Loading…
This event has ended. Visit the official site or create your own event on Sched.
June 25 - 27 - Beijing, China
Click Here For Information & Registration

Monday, June 25
 

07:30 CST

Breakfast
Monday June 25, 2018 07:30 - 09:00 CST
4F Foyer

07:30 CST

Registration
Monday June 25, 2018 07:30 - 17:30 CST
Main Lobby B

08:00 CST

OpenChain Workshop (Registration Required)
The OpenChain Workshop will explain modern open source compliance, how the OpenChain education and reference material can help companies, and how the OpenChain Specification is being used by companies to increase efficiency and save costs.

This is a free workshop designed to answer real-world questions. Program managers, project managers, open source office members, legal personnel and business decision-makers will all find something useful in its content. To register simply send an email to coughlan(at)linux(dot)com

Monday June 25, 2018 08:00 - 12:00 CST
202B

09:00 CST

Keynote: Welcome & Opening Remarks - Jim Zemlin, Executive Director, The Linux Foundation
Speakers
avatar for Jim Zemlin

Jim Zemlin

Executive Director, The Linux Foundation
Jim Zemlin’s career spans three of the largest technology trends to rise over the last decade: mobile computing, cloud computing, and open source software. Today, as executive director of The Linux Foundation, he uses this experience to accelerate innovation in technology through... Read More →


Monday June 25, 2018 09:00 - 09:25 CST
Plenary Hall B
  Keynote

09:30 CST

Keynote: Linus Torvalds, Creator of Linux & Git, in conversation with Dirk Hohndel, VP & Chief Open Source Officer, VMware
Speakers
avatar for Dirk Hohndel

Dirk Hohndel

Head of the Open Source Program Office, Verizon
Dirk is the Head of the Open Source Program Officer at Verizon. Prior to that, Dirk was VMware’s Chief Open Source Officer, where he lead the company’s Open Source Program Office, directing the efforts and strategy around use of and contribution to open-source projects and driving... Read More →
avatar for Linus Torvalds

Linus Torvalds

Fellow, The Linux Foundation
Linus Torvalds was born on December 28, 1969, in Helsinki, Finland. He enrolled at the University of Helsinki in 1988, graduating with a master’s degree in computer science. His M.Sc. thesis was titled “Linux: A Portable Operating System” and was the genesis for what would become... Read More →


Monday June 25, 2018 09:30 - 10:10 CST
Plenary Hall B
  Keynote

10:15 CST

Keynote: Open Source at Huawei Cloud - Dr. Zhexuan Song, Chief Strategy Officer, Cloud Business Unit, Huawei Technologies
Speakers
avatar for Dr. Zhexuan Song

Dr. Zhexuan Song

Chief Strategy Officer, Cloud Business Unit, Huawei Technologies
Dr. Zhexuan Song is the Chief Strategy Officer of Huawei Cloud Business Unit. He earned his Ph.D. from the Department of Computer Science at University of Maryland, and MBA from University of California, Berkeley. After graduation, he worked as a researcher for 8 years in Fujitsu... Read More →


Monday June 25, 2018 10:15 - 10:30 CST
Plenary Hall B
  Keynote

10:35 CST

Keynote: The Software Defined World - Imad Sousou, Corporate Vice President and General Manager, Open Source Technology Center, Intel

As we move toward a world where everything is smart and connected, our experiences are becoming increasingly digitized, resulting in a massive flood of data. We are using the power of that data to transform some of the most exciting areas of human activity. Container technology and open source hypervisors continue to be the driving forces behind the next wave of the technology revolution. Containers are set to usher in the third wave of cloud computing enabling micro-services, whereas, open source hypervisors are optimized to streamline embedded development. Imad Sousou, corporate vice president and general manager of the Open Source Technology Center for Intel Corporation, will highlight how Intel is uniquely positioned to drive the increasingly smart, connected world.


Speakers
avatar for Imad Sousou

Imad Sousou

Imad Sousou is corporate vice president and general manager of the Open Source Technology Center at Intel Corporation. Sousou is responsible for leading Intel's efforts in open source software across technologies and market segments. These include: Linux-based operating systems such... Read More →


Monday June 25, 2018 10:35 - 10:50 CST
Plenary Hall B
  Keynote

10:55 CST

Keynote: Open Source Opening Doors - Michelle Noorali, Sr. Software Engineer, Microsoft
Michelle Noorali, Sr. Software Engineer at Microsoft Azure and open source developer, will talk about open source projects in the cloud-native ecosystem, the benefits of having an open source project in a foundation like the Cloud Native Computing Foundation (CNCF), and the process of transitioning an open source project to the CNCF. Michelle currently serves on the Kubernetes Steering Committee, is on the governing board of the CNCF, and is a core maintainer of Helm, which was recently adopted into the CNCF. In this talk, Michelle will aim to inspire and inform other maintainers of open source projects on how to think about foundations as a long-term home for their open source project.

