Nephele: Bridging DDR–CXL Latency Gaps with Benefit-Aware Caching for In-Memory Databases on Hybrid Memory

In-memory databases rely on DDR memory for performance, yet capacity scaling is impeded by physical constraints and the high cost of high-density DIMMs. Compute Express Link (CXL) provides a practical path for memory expansion through a DDR-compatible interface. However, CXL memory exhibits inferior latency and bandwidth, thus naïve expansion with CXL can lead to significant performance degradation. In hybrid DDR–CXL systems, traditional caching policies (e.g., LRU, S3-FIFO) yield limited reductions in execution latency while incurring substantial metadata management and tuple migration overheads. Our analysis reveals a fundamental misalignment between traditional design assumptions and heterogeneous memory characteristics. To address this, we propose Nephele, a lightweight, benefit-aware caching policy for hybrid DDR–CXL databases. Nephele shifts the focus from eviction selection to effective admission, prioritizing data that are truly worth caching. It also features a low-overhead architecture that supports randomized eviction without relying on global metadata. By integrating epoch-based hotness estimation, Nephele enables probabilistic, benefit-aware admission, reducing cross-tier data movement and mitigating cache pollution. Evaluated on a hybrid DDR–CXL database prototype using YCSB and TPC-C, Nephele achieves up to 1.58× higher throughput than CXL-Expansion and up to 3.2× over existing caching policies, while retaining up to 97% of DDR-only performance. Additional integration with RocksDB further confirms its practical feasibility in a production system. These results demonstrate that lightweight, benefit-aware caching is critical for fully exploiting CXL-enabled memory expansion.