• Share
  • Email
  • Embed
  • Like
  • Private Content
IBM PureData Systems
 

IBM PureData Systems

on

  • 1,380 views

 

Statistics

Views

Total Views
1,380
Views on SlideShare
1,380
Embed Views
0

Actions

Likes
1
Downloads
60
Comments
0

0 Embeds 0

No embeds

Accessibility

Categories

Upload Details

Uploaded via as Adobe PDF

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment

    IBM PureData Systems IBM PureData Systems Presentation Transcript

    • IBM PureData SystemsMeeting data challenges with simplicity, speed & lower costArtur WrońskiIBM Software Group © 2012 IBM Corporation
    • Disclaimer © Copyright IBM Corporation 2012. All rights reserved. U.S. Government Users Restricted Rights - Use, duplication or disclosure restricted by GSA ADP Schedule Contract with IBM Corp. THE INFORMATION CONTAINED IN THIS PRESENTATION IS PROVIDED FOR INFORMATIONAL PURPOSES ONLY. WHILE EFFORTS WERE MADE TO VERIFY THE COMPLETENESS AND ACCURACY OF THE INFORMATION CONTAINED IN THIS PRESENTATION, IT IS PROVIDED “AS IS” WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED. IN ADDITION, THIS INFORMATION IS BASED ON IBM’S CURRENT PRODUCT PLANS AND STRATEGY, WHICH ARE SUBJECT TO CHANGE BY IBM WITHOUT NOTICE. IBM SHALL NOT BE RESPONSIBLE FOR ANY DAMAGES ARISING OUT OF THE USE OF, OR OTHERWISE RELATED TO, THIS PRESENTATION OR ANY OTHER DOCUMENTATION. NOTHING CONTAINED IN THIS PRESENTATION IS INTENDED TO, NOR SHALL HAVE THE EFFECT OF, CREATING ANY WARRANTIES OR REPRESENTATIONS FROM IBM (OR ITS SUPPLIERS OR LICENSORS), OR ALTERING THE TERMS AND CONDITIONS OF ANY AGREEMENT OR LICENSE GOVERNING THE USE OF IBM PRODUCTS AND/OR SOFTWARE. IBM, the IBM logo, ibm.com, Information Management, IMS, CICS, DB2, WebSphere, PureSystems, pureScale, PureExperience, PureApplication, PureData and z/OS are trademarks or registered trademarks of International Business Machines Corporation in the United States, other countries, or both. If these and other IBM trademarked terms are marked on their first occurrence in this information with a trademark symbol (® or ™), these symbols indicate U.S. registered or common law trademarks owned by IBM at the time this information was published. Such trademarks may also be registered or common law trademarks in other countries. A current list of IBM trademarks is available on the Web at “Copyright and trademark information” at www.ibm.com/legal/copytrade.shtml Other company, product, or service names may be trademarks or service marks of others.50 © 2012 IBM Corporation
    • 51 © 2012 IBM Corporation
    • The PureSystems family delivers greater simplicity, speed & lower costToday’s problem: Time and effort is spent tuning general purpose components Design/Deploy Manage/MaintainGeneral Purpose Custom Built Components SystemThe PureSystems solution: Simplifying the entire IT project lifecycle Reduced Time, Cost and Risk Design Deploy Manage MaintainExpert Integrated System52 © 2012 IBM Corporation
    • IBM PureData System: Optimized exclusively for data servicesOptimized fordata services: Workload optimized Transactional performance Analytics Data load ready in hoursExpert integrated: Integrated management Data platform Infrastructure Single point of support Unified platform management Automated maintenance Built-in expertise in hours, not days Data Platform Delivering Data Services53 © 2012 IBM Corporation
    • Different types of workloads require different data services Customer Real Time E-commerce Analysis Fraud Detection Transaction Processing Reporting and Analytics Operational Analytics Random reads & Sequential reads & Random and sequential reads & random updates sequential data loads data loads + continuous ingest Scalable Transactional Database Analytics Data Warehouse Operational Data Warehouse Random reads & Sequential reads & Random and sequential reads & data random updates sequential data loads loads + continuous ingest Many transactions Analytics with broad data scope, split Analytics split into many parts and with narrow data scope into many parts across narrow scope operations, accessing the same database data partitions to run in parallel all running in parallel Shared access to all data Partitioned data access Partitioned data access54 © 2012 IBM Corporation
    • Different data workloads have different characteristics For apps like E-commerce… Database cluster services optimized for System for Transactions transactional throughput and scalability For apps like Customer Analysis… System for Analytics Data warehouse services optimized for powered by high-speed, peta-scale analytics and Netezza technology simplicity For apps like Real-time Fraud Detection… System for Operational data warehouse services Operational Analytics optimized to balance high performance analytics and real-time operational throughput55 © 2012 IBM Corporation
