SlideShare una empresa de Scribd logo
1 de 23
HTTP accelerator
          Cachos 2.0
    Luis Henrique Okama
         Tollef Fog Heen
          Mario Carvalho
What is the problem?
  GET / HTTP/1.1
    Hang on, I need to look up a few hundred things in my
    database and then do a lot of editing controlled by a
    scripting language
  HEAD / HTTP/1.1
    Hang on, I need to look up a few hundred things in my
    database and then do a lot of editing controlled by a
    scripting language, and then I will throw the result
    away.
Why are CMS-es slow?

   Complex content generation process
   Single database prevents clustering
   Expensive software ditto

This means: we need server side caching
Why are the existing solutions not good enough?

  Squid, ancient design, forward proxy
  Apache, not what it's built for, not what it's good at
  Akamai (and similar), expensive, vendor lock-in
What is Varnish?

 Dedicated HTTP accelerator
 Focus on server-side speedups
 Policy control
 High performance
 Varnish Configuration Language
 Shared memory log
High performance

 11 syscalls + 7 locks for a cache hit
 Work with the OS, not against it.
 Multi-CPU, multi-core
 64 bit
 Use advanced OS features:
    Accept filters
    madvise(MADV_RANDOM)
    kqueue, epoll
 Don't copy data if you don't have to
 Use workspaces, not malloc/free
 Compiled configuration
Policy control

  Override TTLs
  Add, remove or change headers
  Strip cookies
  Rewrite URLs
  Invalidate objects in the cache
Varnish Configuration Language

 Simple domain specific language
 Compiled via C language to binary
     Transparently!
 Dynamically loaded
 Multiple configs loaded concurrently
 Instant switch from one VCL to another.
     Can be done from VCL
VCL Example

  acl some_acl { "10.0.0.0/8" }
  if (client.ip ~ some_acl) {
      pass;
  }

  if (req.http.host ~ "foo.com$") {
      set req.http.host =
          regsub(req.http.host,
              "foo.com", "bar.org");
  }

  if (obj.valid) {
      set obj.ttl = 10m;
      deliver;
  }
Shared memory logfile

 Fast
 Custom log tailers
    varnishtop
    varnishlog
    varnishhist
    varnishncsa
    varnishstat
Globo.com cache infrastructure
Comparative
  scalability
  setup time
  cost
  open source
  throughput
  physical space
Comparative
  scalability
  setup time
  cost
  open source
  throughput
  physical space
Comparative
  scalability
  setup time
  cost
  open source
  throughput
  physical space
Comparative
  scalability
  setup time
  cost
  open source
  throughput
  physical space
Comparative
  scalability
  setup time
  cost
  open source
  throughput
  physical space
Comparative
  scalability
  setup time
  cost
  open source
  throughput
  physical space
Comparative
  scalability
  setup time
  cost
  open source
  throughput
  physical space
Some data
Conclusion
  software customization
  work set
Real life performance
Questions
Contacts

  Luis H. Okama
  okama@corp.globo.com (www.globo.com)
  Mario Carvalho
  mariocar@corp.globo.com (www.globo.com)
  Tollef Fog Heen
  tfheen@redpill-linpro.com (www.varnish-cache.com)

  @ Stand Globo.com

Más contenido relacionado

La actualidad más candente

Tarantool: как сэкономить миллион долларов на базе данных на высоконагруженно...
Tarantool: как сэкономить миллион долларов на базе данных на высоконагруженно...Tarantool: как сэкономить миллион долларов на базе данных на высоконагруженно...
Tarantool: как сэкономить миллион долларов на базе данных на высоконагруженно...
Ontico
 

La actualidad más candente (20)

Doing QoS Before Ceph Cluster QoS is available - David Byte, Alex Lau
Doing QoS Before Ceph Cluster QoS is available - David Byte, Alex LauDoing QoS Before Ceph Cluster QoS is available - David Byte, Alex Lau
Doing QoS Before Ceph Cluster QoS is available - David Byte, Alex Lau
 
The Browser Does Not Protect You
The Browser Does Not Protect YouThe Browser Does Not Protect You
The Browser Does Not Protect You
 
