Cluster7 WhatsNew Webinar 043009

download Cluster7 WhatsNew Webinar 043009

of 32

Transcript of Cluster7 WhatsNew Webinar 043009

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    1/32

    1Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    What's New:MySQL Cluster 7.0 Webinar

    Matthew MontgomerySenior MySQL Support [email protected]

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    2/32

    2Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    Agenda

    Industry Trends

    MySQL in CommunicationsMySQL Cluster Architecture

    MySQL Cluster 7.0

    Use Cases

    Resources

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    3/32

    3Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    About MySQL

    High Performance Reliable Easy to Use

    14 Years of Development

    Acquired by Sun in February2008

    400+ in Database Group

    750+ Partners

    70K+ Downloads Per Day

    Customers across every major operating system, hardware

    vendor, geography, industry, and application type

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    4/32

    4Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    Where is MySQL Located? Everywhere!

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    5/32

    5Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    MySQL is the third most commonly used RDBMS

    #1 open-source database

    MySQL Industry Adoption

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    6/32

    6Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    Open-source powers the Web & the Network

    Serving Key Markets & Industry Leaders

    Enterprise 2.0TelecommunicationsOn Demand, SaaS,Hosting

    Web / Web 2.0 OEM /ISV's

    http://images.google.com/imgres?imgurl=http://www.infinitytechnology.com/uploadedImages/Home/TechFocus_News/AlcatelLucent_Hor_2col_lrg.gif&imgrefurl=http://www.infinitytechnology.com/phonesystems.aspx&h=251&w=720&sz=11&hl=en&start=4&sig2=urYvX47BOQRqvADY_UMA0w&um=1&tbnid=pA91nzVKrUFImM:&tbnh=49&tbnw=140&ei=94SgSOaRCaqkpATZu-jgBw&prev=/images%3Fq%3Dalcatel%2Blucent%26um%3D1%26hl%3Den%26suggon%3D0%26rls%3Dcom.microsoft:en-us%26sa%3DN
  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    7/327Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    http://www.mysql.com/industry/communications/resources.html#customer_case_studies

    MySQL in Communications

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    8/328Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    Key Opportunity: Service Convergence

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    9/329Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    MySQL Cluster Customers and ApplicationsNEPs, ISVs and Communications Service Providers

    http://www.mysql.com/industry/telecom/

    Network Subscriber databases Service Delivery Platforms

    > Messaging / Presence

    Telco Application Servers

    VoIP Infrastructure Intelligent Networks Value-added services IPTV / VoD Mobile Content Delivery

    On-Line app stores and portals DNS/DHCP for Broadband Payment Gateways Data Store for LDAP Directories

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    10/3210Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    MySQL Cluster

    Key Capabilities

    Carrier-gradedatabase

    Highlyavailable

    Real-timeperformance

    Linearly &

    dynamicallyscalable

    Opendevelopment

    Shared-nothing, ACID-compliant relationaldatabase

    Five 9s (99.999%) availability using commodityhardware. Self-healing, sub-second failover

    High-load, real-time performance

    Predictable low latency, bounded access times

    Incrementally scale up, out and on-line as

    application demandsLinearly scale with distribution awareness

    Open source, multiple data access

    High-performance APIs (C++/Java), SQL, LDAP,Web Services

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    11/3211Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    MySQL Cluster Data (NDBD)Nodes

    LDAP

    MySQL Cluster Application Nodes

    MGM

    Clients

    MySQL Cluster Architecture

    MGM

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    12/3212Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    MySQL Cluster

    Geographic RedundancyAsynchronous replication

    Cluster 1

    NDB storage engine

    NDB API

    Cluster 2

    NDB storage engine

    NDB API

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    13/3213Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    MySQL Cluster Carrier Grade Edition 7Key Enhancements

    ExpandedPlatforms &Interoperability

    Windows Port

    Data Store for LDAPDirectories

    EnhancedPerformance &Scalability

    Multi-Threaded DataNodes

    Dynamic On-LineScalability

    Large Record

    Handling

    Multi-Threaded DiskData File Access

    SimplifiedMaintenance

    Back-up Snapshot

    Announced at MySQL UC, April 21st 2009

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    14/3214Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    "We view MySQL Cluster Carrier Grade Edition as astrategic technology in our applications portfolio. WithMySQL Cluster CGE 7.0 we are enabling our customers toexpose the rich capabilities of their networks to drive a

    long-tailed innovation model. As a result, the operator canleverage the creativity and agility of the webecosystem to delivernew compelling, personalized andtargeted services to their subscribers withoutcompromising reliability and scalability."

