Overview of Cloud Computing Platforms

(1)

Overview of Cloud Computing

Platforms

July 28, 2010 Big Data for Science Workshop

Judy Qiu

[email protected]

http://salsahpc.indiana.edu http://salsahpc.indiana.edu

Pervasive Technology Institute

School of Informatics and Computing

(2)

Important Trends

•new commercially supported data center model building on compute grids •In all fields of science and

throughout life (e.g. web!) •Impacts preservation,

access/use, programming model

Data Deluge

Cloud

Technologies

•Implies parallel computing important again

•Performance from extra cores – not extra clock

eScience

Multicore/

Parallel

Computing

•A spectrum of eScience or

eResearch applications (biology, chemistry, physics social science and

humanities …) •Data Analysis

(3)

Challenges for CS Research

There’re several challenges to realizing the vision on data intensive systems

and building generic tools (Workflow, Databases, Algorithms, Visualization ).

Science faces a data deluge. How to manage and analyze information?

Recommend CSTB foster tools for data capture, data curation, data analysis

―Jim Gray’s Talk to Computer Science and Telecommunication Board (CSTB), Jan 11, 2007

and building generic tools (Workflow, Databases, Algorithms, Visualization ).

• Cluster/Cloud-management software

• Distributed execution engine

• Security and Privacy

• Language constructs

• Parallel compilers

• Program Development tools

(4)

Gartner 2009 Hype Curve

Source: Gartner (August 2009)

HPC

?

(5)

Data We’re Looking at

• Public Health Data (IU Medical School & IUPUI Polis Center)

(65535 Patient/GIS records / 54 dimensions each)

• Biology DNA sequence alignments (IU Medical School & CGB)

(several million Sequences / at least 300 to 400 base pair each)

• NIH PubChem (Cheminformatics)

(60 million chemical compounds/166 fingerprints each)

• Particle physics LHC (Caltech)

(1 Terabyte data placed in IU Data Capacitor)

(6)

Data is too big and gets bigger to fit into memory

For “All pairs” problem O(N2_),

PubChem data points 100,000 => 480 GB of main memory (Tempest Cluster of 768 cores has 1.536TB)

We need to use distributed memory and new algorithms to solve the problem

Communication overhead is large as main operations include matrix multiplication (O(N2_{)), moving data between nodes and within one node}

adds extra overheads

Data Explosion and Challenges

We use hybrid mode of MPI and MapReduce between nodes and concurrent threading internal to node on multicore clusters

Concurrent threading has side effects (for shared memory model like CCR and OpenMP) that impact performance

sub-block size to fit data into cache cache line padding to avoid false sharing

(7)

Clouds hide Complexity

SaaS

: Software as a Service

(e.g. Clustering is a service)

PaaS

: Platform as a Service

Cyberinfrastructure

Is “Research as a Service”

IaaS

(

HaaS

): Infrastructure as a Service

(get computer time with a credit card and with a Web interface like EC2)

PaaS

: Platform as a Service

IaaS plus core software capabilities on which you build SaaS (e.g. Azure is a PaaS; MapReduce is a Platform)

(8)

Cloud Computing: Infrastructure and Runtimes

• Cloud infrastructure:

outsourcing of servers, computing, data, file

space, utility computing, etc.

–

Handled through (Web) services that control virtual machine

lifecycles.

• Cloud runtimes or Platform:

tools (for using clouds) to do

data-parallel (and other) computations.

parallel (and other) computations.

–

Apache Hadoop, Google MapReduce, Microsoft Dryad, Bigtable,

Chubby and others

–

MapReduce designed for information retrieval but is excellent for

a wide range of

science data analysis applications

–

Can also do much traditional parallel computing for data-mining

if extended to support

iterative

operations

(9)

Authentication and Authorization:

Provide single sign in to both FutureGrid and Commercial

Clouds linked by workflow

Workflow:

Support workflows that link job components between FutureGrid and Commercial

Clouds. Trident from Microsoft Research is initial candidate

Data Transport:

Transport data between job components on FutureGrid and Commercial Clouds

respecting custom storage patterns

Software as a Service:

