SlideShare ist ein Scribd-Unternehmen logo
1 von 36
楽天事例紹介: Clustrix導入による
   DB管理コストの削減
  How Rakuten Reduced Database
Management Spending by 90% through
      Clustrix implementation
                                       October 17th, 2012
                             Ryutaro Yada (矢田 龍太郎)

                                  Database Platform Group
                  Global Infrastructure Development Dept.
                                              Rakuten, Inc.
Introduction

 Ryutaro Yada
   First employed by Rakuten in 2008
   Present job
        Development of a platform database to support Rakuten
        Testing and discussion of new techniques and new architecture in view of having it
         adopted for use.
   Previous functions
        Promotion of Oracle business with specified customer
        Establish collaborative network with Oracle, develop and verify new solutions, etc..
   LinkedIn profile: http://www.linkedin.com/pub/ryutaro-yada/32/368/4b0




                                                                                                1
Agenda

 About Rakuten
 Rakuten database environment and
 operational issues
 What is Clustrix?
 Clustrix verification results and
 implementation effectiveness
 Summary


                                      2
Introduction to Rakuten
   About 3000 employees: (Group approx. 7000)
   Market / more than 40 services provided including travel
   More than 120,000 contracted firms; more than 80,000,000
    registered products
   Group distribution total: 3.2 trillion yen (2011)

                  Rakuten market
Rakuten Global Expansion
   Our Goal is to become the No. 1 Internet Service in the World



LS(UK)

 ★★
  ★
 ★ ★
  ★★
   ★
                                                                                    ★
                                                                                   ★★
                                                                                   ★
                                      ★ ★                                           ★
                                                                                    ★
                                      ★ ★
                                     ★ ★ ★
                                      ★ ★ ★                                    ★
                                                                               ★
                                     ★
                                     ★
                                     ★★
                                     ★
                                     ★★
                                     ★ ★
                                     ★ ★★
                                                                  ★
                                                                  ★
                                 ★
                                 ★★
                                  ★                    ★★
                                             Taiwan   ★
                                                      ★
                                 ★
                                 ★
         *To be open soon          ★
                                   ★
                                                                                        ★
                                                                                        ★




                            ★ Ichiba (EC)
                            ★               ★ Travel ★ Performance marketing
                                            ★        ★
Rakuten’s Global Position


 Rakuten is aiming to be the world’s largest internet firm.
 Firm and highly flexible infrastructure is required to achieve this
  goal
         Retail / auction site global ranking 2011 based on unique (no. of) visitors
                  300000

                  250000

                  200000

                  150000

                  100000

                   50000

                       0
                           Amazon   e-Bay   Alibaba   Apple   Rakuten   Walmart




                                                                                  Source: comScore Media Metrics
Rakuten Database
 Breakdown according to the number of databases:
  approx. 80% MySQL (more than 1100)
 More than 350 MySQL database servers
 MySQL has the largest share
        Oracle PostgreSQL   Teraddata




                                            No. of databases according
              Informix
                                             to actual environment
                                             RDBMS

                                            Same number of databases
                                             for each STG and DEV


                                   MySQL


                                                                          6
MySQL Database Issue (1)

 Data Sharding Operations
    Required for functionality scaling
    Instance/database/table splitting, data redistribution
    Correction of application code, control of database access



 Data Protection, HA Securing
    Replication cannot realize zero data loss at failure
    Switch back/switch over management takes a lot of effort




                                                                  7
MySQL Database Issue (2)

 Online Maintainability
    Schema modification and index addition, rebuild
    Lock, access concentration



 Number of Units Tends to Increase
    Load distribution slave, redundant configuration of slave
    Tendency for preparations on an individual service basis (service level
     differences, maintenance adjustment diversion)
    CPU efficiency decreases; increases in data center costs




                                                                               8
Clustrix Characteristics

What is Clustrix?

 Appliance-style database server
 Cluster database
    NewSQL = LegacySQL + NoSQL
         LegacySQL: SQL access, transaction consistency
         NoSQL: Scalability, high performance

 Fault-tolerance function
 MySQL compatibility
    Usually access is through MySQL protocol




                                                           9
Clustrix Provision Model
 2 Models




                                10
Looking at Clustrix




                      SSD

                       Infiniband
                         Low latency
                         High performance




                            11
Clustrix Operation

 Distributed arrangement on the physical layer
 Redundancy protection, auto rebalance
 Parallel query execution
                                         SQL


         SQL         SQL       SQL       Query, not data, is
                                          migrated (this
                                          concept differs
                                          from Oracle RAC)




                                                                12
TPC-C Benchmark Result




                         13
GUI




      14
Useful Command Interface




                           15
Clustrix Implementation Cases


Rakuten is the first case in Japan
Numerous foreign cases




                                      16
Verification Points


Performance
Scalability
Fault-tolerance verification
Online schema modification




                                17
OLTP Performance Results (1)

                                                        Insert
                    45000

                    40000

                    35000

                    30000

                    25000
(ops/sec)
                    20000

                    15000

                    10000

                     5000

                         0
                                  p3           p12            p24          p48           p96           p192
     Single Throughput        4014.703409   8350.801098   10022.32827   10448.25479   10520.08066   10213.98278
     Clx 3 nodesThroughput    6301.603599   18530.31626   26182.77331   30021.30841   27581.92104   24401.28904
     Clx 4 nodes Throughput   6090.513193    20584.42      30544.8252   38545.21774   36837.10176   33221.72529




                                                                                                                  18
OLTP (2)

                                                     Update
                    25000



                    20000



                    15000

(ops/sec)

                    10000



                     5000



                         0
                                  p3           p12           p24           p48           p96           p192
     Single Throughput        3854.243586   8018.593249   12186.20793   13385.77834   13395.06587   11538.29668
     Clx 3 nodes Throughput   3377.359372   10741.77417   16505.79652   16964.01107   16189.88416   15379.62683
     Clx 4 nodes Throughput   3682.99886    12679.26966   19737.63815   22232.7357    21568.39318   21303.72872