Speakers
avatar for Michelle Noorali

Michelle Noorali

Senior Software Engineer, Microsoft
Michelle Noorali is a Sr. Software Engineer at Microsoft and was Co-Chair for KubeCon+CloudNativeCon 2017. She is a member of the CNCF Technical Oversight Committee and serves as a developer representative on the CNCF Governing Board. Michelle is also a core maintainer of several... Read More →


Monday June 25, 2018 10:55 - 11:15 CST
Plenary Hall B
  Keynote

11:15 CST

Coffee Break
Monday June 25, 2018 11:15 - 11:30 CST
4F Foyer

11:15 CST

11:30 CST

The Last Mile On Democratizing AI - Zhipeng Huang, Huawei & JF Ding, Intel (slides attached)
Democratizing AI is important to enable everyone to be able to utilize one of the great industry innovation of the century. However only open sourcing the frameworks is not going to achieve the goal. While the user could have many open source frameworks at their disposal (Tensorflow, PyTorch, MXNet,...), they have to run it on proprietary public clouds where you have virtually zero control.

In this talk, we will present how Kubernetes working with OpenStack Cyborg project could help truly democratizing AI by providing an open source infrastructure for deep learning. We will also show how the user could achieve better control and performance by correlating hardware accelerator resource with the deep learning graphs.

Speakers
avatar for JF Ding

JF Ding

Engineering Manager, Intel
Jianfeng(JF) Ding, from Open Source Technology Center of Intel Inc., is working on several open source cloud computing projects, such as OpenStack, Kubernetes, etc., as an engineering manager and technical leader.
avatar for Zhipeng Huang

Zhipeng Huang

Director of Open Source, Huawei
Zhipeng Huang currently serve as Director of Open Source for Huawei Compute Product line, in charge of openEuler, MindSpore and openGauss community operation. Zhipeng is now the TAC member of LFAI, TAC and Outreach member of the Confidential Computing Consortium, co-lead of the Kubernetes... Read More →



Monday June 25, 2018 11:30 - 12:10 CST
311A
  AI & Deep Learning

11:30 CST

Best Practice of Adopting Kubernetes on Genome Sequencing - Shengjun Tang, Huawei (slides attached)
The data analysis of genomic sequencing contains many processing steps and each step is independent. In the practice of using Kubernetes for sequencing, the main difficulties to be overcome are: (1) The traditional software installation process is complicated. (2) Data upload channel establishment & data sharing among all processing steps. (3) use k8s objects for so many steps will be tedious, so need an orchestration mechanism to automate the entire process.

Speakers
avatar for Shengjun Tang

Shengjun Tang

Senior Software Engineer 高级软件工程师, Huawei
Huawei Cloud architect, more than 10 years of work experience. At present, he is the technical leader of Huawei cloud application orchestration service and gene container field, leading cloud service catalog, application orchestration, and genetic container architecture design. He... Read More →



Monday June 25, 2018 11:30 - 12:10 CST
309B

11:30 CST

Microservices, Service Mesh, and CI/CD Pipelines - Making it All Work Together - Brian Redmond, Microsoft (slides attached)
Microservices come with many advantages for massively scaling applications. CI/CD is a common approach to automating updates to these applications in kubernetes. Strategies such as canary deployments can be simple with a basic website, but this is a difficult task with distributed systems. I would argue that many CI/CD systems are missing some key components such as: advanced routing, observability, and chaos testing.

Service mesh solutions bring these missing components to kubernetes allowing us to shape traffic to specific versions and obtain metrics to better understand the impact of updates.

I will demonstrate how to use common CI/CD tooling such as Brigade, Jenkins, or Spinnaker to drive deployments with Kubernetes. I will show how service mesh technologies such as istio, conduit, or linkerd ease the ability to efficiently deliver and test microservices in Kubernetes.

Speakers
avatar for Brian Redmond

Brian Redmond

Principal Product Manager, Microsoft
I am a Principal Product Manager working on our Cloud Native Platforms and AKS. My role is to support our customer and community efforts. I have been working in technology for over 28 years and have a mixed background from application development to infrastructure. I am based in Denver... Read More →



Monday June 25, 2018 11:30 - 12:10 CST
309A

11:30 CST

eBPF in Action - Feng Li
eBPF In-Kernel Virtual Machine as an emerging superpower in the Linux world not only has demonstrated its ability to be used as a powerful universal tool but also changing the way you think about Linux Kernel development itself.

