SlideShare una empresa de Scribd logo
1 de 33
Descargar para leer sin conexión
Capacidade Planejada
Rodrigo Albani de Campos - camposr@gmail.com - @xinu



Wednesday, August 25, 2010
Agenda

                   • Motivações
                   • Capacidade + Velocidade
                   • Universal Scalability Model
                   • Extra: Dimensionamento de pools

Wednesday, August 25, 2010
Impacto na imagem do produto


Wednesday, August 25, 2010
Impacto na imagem do produto


Wednesday, August 25, 2010
SLA          Horas / Trimestre   Impacto $
                               98%                 43,2   $142.600.000
                               99%                 21,6    $71.300.000
                             99,90%                2,16     $7.130.000
                             99,99%               0,216      $713.000
                         99,9990%               0,0216        $71.300
                         99,9999%              0,00216         $7.130



Amazon 2010Q1 Net Sales
$7.13 Billion Dollars

Wednesday, August 25, 2010
Distinct     Query     Revenue/       Any Clicks   Satisfaction Time to Click
                         Queries/User Refinement     User                                    (increase in
                                                                                                ms)

 50ms                             0           0              0            0             0             0
 200ms                            0           0              0 -0,30% -0,40%                      500
 500ms                            0 -0,60% -1,20% -1,00% -0,90%                                 1200
 1000ms -0,70% -0,90% -2,80% -1,90% -1,60%                                                      1900
 2000ms -1,80% -2,10% -4,30% -4,40% -3,80%                                                      3100

                                $85.000.000 em três meses na
                                          Amazon

Receita
Impacto de lentidão na entrega de conteúdo
The User and Business Impact of Server Delays, Additional Bytes, and HTTP
Chunking in Web Search - Eric Schurman (Amazon), Jake Brutlag (Google)
Wednesday, August 25, 2010
Receita
Impacto de lentidão na entrega de conteúdo
The User and Business Impact of Server Delays, Additional Bytes, and HTTP
Chunking in Web Search - Eric Schurman (Amazon), Jake Brutlag (Google)
Wednesday, August 25, 2010
“Fast isn’t a feature, fast is
               a Requirement”
                                Jesse Robins - OPSCode




Wednesday, August 25, 2010
Average # of                   Average
                                            Average # of
                              resources /                document size
                                            hosts / page
                                 page                         Kb



                              42,14           8,39       477,26


Composição de páginas na Web - Top Sites
Web Metrics: Size and number of resources - Sreeram
Ramachandran
http://code.google.com/speed/articles/web-metrics.html
Wednesday, August 25, 2010
Load Time   First Byte    Start    Complete    Requests   Bytes In
                                                      Render     Time (s)
   Mercado Livre              1,972      329 ms       543 ms     2,491        22        74 KB
   Ebay                       1,999      399 ms       1493 ms    3,103        36       237 KB
   Amazon                     4,777      504 ms       1105 ms    6,289        69       454 KB
   newegg                     6,848      328 ms       1211 ms    7,891        138      459 KB
   Bestbuy                    7,508      447 ms       1733 ms    10,41        99       676 KB
   Submarino                  10,436     250 ms       2474 ms   10,436        151      1,125 KB
   Casas Bahia                15,09      500 ms       4401 ms   15,799        100      732 KB




http://www.webpagetest.org/ TEST RESULTS
July 2010

Wednesday, August 25, 2010
Capacity and Velocity

Wednesday, August 25, 2010
Service time: Tempo de ocupação do recurso
       (s,ms,μs)
       Arrival rate: Taxa de chegada de requisições
       para o recurso (hit/s,qps,etc...)
       Little’s Law: The long term average number of customers in a
       stable system L is equal to the long term average arrival rate λ,
       multiplied by the long term average time a customer spends in the
       system,W




Queuing Theory 101

Wednesday, August 25, 2010
Service  A
                                    0,1                                                                  1600


                                   0,09
                                                                                                         1400

                                   0,08
                                                                                                         1200
                                   0,07

                                                                                                         1000
                                   0,06
              Service  Time  (s)




                                                                                                                Frequency
                                   0,05                                                                  800


                                   0,04
                                                                                                         600

