SlideShare ist ein Scribd-Unternehmen logo
How Zynga handles monitoring at
scale in its hybrid zCloud

Nov 12th, 2013
Matt West : mwest@zynga.com
Watch the video with slide
synchronization on InfoQ.com!
http://www.infoq.com/presentations
/zynga-zcloud

InfoQ.com: News & Community Site
• 750,000 unique visitors/month
• Published in 4 languages (English, Chinese, Japanese and Brazilian
Portuguese)
• Post content from our QCon conferences
• News 15-20 / week
• Articles 3-4 / week
• Presentations (videos) 12-15 / week
• Interviews 2-3 / week
• Books 1 / month
Presented at QCon San Francisco
www.qconsf.com
Purpose of QCon
- to empower software development by facilitating the spread of
knowledge and innovation
Strategy
- practitioner-driven conference designed for YOU: influencers of
change and innovation in your teams
- speakers and topics driving the evolution and innovation
- connecting and catalyzing the influencers and innovators
Highlights
- attended by more than 12,000 delegates since 2007
- held in 9 cities worldwide
With Great Scale, Comes Great Challenges…
• The Sky is Falling!
– Immense alert volumes
– Irregular checks with inconsistent results
– Environment coverage questionability
• Touching the Oven!
– Investigate a set of standards to provide the customers
– Leverage an API for host information
– Use asynchronous queues for job execution at scale
• Into the Trenches!
– Implement findings with customers
• Profit!

2
Nagios, Gearman, and Mod-Gearman
• Nagios is susceptible to
processing delays for various
reasons.
• Tuning configuration
parameters can help.
• Gearman / Mod-Gearman
gives us access to designated
pool of workers.
– Can Grow and Shrink with
demand from Nagios.
– Written in C and Open
Source.
– Practical and Easy to
deploy.

Non Mod-Gearman Enabled Nagios

Mod-Gearman Enabled Nagios

3
Nagios, Gearman, and Mod-Gearman Continued…
• Nagios Daemon Loads a NEB
(Nagios Event Broker) module.
• NEB Module imports or skips
inserting the job to the
requested Gearman queue.

• Workers running on various
servers execute commands on
behalf of the Nagios instance.
• Workers then inserts the results of executing the command into the results
Gearman queue for processing.
• Result worker(s) consume the Gearman queue information and pass the
information back into the Nagios process for any further processing and
handling.

4
Initial Results
• Host Check Latency Times in
seconds
– Standard: min/max/avg
– 107.62;111.23;109.656

– Mod-Gearman: min/max/avg
– 0;6.59;2.753
– Savings: min/max/avg
– 100.00%;94.08%;97.49%

• Host Check Execution Times in
seconds
– Standard: min/max/avg
– 3.02;4.03;4.014
– Mod-Gearman: min/max/avg
– 0.5;0.53;0.508
– Savings: min/max/avg
– 83.44%;86.85%;87.34%
5
Initial Results Continued…
• Service Check Latency Times in
seconds
– Standard: min/max/avg
– 47.21;118.17;110.78

– Mod-Gearman: min/max/avg
– 0;8.05;0.405
– Savings: min/max/avg
– 100.00%;93.19%;99.63%

• Service Check Execution Times in
seconds
– Standard: min/max/avg
– 0.01;4.21;0.18
– Mod-Gearman: min/max/avg
– 0;3.24;0.121
– Savings: min/max/avg
– 100.00%;23.04%;32.78%
6
Initial Results Continued…
• Host and Service Exec Times stay fairly stable.
• Host and Service Latency Times are immediately reduced.
• Achieved even while adding more hosts and services to this
cluster.
– Standard:
– 10452 Services
– 1294 Hosts

– Mod-Gearman:
– 17996 Services
– 1374 Hosts
– Difference:
– 7544 Services (+72.18%)
– 80 Hosts (+6.18%)

7
Our Monitoring Scaling Pipe Dream
• Saigon (Centralized Nagios Configuration Management)
– What if some of those initial problems, weren’t problems
because everyone came to us for Nagios solutions.
• Distributable Result Information to various customers
– What if all the customers could register an API callback for
information about Nagios alerts they don’t control.
• Increased usage ability of external host information from
external APIs.
– What if we didn’t have to wait around for host information to
come back from off site APIs due to latency issues.

