Patterns For Parallel Computing

Patterns for Parallel Computing

David [email protected]

blogs.msdn.com/dachou

An architectural conversation

• Concepts• Patterns• Design Principles• Microsoft Platform

> Outline

Why is this interesting?

• Amdahl’s law (1967)• Multi-core processors• Virtualization• High-performance computing• Distributed architecture• Web–scale applications• Cloud computing

Paradigm shift!

> Concepts

Parallel Computing == ??

• Simultaneous multi-threading (Intel HyperThreading, IBM Cell microprocessor for PS3, etc.)

• Operating system multitasking (cooperative, preemptive; symmetric multi-processing, etc.)

• Server load-balancing & clustering (Oracle RAC, Windows HPC Server, etc.)

• Grid computing (SETI@home, Sun Grid, DataSynapse, DigiPede, etc.)

• Asynchronous programming (AJAX, JMS, MQ, event-driven, etc.)

• Multi-threaded & concurrent programming (java.lang.Thread, System.Thread, Click, LabVIEW, etc.)

• Massively parallel processing (MapReduce, Hadoop, Dryad, etc.)

Elements and best practices in all of these

> Concepts

Types of Parallelism

• Bit-level parallelism (microprocessors)

• Instruction-level parallelism (compilers)

• Multiprocessing, multi-tasking (operating systems)

• HPC, clustering (servers)

• Multi-threading (application code)

• Data parallelism (massive distributed databases)

• Task parallelism (concurrent distributed processing)

Focus is moving “up” the technology stack…

> Patterns

Clustering Infrastructure for High Availability

> Patterns > HPC, Clustering

High-Performance Computing

> Patterns > HPC, Clustering

Web/App Server

Browser

A-Z

Web/App Server

Browser

A-Z

Microsoft.com

• Infrastructure and Application Footprint– 7 Internet data centers & 3 CDN partnerships– 120+ Websites, 1000’s apps and 2500 databases – 20-30+ Gbits/sec Web traffic; 500+ Gbits/sec download traffic

• 2007 stats (microsoft.com): – #9 ranked domain in U.S; 54.0M UU for 36.0% reach– #5 site worldwide; reaching 287.3M UU– 15K req/sec, 35K concurrent connections on 80 servers– 600 vroots, 350 IIS Web apps & 12 app pools– Windows Server 2008, SQL Server 2008, IIS7, ASP.NET 3.5

• 2007 stats (Windows Update):– 350M UScans/day, 60K ASP.NET req/sec, 1.5M concurrent connections– 50B downloads for CY 2006– Update Egress – MS, Akamai, Level3 & Limelight (50-500+ Gbits/sec)

> Patterns > HPC, Clustering > Example

Multi-threaded programming

> Patterns > Multi-threading

Execution Time

Execution Time

Sequential Concurrent

Multi-threading

• Typically, functional decomposition into individual threads• But, explicit concurrent programming brings complexities

– Managing threads, semaphores, monitors, dead-locks, race conditions, mutual exclusion, synchronization, etc.

• Moving towards implicit parallelism– Integrating concurrency & coordination into mainstream programming

languages– Developing tools to ease development– Encapsulating parallelism in reusable components – Raising the semantic level: new approaches

> Patterns > Multi-threading

API

PIC

Metadata Membership

Web Browser

Content Pods

Content Pods

Content Pods

Content Pods

Thumbs

Content Pods

Content Pods

Content Pods

Content Pods

Images

Content Pods

Content Pods

Content Pods

Content Pods

Albums

Content Pods

Content Pods

Content Pods

Content Pods

Groups

Photobucket

• 2007 stats:– +30M searches processed / day– 25M UU/month in US, +46M worldwide– +7B images uploaded– +300K unique websites link to content– #31 top 50 sites in US– #41 top 100 sites worldwide– 18th largest ad supported site in US

> Patterns > Multi-threading > Example

• Scaling the performance:– Browser handles

concurrency– Centralized lookup– Horizontal partitioning of

distributed content

Data Parallelism

• Loop-level parallelism• Focuses on distributing the data across different parallel

computing nodes– Denormalization, sharding, horizontal partitioning, etc.