                                   0,03
                                                                                                         400
                                   0,02

                                                                                                         200
                                   0,01


                                     0                                                                   0
                                          0   50   100             150                 200   250   300
                                                                  Hits/s

                                                         Service  Time     Frequency




Average Service Time against Arrival Rates

Wednesday, August 25, 2010
Service  B
                                 2,5                                                                                6000




                                                                                                                    5000
                                  2



                                                                                                                    4000

                                 1,5
            Service  Time  (s)




                                                                                                                           Frequency
                                                                                                                    3000


                                  1

                                                                                                                    2000



                                 0,5
                                                                                                                    1000




                                  0                                                                                 0
                                       0   20   40   60   80             100       120      140   160   180   200
                                                                       Hits/s

                                                               Service  Time    Frequency




Average Service Time against Arrival Rates

Wednesday, August 25, 2010
Service  B
                                                  2,5                                                                                6000




                                                                                                                                     5000
                                                   2



                                                                                                                                     4000


    Frustrated                                    1,5




                             Service  Time  (s)




                                                                                                                                            Frequency
                                                                                                                                     3000


                                                   1

                                                                                                                                     2000




    Tolerating
                                                  0,5
                                                                                                                                     1000




                                                   0                                                                                 0
                                                        0   20   40   60   80             100       120      140   160   180   200
                                                                                        Hits/s


      Satisfied                                                                  Service  Time    Frequency




APDEX - http://www.apdex.org

Wednesday, August 25, 2010
Satisfied          Tolerating   Frustrated

APDEX - http://www.apdex.org

Wednesday, August 25, 2010
Samples       12000
                             Satisfied      10000
                             Tolerating      800


                             Apdex        86,67%




APDEX - http://www.apdex.org

Wednesday, August 25, 2010
Forecasting (Sort of...)

Wednesday, August 25, 2010
System  C
                           40



                           35



                           30                                              Measured Throughput
                                                                           Users (N)   X(N)
                                                                                     1         2,91
                           25
              Throughput




                           20                                                        2         5,67
                                                                                     4        10,86
                           15
                                                                                     8        18,65
                           10
                                                                                    16        25,91
                                                                                    32        36,68
                            5
                                                                                    64        37,34
                            0
                                0   10   20   30                      40       50        60           70
                                                     Virtual  Users

                                                   Measured  X




Forecasting (Sort of...)

Wednesday, August 25, 2010
System  C
                             45



                             40



                             35



                             30



                             25
                Throughput




                             20



                             15



                             10



                             5



                             0
                                  0   10   20   30             40                    50            60   70   80   90
                                                                    Virtual  Users

                                                     Measured  X            Poly.  (Measured  X)




Forecasting (Sort of...)

Wednesday, August 25, 2010
System  C
                             45



                             40



                             35



                             30



                             25
                Throughput




                             20



                             15



                             10



                             5



                             0
                                  0   10   20   30             40                    50            60   70   80   90
                                                                    Virtual  Users

                                                     Measured  X            Poly.  (Measured  X)




Forecasting (Sort of...)

Wednesday, August 25, 2010
System  C
                           40



                           35



                           30



                           25
              Throughput




                           20



                           15



                           10



                           5



                           0
                                0   20   40       60                     80      100   120   140
                                                        Virtual  Users

                                              Measured  X        Modeled  X(N)




Using the Universal Scalability Model
Neil J. Gunther http://www.perfdynamics.com/Test/gcaprules.html#sec:scalability



Wednesday, August 25, 2010
System  D
                          60




                          50




                          40
             Throughput




                          30




                          20




                          10




                           0
                               0   100   200                  300                   400   500   600
                                                         Virtual  Users

                                               Measured  X          Modeled  X(N)




Using the Universal Scalability Model
Neil J. Gunther http://www.perfdynamics.com/Test/gcaprules.html#sec:scalability



Wednesday, August 25, 2010
Conclusões e
                             Considerações
                   • Velocidade é tão importante quanto
                     disponibilidade
                     • Fast is a requirement
                   • O SLA deve serdo usuário
                     experiência
                                     definido considerando a

                   • Não existem bolas de cristal

Wednesday, August 25, 2010
In God we trust.
                              Everyone else
                             please show me
                                 the data.