                                                                                         19
OLTP (3)

                                                          Read
                    80000

                    70000

                    60000

                    50000

(ops/sec)           40000

                    30000

                    20000

                    10000

                         0
                                  p3           p12             p24           p48           p96           p192
     Single Throughput        6134.386466   26773.71202     44388.78477   56144.27281   57926.62433   49362.51106
     Clx 3 nodes Throughput   5050.230295   17380.6806      27803.82494   39693.75633   49822.34026   56847.77879
     Clx 4 nodes Throughput   5959.900064   20794.2083      34743.31655   54382.96419   70302.27313   76000.59175




                                                                                           20
OLTP (4)

                                                           Mix
                    40000

                    35000

                    30000

                    25000

(ops/sec)           20000

                    15000

                    10000

                     5000

                         0
                                  p3            p12              p24         p48           p96           p192
     Single Throughput        3976.841546    8587.218158    11632.64122   12946.2536    13122.33748   12769.45794
     Clx 3 nodes Throughput   3113.109431    12940.99191    21264.63309   26759.75291   25976.26625   25334.18054
     Clx 4 nodes Throughput   5150.537999    15220.8469     25601.67909   34647.41616    34697.737    30804.09949




                                                                                            21
Complex and Heavy SQL Comparison




                                    Clustrix        IA with SSD      SPARC with SAN
J) Count+GroupBy+OrderBy+Limit    1.9s (3.4s)        2.1s (8.5s)      3.4s (409.32s)

K) Count+GroupBy+OrderBy+Limit    0.7s (1.13s)      5.9s (7.49s)      13.0s (39.41s)

     L) 2000 of IN+GroupBy        3.8s (8.97s)    106.5s (103.77s)   193.0s (321.68s)

       M) Case+OrderBy           31.0s (45.66s)    47.3s (60.9s) 22 90.5s (112.24s)
Example of Performance Improvements


 Example improvements regarding a particular service
    Before: 116.8ms
    After: 21.4ms




                                            23
Fault-Tolerance Inspection
     Failure Test Items           Downtime
1    Front network (port1)        No

2    Front network (port2)        No

3    Internal network (primary)   < 12s

4    Internal network (standby) No
                                                               Front SW1              Front SW2
5    MySQL instance               < 4s

6    Node OS                      < 4s             1

     Online data disk                                                                                        11
7                                 < 5s                 2
     (SSD) failure
     Log/work data disk
8                                 No         DB            DB                    DB                         DB
     (SATA) failure                          5,6                           7,8

9                                                          4                                                 12
     Infiniband switch (primary) < 12s
                                                   3
10   Infiniband switch (standby) No

11   Front network (port1&2)      < 18s                                                                10
                                                                       9
     Internal network
12                                < 12s                Infiniband SW1                 Infiniband SW2
     (primary & standby)
                                                                                                                  24
Time Required for Online Maintenance
Table Rows and Size

                      Small       Medium                Large
       Row            50,000      500,000          5,000,000
    Size (byte)   113,639,424   1,063,190,528    10,696,130,560

Implementation Time
                       Small       Medium               Large
 Create Column          1.6s         13.5               149.8
  Create Index          1.6s         13.0s              172.7s
  Drop Column           1.5s         13.8s              125.5s
   Drop Index           0.5s         0.5s                0.5s
                                                   25
Impacts During Online Scheme Modification

 No impact on access performance in areas other than those subject to work operations
 Some impact on performance of access to table being subject to work operations (taking
  periods with little impacts, such as night service, into consideration)




                                                                           Online execution –
                                                                            5 million
                                                                            cases, total tables
                                                                            10G
                                                                         26
Clustrix Implementation Impacts Release from Sharding (1)


Before
                                                        ……
    DB           DB            DB           DB
                                                        ……
                                             No more sharding!
After



         DB           DB            DB           DB
                                                          ……    +
Clustrix Implementation Impacts Release from Sharding (2)



 No need for correction of application
 No need for DB distribution
 Sharding production costs reduction (over 90%) for
  both application engineer and DBA


                                                         In case of large-scale
as-i
   s                                                      sharding
                                                          project, actual
                                                          production costs
                                           DBA
                                                          compared to
to-be
                                           APP
                                                          original

        0   2     4     6        8    10   12    14
                        m an-m onth


                                                                                   28
Clustrix Implementation Impacts Cost Reductions due to Consolidation (1)



     Sufficient performance scalability
     Fault-tolerance ready for mission critical
     No data loss
     High online maintainability that doesn’t affect other services
     Possibility of consolidation to Clustrix of existing MySQL
      database




                                                                           29
Clustrix Implementation Impacts Cost Reductions due to Consolidation (2)



    Consolidation of all existing MySQL within Clustrix
    Number of servers will be reduced to 10%
    Monthly system costs will be reduced to 40%




                                                                           30
Back-up Structure




                             Clustrix

DB                      DB                     DB
                                                                 …
     Node 1                    Node 2               Node 3




                                 Replication
      Slave as first
         backup
                                          Backup by mysqldump
                       MySQL
               DB

                                                     NFS

                                                           NAS
                                                                     31
Data Migration Procedure


      Replication to DEV for verification
      Replication to PRO for migration
      Conversion of application access point to PRO


                                                             MySQL
                                                        DB


                                                         Replication
                                 Replication
                                                              Clustrix DEV

               Clustrix PRO                        DB         DB             DB




DB              DB             DB




                                                                                  32
Other Advantages of Clustrix


 Auto-Defrag
 Cordial Support Service
      Advice regarding structure
      Troubleshooting
      Tuning advice
      Etc.




                                           33
Operational Issues Resolved with Clustrix


 Data sharding operations           Unnecessary, operational
                                      cost reduction

 Data protection, HA securing       Possible

 Online maintenance                 Possible

 Tendency for large number of units  Consolidation possible
                                      Cost reduction



                                                                 34
Clustrix at Rakuten


 An important database platform
 Provided as Database-as-a-Service
 No lead-time
 Usage volume rate structure




                                      35

Weitere ähnliche Inhalte

Was ist angesagt?

