SlideShare a Scribd company logo
1 of 17
Data WarehousingData Warehousing
11
Data WarehousingData Warehousing
Lecture-24Lecture-24
Need for Speed: ParallelismNeed for Speed: Parallelism
Virtual University of PakistanVirtual University of Pakistan
Ahsan Abdullah
Assoc. Prof. & Head
Center for Agro-Informatics Research
www.nu.edu.pk/cairindex.asp
National University of Computers & Emerging Sciences, Islamabad
Email: ahsan101@yahoo.com
Data Warehousing
2
BackgroundBackground
Data Warehousing
3
When to parallelize?When to parallelize?
Useful for operations that access significant amountsUseful for operations that access significant amounts
of data.of data.
Useful for operations that can be implementedUseful for operations that can be implemented
independent of each other “Divide-&-Conquer”independent of each other “Divide-&-Conquer”
Parallel execution improves processing for:Parallel execution improves processing for:
 Large table scans and joinsLarge table scans and joins
 Creation of large indexesCreation of large indexes
 Partitioned index scansPartitioned index scans
 Bulk inserts, updates, and deletesBulk inserts, updates, and deletes
 Aggregations and copyingAggregations and copying
SizeSize
SizeSize
D&CD&C
SizeSize
D&CD&C
Data Warehousing
4
Are you ready to parallelize?Are you ready to parallelize?
Parallelism can be exploited, if there is…Parallelism can be exploited, if there is…
 Symmetric multi-processors (SMP), clusters, or MassivelySymmetric multi-processors (SMP), clusters, or Massively
Parallel (MPP) systemsParallel (MPP) systems ANDAND
 Sufficient I/O bandwidthSufficient I/O bandwidth ANDAND
 Underutilized or intermittently used CPUs (for example,Underutilized or intermittently used CPUs (for example,
systems where CPU usage is typically less than 30%)systems where CPU usage is typically less than 30%) ANDAND
 Sufficient memory to support additional memory-intensiveSufficient memory to support additional memory-intensive
processes such as sorts, hashing, and I/O buffersprocesses such as sorts, hashing, and I/O buffers
Word of cautionWord of caution
Parallelism can reduce system performance on over-utilized
systems or systems with small I/O bandwidth.
Data Warehousing
5
Scalability – Size is NOT everythingScalability – Size is NOT everything
Number of ConcurrentNumber of Concurrent
UsersUsers
• Simple table retrieval
• Moderate complexity Join
• Propensity analysis
• Clustering
Complexity of TechniqueComplexity of Technique
• Hash based
• B-Tree
• Multiple
• Bitmapped
Index usageIndex usage
Amount of detailed dataAmount of detailed data
Complexity of Data ModelComplexity of Data Model



 