This concept is shared between Clouds and Grids and can be supported

without special attention

SQL:

Relational Database

Program Library:

Store Images and other Program material (basic FutureGrid facility)

Blob:

Basic storage concept similar to Azure Blob or Amazon S3

S

A

LS

A

Blob:

Basic storage concept similar to Azure Blob or Amazon S3

DPFS Data Parallel File System:

Support of file systems like Google (MapReduce), HDFS (Hadoop)

or Cosmos (Dryad) with compute-data affinity optimized for data processing

Table:

Support of Table Data structures modeled on Apache Hbase (Google Bigtable) or Amazon

SimpleDB/Azure Table (eg. Scalable distributed “Excel”)

Queues:

Publish Subscribe based queuing system

Worker Role:

This concept is implicitly used in both Amazon and TeraGrid but was first

introduced as a high level construct by Azure

Web Role:

This is used in Azure to describe important link to user and can be supported in

FutureGrid with a Portal framework

(10)

MapReduce “File/Data Repository” Parallelism

Instruments

Disks

Map

1

Map

2

Map

3

Reduce

Communication

Map

= (data parallel) computation reading and writing data

Reduce

= Collective/Consolidation phase e.g. forming multiple

global sums as in histogram

Portals

/Users

MPI and Iterative MapReduce

Map Map

Map

Reduce Reduce

Reduce

(11)

MapReduce

Map(Key, Value)

Reduce(Key, List<Value>)

Data Partitions

A hash function maps the results of the map tasks to r reduce tasks

A parallel Runtime coming from Information Retrieval

• Implementations support:

–

Splitting of data

–

Passing the output of map functions to reduce functions

–

Sorting the inputs to the reduce function based on the

intermediate keys

–

Quality of services

(12)

• Sam thought of “drinking” the apple

Sam’s Problem

He used a to cut the

(13)

• Implemented a

parallel

version of his innovation

Creative Sam

(<a, > , <o, > , <p, > , …)

Each input to a map is a list of <key, value> pairs

Each output of slice is a list of <key, value> pairs

A list of <key, value> pairs mapped into another list of <key, value> pairs which gets grouped by

the key and reduced into a list of values

(<a’, > , <o’, > , <p’, > )

Each output of slice is a list of <key, value> pairs

Grouped by key

Each input to a reduce is a <key, value-list> (possibly a list of these, depending on the grouping/hashing mechanism)

e.g. <ao, ( …)>

Reduced into a list of values

The idea of Map Reduce in Data Intensive Computing

(14)

Hadoop & DryadLINQ

Job

Tracker

Name

Node

1

2

3

2

3

4

4 M

M

R

H D F Data blocks Data/Compute Nodes Master Node

Apache Hadoop

_{Microsoft DryadLINQ}

Edge : Vertex :

execution task

Standard LINQ operations DryadLINQ operations

DryadLINQ Compiler

Directed

Acyclic Graph (DAG) based

• Apache Implementation of Google’s MapReduce

• Hadoop Distributed File System (HDFS) manage data

• Map/Reduce tasks are scheduled based on data locality in HDFS (replicated data blocks)

• Dryad process the DAG executing vertices on compute clusters

• LINQ provides a query interface for structured data

• Provide Hash, Range, and Round-Robin partition patterns

3

4

S Edge : communication path

Dryad Execution Engine

(DAG) based execution flows

(15)

Reduce Phase of Particle Physics

“Find the Higgs” using Dryad

Higgs in Monte Carlo

• Combine Histograms produced by separate Root “Maps” (of event data to partial histograms) into a single Histogram delivered to Client

(16)

High Energy Physics Data Analysis

Input to a map task: <key, value>

key = Some Id value = HEP file Name

Output of a map task: <key, value>

key = random # (0<= num<= max reduce tasks) value = Histogram as binary data

An application analyzing data from Large Hadron Collider (1TB but 100 Petabytes eventually)

Input to a reduce task: <key, List<value>>

key = random # (0<= num<= max reduce tasks) value = List of histogram as binary data

Output from a reduce task: value

value = Histogram file

Combine outputs from reduce tasks to form the final histogram

(17)

AWS/ Azure

Hadoop

DryadLINQ

Programming

patterns

Independent job execution

MapReduce

DAG execution,

MapReduce + Other

patterns

Fault Tolerance

Task re-execution based

on a time out

Re-execution of failed

and slow tasks.

