Reverse mappings help the system continue to perform and scale well when large applications are placing huge memory demands on the kernel and multiple processes are sharing memory.
当大型应用程序向内核请求大量内存和多个进程共享内存时，反向映射帮助系统继续有效地运行和扩展。
2
Clearly, all three solutions present limitations and the conventional buffer memory management approach is not a good mechanism for coding large-scale interacting software.
The reason is that a program written with MPI is supposed to scale to a large number of processors, and a large number of processors never have Shared memory.