RR-Compound: RDMA-Fused gRPC for Low Latency and High Throughput With an Easy Interface

远程直接内存访问 计算机科学 吞吐量 接口(物质) 低延迟(资本市场) 延迟(音频) 并行计算 计算机硬件 操作系统 计算机网络 电信 气泡 最大气泡压力法 无线
作者
Liang Geng,Hao Wang,Jingsong Meng,Dayi Fan,Sami Ben-Romdhane,Hari Kadayam Pichumani,Vinay Phegade,X Zhang
出处
期刊:IEEE Transactions on Parallel and Distributed Systems [Institute of Electrical and Electronics Engineers]
卷期号:35 (8): 1488-1505
标识
DOI:10.1109/tpds.2024.3404394
摘要

Advanced data centers strive for high performance and throughput, which can be achieved through the desirable merits of Remote Procedure Call (RPC) programming model and the low latency of Remote Direct Memory Access (RDMA). However, despite the widespread availability of these software and hardware utilities, they have been utilized separately for their own applications in existing production systems for many years. Although researchers have attempted to develop RDMA-enabled RPC prototypes, they often face challenges such as API discrepancies and a lack of specific features for effective integration with major production software, rendering them incompatible. This industry R&D project aims to enhance the performance of gRPC, a widely utilized RPC framework in major companies, by integrating RDMA as an internal component. Our system solution, called, combines the simple user interface and other merits of gRPC with low latency for remote data accesses. RR-Compound is fully compatible with gRPC and can serve as a seamless replacement without altering existing applications. However, to achieve low latency, high throughput, and scalability for RR-Compound, several technical challenges in managing network connections and memory space utilization must be effectively addressed. To overcome the limitations of existing connection methods, we have developed a new method called BPEV that is independent of gRPC and applicable to all RDMA systems. We have also retained the asynchronous framework of gRPC, albeit with limited buffer space in RDMA memory management. In micro-benchmarks, RR-Compound outperforms mRPC - the state-of-the-art RPC framework for a large number of connections, achieving a 14.77% increase in throughput and a 42.55% reduction in latency. Subsequently, we compare RR-Compound with gRPC over IPoIB using two real-world applications: KV-Store and TensorFlow. RR-Compound achieves up to a 2.35x increase in throughput and reduces the average latency by 46.92%.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
xiaofei应助Tonypig采纳,获得30
刚刚
月亮发布了新的文献求助10
1秒前
包凡之发布了新的文献求助20
1秒前
agentsmith发布了新的文献求助10
1秒前
1秒前
张慢慢完成签到,获得积分10
2秒前
彩虹的微笑发布了新的文献求助500
2秒前
annafan完成签到,获得积分10
3秒前
科目三应助小瑞采纳,获得10
3秒前
大个应助czj采纳,获得10
4秒前
5秒前
天天快乐应助shJ采纳,获得10
5秒前
桐桐应助小小廖采纳,获得10
5秒前
蓝色完成签到,获得积分10
5秒前
领导范儿应助actor2006采纳,获得10
6秒前
华西招生版完成签到,获得积分10
6秒前
6秒前
6秒前
耍酷如柏完成签到,获得积分10
6秒前
啊姚爱学习完成签到,获得积分10
8秒前
9秒前
bkagyin应助研友_Z7mqzL采纳,获得10
9秒前
正直画笔发布了新的文献求助10
9秒前
9秒前
赘婿应助annafan采纳,获得10
9秒前
Imran完成签到,获得积分10
9秒前
wanci应助11111采纳,获得10
9秒前
奔跑917完成签到,获得积分10
10秒前
Li梨发布了新的文献求助10
11秒前
1234发布了新的文献求助10
11秒前
闪闪凝冬完成签到,获得积分10
13秒前
JayL完成签到,获得积分10
13秒前
但行好事发布了新的文献求助10
14秒前
科研通AI6.3应助张慢慢采纳,获得10
15秒前
小巧十三完成签到,获得积分10
15秒前
科研通AI6.1应助xszhang采纳,获得10
15秒前
小瑞发布了新的文献求助10
15秒前
16秒前
狡猾的DNA完成签到,获得积分10
17秒前
20秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
PowerCascade: A Synthetic Dataset for Cascading Failure Analysis in Power Systems 2000
Picture this! Including first nations fiction picture books in school library collections 1500
Signals, Systems, and Signal Processing 610
Unlocking Chemical Thinking: Reimagining Chemistry Teaching and Learning 555
Photodetectors: From Ultraviolet to Infrared 500
Cancer Targets: Novel Therapies and Emerging Research Directions (Part 1) 400
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 物理 内科学 复合材料 催化作用 物理化学 光电子学 电极 细胞生物学 基因 无机化学
热门帖子
关注 科研通微信公众号,转发送积分 6359264
求助须知:如何正确求助?哪些是违规求助? 8173237
关于积分的说明 17213576
捐赠科研通 5414355
什么是DOI,文献DOI怎么找? 2865433
邀请新用户注册赠送积分活动 1842799
关于科研通互助平台的介绍 1690962