Wednesday, August 25, 2010
http://capacitricks.wordpress.com/




Wednesday, August 25, 2010
How many servers do we need ?

Wednesday, August 25, 2010
Redundância

               55%                         55%



               55%                         55%




Wednesday, August 25, 2010
Redundância

            73,3%
                                      X
            73,3%                          73,3%




Wednesday, August 25, 2010
Redundância

             110%
                                      X
             110%
                                      X
Wednesday, August 25, 2010
How many servers do we need ?

Wednesday, August 25, 2010
How many servers do we need ?

Wednesday, August 25, 2010
Perguntas ?



Wednesday, August 25, 2010

Más contenido relacionado

Similar a Capacidade Planejada: Dimensionamento de Recursos para Escala Universal

Spreaker - Live Podcasting on AWS - AWS Case Study
Spreaker - Live Podcasting on AWS - AWS Case StudySpreaker - Live Podcasting on AWS - AWS Case Study
Spreaker - Live Podcasting on AWS - AWS Case StudyAmazon Web Services
 
NLCMG - Performance is good, Understanding performance is better
NLCMG - Performance is good, Understanding performance is better NLCMG - Performance is good, Understanding performance is better
NLCMG - Performance is good, Understanding performance is better nlwebperf
 
MBL303 Scalable Mobile and Web Apps - AWS re: Invent 2012
MBL303 Scalable Mobile and Web Apps - AWS re: Invent 2012MBL303 Scalable Mobile and Web Apps - AWS re: Invent 2012
MBL303 Scalable Mobile and Web Apps - AWS re: Invent 2012Amazon Web Services
 
White Paper: xDesign Online Editor & API Performance Benchmark Summary
White Paper: xDesign Online Editor & API Performance Benchmark Summary   White Paper: xDesign Online Editor & API Performance Benchmark Summary
White Paper: xDesign Online Editor & API Performance Benchmark Summary EMC
 
SPICE MODEL of SSM3K102TU (Standard+BDS Model) in SPICE PARK
SPICE MODEL of SSM3K102TU (Standard+BDS Model) in SPICE PARKSPICE MODEL of SSM3K102TU (Standard+BDS Model) in SPICE PARK
SPICE MODEL of SSM3K102TU (Standard+BDS Model) in SPICE PARKTsuyoshi Horigome
 
Top Application Performance Landmines
Top Application Performance LandminesTop Application Performance Landmines
Top Application Performance LandminesAndreas Grabner
 
CMG 101 - Understanding performance
CMG 101 - Understanding performanceCMG 101 - Understanding performance
CMG 101 - Understanding performancePeter HJ van Eijk
 
Running a Lean Startup with AWS - Spreaker Case Study
Running a Lean Startup with AWS - Spreaker Case StudyRunning a Lean Startup with AWS - Spreaker Case Study
Running a Lean Startup with AWS - Spreaker Case StudyMarco Pracucci
 
Cassandra Performance: Past, present & future
Cassandra Performance: Past, present & futureCassandra Performance: Past, present & future
Cassandra Performance: Past, present & futureAcunu
 
Magento Imagine eCommerce, Day 2, Yoav Kutner CTO
Magento Imagine eCommerce, Day 2, Yoav Kutner CTOMagento Imagine eCommerce, Day 2, Yoav Kutner CTO
Magento Imagine eCommerce, Day 2, Yoav Kutner CTOvarien
 
Dental Network Trends - Updated July 2012
Dental Network Trends - Updated July 2012Dental Network Trends - Updated July 2012
Dental Network Trends - Updated July 2012agroffman
 
Apstartup crowdfunding ver1
Apstartup crowdfunding ver1 Apstartup crowdfunding ver1
Apstartup crowdfunding ver1 AP DealFlow
 
SPICE MODEL of SSM3J108TU (Professional+BDP Model) in SPICE PARK
SPICE MODEL of SSM3J108TU (Professional+BDP Model) in SPICE PARKSPICE MODEL of SSM3J108TU (Professional+BDP Model) in SPICE PARK
SPICE MODEL of SSM3J108TU (Professional+BDP Model) in SPICE PARKTsuyoshi Horigome
 
