Actian Corporation

Columnar Databases

Ingres just published a TPC-H benchmark for VectorWise, an analytic database technology employing    1) SIMD processing (Intel SSE 4.2),   2) better memory optimizations to leverage on-chip cache,   3) compression,    4) Column-based storage.

Ingres originated as a research project at UC Berkeley (see Wikipedia) in the 1970s, and has since become a commercially supported, open source database system. Apparently, Ingres project people later founded Sybase. So Ingres in a sense, is the grandfather (or perhap grand-step-uncle?) to SQL Server. According to the Ingres whitepaper, VectorWise spun off from CWI in Amstersdam, with some roots in MonetDB? For the time being, Ingres VectorWise is not open-source. The interesting aspect of VectorWise among other column store database products is use of the SIMD, as in utilizing the special instructions and registers built into recent generation microprocessors. (In a previous blog, I proposed special SIMD instructions to improve the efficiency on accessing pages in traditional row-storage database engines.)

Below are TPC-H results at scale factor 100GB on HP ProLiant DL380 G7 with two Xeon 5680 six-core 3.33GHz processors for SQL Server 2008 R2 and Ingres VectorWise 1.5.

 PowerThroughputQphHSQL Server99,626.355,038.273,974.6VectorWise257,142.9246,101.7251,561.7

Overall, the VectorWise columnar database has about 2.5X higher score on Power, and 5X on Throughput. The glaring weak point of SQL Server is that the throughput is (almost 2X) lower than the power. The SQL Server parallel execution engine is very powerful running a single stream with no other concurrent queries competing for CPU. It does not have a good strategy for sharing compute resources with other concurrent long running queries.

SOLUTION SHOWCASE

Learn, analyze, compare and decide

Visit the Solution Showcase, where you'll learn about the latest cutting-edge solutions — from the best-of-breed providers and up-and-comers. Get the information you need from our exhibitors to make informed decisions.

FACE-TO-FACE SPONSOR MEETINGS

Gain insight on your pressing IT needs

Discuss your technology requirements with qualified solution providers at the event. Use Agenda Builder to schedule private 30-minute sponsor meetings that will bolster your projects and relationships, wherever you are in the buying cycle.

SOLUTION PROVIDER SESSIONS

Real success stories

　【IT168 专稿】在上一系列文章中，我们先后介绍了Gbase 8a,Infobright,InfiniDB, MonetDB，SybaseIQ等5种列式数据库的功能，利用tpc-h模型scala=1和10的数据作了测试，并和传统行存储的Oracle数据库作了对比，得到了一些结论。本文将介绍另一种重要的新型列存储数据库Ingres VectorWise的功能特点，同样采用tpc-h scala=10数据评估它的性能，为用户数据库选型提供参考。

　　Ingres是关系数据库软件中的元老级产品，70 年代开始于加利福尼亚大学伯克利分校的一个研究项目，它的代码使用BSD许可证。从 80 年代中期起，在Ingres 基础上产生了很多商业数据库软件，包括 Sybase、Microsoft SQL Server、Informix 和许多其他的系统。在 80 年代中期启动的后继项目 Postgres，产生了 PostgreSQL，在开源数据库市场份额仅次于MySQL。由于Ingres有它自己的查询语言Quel，导致它对SQL语言的支持比较晚，从而慢慢淡出了主流用户的视线，但Ingres仍在继续发展，先后发布了Ingres 2006等产品，目前最新版是10.0。Ingres公司和荷兰的CWI研究院合作推出的VectorWise是基于Ingres10.0和MonetDB/X100这2种各自领域的领先产品，可以说是系出名门。2010年6月发布1.0版，2011年3月31日，发布了获取了tpc-h的100GB数据量的第一排名的1.5版。详细信息见http://www.tpc.org/tpch/results/tpch_perf_results.asp。本文即针对VectorWise 1.5版展开测试。　

       系列文章回顾：

        四款主流列式数据库横评

        主流列式数据库评测：Sybase IQ

　　     主流列式数据库评测:InfiniDB和MonetDB

　　     主流列式数据库评测之Infobright

　　     主流列式数据库评测:南大通用GBase 8a

　　一、测试平台

       本次测试基于Intel Xeon 7550*8的PC服务器上用VMWare VSphere 4.1管理的虚拟机，虚拟机的逻辑CPU个数是8，内存100GB，存储为8个300GB SAS本地磁盘，采用一块512M缓存RAID卡，按RAID5方式组成磁盘阵列。操作系统采用和RHEL 5相同的核心级别的RedFlag Asian Linux Sever 3.0 x64。

