mTCP: A high-performance user-level TCP stack for multicore systems

Besides adopting well-known techniques, our mTCP stack (1) translates expensive system calls to shared memory access between two threads within the same CPU core, (2) allows efficient flow-level event aggregation, and (3) performs batch processing of RX/TX packets for high I/O efficiency. (e.g., ~80% inside kernel for lighttpd) Even worse, these CPU cycles are not utilized effectively; according to our measurements, Linux spends more than 4x the cycles than mTCP in handling the same number of TCP transactions. Students: EunYoung Jeong, Shinae Woo, Muhammad Asim Jamshed, and Haewon Jeong

Faculty: KyoungSoo Park, Dongsu Han, and Sunghwan Ihm

We are collectively reached by our mailing list: mtcp-user at list.ndsl.kaist.edu.

Source: shader.kaist.edu