8
Saigon and Beanstalkd
• Saigon UI Explanation
– Beanstalkd integration
– RPM Builder
– Configuration Viewing
– Configuration Tester
– Configuration Version
Diffing
• Saigon API Explanation
– Caching Layer
– RESTful Syntax
– Scripted Consumers

9
Distributed Results with Beanstalkd
• Nagios
– Script sends data to an API to be placed into Beanstalkd.

• Beanstalkd
– Reduces work done by Nagios server to bare minimum.
– Possible customers for Nagios results.
– Stats and Analytics
– Lifetime Server State Change Logs
– External Break/Fix Systems

10
Rightscale Cache and Beanstalkd
• External calls to Rightscale API could be untimely.
– Fairly reliable at returning data small sets of data.
– Certain large requests had a 10% chance of failing.
• Implemented Host Hot Cache
– Leveraged Beanstalkd to manage sub jobs of global jobs.
– Beanstalkd is used to keep global re-occurring jobs running.
– Hot Cache is completely refreshed once every 4 hours.
• Fronted by RESTful API
– Allows for single, multi, global host invalidation or revalidation.
– Created jobs for surfacing known problems between
Cloudstack, Rightscale and our Physical Hosts.

11
Software Used
• Nagios : http://nagios.org
o v3.2.3 and v3.5.0
• Gearman : http://gearman.org
o v0.25
• Mod-Gearman : https://labs.consol.de/lang/en/nagios/mod-gearman/
o v1.4.2
• Beanstalkd : http://kr.github.io/beanstalkd/
o v1.4.6
• Check-MK : http://mathias-kettner.com/check_mk.html
o v1.2.2p1

12
Thank you…

We can now begin the,
Interrogation Gauntlet… ;)

13
Watch the video with slide synchronization on
InfoQ.com!
http://www.infoq.com/presentations/zyngazcloud

Weitere ähnliche Inhalte

Mehr von C4Media

Mehr von C4Media (20)

Service Meshes- The Ultimate Guide
Service Meshes- The Ultimate GuideService Meshes- The Ultimate Guide
Service Meshes- The Ultimate Guide
 
Shifting Left with Cloud Native CI/CD
Shifting Left with Cloud Native CI/CDShifting Left with Cloud Native CI/CD
Shifting Left with Cloud Native CI/CD
 
CI/CD for Machine Learning
CI/CD for Machine LearningCI/CD for Machine Learning
CI/CD for Machine Learning
 
Fault Tolerance at Speed
Fault Tolerance at SpeedFault Tolerance at Speed
Fault Tolerance at Speed
 
Architectures That Scale Deep - Regaining Control in Deep Systems
Architectures That Scale Deep - Regaining Control in Deep SystemsArchitectures That Scale Deep - Regaining Control in Deep Systems
Architectures That Scale Deep - Regaining Control in Deep Systems
 
ML in the Browser: Interactive Experiences with Tensorflow.js
ML in the Browser: Interactive Experiences with Tensorflow.jsML in the Browser: Interactive Experiences with Tensorflow.js
ML in the Browser: Interactive Experiences with Tensorflow.js
 
Build Your Own WebAssembly Compiler
Build Your Own WebAssembly CompilerBuild Your Own WebAssembly Compiler
Build Your Own WebAssembly Compiler
 
User & Device Identity for Microservices @ Netflix Scale
User & Device Identity for Microservices @ Netflix ScaleUser & Device Identity for Microservices @ Netflix Scale
User & Device Identity for Microservices @ Netflix Scale
 
Scaling Patterns for Netflix's Edge
Scaling Patterns for Netflix's EdgeScaling Patterns for Netflix's Edge
Scaling Patterns for Netflix's Edge
 
Make Your Electron App Feel at Home Everywhere
Make Your Electron App Feel at Home EverywhereMake Your Electron App Feel at Home Everywhere
Make Your Electron App Feel at Home Everywhere
 
