SCOR-KV: SIMD-Aware Client-Centric and Optimistic RDMA-Based Key-Value Store for Emerging CPU Architectures
SCOR-KV: SIMD-Aware Client-Centric and Optimistic RDMA-Based Key-Value Store for Emerging CPU Architectures
复制标题
DOI：
10.1109/hipc.2019.00040
复制
发表时间：
2019-12
期刊：
影响因子：
--
通讯作者：
Dipti Shankar;Xiaoyi Lu;D. Panda
中科院分区：
文献类型：
--
作者：
Dipti Shankar;Xiaoyi Lu;D. Panda
现代基于键值存储的分布式应用程序依赖于像“Multi-Get”（MGet）这样的批量读取操作来加速其数据服务阶段。虽然最先进的数据库系统使用基于simd的技术来优化其内存结构（如哈希表）上的数据并行操作，但它们尚未适应于高性能rdma加速键值（KV）存储。在本文中，我们提出了一种为新兴的多核CPU架构设计高性能simd感知KV存储的整体方法。为此，我们首先对利用AVX-512矢量化并行哈希表设计与最先进的高性能键值存储（如RDMA-Memcached）所涉及的机遇和挑战进行了深入研究。在此基础上，我们提出了一种基于SIMD的以客户端为中心的乐观的基于RDMA的键值存储，SCOR-KV，它最佳地利用“RDMA+SIMD”来加速读取繁重的MGet操作。score -KV提出了一种具有simd意识的KV存储友好哈希表布局，它利用了垂直矢量化的n向杜鹃哈希表设计和乐观的KV对查找方案。为了补充这一点，我们提出了rdma优化的simd感知MGet通信协议，该协议将服务器端的预处理/后处理开销转移到客户端，同时实现最佳的端到端性能。我们对最新的英特尔Skylake cpu和IB EDR互连的性能评估表明，我们提出的SCOR-KV可以在服务器端Get吞吐量方面实现高达3.7-8.6倍的改进。通过我们的simd感知RDMA方案，与运行在最先进的cpu优化MemC3哈希表设计上的RDMA- memcached设计相比，scr - kv还可以将读取繁重的YCSB工作负载的Multi-Get延迟提高约2.2倍。
Modern distributed key-value store-based applications rely on bulk-read operations like 'Multi-Get' (MGet) to accelerate their data serving phase. While state-of-the-art database systems employ SIMD-based techniques to optimize data-parallel operations on their in-memory structures, such as hash-tables, they have not been adapted into high-performance RDMA-accelerated key-value (KV) stores. In this paper, we present a holistic approach to designing high-performance SIMD-aware KV stores for emerging multi-core CPU architectures. Towards this, we first perform an in-depth study of the opportunities and challenges involved in leveraging AVX-512 vectorization-based parallel hash table designs with a state-of-the-art high-performance key-value store like RDMA-Memcached. Based on this, we propose a SIMD-Aware Client-Centric and Optimistic RDMA-based Key-Value Store, SCOR-KV, that optimally exploits 'RDMA+SIMD' to accelerate read-heavy MGet operations. SCOR-KV presents an SIMD-conscious KV store friendly hash table layout, that leverages the vertically vectorized N-way cuckoo hash table design with optimistic KV pair lookup schemes. To complement this, we propose RDMA-optimized SIMD-aware MGet communication protocols that offload the server-side pre-/post-processing overheads to the client, while enabling optimal end-to-end performance. Our performance evaluations over the latest Intel Skylake CPUs and IB EDR interconnects show that our proposed SCOR-KV can achieve up to 3.7-8.6x improvement in server-side Get throughput. Through our SIMD-aware RDMA schemes, SCOR-KV can also improve Multi-Get latencies for read-heavy YCSB workloads by about 2.2x, as compared to the RDMA-Memcached design running over the state-of-the-art CPU-optimized MemC3 hash table design.