220 likes | 313 Views
Design of Cloud Management Layer for High-Performance File Transfer. 高效能檔案傳輸之雲端層設計. Outline. Introduction Background System Design Implementation Experiments. Introduction. Motivation File Transfer with load sharing and fault tolerance. Introduction.
E N D
Design of Cloud Management Layerfor High-Performance File Transfer 高效能檔案傳輸之雲端層設計
Outline • Introduction • Background • System Design • Implementation • Experiments
Introduction • Motivation • File Transfer with load sharing and fault tolerance.
Introduction • Clients can upload the files to the cloud, and promise your file cannot be lose . Files Upload Download Files User (Client) Cluster Storage Server Management Layer
Introduction (Cont.) • Surveillance Application Host Device x 30 2000G(2T) / 30 = 67G 67G / 0.3G = 223h 223h / 24h = 9.3 day Size: 0.2~0.5 GB/1hr Storage:2TB
Introduction (Cont.) • Used Platforms and API • Hadoop • HadoopDistributed File System (HDFS) • File Storage • Hbase • User Authentication • Socket • File Data • Transmissions
Outline • Introduction • Background • System Design • Implementation • Experiments
Background (Cont.) What is Cloud Computing? • Scalable Computing and Storage Resource. Cloud Source Models
Background (Cont.) Hadoop DataBase Parallel Processing File System • The other components of Hadoop
Background (Cont.) What is “Hadoop Distributed File System (HDFS)”? Clients Transmission Cluster Storage Server PC Datanode Namenode
Background (Cont.) • Hbasehave high availability, high performance, and high expansion flexibility.
Outline • Introduction • Background • System Design • Implementation • Experiments • Conclusions • Reference
System Design(Cont.) • Components • Manager Selection • Authentication • Synchronization • Cloud-Based File Transfer
System Design(Cont.) • Manager Selection • Connect Management layer and perform load balance • Collect memory load information from each nodes • Select the lowest memory load as connection port(Nodei) • Connect with Nodei • Authentication
System Design(Cont.) • Authentication • Key in account / password • Authentication(Hbaseverification) • Synchronization
System Design(Cont.) • Synchronization • HDFS files synchronization in client side • Check files existence • Cloud-Based files transfer • Background Monitoring
System Design(Cont.) • Synchronization • HDFS files synchronization in client side • Check files existence • Cloud-Based files transfer • Background Monitoring
System Design(Cont.) • Cloud-Based File Transfer • Send request using socket • Analysis The packet (to extract the command and path) • Execute command (Write/Send/Delete)
Outline • Introduction • Background • System Design • Experiments • Conclusions • Reference
Experiments • Manager Selection • 隨機配置 • 負載平衡配置 • 選擇負載最小之節點:5 個 • 更新時間:10 秒 • 可同時連線數量:10 個 • Environmental Environment 1 • Servers: 50, 100, 150, 200, 250 • Clients: 2000 • Environmental Environment2 • Servers: 50 • Clients:1000, 2000, 3000, 4000, 5000
Experiments(Cont.) • Experiment 1 • Servers: 50, 100, 150, 200, 250 • Clients: 2000
Experiments(Cont.) • Experiment 2 • Servers: 50 • Clients:1000, 2000, 3000, 4000, 5000