Monitoring Copy on write (COW) faults to control zero-copy data transfer

摘要

The method transfers data from an application program memory to a network stack using zero-copy data transfer. The number of potential copy on write (COW) faults is monitored (step 213) during this transfer. If the number of potential COW faults exceeds a predetermined threshold for that application, then, in subsequent data transfers the data is copied to another memory location before transferring the data to the network stack, and zero-copy data transfer is not used. Thus the system has a learning state 211 to determine when to zero-copy data. It is particularly applicable to transferring data between an application program layer and a socket layer in a Unix (r.t.m.) operating system.