Re-execution of failed

and slow tasks.

Data Storage

S3/Azure Storage.

HDFS parallel file system.

Local files

Environments

EC2/Azure, local compute

resources

Linux cluster, Amazon

Elastic MapReduce

Windows HPCS cluster

Ease of

Programming

EC2 : **

Azure: ***

****

Ease of use

EC2 : ***

Azure: **

***

****

Scheduling &

Load Balancing

Dynamic scheduling

through a global queue,

Good natural load

balancing

Data locality, rack aware

dynamic task scheduling

through a global queue,

Good natural load

balancing

Data locality, network

topology aware

scheduling. Static task

partitions at the node

level, suboptimal load

(18)

Some Life Sciences Applications

• EST (Expressed Sequence Tag)

sequence assembly program using DNA sequence

assembly program software

CAP3

.

• Metagenomics

and

Alu

repetition alignment using Smith Waterman dissimilarity

computations followed by MPI applications for Clustering and MDS (Multi

Dimensional Scaling) for dimension reduction before visualization

• Mapping the 60 million entries in PubChem

into two or three dimensions to aid

selection of related chemicals with convenient Google Earth like Browser. This

uses either hierarchical MDS (which cannot be applied directly as O(N

2

_{)) or GTM}

(Generative Topographic Mapping).

• Correlating Childhood obesity with environmental factors

by combining medical

records with Geographical Information data with over 100 attributes using

correlation computation, MDS and genetic algorithms for choosing optimal

environmental factors.

(19)

DNA Sequencing Pipeline

Read Visualization Plotviz Visualization Plotviz Blocking

Blocking Sequence_alignmentSequence_alignment

MDS MDS Dissimilarity Matrix N(N-1)/2 values Dissimilarity Matrix N(N-1)/2 values FASTA File N Sequences FASTA File N Sequences block Pairings Pairwise clustering Pairwise clustering

MapReduce

MPI

Illumina/Solexa Roche/454 Life Sciences Applied Biosystems/SOLiD

Modern Commerical Gene Sequences Internet

Read Alignment

• This chart illustrate our research of a pipeline mode to provide services on demand (Software as a Service SaaS)

(20)

Alu and Metagenomics Workflow

“All pairs” problem

Data is a collection of N sequences. Need to calcuate N2_{dissimilarities (distances) between}

sequnces (all pairs).

• These cannot be thought of as vectors because there are missing characters

• “Multiple Sequence Alignment” (creating vectors of characters) doesn’t seem to work if N larger than O(100), where 100’s of characters long.

Step 1: Can calculate N2_{dissimilarities (distances) between sequences}

Step 1: Can calculate N dissimilarities (distances) between sequences

Step 2: Find families by clustering (using much better methods than Kmeans). As no vectors, use vector free O(N2₎_methods

Step 3: Map to 3D for visualization using Multidimensional Scaling (MDS) – also O(N2₎

Results:

N = 50,000 runs in 10hours (the complete pipeline above) on 768 cores

Discussions:

• Need to address millions of sequences …..

• Currently using a mix of MapReduce and MPI

(21)

Biology MDS and Clustering Results

Alu Families

This visualizes results of Alu repeats from Chimpanzee and Human Genomes. Young families (green, yellow) are seen as tight clusters. This is projection of MDS dimension reduction to 3D of 35399 repeats – each with about 400 base pairs

Metagenomics

This visualizes results of dimension reduction to 3D of 30000 gene sequences from an environmental sample. The many different genes are classified by clustering algorithm and visualized by MDS dimension reduction

(22)

All-Pairs Using DryadLINQ

5000 10000 15000 20000 DryadLINQ MPI 125 million distances 4 hours & 46 minutes

0

35339 50000

Calculate Pairwise Distances (Smith Waterman Gotoh)

• Calculate pairwise distances for a collection of genes (used for clustering, MDS)