This speech aims at demystifying the essentials of eBPF, it will also show Feng Li's personal research work and practicing  on real ARM hardware like Raspberry Pi:
1) Anatomy of eBPF In-kernel Virtual Machine
internal of eBPF, bpftool, BPF LLVM backend, BCC, py2bpf...
2) XDP(eXpress Data Path)
fast packet processing and programmable network data path in Linux.
3) New eBPF-driven secure Network solutions
project Cilium and Suricata for secure networking, and why eBPF plays an important role in next generation Cloud Computing.
4) eBPF on ARM
practicing eBPF on open source hardware platforms like Raspberry Pi, and project BPFd for ARM64...

Speakers
FL

Feng Li

Freelancer, N/A
After focused on mobile software development for 11+ years(has been working in Motorola, Samsung, and Alibaba) in China, I am now engaged in the field of Cloud infrastructure (had been worked in Dell EMC and Citrix Systems). My previous speaking experience: 1) "eBPF in Action", LinuxCon... Read More →



Monday June 25, 2018 11:30 - 12:10 CST
306B

11:30 CST

Cloud Foundry and IoT - Yang Hin, Cloud Foundry Foundation
In response to the China’s 19th Congress, it proposed to “strengthen the construction of manufacturing powers, accelerate the development of advanced manufacturing industries, and promote the integration of the Internet, big data and artificial intelligence, with the real economy.” Many domestic companies are looking for their own path of digital transformation. In the past few years, with the help of the open source platform Cloud Foundry, many Fortune 500 companies have achieved big success in the IoT field. This lecture through case sharing, hoping to work with the domestic open source community to explore how to build China’s road of IoT.

Speakers
avatar for Yang Hin

Yang Hin

Director, Cloud Foundry APAC
Yang Hin manage Cloud Foundry Foundation’s ecosystem development in Greater China. He and team working closely with enterprise CIO/CTO, partners, developers, industry organisations, medias and technical communities in the region. Yang Hin has over 20 years experience on enterprise... Read More →


Monday June 25, 2018 11:30 - 12:10 CST
307A

11:30 CST

Preempt-RT Linuxkit -- Put Docker into IoT - Tiejun Chen, VMware
Linuxkit is a toolkit for building secure, portable and lean operating systems for containers. But currently Linuxkit is built based on mainline linux. So it just provide such the soft real time implementation. In many use cases like IoT, even some time-sensitive tasks in the cloud, we really need to meet hard real time requirement. Preempt-RT Linux patch can convert mainline Linux to be preempt-able. Here we will review together how we can integrate Preempt-RT Linux patches to make sure Linuxkit can build out Real Time Linux for container. This can help us deploy different Linux/Docker onto the resource constrained IoT Gateway. In addition, I hope we can discuss if-how we can tune Real Time Configuration in the case of Docker.

Speakers
avatar for Tiejun Chen

Tiejun Chen

Tech lead, VMware
Tiejun Chen is Sr. technical leader from VMware OCTO, also strategic Representative of RISC-V International TSC 2023. He's been working on a lot of areas - cloud native, edge computing, ML/AI, RISC-V, WebAssembly, etc. He ever made many presentations at kubecon China 2021, Kube Edge... Read More →


Monday June 25, 2018 11:30 - 12:10 CST
306A
  IoT & M2M

11:30 CST

Torwards a more Scalable KVM Hypervisor - Wanpeng Li, Tencent Cloud
The KVM hypervisor is at the core of cloud computing, Virtual Machine based approaches to workload consolidation, as seen in IaaS cloud as well as datacenter platforms, have long had to contend with performance degradation caused by synchronization primitives inside the guest environments. These primitives can be affected by virtual CPU preemptions by the host scheduler that can introduce delays that are orders of magnitude longer than those primitives were designed for. In this presentation, Wanpeng Li will discuss the features which he introduced to KVM can eliminate TLB Shootdown Preemption influence.