    • 56 © 2012 IBM Corporation
    • Database Architectures: Single, Shared Storage, Shared Nothing Optimized for OLTP Optimized for Analytics Single Database View Single Database View SQL 1 Tran Tran 1 Tran 2 Tran 3 SQL 1’ SQL 1’’ SQL 1’’’ DB2 DB2 DB2 DB2 DB2 DB2 DB2 Log Log Log Log Log Database Shared Data Access Part 1 Part 2 Part 3 Core DB2 DB2 pureScale Data Sharing DB2 InfoSphere Warehouse (aka DPF) Ideal for OLTP Ideal for active/active OLTP/ERP Ideal for data warehousing with MPP scale out and data marts scale out for near linear scalability and query processing57 © 2012 IBM Corporation
    • IBM PureData System for Transactions highlightsOptimized exclusively for transactional data workloads Speed Industry leading DB2 performance System for Database node recovery in seconds1 Transactions Simplicity Delivering data services Database deployment in minutes, not hours1 for transactions Capable of running multiple database software versions Handles more than 100 databases on 1 system2 No planned system downtime for firmware / OS upgrades1 Scalability Scaling up to 30x3 Designed to expand from small to medium & medium to large configuration with no planned system downtime required Smart Supports Oracle Database apps with minimal change; supports DB2 applications unchanged Clients have experienced cases of 10x storage space Footnotes: 1. Based on IBM internal tests and system design for normal operation under savings via Adaptive Compression4 expected typical workload. Individual results may vary. 2. Based on one large configuration. 3. Based on the designed minimum and maximum processor and memory resources required for a single database. 4. Based on client testing in the DB2 10 Early Access Program.58 © 2012 IBM Corporation
    • Reduce your system integration costs Deployment Databases Optimized solution stack Data Management • Factory integrated and optimized • Server, storage, networking and software • High data availability • Automatic failure detection and onlineManagement recovery • Solid State exploitation • Automatic management of hot, warm and cold data for faster performance Storage • Optimized database patterns • Database patterns pre-tuned and pre- configured for performance • Integrated fixes Networking • Zero down time for system maintenance Servers 59 © 2012 IBM Corporation
    • Simplified deployment with high availability Uninterrupted access to data with consistent performance Traditional systems - PureData System for build it yourself 6-node Transactions - database cluster instance built-inOver several days/weeks:1. Define High Availability topology In minutes,2. Configure HW/SW/Network 1. Just specify cluster3. Set up storage pools name, description and4. Install multiple operating systems topology pattern5. Install database instances6. Set up primary and secondary management systems7. Set up database members8. Set up backup processes9. Test, tune, reconfigure...60 © 2012 IBM Corporation
    • Simplified, pattern based database deployment Consolidate Captures your expertise in patterns 100s of database servers for consistent, reliable deployment to a single system for optimal resource efficiency of critical databases as a service and easier administration Optimize storage resources for up to 10x storage space savings Vir HTTP tua Server l Operatin g Ap system pli Cluster Innovate Deploy an Metadata ce Vir Ap plication tua Server l Operatin g Ap system Virt Ap plication ual Server Ap Operatin g plia system Topology faster by deploying pli nce an Metadata ce Metadata new databases in minutes Accelerate deployment of new database services in cloud environments using patterns of expertise Database Deploy61 © 2012 IBM Corporation
    • Simplified Application Development • Higher scalability provided by adding more nodes with no application changes required Applications • Dev/Test/Staging/Production database repeatability through database patterns Database Database Database Database • Integrated data movement tools to Management Software Management Software Management Software Management Software speed creation of test databases • Built-in Oracle compatibility mode for minimal to no application changes • Higher utilization and lower costs provided through shared resource management62 © 2012 IBM Corporation