Data Warehousing
6
Scalability- Speed-Up & Scale-UpScalability- Speed-Up & Scale-Up
Speed-UpSpeed-Up
More resources means
proportionally less time
for given amount of data.
Scale-UpScale-Up
If resources increased in
proportion to increase in
data size, time is constant.
Degree of Parallelism
Transactions/Sec
Degree of Parallelism
Secs/Transaction
Ideal
Ideal
Real
Data Warehousing
7
Quantifying Speed-upQuantifying Speed-up
Sequential Execution IdealIdeal Parallel Execution
18 time units 6 time units
Task-1 Task-2 Task-3
Control work (“overhead”)
Speedup = 18 = 300%
6
Ts: Time on serial processor
Tm: Time on multiple processors
Speedup =
Ts
Tm
Task-1
Task-2
Task-3
Data Warehousing
8
Speed-Up & Amdahl’s LawSpeed-Up & Amdahl’s Law
Reveals maximum expected speedup from parallel
algorithms given the proportion of task that must be
computed sequentially. It gives the speedup S as
ff is the fraction of the problem that must be computed sequentially
NN is the number of processors
As ff approaches 0, SS approaches NN
Example-1: ff = 5% and NN = 100 then SS = 16.8
Example-2: ff = 10% and NN = 200 then SS = 9.56
Not
1:1
Ratio
Only formula and explanation will go to graphics
Data Warehousing
9
Amdahl’s Law: Limits of parallelizationAmdahl’s Law: Limits of parallelization
For less than 80% parallelism, the speedup drastically drops.
At 90% parallelism, 128128 processors give performance of less than 1010
processors.
1
2
3
4
5
6
7
8
9
10
0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1
% sequential code (f)
Speedup(S)
N=2 N=4 N=8 N=16 N=32 N=64 N=128
Data Warehousing
10
Parallelization OLTP Vs. DSSParallelization OLTP Vs. DSS
There is a big difference.
DSS
Parallelization of a SINGLE query
OLTP
Parallelization of MULTIPLE queries
Or Batch updates in parallel
Data Warehousing
11
Brief Intro to Parallel ProcessingBrief Intro to Parallel Processing
 Parallel Hardware ArchitecturesParallel Hardware Architectures
 Symmetric Multi Processing (SMP)Symmetric Multi Processing (SMP)
 Distributed Memory or Massively Parallel ProcessingDistributed Memory or Massively Parallel Processing
(MPP)(MPP)
 Non-uniform Memory Access (NUMA)Non-uniform Memory Access (NUMA)
 Parallel Software ArchitecturesParallel Software Architectures
 Shared MemoryShared Memory
 Shard DiskShard Disk
 Shared NothingShared Nothing
 Types of parallelismTypes of parallelism
 Data ParallelismData Parallelism
 Spatial ParallelismSpatial Parallelism
Shared Everything
Data Warehousing
12
Symmetrical Multi Processing (SMP)Symmetrical Multi Processing (SMP)
 A number of independent I/O and number ofA number of independent I/O and number of
processors all sharing access to a single large memoryprocessors all sharing access to a single large memory
space.space.
Main Memory
I/O I/O I/O P1 P2 P3 P4
 Typically each CPU executes its job independently.Typically each CPU executes its job independently.
 Supports both Multi-Tasking and Parallel Processing.Supports both Multi-Tasking and Parallel Processing.
 Have to deal with issues such as Cache Coherence, Processor AffinityHave to deal with issues such as Cache Coherence, Processor Affinity
and Hot Spots.and Hot Spots.
Yellow will not go to graphics
Data Warehousing
13
 Composed of a number of self-contained, self-controlled nodesComposed of a number of self-contained, self-controlled nodes
connected through a network interface.connected through a network interface.
 Each node contains its own CPU, processor, memory and I/O.Each node contains its own CPU, processor, memory and I/O.
 Architecture better known as Massively Parallel Processing (MPP)Architecture better known as Massively Parallel Processing (MPP)
or cluster computing.or cluster computing.
 Memory is distributed across all nodes.Memory is distributed across all nodes.
Distributed Memory MachinesDistributed Memory Machines
Bus, Switch or Network
I/O P
Memory
I/O P
Memory
I/O P
Memory
 Network has the tendency to become the bottleneck.Network has the tendency to become the bottleneck.
 Issues fundamentally different from those in SMP.Issues fundamentally different from those in SMP.
Yellow will not go to graphics
Node
Data Warehousing
14
A little bit of both worlds !A little bit of both worlds !
Distributed Shared Memory MachinesDistributed Shared Memory Machines
Interconnection
Network
Main Memory
I/O I/O I/O P1 P2 P3 P4
Main Memory
I/O I/O I/O P1 P2 P3 P4
Main Memory
I/O I/O I/O P1 P2 P3 P4
Main Memory
I/O I/O I/O P1 P2 P3 P4
Data Warehousing
15
Shared disk RDBMS ArchitectureShared disk RDBMS Architecture
Clients/Users
Shared Disk
Interconnect
Adv
High level of fault tolerance
Dis Adv
Serialization due to locking
Interconnect can become a bottleneck
Yellow ill not go to graphics
Data Warehousing
16
Shared Nothing RDBMS ArchitectureShared Nothing RDBMS Architecture
Clients/Users
Adv
Data ownership changes infrequently
There is no locking
Dis Adv
Data availability low on failure
Very careful with data distribution
Redistribution is expensive
Yellow ill not go to graphics
Data Warehousing
17
Shared disk Vs. Shared Nothing RDBMSShared disk Vs. Shared Nothing RDBMS
 Important note:Important note: Do not confuse RDBMSDo not confuse RDBMS
architecture with hardware architecture.architecture with hardware architecture.
 Shared nothing databases can run on sharedShared nothing databases can run on shared
everything (SMP or NUMA) hardware.everything (SMP or NUMA) hardware.
 Shared disk databases can run on sharedShared disk databases can run on shared
nothing (MPP) hardware.nothing (MPP) hardware.
This slide will not go to graphics

More Related Content

What's hot

Hadoop World Vertica
Hadoop World VerticaHadoop World Vertica
Hadoop World VerticaOmer Trajman
 
Hadoop interview question
Hadoop interview questionHadoop interview question
Hadoop interview questionpappupassindia
 
Hive Training -- Motivations and Real World Use Cases
Hive Training -- Motivations and Real World Use CasesHive Training -- Motivations and Real World Use Cases
Hive Training -- Motivations and Real World Use Casesnzhang
 
Hive and data analysis using pandas
 Hive  and  data analysis  using pandas Hive  and  data analysis  using pandas
Hive and data analysis using pandasPurna Chander K
 
Big Data and Cloud Computing
Big Data and Cloud ComputingBig Data and Cloud Computing
Big Data and Cloud ComputingFarzad Nozarian
 
Python in an Evolving Enterprise System (PyData SV 2013)
Python in an Evolving Enterprise System (PyData SV 2013)Python in an Evolving Enterprise System (PyData SV 2013)
Python in an Evolving Enterprise System (PyData SV 2013)PyData
 
Hadoop: The Default Machine Learning Platform ?
Hadoop: The Default Machine Learning Platform ?Hadoop: The Default Machine Learning Platform ?
Hadoop: The Default Machine Learning Platform ?Milind Bhandarkar
 
Spark Application Development Made Easy
Spark Application Development Made EasySpark Application Development Made Easy
Spark Application Development Made EasyDataWorks Summit
 
Introduction to Hadoop
Introduction to HadoopIntroduction to Hadoop
Introduction to Hadoopjoelcrabb
 
Tuning data warehouse
Tuning data warehouseTuning data warehouse
Tuning data warehouseSrinivasan R
 
TheETLBottleneckinBigDataAnalytics(1)
TheETLBottleneckinBigDataAnalytics(1)TheETLBottleneckinBigDataAnalytics(1)
TheETLBottleneckinBigDataAnalytics(1)ruchabhandiwad
 
XML Parsing with Map Reduce
XML Parsing with Map ReduceXML Parsing with Map Reduce
XML Parsing with Map ReduceEdureka!
 
co-Hadoop: Data co-location on Hadoop.
co-Hadoop: Data co-location on Hadoop.co-Hadoop: Data co-location on Hadoop.
co-Hadoop: Data co-location on Hadoop.Yousef Fadila
 

What's hot (19)

Greenplum Architecture
Greenplum ArchitectureGreenplum Architecture
Greenplum Architecture
 
Map Reduce
Map ReduceMap Reduce
Map Reduce
 
Hadoop World Vertica
Hadoop World VerticaHadoop World Vertica
Hadoop World Vertica
 