Case Study on Caterpillar Inc. (CAT)
Case Study on Caterpillar Inc. (CAT)Case Study on Caterpillar Inc. (CAT)
Case Study on Caterpillar Inc. (CAT)Rishav Kar
 
Star Alliance| formation of Star Alliance| Benefits and Services
Star Alliance| formation of Star Alliance| Benefits and ServicesStar Alliance| formation of Star Alliance| Benefits and Services
Star Alliance| formation of Star Alliance| Benefits and ServicesAishwarya Saraf
 
Business Strategy Retail Wal Mart
Business Strategy Retail Wal MartBusiness Strategy Retail Wal Mart
Business Strategy Retail Wal MartJaspal Bhatia
 
Airbus A3XX: Developing the World’s Largest Commercial Jet
Airbus A3XX: Developing the World’s Largest Commercial Jet Airbus A3XX: Developing the World’s Largest Commercial Jet
Airbus A3XX: Developing the World’s Largest Commercial Jet Rishi Bajaj
 
Which fast food place is the best: McDonald's, Burger King, Jack in the Box, ...
Which fast food place is the best: McDonald's, Burger King, Jack in the Box, ...Which fast food place is the best: McDonald's, Burger King, Jack in the Box, ...
Which fast food place is the best: McDonald's, Burger King, Jack in the Box, ...Mrs. Sumida
 
Architecting for GxP Compliance in Life Sciences (LFS316) - AWS re:Invent 2018
Architecting for GxP Compliance in Life Sciences (LFS316) - AWS re:Invent 2018Architecting for GxP Compliance in Life Sciences (LFS316) - AWS re:Invent 2018
Architecting for GxP Compliance in Life Sciences (LFS316) - AWS re:Invent 2018Amazon Web Services
 
Caterpillar inc. Case study
Caterpillar inc. Case studyCaterpillar inc. Case study
Caterpillar inc. Case studySaideep Punna
 
Wholesale strategies.pptx
Wholesale strategies.pptxWholesale strategies.pptx
Wholesale strategies.pptxAsmaRauf5
 
SPSS- Output and Interpretation
SPSS- Output and InterpretationSPSS- Output and Interpretation
SPSS- Output and InterpretationHarshvardhan Pal
 
Olympics car rental case study
Olympics car rental case studyOlympics car rental case study
Olympics car rental case studyVivek Jha
 
CRM: MAHINDRA FIRST CHOICE SERVICES: CREATING A VALUE PROPOSITION
CRM: MAHINDRA FIRST CHOICE SERVICES: CREATING A VALUE PROPOSITIONCRM: MAHINDRA FIRST CHOICE SERVICES: CREATING A VALUE PROPOSITION
CRM: MAHINDRA FIRST CHOICE SERVICES: CREATING A VALUE PROPOSITIONDisha Ghoshal
 
Nestle Purina Power Point(withVideo)
Nestle Purina Power Point(withVideo)Nestle Purina Power Point(withVideo)
Nestle Purina Power Point(withVideo)David Friedman
 
Virgin atlantic
Virgin atlanticVirgin atlantic
Virgin atlanticHarsh Shah
 
Entity relationship diagram for foxcore retail
Entity relationship diagram for foxcore retailEntity relationship diagram for foxcore retail
Entity relationship diagram for foxcore retailSHIVAMSHARMA1271
 

Was ist angesagt? (20)

Case Study on Caterpillar Inc. (CAT)
Case Study on Caterpillar Inc. (CAT)Case Study on Caterpillar Inc. (CAT)
Case Study on Caterpillar Inc. (CAT)
 
Nike valuation report
Nike valuation reportNike valuation report
Nike valuation report
 
Star Alliance| formation of Star Alliance| Benefits and Services
Star Alliance| formation of Star Alliance| Benefits and ServicesStar Alliance| formation of Star Alliance| Benefits and Services
Star Alliance| formation of Star Alliance| Benefits and Services
 
Business Strategy Retail Wal Mart
Business Strategy Retail Wal MartBusiness Strategy Retail Wal Mart
Business Strategy Retail Wal Mart
 
Airbus A3XX: Developing the World’s Largest Commercial Jet
Airbus A3XX: Developing the World’s Largest Commercial Jet Airbus A3XX: Developing the World’s Largest Commercial Jet
Airbus A3XX: Developing the World’s Largest Commercial Jet
 
Which fast food place is the best: McDonald's, Burger King, Jack in the Box, ...
Which fast food place is the best: McDonald's, Burger King, Jack in the Box, ...Which fast food place is the best: McDonald's, Burger King, Jack in the Box, ...
Which fast food place is the best: McDonald's, Burger King, Jack in the Box, ...
 
Architecting for GxP Compliance in Life Sciences (LFS316) - AWS re:Invent 2018
Architecting for GxP Compliance in Life Sciences (LFS316) - AWS re:Invent 2018Architecting for GxP Compliance in Life Sciences (LFS316) - AWS re:Invent 2018
Architecting for GxP Compliance in Life Sciences (LFS316) - AWS re:Invent 2018
 
Caterpillar inc. Case study
Caterpillar inc. Case studyCaterpillar inc. Case study
Caterpillar inc. Case study
 
Lockheed martin
Lockheed martinLockheed martin
Lockheed martin
 
Wholesale strategies.pptx
Wholesale strategies.pptxWholesale strategies.pptx
Wholesale strategies.pptx
 
Carnival
CarnivalCarnival
Carnival
 
SPSS- Output and Interpretation
SPSS- Output and InterpretationSPSS- Output and Interpretation
SPSS- Output and Interpretation
 
Olympics car rental case study
Olympics car rental case studyOlympics car rental case study
Olympics car rental case study
 
CRM: MAHINDRA FIRST CHOICE SERVICES: CREATING A VALUE PROPOSITION
CRM: MAHINDRA FIRST CHOICE SERVICES: CREATING A VALUE PROPOSITIONCRM: MAHINDRA FIRST CHOICE SERVICES: CREATING A VALUE PROPOSITION
CRM: MAHINDRA FIRST CHOICE SERVICES: CREATING A VALUE PROPOSITION
 
United Parcel Service
United Parcel ServiceUnited Parcel Service
United Parcel Service
 
Nestle Purina Power Point(withVideo)
Nestle Purina Power Point(withVideo)Nestle Purina Power Point(withVideo)
Nestle Purina Power Point(withVideo)
 
Application of porter analysis to steel industry jeet
Application of porter analysis to steel industry jeetApplication of porter analysis to steel industry jeet
Application of porter analysis to steel industry jeet
 
MidlandCase
MidlandCaseMidlandCase
MidlandCase
 
Virgin atlantic
Virgin atlanticVirgin atlantic
Virgin atlantic
 
Entity relationship diagram for foxcore retail
Entity relationship diagram for foxcore retailEntity relationship diagram for foxcore retail
Entity relationship diagram for foxcore retail
 

Andere mochten auch

How Rakuten Reduced Database Management Spending by 90%
How Rakuten Reduced Database Management Spending by 90%How Rakuten Reduced Database Management Spending by 90%
How Rakuten Reduced Database Management Spending by 90%Rakuten Group, Inc.
 