    • PureData for TransactionsThree standard configurations to choose from Upgrade Upgrade Configurations Small Medium Large ¼ Rack ½ Rack Full Rack Chassis 1 1 2 Blacktip ITEs 6 12 24 (16 cores per ITE) Cores 96 192 384 Memory 1.5 TB 3.1 TB 6.1 TB V7000 1 2 4 V7000 Exp 1 2 4 User Capacity 18.6 TB 37.2 TB 74.4 TB Raw SSD Storage (400 GB drives) 4.8 TB 9.6 TB 19.2 TB Raw HDD Storage (900 GB drives) 32.4 TB 64.0 TB 128.0 TB63 © 2012 IBM Corporation
    • Simplified database administration Data access requests automatically load balanced for optimal Self-balancing performance Self-tuning Memory management dynamically balances resources Best data placement and access automatically selected based Self-optimizing on usage statistics for optimal performance Self-monitoring Based on thresholds and alerts, system will monitor and automatically make changes as needed to improve performance Self-healing Failed database nodes are isolated and recovered automatically64 © 2012 IBM Corporation
    • Simplified and integrated system management • Single console to manage all resources and work running on the system • Role-based security and tasks • management • monitoring • maintenance • Easy integration with broader enterprise monitoring tools and processes • Consistent IBM PureSystems console65 © 2012 IBM Corporation
    • Simplified maintenance with pre-integrated fixes Reduce risk and eliminate manual errors when applying maintenance • All hardware firmware and OS software patches integrated and tested together at the factory • Can apply hardware and OS maintenance with zero downtime • Single line of support • Integrated stack support66 © 2012 IBM Corporation
    • 67 © 2012 IBM Corporation
    • Database Architectures: Single, Shared Storage, Shared Nothing Optimized for OLTP Optimized for Analytics Single Database View Single Database View SQL 1 Tran Tran 1 Tran 2 Tran 3 SQL 1’ SQL 1’’ SQL 1’’’ DB2 DB2 DB2 DB2 DB2 DB2 DB2 Log Log Log Log Log Database Shared Data Access Part 1 Part 2 Part 3 Core DB2 DB2 pureScale Data Sharing DB2 InfoSphere Warehouse (aka DPF) Ideal for OLTP Ideal for active/active OLTP/ERP Ideal for data warehousing with MPP scale out and data marts scale out for near linear scalability and query processing68 © 2012 IBM Corporation
    • IBM PureData System for Operational AnalyticsOptimized exclusively for operational analytic data workloads Speed Designed for 1000+ concurrent operational queries Continuous ingest of operational data System for Operational Analytics MPP analytics (Massively Parallel Processing) Delivering data services for operational analytics Simplicity Fast time-to-value Automatic workload management Integrated backup on the system Integrated management and support Scalability Multiple sizes with data capacity up to a Petabyte Smart In-database analytics for leading applications Supports DB2 applications unchanged and Oracle Database apps with minimal change Clients have experienced cases of 10x storage space savings via Adaptive Compression69 © 2012 IBM Corporation
    • IBM PureData System for Operational Analytics Optimized for a mix of interactive and analytic queries Preset and configured for top performance, throughput, and efficient resource utilization Continuous ingest of operational data Balanced throughput and performance through dynamic self-tuning Policy-based automatic workload management Adaptive compression that delivers storage savings and improved query performance © 2012 IBM Corporation7070
    • Real-time operational analytics with continuous data ingest The Time-Value Curve: How does business value change through time?* Value Business event Data ready for analytics Data Sources DW Analytics delivered Decision latency Decision / Action taken gained Value ETL- Extract, Transform, Load Up to the Second Loads, Time Faster Loads Faster decision / action Complete, built-in support for continuous feed of data into the warehouse Parallel processing, and support for multiple connections Minimum impact on query performance Analytics are delivered to decision makers faster71 © 2012 IBM Corporation * Above diagram adapted from TDWI Best Practices Report - Operational Data Warehousing by Philip Russom, 4Q 2010
    • PureData System for Operational Analytics hardware and capacity sizes IBM POWER7 P740 & P730 16 Core servers @ 3.55GHz IBM Storwize® V7000 with Storwize® Scales to 900GB drives PB+ Ultra SSD I/O Drawers, each with capacity* six 387GB SSD Blade Network Technologies 10G and 1G Ethernet switches Brocade SAN switches (SAN48B-5) Scalable to PB+* Extra Small Small Medium Large 64.8 TB* 151.2 TB* 237.6 TB* 324 TB*72 *Unformatted raw disk capacity © 2012 IBM Corporation
    • PureData System for Operational Analytics hardware73 © 2012 IBM Corporation
    • 74 © 2012 IBM Corporation
