SlideShare uma empresa Scribd logo
1 de 34
Baixar para ler offline
King Abdullah University of Science and
             Technology

       CS348: Cloud Computing

    Large-Scale Graph Processing


               Zuhair Khayyat
               10/March/2013
The Importance of Graphs
     ●   A graph is a mathematical structure that represents pairwise
         relations between entities or objects. Such as:

               –   Physical communication networks

               –   Web pages links

               –   Social interaction graphs

               –   Protein-to-protein interactions

     ●   Graphs are used to abstract application-specific features into a
         generic problem, which makes Graph Algorithms applicable to
         a wide variety of applications*.
*http://11011110.livejournal.com/164613.html
Graph algorithm characteristics*
    ●   Data-Drivin Computations: Computations in graph
        algorithms depends on the structure of the graph. It is hard to
        predict the algorithm behavior

    ●   Unstructured Problems: Different graph distributions
        requires distinct load balancing techniques.

    ●   Poor Data Locality.

    ●   High Data Access to Computation Ratio: Runtime can be
        dominated by waiting memory fetches.


*Lumsdaine et. al, Challenges in Parallel Graph Processing
Challenges in Graph processing
    ●   Graphs grows fast; a single computer either cannot fit a large
        graph into memory or it fits the large graph with huge cost.

    ●   Custom implementations for a single graph algorithm requires
        time and effort and cannot be used on other algorithms

    ●   Scientific parallel applications (i.e. parallel PDE solvers)
        cannot fully adapt to the computational requirements of graph
        algorithms*.

    ●   Fault tolerance is required to support large scale processing.


*Lumsdaine et. al, Challenges in Parallel Graph Processing
Why Cloud in Graph Processing
●   Easy to scale up and down; provision machines
    depending on your graph size.
●   Cheaper than buying a physical large cluster.
●   Can be used in the cloud as “Software as a services” to
    support online social networks.
Large Scale Graph Processing
●   Systems that tries to solve the problem of processing large
    graphs in parallel:
          –   MapReduce – auto task scheduling, distributed disk
               based computations:
                   ●  Pegasus
                   ● X-Rime


          –   Pregel - Bulk Synchronous Parallel Graph Processing:
                   ● Giraph
                   ● GPS


                   ● Mizan


          –   GraphLab – Asynchronous Parallel Graph Processing.
Pregel* Graph Processing
   ●   Consists of a series of synchronized iterations
       (supersteps); based on Bulk Synchronous Parallel
       computing model. Each superstep consists of:
             –   Concurrent computations
             –   Communication
             –   Synchronization barrier
   ●   Vertex centric computation, the user's compute() function
       is applied individually on each vertex, which is able to:
             –   Send message to vertices in the next superstep
             –   Receive messages from the previous superstep

*Malewicz et. al., Pregel: A System for Large-Scale Graph Processing
Pregel messaging Example 1
Superstep 0

       A      B



       D      C
Pregel messaging Example 1
Superstep 0            Superstep 1
                                         22
       A      B               A               B

                                     9            15


       D      C               D               C
                                         47
Pregel messaging Example 1
Superstep 0                          Superstep 1
                                                       22
        A              B                    A               B

                                                   9            15


        D              C                    D               C
                                                       47
Superstep 2
                  -2       22, 9
       A               B

              7            55


 47    D               C        15
                  14
Pregel messaging Example 1
Superstep 0                          Superstep 1
                                                       22
        A              B                    A               B

                                                   9            15


        D              C                    D               C
                                                       47
Superstep 2                          Superstep 3
                  -2       22, 9                        5        -2, 7
       A               B                     A              B

              7            55                      5            98


 47    D               C        15     14    D              C        55
                  14                                    9
Vertex's State
 ●   All vertices are active at superstep 1

 ●   All active vertices runs user function compute() at any
     superstep

 ●   A vertex deactivates itself by voting to halt, but returns to
     active if it received messages.