SPICE MODEL of 2SK4002 (Standard+BDS Model) in SPICE PARK
SPICE MODEL of 2SK4002 (Standard+BDS Model) in SPICE PARKSPICE MODEL of 2SK4002 (Standard+BDS Model) in SPICE PARK
SPICE MODEL of 2SK4002 (Standard+BDS Model) in SPICE PARKTsuyoshi Horigome
 
SPICE MODEL of SSM3J108TU (Standard+BDS Model) in SPICE PARK
SPICE MODEL of SSM3J108TU (Standard+BDS Model) in SPICE PARKSPICE MODEL of SSM3J108TU (Standard+BDS Model) in SPICE PARK
SPICE MODEL of SSM3J108TU (Standard+BDS Model) in SPICE PARKTsuyoshi Horigome
 

Similar a Capacidade Planejada: Dimensionamento de Recursos para Escala Universal (20)

SDS Amazon RDS
SDS Amazon RDSSDS Amazon RDS
SDS Amazon RDS
 
Spreaker - Live Podcasting on AWS - AWS Case Study
Spreaker - Live Podcasting on AWS - AWS Case StudySpreaker - Live Podcasting on AWS - AWS Case Study
Spreaker - Live Podcasting on AWS - AWS Case Study
 
NLCMG - Performance is good, Understanding performance is better
NLCMG - Performance is good, Understanding performance is better NLCMG - Performance is good, Understanding performance is better
NLCMG - Performance is good, Understanding performance is better
 
White label pricing
White label pricingWhite label pricing
White label pricing
 
MBL303 Scalable Mobile and Web Apps - AWS re: Invent 2012
MBL303 Scalable Mobile and Web Apps - AWS re: Invent 2012MBL303 Scalable Mobile and Web Apps - AWS re: Invent 2012
MBL303 Scalable Mobile and Web Apps - AWS re: Invent 2012
 
Lte asia 2011 s niri
Lte asia 2011 s niriLte asia 2011 s niri
Lte asia 2011 s niri
 
White Paper: xDesign Online Editor & API Performance Benchmark Summary
White Paper: xDesign Online Editor & API Performance Benchmark Summary   White Paper: xDesign Online Editor & API Performance Benchmark Summary
White Paper: xDesign Online Editor & API Performance Benchmark Summary
 
SPICE MODEL of SSM3K102TU (Standard+BDS Model) in SPICE PARK
SPICE MODEL of SSM3K102TU (Standard+BDS Model) in SPICE PARKSPICE MODEL of SSM3K102TU (Standard+BDS Model) in SPICE PARK
SPICE MODEL of SSM3K102TU (Standard+BDS Model) in SPICE PARK
 
Top Application Performance Landmines
Top Application Performance LandminesTop Application Performance Landmines
Top Application Performance Landmines
 
CMG 101 - Understanding performance
CMG 101 - Understanding performanceCMG 101 - Understanding performance
CMG 101 - Understanding performance
 
Running a Lean Startup with AWS - Spreaker Case Study
Running a Lean Startup with AWS - Spreaker Case StudyRunning a Lean Startup with AWS - Spreaker Case Study
Running a Lean Startup with AWS - Spreaker Case Study
 
Vevo 2100 Brochure
Vevo 2100 BrochureVevo 2100 Brochure
Vevo 2100 Brochure
 
Database Health Check
Database Health CheckDatabase Health Check
Database Health Check
 
Cassandra Performance: Past, present & future
Cassandra Performance: Past, present & futureCassandra Performance: Past, present & future
Cassandra Performance: Past, present & future
 
Magento Imagine eCommerce, Day 2, Yoav Kutner CTO
Magento Imagine eCommerce, Day 2, Yoav Kutner CTOMagento Imagine eCommerce, Day 2, Yoav Kutner CTO
Magento Imagine eCommerce, Day 2, Yoav Kutner CTO
 
Dental Network Trends - Updated July 2012
Dental Network Trends - Updated July 2012Dental Network Trends - Updated July 2012
Dental Network Trends - Updated July 2012
 
Apstartup crowdfunding ver1
Apstartup crowdfunding ver1 Apstartup crowdfunding ver1
Apstartup crowdfunding ver1
 
