Loading…
This event has ended. View the official site or create your own event → Check it out
This event has ended. Create your own
Get more information on MesosCon Asia, or register to attend.

Customize your schedule by experience level and/or presentation language:

Refer to the “Filter by Type” list on the right to find a session based on topic and/or experience level.

Presentation Language – Sessions are categorized as [C] Chinese, [C,E] Chinese with English Slides or [E] English at the end of each talk title.

View analytic

Sign up or log in to bookmark your favorites and sync them to your phone or calendar.

Frameworks [clear filter]
Wednesday, June 21
 

14:20

Jupyter and Spark on Mesos: Best Practices [C,E] - Shuai Lin, Scrapinghub
Many companies make use of Apache Spark and Apache Mesos to do offline data analytics. Before launching these jobs to production, it is important to provide a place for engineers to test their spark code interactively. At Scrapinghub, we have set up a Jupyter notebook server for this purpose. Engineers can launch their spark jobs via Jupyter interactively on top of Mesos while there is no any extra configuration needed and it provides full access to various stateful services (e.g., HDFS/HBase/Kafka). This architecture is used by multiple teams in the company. For instance, the backend application team uses it to aggregate their logs and metrics, and data science team relies on it to do model training while developing the code. In this talk, Shuai Lin will share the experience they learned in details, including caveats they encountered when deploying and maintaining the notebook server.

Speakers
SL

Shuai Lin

Scrapinghub
Shuai Lin is an Infrastructure Engineer in Scrapinghub, a company that provides PaaS for running web crawlers. He graduated from Tsinghua University in 2010 and has been working in the software industry since then. He has been contributing to Apache Mesos and Apache Spark for yea... Read More →


Wednesday June 21, 2017 14:20 - 15:05
Room 309B

15:10

The Best Practices of DevOps over DC/OS - Sam Chen & Ben Lin, Mesosphere APAC
DC/OS is super hot container technology in China. In this talk, Ben and I will introduce how to realize DevOps scenarios with customer references in China. It includes how to architect DevOps, coding, Gitlab, Jenkins for testing, Marathon for deploying, production deployment etc.

In the same time, being able to show the best practices of customer reference cases.

Speakers
SC

Sam Chen

APJ Country Director, Mesosphere APAC
Running business in APJ
BL

Ben Lin

Solutions Architect, Mesosphere
Ben is currently leads all technical initiatives for Mesosphere in APAC. He has presented at MesosCon Asia, VMworld, VMworld Europe, LISA, HotCloud, and other conferences.


Wednesday June 21, 2017 15:10 - 15:55
Room 309B

16:30

Apache Flink and More [E] - Jörg Schad, Mesosphere & Till Rohrmann, dataArtisans
Apache Mesos allows operators to run distributed applications across an entire datacenter and is attracting ever increasing interest. As much as distributed applications see increased use enabled by Mesos, Mesos also sees increasing use due to a growing ecosystem of well-integrated applications. One of the latest additions to the Mesos family is Apache Flink.

Flink is one of the most popular open source systems for real-time high scale data processing and allows users to deal with low-latency streaming analytical workloads on Mesos.

In this talk, we explain the challenges solved while integrating Flink with Mesos, including how Flink’s distributed architecture can be modeled as a Mesos framework, and how Flink was integrated with Fenzo. Next, we describe how Flink was packaged to easily run on DC/OS.

Speakers
avatar for Till Rohrmann

Till Rohrmann

Engineering lead, data Artisans
Till is a PMC member of Apache Flink and software engineer at dataArtisans. His main work focuses on enhancing Flink’s scalability as a distributed system. Till studied computer science at TU Berlin, TU Munich and École Polytechnique where he specialized in machine learning an... Read More →
JS

Jörg Schad

Software Engineer, Mesosphere
Jörg is a software engineer at Mesosphere in Hamburg. In his previous life he implemented distributed and in memory databases and conducted research in the Hadoop and Cloud area. His speaking experience includes various Meetups, international conferences, and lecture halls.