 ●   Pregel terminates of all vertices are inactive
Pregel Example 2
    Data Distribution
(Hash-based partitioning)

                             Worker 1          Worker 2           Worker 3



 Computation



 Communication
                                        Synchronization Barrier

                                         Yes               No
                 Terminate                       Done?
Pregel Example 3 – Max
       3     6     2     1
Pregel Example 3 – Max
       3     6     2     1


       6     6     2     6
Pregel Example 3 – Max
       3     6     2     1


       6     6     2     6


       6     6     6     6
Pregel Example 3 – Max
       3     6     2     1


       6     6     2     6


       6     6     6     6

       6     6     6     6
Pregel Example 4 – Max code                                 Vertex value
                                                               class
Class MaxFindVertex:public Vertex<double, void, double> {   Edge value class
  public:
                                                            Message class
  virtual void Compute(MessageIterator* msgs) {

      int currMax = GetValue();                             Send current Max
      SendMessageToAllNeighbors(currMax);
                                                            Check messages
      for ( ; !msgs­>Done(); msgs­>Next()) {                and store max
          if (msgs­>Value() > currMax)

               currMax = msgs­>Value();
                                                            Store new max
      }

      if (currMax > GetValue())

         *MutableValue() = currMax;

      else VoteToHalt();

  }

};
Pregel Message Optimizations
●   Message Combiners:

         –   A special function that combines the incoming
               messages for a vertex before running compute()

         –   Can run on the message sending or receiving worker
●   Global Aggregators :

         –   A shared object accessible to all vertices. that is
               synchronized at the end of each superstep, i.e., max
               and min aggregators.
Pregel Guarantees
 ●   Scalability: process vertices in parallel, overlap
     computation and communication.
 ●   Messages will be received without duplication in any
     order.
 ●   Fault tolerance through check points
Pregel's Limitations
 ●   Pregel's superstep waits for all workers to finish at the
     synchronization barrier. That is, it waits for the slowest
     worker to finish.
 ●   Smart partitioning can solve the load balancing problem
     for static algorithms. However not all algorithms are
     static, algorithms can have a variable execution behaviors
     which leads to an unbalanced supersteps.
Mizan* Graph Processing
      ●   Mizan is an open source graph processing system, similar
          to Pregel, developed locally at KAUST.
      ●   Mizan employs dynamic graph repartitioning without
          affecting the correctness of graph processing to
          rebalanced the execution of the supersteps for all types of
          workloads.




*Khayyat et. al., Mizan: A System for Dynamic Load Balancing in Large-scale
Graph Processing
Source of Imbalance in BSP
Source of Imbalance in BSP
Types of Graph Algorithms
 ●   Stationary Graph Algorithms:

           –   Algorithms with fixed message distribution across superstep

           –   All vertices are either active or inactive at same time

           –   i.e. PageRank, Diameter Estimation and weakly connected
                 components.

 ●   Non-stationary Graph Algorithms

           –   Algorithms with variable message distribution across supersteps

           –   Vertices can be active and inactive independent to others

           –   i.e. Distributed Minimal spanning tree
Mizan architecture
 ●   Each Mizan worker contains three distinct main
     components: BSP Processor, communicator and storage
     manager.
 ●   The distributed hash table (DHT) is used to maintain the
     location of each vertex
 ●   The migration planner interacts

     with other components during

     the BSP barrier
Mizan's Barriers
Dynamic migration: Statistics
 ●   Mizan monitors the following for every vertex:
          –   Response time
          –   Remote outgoing messages
          –   Incoming messages
Dynamic migration: planning
 ●   Mizan's migration planner runs after the BSP barrier and creates a
     new barrier. The planning includes the following steps:

      –   Identifying unbalanced workers.

      –   Identifying migration objective:
            ●   Response time
            ●   Incoming messages
            ●   Outgoing messages
      –   Pair over-utilized workers with underutilized

      –   Select vertices to migrate
Mizan's Migration Work-flow
Mizan PageRank Compute() Example
void compute(messageIterator<mDouble> * messages, userVertexObject<mLong, mDouble, 
mDouble, mLong> * data,messageManager<mLong, mDouble, mDouble, mLong> * comm) {

       double currVal = data­>getVertexValue().getValue();
       double newVal = 0;  double c = 0.85;

       while (messages­>hasNext()) {
            double tmp = messages­>getNext().getValue();              Processing
            newVal = newVal + tmp;                                    Messages
       }

       newVal = newVal * c + (1.0 ­ c) / ((double) vertexTotal);
       mDouble outVal(newVal / ((double) data­>getOutEdgeCount()));