Hadoop interview question
Hadoop interview questionHadoop interview question
Hadoop interview question
 
Pig Experience
Pig ExperiencePig Experience
Pig Experience
 
Hive Training -- Motivations and Real World Use Cases
Hive Training -- Motivations and Real World Use CasesHive Training -- Motivations and Real World Use Cases
Hive Training -- Motivations and Real World Use Cases
 
Hive and data analysis using pandas
 Hive  and  data analysis  using pandas Hive  and  data analysis  using pandas
Hive and data analysis using pandas
 
Hadoop-Introduction
Hadoop-IntroductionHadoop-Introduction
Hadoop-Introduction
 
Big Data and Cloud Computing
Big Data and Cloud ComputingBig Data and Cloud Computing
Big Data and Cloud Computing
 
Python in an Evolving Enterprise System (PyData SV 2013)
Python in an Evolving Enterprise System (PyData SV 2013)Python in an Evolving Enterprise System (PyData SV 2013)
Python in an Evolving Enterprise System (PyData SV 2013)
 
Vertica
VerticaVertica
Vertica
 
Hadoop: The Default Machine Learning Platform ?
Hadoop: The Default Machine Learning Platform ?Hadoop: The Default Machine Learning Platform ?
Hadoop: The Default Machine Learning Platform ?
 
HDFS Erasure Coding in Action
HDFS Erasure Coding in Action HDFS Erasure Coding in Action
HDFS Erasure Coding in Action
 
Spark Application Development Made Easy
Spark Application Development Made EasySpark Application Development Made Easy
Spark Application Development Made Easy
 
Introduction to Hadoop
Introduction to HadoopIntroduction to Hadoop
Introduction to Hadoop
 
Tuning data warehouse
Tuning data warehouseTuning data warehouse
Tuning data warehouse
 
TheETLBottleneckinBigDataAnalytics(1)
TheETLBottleneckinBigDataAnalytics(1)TheETLBottleneckinBigDataAnalytics(1)
TheETLBottleneckinBigDataAnalytics(1)
 
XML Parsing with Map Reduce
XML Parsing with Map ReduceXML Parsing with Map Reduce
XML Parsing with Map Reduce
 
co-Hadoop: Data co-location on Hadoop.
co-Hadoop: Data co-location on Hadoop.co-Hadoop: Data co-location on Hadoop.
co-Hadoop: Data co-location on Hadoop.
 

Viewers also liked

Стратегічні партнери КНЕУ: British Council
Стратегічні партнери КНЕУ: British CouncilСтратегічні партнери КНЕУ: British Council
Стратегічні партнери КНЕУ: British CouncilАлександр Кулиевич
 
Forklift Usage Reporting, Utilization factor
Forklift Usage Reporting, Utilization factorForklift Usage Reporting, Utilization factor
Forklift Usage Reporting, Utilization factorTed Jurca
 
An event on stem education (science,technology,engineering,math)
An event on stem education (science,technology,engineering,math)An event on stem education (science,technology,engineering,math)
An event on stem education (science,technology,engineering,math)PSTTI
 
Integración de Herramientas Webconference en Campus Virtuales
Integración de Herramientas Webconference en Campus VirtualesIntegración de Herramientas Webconference en Campus Virtuales
Integración de Herramientas Webconference en Campus VirtualesCRISEL BY AEFOL
 
Ed3 & ed4 pc
Ed3 & ed4 pcEd3 & ed4 pc
Ed3 & ed4 pcTed Jurca
 
σαρρης σχολικη βια ετεροτητα
σαρρης σχολικη βια ετεροτητασαρρης σχολικη βια ετεροτητα
σαρρης σχολικη βια ετεροτηταΡουλα Τσαγκαρη
 
Linear Vibratory Feeders
Linear Vibratory FeedersLinear Vibratory Feeders
Linear Vibratory Feederskezhassan
 
Η γη είναι στα χέρια σου
Η γη είναι στα χέρια σου Η γη είναι στα χέρια σου
Η γη είναι στα χέρια σου TINA MANTIKOU
 
Punk Rock: A History of Expressions of Emancipative Social Capital
Punk Rock: A History of Expressions of Emancipative Social CapitalPunk Rock: A History of Expressions of Emancipative Social Capital
Punk Rock: A History of Expressions of Emancipative Social CapitalCommunity Development Society
 
Pakistan Economic Survey 2014-15
Pakistan Economic Survey 2014-15Pakistan Economic Survey 2014-15
Pakistan Economic Survey 2014-15Asfar Shah
 
Architectural styles class 1
Architectural  styles class 1Architectural  styles class 1
Architectural styles class 1Dr Reeja S R
 

Viewers also liked (16)

Стратегічні партнери КНЕУ: British Council
Стратегічні партнери КНЕУ: British CouncilСтратегічні партнери КНЕУ: British Council
Стратегічні партнери КНЕУ: British Council
 
Forklift Usage Reporting, Utilization factor
Forklift Usage Reporting, Utilization factorForklift Usage Reporting, Utilization factor
Forklift Usage Reporting, Utilization factor
 
An event on stem education (science,technology,engineering,math)
An event on stem education (science,technology,engineering,math)An event on stem education (science,technology,engineering,math)
An event on stem education (science,technology,engineering,math)
 
Integración de Herramientas Webconference en Campus Virtuales
Integración de Herramientas Webconference en Campus VirtualesIntegración de Herramientas Webconference en Campus Virtuales
Integración de Herramientas Webconference en Campus Virtuales
 
