In current architectures, page tables are the fundamental mechanism that allows contemporary OSs to isolate user processes, binding each thread to a specific page table. A thread cannot therefore directly call another process's function or access its data; instead, the OS kernel provides data communication primitives and mediates process synchronization through inter-process communication (IPC) channels, which impede system performance. Alternatively, the recently proposed CODOMs architecture provides memory protection across software modules. Threads can cross module protection boundaries inside the same process using simple procedure calls, while preserving memory isolation. We present dIPC (for "direct IPC"), an OS extension that repurposes and extends the CODOMs architecture to allow threads to cross process boundaries. It maps processes into a shared address space, and eliminates the OS kernel from the critical path of inter-process communication. dIPC is 64.12× faster than local remote procedure calls (RPCs), and 8.87× faster than IPC in the L4 microkernel. We show that applying dIPC to a multi-tier OLTP web server improves performance by up to 5.12× (2.13× on average), and reaches over 94% of the ideal system efficiency.

We thank Diego Marr´on for helping with MariaDB, the anonymous reviewers for their feedback and, especially, Andrew Baumann for helping us improve the paper. This research was partially funded by HiPEAC through a collaboration grant for Lluís Vilanova (agreement number 687698 for the EU’s Horizon2020 research and innovation programme), the Israel Science Fundation (ISF grant 769/12) and the Israeli Ministry of Science, Technology and Space.

Peer Reviewed