New and Changed Features 143 Server 143 Query Processing 144 Release 6.27.0 144 Features 144 Resolved Issues 145 Server 145 Query Processing 146 Database Utilities 146 Cluster Management 146 Release 6.26.4 146 Server 147 Query Processing 147 Release 6.26.3 147 Server 147 Release 6.26.2 147 New Features 148 Query Processing 148 Server 148 Cluster Management 148 Disaster Supported Version 149 Query Processing 149 Server 149 Cluster Management 150 Release 6.26.0 150 Features 150 Resolved Issues 150 Server 151 Query Processing 151 Cluster Management 151

Orientation 333 Compression 334 Distributions 334 Local (Co-located) Joins 335 Data Skew 335 Processing Skew 336 Partitioning 336 Number of Partition and Columnar Storage Files 337 Indexes 338 Column Restoring Databases 536 Backup and Restore Overview 536 Parallel Backup with gpbackup and gprestore 536 Non-Parallel Backup with pg_dump 536 Parallel Backup with gpbackup and gprestore 537 Requirements 607 Viewing a Table’s Distribution Key 607 Viewing Data Distribution 607 Checking for Query Processing Skew 608 Avoiding an Extreme Skew Warning 608 Viewing Metadata Information about Database Objects

2016 – Major Greenplum 5.0 release planned early 2017 ## Greenplum Database Overview - Massively Parallel Processing (MPP) database system - Scales out to hundreds $ ^{(*)} $ of nodes • Shared nothing  Raster Image Processing  Spatial Indexes

Server 134 Query Processing 135 Data Flow 135 Cluster Management 136 Release 6.23 136 Release 6.23.3 136 Changed Feature 136 Resolved Issues 136 Extensions 136 Server 136 Query Processing 137 MADlib 138 138 Server 138 Query Processing 140 Data Flow 140 VMware Greenplum 6 Documentation VMware, Inc 3 Release 6.23.0 140 Features 140 Resolved Issues 142 Server 142 Query Processing 143 Cluster Management Release 6.22.2 144 Resolved Issues 144 Server 144 Query Processing 145 Data Flow 146 Release 6.22.1 146 Resolved Issues 146 Server 146 Query Processing 147 Cluster Management 147 Release 6.22.0 147 Features

Release 6.22.2 134 Resolved Issues 134 Server 135 Query Processing 136 Data Flow 136 Release 6.22.1 136 Resolved Issues 136 Server 137 Query Processing 137 Cluster Management 138 Release 6.22.0 138 Features Features 138 Resolved Issues 140 Server 140 Query Processing 141 Data Flow 141 Cluster Management 141 DataDirect ODBC 141 Release 6.21 142 VMware Tanzu Greenplum 6 Documentation VMware, Inc. 3 Release 6.21 3 142 Server 142 Release 6.21.2 142 Server 142 Query Processing 142 Release 6.21.1 142 Features 142 Resolved Issues 142 Server 142 Query Processing 144 Data Flow 144 Tanzu Greenplum on vSphere 144 Release

mine! You can't have them. ## Agenda 1. Current status of C++ safety: MISRA and C++ CG 2. Parallel Safety rules 3. Automotive Safety case ## Safety Critical API Evolution  • WG23 (no parallel rules) • Added some from our own contributions • Many joined, average 5-8 per meeting

Orientation 338 Compression 339 Distributions 339 Local (Co-located) Joins 340 Data Skew 340 Processing Skew 341 Partitioning 341 Number of Partition and Columnar Storage Files 342 Indexes 343 Column Backup and Restore Overview 0 Parallel Backup with gpbackup and gprestore 544 Non-Parallel Backup with pg_dump 544 Parallel Backup with gpbackup and gprestore 544 Parallel Backup with gpbackup and gprestore Viewing a Table's Distribution Key 616 Viewing Data Distribution 617 Checking for Query Processing Skew 617 Avoiding an Extreme Skew Warning 617 Viewing Metadata Information about Database Objects

## CurveBS I/O processing flow Before introducing IO processing flow, we first describe the overall architecture, data organization and topology structure of CURVE. ![Image](/uploads/documents/7/a/1 sockets. ● Nebdserver: Accepts requests from NEBDClient and calls Curve Client for corresponding processing. It can receive requests from different NEBDClients. 3. Through the above splitting, NebdClient NebdClient replaces Curve Client and directly interfaces with upper services. There is no logical processing in NEBDClient, it just proxy requests and has limited retries, which ensuring that NEBDClient needs no

# Design patterns for error handling in C++ programs using parallel algorithms and executors Mark Hoemmen $ ^{*} $ mhoemmen@stellarscience.com CppCon 2020 * hou'màn, or hœm'màn; he/him ## ## Who am I? • > 10 years post-PhD experience writing parallel C++ for science and engineering • Background: Parallel algorithms for big linear algebra problems • 1 $ ^{st} $ WG21: Nov 2017 • Started makes error handling harder... • ...C++ parallel algorithms and tasks specifically • Message Passing Interface (MPI): 3 decades of distributed-memory parallel programming • MPI teaches design patterns

Data Stream Processing and Analytics Spring 2020 ## 1 /23: Stream Processing Fundamentals Vasiliki (Vasia) Kalavri vkalavri@bu.edu ## What is a stream? - In traditional data processing applications data set that is produced incrementally over time, rather than being available in full before its processing begins. • Data streams are high-volume, real-time data that might be unbounded • we cannot store tial, single-pass| |Updates|arbitrary|append-only| |Update rates|relatively low|high, bursty| |Processing Model|query-driven / pull-based|data-driven / push-based| |Queries|ad-hoc|continuous| |Latency|relatively