Experiences building a distributed shared log on RADOS - Noah Watkins
Experiences building a distributed shared log on RADOS - Noah WatkinsExperiences building a distributed shared log on RADOS - Noah Watkins
Experiences building a distributed shared log on RADOS - Noah Watkins
 
Troubleshooting redis
Troubleshooting redisTroubleshooting redis
Troubleshooting redis
 
3 Ways to Improve Performance from a Storage Perspective
3 Ways to Improve Performance from a Storage Perspective3 Ways to Improve Performance from a Storage Perspective
3 Ways to Improve Performance from a Storage Perspective
 
Basic and Advanced Analysis of Ceph Volume Backend Driver in Cinder - John Haan
Basic and Advanced Analysis of Ceph Volume Backend Driver in Cinder - John HaanBasic and Advanced Analysis of Ceph Volume Backend Driver in Cinder - John Haan
Basic and Advanced Analysis of Ceph Volume Backend Driver in Cinder - John Haan
 
Day 2 General Session Presentations RedisConf
Day 2 General Session Presentations RedisConfDay 2 General Session Presentations RedisConf
Day 2 General Session Presentations RedisConf
 
Redis Day Keynote Salvatore Sanfillipo Redis Labs
Redis Day Keynote Salvatore Sanfillipo Redis LabsRedis Day Keynote Salvatore Sanfillipo Redis Labs
Redis Day Keynote Salvatore Sanfillipo Redis Labs
 
Accelerating HBase with NVMe and Bucket Cache
Accelerating HBase with NVMe and Bucket CacheAccelerating HBase with NVMe and Bucket Cache
Accelerating HBase with NVMe and Bucket Cache
 
Performance & Scalability Improvements in Perforce
Performance & Scalability Improvements in PerforcePerformance & Scalability Improvements in Perforce
Performance & Scalability Improvements in Perforce
 
RBD: What will the future bring? - Jason Dillaman
RBD: What will the future bring? - Jason DillamanRBD: What will the future bring? - Jason Dillaman
RBD: What will the future bring? - Jason Dillaman
 
Performance
PerformancePerformance
Performance
 
OOPs, OOMs, oh my! Containerizing JVM apps
OOPs, OOMs, oh my! Containerizing JVM appsOOPs, OOMs, oh my! Containerizing JVM apps
OOPs, OOMs, oh my! Containerizing JVM apps
 
Common Support Issues And How To Troubleshoot Them - Michael Hackett, Vikhyat...
Common Support Issues And How To Troubleshoot Them - Michael Hackett, Vikhyat...Common Support Issues And How To Troubleshoot Them - Michael Hackett, Vikhyat...
Common Support Issues And How To Troubleshoot Them - Michael Hackett, Vikhyat...
 
Caching with Memcached and APC
Caching with Memcached and APCCaching with Memcached and APC
Caching with Memcached and APC
 
Tarantool: как сэкономить миллион долларов на базе данных на высоконагруженно...
Tarantool: как сэкономить миллион долларов на базе данных на высоконагруженно...Tarantool: как сэкономить миллион долларов на базе данных на высоконагруженно...
Tarantool: как сэкономить миллион долларов на базе данных на высоконагруженно...
 
RedisConf17- Using Redis at scale @ Twitter
RedisConf17- Using Redis at scale @ TwitterRedisConf17- Using Redis at scale @ Twitter
RedisConf17- Using Redis at scale @ Twitter
 
Oscon 2010 - ATS
Oscon 2010 - ATSOscon 2010 - ATS
Oscon 2010 - ATS
 
Scaling Apache Pulsar to 10 Petabytes/Day
Scaling Apache Pulsar to 10 Petabytes/DayScaling Apache Pulsar to 10 Petabytes/Day
Scaling Apache Pulsar to 10 Petabytes/Day
 
Perforce BTrees: The Arcane and the Profane
Perforce BTrees: The Arcane and the ProfanePerforce BTrees: The Arcane and the Profane
Perforce BTrees: The Arcane and the Profane
 

Destacado

Prezentacja korzysci Fm Mobile dla Biznesfm.pl
Prezentacja korzysci Fm Mobile dla Biznesfm.plPrezentacja korzysci Fm Mobile dla Biznesfm.pl
Prezentacja korzysci Fm Mobile dla Biznesfm.pl
biznesfm.pl
 