    • IBM PureData System for AnalyticsOptimized exclusively for analytic data workloads Speed 10-100x faster than traditional custom systems* System for Analytics Patented MPP hardware acceleration (Massively Parallel Processing) Delivering data services Simplicity for analytics Data load ready in hours No database indexes No tuning No storage administration Scalability Peta-scale data capacity Smart Designed to runs complex analytics in minutes, not hours Richest set of in-database analytics * Based on IBM customers reported results. "Traditional custom systems" refers to systems that are not professionally pre-built, © 2012 IBM Corporation75 pre-tested and optimized. Individual results may vary.
    • Inside the IBM PureData System for Analytics Disk Enclosures Optimized Hardware + Software User data, mirror, swap partitions Hardware accelerated High speed dataAMPP streaming Purpose-built for highperformance analytics Snippet Blades ™ Requires no tuning Hardware-based query SMP Hosts acceleration with FPGAs SQL Compiler Blistering fast results Query Plan Complex analytics Optimize executed as the data Admin streams from disk76 © 2012 IBM Corporation
    • Snippet-Blade™ (S-Blade) Components SAS Expander Module DRAM SAS Expander Dual-Core FPGA ModuleIntel Quad-Core IBM BladeCenter Server Netezza DB Accelerator77 © 2012 IBM Corporation
    • PureData System for Analytics Takes Analytics Beyond Reporting Optimization Predictive Analytics BI Reporting and Ad-Hoc Analysis What is the best choice? What will happen? What will the impact be? What happened? When and where? How much?78 © 2012 IBM Corporation © 2012 IBM Corporation
    • Pre-Built In-Database Analytics Statistics Transformations Time Series Mathematical Descriptive Statistics+ Basic Math* Data Profiling / Autoregressive+ Descriptive Statistics+ Permutation and Distance Measures* Forecasting* Combination* General Diagnostics Greatest Common Hypothesis Testing* Divisor and Least Statistics+ Common Multiple* Chi-Square & Contingency Tables* Conversion of Values* Sampling Exponential and Univariate & Data prep Logarithm* Multivariate Distributions+ Gamma and Beta Functions Monte Carlo Matrix Algebra+ Simulation* Area Under Curve* Interpolation Methods* Data Mining Predictive Geospatial Association Rules+ Linear Regression+ Geospatial Data Type * Fuzzy Logix DB Lytix Clustering+ Logistic Regression+ Geometric Functions capabilities Feature Extraction+ Classification Geometric Analysis + Netezza Analytics Discriminant Bayesian and Fuzzy Analysis* Logix DB Sampling Lytix capabilities Model Testing79 © 2012 IBM Corporation
    • What’s New?Improved Concurrency, Performance, I/O efficiency and Manageability Better Improved Improved Resiliency Performance Management & Efficiency and Fault Tolerance 20x greater throughput More than half a dozen Blade level resilience performance improvements and concurrency for in: for continuous high tactical queries than performance Optimizer efficiency previous generations of Memory management Enhanced automatic IBM Netezza appliances1 system software Up to 200 queries/second Communications resilience for protocols micro analytic workloads enterprise level Workload management requirements Directed Data Processing Faster, Better, and increases throughput for completely transparent to the tactical queries end-user1Based on IBM internal performance benchmarking of previous version to current version.80 © 2012 IBM Corporation
    • IBM PureData System is unique Different models pre-optimized exclusively for different data workloads saving clients time, effort and cost to tune on their own Pattern based database deployment in minutes, not hours1 System for Transactions Handles more than 100 databases on 1 system2 10-100x faster than traditional custom systems4 System for Analytics 20x greater concurrency and throughput powered by for tactical queries than previous Netezza technology Netezza technology5 Continuous ingest of operation data Designed to handle 1000+ concurrent System for operational queries3 Operational Analytics 1 Based on IBM internal tests and system design for normal operation under Expected typical workload. Individual results may vary. Up to 10x storage savings with 2 Based on one large configuration 3 Based on IBM internal tests of prior generation system, and on system design for normal operations under expected typical workload. Individual results may vary. active compression6 4 Based on IBM customers reported results. "Traditional custom systems" refers to systems that are not81 professionally pre-built, pre-tested and optimized. Individual results may vary. © 2012 IBM Corporation 5 Based on IBM internal performance benchmarking 6 Based on client testing is the DB2 10 Early Access Program