Speakers
avatar for Wanpeng Li

Wanpeng Li

Linux Kernel Contributor, Tencent Cloud
Wanpeng Li is a 9 years experienced Linux kernel/virtualization developer who works in Tencent Cloud currently. He mainly focuses on KVM, scheduler and memory management. In KVM, he contributes a lot of features to improve performance and stability. He has worked in the IBM LTC kernel... Read More →


Monday June 25, 2018 11:30 - 12:10 CST
203AB
  KVM

11:30 CST

System Memory QoS Challenges - Oliver Yang, Alibaba Cloud
System memory resource is a key system performance aspect. Because of nature of memory resource management in OS kernel, there is always a tradeoff between utilization and QoS. By increasing the memory utilization, memory QoS problems could be more easily triggered by inadequate capacity planning,unexpected software working-set or workload changes, or software and hardware contentions among the applications co-located in the same system. This talk will give a brief introduction to the various memory QoS challenges found in Alibaba Cloud, related to memory utilization, memory QoS, memory errors. It also gives detailed analysis and possible solutions for these issues.

Speakers
avatar for Oliver Yang

Oliver Yang

Staff Engineer, Alibaba Cloud
About Oliver Yang Oliver Yang, a Linux system and performance engineer in Alibaba Cloud. He has rich working experiences in system software, server and storage industry. Before joining Alibaba Cloud, he worked for EMC, Oracle, Sun Microsystem as a kernel developer. Currently, his... Read More →


Monday June 25, 2018 11:30 - 12:10 CST
307B
  Linux Systems

11:30 CST

Empowering Container-Based NFV Infrastructure with VPP on Arm Architecture - Trevor Tao & Song Zhu, Arm (slides attached)
The presentation will show a reference design of containerized VNFs with VPP integration on Arm-based NFV infrastructure. Kubernetes is used as VIM to deploy Docker cluster for OPNFV platform. DPDK is used to accelerate containerized VNFs, meanwhile, the VPP vhost-user interfaces are used to create an L2 bridge and VxLAN overlay to connect between containers, which can be on the same host or different hosts. The design ensures high throughput performance for VNFs, as well as provides high scalability. The whole deployment process for container networking with VPP on Arm platform would be demoed.

This presentation will be useful for an audience who want to understand the progress of NFV on Arm and who have the plan to deploy their containerized NFV solutions on Arm architecture.

Speakers
avatar for Trevor Tao

Trevor Tao

Staff Software Engineer, Arm
Trevor Tao(Zijin Tao) is a Ph.D in Computer Networking, who has worked in this area for more than 15 years. He has worked as a network engineer in research institute of university for more than 10 years. Then he worked in IBM for almost 5 years for SDN and Cloud Networking. Now he... Read More →
SZ

Song Zhu

Senior Software Manager, Arm



Monday June 25, 2018 11:30 - 12:10 CST
311B

11:30 CST

The Evolution of the Open Source Software Foundation - Stephen R. Walli, Microsoft
Non-profit organizations have played a key role in the evolution of the open source ecosystem over the past 30 years. While each of the organizations has been created to address a particular need or constituency, they all provide a strong base to enable the next wave of growth and investment in successful, maturing open source projects in the wild. Over the past decade, corporations have begun to engage more in collaborations and look to non-profit organizations to act as the point of cooperation to encourage growth and investment in new projects. With that difference in mind, the presentation looks at what evolution is needed to support the differences and challenges to be managed (with examples) to continue to grow a strong open source ecosystem.

Speakers
avatar for Stephen Walli

Stephen Walli

Principal Program Manager, Microsoft
I'm a principal program manager at Microsoft in the Azure Office of the CTO. I've worked with Docker, been a Distinguished Technologist at Hewlett-Packard, technical director at the Outercurve Foundation, founded a start-up, and been a writer and consultant. I've been around open... Read More →


Monday June 25, 2018 11:30 - 12:10 CST
310
  Open Source Leadership

12:10 CST

Lunch
Monday June 25, 2018 12:10 - 13:20 CST
Plenary Hall A

12:10 CST

Sponsor Showcase
Monday June 25, 2018 12:10 - 17:20 CST
Plenary Hall A

13:00 CST

Office Hours: Kevin Huang, Director of Licensing, Open Invention Network
Speakers
avatar for Kevin Huang

Kevin Huang

Director of Licensing, Open Invention Network
Kevin Huang joined Open Invention Network in 2015 to promote patent non-aggression community for Linux System. Before joining OIN, Kevin Huang was responsible Canonical service business in Asia to promote Ubuntu Linux system. OIN’s community practices patent non-aggression in... Read More →