    Jeff Cortley,VP Subscriber Data Management,Alcatel-Lucent

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    15/3215Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    Online Add Node (1) Add Node Group

    Node group New node group

    Application

    Authid (PK) Frame Iname Country

    1 Albert Camus France

    2 Ernest Hemingway USA

    3 Johann Goethe Germany

    4 Junichiro Tanizaki Japan

    Authid (PK) Frame Iname Country

    1 Albert Camus France

    2 Ernest Hemingway USA

    3 Johann Goethe Germany

    4 Junichiro Tanizaki Japan

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    16/3216Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    Authid (PK) Frame Iname Country

    1 Albert Camus France

    2 Ernest Hemingway USA

    3 Johann Goethe Germany

    4 Junichiro Tanizaki Japan

    Online Add Node (2) Copy Data

    Node Group New Node Group

    No extra space needed on existing

    nodes!

    Authid (PK) Frame Iname Country

    2 Ernest Hemingway USA

    4 Junichiro Tanizaki Japan

    Authid (PK) Frame Iname Country

    1 Albert Camus France

    2 Ernest Hemingway USA

    3 Johann Goethe Germany

    4 Junichiro Tanizaki Japan

    Application

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    17/3217Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    Online Add Node (3) Switch Distribution

    Node group 1 Node group 2

    Authid (PK) Frame Iname Country

    2 Ernest Hemingway USA

    4 Junichiro Tanizaki Japan

    Authid (PK) Frame Iname Country

    1 Albert Camus France

    2 Ernest Hemingway USA

    3 Johann Goethe Germany

    4 Junichiro Tanizaki Japan

    Authid (PK) Frame Iname Country

    1 Albert Camus France

    2 Ernest Hemingway USA

    3 Johann Goethe Germany

    4 Junichiro Tanizaki Japan

    Application

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    18/3218Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    Online Add Node (4) Delete Rows

    Node group 1 Node group 2

    Dynamic scaling of a running clusterwith no interruption to service

    Authid (PK) Frame Iname Country

    2 Ernest Hemingway USA

    4 Junichiro Tanizaki Japan

    Authid (PK) Frame Iname Country

    1 Albert Camus France

    3 Johann Goethe Germany

    Authid (PK) Frame Iname Country

    1 Albert Camus France

    2 Ernest Hemingway USA

    3 Johann Goethe Germany

    4 Junichiro Tanizaki Japan

    Application

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    19/3219Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    Scale Up: Multi-Threaded Data Nodes

    Multi threaded ndbd

    Cluster 7.0

    Sub partition threads (up to 4)

    Separate TC andcommunication threads

    Utilizes 8 cores

    - Increase Cluster throughput

    - Reduce hardwarerequirements to achieveequivalent throughput

    Indexmemor

    y

    Datamemor

    y

    ACC TUP

    Indexmemor

    y

    Datamemor

    y

    ACC TUP

    Indexmemor

    y

    Datamemor

    y

    ACC TUP

    TC

    LQH

    Indexmemory

    Datamemory

    LQHLQH

    LQH

    ACC TUP

    Improved Vertical Scalability on

    Multi-Core / Multi-ThreadHardware

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    20/3220Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    MySQL Cluster Benchmarks

    MySQL Cluster delivers 4.3x higher throughput at 4-nodes

    MySQL Cluster 7 achieves 140k+ TPM with 2 data nodes vs 8data nodes required for MySQL Cluster 6.3