Wednesday June 21, 2017 16:30 - 17:15
Room 309B
 
Thursday, June 22
 

12:20

An Introduction to VM Management Framework [C,E] - Xiaohui Liu, UCloud
A mesos framework is the component used to manage mesos tasks. The tasks could be long-running services, big data processing, batch job scheduling etc with different frameworks.
Is it possible to run a virtual machine on mesos? If it is, how to do that? In this presentation, Xiaohui will discuss how to build a framework to run virtual machines on mesos,
describe the design of scheduler and executor of framework in details, and introduce some management experience of network, storage, image. 

Speakers
XL

Xiaohui Liu

Xiaohui,Liu, is a senior software engineer at UCloud. He works mainly on the cluster management.



Thursday June 22, 2017 12:20 - 13:05
Room 309B

12:20

Doing “DropBox” the Cloud Native Way - Jörg Schad, Mesosphere
Cloud Native architecture has slowly become the default way to build robust, scalable applications. How would you rebuild a large scale storage service such as Dropbox (please note Dropbox is just an example here and we have no plans of actually competing with Dropbox), using the Cloud Native architecture?

In this presentation, Joerg and Nitish will discuss the Cloud Native architecture, its advantages, and then explain how to build a scalable, multi-tenant, Dropbox like cloud storage system using modern, containerized applications like Minio as the unstructured data/blob store, MongoDB for structured data, Redis for key value pairs etc, all orchestrated on DC/OS.

The presentation will also include a live demo of the Dropbox equivalent product.

Speakers
JS

Jörg Schad

Software Engineer, Mesosphere
Jörg is a software engineer at Mesosphere in Hamburg. In his previous life he implemented distributed and in memory databases and conducted research in the Hadoop and Cloud area. His speaking experience includes various Meetups, international conferences, and lecture halls.


Thursday June 22, 2017 12:20 - 13:05
Room 308

15:10

Swan: Another Long Running Task Scheduler [C] - Chunming Xu, Dataman-Cloud
Swan, Another long running task scheduler (Kevin Xu, Dataman-Cloud.inc) - Marathon shouldn't be the only choice for scheduling long running tasks among Mesos community, Swan add diversity to the ecosystem, it borrows idea from Marathon but also added with new thoughts. Application orchestration shouldn't be a standalone component, also service discovery and API gateway should be together with it. Swan help exposing user's services out with single software instead of Marathon + Mesos DNS + Marathon-LB.

Speakers
CX

Chunming Xu

Before joining Dataman-Cloud Beijing two years ago, I have been doing backend development for more then 8 years. Dataman-Cloud Beijing is a startup company which is helping our customers transforming existing IT platforms from old way to new containerized and more flexible way. O... Read More →


Thursday June 22, 2017 15:10 - 15:55
Room 309B

16:30

Visualize data with Zeppelin and Mesos - Jongyoul Lee, ZEPL
One of the success points of data analysis is speed and fast iteration. In a modern way, there are a lot of tools to help to clean and analyze data like Spark. But making your result beautiful is still a problem. Zeppelin reduces the step, moving the result to make a graph or table. In your browser, you can run your Spark job through your own cluster and make a graph directly from your result. Including Spark, you can run JDBC, Flink, and python job, too.

But Zeppelin had a problem. Zeppelin runs just a single machine for a long time. It doesn't fit in production level. Now Zeppelin supports to run its jobs into Mesos Cluster. Even if it makes Zeppelin execute jobs, Zeppelin can share in the benefits of solid fault tolerant features of Mesos.

This talks will show demo from installing, launching Zeppelin to running jobs into Mesos. And it also shows beautiful visualization of Zeppelin.

Speakers
avatar for Jongyoul Lee

Jongyoul Lee

Software Development Engineer, ZEPL
I'm a member of PMC of Apache Zeppelin and works at ZEPL. In Apache Zeppelin, I focus on stabilizing Apache Zeppelin to be used in production level, developing some enterprise features and enhancing Apache Spark/JDBC features. Personally, I'm really interested in distributed and... Read More →


Thursday June 22, 2017 16:30 - 17:15
Room 309B