Me & You
Me & YouMe & You
Me & You
 
Ed3 & ed4 pc
Ed3 & ed4 pcEd3 & ed4 pc
Ed3 & ed4 pc
 
La contaminacion
La contaminacionLa contaminacion
La contaminacion
 
σαρρης σχολικη βια ετεροτητα
σαρρης σχολικη βια ετεροτητασαρρης σχολικη βια ετεροτητα
σαρρης σχολικη βια ετεροτητα
 
Concurrent vsparallel
Concurrent vsparallelConcurrent vsparallel
Concurrent vsparallel
 
Linear Vibratory Feeders
Linear Vibratory FeedersLinear Vibratory Feeders
Linear Vibratory Feeders
 
Go global
Go globalGo global
Go global
 
Η γη είναι στα χέρια σου
Η γη είναι στα χέρια σου Η γη είναι στα χέρια σου
Η γη είναι στα χέρια σου
 
Punk Rock: A History of Expressions of Emancipative Social Capital
Punk Rock: A History of Expressions of Emancipative Social CapitalPunk Rock: A History of Expressions of Emancipative Social Capital
Punk Rock: A History of Expressions of Emancipative Social Capital
 
BOP and EXIM Policy
BOP and EXIM PolicyBOP and EXIM Policy
BOP and EXIM Policy
 
Pakistan Economic Survey 2014-15
Pakistan Economic Survey 2014-15Pakistan Economic Survey 2014-15
Pakistan Economic Survey 2014-15
 
Architectural styles class 1
Architectural  styles class 1Architectural  styles class 1
Architectural styles class 1
 

Similar to Lecture 24

Big and Fast Data - Building Infinitely Scalable Systems
Big and Fast Data - Building Infinitely Scalable SystemsBig and Fast Data - Building Infinitely Scalable Systems
Big and Fast Data - Building Infinitely Scalable SystemsFred Melo
 
New Business Applications Powered by In-Memory Technology @MIT Forum for Supp...
New Business Applications Powered by In-Memory Technology @MIT Forum for Supp...New Business Applications Powered by In-Memory Technology @MIT Forum for Supp...
New Business Applications Powered by In-Memory Technology @MIT Forum for Supp...Paul Hofmann
 
Big Data Anti-Patterns: Lessons From the Front LIne
Big Data Anti-Patterns: Lessons From the Front LIneBig Data Anti-Patterns: Lessons From the Front LIne
Big Data Anti-Patterns: Lessons From the Front LIneDouglas Moore
 
Netezza Deep Dives
Netezza Deep DivesNetezza Deep Dives
Netezza Deep DivesRush Shah
 
Hive + Amazon EMR + S3 = Elastic big data SQL analytics processing in the cloud
Hive + Amazon EMR + S3 = Elastic big data SQL analytics processing in the cloudHive + Amazon EMR + S3 = Elastic big data SQL analytics processing in the cloud
Hive + Amazon EMR + S3 = Elastic big data SQL analytics processing in the cloudJaipaul Agonus
 
Explore big data at speed of thought with Spark 2.0 and Snappydata
Explore big data at speed of thought with Spark 2.0 and SnappydataExplore big data at speed of thought with Spark 2.0 and Snappydata
Explore big data at speed of thought with Spark 2.0 and SnappydataData Con LA
 
2016 August POWER Up Your Insights - IBM System Summit Mumbai
2016 August POWER Up Your Insights - IBM System Summit Mumbai2016 August POWER Up Your Insights - IBM System Summit Mumbai
2016 August POWER Up Your Insights - IBM System Summit MumbaiAnand Haridass
 
Meta scale kognitio hadoop webinar
Meta scale kognitio hadoop webinarMeta scale kognitio hadoop webinar
Meta scale kognitio hadoop webinarKognitio
 
Vargas polyglot-persistence-cloud-edbt
Vargas polyglot-persistence-cloud-edbtVargas polyglot-persistence-cloud-edbt
Vargas polyglot-persistence-cloud-edbtGenoveva Vargas-Solar
 
Data has a better idea the in-memory data grid
Data has a better idea   the in-memory data gridData has a better idea   the in-memory data grid
Data has a better idea the in-memory data gridBogdan Dina
 
[NetApp] Simplified HA:DR Using Storage Solutions
[NetApp] Simplified HA:DR Using Storage Solutions[NetApp] Simplified HA:DR Using Storage Solutions
[NetApp] Simplified HA:DR Using Storage SolutionsPerforce
 
EMC Greenplum Database version 4.2
EMC Greenplum Database version 4.2 EMC Greenplum Database version 4.2
EMC Greenplum Database version 4.2 EMC
 
IMCSummit 2015 - Day 2 IT Business Track - Drive IMC Efficiency with Flash E...
IMCSummit 2015 - Day 2  IT Business Track - Drive IMC Efficiency with Flash E...IMCSummit 2015 - Day 2  IT Business Track - Drive IMC Efficiency with Flash E...
IMCSummit 2015 - Day 2 IT Business Track - Drive IMC Efficiency with Flash E...In-Memory Computing Summit
 
Big Data LDN 2016: Kick Start your Big Data project with Hyperconverged Infra...
Big Data LDN 2016: Kick Start your Big Data project with Hyperconverged Infra...Big Data LDN 2016: Kick Start your Big Data project with Hyperconverged Infra...
Big Data LDN 2016: Kick Start your Big Data project with Hyperconverged Infra...Matt Stubbs
 
Distributed Systems: scalability and high availability
Distributed Systems: scalability and high availabilityDistributed Systems: scalability and high availability
Distributed Systems: scalability and high availabilityRenato Lucindo
 
Ogf2008 Grid Data Caching
Ogf2008 Grid Data CachingOgf2008 Grid Data Caching
Ogf2008 Grid Data CachingJags Ramnarayan
 
useR2011 - Edlefsen
useR2011 - EdlefsenuseR2011 - Edlefsen
useR2011 - Edlefsenrusersla
 