SPICE MODEL of SSM3J108TU (Professional+BDP Model) in SPICE PARK
SPICE MODEL of SSM3J108TU (Professional+BDP Model) in SPICE PARKSPICE MODEL of SSM3J108TU (Professional+BDP Model) in SPICE PARK
SPICE MODEL of SSM3J108TU (Professional+BDP Model) in SPICE PARK
 
SPICE MODEL of 2SK4002 (Standard+BDS Model) in SPICE PARK
SPICE MODEL of 2SK4002 (Standard+BDS Model) in SPICE PARKSPICE MODEL of 2SK4002 (Standard+BDS Model) in SPICE PARK
SPICE MODEL of 2SK4002 (Standard+BDS Model) in SPICE PARK
 
SPICE MODEL of SSM3J108TU (Standard+BDS Model) in SPICE PARK
SPICE MODEL of SSM3J108TU (Standard+BDS Model) in SPICE PARKSPICE MODEL of SSM3J108TU (Standard+BDS Model) in SPICE PARK
SPICE MODEL of SSM3J108TU (Standard+BDS Model) in SPICE PARK
 

Más de Rodrigo Campos

Velocity Conference NYC 2014 - Real World DevOps
Velocity Conference NYC 2014 - Real World DevOpsVelocity Conference NYC 2014 - Real World DevOps
Velocity Conference NYC 2014 - Real World DevOpsRodrigo Campos
 
DevOps no mundo real - QCON 2014
DevOps no mundo real - QCON 2014DevOps no mundo real - QCON 2014
DevOps no mundo real - QCON 2014Rodrigo Campos
 
7Masters Webops in the Cloud
7Masters Webops in the Cloud7Masters Webops in the Cloud
7Masters Webops in the CloudRodrigo Campos
 
Otimização holistica de ambiente computacional
Otimização holistica de ambiente computacionalOtimização holistica de ambiente computacional
Otimização holistica de ambiente computacionalRodrigo Campos
 
Desempenho e Escalabilidade de Banco de Dados em ambiente x86
Desempenho e Escalabilidade de Banco de Dados em ambiente x86Desempenho e Escalabilidade de Banco de Dados em ambiente x86
Desempenho e Escalabilidade de Banco de Dados em ambiente x86Rodrigo Campos
 
Mistério ou tecnologia? Paralelismo!
Mistério ou tecnologia? Paralelismo!Mistério ou tecnologia? Paralelismo!
Mistério ou tecnologia? Paralelismo!Rodrigo Campos
 
z/VM Performance Analysis
z/VM Performance Analysisz/VM Performance Analysis
z/VM Performance AnalysisRodrigo Campos
 
Sistemas de proteção de perímetro
Sistemas de proteção de perímetroSistemas de proteção de perímetro
Sistemas de proteção de perímetroRodrigo Campos
 
Devops at Walmart GeC Brazil
Devops at Walmart GeC BrazilDevops at Walmart GeC Brazil
Devops at Walmart GeC BrazilRodrigo Campos
 
Disk IO Benchmarking in shared multi-tenant environments
Disk IO Benchmarking in shared multi-tenant environmentsDisk IO Benchmarking in shared multi-tenant environments
Disk IO Benchmarking in shared multi-tenant environmentsRodrigo Campos
 
Cloud Computing Oportunidades e Desafios
Cloud Computing Oportunidades e DesafiosCloud Computing Oportunidades e Desafios
Cloud Computing Oportunidades e DesafiosRodrigo Campos
 
The good, the bad and the big... data
The good, the bad and the big... dataThe good, the bad and the big... data
The good, the bad and the big... dataRodrigo Campos
 
CMG 2012 - Tuning where it matters - Gerry Tuddenham
CMG 2012 - Tuning where it matters - Gerry TuddenhamCMG 2012 - Tuning where it matters - Gerry Tuddenham
CMG 2012 - Tuning where it matters - Gerry TuddenhamRodrigo Campos
 
A Consumerização da TI e o Efeito BYOT
A Consumerização da TI e o Efeito BYOTA Consumerização da TI e o Efeito BYOT
A Consumerização da TI e o Efeito BYOTRodrigo Campos
 