Clustrixによる社内データベースクラウド環境の提供
Clustrixによる社内データベースクラウド環境の提供Clustrixによる社内データベースクラウド環境の提供
Clustrixによる社内データベースクラウド環境の提供Rakuten Group, Inc.
 
楽天トラベルの開発プロセスに関して
楽天トラベルの開発プロセスに関して楽天トラベルの開発プロセスに関して
楽天トラベルの開発プロセスに関してRakuten Group, Inc.
 
Rakuten’s Journey with Splunk - Evolution of Splunk as a Service
Rakuten’s Journey with Splunk - Evolution of Splunk as a ServiceRakuten’s Journey with Splunk - Evolution of Splunk as a Service
Rakuten’s Journey with Splunk - Evolution of Splunk as a ServiceRakuten Group, Inc.
 
NewSQL - The Future of Databases?
NewSQL - The Future of Databases?NewSQL - The Future of Databases?
NewSQL - The Future of Databases?Elvis Saravia
 
Jubatus: Realtime deep analytics for BIgData@Rakuten Technology Conference 2012
Jubatus: Realtime deep analytics for BIgData@Rakuten Technology Conference 2012Jubatus: Realtime deep analytics for BIgData@Rakuten Technology Conference 2012
Jubatus: Realtime deep analytics for BIgData@Rakuten Technology Conference 2012Preferred Networks
 
NewSQL overview, Feb 2015
NewSQL overview, Feb 2015NewSQL overview, Feb 2015
NewSQL overview, Feb 2015Ivan Glushkov
 

Andere mochten auch (8)

How Rakuten Reduced Database Management Spending by 90%
How Rakuten Reduced Database Management Spending by 90%How Rakuten Reduced Database Management Spending by 90%
How Rakuten Reduced Database Management Spending by 90%
 
Clustrixによる社内データベースクラウド環境の提供
Clustrixによる社内データベースクラウド環境の提供Clustrixによる社内データベースクラウド環境の提供
Clustrixによる社内データベースクラウド環境の提供
 
楽天のSplunk as a service
楽天のSplunk as a service楽天のSplunk as a service
楽天のSplunk as a service
 
楽天トラベルの開発プロセスに関して
楽天トラベルの開発プロセスに関して楽天トラベルの開発プロセスに関して
楽天トラベルの開発プロセスに関して
 
Rakuten’s Journey with Splunk - Evolution of Splunk as a Service
Rakuten’s Journey with Splunk - Evolution of Splunk as a ServiceRakuten’s Journey with Splunk - Evolution of Splunk as a Service
Rakuten’s Journey with Splunk - Evolution of Splunk as a Service
 
NewSQL - The Future of Databases?
NewSQL - The Future of Databases?NewSQL - The Future of Databases?
NewSQL - The Future of Databases?
 
Jubatus: Realtime deep analytics for BIgData@Rakuten Technology Conference 2012
Jubatus: Realtime deep analytics for BIgData@Rakuten Technology Conference 2012Jubatus: Realtime deep analytics for BIgData@Rakuten Technology Conference 2012
Jubatus: Realtime deep analytics for BIgData@Rakuten Technology Conference 2012
 
NewSQL overview, Feb 2015
NewSQL overview, Feb 2015NewSQL overview, Feb 2015
NewSQL overview, Feb 2015
 

Ähnlich wie How Rakuten Reduced Database Management Spending by 90% through Clustrix implementation

MySQL Manchester TT - MySQL Enterprise Edition
MySQL Manchester TT - MySQL Enterprise EditionMySQL Manchester TT - MySQL Enterprise Edition
MySQL Manchester TT - MySQL Enterprise EditionMark Swarbrick
 
Introducing the ultimate MariaDB cloud, SkySQL
Introducing the ultimate MariaDB cloud, SkySQLIntroducing the ultimate MariaDB cloud, SkySQL
Introducing the ultimate MariaDB cloud, SkySQLMariaDB plc
 
How MariaDB is approaching DBaaS
How MariaDB is approaching DBaaSHow MariaDB is approaching DBaaS
How MariaDB is approaching DBaaSMariaDB plc
 
NoSQL – Beyond the Key-Value Store
NoSQL – Beyond the Key-Value StoreNoSQL – Beyond the Key-Value Store
NoSQL – Beyond the Key-Value StoreDATAVERSITY
 
DataStax C*ollege Credit: What and Why NoSQL?
DataStax C*ollege Credit: What and Why NoSQL?DataStax C*ollege Credit: What and Why NoSQL?
DataStax C*ollege Credit: What and Why NoSQL?DataStax
 
Vote NO for MySQL
Vote NO for MySQLVote NO for MySQL
Vote NO for MySQLUlf Wendel
 
Cloud Patterns Beuth Hochschule
Cloud Patterns Beuth HochschuleCloud Patterns Beuth Hochschule
Cloud Patterns Beuth HochschuleSascha Möllering
 
Supersizing Magento
Supersizing MagentoSupersizing Magento
Supersizing MagentoClustrix
 
2019 - GUOB Tech Day / Groundbreakers LAD Tour - Database Migration Methods t...
2019 - GUOB Tech Day / Groundbreakers LAD Tour - Database Migration Methods t...2019 - GUOB Tech Day / Groundbreakers LAD Tour - Database Migration Methods t...
2019 - GUOB Tech Day / Groundbreakers LAD Tour - Database Migration Methods t...Marcus Vinicius Miguel Pedro
 
001 hbase introduction
001 hbase introduction001 hbase introduction
001 hbase introductionScott Miao
 