CTO-CybersecurityForum-2010-Will Gardner
CTO-CybersecurityForum-2010-Will GardnerCTO-CybersecurityForum-2010-Will Gardner
CTO-CybersecurityForum-2010-Will Gardner
segughana
 
Hiv aids sample questions based on neet pg , usmle, plab and fmge pattern (mc...
Hiv aids sample questions based on neet pg , usmle, plab and fmge pattern (mc...Hiv aids sample questions based on neet pg , usmle, plab and fmge pattern (mc...
Hiv aids sample questions based on neet pg , usmle, plab and fmge pattern (mc...
Medico Apps
 
Diapositivas de Web profunda
Diapositivas de Web profundaDiapositivas de Web profunda
Diapositivas de Web profunda
mcmazon
 

Destacado (20)

Scel adc
Scel adcScel adc
Scel adc
 
Empleo ENFINET 241
Empleo  ENFINET 241Empleo  ENFINET 241
Empleo ENFINET 241
 
Abadia De Melk
Abadia De MelkAbadia De Melk
Abadia De Melk
 
Previsiones de la demanda energía
Previsiones de la demanda energíaPrevisiones de la demanda energía
Previsiones de la demanda energía
 
Casos| 2da Sesión| Alejandra Jazmín Simental Franco
Casos| 2da Sesión| Alejandra Jazmín Simental FrancoCasos| 2da Sesión| Alejandra Jazmín Simental Franco
Casos| 2da Sesión| Alejandra Jazmín Simental Franco
 
Prezentacja korzysci Fm Mobile dla Biznesfm.pl
Prezentacja korzysci Fm Mobile dla Biznesfm.plPrezentacja korzysci Fm Mobile dla Biznesfm.pl
Prezentacja korzysci Fm Mobile dla Biznesfm.pl
 
PRESENTATION CPGID AKKERMAN
PRESENTATION CPGID AKKERMANPRESENTATION CPGID AKKERMAN
PRESENTATION CPGID AKKERMAN
 
Elevador eléctrico para video proyector
Elevador eléctrico para video proyectorElevador eléctrico para video proyector
Elevador eléctrico para video proyector
 
Qué es IMS
Qué es IMSQué es IMS
Qué es IMS
 
Fulltext01
Fulltext01Fulltext01
Fulltext01
 
CTO-CybersecurityForum-2010-Will Gardner
CTO-CybersecurityForum-2010-Will GardnerCTO-CybersecurityForum-2010-Will Gardner
CTO-CybersecurityForum-2010-Will Gardner
 
Presentación Institucional 2014
Presentación Institucional 2014Presentación Institucional 2014
Presentación Institucional 2014
 
¡¡CUIDA TU PIEL !!
¡¡CUIDA TU PIEL  !!¡¡CUIDA TU PIEL  !!
¡¡CUIDA TU PIEL !!
 
Quien ordena a quien, y que se ordena en el territorio
Quien ordena a quien, y que se ordena en el territorioQuien ordena a quien, y que se ordena en el territorio
Quien ordena a quien, y que se ordena en el territorio
 
Kemira IR Deck - May 2015
Kemira IR Deck - May 2015Kemira IR Deck - May 2015
Kemira IR Deck - May 2015
 
SUNOPTICS VERSUS BRISTOLITE - CUANDO LO BARATO SALE CARO, EL SALVADOR
SUNOPTICS VERSUS BRISTOLITE - CUANDO LO BARATO SALE CARO, EL SALVADORSUNOPTICS VERSUS BRISTOLITE - CUANDO LO BARATO SALE CARO, EL SALVADOR
SUNOPTICS VERSUS BRISTOLITE - CUANDO LO BARATO SALE CARO, EL SALVADOR
 
Hiv aids sample questions based on neet pg , usmle, plab and fmge pattern (mc...
Hiv aids sample questions based on neet pg , usmle, plab and fmge pattern (mc...Hiv aids sample questions based on neet pg , usmle, plab and fmge pattern (mc...
Hiv aids sample questions based on neet pg , usmle, plab and fmge pattern (mc...
 
