Docstoc

Scaling MySQL in the Cloud Presentation

Document Sample
Scaling MySQL in the Cloud Presentation Powered By Docstoc
					             ScaleDB
Transactional Shared Disk storage engine for MySQL


          Moshe Shadmon, Founder, CTO
The product




                             DBMS/Apps


   MySQL-ScaleDB Interface



                             Storage Engine




        Storage Layer
          ScaleDB Benefits



 Enables open source DBMS (eg: MySQL) to operate as
  clustered, high end database
 Scales applications in cloud environments
 No need to change the applications
 Provides high performance
 Provides unified data store
              Shared Disk vs. Shared Nothing
          Shared Nothing              Shared Disk
          SQL Server                  Oracle RAC
          DB2 (Unix)                  IBM - DB2, IMS (MF)
          MySQL                       ScaleDB
          PostgreSQL




Masters




Slaves
              Shared Disk vs Shared Nothing


                       Shared Nothing                Shared Disk
Storage                Per DBMS machine              Shared storage (NAS/SAN)
Scalability            By data partitioning          By adding CPU
Scaling complexity High                              Low
High Availability      Master-Slave                  Multi-Masters
HA complexity          High                          Low
Implemented By         MySQL                         Oracle RAC
                       PostgreSQL                    IBM on mainframe (DB2/IMS)
                       SQL Server                    ScaleDB
                       DB2 (Unix)



           Shared disk provides “out of the box” scalability and availability
          Currently available with the high end commercial databases only
         The Virtualized Cloud Database


MySQL Server                Server 1                               Server 2

                       VM      VM     VM                             VM       VM
   OSS DBMS
                       OSS OSS OSS                                   OSS OSS
 Storage Engine       DBMSDBMSDBMS                                  DBMSDBMS
                       ScaleDB ScaleDB ScaleDB                       ScaleDB ScaleDB

     Local Disk




 Shared Nothing




                                                  Shared Storage




                                                 Shared Disk
                Deploying ScaleDB


          Application Layer                                                        Application




            Database Layer
                                                   Node 1                       Node 2                            Node N
    (Physical or VM nodes)

                                                                                                      …
                                                      DBMS                         DBMS                              DBMS



                                                     ScaleDB                      ScaleDB                           ScaleDB

ScaleDB                  ScaleDB Cluster Manager




                 Standby Cluster Manager




           Storage Layer
                                                               Shared Storage                    Shared Storage
         Benefits of ScaleDB Technology


 High Availability – No single point of failure
 If a node fails – a different node takes over
 If the cluster manager fails – the standby cluster manager is
  initiated to manage the cluster
 Scalability
 No limit on the number of nodes that can join the cluster
 Algorithms to minimize the need to communicate
 Performance
 Innovative, high performance, general purpose indexing
     ScaleDB’s Internal Architecture

                         Applications                                XML



    ScaleDB                          ScaleDB API
Cluster Manager                Transaction Manager

  Global Buffer      Lock Manager           Index          Data            ScaleDB
    Manager                                Manager        Manager           Node
                      Local Lock
   Global Lock         Manager                Buffer Manager
    Manager          Global Lock               Log Manager
                     Coordinator
 Global Recovery                          Recovery        Storage
    Manager                               Manager         Manager


                                     File System


                   Storage Devices                 Storage Devices
              Distributed Lock Manager

        ScaleDB                                                             ScaleDB
    Cluster Manager                                                          Node

          H List   Node 1   Node 2                                       Read Customer
DBMS X              R/W      R/W                                              Info

          H List   Node 1   Node 2                                        Index translates
                    R/W      R/W                                        logical id to Row ID
Table Y
          H List                                                Shared
                   Node 1   Node 2
                     R        R                                DBMS lock
Block Z
                                                                     Shared
     W List        Node 2
                    R/W
                                                                    Table lock
                                                                          Shared
                                                                         Row lock


                                                       File System


                                     Storage Devices                 Storage Devices
        Shared Disk in the Cloud


 Cloud provides Scalability and HA
 Scalability - Enables dynamic allocation of computing and
  storage
 Availability – Multiple servers over the same physical data
 High performance
 Reduces Management Overhead
 Reduced tuning and partitioning support
 No manual slave promotion or replication
             Performance / Scalability

 Benchmarks


 Join operations using Multi-Table index
 Sysbench
 TPCC


 Example multiple MySQL + ScaleDB nodes on Amazon EC2
 Demo
Benchmark multi-table index



  Queries/Sec

  60

  50

  40

  30

  20

  10

   0
        Engine X Join   ScaleDB MTI   ScaleDB 2 Nodes
                                Sysbench Performance on EC2

                                                                                  2303 TPS

                                                                           2033
Transactions Per Second




                                                                    1764

                                                             1494
                                                                                             Other Engine

                                                      1224
                                                                                             ScaleDB

                                                954
                          775 TPS
                                          685

                                    415




                            1       1     2      3     4     5      6       7        8
                                                Number of Nodes
             Current & Future Work

 Optimizing TPCC – soon to be published
 Integrating with other environments
 GA – later this year
 Demo

				
DOCUMENT INFO
Shared By:
Categories:
Stats:
views:6
posted:9/21/2011
language:English
pages:15