| 引用本文: | 舒俊宜,黄小龙,马郓,李浩源,黄罡,刘譞哲,金鑫,梅宏.基于服务器无感知计算的对象存储跨云复制系统.软件学报,,():1-16 |
| |
|
| |
|
|
| 本文已被：浏览 291次 下载 122次 |
码上扫一扫！ |
|
|
| 基于服务器无感知计算的对象存储跨云复制系统 |
|
舒俊宜1,2, 黄小龙1,2, 马郓2, 李浩源2,3, 黄罡1,2, 刘譞哲1,2, 金鑫1,2, 梅宏1,2
|
|
1.北京大学 计算机学院, 北京 100871;2.高可信软件技术教育部重点实验室(北京大学) , 北京 100871;3.北京开元维度科技有限公司, 北京 100080
|
|
| 摘要: |
| 对象存储是云计算环境下最常用的存储方案之一. 将对象存储中的数据复制到一个或多个云区域能够提升其可靠性和可用性, 并降低用户的访问延迟. 对象存储复制系统需要保障副本间的一致性并尽可能降低复制时延. 现有的开源跨云区域对象存储复制系统Skyplane尽管能支持主流云平台间的对象数据复制, 但无法保障数据一致性, 且在动态负载下复制时延较高. 为了实现动态负载下的低成本、低延迟对象数据复制, 提出基于服务器无感知计算的对象存储跨云复制系统FastRep. FastRep通过对象粒度的复制任务锁和乐观的复制机制保障数据一致性, 通过时间有界完全树实现云函数快速调用, 通过自适应函数克隆应对带宽下降问题. 实验结果显示, FastRep能以分钟级延迟实现大小动态变化的对象数据的低成本复制. |
| 关键词: 跨云数据复制 服务器无感知计算 对象存储 |
| DOI：10.13328/j.cnki.jos.007623 |
| 分类号:TP311 |
| 基金项目:国家重点研发计划(2022YFB4500700); 国家自然科学基金(62325201, 62172008); 中央高校青年教师科研创新能力支持项目(ZYGXQNJSKYCXNLZCXM-I1) |
|
| Cross-cloud Replication System for Object Storage Based on Serverless Computing |
|
SHU Jun-Yi1,2, HUANG Xiao-Long1,2, MA Yun2, LI Hao-Yuan2,3, HUANG Gang1,2, LIU Xuan-Zhe1,2, JIN Xin1,2, MEI Hong1,2
|
|
1.School of Computer Science, Peking University, Beijing 100871, China;2.Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education, Beijing 100871, China;3.Alluxio Inc, Beijing 100080, China
|
| Abstract: |
| Object storage is one of the most widely used storage solutions in cloud computing environments. Replicating data stored in object storage across one or more cloud regions improves reliability and availability while reducing access latency for users. An object storage replication system is required to ensure consistency among replicas while minimizing replication latency. Existing open-source cross-cloud object storage replication systems, such as Skyplane, support object data replication across major cloud platforms but do not guarantee data consistency and exhibit high replication latency under dynamic workloads. To enable low-cost and low-latency object data replication under dynamic workloads, this study proposes a cross-cloud object storage replication system, termed FastRep, based on serverless computing. Data consistency is ensured through object-grained replication task locks and an optimistic replication mechanism. Cloud function invocation latency is reduced via a time-bounded complete tree, while bandwidth degradation is mitigated through adaptive function cloning. Experimental results demonstrate that FastRep achieves low-cost replication of dynamically sized object data with latency at the minute level. |
| Key words: cross-cloud data replication serverless computing object storage |
|
|
|
|