Monday June 25, 2018 13:00 - 14:00 CST
Level 3, Parkview Foyer

13:20 CST

Panel: How LFDL Driving Open Source Innovation in AI & Deep Learning in China - Moderated by Keith Chan, Linux Foundation APAC
The Linux Foundation has recently launched the LF Deep Learning Foundation.  It is a project of The Linux Foundation that supports open source innovation in artificial intelligence, machine learning, and deep learning. LF Deep Learning was created to support numerous technical projects within this important space.  With LF Deep Learning (LFDL), members are working to create a neutral space for harmonization and acceleration of separate technical projects focused on AI, ML, and DL technologies.
This panel session will bring AI leading companies in China to discuss how AI and LFDL drive their technologies, business, and strategies. The panelists will share different AI-related use cases, investments, best practices, and challenges. There will be a discussion about how AI can bring a brilliant future in China and how LFDL can facilitate achieving it.

Moderators
avatar for Keith Chan

Keith Chan

Director of Strategic Planning, Linux Foundation APAC

Speakers
avatar for xiaoli jiang

xiaoli jiang

GM, HUAWEI
Jiang Xiaoli is the General Manager of Cloud Open Source Ecosystem, Huawei. He is responsible for Huawei Cloud's open source management and ecosystem development.He joined in Huawei in 1999 and has more than 16 years' experience in the ICT industry. He has taken the manager positions... Read More →
avatar for Xiangang Li

Xiangang Li

DIDI Voice Technology Leader (滴滴语音技术负责人)
Mr. Li Xiangang, Head of Didi Voice, has been engaging in the research of speech recognition, speech synthesis, and speaker recognition. He participated in the Blizzard 2013 International Speech Synthesis Competition and he created the best English speech synthesis system during the... Read More →
avatar for Mingjun SUN

Mingjun SUN

Head of the Artificial Intelligence department of CAICT, China Academy of Information and Communication Technology
Ms SUN Mingjun, works at China Academy of Information and Communication Technology (CAICT), has more than ten years experiences in the area of ICT Standardization. She’s now head of the Artificial Intelligence department of CAICT, general group leader of Artificial Intelligence... Read More →
avatar for Tan Zhongyi (Jerry Tan)

Tan Zhongyi (Jerry Tan)

Open Source Program Officer, Baidu
OSPO of Baidu.Inc,Over 20 years working experience with OSS,committer of Mozilla/Gnome/Apache,Speaker of OSCON/ApacheCON/Open Source Summit, Contributor of OpenChain projectLinux Foundation Authorized Instructor for CKA/CKAD
avatar for Dr. Xiaolong Zhu

Dr. Xiaolong Zhu

Senior AI Architect of Tencent and Member of LF Deep Learning TAC, Tencent
Dr. Xiaolong Zhu is a senior AI architect of Tencent and Member of LF Deep Learning TAC. Xiaolong Zhu engages in deep learning related application research and development. He has participated in the distributed training of speech recognition, art filter, gesture recognition and other... Read More →


Monday June 25, 2018 13:20 - 14:00 CST
311A

13:20 CST

All About That Base - Keeley Erhardt, Improbable (slides attached)
Microservice architectures promise to deliver flexibility and scalability to the development and deployment of service-based applications. With these obvious benefits, however, comes the difficulty and operational complexity of managing a distributed system. In this presentation, we will cover why building production services is hard, and how Improbable has tackled the problem through a new project designed to unify services' common functionality in a single base server. We will discuss how developing microservices utilizing a common base server has reduced development time and led to more stable and reliable systems at Improbable, and how you can use the strategy to achieve similar benefits in your own systems.

Speakers
avatar for Keeley Erhardt

Keeley Erhardt

Software Engineer, Improbable
Keeley is a software engineer at Improbable, a London-based tech company focused on enabling massive-scale simulation. She graduated from MIT with a B.S. and an M.Eng in Computer Science. Keeley is passionate about distributed systems and open source and has contributed to a variety... Read More →



Monday June 25, 2018 13:20 - 14:00 CST
309B

13:20 CST

State of Serverless - Doug Davis, IBM (slides attached)
Serverless and FaaS computing are gaining in popularity to easily create microservice applications. In this talk we will discuss what are the characteristics of serverless, the status of the serverless working group within the CNCF and the new CloudEvents specification they’re working on, as well as the open source options available for running serverless and associated services with a focus on Kubernetes.