CMG Brasil 2012 - Uso de Lines nos z196
CMG Brasil 2012 - Uso de Lines nos z196CMG Brasil 2012 - Uso de Lines nos z196
CMG Brasil 2012 - Uso de Lines nos z196Rodrigo Campos
 
Racionalização e Otimização de Energia em Computação na Nuvem
Racionalização e Otimização de Energia em Computação na NuvemRacionalização e Otimização de Energia em Computação na Nuvem
Racionalização e Otimização de Energia em Computação na NuvemRodrigo Campos
 
SDN - Openflow + OpenVSwitch + Quantum
SDN - Openflow + OpenVSwitch + QuantumSDN - Openflow + OpenVSwitch + Quantum
SDN - Openflow + OpenVSwitch + QuantumRodrigo Campos
 

Más de Rodrigo Campos (20)

Velocity Conference NYC 2014 - Real World DevOps
Velocity Conference NYC 2014 - Real World DevOpsVelocity Conference NYC 2014 - Real World DevOps
Velocity Conference NYC 2014 - Real World DevOps
 
DevOps no mundo real - QCON 2014
DevOps no mundo real - QCON 2014DevOps no mundo real - QCON 2014
DevOps no mundo real - QCON 2014
 
7Masters Webops in the Cloud
7Masters Webops in the Cloud7Masters Webops in the Cloud
7Masters Webops in the Cloud
 
14 guendert pres
14 guendert pres14 guendert pres
14 guendert pres
 
Large and Giant Pages
Large and Giant PagesLarge and Giant Pages
Large and Giant Pages
 
Otimização holistica de ambiente computacional
Otimização holistica de ambiente computacionalOtimização holistica de ambiente computacional
Otimização holistica de ambiente computacional
 
Desempenho e Escalabilidade de Banco de Dados em ambiente x86
Desempenho e Escalabilidade de Banco de Dados em ambiente x86Desempenho e Escalabilidade de Banco de Dados em ambiente x86
Desempenho e Escalabilidade de Banco de Dados em ambiente x86
 
13 coelho final-pres
13 coelho final-pres13 coelho final-pres
13 coelho final-pres
 
Mistério ou tecnologia? Paralelismo!
Mistério ou tecnologia? Paralelismo!Mistério ou tecnologia? Paralelismo!
Mistério ou tecnologia? Paralelismo!
 
z/VM Performance Analysis
z/VM Performance Analysisz/VM Performance Analysis
z/VM Performance Analysis
 
Sistemas de proteção de perímetro
Sistemas de proteção de perímetroSistemas de proteção de perímetro
Sistemas de proteção de perímetro
 
Devops at Walmart GeC Brazil
Devops at Walmart GeC BrazilDevops at Walmart GeC Brazil
Devops at Walmart GeC Brazil
 
Disk IO Benchmarking in shared multi-tenant environments
Disk IO Benchmarking in shared multi-tenant environmentsDisk IO Benchmarking in shared multi-tenant environments
Disk IO Benchmarking in shared multi-tenant environments
 
Cloud Computing Oportunidades e Desafios
Cloud Computing Oportunidades e DesafiosCloud Computing Oportunidades e Desafios
Cloud Computing Oportunidades e Desafios
 
The good, the bad and the big... data
The good, the bad and the big... dataThe good, the bad and the big... data
The good, the bad and the big... data
 
CMG 2012 - Tuning where it matters - Gerry Tuddenham
CMG 2012 - Tuning where it matters - Gerry TuddenhamCMG 2012 - Tuning where it matters - Gerry Tuddenham
CMG 2012 - Tuning where it matters - Gerry Tuddenham
 
A Consumerização da TI e o Efeito BYOT
A Consumerização da TI e o Efeito BYOTA Consumerização da TI e o Efeito BYOT
A Consumerização da TI e o Efeito BYOT
 
CMG Brasil 2012 - Uso de Lines nos z196
CMG Brasil 2012 - Uso de Lines nos z196CMG Brasil 2012 - Uso de Lines nos z196
CMG Brasil 2012 - Uso de Lines nos z196
 
Racionalização e Otimização de Energia em Computação na Nuvem
Racionalização e Otimização de Energia em Computação na NuvemRacionalização e Otimização de Energia em Computação na Nuvem
Racionalização e Otimização de Energia em Computação na Nuvem
 