The Talk You've Been Await-ing For
The Talk You've Been Await-ing ForThe Talk You've Been Await-ing For
The Talk You've Been Await-ing For
 
Future of Data Engineering
Future of Data EngineeringFuture of Data Engineering
Future of Data Engineering
 
Automated Testing for Terraform, Docker, Packer, Kubernetes, and More
Automated Testing for Terraform, Docker, Packer, Kubernetes, and MoreAutomated Testing for Terraform, Docker, Packer, Kubernetes, and More
Automated Testing for Terraform, Docker, Packer, Kubernetes, and More
 
Navigating Complexity: High-performance Delivery and Discovery Teams
Navigating Complexity: High-performance Delivery and Discovery TeamsNavigating Complexity: High-performance Delivery and Discovery Teams
Navigating Complexity: High-performance Delivery and Discovery Teams
 
High Performance Cooperative Distributed Systems in Adtech
High Performance Cooperative Distributed Systems in AdtechHigh Performance Cooperative Distributed Systems in Adtech
High Performance Cooperative Distributed Systems in Adtech
 
Rust's Journey to Async/await
Rust's Journey to Async/awaitRust's Journey to Async/await
Rust's Journey to Async/await
 
Opportunities and Pitfalls of Event-Driven Utopia
Opportunities and Pitfalls of Event-Driven UtopiaOpportunities and Pitfalls of Event-Driven Utopia
Opportunities and Pitfalls of Event-Driven Utopia
 
Datadog: a Real-Time Metrics Database for One Quadrillion Points/Day
Datadog: a Real-Time Metrics Database for One Quadrillion Points/DayDatadog: a Real-Time Metrics Database for One Quadrillion Points/Day
Datadog: a Real-Time Metrics Database for One Quadrillion Points/Day
 
Are We Really Cloud-Native?
Are We Really Cloud-Native?Are We Really Cloud-Native?
Are We Really Cloud-Native?
 
CockroachDB: Architecture of a Geo-Distributed SQL Database
CockroachDB: Architecture of a Geo-Distributed SQL DatabaseCockroachDB: Architecture of a Geo-Distributed SQL Database
CockroachDB: Architecture of a Geo-Distributed SQL Database
 

Kürzlich hochgeladen

Structuring Teams and Portfolios for Success
Structuring Teams and Portfolios for SuccessStructuring Teams and Portfolios for Success
Structuring Teams and Portfolios for Success
UXDXConf
 

Kürzlich hochgeladen (20)

IESVE for Early Stage Design and Planning
IESVE for Early Stage Design and PlanningIESVE for Early Stage Design and Planning
IESVE for Early Stage Design and Planning
 
Motion for AI: Creating Empathy in Technology
Motion for AI: Creating Empathy in TechnologyMotion for AI: Creating Empathy in Technology
Motion for AI: Creating Empathy in Technology
 
Speed Wins: From Kafka to APIs in Minutes
Speed Wins: From Kafka to APIs in MinutesSpeed Wins: From Kafka to APIs in Minutes
Speed Wins: From Kafka to APIs in Minutes
 
UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2
 
Agentic RAG What it is its types applications and implementation.pdf
Agentic RAG What it is its types applications and implementation.pdfAgentic RAG What it is its types applications and implementation.pdf
Agentic RAG What it is its types applications and implementation.pdf
 
Intro in Product Management - Коротко про професію продакт менеджера
Intro in Product Management - Коротко про професію продакт менеджераIntro in Product Management - Коротко про професію продакт менеджера
Intro in Product Management - Коротко про професію продакт менеджера
 
Structuring Teams and Portfolios for Success
Structuring Teams and Portfolios for SuccessStructuring Teams and Portfolios for Success
Structuring Teams and Portfolios for Success
 
WSO2CONMay2024OpenSourceConferenceDebrief.pptx
WSO2CONMay2024OpenSourceConferenceDebrief.pptxWSO2CONMay2024OpenSourceConferenceDebrief.pptx
WSO2CONMay2024OpenSourceConferenceDebrief.pptx
 
ODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User GroupODC, Data Fabric and Architecture User Group
ODC, Data Fabric and Architecture User Group
 