       if (data­>getCurrentSS() <= maxSuperStep) {
          for (int i = 0; i < data­>getOutEdgeCount(); i++) {         Termination
               comm­>sendMessage(data­>getOutEdgeID(i), outVal);
               data­>getOutEdgeID(i);                                  Condition
          }
        } else {
           data­>voteToHalt();
        }                                                             Sending to
                                                                      Neighbors
      data­>setVertexValue(mDouble(newVal));
}
Mizan PageRank Combiner Example
void combineMessages(mLong dst, messageIterator<mDouble> * 
messages,messageManager<mLong, mDouble, mDouble, mLong> * mManager) {

       double newVal = 0;

       while (messages­>hasNext()) {
              double tmp = messages­>getNext().getValue();
              newVal = newVal + tmp;
       }

       mDouble messageOut(newVal);
       mManager­>sendMessage(dst,messageOut);
}
Mizan Max Aggregator Example
class maxAggregator: public IAggregator<mLong> {
Public:
       mlong aggValue;

       maxAggregator() {
          aggValue.setValue(0);
       }

       void aggregate(mLong value) {
           if (value > aggValue) {
               aggValue = value;
           }
       }

       mLong getValue() {
            return aggValue;
       }

       void setValue(mLong value) {
            this­>aggValue = value;
       }
       
       virtual ~maxAggregator() {}
};
Class Assignment
 ●   Your assignment is to configure, install and run Mizan on
     a single Linux machine throw following this tutorial:
     https://thegraphsblog.wordpress.com/mizan-on-ubuntu/
 ●   By the end of the tutorial, you should be able to execute
     the command on your machine:
     mpirun ­np 2 ./Mizan­0.1b ­u ubuntu ­g web­Google.txt ­w 2

 ●   Deliverables: you store the output of of the above
     command and submit it by Wednesday's class.
 ●   Any questions regarding the tutorial or to get an account
     for a Ubuntu machine, contact me on:
     zuhair.khayyat@kaust.edu.sa

Mais conteúdo relacionado

Mais procurados

Briefing - The Atlast V Aft Bulkhead Carrier Update - Past Missions, Upcoming...
Briefing - The Atlast V Aft Bulkhead Carrier Update - Past Missions, Upcoming...Briefing - The Atlast V Aft Bulkhead Carrier Update - Past Missions, Upcoming...
Briefing - The Atlast V Aft Bulkhead Carrier Update - Past Missions, Upcoming...
Dave Callen
 
[Capella Day 2019] Model execution and system simulation in Capella
[Capella Day 2019] Model execution and system simulation in Capella[Capella Day 2019] Model execution and system simulation in Capella
[Capella Day 2019] Model execution and system simulation in Capella
Obeo
 
Innovative Solar Array Drive Assembly for CubeSat Satellite
Innovative Solar Array Drive Assembly for CubeSat SatelliteInnovative Solar Array Drive Assembly for CubeSat Satellite
Innovative Solar Array Drive Assembly for CubeSat Satellite
Michele Marino
 
MapReduce : Simplified Data Processing on Large Clusters
MapReduce : Simplified Data Processing on Large ClustersMapReduce : Simplified Data Processing on Large Clusters
MapReduce : Simplified Data Processing on Large Clusters
Abolfazl Asudeh
 
Distributed Convex Optimization Thesis - Behroz Sikander
Distributed Convex Optimization Thesis - Behroz SikanderDistributed Convex Optimization Thesis - Behroz Sikander
Distributed Convex Optimization Thesis - Behroz Sikander
rogerz1234567
 
Insight Demo
Insight DemoInsight Demo
Insight Demo
reza-asad
 
Insight Recent Demo
Insight Recent DemoInsight Recent Demo
Insight Recent Demo
reza-asad
 

Mais procurados (20)

SMiLE: Design and Development of an ISS Payload for Liquid Behavior Study in ...
SMiLE: Design and Development of an ISS Payload for Liquid Behavior Study in ...SMiLE: Design and Development of an ISS Payload for Liquid Behavior Study in ...
SMiLE: Design and Development of an ISS Payload for Liquid Behavior Study in ...
 
Briefing - The Atlast V Aft Bulkhead Carrier Update - Past Missions, Upcoming...
Briefing - The Atlast V Aft Bulkhead Carrier Update - Past Missions, Upcoming...Briefing - The Atlast V Aft Bulkhead Carrier Update - Past Missions, Upcoming...
Briefing - The Atlast V Aft Bulkhead Carrier Update - Past Missions, Upcoming...
 
