Apache Mesos

History

Mesos began as a research project in the UC Berkeley RAD Lab by then PhD students Benjamin Hindman, Andy Konwinski, and Matei Zaharia, as well as professor Ion Stoica. The students started working on the project as part of a course taught by David Culler. It was originally named Nexus but due to a conflict with another university's project, was renamed to Mesos.[2]

Mesos was first presented in 2009 (while still named Nexus) by Andy Konwinski at HotCloud '09 in a talk accompanying the first paper published about the project.[3] Later in 2011 it was presented in a more mature state in a talk by Zaharia at the Usenix Symposium on Networked Systems Design and Implementation conference about the paper "Mesos: A Platform for Fine-Grained Resource Sharing in the Data Center" by Benjamin Hindman, Andy Konwinski, Zaharia, Ali Ghodsi, Anthony D. Joseph, Randy Katz, Scott Shenker, Ion Stoica.[4]

On July 27, 2016, the Apache Software Foundation announced version 1.[5] It added the ability to centrally supply Docker, rkt and appc instances.[6]

Technology

Mesos uses Linux cgroups to provide isolation for CPU, memory, I/O and file system.[7]

Mesos is comparable to Google's Borg scheduler, a platform used internally to manage and distribute Google's services.[8]

Apache Aurora
Developer(s)Apache Software Foundation
Stable release
0.21.0 / September 10, 2018 (2018-09-10)[9]
RepositoryAurora Repository
Written inJava, Python
TypeMesos Framework
LicenseApache License 2.0
Websiteaurora.apache.org

Apache Aurora

Apache Aurora is a Mesos framework for both long-running services and cron jobs, originally developed by Twitter starting in 2010 and open sourced in late 2013.[10] It can scale to tens of thousands of servers, and holds many similarities to Borg[11][12] including its rich domain-specific language (DSL) for configuring services.

Chronos

Chronos is a distributed cron-like system which is elastic and capable of expressing dependencies between jobs.[13]

Marathon

Marathon is promoted for platform as a service or container orchestration system scaling to thousands of physical servers. It is fully REST-based and allows canary-style deployments and deployment topologies. It is written in the programming language Scala.[14]

Users

The social networking site Twitter began using Mesos and Apache Aurora in 2010, after Hindman gave a presentation to a group of Twitter engineers.[8]

Airbnb said in July 2013 that it uses Mesos to run data processing systems like Apache Hadoop and Apache Spark.[15]

The Internet auction website eBay stated in April 2014 that it used Mesos to run continuous integration on a per-developer basis. They accomplish this by using a custom Mesos plugin that allows developers to launch their own private Jenkins instance.[16]

In April 2015, it was announced that Apple service Siri is using its own Mesos framework called Jarvis.[17]

In August 2015, it was announced that Verizon selected Mesosphere's DC/OS, which is based on open source Apache Mesos, for data center service orchestration.[18]

In November 2015, Yelp announced they had been using Mesos and Marathon for a year and a half for production services.[19]

Commercial support

Software startup Mesosphere, Inc. sells the Datacenter Operating System, a distributed operating system, based on Apache Mesos.[20] In September 2015, Microsoft announced a commercial partnership with Mesosphere to build container scheduling and orchestration services for Microsoft Azure.[21] In October 2015, Oracle announced support for Mesos through Oracle Container Cloud Service.[22]

See also

References
  1. "ASF Git Repos - mesos.git/commit". Retrieved 30 September 2020.
  2. Zaharia, Matei. "HUG Meetup August 2010: Mesos: A Flexible Cluster Resource manager - Part 1". youtube.com. Retrieved 13 January 2015.
  3. "A Common Substrate for Cluster Computing" (PDF).
  4. Hindman, Benjamin; Konwinski, Andy; Zaharia, Matei; Ghodsi, Ali; Joseph, Anthony; Katz, Randy; Shenker, Scott; Stoica, Ion (2011). "Mesos: A Platform for Fine-Grained Resource Sharing in the Data Center" (PDF). NSDI. 11: 22-22. Retrieved 12 January 2015.
  5. "The Apache Software Foundation Announces Apache Mesos v1.0". Press release. July 27, 2016. Retrieved February 24, 2017.
  6. "Mesos 1.0 brings a new container runtime and more third party integrations". July 27, 2016.
  7. Bappalige, Sachin P. (2014-09-15). "Open-Source Datacenter Computing with Apache Mesos". OpenSource.com. Red Hat. Retrieved 2016-12-10.
  8. Metz, Cade. "Return of the Borg: How Twitter Rebuilt Google's Secret Weapon". wired.com. Wired. Retrieved 12 January 2015.
  9. "Apache Aurora 0.21.0 Released". Retrieved 7 September 2019.
  10. "All about Apache Aurora". Twitter. Retrieved 20 May 2015.
  11. "Large-scale cluster management at Google with Borg" (PDF). Google. Retrieved 20 May 2015.
  12. "Twitter's Aurora and How It Relates to Google's Borg". Retrieved 20 May 2015.
  13. "Chronos". GitHub.com. GitHub. Retrieved 30 March 2015.
  14. "Marathon". Mesosphere.GitHub.io. Mesosphere. 2014. Retrieved 30 March 2015.
  15. Harris, Derrick. "Airbnb is engineering itself into a data-driven company". gigaom.com. Retrieved 12 January 2015.
  16. The eBay PAAS Team. "Delivering eBay's CI Solution with Apache Mesos - Part I". EbayTechBlog.com. eBay. Retrieved 12 January 2015.
  17. Harris, Derrick (2015-04-23). "Apple Details How It Rebuilt Siri on Mesos". Mesosphere.com. Mesosphere. Archived from the original on 2015-04-29. Retrieved 2015-04-27.
  18. "Verizon selects Mesosphere DCOS as nationwide platform for data center service orchestration". Verizon. Retrieved 21 August 2015.
  19. "Introducing PaaSTA: An Open, Distributed, Platform as a Service". engineeringblog.yelp.com. Retrieved 2016-07-12.
  20. "The Mesosphere DCOS". mesosphere.com. Retrieved 13 January 2015.
  21. Mary Jo Foley (September 29, 2015). "New Azure Container Service to bring together Mesos, Docker and Azure cloud". ZDNet.
  22. "Oracle Updates Oracle Cloud Infrastructure Services". oracle.com. Retrieved 2018-02-06.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.