　　二、安装

　　(一)VectorWise的安装步骤

        VectorWise的评估版安装包可从网站http://www.ingres.com/downloads/vectorwise获取，Linux x86-64平台同时提供了rpm和非rpm二种安装包，前者简便易行，适合于初学者，后者提供更多的定制选项，适合于熟练用户。下面分别介绍这2种安装包的安装步骤。rpm安装包文件名是ingresvw-1.5-141-NPTL-eval-linux-x86_64.tgz，大约38MB,包含了服务器端核心和基于字符终端的命令行工具。这里NPTL 是Native POSIX ThreadingLibrary 的缩写。

         http://esd.ingres.com/上提供了详细的用户手册，内容包括概念、安装、管理和维护、基准测试、功能特性和系统限制等方面，基本涵盖了用户日常使用的各方面。至于更详细的SQL命令和网络配置步骤，需要参考Ingres 10.0的相关文档。

contact vectorwise research publications talks varia 

Contact

To contact me, please write to marcin at vectorwise dot com.

VectorWise

In 2008 the MonetDB/X100 project described further on this page has been converted into VectorWise, a company which I currently manage.

VectorWise cooperates with Ingres, the leading open-source database company, on the Ingres VectorWise product.

Research

Between 2001 and 2008 I was a member of the MonetDB development team. My initial work with MonetDB concentrated on parallel query execution, which resulted in my master's thesis (pdf).

From 2003 I was working on the MonetDB/X100 project under the supervision of Peter Boncz and Martin Kersten.

Five Non-obvious Tips for iPhone Novices

A Time to Count the Bounties of Big Data

As the Thanksgiving holiday approaches, we here in the US often take the time to come together, reflect on the year that was and count our good fortunes. Of course, the long Thanksgiving weekend – including Thanksgiving Thursday, Black Friday and Cyber Monday – is one of the busiest shopping events of the year. As big data analytics become even more important to retailers in the US and internationally, we at Actian decided to look at some of the statistics surrounding the unofficial kickoff to holiday shopping season.

PBS Software announces PBS Nearline Storage solution with Actian Vectorwise

PBS Software GmbH and Actian Corporation today announced their newly formed agreement to bring the power of Actian’s record-breaking analytic database, Vectorwise, to PBS nearline storage solutions.

Actian and Numsight Sign Strategic Partnership

Agreement marks the launch of bundled solution for analysing large databases at a lower cost

EnvoiMoinsCher.com Boosts Customer Satisfaction and Service Delivery with Actian Vectorwise

rance’s first online shipping comparison site uses record-breaking analytic database

Boxtale, the firm behind the EnvoiMoinsCher.com website, is using the high-performance analytic database Actian Vectorwise to accelerate complex analytic query response times. Visitors to the online shipping price comparison website now benefit from a dramatically-improved user experience when searching for the best delivery prices from a selection of more than twenty shipping providers and when placing their order.

he UK government has said it will accelerate the use of open source software in public services.

Tom Watson MP, minister for digital engagement, said open source software would be on a level playing field with proprietary software such as Windows.

Open source software will be adopted "when it delivers best value for money", the government said.

Ingres Database ( /ɪŋˈɡrɛs/ ing-gress) is a commercially supported, open-source SQL relational database management systemintended to support large commercial and government applications. Ingres Database is fully open source with a growing[citation needed]global community of contributors. However, Actian Corporation controls the development of Ingres and makes certified binaries available for download, as well as providing worldwide support.

Ingres was first created as a research project at the University of California, Berkeley, starting in the early 1970s and ending in the early 1980s. The original code, like that from other projects at Berkeley, was available at minimal cost under a version of the BSD license. Since the mid-1980s, Ingres has spawned a number of commercial database applications, including Sybase, Microsoft SQL Server,NonStop SQL and a number of others. Postgres (Post Ingres), a project which started in the mid-1980s, later evolved into PostgreSQL.