Graph processing
Graph processingGraph processing
Graph processing
 
Introduction to map reduce
Introduction to map reduceIntroduction to map reduce
Introduction to map reduce
 
[Capella Day 2019] Model execution and system simulation in Capella
[Capella Day 2019] Model execution and system simulation in Capella[Capella Day 2019] Model execution and system simulation in Capella
[Capella Day 2019] Model execution and system simulation in Capella
 
Innovative Solar Array Drive Assembly for CubeSat Satellite
Innovative Solar Array Drive Assembly for CubeSat SatelliteInnovative Solar Array Drive Assembly for CubeSat Satellite
Innovative Solar Array Drive Assembly for CubeSat Satellite
 
Mapreduce advanced
Mapreduce advancedMapreduce advanced
Mapreduce advanced
 
Modeling & Simulation of CubeSat-based Missions'Concept of Operations
Modeling & Simulation of CubeSat-based Missions'Concept of OperationsModeling & Simulation of CubeSat-based Missions'Concept of Operations
Modeling & Simulation of CubeSat-based Missions'Concept of Operations
 
Flink Forward Berlin 2017: Matt Zimmer - Custom, Complex Windows at Scale Usi...
Flink Forward Berlin 2017: Matt Zimmer - Custom, Complex Windows at Scale Usi...Flink Forward Berlin 2017: Matt Zimmer - Custom, Complex Windows at Scale Usi...
Flink Forward Berlin 2017: Matt Zimmer - Custom, Complex Windows at Scale Usi...
 
Progress_190118
Progress_190118Progress_190118
Progress_190118
 
Apache YARN Federation and Tez at Microsoft, Anupam Upadhyay, Adrian Nicoara,...
Apache YARN Federation and Tez at Microsoft, Anupam Upadhyay, Adrian Nicoara,...Apache YARN Federation and Tez at Microsoft, Anupam Upadhyay, Adrian Nicoara,...
Apache YARN Federation and Tez at Microsoft, Anupam Upadhyay, Adrian Nicoara,...
 
Virtual Flink Forward 2020: Autoscaling Flink at Netflix - Timothy Farkas
Virtual Flink Forward 2020: Autoscaling Flink at Netflix - Timothy FarkasVirtual Flink Forward 2020: Autoscaling Flink at Netflix - Timothy Farkas
Virtual Flink Forward 2020: Autoscaling Flink at Netflix - Timothy Farkas
 
MapReduce : Simplified Data Processing on Large Clusters
MapReduce : Simplified Data Processing on Large ClustersMapReduce : Simplified Data Processing on Large Clusters
MapReduce : Simplified Data Processing on Large Clusters
 
Distributed Convex Optimization Thesis - Behroz Sikander
Distributed Convex Optimization Thesis - Behroz SikanderDistributed Convex Optimization Thesis - Behroz Sikander
Distributed Convex Optimization Thesis - Behroz Sikander
 
Insight Demo
Insight DemoInsight Demo
Insight Demo
 
Insight Recent Demo
Insight Recent DemoInsight Recent Demo
Insight Recent Demo
 
Braxton McKee, Founder & CEO, Ufora at MLconf SF - 11/13/15
Braxton McKee, Founder & CEO, Ufora at MLconf SF - 11/13/15Braxton McKee, Founder & CEO, Ufora at MLconf SF - 11/13/15
Braxton McKee, Founder & CEO, Ufora at MLconf SF - 11/13/15
 
RTX Kernal
RTX KernalRTX Kernal
RTX Kernal
 
MapReduce
MapReduceMapReduce
MapReduce
 
Scylla Summit 2022: How to Migrate a Counter Table for 68 Billion Records
Scylla Summit 2022: How to Migrate a Counter Table for 68 Billion RecordsScylla Summit 2022: How to Migrate a Counter Table for 68 Billion Records
Scylla Summit 2022: How to Migrate a Counter Table for 68 Billion Records
 

Semelhante a Large Graph Processing

Pregel: A System For Large Scale Graph Processing
Pregel: A System For Large Scale Graph ProcessingPregel: A System For Large Scale Graph Processing
Pregel: A System For Large Scale Graph Processing
Riyad Parvez
 
MHH_20Feb_2012111111111111111111111111111.ppt
MHH_20Feb_2012111111111111111111111111111.pptMHH_20Feb_2012111111111111111111111111111.ppt
MHH_20Feb_2012111111111111111111111111111.ppt
BiHongPhc
 