    4x less power and space consumption

    Higher cluster throughput with fewer nodes

    Data Nodes

    Sun Firex4450s

    SQL Nodes

    Sun Firex4600s &x4450s

    OpenSolaris

    Gigabit Ethernet

    1 4 8 12 16 20 24 28 32 36 40

    0

    50000

    100000

    150000

    200000

    250000

    300000

    DBT2 Benchmark, 4-MySQL Cluster Data Nodes

    MySQL Cluster 7.0

    MySQL Cluster 6.3

    Number of MySQL Server Nodes

    Tran

    saction

    sPerMinu

    te

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    21/3221Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    Multithreaded Disk Data Access

    All file access is through I/Othreads

    Previously a one-to-one mappingbetween all open files and I/Othreads

    > Still used for some files wherelatency of single I/O critical e.g., redo logs

    Can now use pooled I/O threads,breaking the one-to-one mapping

    > Greater I/O throughput to the file

    > Results in increasedperformance for disk-basedtable data

    > Users no longer need to split

    large files into smaller ones as aworkaround saving adminwork

    > Extends to other files to reduceoverall number of I/O threads inthe system saving memory

    Single-threadeddisk access

    Multithreadeddisk access

    Operations

    requiringI/O

    I/Othreads

    Files

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    22/3222Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    Large Record Handling (1)

    Optimization of the NDBmessaging protocols betweenapps and NDB nodes andbetween NDB nodes

    Packed read reduces the size ofread and response messages

    > Reduces bandwidth used on

    the network increasingthroughput

    Read request: replaces a list ofcolumn identifiers with a bitmap

    Read response: column valuesno longer need to be packed toa 4 byte boundary

    Changes are transparent to theapplication, but designers mightchoose to design schemas thatfurther exploit the mechanism sothat fields pack tightly

    Col id 1 Col id 2 Col id 3

    App NDB4 bytes

    1

    4 bytes

    2 3

    App NDB

    1 2 3

    bitmap

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    23/3223Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    Large Record Handling (2)

    TCKEYREQ

    App

    NDBReduces bandwidth used on the network,increasing throughput (50100% improvementsobserved)

    Transparent to the application

    Existing messages limited to 100 bytes so complexrequests split across multiple messages:

    > Bandwidth wasted on protocol overhead (headerinfo) for each message

    > CPU consumed reassembling operation

    LST enables large operations to be specified in asingle message (up to 32 KB); fragmented signalscan be used if larger messages are needed

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    24/3224Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    MySQL Cluster as a Directory Data Store

    Designed for large,complex directorieswith high update rates

    Preserves and enhances

    investment in existingLDAP Directories

    Enables user to take advantage of MySQL Cluster to

    provide high availability, massively scaleable, realtime clustered database, using driver from directoryvendor

    Maintain standard API data access of LDAP

    Maintain directory benefits while improving agility,reducin database mana ement com lexit & cost

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    25/32

    25Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    MySQL Cluster CGE 7.0 Key Features

    n d b m t d s i n g l e d a t a n o d e e f f e c t i v e l y e x p l o i t i n g

    O n- l i n e a d d- n o d e w i t h r e p a r t i t i o n i n g L a r g e r e c o r d h a n d l i n g

    I m p r o v e m e n t s t o i n t e r - n o d a l c o m m u n i c a t i o n s

    S p e e d s u p i n s e r t s / u p d a t e s / r e a d s o f l a r g e M u l t i- T h r e a d e d D i s k D a t a A c c e s s

    P a r a l l e l a c c e s s t o t h e s a m e f i l e s ; s p e e d s- b a s e d t a b l e d a t a a c c

    E n h a n c e d P e r f o r m a n c e & S c a l a b i l i t y :

    W i n d o w s s u p p o r t ( p r e- G A )

    S u p p o r t f o r C l u s t e r a s a C a r r i e r - G r a d e D i r e c t o r y B a c k- E n d R e a l- t i m e c l u s t e r e d d a t a b a s e u s i n g d r i v e r f r o