Speakers
avatar for Doug Davis

Doug Davis

PM Microservices, Microsoft
Doug is currently focusing on improving the developer experience for cloud native computing in Azure Cloud. He’s been working on Cloud related technologies for many years and has worked on many of the most popular OSS projects, including OpenStack, CloudFoundry, Docker, Kubernetes... Read More →



Monday June 25, 2018 13:20 - 14:00 CST
309A

13:20 CST

Automation to Make OSS License Compliance Easier - Kate Stewart & Greg Kroah-Hartman, The Linux Foundation
Until now, the software industry has been treating compliance with open source licenses as something to worry about when a product is ready to ship, and relying on more and more sophisticated tooling and heuristics to guess what the license is. Code sharing between projects (with different licenses!) has become common and enables much innovation, but causes the license detection problem to only get worse. More resources (tooling, people, time) are needed to figure out the licensing to comply with the terms of open source licenses.

In this session, we’ll look at the the Linux kernel which while it has a LICENSE file indicating it is GPL-2.0-only, actually has over 80 licenses, expressed over 1000+ ways. We’ll go through a simple solution that is being applied at the source code level in the Linux kernel to remove the guesswork from the tooling, and to simplify the analysis. This technique can be applied to any open source project. This will take us significantly closer to the goal that for every build, you know the licenses that apply (via a simple ‘grep” if you prefer) and can easily and automatically generate the artifacts to comply with those licenses.

Speakers
avatar for Greg Kroah-Hartman

Greg Kroah-Hartman

Fellow, Linux Foundation
Greg Kroah-Hartman is among a distinguished group of software developers who maintain Linux at the kernel level. In his role as a Linux Foundation Fellow, he continues his work as the maintainer for the Linux stable kernel branch and a variety of subsystems while working in a fully... Read More →
avatar for Kate Stewart

Kate Stewart

Senior Director of Strategic Programs, Linux Foundation
Kate Stewart is a Senior Director of Strategic Programs, responsible for Embedded and Open Compliance programs. Since joining The Linux Foundation, she has launched Real-Time Linux, Zephyr Project, CHAOSS, and ELISA.


Monday June 25, 2018 13:20 - 14:00 CST
306B
  Emerging Technologies & Wildcard

13:20 CST

Building on Web of Things : Make Your IoT Accessible, Open and Secure using Javascript - Rabimba Karanjai, Mozilla
The IoT is a system of physical objects connected to the Internet that can be discovered and interacted with. What IoT was supposed to be. Instead what we have is
- Vertical stacks
- Don’t talk to each other
- Per-vendor integrations

Like the Internet before the world wide web with competing for hypertext systems and proprietary GUIs from AOL and CompuServe

In this talk, we take a step back and apply lessons learned from the World Wide Web to the IOT. WoT is not another vertical IoT technology stack to compete with existing platforms
It is a unifying horizontal layer to bridge together underlying IoT protocols.

In this talk, I introduce you to Mozilla “Project Things”, with the goal of building a decentralized ‘Internet of Things’ that is focused on security, privacy, and interoperability.

Speakers
avatar for Rabimba Karanjai

Rabimba Karanjai

Researcher, Mozilla
Rabimba Karanjai is a full time graduate researcher, part time hacker and FOSS enthusiast. He is working with Mozilla Research Mixed Reality team on WebVR. He also is a Mozilla TechSpeaker and would love to chat with you on VR,AR,Security and openweb over a cup of coffee or bottle... Read More →


Monday June 25, 2018 13:20 - 14:00 CST
306A
  IoT & M2M

13:20 CST

Crypto as Service: A New All-inclusive VIRTIO-CRYPTO Acceleration Solution Based on DPDK and DPDK Cryptodev - Fan Zhang & Xin Zeng, Intel
Multi-tenant public cloud tenants nowadays have the increasing demand for cryptographic service to secure their applications. Virtio-Crypto device proposed to the community as a cloud-friendly virtual device, lacks a high-performance acceleration method in both frontend and backend.

To solve this challenge, we propose an all-inclusive Virtio-Crypto acceleration solution based on DPDK and DPDK Cryptodev Framework. The solution is composed of a backend DPDK vhost-crypto extension as well as a frontend DPDK Virtio crypto PMD. We will present this solution in detail including the utilization of the techniques such as burst-operation, polling mode Virtio queue access, zero-copy, and DPDK Cryptodev Framework including scheduler PMD, and the significant performance gain achieved. We will also describe the possible use cases this solution may help achieve in the cloud-based crypto applications.

Speakers
XZ

Xin Zeng

Software Engineer, Intel
Xin Zeng is a software engineer of Network Platform Group at Intel Data Center Group. He is now working on virtualization projects for Intel QuickAssist Technology product. Intel QuickAssist Technology can be used to handle compute-intensive security and compression operations that... Read More →
avatar for Fan Zhang

Fan Zhang

Senior Software Engineer, 3M
Fan Zhang is a Senior Software Engineer at 3M Digital Science Community Ireland.