Proyecto Grado
Proyecto GradoProyecto Grado
Proyecto Grado
 
Diapositivas de Web profunda
Diapositivas de Web profundaDiapositivas de Web profunda
Diapositivas de Web profunda
 
Zinhle Hazel Tshabalala CV
Zinhle Hazel Tshabalala CVZinhle Hazel Tshabalala CV
Zinhle Hazel Tshabalala CV
 

Similar a Globo.com & Varnish

WE18_Performance_Up.ppt
WE18_Performance_Up.pptWE18_Performance_Up.ppt
WE18_Performance_Up.ppt
webhostingguy
 
Planning for-high-performance-web-application
Planning for-high-performance-web-applicationPlanning for-high-performance-web-application
Planning for-high-performance-web-application
Nguyễn Duy Nhân
 
Drupalcamp Estonia - High Performance Sites
Drupalcamp Estonia - High Performance SitesDrupalcamp Estonia - High Performance Sites
Drupalcamp Estonia - High Performance Sites
drupalcampest
 
Krug Fat Client
Krug Fat ClientKrug Fat Client
Krug Fat Client
Paul Klipp
 
Varnish http accelerator
Varnish http acceleratorVarnish http accelerator
Varnish http accelerator
no no
 
Data processing at the speed of 100 Gbps@Apache Crail (Incubating)
Data processing at the speed of 100 Gbps@Apache Crail (Incubating)Data processing at the speed of 100 Gbps@Apache Crail (Incubating)
Data processing at the speed of 100 Gbps@Apache Crail (Incubating)
DataWorks Summit
 

Similar a Globo.com & Varnish (20)

MNPHP Scalable Architecture 101 - Feb 3 2011
MNPHP Scalable Architecture 101 - Feb 3 2011MNPHP Scalable Architecture 101 - Feb 3 2011
MNPHP Scalable Architecture 101 - Feb 3 2011
 
DrupalCampLA 2011: Drupal backend-performance
DrupalCampLA 2011: Drupal backend-performanceDrupalCampLA 2011: Drupal backend-performance
DrupalCampLA 2011: Drupal backend-performance
 
UnConference for Georgia Southern Computer Science March 31, 2015
UnConference for Georgia Southern Computer Science March 31, 2015UnConference for Georgia Southern Computer Science March 31, 2015
UnConference for Georgia Southern Computer Science March 31, 2015
 
Experience In Building Scalable Web Sites Through Infrastructure's View
Experience In Building Scalable Web Sites Through Infrastructure's ViewExperience In Building Scalable Web Sites Through Infrastructure's View
Experience In Building Scalable Web Sites Through Infrastructure's View
 
Clug 2011 March web server optimisation
Clug 2011 March  web server optimisationClug 2011 March  web server optimisation
Clug 2011 March web server optimisation
 
WE18_Performance_Up.ppt
WE18_Performance_Up.pptWE18_Performance_Up.ppt
WE18_Performance_Up.ppt
 
Fluentd Overview, Now and Then
Fluentd Overview, Now and ThenFluentd Overview, Now and Then
Fluentd Overview, Now and Then
 
Planning for-high-performance-web-application
Planning for-high-performance-web-applicationPlanning for-high-performance-web-application
Planning for-high-performance-web-application
 
Drupalcamp Estonia - High Performance Sites
Drupalcamp Estonia - High Performance SitesDrupalcamp Estonia - High Performance Sites
Drupalcamp Estonia - High Performance Sites
 
Drupalcamp Estonia - High Performance Sites
Drupalcamp Estonia - High Performance SitesDrupalcamp Estonia - High Performance Sites
Drupalcamp Estonia - High Performance Sites
 
Sun Web Server Brief
Sun Web Server BriefSun Web Server Brief
Sun Web Server Brief
 
Krug Fat Client
Krug Fat ClientKrug Fat Client
Krug Fat Client
 
SharePoint 2010 Boost your farm performance!
SharePoint 2010 Boost your farm performance!SharePoint 2010 Boost your farm performance!
SharePoint 2010 Boost your farm performance!
 