SDN - Openflow + OpenVSwitch + Quantum
SDN - Openflow + OpenVSwitch + QuantumSDN - Openflow + OpenVSwitch + Quantum
SDN - Openflow + OpenVSwitch + Quantum
 

Último

Training state-of-the-art general text embedding
Training state-of-the-art general text embeddingTraining state-of-the-art general text embedding
Training state-of-the-art general text embeddingZilliz
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr BaganFwdays
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebUiPathCommunity
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfSeasiaInfotech2
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsMiki Katsuragi
 
Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Manik S Magar
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Mark Simos
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationSafe Software
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 3652toLead Limited
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 
Vector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector DatabasesVector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector DatabasesZilliz
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLScyllaDB
 
Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time ClashPowerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clashcharlottematthew16
 

Último (20)

Training state-of-the-art general text embedding
Training state-of-the-art general text embeddingTraining state-of-the-art general text embedding
Training state-of-the-art general text embedding
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdf
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering Tips
 
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 
Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
Vector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector DatabasesVector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector Databases
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
 
Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time ClashPowerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clash
 

Capacidade Planejada: Dimensionamento de Recursos para Escala Universal

  • 1. Capacidade Planejada Rodrigo Albani de Campos - camposr@gmail.com - @xinu Wednesday, August 25, 2010
  • 2. Agenda • Motivações • Capacidade + Velocidade • Universal Scalability Model • Extra: Dimensionamento de pools Wednesday, August 25, 2010
  • 3. Impacto na imagem do produto Wednesday, August 25, 2010
  • 4. Impacto na imagem do produto Wednesday, August 25, 2010
  • 5. SLA Horas / Trimestre Impacto $ 98% 43,2 $142.600.000 99% 21,6 $71.300.000 99,90% 2,16 $7.130.000 99,99% 0,216 $713.000 99,9990% 0,0216 $71.300 99,9999% 0,00216 $7.130 Amazon 2010Q1 Net Sales $7.13 Billion Dollars Wednesday, August 25, 2010
  • 6. Distinct Query Revenue/ Any Clicks Satisfaction Time to Click Queries/User Refinement User (increase in ms) 50ms 0 0 0 0 0 0 200ms 0 0 0 -0,30% -0,40% 500 500ms 0 -0,60% -1,20% -1,00% -0,90% 1200 1000ms -0,70% -0,90% -2,80% -1,90% -1,60% 1900 2000ms -1,80% -2,10% -4,30% -4,40% -3,80% 3100 $85.000.000 em três meses na Amazon Receita Impacto de lentidão na entrega de conteúdo The User and Business Impact of Server Delays, Additional Bytes, and HTTP Chunking in Web Search - Eric Schurman (Amazon), Jake Brutlag (Google) Wednesday, August 25, 2010
  • 7. Receita Impacto de lentidão na entrega de conteúdo The User and Business Impact of Server Delays, Additional Bytes, and HTTP Chunking in Web Search - Eric Schurman (Amazon), Jake Brutlag (Google) Wednesday, August 25, 2010
  • 8. “Fast isn’t a feature, fast is a Requirement” Jesse Robins - OPSCode Wednesday, August 25, 2010