• Each processor performs the same task on different pieces of distributed data

• Emphasizes the distributed (parallelized) nature of the data• Ideal for data that is read more than written (scale vs.

consistency)

> Patterns > Data Parallelism

Parallelizing Data in Distributed Architecture

> Patterns > Data Parallelism

Web/App Server

Browser

A-Z

Web/App Server

Browser

A-M N-Z

Browser

H-M N-S

Web/App Server

A-G T-Z

Index

Web/App Server

Web/App Server

Flickr

• 2007 stats:– Serve 40,000 photos / second– Handle 100,000 cache operations / second– Process 130,000 database queries / second

> Patterns > Data Parallelism > Example

• Scaling the “read” data:– Data denormalization– Database replication and

federation• Vertical partitioning• Central cluster for index

lookups• Large data sets horizontally

partitioned as shards• Grow by binary hashing of

user buckets

MySpace

• 2007 stats:– 115B pageviews/month– 5M concurrent users @ peak– +3B images, mp3, videos– +10M new images/day– 160 Gbit/sec peak bandwidth

> Patterns > Data Parallelism > Example

• Scaling the “write” data:– MyCache: distributed dynamic memory cache– MyRelay: inter-node messaging transport handling +100K req/sec, directs

reads/writes to any node– MySpace Distributed File System: geographically redundant distributed

storage providing massive concurrent access to images, mp3, videos, etc.– MySpace Distributed Transaction Manager: broker for all non-transient

writes to databases/SAN, multi-phase commit across data centers

Facebook

• 2009 stats:– +200B pageviews/month– >3.9T feed actions/day– +300M active users– >1B chat mesgs/day– 100M search queries/day– >6B minutes spent/day

(ranked #2 on Internet)

– +20B photos, +2B/month growth

– 600,000 photos served / sec

– 25TB log data / day processed thru Scribe

– 120M queries /sec on memcache

> Patterns > Data Parallelism > Example

• Scaling the “relational” data:– Keeps data normalized, randomly

distributed, accessed at high volumes– Uses “shared nothing” architecture

Task Parallelism

• Functional parallelism• Focuses on distributing execution processes (threads) across

different parallel computing nodes• Each processor executes a different thread (or process) on the

same or different data• Communication takes place usually to pass data from one thread

to the next as part of a workflow• Emphasizes the distributed (parallelized) nature of the

processing (i.e. threads)• Need to design how to compose partial output from concurrent

processes

> Patterns > Task Parallelism

Google

• 2007 stats:– +20 petabytes of data processed / day by +100K MapReduce jobs – 1 petabyte sort took ~6 hours on ~4K servers replicated onto ~48K disks– +200 GFS clusters, each at 1-5K nodes, handling +5 petabytes of storage– ~40 GB/sec aggregate read/write throughput across the cluster– +500 servers for each search query < 500ms

> Patterns > Task Parallelism > Example

• Scaling the process:– MapReduce: parallel

processing framework– BigTable: structured

hash database– Google File System:

massively scalable distributed storage

Parallelism for Speedup

• Amdahl’s law (1967): • Amdahl’s speedup: • Gustafson’s law (1988): • Gustafson’s speedup: • Karp-Flatt metric (1990): • Speedup: • Efficiency:

> Design Principles

Parallelism for Scale-out

• Sequential Parallel– Convert sequential and/or single-machine program into a form in which it

can be executed in a concurrent, potentially distributed environment

• Over-decompose for scaling– Structured multi-threading with a data focus

• Relax sequential order to gain more parallelism– Ensure atomicity of unordered interactions

• Consider data as well as control flow– Careful data structure & locking choices to manage contention– User parallel data structures– Minimize shared data and synchronization

• Continuous optimization

> Design Principles

Amazon

• Principles for Scalable Service Design (Werner Vogels, CTO, Amazon)

> Design Principles > Example

– Autonomy– Asynchrony– Controlled concurrency– Controlled parallelism– Decentralize– Decompose into small

well-understood building blocks

– Failure tolerant– Local responsibility– Recovery built-in– Simplicity– Symmetry

Parallel computing on the Microsoft platform

• Concurrent Programming (.NET 4.0 Parallel APIs)

• Distributed Computing (CCR & DSS Runtime, Dryad)

• Cloud Computing (Azure Services Platform)

• Grid Computing (Windows HPC Server 2008)

• Massive Data Processing (SQL Server “Madison”)

