。 话说当年 Greenplum（当时还是一个 Startup 公司，创始人家门口有 一棵青梅 ——greenplum，因此而得名）召集了十几位业界大咖（据 说来自 google、yahoo、ibm 和 TD），说干就干，花了一年多的时间 完成最初的版本设计和开发，用软件实现了在开放 X86 平台上的分布 式并行计算，不依赖于任何专有硬件，达到的性能却远远超过传统高 昂的专有系统。 Big Date2 块 SAS 盘的 X86 服务器，每秒的 IO 数据扫描性能约在 2000MB/s 左右，可以想象，20 台这样的服务器构成的机群 IO 性能 是 40GB/s，这样超大的 IO 吞吐是传统的 Storage 难以达到的。 (MPP Share-nothing 架构实现超大 IO 吞吐能力 ) 另外，Greenplum 还是建立在实例级别上的并行计算，可在一次 SQL 请求中利用到每个节点上的多个 （分享一下开源的直接好处，最近我们某用户的一个特殊需求，加载 数据中有回车等特殊字符，我们下载了 GP 外部表 gpfdist 源代码，不 到一天就轻松搞定问题） Greenplum 也正在积极的拥抱云计算，Cloud Foundry 的 PaaS 云平 台正在技术考虑把 Greenplum MPP 做为 DaaS 服务来提供，对于 Mesos 或其它云计算技术的爱好者，也可以考虑采用容器镜像技术 + 集群资源框架管理技术来部署

Software Dependencies 143 Java 145 Hardware and Network 145 Tanzu Greenplum on DCA Systems 145 Storage 146 Data Domain Boost (Tanzu Greenplum) 146 Tanzu Greenplum Tools and Extensions Compatibility Hosts for Data Loading 242 Tanzu Greenplum Performance Monitoring 243 Estimating Storage Capacity 244 Estimating Storage Capacity 0 Calculating Usable Disk Capacity 244 Calculating User Data Size 245 Software Download 0 Creating the Data Storage Areas 267 VMware Greenplum v6.19 Documentation VMware, Inc. 10 Creating the Data Storage Areas 0 Creating Data Storage Areas on the Master and Standby Master

Software Dependencies 142 Java 144 Hardware and Network 144 Tanzu Greenplum on DCA Systems 144 Storage 145 Data Domain Boost (Tanzu Greenplum) 145 Tanzu Greenplum Tools and Extensions Compatibility Hosts for Data Loading 235 Tanzu Greenplum Performance Monitoring 236 Estimating Storage Capacity 237 Estimating Storage Capacity 0 Calculating Usable Disk Capacity 237 Calculating User Data Size 238 Greenplum Database Installation 258 Next Steps 258 Creating the Data Storage Areas 258 Creating the Data Storage Areas 0 Creating Data Storage Areas on the Master and Standby Master Hosts 259 To create the

Software Dependencies 137 Java 139 Hardware and Network 139 Tanzu Greenplum on DCA Systems 139 Storage 140 Data Domain Boost 140 Tools and Extensions Compatibility 140 Client Tools 141 Extensions ETL Hosts for Data Loading 169 Greenplum Performance Monitoring 170 Estimating Storage Capacity 171 Estimating Storage Capacity 0 Calculating Usable Disk Capacity 171 Calculating User Data Size 172 Greenplum Database Installation 191 Next Steps 192 Creating the Data Storage Areas 192 Creating the Data Storage Areas 0 Creating Data Storage Areas on the Master and Standby Master Hosts 192 To create the

Software Dependencies 135 Java 137 Hardware and Network 137 Tanzu Greenplum on DCA Systems 137 Storage 137 Data Domain Boost (Tanzu Greenplum) 138 Tanzu Greenplum Tools and Extensions Compatibility Configuration 239 ETL Hosts for Data Loading 240 Tanzu Greenplum Performance Monitoring 241 Estimating Storage Capacity 242 Calculating Usable Disk Capacity 242 Calculating User Data Size 243 Calculating Space Creating the Data Storage Areas 264 Creating Data Storage Areas on the Master and Standby Master Hosts 264 To create the data directory location on the master 264 Creating Data Storage Areas on Segment

VMware Greenplum on DCA Systems 293 Storage 293 Hadoop Distributions 294 VMware vSphere Requirements 294 Public Cloud Requirements 295 Operating System 295 Storage 295 Amazon Web Services (AWS) 295 295 Virtual Machine Type 295 Compute 296 Memory 296 Network 296 Storage 296 Elastic Block Storage (EBS) 296 Ephemeral 297 AWS Recommendations 297 Master 297 VMware Greenplum 6 Documentation VMware Memory 298 Network 298 Storage 298 GCP Recommendations 298 Master and Segment Instances 299 Azure 299 Virtual Machine Type 299 Compute 299 Memory 299 Network 300 Storage 300 Azure Recommendations

Software Dependencies 275 Java 277 Hardware and Network 277 VMware Greenplum on DCA Systems 277 Storage 278 VMware Greenplum Tools and Extensions Compatibility 278 Client Tools 278 Extensions 279 Data Public Cloud Requirements 281 Operating System 281 Storage 282 Security 282 Amazon Web Services (AWS) 282 Virtual Machine Type 282 Compute 282 Memory 282 Network 283 Storage 283 Elastic Block Storage Memory 284 Network 284 Storage 284 GCP Recommendations 285 Master and Segment Instances 285 Azure 285 Virtual Machine Type 286 Compute 286 Memory 286 Network 286 Storage 286 Azure Recommendations

Software Dependencies 256 Java 258 Hardware and Network 259 VMware Greenplum on DCA Systems 259 Storage 259 Data Domain Boost (VMware Greenplum) 260 VMware Greenplum Tools and Extensions Compatibility Public Cloud Requirements 263 Operating System 263 Storage 263 Security 264 Amazon Web Services (AWS) 264 Virtual Machine Type 264 Compute 264 Memory 264 Network 264 Storage 264 Elastic Block Storage Memory 266 Network 266 Storage 266 GCP Recommendations 267 Master and Segment Instances 267 Azure 267 Virtual Machine Type 268 Compute 268 Memory 268 Network 268 Storage 268 Azure Recommendations

Software Dependencies 249 Java 251 Hardware and Network 251 Tanzu Greenplum on DCA Systems 251 Storage 251 Data Domain Boost (Tanzu Greenplum) 252 Tanzu Greenplum Tools and Extensions Compatibility Database Cloud Technical Recommendations 255 Operating System 255 Storage 255 Security 256 Amazon Web Services (AWS) 256 Virtual Machine Type 256 Compute 256 Memory 256 Network 256 Storage 256 Elastic Elastic Block Storage (EBS) 256 Ephemeral 257 AWS Recommendations 257 Master 257 Segments 257 Google Compute Platform (GCP) 258 Virtual Machine Type 258 Compute 258 Memory 258 Network 258 Storage

Software Dependencies 245 Java 247 Hardware and Network 247 Tanzu Greenplum on DCA Systems 248 Storage 248 VMware Tanzu Greenplum 6 Documentation VMware, Inc. 10 Data Domain Boost (Tanzu Greenplum) Database Cloud Technical Recommendations 251 Operating System 251 Storage 252 Security 252 Amazon Web Services (AWS) 252 Virtual Machine Type 252 Compute 252 Memory 252 Network 253 Storage 253 Elastic Elastic Block Storage (EBS) 253 Ephemeral 253 AWS Recommendations 254 Master 254 Segments 254 Google Compute Platform (GCP) 254 Virtual Machine Type 254 Compute 254 Memory 254 Network 254 Storage