Monday June 25, 2018 13:20 - 14:00 CST
203AB
  KVM

13:20 CST

The Implementations of Anti-Pages Fragmentation in Linux Kernel - Hui Zhu, HyperHQ Inc.
This presentation will introduce why Linux kernel needs anti pages fragmentation and the implementations of anti pages fragmentation in Linux kernel.

Speakers
avatar for Hui Zhu

Hui Zhu

Software Engineer, HyperHQ Inc.
Hui ZHU has more than 10 years experience in open source projects. For example GDB, Linux kernel.


Monday June 25, 2018 13:20 - 14:00 CST
307B
  Linux Systems

13:20 CST

13:20 CST

Complex Made Simple: The State of Governance in Open Source - Shane Martin Coughlan, The OpenChain Project (slides attached)
Clear governance, a shared understanding of process and rules, is key to the success of open source adoption at scale. Our global community represents many perspectives, many cultures, and many jurisdictions. To address these we have seen the emergence of overarching principles, practical guides and effective tools that support the necessary balance of flexibility and shared trust. This talk will focus on the key open source solutions that address real-world challenges. It will highlight a stack of solutions that includes OpenChain, SPDX, Reuse.Software, FOSSology, ScanCode, sw360, ClearlyDefined and QuarterMaster and explain how they work together at a high level (e.g OpenChain standard) to practical tooling (e.g QuarterMaster CI/CD).

Speakers
avatar for Shane Coughlan

Shane Coughlan

OpenChain General Manager, Linux Foundation
Shane Coughlan is an expert in communication, security and business development. His professional accomplishments include spearheading the licensing team that elevated Open Invention Network into the largest patent non-aggression community in history, establishing the leading professional... Read More →



Monday June 25, 2018 13:20 - 14:00 CST
310
  Open Source Leadership

13:20 CST

TARS: Open Source Microservice Architecture From Tencent - Zhong Ke, Tencent
The idea of micro-service architecture is being adopted by an increasing number of companies. How to put this idea into practice in production environment becomes a critical problem for system designers. Tars gives designers Tencent's solution. After being used in production environment for more than ten years, Tars is open-sourced. In this tutorial, the audience will learn the technical principles of Tars and how it works. Case studies and the future of Tars is also introduced.

Speakers
ZK

Zhong Ke

Senior Technical Expert, Tencent


Monday June 25, 2018 13:20 - 14:00 CST
VIP4-3

13:20 CST

Introduction to Serverless Containers - Ria Bhatia, Microsoft
Kubernetes has won the orchestration war but now how to developers build production ready code with Kubernetes? Standalone Kubernetes still requires a layer of management and Kubernetes alone isn’t the answer developers are looking for. Virtual Kubelet is an open source project that takes away operational hardships for developers so they can continue to focus on building great apps rather than fumbling with infrastructure they shouldn’t have to care about.

This is where containers fill the gap for flexibility, scalability, light-weight infrastructure matched with a per-second billing model, customers get exactly what they pay for. Azure Container Instances and other pods as a service platforms like Hyper.sh is the story for flexible billing, instant compute power and efficiency within the cloud. This changes the game for deploying infrastructure.

Speakers
avatar for Ria Bhatia

Ria Bhatia

Program Manager, Independent
Ria Bhatia was a Program Manager for Upstream Azure Compute within Microsoft. She's been working with the community on different ways to scale in Kubernetes and operate Kubernetes. She actively maintains Virtual Kubelet and has spoken at multiple meetups and conferences, including... Read More →


Monday June 25, 2018 13:20 - 14:50 CST
307A
  Infrastructure & Automation

13:20 CST

JStorm Based Network Analytics Platform - Biao Lyu, Alibaba Cloud (slides attached)
The fast growing scale and complexity of data centers brings huge challenges to network analytics. To understand how network operates, huge amount of network metrics needs to be processed timely. Apart from that, new network topology could be built at any time, hence the analytic needs to be nimble to adapt these changes.

This tutorial will introduce a JStorm based solution to analyze network in real-time. An application based on JStorm is built to consume huge amount of network metrics data as stream. To handle the complexity of analysis, an analytic modeling system is built to work with the JStorm application so that dimension or topology could be recognized on the fly. The analyzed stream data is then sent to batch-data-processing system for further analysis such as high-level statistics or OLAP.