Components spanning a spectrum of computing models

> Microsoft Platform

.NET 4.0 Parallel APIs

• Task Parallel Library (TPL)• Parallel LINQ (PLINQ)• Data Structures• Diagnostic Tools

> Microsoft Platform > Concurrent Programming

CCR & DSS Toolkit

• Supporting multi-core and concurrent applications by facilitating asynchronous operations

• Dealing with concurrency, exploiting parallel hardware and handling partial failure

• Supporting robust, distributed applications based on a light-weight state-driven service model

• Providing service composition, event notification, and data isolation

> Microsoft Platform > Distributed Computing

• Concurrency & Coordination Runtime

• Decentralized Software Services

Dryad

• General-purpose execution environment for distributed, data-parallel applications

• Automated management of resources, scheduling, distribution, monitoring, fault tolerance, accounting, etc.

• Concurrency and mutual exclusion semantics transparency• Higher-level and domain-specific language support

> Microsoft Platform > Distributed Computing

28

Windows Server

Cluster Services

Distributed Filesystem

Dryad

Distributed Shell

PSQL

DryadLINQ

PerlSQL

server

C++

Windows Server

Windows Server

Windows Server

C++

CIFS/NTFS

legacycode

sed, awk, grep, etc.

SSISQueries

C#

Vectors

Machine Learning

C#

Job

queu

eing

, mon

itorin

g

Azure Services Platform

• Internet-scale, highly available cloud fabric• Auto-provisioning 64-bit compute nodes on Windows Server VMs• Massively scalable distributed storage (table, blob, queue)• Massively scalable and highly consistent relational database

> Microsoft Platform > Cloud Computing

Table StorageService

Blob StorageService

QueueService

CacheService

ASP.NET(Web Role)

ASP.NET(Web Role)

ASP.NET(Web Role)

ASP.NET(Web Role)

ASP.NET(Web Role)

ASP.NET(Web Role)

ASP.NET(Web Role)

ASP.NET(Web Role)

ASP.NET(Web Role)

Web Svc(Web Role)

ASP.NET(Web Role)

ASP.NET(Web Role)

ASP.NET(Web Role)

ASP.NET(Web Role)

Jobs(Worker

Role)

Service Bus

Access Control Service

WorkflowService

Service Orch.

Identities & Roles

Conn. Bindings

Application Data

SQL Data Services

BIServices

Application Data

Reference Data

Windows HPC Server

• Image multicasting-based parallel deployment of cluster nodes• Fault tolerance with failover clustering of head node• Policy-driven, NUMA-aware, multicore-aware, job scheduler• Inter-process distributed communication via MS-MPI

> Microsoft Platform > Grid Computing

• #10 fastest supercomputer in the world (top500.org)– 30,720 cores– 180.6 teraflops– 77.5% efficiency

SQL Server “Madison”

– IO and CPU affinity within symmetric multi-processing (SMP) nodes– Multiple physical instances of tables w/ dynamic re-distribution

• Distribute / partition large tables across multiple nodes• Replicate small tables• Replicate + distribute medium tables

> Microsoft Platform > Massive Data Processing

• Massively parallel processing (MPP) architecture

• +500TB to PB’s databases• “Ultra Shared Nothing” design

For More Information

• Architect Council Website (blogs.msdn.com/sac)

– This series (blogs.msdn.com/sac/pages/council-2009q2.aspx)

• .NET 4.0 Parallel APIs (msdn.com/concurrency)

• CCR & DSS Toolkit (microsoft.com/ccrdss)

• Dryad (research.microsoft.com/dryad)

• Azure Services Platform (azure.com)

• SQL Server “Madison” (microsoft.com/madison)

• Windows HPC Server 2008 (microsoft.com/hpc)

> Resources

© 2009 Microsoft Corporation. All rights reserved. Microsoft, Windows, Windows Vista and other product names are or may be registered trademarks and/or trademarks in the U.S. and/or other countries.The information herein is for informational purposes only and represents the current view of Microsoft Corporation as of the date of this presentation. Because Microsoft must respond to changing market conditions, it should not be interpreted to be a commitment on the part of Microsoft, and Microsoft cannot guarantee the accuracy of any information provided after the date of this presentation. MICROSOFT MAKES NO WARRANTIES, EXPRESS, IMPLIED OR STATUTORY, AS TO THE INFORMATION IN THIS PRESENTATION.

Thank you!

[email protected]/dachou