(ARC309) Getting to Microservices: Cloud Architecture Patterns
(ARC309) Getting to Microservices: Cloud Architecture Patterns(ARC309) Getting to Microservices: Cloud Architecture Patterns
(ARC309) Getting to Microservices: Cloud Architecture PatternsAmazon Web Services
 
The architecture of SkySQL
The architecture of SkySQLThe architecture of SkySQL
The architecture of SkySQLMariaDB plc
 
M|18 How Copart Switched to MariaDB and Reduced Costs During Growth
M|18 How Copart Switched to MariaDB and Reduced Costs During GrowthM|18 How Copart Switched to MariaDB and Reduced Costs During Growth
M|18 How Copart Switched to MariaDB and Reduced Costs During GrowthMariaDB plc
 
AWS Certified Cloud Practitioner Course S11-S17
AWS Certified Cloud Practitioner Course S11-S17AWS Certified Cloud Practitioner Course S11-S17
AWS Certified Cloud Practitioner Course S11-S17Neal Davis
 
Commit Conf 2018 - Hotelbeds' journey to a microservice cloud-based architecture
Commit Conf 2018 - Hotelbeds' journey to a microservice cloud-based architectureCommit Conf 2018 - Hotelbeds' journey to a microservice cloud-based architecture
Commit Conf 2018 - Hotelbeds' journey to a microservice cloud-based architectureJordi Puigsegur Figueras
 
Webinar Slides: MySQL HA/DR/Geo-Scale - High Noon #5: Oracle’s InnoDB Cluster
Webinar Slides: MySQL HA/DR/Geo-Scale - High Noon #5: Oracle’s InnoDB ClusterWebinar Slides: MySQL HA/DR/Geo-Scale - High Noon #5: Oracle’s InnoDB Cluster
Webinar Slides: MySQL HA/DR/Geo-Scale - High Noon #5: Oracle’s InnoDB ClusterContinuent
 
Benchmark Showdown: Which Relational Database is the Fastest on AWS?
Benchmark Showdown: Which Relational Database is the Fastest on AWS?Benchmark Showdown: Which Relational Database is the Fastest on AWS?
Benchmark Showdown: Which Relational Database is the Fastest on AWS?Clustrix
 

Ähnlich wie How Rakuten Reduced Database Management Spending by 90% through Clustrix implementation (20)

MySQL@king
MySQL@kingMySQL@king
MySQL@king
 
MySQL Manchester TT - MySQL Enterprise Edition
MySQL Manchester TT - MySQL Enterprise EditionMySQL Manchester TT - MySQL Enterprise Edition
MySQL Manchester TT - MySQL Enterprise Edition
 
Introducing the ultimate MariaDB cloud, SkySQL
Introducing the ultimate MariaDB cloud, SkySQLIntroducing the ultimate MariaDB cloud, SkySQL
Introducing the ultimate MariaDB cloud, SkySQL
 
How MariaDB is approaching DBaaS
How MariaDB is approaching DBaaSHow MariaDB is approaching DBaaS
How MariaDB is approaching DBaaS
 
NoSQL – Beyond the Key-Value Store
NoSQL – Beyond the Key-Value StoreNoSQL – Beyond the Key-Value Store
NoSQL – Beyond the Key-Value Store
 
DataStax C*ollege Credit: What and Why NoSQL?
DataStax C*ollege Credit: What and Why NoSQL?DataStax C*ollege Credit: What and Why NoSQL?
DataStax C*ollege Credit: What and Why NoSQL?
 
Trustpilot
TrustpilotTrustpilot
Trustpilot
 
Vote NO for MySQL
Vote NO for MySQLVote NO for MySQL
Vote NO for MySQL
 
Cloud Patterns Beuth Hochschule
Cloud Patterns Beuth HochschuleCloud Patterns Beuth Hochschule
Cloud Patterns Beuth Hochschule
 
Supersizing Magento
Supersizing MagentoSupersizing Magento
Supersizing Magento
 
2019 - GUOB Tech Day / Groundbreakers LAD Tour - Database Migration Methods t...
2019 - GUOB Tech Day / Groundbreakers LAD Tour - Database Migration Methods t...2019 - GUOB Tech Day / Groundbreakers LAD Tour - Database Migration Methods t...
2019 - GUOB Tech Day / Groundbreakers LAD Tour - Database Migration Methods t...
 
001 hbase introduction
001 hbase introduction001 hbase introduction
001 hbase introduction
 
(ARC309) Getting to Microservices: Cloud Architecture Patterns
(ARC309) Getting to Microservices: Cloud Architecture Patterns(ARC309) Getting to Microservices: Cloud Architecture Patterns
(ARC309) Getting to Microservices: Cloud Architecture Patterns
 
The architecture of SkySQL
The architecture of SkySQLThe architecture of SkySQL
The architecture of SkySQL
 
M|18 How Copart Switched to MariaDB and Reduced Costs During Growth
M|18 How Copart Switched to MariaDB and Reduced Costs During GrowthM|18 How Copart Switched to MariaDB and Reduced Costs During Growth
M|18 How Copart Switched to MariaDB and Reduced Costs During Growth
 
AWS Certified Cloud Practitioner Course S11-S17
AWS Certified Cloud Practitioner Course S11-S17AWS Certified Cloud Practitioner Course S11-S17
AWS Certified Cloud Practitioner Course S11-S17
 
Commit Conf 2018 - Hotelbeds' journey to a microservice cloud-based architecture
Commit Conf 2018 - Hotelbeds' journey to a microservice cloud-based architectureCommit Conf 2018 - Hotelbeds' journey to a microservice cloud-based architecture
Commit Conf 2018 - Hotelbeds' journey to a microservice cloud-based architecture
 
2020 - OCI Key Concepts for Oracle DBAs
2020 - OCI Key Concepts for Oracle DBAs2020 - OCI Key Concepts for Oracle DBAs
2020 - OCI Key Concepts for Oracle DBAs
 
Webinar Slides: MySQL HA/DR/Geo-Scale - High Noon #5: Oracle’s InnoDB Cluster
Webinar Slides: MySQL HA/DR/Geo-Scale - High Noon #5: Oracle’s InnoDB ClusterWebinar Slides: MySQL HA/DR/Geo-Scale - High Noon #5: Oracle’s InnoDB Cluster
Webinar Slides: MySQL HA/DR/Geo-Scale - High Noon #5: Oracle’s InnoDB Cluster
 
Benchmark Showdown: Which Relational Database is the Fastest on AWS?
Benchmark Showdown: Which Relational Database is the Fastest on AWS?Benchmark Showdown: Which Relational Database is the Fastest on AWS?
Benchmark Showdown: Which Relational Database is the Fastest on AWS?
 