Semelhante a Large Graph Processing (20)

Pregel: A System For Large Scale Graph Processing
Pregel: A System For Large Scale Graph ProcessingPregel: A System For Large Scale Graph Processing
Pregel: A System For Large Scale Graph Processing
 
Pregel reading circle
Pregel reading circlePregel reading circle
Pregel reading circle
 
MHH_20Feb_2012111111111111111111111111111.ppt
MHH_20Feb_2012111111111111111111111111111.pptMHH_20Feb_2012111111111111111111111111111.ppt
MHH_20Feb_2012111111111111111111111111111.ppt
 
Optimization for Deep Networks (D2L1 2017 UPC Deep Learning for Computer Vision)
Optimization for Deep Networks (D2L1 2017 UPC Deep Learning for Computer Vision)Optimization for Deep Networks (D2L1 2017 UPC Deep Learning for Computer Vision)
Optimization for Deep Networks (D2L1 2017 UPC Deep Learning for Computer Vision)
 
Optimizing Deep Networks (D1L6 Insight@DCU Machine Learning Workshop 2017)
Optimizing Deep Networks (D1L6 Insight@DCU Machine Learning Workshop 2017)Optimizing Deep Networks (D1L6 Insight@DCU Machine Learning Workshop 2017)
Optimizing Deep Networks (D1L6 Insight@DCU Machine Learning Workshop 2017)
 
Computer Graphics - Lecture 01 - 3D Programming I
Computer Graphics - Lecture 01 - 3D Programming IComputer Graphics - Lecture 01 - 3D Programming I
Computer Graphics - Lecture 01 - 3D Programming I
 
Mining quasi bicliques using giraph
Mining quasi bicliques using giraphMining quasi bicliques using giraph
Mining quasi bicliques using giraph
 
Presentation on "Mizan: A System for Dynamic Load Balancing in Large-scale Gr...
Presentation on "Mizan: A System for Dynamic Load Balancing in Large-scale Gr...Presentation on "Mizan: A System for Dynamic Load Balancing in Large-scale Gr...
Presentation on "Mizan: A System for Dynamic Load Balancing in Large-scale Gr...
 
Time-Evolving Graph Processing On Commodity Clusters
Time-Evolving Graph Processing On Commodity ClustersTime-Evolving Graph Processing On Commodity Clusters
Time-Evolving Graph Processing On Commodity Clusters
 
Pregel
PregelPregel
Pregel
 
Greenplum Overview for Postgres Hackers - Greenplum Summit 2018
Greenplum Overview for Postgres Hackers - Greenplum Summit 2018Greenplum Overview for Postgres Hackers - Greenplum Summit 2018
Greenplum Overview for Postgres Hackers - Greenplum Summit 2018
 
Narayanan Sundaram, Research Scientist, Intel Labs at MLconf SF - 11/13/15
Narayanan Sundaram, Research Scientist, Intel Labs at MLconf SF - 11/13/15Narayanan Sundaram, Research Scientist, Intel Labs at MLconf SF - 11/13/15
Narayanan Sundaram, Research Scientist, Intel Labs at MLconf SF - 11/13/15
 
Advanced Spark Programming - Part 2 | Big Data Hadoop Spark Tutorial | CloudxLab
Advanced Spark Programming - Part 2 | Big Data Hadoop Spark Tutorial | CloudxLabAdvanced Spark Programming - Part 2 | Big Data Hadoop Spark Tutorial | CloudxLab
Advanced Spark Programming - Part 2 | Big Data Hadoop Spark Tutorial | CloudxLab
 
Graph Neural Network #2-1 (PinSage)
Graph Neural Network #2-1 (PinSage)Graph Neural Network #2-1 (PinSage)
Graph Neural Network #2-1 (PinSage)
 
Hpg2011 papers kazakov
Hpg2011 papers kazakovHpg2011 papers kazakov
Hpg2011 papers kazakov
 
New Directions for Mahout
New Directions for MahoutNew Directions for Mahout
New Directions for Mahout
 
Introduction to Machine Learning with Spark
Introduction to Machine Learning with SparkIntroduction to Machine Learning with Spark
Introduction to Machine Learning with Spark
 