• Fine grained tasks in MPI

• Coarse grained tasks in DryadLINQ

• Performed on 768 cores (Tempest Cluster)

(23)

Hadoop/Dryad Comparison

Inhomogeneous Data I

1650 1700 1750 1800 1850 1900

T

im

e

(

s)

Randomly Distributed Inhomogeneous Data Mean: 400, Dataset Size: 10000

1500 1550 1600 1650 0 50 100 150 200 250 300

T

im

e

(

s)

Standard Deviation

DryadLinq SWG Hadoop SWG Hadoop SWG on VM

Inhomogeneity of data does not have a significant effect when the sequence

lengths are randomly distributed

(24)

Hadoop/Dryad Comparison

Inhomogeneous Data II

2,000 3,000 4,000 5,000 6,000

To

ta

l

T

im

e

(

s)

Skewed Distributed Inhomogeneous data Mean: 400, Dataset Size: 10000

0 1,000 2,000 0 50 100 150 200 250 300

To

ta

l

T

im

e

(

s)

Standard Deviation

DryadLinq SWG Hadoop SWG Hadoop SWG on VM

This shows the natural load balancing of Hadoop MR dynamic task assignment

using a global pipe line in contrast to the DryadLinq static assignment

(25)

Hadoop VM Performance Degradation

15% 20% 25% 30%

• 15.3% Degradation at largest data set size

10000 20000 30000 40000 50000

0% 5% 10%

No. of Sequences

(26)

Application Classes

1

Synchronous Lockstep Operation as in SIMD architectures

_SIMD

2

Loosely Synchronous

Iterative Compute-Communication stages with

independent compute (map) operations for each CPU. Heart of most MPI jobs

MPP

3

Asynchronous Compute Chess; Combinatorial Search often supported by dynamic threads

MPP

4

Pleasingly Parallel Each component independent

_Grids

Classification of Parallel software/hardware use in terms of “Application architecture” Structures

4

Pleasingly Parallel Each component independent

_Grids

5

Metaproblems Coarse grain (asynchronous) combinations of classes 1)-4). The preserve of workflow.

Grids

6

MapReduce++ It describes file(database) to file(database) operations which has subcategories including.

1) Pleasingly Parallel Map Only (e.g. Cap3) 2) Map followed by reductions (e.g. HEP) 3) Iterative “Map followed by reductions” –

Extension of Current Technologies that

supports much linear algebra and datamining

Clouds

Hadoop/

Dryad

(27)

Applications & Different Interconnection Patterns

Map Only

Classic

MapReduce

Iterative Reductions

MapReduce++

Loosely

Synchronous

CAP3Analysis High Energy Physics Expectation Many MPI scientific

Input

Output

map

Input

map

reduce

Input

map

reduce

iterations

Pij

CAP3Analysis Document conversion (PDF -> HTML)

Brute force searches in cryptography

Parametric sweeps

High Energy Physics (HEP) Histograms SWGgene alignment Distributed search Distributed sorting Information retrieval Expectation maximization algorithms Clustering Linear Algebra

Many MPI scientific applications utilizing wide variety of communication constructs including local interactions - CAP3 Gene Assembly

- PolarGrid Matlab data analysis

Information Retrieval -HEP Data Analysis

- Calculation of Pairwise Distances for ALU

Sequences - Kmeans - Deterministic Annealing Clustering - Multidimensional Scaling MDS - Solving Differential Equations and - particle dynamics with short range forces

(28)

Twister(MapReduce++)

• Streaming based communication

• Intermediate results are directly transferred from the map tasks to the reduce tasks –eliminates local files

• Cacheablemap/reduce tasks

• Static data remains in memory

• Combine phase to combine reductions

• User Program is the composerof MapReduce computations

• Extendsthe MapReduce model to

iterativecomputations Data Split D _MR Driver User Program

Pub/Sub Broker Network

D File System M R M R M R M R Worker Nodes M R D Map Worker Reduce Worker MRDeamon Data Read/Write Communication

Reduce (Key, List<Value>) Iterate

Map(Key, Value)

Combine (Key, List<Value>) User Program Configure() Static data δ flow

(29)