PLAI - Acceleration Program for Generative A.I. Startups
PLAI - Acceleration Program for Generative A.I. StartupsPLAI - Acceleration Program for Generative A.I. Startups
PLAI - Acceleration Program for Generative A.I. Startups
 
Server-Driven User Interface (SDUI) at Priceline
Server-Driven User Interface (SDUI) at PricelineServer-Driven User Interface (SDUI) at Priceline
Server-Driven User Interface (SDUI) at Priceline
 
Transforming The New York Times: Empowering Evolution through UX
Transforming The New York Times: Empowering Evolution through UXTransforming The New York Times: Empowering Evolution through UX
Transforming The New York Times: Empowering Evolution through UX
 
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
 
Unpacking Value Delivery - Agile Oxford Meetup - May 2024.pptx
Unpacking Value Delivery - Agile Oxford Meetup - May 2024.pptxUnpacking Value Delivery - Agile Oxford Meetup - May 2024.pptx
Unpacking Value Delivery - Agile Oxford Meetup - May 2024.pptx
 
IoT Analytics Company Presentation May 2024
IoT Analytics Company Presentation May 2024IoT Analytics Company Presentation May 2024
IoT Analytics Company Presentation May 2024
 
Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)
Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)
Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)
 
Enterprise Security Monitoring, And Log Management.
Enterprise Security Monitoring, And Log Management.Enterprise Security Monitoring, And Log Management.
Enterprise Security Monitoring, And Log Management.
 
UiPath Test Automation using UiPath Test Suite series, part 1
UiPath Test Automation using UiPath Test Suite series, part 1UiPath Test Automation using UiPath Test Suite series, part 1
UiPath Test Automation using UiPath Test Suite series, part 1
 
Powerful Start- the Key to Project Success, Barbara Laskowska
Powerful Start- the Key to Project Success, Barbara LaskowskaPowerful Start- the Key to Project Success, Barbara Laskowska
Powerful Start- the Key to Project Success, Barbara Laskowska
 
Designing for Hardware Accessibility at Comcast
Designing for Hardware Accessibility at ComcastDesigning for Hardware Accessibility at Comcast
Designing for Hardware Accessibility at Comcast
 