PREDIcT
PREDIcTPREDIcT
PREDIcT
 
Attention is all you need (UPC Reading Group 2018, by Santi Pascual)
Attention is all you need (UPC Reading Group 2018, by Santi Pascual)Attention is all you need (UPC Reading Group 2018, by Santi Pascual)
Attention is all you need (UPC Reading Group 2018, by Santi Pascual)
 
RCIM 2008 - Modello Generale
RCIM 2008 - Modello GeneraleRCIM 2008 - Modello Generale
RCIM 2008 - Modello Generale
 

Mais de Zuhair khayyat

Graphlab under the hood
Graphlab under the hoodGraphlab under the hood
Graphlab under the hood
Zuhair khayyat
 

Mais de Zuhair khayyat (10)

Scaling Big Data Cleansing
Scaling Big Data CleansingScaling Big Data Cleansing
Scaling Big Data Cleansing
 
BigDansing presentation slides for KAUST
BigDansing presentation slides for KAUSTBigDansing presentation slides for KAUST
BigDansing presentation slides for KAUST
 
IEJoin and Big Data Cleansing
IEJoin and Big Data CleansingIEJoin and Big Data Cleansing
IEJoin and Big Data Cleansing
 
BigDansing presentation slides for SIGMOD 2015
BigDansing presentation slides for SIGMOD 2015BigDansing presentation slides for SIGMOD 2015
BigDansing presentation slides for SIGMOD 2015
 
Mizan: A System for Dynamic Load Balancing in Large-scale Graph Processing
Mizan: A System for Dynamic Load Balancing in Large-scale Graph ProcessingMizan: A System for Dynamic Load Balancing in Large-scale Graph Processing
Mizan: A System for Dynamic Load Balancing in Large-scale Graph Processing
 
Google appengine
Google appengineGoogle appengine
Google appengine
 
MapReduce
MapReduceMapReduce
MapReduce
 
Kineograph
KineographKineograph
Kineograph
 
Graphlab under the hood
Graphlab under the hoodGraphlab under the hood
Graphlab under the hood
 
Dynamo db
Dynamo dbDynamo db
Dynamo db
 

Último

1029 - Danh muc Sach Giao Khoa 10 . pdf
1029 -  Danh muc Sach Giao Khoa 10 . pdf1029 -  Danh muc Sach Giao Khoa 10 . pdf
1029 - Danh muc Sach Giao Khoa 10 . pdf
QucHHunhnh
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
kauryashika82
 
Gardella_Mateo_IntellectualProperty.pdf.
Gardella_Mateo_IntellectualProperty.pdf.Gardella_Mateo_IntellectualProperty.pdf.
Gardella_Mateo_IntellectualProperty.pdf.
MateoGardella
 
Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptx
negromaestrong
 
Making and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdfMaking and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdf
Chris Hunter
 

Último (20)

Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdf
 
Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024
 
1029 - Danh muc Sach Giao Khoa 10 . pdf
1029 -  Danh muc Sach Giao Khoa 10 . pdf1029 -  Danh muc Sach Giao Khoa 10 . pdf
1029 - Danh muc Sach Giao Khoa 10 . pdf
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
 
ICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptx
 
Gardella_Mateo_IntellectualProperty.pdf.
Gardella_Mateo_IntellectualProperty.pdf.Gardella_Mateo_IntellectualProperty.pdf.
Gardella_Mateo_IntellectualProperty.pdf.
 
Class 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdfClass 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdf
 
Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptx
 
Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..
 
Web & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfWeb & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdf
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy Consulting
 
Paris 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityParis 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activity
 
Accessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactAccessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impact
 
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17  How to Extend Models Using Mixin ClassesMixin Classes in Odoo 17  How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17
 
Making and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdfMaking and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdf
 
Holdier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfHoldier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdf
 
Unit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxUnit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptx
 
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
 
Application orientated numerical on hev.ppt
Application orientated numerical on hev.pptApplication orientated numerical on hev.ppt
Application orientated numerical on hev.ppt
 