(30)

Iterative Computations

K-means

Matrix

Multiplication

Smith Waterman

Performance of K-Means

Parallel Overhead Matrix Multiplication

Smith Waterman

(31)

Performance of Pagerank using

ClueWeb Data (Time for 20 iterations)

(32)

TwisterMPIReduce

PairwiseClustering MPI Multi Dimensional Scaling MPI Generative Topographic Mapping MPI Other …

Azure Twister (C# C++)

Java Twister

FutureGrid

Local

Amazon

• Runtime package supporting subset of MPI

mapped to Twister

• Set-up, Barrier, Broadcast, Reduce

(33)

Google MapReduce Apache Hadoop Microsoft Dryad Twister Azure Twister

Programming Model

MapReduce MapReduce DAG execution,

Extensible to MapReduce and other patterns Iterative MapReduce MapReduce-- will extend to Iterative MapReduce

Data Handling GFS (Google File System)

HDFS (Hadoop Distributed File System)

Shared Directories & local disks

Local disks and data management tools

Azure Blob Storage

Scheduling Data Locality Data Locality; Rack aware, Dynamic task scheduling through global queue Data locality; Network topology based run time graph optimizations; Static task partitions Data Locality; Static task partitions Dynamic task scheduling through global queue

Failure Handling Re-execution of failed Re-execution of Re-execution of failed Re-execution Re-execution of

S

A

LS

A

Failure Handling Re-execution of failed

tasks; Duplicate

execution of slow tasks

Re-execution of failed tasks; Duplicate execution of slow tasks Re-execution of failed tasks; Duplicate execution of slow tasks Re-execution of Iterations Re-execution of failed tasks; Duplicate execution of slow tasks High Level Language Support

Sawzall Pig Latin DryadLINQ Pregel has

related features

N/A

Environment Linux Cluster. Linux Clusters, Amazon Elastic Map Reduce on EC2 Windows HPCS cluster Linux Cluster EC2 Window Azure Compute, Windows Azure Local Development Fabric Intermediate data transfer

File File, Http File, TCP pipes,

shared-memory

Publish/Subscr ibe messaging

(34)

High Performance

Dimension Reduction and Visualization

• Need is pervasive

–

Large and high dimensional data

are everywhere: biology, physics,

Internet, …

–

Visualization can help data analysis

• Visualization of large datasets with high performance

–

Map high-dimensional data into low dimensions (2D or 3D).

–

Map high-dimensional data into low dimensions (2D or 3D).

–

Need Parallel programming for processing large data sets

–

Developing high performance dimension reduction algorithms:

• MDS(Multi-dimensional Scaling), used earlier in DNA sequencing application

• GTM(Generative Topographic Mapping)

• DA-MDS(Deterministic Annealing MDS)

• DA-GTM(Deterministic Annealing GTM)

–

Interactive visualization tool

PlotViz

(35)

Dimension Reduction Algorithms

• Multidimensional Scaling (MDS) [1]

o Given the proximity information among points.

o Optimization problem to find mapping in target dimension of the given data based on pairwise proximity information while

minimize the objective function.

o Objective functions: STRESS (1) or SSTRESS (2)

• Generative Topographic Mapping

(GTM) [2]

o Find optimal K-representations for the given data (in 3D), known as

K-cluster problem (NP-hard)

o Original algorithm use EM method for optimization

o Deterministic Annealing algorithm can be used for finding a global solution

o Only needs pairwise distances δ

ij between

original points (typically not Euclidean) o d

ij(X) is Euclidean distance between mapped

(3D) points

o Objective functions is to maximize log-likelihood:

[1]I. Borg and P. J. Groenen. Modern Multidimensional Scaling: Theory and Applications. Springer, New York, NY, U.S.A., 2005. [2] C. Bishop, M. Svens´en, and C. Williams. GTM: The generative topographic mapping. Neural computation, 10(1):215–234, 1998.