    E x p a n d e d P l a t f o r m s & I n t e r o p e r a b i l i t y

    S n a p s h o t o p t i o n f o r b a c k u p s

    N D B C o n s i s t e n t c o n f i g u r a t i o n c o n f i g u r a t i o n d a t a c a c h e d &s c h e m a c h a n g e s

    S i m p l i f i e d M o n i t o r i n g & M a n a g e m e n t

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    26/32

    26Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    Management System Improved Management

    Centralized deployment

    Upgrade> Drop in new version

    Cluster reconfiguration> Rolling restart

    Cluster monitoring> Recovery actions

    Multi-site management

    Today, need to write applicationlogic for replication, such as:

    > synchronizing a slave

    > detection link failure

    > link failover

    > master promotion

    > others

    Simplified replicationmanagementwith automation andoptimization of:

    > Slave synchronization

    > Replication monitoring

    > Link failover

    > Resynchronization after sitefailover

    MySQL Cluster Manager 1.0 GA secondhalf CY09 will deliver a subset of thisfunctionality

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    27/32

    27Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    MySQL Cluster won the performance test hands-down, and it fitted our needs

    perfectly. We evaluated shared-disk clustered databases, but the cost would

    have been at least 10x more. Franois Leygues, Systems Manager, Alcatel-Lucent

    Applications Infrastructure for next-generation

    converged services includingsubscriber data management (HLR,HSS) and the XDMS contacts andpresence management SDP

    Key business benefits Only MySQL Cluster CGE offers

    the scalability and the highavailability required for the system

    Why MySQL?

    Performance

    Reliability

    Lower costs

    Alcatel-Lucent: Real-Time Platform

    27

    http://mysql.com/customers/view/?id=566

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    28/32

    28Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    UTStarcom

    As one of the leading databases, MySQL Cluster provides high availability,reliable services, and proven ability to scale, satisfying our telco requirements.

    Tommy L, Senior Product Manager, UTStarcom

    Applications

    IPTV with data base

    requirements for eCommerce,OLTP, and data warehousing

    Key Business Benefits

    Unlock new revenue streamsfor operators with bundled IPTV

    offering Delivered high quality solution

    to millions of subscribers

    Why MySQL?

    Ensured 99.999% availability

    High performance andscalability

    28

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    29/32

    29Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    M1 Singapore Application

    > RewardsPlus enables M1 to runcredit expiration campaigns,generate comparison reports onpromotional efficiency and sendcustomized SMS messages tosubscribers.

    Key business benefit> M1 has improved customer loyalty

    in a highly competitive marketwhere delivering new value-addedservicesand growing your subscriber baseare key to success.

    Why MySQL?

    > Reliability & Scale Out

    We rely on MySQL Cluster as the key technology behind RewardsPlus, whichhelps us increase the average revenue per user, and improve customerloyalty.

    Tan Tiong Heng, General Manager, Core Network Planning, M1, Singapore 29

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    30/32

    30Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    Resources to Get Started

    Getting Started with MySQL Cluster http://www.mysql.com/products/database/cluster/get-started.html

    Download MySQL Cluster http://dev.mysql.com/downloads/cluster/7.0.html

    MySQL Cluster on the Web http://www.mysql.com/products/database/cluster/

    MySQL Cluster 7.0, Architecture and New Features http://www.mysql.com/why-mysql/white-

    papers/mysql_wp_cluster7_architecture.php

    MySQL Cluster 7.0 Evaluation Guide http://www.mysql.com/why-mysql/white-

    papers/mysql_cluster_eval_guide.php

    MySQL in Communications http://www.mysql.com/industry/communications/

    http://dev.mysql.com/downloads/cluster/http://www.mysql.com/products/database/cluster/http://www.mysql.com/industry/communications/http://www.mysql.com/industry/communications/http://www.mysql.com/products/database/cluster/http://dev.mysql.com/downloads/cluster/
  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    31/32

    31Copyright 2009 MySQL Sun Microsystems. The Worlds Most Popular Open Source Database

    Questions?

    Matthew MontgomerySenior MySQL Support [email protected]

  • 8/3/2019 Cluster7 WhatsNew Webinar 043009

    32/32