Mehr von Rakuten Group, Inc.

コードレビュー改善のためにJenkinsとIntelliJ IDEAのプラグインを自作してみた話
コードレビュー改善のためにJenkinsとIntelliJ IDEAのプラグインを自作してみた話コードレビュー改善のためにJenkinsとIntelliJ IDEAのプラグインを自作してみた話
コードレビュー改善のためにJenkinsとIntelliJ IDEAのプラグインを自作してみた話Rakuten Group, Inc.
 
楽天における安全な秘匿情報管理への道のり
楽天における安全な秘匿情報管理への道のり楽天における安全な秘匿情報管理への道のり
楽天における安全な秘匿情報管理への道のりRakuten Group, Inc.
 
Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product At...
Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product At...Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product At...
Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product At...Rakuten Group, Inc.
 
DataSkillCultureを浸透させる楽天の取り組み
DataSkillCultureを浸透させる楽天の取り組みDataSkillCultureを浸透させる楽天の取り組み
DataSkillCultureを浸透させる楽天の取り組みRakuten Group, Inc.
 
大規模なリアルタイム監視の導入と展開
大規模なリアルタイム監視の導入と展開大規模なリアルタイム監視の導入と展開
大規模なリアルタイム監視の導入と展開Rakuten Group, Inc.
 
楽天における大規模データベースの運用
楽天における大規模データベースの運用楽天における大規模データベースの運用
楽天における大規模データベースの運用Rakuten Group, Inc.
 
楽天サービスを支えるネットワークインフラストラクチャー
楽天サービスを支えるネットワークインフラストラクチャー楽天サービスを支えるネットワークインフラストラクチャー
楽天サービスを支えるネットワークインフラストラクチャーRakuten Group, Inc.
 
楽天の規模とクラウドプラットフォーム統括部の役割
楽天の規模とクラウドプラットフォーム統括部の役割楽天の規模とクラウドプラットフォーム統括部の役割
楽天の規模とクラウドプラットフォーム統括部の役割Rakuten Group, Inc.
 
Rakuten Services and Infrastructure Team.pdf
Rakuten Services and Infrastructure Team.pdfRakuten Services and Infrastructure Team.pdf
Rakuten Services and Infrastructure Team.pdfRakuten Group, Inc.
 
The Data Platform Administration Handling the 100 PB.pdf
The Data Platform Administration Handling the 100 PB.pdfThe Data Platform Administration Handling the 100 PB.pdf
The Data Platform Administration Handling the 100 PB.pdfRakuten Group, Inc.
 
Supporting Internal Customers as Technical Account Managers.pdf
Supporting Internal Customers as Technical Account Managers.pdfSupporting Internal Customers as Technical Account Managers.pdf
Supporting Internal Customers as Technical Account Managers.pdfRakuten Group, Inc.
 
Making Cloud Native CI_CD Services.pdf
Making Cloud Native CI_CD Services.pdfMaking Cloud Native CI_CD Services.pdf
Making Cloud Native CI_CD Services.pdfRakuten Group, Inc.
 
How We Defined Our Own Cloud.pdf
How We Defined Our Own Cloud.pdfHow We Defined Our Own Cloud.pdf
How We Defined Our Own Cloud.pdfRakuten Group, Inc.
 
Travel & Leisure Platform Department's tech info
Travel & Leisure Platform Department's tech infoTravel & Leisure Platform Department's tech info
Travel & Leisure Platform Department's tech infoRakuten Group, Inc.
 
Travel & Leisure Platform Department's tech info
Travel & Leisure Platform Department's tech infoTravel & Leisure Platform Department's tech info
Travel & Leisure Platform Department's tech infoRakuten Group, Inc.
 
Introduction of GORA API Group technology
Introduction of GORA API Group technologyIntroduction of GORA API Group technology
Introduction of GORA API Group technologyRakuten Group, Inc.
 
100PBを越えるデータプラットフォームの実情
100PBを越えるデータプラットフォームの実情100PBを越えるデータプラットフォームの実情
100PBを越えるデータプラットフォームの実情Rakuten Group, Inc.
 
社内エンジニアを支えるテクニカルアカウントマネージャー
社内エンジニアを支えるテクニカルアカウントマネージャー社内エンジニアを支えるテクニカルアカウントマネージャー
社内エンジニアを支えるテクニカルアカウントマネージャーRakuten Group, Inc.
 

Mehr von Rakuten Group, Inc. (20)

コードレビュー改善のためにJenkinsとIntelliJ IDEAのプラグインを自作してみた話
コードレビュー改善のためにJenkinsとIntelliJ IDEAのプラグインを自作してみた話コードレビュー改善のためにJenkinsとIntelliJ IDEAのプラグインを自作してみた話
コードレビュー改善のためにJenkinsとIntelliJ IDEAのプラグインを自作してみた話
 
楽天における安全な秘匿情報管理への道のり
楽天における安全な秘匿情報管理への道のり楽天における安全な秘匿情報管理への道のり
楽天における安全な秘匿情報管理への道のり
 
What Makes Software Green?
What Makes Software Green?What Makes Software Green?
What Makes Software Green?
 
Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product At...
Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product At...Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product At...
Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product At...
 