Large Graph Processing

  • 1. King Abdullah University of Science and Technology CS348: Cloud Computing Large-Scale Graph Processing Zuhair Khayyat 10/March/2013
  • 2. The Importance of Graphs ● A graph is a mathematical structure that represents pairwise relations between entities or objects. Such as: – Physical communication networks – Web pages links – Social interaction graphs – Protein-to-protein interactions ● Graphs are used to abstract application-specific features into a generic problem, which makes Graph Algorithms applicable to a wide variety of applications*. *http://11011110.livejournal.com/164613.html
  • 3. Graph algorithm characteristics* ● Data-Drivin Computations: Computations in graph algorithms depends on the structure of the graph. It is hard to predict the algorithm behavior ● Unstructured Problems: Different graph distributions requires distinct load balancing techniques. ● Poor Data Locality. ● High Data Access to Computation Ratio: Runtime can be dominated by waiting memory fetches. *Lumsdaine et. al, Challenges in Parallel Graph Processing
  • 4. Challenges in Graph processing ● Graphs grows fast; a single computer either cannot fit a large graph into memory or it fits the large graph with huge cost. ● Custom implementations for a single graph algorithm requires time and effort and cannot be used on other algorithms ● Scientific parallel applications (i.e. parallel PDE solvers) cannot fully adapt to the computational requirements of graph algorithms*. ● Fault tolerance is required to support large scale processing. *Lumsdaine et. al, Challenges in Parallel Graph Processing
  • 5. Why Cloud in Graph Processing ● Easy to scale up and down; provision machines depending on your graph size. ● Cheaper than buying a physical large cluster. ● Can be used in the cloud as “Software as a services” to support online social networks.
  • 6. Large Scale Graph Processing ● Systems that tries to solve the problem of processing large graphs in parallel: – MapReduce – auto task scheduling, distributed disk based computations: ● Pegasus ● X-Rime – Pregel - Bulk Synchronous Parallel Graph Processing: ● Giraph ● GPS ● Mizan – GraphLab – Asynchronous Parallel Graph Processing.
  • 7. Pregel* Graph Processing ● Consists of a series of synchronized iterations (supersteps); based on Bulk Synchronous Parallel computing model. Each superstep consists of: – Concurrent computations – Communication – Synchronization barrier ● Vertex centric computation, the user's compute() function is applied individually on each vertex, which is able to: – Send message to vertices in the next superstep – Receive messages from the previous superstep *Malewicz et. al., Pregel: A System for Large-Scale Graph Processing
  • 8. Pregel messaging Example 1 Superstep 0 A B D C
  • 9. Pregel messaging Example 1 Superstep 0 Superstep 1 22 A B A B 9 15 D C D C 47
  • 10. Pregel messaging Example 1 Superstep 0 Superstep 1 22 A B A B 9 15 D C D C 47 Superstep 2 -2 22, 9 A B 7 55 47 D C 15 14
  • 11. Pregel messaging Example 1 Superstep 0 Superstep 1 22 A B A B 9 15 D C D C 47 Superstep 2 Superstep 3 -2 22, 9 5 -2, 7 A B A B 7 55 5 98 47 D C 15 14 D C 55 14 9
  • 12. Vertex's State ● All vertices are active at superstep 1 ● All active vertices runs user function compute() at any superstep ● A vertex deactivates itself by voting to halt, but returns to active if it received messages. ● Pregel terminates of all vertices are inactive
  • 13. Pregel Example 2 Data Distribution (Hash-based partitioning) Worker 1 Worker 2 Worker 3 Computation Communication Synchronization Barrier Yes No Terminate Done?
  • 14. Pregel Example 3 – Max 3 6 2 1
  • 15. Pregel Example 3 – Max 3 6 2 1 6 6 2 6
  • 16. Pregel Example 3 – Max 3 6 2 1 6 6 2 6 6 6 6 6
  • 17. Pregel Example 3 – Max 3 6 2 1 6 6 2 6 6 6 6 6 6 6 6 6
  • 18. Pregel Example 4 – Max code Vertex value class Class MaxFindVertex:public Vertex<double, void, double> { Edge value class   public: Message class   virtual void Compute(MessageIterator* msgs) {       int currMax = GetValue(); Send current Max       SendMessageToAllNeighbors(currMax); Check messages       for ( ; !msgs­>Done(); msgs­>Next()) { and store max           if (msgs­>Value() > currMax)                currMax = msgs­>Value(); Store new max       }       if (currMax > GetValue())          *MutableValue() = currMax;       else VoteToHalt();   } };
  • 19. Pregel Message Optimizations ● Message Combiners: – A special function that combines the incoming messages for a vertex before running compute() – Can run on the message sending or receiving worker ● Global Aggregators : – A shared object accessible to all vertices. that is synchronized at the end of each superstep, i.e., max and min aggregators.