Making it fast: Zotonic & Performance
Making it fast: Zotonic & PerformanceMaking it fast: Zotonic & Performance
Making it fast: Zotonic & Performance
 
Varnish http accelerator
Varnish http acceleratorVarnish http accelerator
Varnish http accelerator
 
Open ebs 101
Open ebs 101Open ebs 101
Open ebs 101
 
Data processing at the speed of 100 Gbps@Apache Crail (Incubating)
Data processing at the speed of 100 Gbps@Apache Crail (Incubating)Data processing at the speed of 100 Gbps@Apache Crail (Incubating)
Data processing at the speed of 100 Gbps@Apache Crail (Incubating)
 
Lamp Stack Optimization
Lamp Stack OptimizationLamp Stack Optimization
Lamp Stack Optimization
 
Voldemort & Hadoop @ Linkedin, Hadoop User Group Jan 2010
Voldemort & Hadoop @ Linkedin, Hadoop User Group Jan 2010Voldemort & Hadoop @ Linkedin, Hadoop User Group Jan 2010
Voldemort & Hadoop @ Linkedin, Hadoop User Group Jan 2010
 
Hadoop and Voldemort @ LinkedIn
Hadoop and Voldemort @ LinkedInHadoop and Voldemort @ LinkedIn
Hadoop and Voldemort @ LinkedIn
 

Último

Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Safe Software
 

Último (20)

Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectors
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf
 
Exploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusExploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with Milvus
 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
 
Ransomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdfRansomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdf
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 

Globo.com & Varnish

  • 1. HTTP accelerator Cachos 2.0 Luis Henrique Okama Tollef Fog Heen Mario Carvalho
  • 2. What is the problem? GET / HTTP/1.1 Hang on, I need to look up a few hundred things in my database and then do a lot of editing controlled by a scripting language HEAD / HTTP/1.1 Hang on, I need to look up a few hundred things in my database and then do a lot of editing controlled by a scripting language, and then I will throw the result away.
  • 3. Why are CMS-es slow? Complex content generation process Single database prevents clustering Expensive software ditto This means: we need server side caching
  • 4. Why are the existing solutions not good enough? Squid, ancient design, forward proxy Apache, not what it's built for, not what it's good at Akamai (and similar), expensive, vendor lock-in
  • 5. What is Varnish? Dedicated HTTP accelerator Focus on server-side speedups Policy control High performance Varnish Configuration Language Shared memory log
  • 6. High performance 11 syscalls + 7 locks for a cache hit Work with the OS, not against it. Multi-CPU, multi-core 64 bit Use advanced OS features: Accept filters madvise(MADV_RANDOM) kqueue, epoll Don't copy data if you don't have to Use workspaces, not malloc/free Compiled configuration
  • 7. Policy control Override TTLs Add, remove or change headers Strip cookies Rewrite URLs Invalidate objects in the cache
  • 8. Varnish Configuration Language Simple domain specific language Compiled via C language to binary Transparently! Dynamically loaded Multiple configs loaded concurrently Instant switch from one VCL to another. Can be done from VCL
  • 9. VCL Example acl some_acl { "10.0.0.0/8" } if (client.ip ~ some_acl) { pass; } if (req.http.host ~ "foo.com$") { set req.http.host = regsub(req.http.host, "foo.com", "bar.org"); } if (obj.valid) { set obj.ttl = 10m; deliver; }
  • 10. Shared memory logfile Fast Custom log tailers varnishtop varnishlog varnishhist varnishncsa varnishstat
  • 12. Comparative scalability setup time cost open source throughput physical space
  • 13. Comparative scalability setup time cost open source throughput physical space
  • 14. Comparative scalability setup time cost open source throughput physical space
  • 15. Comparative scalability setup time cost open source throughput physical space
  • 16. Comparative scalability setup time cost open source throughput physical space
  • 17. Comparative scalability setup time cost open source throughput physical space
  • 18. Comparative scalability setup time cost open source throughput physical space
  • 20. Conclusion software customization work set
  • 23. Contacts Luis H. Okama okama@corp.globo.com (www.globo.com) Mario Carvalho mariocar@corp.globo.com (www.globo.com) Tollef Fog Heen tfheen@redpill-linpro.com (www.varnish-cache.com) @ Stand Globo.com