DataSkillCultureを浸透させる楽天の取り組み
DataSkillCultureを浸透させる楽天の取り組みDataSkillCultureを浸透させる楽天の取り組み
DataSkillCultureを浸透させる楽天の取り組み
 
大規模なリアルタイム監視の導入と展開
大規模なリアルタイム監視の導入と展開大規模なリアルタイム監視の導入と展開
大規模なリアルタイム監視の導入と展開
 
楽天における大規模データベースの運用
楽天における大規模データベースの運用楽天における大規模データベースの運用
楽天における大規模データベースの運用
 
楽天サービスを支えるネットワークインフラストラクチャー
楽天サービスを支えるネットワークインフラストラクチャー楽天サービスを支えるネットワークインフラストラクチャー
楽天サービスを支えるネットワークインフラストラクチャー
 
楽天の規模とクラウドプラットフォーム統括部の役割
楽天の規模とクラウドプラットフォーム統括部の役割楽天の規模とクラウドプラットフォーム統括部の役割
楽天の規模とクラウドプラットフォーム統括部の役割
 
Rakuten Services and Infrastructure Team.pdf
Rakuten Services and Infrastructure Team.pdfRakuten Services and Infrastructure Team.pdf
Rakuten Services and Infrastructure Team.pdf
 
The Data Platform Administration Handling the 100 PB.pdf
The Data Platform Administration Handling the 100 PB.pdfThe Data Platform Administration Handling the 100 PB.pdf
The Data Platform Administration Handling the 100 PB.pdf
 
Supporting Internal Customers as Technical Account Managers.pdf
Supporting Internal Customers as Technical Account Managers.pdfSupporting Internal Customers as Technical Account Managers.pdf
Supporting Internal Customers as Technical Account Managers.pdf
 
Making Cloud Native CI_CD Services.pdf
Making Cloud Native CI_CD Services.pdfMaking Cloud Native CI_CD Services.pdf
Making Cloud Native CI_CD Services.pdf
 
How We Defined Our Own Cloud.pdf
How We Defined Our Own Cloud.pdfHow We Defined Our Own Cloud.pdf
How We Defined Our Own Cloud.pdf
 
Travel & Leisure Platform Department's tech info
Travel & Leisure Platform Department's tech infoTravel & Leisure Platform Department's tech info
Travel & Leisure Platform Department's tech info
 
Travel & Leisure Platform Department's tech info
Travel & Leisure Platform Department's tech infoTravel & Leisure Platform Department's tech info
Travel & Leisure Platform Department's tech info
 
OWASPTop10_Introduction
OWASPTop10_IntroductionOWASPTop10_Introduction
OWASPTop10_Introduction
 
Introduction of GORA API Group technology
Introduction of GORA API Group technologyIntroduction of GORA API Group technology
Introduction of GORA API Group technology
 
100PBを越えるデータプラットフォームの実情
100PBを越えるデータプラットフォームの実情100PBを越えるデータプラットフォームの実情
100PBを越えるデータプラットフォームの実情
 
社内エンジニアを支えるテクニカルアカウントマネージャー
社内エンジニアを支えるテクニカルアカウントマネージャー社内エンジニアを支えるテクニカルアカウントマネージャー
社内エンジニアを支えるテクニカルアカウントマネージャー
 

How Rakuten Reduced Database Management Spending by 90% through Clustrix implementation