  • 20. Pregel Guarantees ● Scalability: process vertices in parallel, overlap computation and communication. ● Messages will be received without duplication in any order. ● Fault tolerance through check points
  • 21. Pregel's Limitations ● Pregel's superstep waits for all workers to finish at the synchronization barrier. That is, it waits for the slowest worker to finish. ● Smart partitioning can solve the load balancing problem for static algorithms. However not all algorithms are static, algorithms can have a variable execution behaviors which leads to an unbalanced supersteps.
  • 22. Mizan* Graph Processing ● Mizan is an open source graph processing system, similar to Pregel, developed locally at KAUST. ● Mizan employs dynamic graph repartitioning without affecting the correctness of graph processing to rebalanced the execution of the supersteps for all types of workloads. *Khayyat et. al., Mizan: A System for Dynamic Load Balancing in Large-scale Graph Processing
  • 25. Types of Graph Algorithms ● Stationary Graph Algorithms: – Algorithms with fixed message distribution across superstep – All vertices are either active or inactive at same time – i.e. PageRank, Diameter Estimation and weakly connected components. ● Non-stationary Graph Algorithms – Algorithms with variable message distribution across supersteps – Vertices can be active and inactive independent to others – i.e. Distributed Minimal spanning tree
  • 26. Mizan architecture ● Each Mizan worker contains three distinct main components: BSP Processor, communicator and storage manager. ● The distributed hash table (DHT) is used to maintain the location of each vertex ● The migration planner interacts with other components during the BSP barrier
  • 28. Dynamic migration: Statistics ● Mizan monitors the following for every vertex: – Response time – Remote outgoing messages – Incoming messages
  • 29. Dynamic migration: planning ● Mizan's migration planner runs after the BSP barrier and creates a new barrier. The planning includes the following steps: – Identifying unbalanced workers. – Identifying migration objective: ● Response time ● Incoming messages ● Outgoing messages – Pair over-utilized workers with underutilized – Select vertices to migrate
  • 31. Mizan PageRank Compute() Example void compute(messageIterator<mDouble> * messages, userVertexObject<mLong, mDouble,  mDouble, mLong> * data,messageManager<mLong, mDouble, mDouble, mLong> * comm) {        double currVal = data­>getVertexValue().getValue();        double newVal = 0;  double c = 0.85;        while (messages­>hasNext()) {             double tmp = messages­>getNext().getValue(); Processing             newVal = newVal + tmp; Messages        }        newVal = newVal * c + (1.0 ­ c) / ((double) vertexTotal);        mDouble outVal(newVal / ((double) data­>getOutEdgeCount()));        if (data­>getCurrentSS() <= maxSuperStep) {           for (int i = 0; i < data­>getOutEdgeCount(); i++) { Termination                comm­>sendMessage(data­>getOutEdgeID(i), outVal);                data­>getOutEdgeID(i); Condition           }         } else {            data­>voteToHalt();         } Sending to         Neighbors       data­>setVertexValue(mDouble(newVal)); }
  • 32. Mizan PageRank Combiner Example void combineMessages(mLong dst, messageIterator<mDouble> *  messages,messageManager<mLong, mDouble, mDouble, mLong> * mManager) {        double newVal = 0;        while (messages­>hasNext()) {               double tmp = messages­>getNext().getValue();               newVal = newVal + tmp;        }        mDouble messageOut(newVal);        mManager­>sendMessage(dst,messageOut); }
  • 33. Mizan Max Aggregator Example class maxAggregator: public IAggregator<mLong> { Public:        mlong aggValue;        maxAggregator() {           aggValue.setValue(0);        }        void aggregate(mLong value) {            if (value > aggValue) {                aggValue = value;            }        }        mLong getValue() {             return aggValue;        }        void setValue(mLong value) {             this­>aggValue = value;        }                virtual ~maxAggregator() {} };
  • 34. Class Assignment ● Your assignment is to configure, install and run Mizan on a single Linux machine throw following this tutorial: https://thegraphsblog.wordpress.com/mizan-on-ubuntu/ ● By the end of the tutorial, you should be able to execute the command on your machine: mpirun ­np 2 ./Mizan­0.1b ­u ubuntu ­g web­Google.txt ­w 2 ● Deliverables: you store the output of of the above command and submit it by Wednesday's class. ● Any questions regarding the tutorial or to get an account for a Ubuntu machine, contact me on: zuhair.khayyat@kaust.edu.sa