CINDA: Using Cache-Coherent Interconnects for Accelerating Databases by Enabling Near-Data Processing of Update Transactions

Near-Data Processing (NDP) has been proven useful to accelerate Database Management Systems (DBMS) that handle infrequently accessed data stored in slow persistent storage. A key challenge for such an architecture is the synchronization of host-based and NDP operations, which require fine-grained interactions especially when the NDP device can also update (modify) the DBMS data autonomously. <p xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">This paper introduces CINDA, the first full-stack computational storage capable of accelerating <i>both</i> read and update (write) database transactions using NDP. The proposed system relies on a hybrid host-device interface to enable the DBMS accessing persisted data, offloading computation to the storage device, and coordinating concurrent device-update operations with the host-update ones. A hybrid interface utilizes a cache-coherent inter-connect such as CCIX or CXL for low-latency synchronization using a shared-lock table, and PCIe DMA for high-throughput bulk I/O. We evaluated the effectiveness of the proposed approach in a CCIX-based system by realizing an FPGA-based NDP-capable computational storage device and customizing an NDP-capable DBMS based on PostgreSQL to support update NDP operations. Our full-stack evaluation using the YCSB benchmark demonstrates that CINDA can deliver ≈4.2× end-to-end speedup when executing long-running update transactions directly on the storage device, while the host DBMS performs frequent short updates.