  • 9. Average # of Average Average # of resources / document size hosts / page page Kb 42,14 8,39 477,26 Composição de páginas na Web - Top Sites Web Metrics: Size and number of resources - Sreeram Ramachandran http://code.google.com/speed/articles/web-metrics.html Wednesday, August 25, 2010
  • 10. Load Time First Byte Start Complete Requests Bytes In Render Time (s) Mercado Livre 1,972 329 ms 543 ms 2,491 22 74 KB Ebay 1,999 399 ms 1493 ms 3,103 36 237 KB Amazon 4,777 504 ms 1105 ms 6,289 69 454 KB newegg 6,848 328 ms 1211 ms 7,891 138 459 KB Bestbuy 7,508 447 ms 1733 ms 10,41 99 676 KB Submarino 10,436 250 ms 2474 ms 10,436 151 1,125 KB Casas Bahia 15,09 500 ms 4401 ms 15,799 100 732 KB http://www.webpagetest.org/ TEST RESULTS July 2010 Wednesday, August 25, 2010
  • 12. Service time: Tempo de ocupação do recurso (s,ms,μs) Arrival rate: Taxa de chegada de requisições para o recurso (hit/s,qps,etc...) Little’s Law: The long term average number of customers in a stable system L is equal to the long term average arrival rate λ, multiplied by the long term average time a customer spends in the system,W Queuing Theory 101 Wednesday, August 25, 2010
  • 13. Service  A 0,1 1600 0,09 1400 0,08 1200 0,07 1000 0,06 Service  Time  (s) Frequency 0,05 800 0,04 600 0,03 400 0,02 200 0,01 0 0 0 50 100 150 200 250 300 Hits/s Service  Time Frequency Average Service Time against Arrival Rates Wednesday, August 25, 2010
  • 14. Service  B 2,5 6000 5000 2 4000 1,5 Service  Time  (s) Frequency 3000 1 2000 0,5 1000 0 0 0 20 40 60 80 100 120 140 160 180 200 Hits/s Service  Time Frequency Average Service Time against Arrival Rates Wednesday, August 25, 2010
  • 15. Service  B 2,5 6000 5000 2 4000 Frustrated 1,5 Service  Time  (s) Frequency 3000 1 2000 Tolerating 0,5 1000 0 0 0 20 40 60 80 100 120 140 160 180 200 Hits/s Satisfied Service  Time Frequency APDEX - http://www.apdex.org Wednesday, August 25, 2010
  • 16. Satisfied Tolerating Frustrated APDEX - http://www.apdex.org Wednesday, August 25, 2010
  • 17. Samples 12000 Satisfied 10000 Tolerating 800 Apdex 86,67% APDEX - http://www.apdex.org Wednesday, August 25, 2010
  • 19. System  C 40 35 30 Measured Throughput Users (N) X(N) 1 2,91 25 Throughput 20 2 5,67 4 10,86 15 8 18,65 10 16 25,91 32 36,68 5 64 37,34 0 0 10 20 30 40 50 60 70 Virtual  Users Measured  X Forecasting (Sort of...) Wednesday, August 25, 2010
  • 20. System  C 45 40 35 30 25 Throughput 20 15 10 5 0 0 10 20 30 40 50 60 70 80 90 Virtual  Users Measured  X Poly.  (Measured  X) Forecasting (Sort of...) Wednesday, August 25, 2010
  • 21. System  C 45 40 35 30 25 Throughput 20 15 10 5 0 0 10 20 30 40 50 60 70 80 90 Virtual  Users Measured  X Poly.  (Measured  X) Forecasting (Sort of...) Wednesday, August 25, 2010
  • 22. System  C 40 35 30 25 Throughput 20 15 10 5 0 0 20 40 60 80 100 120 140 Virtual  Users Measured  X Modeled  X(N) Using the Universal Scalability Model Neil J. Gunther http://www.perfdynamics.com/Test/gcaprules.html#sec:scalability Wednesday, August 25, 2010
  • 23. System  D 60 50 40 Throughput 30 20 10 0 0 100 200 300 400 500 600 Virtual  Users Measured  X Modeled  X(N) Using the Universal Scalability Model Neil J. Gunther http://www.perfdynamics.com/Test/gcaprules.html#sec:scalability Wednesday, August 25, 2010
  • 24. Conclusões e Considerações • Velocidade é tão importante quanto disponibilidade • Fast is a requirement • O SLA deve serdo usuário experiência definido considerando a • Não existem bolas de cristal Wednesday, August 25, 2010
  • 25. In God we trust. Everyone else please show me the data. Wednesday, August 25, 2010
  • 27. How many servers do we need ? Wednesday, August 25, 2010
  • 28. Redundância 55% 55% 55% 55% Wednesday, August 25, 2010
  • 29. Redundância 73,3% X 73,3% 73,3% Wednesday, August 25, 2010
  • 30. Redundância 110% X 110% X Wednesday, August 25, 2010
  • 31. How many servers do we need ? Wednesday, August 25, 2010
  • 32. How many servers do we need ? Wednesday, August 25, 2010