How Zynga Handles Monitoring at Scale in Its Hybrid zCloud

  • 1. How Zynga handles monitoring at scale in its hybrid zCloud Nov 12th, 2013 Matt West : mwest@zynga.com
  • 2. Watch the video with slide synchronization on InfoQ.com! http://www.infoq.com/presentations /zynga-zcloud InfoQ.com: News & Community Site • 750,000 unique visitors/month • Published in 4 languages (English, Chinese, Japanese and Brazilian Portuguese) • Post content from our QCon conferences • News 15-20 / week • Articles 3-4 / week • Presentations (videos) 12-15 / week • Interviews 2-3 / week • Books 1 / month
  • 3. Presented at QCon San Francisco www.qconsf.com Purpose of QCon - to empower software development by facilitating the spread of knowledge and innovation Strategy - practitioner-driven conference designed for YOU: influencers of change and innovation in your teams - speakers and topics driving the evolution and innovation - connecting and catalyzing the influencers and innovators Highlights - attended by more than 12,000 delegates since 2007 - held in 9 cities worldwide
  • 4. With Great Scale, Comes Great Challenges… • The Sky is Falling! – Immense alert volumes – Irregular checks with inconsistent results – Environment coverage questionability • Touching the Oven! – Investigate a set of standards to provide the customers – Leverage an API for host information – Use asynchronous queues for job execution at scale • Into the Trenches! – Implement findings with customers • Profit! 2
  • 5. Nagios, Gearman, and Mod-Gearman • Nagios is susceptible to processing delays for various reasons. • Tuning configuration parameters can help. • Gearman / Mod-Gearman gives us access to designated pool of workers. – Can Grow and Shrink with demand from Nagios. – Written in C and Open Source. – Practical and Easy to deploy. Non Mod-Gearman Enabled Nagios Mod-Gearman Enabled Nagios 3
  • 6. Nagios, Gearman, and Mod-Gearman Continued… • Nagios Daemon Loads a NEB (Nagios Event Broker) module. • NEB Module imports or skips inserting the job to the requested Gearman queue. • Workers running on various servers execute commands on behalf of the Nagios instance. • Workers then inserts the results of executing the command into the results Gearman queue for processing. • Result worker(s) consume the Gearman queue information and pass the information back into the Nagios process for any further processing and handling. 4
  • 7. Initial Results • Host Check Latency Times in seconds – Standard: min/max/avg – 107.62;111.23;109.656 – Mod-Gearman: min/max/avg – 0;6.59;2.753 – Savings: min/max/avg – 100.00%;94.08%;97.49% • Host Check Execution Times in seconds – Standard: min/max/avg – 3.02;4.03;4.014 – Mod-Gearman: min/max/avg – 0.5;0.53;0.508 – Savings: min/max/avg – 83.44%;86.85%;87.34% 5
  • 8. Initial Results Continued… • Service Check Latency Times in seconds – Standard: min/max/avg – 47.21;118.17;110.78 – Mod-Gearman: min/max/avg – 0;8.05;0.405 – Savings: min/max/avg – 100.00%;93.19%;99.63% • Service Check Execution Times in seconds – Standard: min/max/avg – 0.01;4.21;0.18 – Mod-Gearman: min/max/avg – 0;3.24;0.121 – Savings: min/max/avg – 100.00%;23.04%;32.78% 6
  • 9. Initial Results Continued… • Host and Service Exec Times stay fairly stable. • Host and Service Latency Times are immediately reduced. • Achieved even while adding more hosts and services to this cluster. – Standard: – 10452 Services – 1294 Hosts – Mod-Gearman: – 17996 Services – 1374 Hosts – Difference: – 7544 Services (+72.18%) – 80 Hosts (+6.18%) 7
  • 10. Our Monitoring Scaling Pipe Dream • Saigon (Centralized Nagios Configuration Management) – What if some of those initial problems, weren’t problems because everyone came to us for Nagios solutions. • Distributable Result Information to various customers – What if all the customers could register an API callback for information about Nagios alerts they don’t control. • Increased usage ability of external host information from external APIs. – What if we didn’t have to wait around for host information to come back from off site APIs due to latency issues. 8
  • 11. Saigon and Beanstalkd • Saigon UI Explanation – Beanstalkd integration – RPM Builder – Configuration Viewing – Configuration Tester – Configuration Version Diffing • Saigon API Explanation – Caching Layer – RESTful Syntax – Scripted Consumers 9
  • 12. Distributed Results with Beanstalkd • Nagios – Script sends data to an API to be placed into Beanstalkd. • Beanstalkd – Reduces work done by Nagios server to bare minimum. – Possible customers for Nagios results. – Stats and Analytics – Lifetime Server State Change Logs – External Break/Fix Systems 10
  • 13. Rightscale Cache and Beanstalkd • External calls to Rightscale API could be untimely. – Fairly reliable at returning data small sets of data. – Certain large requests had a 10% chance of failing. • Implemented Host Hot Cache – Leveraged Beanstalkd to manage sub jobs of global jobs. – Beanstalkd is used to keep global re-occurring jobs running. – Hot Cache is completely refreshed once every 4 hours. • Fronted by RESTful API – Allows for single, multi, global host invalidation or revalidation. – Created jobs for surfacing known problems between Cloudstack, Rightscale and our Physical Hosts. 11
  • 14. Software Used • Nagios : http://nagios.org o v3.2.3 and v3.5.0 • Gearman : http://gearman.org o v0.25 • Mod-Gearman : https://labs.consol.de/lang/en/nagios/mod-gearman/ o v1.4.2 • Beanstalkd : http://kr.github.io/beanstalkd/ o v1.4.6 • Check-MK : http://mathias-kettner.com/check_mk.html o v1.2.2p1 12
  • 15. Thank you… We can now begin the, Interrogation Gauntlet… ;) 13
  • 16. Watch the video with slide synchronization on InfoQ.com! http://www.infoq.com/presentations/zyngazcloud