  • 1. 楽天事例紹介: Clustrix導入による DB管理コストの削減 How Rakuten Reduced Database Management Spending by 90% through Clustrix implementation October 17th, 2012 Ryutaro Yada (矢田 龍太郎) Database Platform Group Global Infrastructure Development Dept. Rakuten, Inc.
  • 2. Introduction  Ryutaro Yada  First employed by Rakuten in 2008  Present job  Development of a platform database to support Rakuten  Testing and discussion of new techniques and new architecture in view of having it adopted for use.  Previous functions  Promotion of Oracle business with specified customer  Establish collaborative network with Oracle, develop and verify new solutions, etc..  LinkedIn profile: http://www.linkedin.com/pub/ryutaro-yada/32/368/4b0 1
  • 3. Agenda  About Rakuten  Rakuten database environment and operational issues  What is Clustrix?  Clustrix verification results and implementation effectiveness  Summary 2
  • 4. Introduction to Rakuten  About 3000 employees: (Group approx. 7000)  Market / more than 40 services provided including travel  More than 120,000 contracted firms; more than 80,000,000 registered products  Group distribution total: 3.2 trillion yen (2011) Rakuten market
  • 5. Rakuten Global Expansion Our Goal is to become the No. 1 Internet Service in the World LS(UK) ★★ ★ ★ ★ ★★ ★ ★ ★★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★ ★★ ★ ★★ ★ ★ ★ ★★ ★ ★ ★ ★★ ★ ★★ Taiwan ★ ★ ★ ★ *To be open soon ★ ★ ★ ★ ★ Ichiba (EC) ★ ★ Travel ★ Performance marketing ★ ★
  • 6. Rakuten’s Global Position  Rakuten is aiming to be the world’s largest internet firm.  Firm and highly flexible infrastructure is required to achieve this goal Retail / auction site global ranking 2011 based on unique (no. of) visitors 300000 250000 200000 150000 100000 50000 0 Amazon e-Bay Alibaba Apple Rakuten Walmart Source: comScore Media Metrics
  • 7. Rakuten Database  Breakdown according to the number of databases: approx. 80% MySQL (more than 1100)  More than 350 MySQL database servers  MySQL has the largest share Oracle PostgreSQL Teraddata  No. of databases according Informix to actual environment RDBMS  Same number of databases for each STG and DEV MySQL 6
  • 8. MySQL Database Issue (1)  Data Sharding Operations  Required for functionality scaling  Instance/database/table splitting, data redistribution  Correction of application code, control of database access  Data Protection, HA Securing  Replication cannot realize zero data loss at failure  Switch back/switch over management takes a lot of effort 7
  • 9. MySQL Database Issue (2)  Online Maintainability  Schema modification and index addition, rebuild  Lock, access concentration  Number of Units Tends to Increase  Load distribution slave, redundant configuration of slave  Tendency for preparations on an individual service basis (service level differences, maintenance adjustment diversion)  CPU efficiency decreases; increases in data center costs 8
  • 10. Clustrix Characteristics What is Clustrix?  Appliance-style database server  Cluster database  NewSQL = LegacySQL + NoSQL  LegacySQL: SQL access, transaction consistency  NoSQL: Scalability, high performance  Fault-tolerance function  MySQL compatibility  Usually access is through MySQL protocol 9
  • 12. Looking at Clustrix SSD Infiniband  Low latency  High performance 11
  • 13. Clustrix Operation  Distributed arrangement on the physical layer  Redundancy protection, auto rebalance  Parallel query execution SQL SQL SQL SQL  Query, not data, is migrated (this concept differs from Oracle RAC) 12
  • 15. GUI 14
  • 17. Clustrix Implementation Cases Rakuten is the first case in Japan Numerous foreign cases 16
  • 19. OLTP Performance Results (1) Insert 45000 40000 35000 30000 25000 (ops/sec) 20000 15000 10000 5000 0 p3 p12 p24 p48 p96 p192 Single Throughput 4014.703409 8350.801098 10022.32827 10448.25479 10520.08066 10213.98278 Clx 3 nodesThroughput 6301.603599 18530.31626 26182.77331 30021.30841 27581.92104 24401.28904 Clx 4 nodes Throughput 6090.513193 20584.42 30544.8252 38545.21774 36837.10176 33221.72529 18
  • 20. OLTP (2) Update 25000 20000 15000 (ops/sec) 10000 5000 0 p3 p12 p24 p48 p96 p192 Single Throughput 3854.243586 8018.593249 12186.20793 13385.77834 13395.06587 11538.29668 Clx 3 nodes Throughput 3377.359372 10741.77417 16505.79652 16964.01107 16189.88416 15379.62683 Clx 4 nodes Throughput 3682.99886 12679.26966 19737.63815 22232.7357 21568.39318 21303.72872 19
  • 21. OLTP (3) Read 80000 70000 60000 50000 (ops/sec) 40000 30000 20000 10000 0 p3 p12 p24 p48 p96 p192 Single Throughput 6134.386466 26773.71202 44388.78477 56144.27281 57926.62433 49362.51106 Clx 3 nodes Throughput 5050.230295 17380.6806 27803.82494 39693.75633 49822.34026 56847.77879 Clx 4 nodes Throughput 5959.900064 20794.2083 34743.31655 54382.96419 70302.27313 76000.59175 20
  • 22. OLTP (4) Mix 40000 35000 30000 25000 (ops/sec) 20000 15000 10000 5000 0 p3 p12 p24 p48 p96 p192 Single Throughput 3976.841546 8587.218158 11632.64122 12946.2536 13122.33748 12769.45794 Clx 3 nodes Throughput 3113.109431 12940.99191 21264.63309 26759.75291 25976.26625 25334.18054 Clx 4 nodes Throughput 5150.537999 15220.8469 25601.67909 34647.41616 34697.737 30804.09949 21
  • 23. Complex and Heavy SQL Comparison Clustrix IA with SSD SPARC with SAN J) Count+GroupBy+OrderBy+Limit 1.9s (3.4s) 2.1s (8.5s) 3.4s (409.32s) K) Count+GroupBy+OrderBy+Limit 0.7s (1.13s) 5.9s (7.49s) 13.0s (39.41s) L) 2000 of IN+GroupBy 3.8s (8.97s) 106.5s (103.77s) 193.0s (321.68s) M) Case+OrderBy 31.0s (45.66s) 47.3s (60.9s) 22 90.5s (112.24s)
  • 24. Example of Performance Improvements  Example improvements regarding a particular service  Before: 116.8ms  After: 21.4ms 23
  • 25. Fault-Tolerance Inspection Failure Test Items Downtime 1 Front network (port1) No 2 Front network (port2) No 3 Internal network (primary) < 12s 4 Internal network (standby) No Front SW1 Front SW2 5 MySQL instance < 4s 6 Node OS < 4s 1 Online data disk 11 7 < 5s 2 (SSD) failure Log/work data disk 8 No DB DB DB DB (SATA) failure 5,6 7,8 9 4 12 Infiniband switch (primary) < 12s 3 10 Infiniband switch (standby) No 11 Front network (port1&2) < 18s 10 9 Internal network 12 < 12s Infiniband SW1 Infiniband SW2 (primary & standby) 24
  • 26. Time Required for Online Maintenance Table Rows and Size Small Medium Large Row 50,000 500,000 5,000,000 Size (byte) 113,639,424 1,063,190,528 10,696,130,560 Implementation Time Small Medium Large Create Column 1.6s 13.5 149.8 Create Index 1.6s 13.0s 172.7s Drop Column 1.5s 13.8s 125.5s Drop Index 0.5s 0.5s 0.5s 25
  • 27. Impacts During Online Scheme Modification  No impact on access performance in areas other than those subject to work operations  Some impact on performance of access to table being subject to work operations (taking periods with little impacts, such as night service, into consideration)  Online execution – 5 million cases, total tables 10G 26
  • 28. Clustrix Implementation Impacts Release from Sharding (1) Before …… DB DB DB DB …… No more sharding! After DB DB DB DB …… +
  • 29. Clustrix Implementation Impacts Release from Sharding (2)  No need for correction of application  No need for DB distribution  Sharding production costs reduction (over 90%) for both application engineer and DBA  In case of large-scale as-i s sharding project, actual production costs DBA compared to to-be APP original 0 2 4 6 8 10 12 14 m an-m onth 28
  • 30. Clustrix Implementation Impacts Cost Reductions due to Consolidation (1)  Sufficient performance scalability  Fault-tolerance ready for mission critical  No data loss  High online maintainability that doesn’t affect other services  Possibility of consolidation to Clustrix of existing MySQL database 29
  • 31. Clustrix Implementation Impacts Cost Reductions due to Consolidation (2)  Consolidation of all existing MySQL within Clustrix  Number of servers will be reduced to 10%  Monthly system costs will be reduced to 40% 30
  • 32. Back-up Structure Clustrix DB DB DB … Node 1 Node 2 Node 3 Replication Slave as first backup Backup by mysqldump MySQL DB NFS NAS 31
  • 33. Data Migration Procedure  Replication to DEV for verification  Replication to PRO for migration  Conversion of application access point to PRO MySQL DB Replication Replication Clustrix DEV Clustrix PRO DB DB DB DB DB DB 32
  • 34. Other Advantages of Clustrix  Auto-Defrag  Cordial Support Service  Advice regarding structure  Troubleshooting  Tuning advice  Etc. 33
  • 35. Operational Issues Resolved with Clustrix  Data sharding operations  Unnecessary, operational cost reduction  Data protection, HA securing  Possible  Online maintenance  Possible  Tendency for large number of units  Consolidation possible  Cost reduction 34
  • 36. Clustrix at Rakuten  An important database platform  Provided as Database-as-a-Service  No lead-time  Usage volume rate structure 35