Data Engineering for Data Scientists
Data Engineering for Data Scientists Data Engineering for Data Scientists
Data Engineering for Data Scientists jlacefie
 
Webinar: Large Scale Graph Processing with IBM Power Systems & Neo4j
Webinar: Large Scale Graph Processing with IBM Power Systems & Neo4jWebinar: Large Scale Graph Processing with IBM Power Systems & Neo4j
Webinar: Large Scale Graph Processing with IBM Power Systems & Neo4jNeo4j
 

Similar to Lecture 24 (20)

Wolfgang Lehner Technische Universitat Dresden
Wolfgang Lehner Technische Universitat DresdenWolfgang Lehner Technische Universitat Dresden
Wolfgang Lehner Technische Universitat Dresden
 
Big and Fast Data - Building Infinitely Scalable Systems
Big and Fast Data - Building Infinitely Scalable SystemsBig and Fast Data - Building Infinitely Scalable Systems
Big and Fast Data - Building Infinitely Scalable Systems
 
New Business Applications Powered by In-Memory Technology @MIT Forum for Supp...
New Business Applications Powered by In-Memory Technology @MIT Forum for Supp...New Business Applications Powered by In-Memory Technology @MIT Forum for Supp...
New Business Applications Powered by In-Memory Technology @MIT Forum for Supp...
 
Big Data Anti-Patterns: Lessons From the Front LIne
Big Data Anti-Patterns: Lessons From the Front LIneBig Data Anti-Patterns: Lessons From the Front LIne
Big Data Anti-Patterns: Lessons From the Front LIne
 
Netezza Deep Dives
Netezza Deep DivesNetezza Deep Dives
Netezza Deep Dives
 
Hive + Amazon EMR + S3 = Elastic big data SQL analytics processing in the cloud
Hive + Amazon EMR + S3 = Elastic big data SQL analytics processing in the cloudHive + Amazon EMR + S3 = Elastic big data SQL analytics processing in the cloud
Hive + Amazon EMR + S3 = Elastic big data SQL analytics processing in the cloud
 
Explore big data at speed of thought with Spark 2.0 and Snappydata
Explore big data at speed of thought with Spark 2.0 and SnappydataExplore big data at speed of thought with Spark 2.0 and Snappydata
Explore big data at speed of thought with Spark 2.0 and Snappydata
 
2016 August POWER Up Your Insights - IBM System Summit Mumbai
2016 August POWER Up Your Insights - IBM System Summit Mumbai2016 August POWER Up Your Insights - IBM System Summit Mumbai
2016 August POWER Up Your Insights - IBM System Summit Mumbai
 
Meta scale kognitio hadoop webinar
Meta scale kognitio hadoop webinarMeta scale kognitio hadoop webinar
Meta scale kognitio hadoop webinar
 
Vargas polyglot-persistence-cloud-edbt
Vargas polyglot-persistence-cloud-edbtVargas polyglot-persistence-cloud-edbt
Vargas polyglot-persistence-cloud-edbt
 
Data has a better idea the in-memory data grid
Data has a better idea   the in-memory data gridData has a better idea   the in-memory data grid
Data has a better idea the in-memory data grid
 
[NetApp] Simplified HA:DR Using Storage Solutions
[NetApp] Simplified HA:DR Using Storage Solutions[NetApp] Simplified HA:DR Using Storage Solutions
[NetApp] Simplified HA:DR Using Storage Solutions
 
EMC Greenplum Database version 4.2
EMC Greenplum Database version 4.2 EMC Greenplum Database version 4.2
EMC Greenplum Database version 4.2
 
IMCSummit 2015 - Day 2 IT Business Track - Drive IMC Efficiency with Flash E...
IMCSummit 2015 - Day 2  IT Business Track - Drive IMC Efficiency with Flash E...IMCSummit 2015 - Day 2  IT Business Track - Drive IMC Efficiency with Flash E...
IMCSummit 2015 - Day 2 IT Business Track - Drive IMC Efficiency with Flash E...
 
Big Data LDN 2016: Kick Start your Big Data project with Hyperconverged Infra...
Big Data LDN 2016: Kick Start your Big Data project with Hyperconverged Infra...Big Data LDN 2016: Kick Start your Big Data project with Hyperconverged Infra...
Big Data LDN 2016: Kick Start your Big Data project with Hyperconverged Infra...
 
Distributed Systems: scalability and high availability
Distributed Systems: scalability and high availabilityDistributed Systems: scalability and high availability
Distributed Systems: scalability and high availability
 
Ogf2008 Grid Data Caching
Ogf2008 Grid Data CachingOgf2008 Grid Data Caching
Ogf2008 Grid Data Caching
 
useR2011 - Edlefsen
useR2011 - EdlefsenuseR2011 - Edlefsen
useR2011 - Edlefsen
 
Data Engineering for Data Scientists
Data Engineering for Data Scientists Data Engineering for Data Scientists
Data Engineering for Data Scientists
 
Webinar: Large Scale Graph Processing with IBM Power Systems & Neo4j
Webinar: Large Scale Graph Processing with IBM Power Systems & Neo4jWebinar: Large Scale Graph Processing with IBM Power Systems & Neo4j
Webinar: Large Scale Graph Processing with IBM Power Systems & Neo4j
 

More from Shani729

Python tutorialfeb152012
Python tutorialfeb152012Python tutorialfeb152012
Python tutorialfeb152012Shani729
 
