amount of metadata stored by the master is increasing to a level where it is getting difficult to keep all the metadata in main memory.