(36)

GTM vs. MDS

GTM

MDS (SMACOF)

Maximize Log-Likelihood

Minimize STRESS or SSTRESS

Objective

• Non-linear dimension reduction

• Find an optimal configuration in a lower-dimension

• Iterative optimization method

Purpose

• MDS also soluble by viewing as nonlinear χ

2 with iterative linear equation solver

Maximize Log-Likelihood

Minimize STRESS or SSTRESS

Objective Function

O(KN) (K << N)

O(N

2

₎

Complexity

EM

Iterative Majorization (EM-like)

Optimization Method

(37)

MDS and GTM Example

37

Chemical compounds shown in literatures, visualized by MDS (left) and GTM (right)

Visualized 234,000 chemical compounds which may be related with a set of 5 genes of

interest (ABCB1, CHRNB2, DRD2, ESR1, and F2) based on the dataset collected from

major journal literatures which is also stored in Chem2Bio2RDF system.

(38)

Interpolation Method

• MDS and GTM are highly memory and time consuming

process for large dataset such as millions of data points

• MDS requires O(N

2 ) and GTM does O(KN) (N is the number of

data points and K is the number of latent variables)

• Training only for sampled data and interpolating for

out-of-sample set can improve performance

• Interpolation is a pleasingly parallel application

suitable for

• Interpolation is a pleasingly parallel application

suitable for

MapReduce and Clouds

n

in-sample

N-n

out-of-sample

Total N data

Training

Interpolation

Trained data

Interpolated

MDS/GTM

map

(39)

Quality Comparison

(O(N

2 ) Full vs. Interpolation)

MDS

GTM

16 nodes

• Quality comparison between Interpolated result upto 100k based on the sample data (12.5k, 25k, and 50k) and original MDS result w/ 100k.

• STRESS:

w_ij = 1/ ∑δ

ij2

Interpolation result (blue) is

getting close to the original

(red) result as sample size is

increasing.

12.5K 25K 50K 100K Run on 16 nodes of Tempest

(40)

Convergence is Happening

Data Intensive Paradigms

Data intensive application with basic activities: capture, curation, preservation, and analysis (visualization)

Cloud infrastructure and runtime

Multicore

Clouds

(41)

Linux Virtual

Microsoft DryadLINQ / Twister / MPI

Apache Hadoop / Twister/ MPI

Smith Waterman Dissimilarities, CAP-3 Gene Assembly, PhyloD Using

DryadLINQ, High Energy Physics, Clustering, Multidimensional Scaling,

Generative Topological Mapping

Applications

Runtimes

Windows Server

Science Cloud (Dynamic Virtual Cluster)

Architecture

Services and Workflow

• Dynamic Virtual Cluster provisioning via XCAT

• Supports both stateful and stateless OS images

iDataplex Bare-metal Nodes

Linux

Bare-system

Linux Virtual

Machines

Windows Server

_{2008 HPC}

Bare-system

_{Virtualization}

XCAT Infrastructure

Xen Virtualization

Infrastructure

software

Hardware

Windows Server

2008 HPC

(42)

Summary of Initial Results

• Cloud technologies

(Dryad/Hadoop/Azure/EC2) promising for Life

Science computations

• Dynamic Virtual Clusters

allow one to switch between different

modes

• Overhead of VM’s

on Hadoop (15%) acceptable

• Twister

allows iterative problems (classic linear algebra/datamining) to

• Twister

allows iterative problems (classic linear algebra/datamining) to

use MapReduce model efficiently

–

Prototype Twister released

(43)

Acknowledgements

S

A

L

S

A

_Group

http://salsahpc.indiana.edu

Judy Qiu, Adam Hughes

Jaliya Ekanayake, Thilina Gunarathne, Jong Youl Choi, Seung-Hee Bae, Yang Ruan, Hui Li, Bingjing Zhang, Saliya Ekanayake, Stephen Wu

Collaborators

Yves Brun, Peter Cherbas, Dennis Fortenberry, Roger Innes, David Nelson, Homer Twigg, Yves Brun, Peter Cherbas, Dennis Fortenberry, Roger Innes, David Nelson, Homer Twigg, Craig Stewart, Haixu Tang, Mina Rho, David Wild, Bin Cao, Qian Zhu, Maureen Biggers, Gilbert Liu,

Neil Devadasan

Support by