Python tutorial
Python tutorialPython tutorial
Python tutorialShani729
 
Interaction design _beyond_human_computer_interaction
Interaction design _beyond_human_computer_interactionInteraction design _beyond_human_computer_interaction
Interaction design _beyond_human_computer_interactionShani729
 
Fm lecturer 13(final)
Fm lecturer 13(final)Fm lecturer 13(final)
Fm lecturer 13(final)Shani729
 
Lecture slides week14-15
Lecture slides week14-15Lecture slides week14-15
Lecture slides week14-15Shani729
 
Frequent itemset mining using pattern growth method
Frequent itemset mining using pattern growth methodFrequent itemset mining using pattern growth method
Frequent itemset mining using pattern growth methodShani729
 
Dwh lecture slides-week15
Dwh lecture slides-week15Dwh lecture slides-week15
Dwh lecture slides-week15Shani729
 
Dwh lecture slides-week10
Dwh lecture slides-week10Dwh lecture slides-week10
Dwh lecture slides-week10Shani729
 
Dwh lecture slidesweek7&8
Dwh lecture slidesweek7&8Dwh lecture slidesweek7&8
Dwh lecture slidesweek7&8Shani729
 
Dwh lecture slides-week5&6
Dwh lecture slides-week5&6Dwh lecture slides-week5&6
Dwh lecture slides-week5&6Shani729
 
Dwh lecture slides-week3&4
Dwh lecture slides-week3&4Dwh lecture slides-week3&4
Dwh lecture slides-week3&4Shani729
 
Dwh lecture slides-week2
Dwh lecture slides-week2Dwh lecture slides-week2
Dwh lecture slides-week2Shani729
 
Dwh lecture slides-week1
Dwh lecture slides-week1Dwh lecture slides-week1
Dwh lecture slides-week1Shani729
 
Dwh lecture slides-week 13
Dwh lecture slides-week 13Dwh lecture slides-week 13
Dwh lecture slides-week 13Shani729
 
Dwh lecture slides-week 12&13
Dwh lecture slides-week 12&13Dwh lecture slides-week 12&13
Dwh lecture slides-week 12&13Shani729
 
Data warehousing and mining furc
Data warehousing and mining furcData warehousing and mining furc
Data warehousing and mining furcShani729
 
Lecture 40
Lecture 40Lecture 40
Lecture 40Shani729
 
Lecture 39
Lecture 39Lecture 39
Lecture 39Shani729
 
Lecture 38
Lecture 38Lecture 38
Lecture 38Shani729
 
Lecture 37
Lecture 37Lecture 37
Lecture 37Shani729
 

More from Shani729 (20)

Python tutorialfeb152012
Python tutorialfeb152012Python tutorialfeb152012
Python tutorialfeb152012
 
Python tutorial
Python tutorialPython tutorial
Python tutorial
 
Interaction design _beyond_human_computer_interaction
Interaction design _beyond_human_computer_interactionInteraction design _beyond_human_computer_interaction
Interaction design _beyond_human_computer_interaction
 
Fm lecturer 13(final)
Fm lecturer 13(final)Fm lecturer 13(final)
Fm lecturer 13(final)
 
Lecture slides week14-15
Lecture slides week14-15Lecture slides week14-15
Lecture slides week14-15
 
Frequent itemset mining using pattern growth method
Frequent itemset mining using pattern growth methodFrequent itemset mining using pattern growth method
Frequent itemset mining using pattern growth method
 
Dwh lecture slides-week15
Dwh lecture slides-week15Dwh lecture slides-week15
Dwh lecture slides-week15
 
Dwh lecture slides-week10
Dwh lecture slides-week10Dwh lecture slides-week10
Dwh lecture slides-week10
 
Dwh lecture slidesweek7&8
Dwh lecture slidesweek7&8Dwh lecture slidesweek7&8
Dwh lecture slidesweek7&8
 
Dwh lecture slides-week5&6
Dwh lecture slides-week5&6Dwh lecture slides-week5&6
Dwh lecture slides-week5&6
 
Dwh lecture slides-week3&4
Dwh lecture slides-week3&4Dwh lecture slides-week3&4
Dwh lecture slides-week3&4
 
Dwh lecture slides-week2
Dwh lecture slides-week2Dwh lecture slides-week2
Dwh lecture slides-week2
 
Dwh lecture slides-week1
Dwh lecture slides-week1Dwh lecture slides-week1
Dwh lecture slides-week1
 
Dwh lecture slides-week 13
Dwh lecture slides-week 13Dwh lecture slides-week 13
Dwh lecture slides-week 13
 
Dwh lecture slides-week 12&13
Dwh lecture slides-week 12&13Dwh lecture slides-week 12&13
Dwh lecture slides-week 12&13
 
Data warehousing and mining furc
Data warehousing and mining furcData warehousing and mining furc
Data warehousing and mining furc
 
Lecture 40
Lecture 40Lecture 40
Lecture 40
 
Lecture 39
Lecture 39Lecture 39
Lecture 39
 
Lecture 38
Lecture 38Lecture 38
Lecture 38
 
Lecture 37
Lecture 37Lecture 37
Lecture 37
 

Recently uploaded

HARMONY IN THE HUMAN BEING - Unit-II UHV-2
HARMONY IN THE HUMAN BEING - Unit-II UHV-2HARMONY IN THE HUMAN BEING - Unit-II UHV-2
HARMONY IN THE HUMAN BEING - Unit-II UHV-2RajaP95
 
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfCCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfAsst.prof M.Gokilavani
 
Past, Present and Future of Generative AI
Past, Present and Future of Generative AIPast, Present and Future of Generative AI
Past, Present and Future of Generative AIabhishek36461
 
Electronically Controlled suspensions system .pdf
Electronically Controlled suspensions system .pdfElectronically Controlled suspensions system .pdf
Electronically Controlled suspensions system .pdfme23b1001
 
VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...
VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...
VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...VICTOR MAESTRE RAMIREZ
 
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...srsj9000
 
Application of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptxApplication of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptx959SahilShah
 
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSAPPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSKurinjimalarL3
 
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerStudy on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerAnamika Sarkar
 
Sachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
Sachpazis Costas: Geotechnical Engineering: A student's Perspective IntroductionSachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
Sachpazis Costas: Geotechnical Engineering: A student's Perspective IntroductionDr.Costas Sachpazis
 
Introduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptxIntroduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptxk795866
 
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130Suhani Kapoor
 
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxDecoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxJoão Esperancinha
 
Churning of Butter, Factors affecting .
Churning of Butter, Factors affecting  .Churning of Butter, Factors affecting  .
Churning of Butter, Factors affecting .Satyam Kumar
 
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETEINFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETEroselinkalist12
 
Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024hassan khalil
 

Recently uploaded (20)

HARMONY IN THE HUMAN BEING - Unit-II UHV-2
HARMONY IN THE HUMAN BEING - Unit-II UHV-2HARMONY IN THE HUMAN BEING - Unit-II UHV-2
HARMONY IN THE HUMAN BEING - Unit-II UHV-2
 
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfCCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
 
Past, Present and Future of Generative AI
Past, Present and Future of Generative AIPast, Present and Future of Generative AI
Past, Present and Future of Generative AI
 
POWER SYSTEMS-1 Complete notes examples
POWER SYSTEMS-1 Complete notes  examplesPOWER SYSTEMS-1 Complete notes  examples
POWER SYSTEMS-1 Complete notes examples
 
young call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Service
young call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Serviceyoung call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Service
young call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Service
 
Electronically Controlled suspensions system .pdf
Electronically Controlled suspensions system .pdfElectronically Controlled suspensions system .pdf
Electronically Controlled suspensions system .pdf
 
VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...
VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...
VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...
 
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
 
Application of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptxApplication of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptx
 
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSAPPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
 
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerStudy on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
 
Sachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
Sachpazis Costas: Geotechnical Engineering: A student's Perspective IntroductionSachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
Sachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
 
Design and analysis of solar grass cutter.pdf
Design and analysis of solar grass cutter.pdfDesign and analysis of solar grass cutter.pdf
Design and analysis of solar grass cutter.pdf
 
Call Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCR
Call Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCRCall Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCR
Call Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCR
 
Introduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptxIntroduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptx
 
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
 
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxDecoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
 
Churning of Butter, Factors affecting .
Churning of Butter, Factors affecting  .Churning of Butter, Factors affecting  .
Churning of Butter, Factors affecting .
 
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETEINFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
 
Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024
 

Lecture 24

  • 1. Data WarehousingData Warehousing 11 Data WarehousingData Warehousing Lecture-24Lecture-24 Need for Speed: ParallelismNeed for Speed: Parallelism Virtual University of PakistanVirtual University of Pakistan Ahsan Abdullah Assoc. Prof. & Head Center for Agro-Informatics Research www.nu.edu.pk/cairindex.asp National University of Computers & Emerging Sciences, Islamabad Email: ahsan101@yahoo.com
  • 3. Data Warehousing 3 When to parallelize?When to parallelize? Useful for operations that access significant amountsUseful for operations that access significant amounts of data.of data. Useful for operations that can be implementedUseful for operations that can be implemented independent of each other “Divide-&-Conquer”independent of each other “Divide-&-Conquer” Parallel execution improves processing for:Parallel execution improves processing for:  Large table scans and joinsLarge table scans and joins  Creation of large indexesCreation of large indexes  Partitioned index scansPartitioned index scans  Bulk inserts, updates, and deletesBulk inserts, updates, and deletes  Aggregations and copyingAggregations and copying SizeSize SizeSize D&CD&C SizeSize D&CD&C
  • 4. Data Warehousing 4 Are you ready to parallelize?Are you ready to parallelize? Parallelism can be exploited, if there is…Parallelism can be exploited, if there is…  Symmetric multi-processors (SMP), clusters, or MassivelySymmetric multi-processors (SMP), clusters, or Massively Parallel (MPP) systemsParallel (MPP) systems ANDAND  Sufficient I/O bandwidthSufficient I/O bandwidth ANDAND  Underutilized or intermittently used CPUs (for example,Underutilized or intermittently used CPUs (for example, systems where CPU usage is typically less than 30%)systems where CPU usage is typically less than 30%) ANDAND  Sufficient memory to support additional memory-intensiveSufficient memory to support additional memory-intensive processes such as sorts, hashing, and I/O buffersprocesses such as sorts, hashing, and I/O buffers Word of cautionWord of caution Parallelism can reduce system performance on over-utilized systems or systems with small I/O bandwidth.
  • 5. Data Warehousing 5 Scalability – Size is NOT everythingScalability – Size is NOT everything Number of ConcurrentNumber of Concurrent UsersUsers • Simple table retrieval • Moderate complexity Join • Propensity analysis • Clustering Complexity of TechniqueComplexity of Technique • Hash based • B-Tree • Multiple • Bitmapped Index usageIndex usage Amount of detailed dataAmount of detailed data Complexity of Data ModelComplexity of Data Model       
  • 6. Data Warehousing 6 Scalability- Speed-Up & Scale-UpScalability- Speed-Up & Scale-Up Speed-UpSpeed-Up More resources means proportionally less time for given amount of data. Scale-UpScale-Up If resources increased in proportion to increase in data size, time is constant. Degree of Parallelism Transactions/Sec Degree of Parallelism Secs/Transaction Ideal Ideal Real
  • 7. Data Warehousing 7 Quantifying Speed-upQuantifying Speed-up Sequential Execution IdealIdeal Parallel Execution 18 time units 6 time units Task-1 Task-2 Task-3 Control work (“overhead”) Speedup = 18 = 300% 6 Ts: Time on serial processor Tm: Time on multiple processors Speedup = Ts Tm Task-1 Task-2 Task-3
  • 8. Data Warehousing 8 Speed-Up & Amdahl’s LawSpeed-Up & Amdahl’s Law Reveals maximum expected speedup from parallel algorithms given the proportion of task that must be computed sequentially. It gives the speedup S as ff is the fraction of the problem that must be computed sequentially NN is the number of processors As ff approaches 0, SS approaches NN Example-1: ff = 5% and NN = 100 then SS = 16.8 Example-2: ff = 10% and NN = 200 then SS = 9.56 Not 1:1 Ratio Only formula and explanation will go to graphics
  • 9. Data Warehousing 9 Amdahl’s Law: Limits of parallelizationAmdahl’s Law: Limits of parallelization For less than 80% parallelism, the speedup drastically drops. At 90% parallelism, 128128 processors give performance of less than 1010 processors. 1 2 3 4 5 6 7 8 9 10 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1 % sequential code (f) Speedup(S) N=2 N=4 N=8 N=16 N=32 N=64 N=128
  • 10. Data Warehousing 10 Parallelization OLTP Vs. DSSParallelization OLTP Vs. DSS There is a big difference. DSS Parallelization of a SINGLE query OLTP Parallelization of MULTIPLE queries Or Batch updates in parallel
  • 11. Data Warehousing 11 Brief Intro to Parallel ProcessingBrief Intro to Parallel Processing  Parallel Hardware ArchitecturesParallel Hardware Architectures  Symmetric Multi Processing (SMP)Symmetric Multi Processing (SMP)  Distributed Memory or Massively Parallel ProcessingDistributed Memory or Massively Parallel Processing (MPP)(MPP)  Non-uniform Memory Access (NUMA)Non-uniform Memory Access (NUMA)  Parallel Software ArchitecturesParallel Software Architectures  Shared MemoryShared Memory  Shard DiskShard Disk  Shared NothingShared Nothing  Types of parallelismTypes of parallelism  Data ParallelismData Parallelism  Spatial ParallelismSpatial Parallelism Shared Everything
  • 12. Data Warehousing 12 Symmetrical Multi Processing (SMP)Symmetrical Multi Processing (SMP)  A number of independent I/O and number ofA number of independent I/O and number of processors all sharing access to a single large memoryprocessors all sharing access to a single large memory space.space. Main Memory I/O I/O I/O P1 P2 P3 P4  Typically each CPU executes its job independently.Typically each CPU executes its job independently.  Supports both Multi-Tasking and Parallel Processing.Supports both Multi-Tasking and Parallel Processing.  Have to deal with issues such as Cache Coherence, Processor AffinityHave to deal with issues such as Cache Coherence, Processor Affinity and Hot Spots.and Hot Spots. Yellow will not go to graphics
  • 13. Data Warehousing 13  Composed of a number of self-contained, self-controlled nodesComposed of a number of self-contained, self-controlled nodes connected through a network interface.connected through a network interface.  Each node contains its own CPU, processor, memory and I/O.Each node contains its own CPU, processor, memory and I/O.  Architecture better known as Massively Parallel Processing (MPP)Architecture better known as Massively Parallel Processing (MPP) or cluster computing.or cluster computing.  Memory is distributed across all nodes.Memory is distributed across all nodes. Distributed Memory MachinesDistributed Memory Machines Bus, Switch or Network I/O P Memory I/O P Memory I/O P Memory  Network has the tendency to become the bottleneck.Network has the tendency to become the bottleneck.  Issues fundamentally different from those in SMP.Issues fundamentally different from those in SMP. Yellow will not go to graphics Node
  • 14. Data Warehousing 14 A little bit of both worlds !A little bit of both worlds ! Distributed Shared Memory MachinesDistributed Shared Memory Machines Interconnection Network Main Memory I/O I/O I/O P1 P2 P3 P4 Main Memory I/O I/O I/O P1 P2 P3 P4 Main Memory I/O I/O I/O P1 P2 P3 P4 Main Memory I/O I/O I/O P1 P2 P3 P4
  • 15. Data Warehousing 15 Shared disk RDBMS ArchitectureShared disk RDBMS Architecture Clients/Users Shared Disk Interconnect Adv High level of fault tolerance Dis Adv Serialization due to locking Interconnect can become a bottleneck Yellow ill not go to graphics
  • 16. Data Warehousing 16 Shared Nothing RDBMS ArchitectureShared Nothing RDBMS Architecture Clients/Users Adv Data ownership changes infrequently There is no locking Dis Adv Data availability low on failure Very careful with data distribution Redistribution is expensive Yellow ill not go to graphics
  • 17. Data Warehousing 17 Shared disk Vs. Shared Nothing RDBMSShared disk Vs. Shared Nothing RDBMS  Important note:Important note: Do not confuse RDBMSDo not confuse RDBMS architecture with hardware architecture.architecture with hardware architecture.  Shared nothing databases can run on sharedShared nothing databases can run on shared everything (SMP or NUMA) hardware.everything (SMP or NUMA) hardware.  Shared disk databases can run on sharedShared disk databases can run on shared nothing (MPP) hardware.nothing (MPP) hardware. This slide will not go to graphics

Editor's Notes

  1. <number>
  2. <number>
  3. <number>
  4. <number>
  5. <number>
  6. <number>
  7. <number>