Speakers
LB

Lv Biao

Staff Engineer, Alibaba
Alibaba Cloud Senior Techinical Manager, reponsible for Alibaba Cloud network data-driven operation and management platform Qitian. Before he joined Alibaba, Biao has been working in Microsoft Windows team, specialized in virtual machine and virtual networking. Alibaba Cloud is a... Read More →



Monday June 25, 2018 13:20 - 14:50 CST
311B

14:00 CST

14:00 CST

Office Hours: Gavin Guo, Engineering Technical Lead, Canonical
Speakers
avatar for Gavin Guo

Gavin Guo

Engineering Technical Lead, Canonical
Gavin Guo is a Linux kernel developer in the Ubuntu community. He is the speaker of 2016 China Linux Kernel Conference. He is now working for Canonical in the Customer Success division. He is responsible for the kernel stability and performance tuning of the OpenStack platform especially... Read More →


Monday June 25, 2018 14:00 - 15:00 CST
Level 3, Parkview Foyer

14:00 CST

Office Hours: Morgan Bauer, Software Engineer, IBM Corp.
Things I can speak about:
  • Open Source Participation - https://developer.ibm.com/code/open/
  • Docker - http://docker.io/
  • Kubernetes - https://kubernetes.io/
  • Service-Catalog - http://svc-cat.io/
  • Open Service Broker API - https://www.openservicebrokerapi.org/

Speakers
avatar for Morgan

Morgan

Sr Software Engineer, IBM
After contributing to Docker & Kubernetes for 3 years, Morgan has gained valuable insight into the varying culture around open source container technology. Pivoting towards blockchain technologies has landed Morgan in Hyperledger Fabric. Morgan is a maintainer on the core Docker Engine... Read More →


Monday June 25, 2018 14:00 - 15:00 CST
Level 3, Parkview Foyer

14:00 CST

Office Hours: Swetha Repakula, Open Source Developer, IBM
Things I can talk about:
Hyperledger Fabric + EVM Integration
Cloud Foundry

Speakers
avatar for Swetha Repakula

Swetha Repakula

Open Source Contributor, IBM
Swetha Repakula is currently a software engineer at IBM’s Open Technologies and a member of the Technical Steering Committee at Hyperledger. For the last two years, she has been working on Hyperledger Fabric, specifically on its EVM integration. Previously she was a full time open... Read More →


Monday June 25, 2018 14:00 - 15:00 CST
Level 3, Parkview Foyer

14:10 CST

Rebuild the Spark Engine to Support Data CRUD and Stored Procedures, Replacing Traditional Enterprise Data Warehouses - Zhang Chengsong, Lenovo
In a traditional enterprise, relational databases such as Oracle, SQL Server, DB2, Mysql are widely used. there are lots of data CRUD and stored procedure usage scenarios in their business system. With the increase of business data, these relational databases are difficult to meet the daily business requirements. How to provide a more efficient data platform for these traditional relational databases and how to quickly and smoothly migrate these old services to the data platform has become an urgent problem to be solved in the technical transformation of traditional enterprises. This topic describes how to extend the Spark engine on big data platforms to implement data CRUD and stored procedures to meet the needs of data warehousing in the context of big data, achieving enterprise Internet transformation.

Speakers

成松 张

大数据技术总监, 联想
Zhang Chengsong, Lenovo big data technical director, Lenovo big data chief architect, Lenovo big data pioneer, senior Internet technologist, once served as architect in Baidu. He personally led the team to establish the Lenovo big data platform of 10 IDC and thousands of nodes around... Read More →


Monday June 25, 2018 14:10 - 14:50 CST
311A
  AI & Deep Learning

14:10 CST

BoF: Embedded Applications with Debian - Jaminy Prabaharan
Debian is widely used in many embedded application. For example, Raspbian on Raspberry pi and Debian for BeagleBone Black. I'll be sharing my experience on embedded application using Debian.

Speakers
J

Jaminy

Engineer, N/A


Monday June 25, 2018 14:10 - 14:50 CST
307B

14:10 CST

Introduction to Container Security - Thomas Cameron, Red Hat
Application containerization is one of the coolest technologies in IT. It solves numerous problems, allows for incredible application density, and can really increase flexibility and responsiveness. But not everyone understands what makes up container security - it's a LOT more than what application is in the container.

In this session, Red Hat’s Thomas Cameron will talk about the basic components of container security. He'll talk about kernel namespaces, Security Enhanced Linux, Linux control groups, the Docker daemon, etc. and how they all work. He'll provide demonstrations of how each of these technologies affects security.

He'll also talk about tips and tricks for planning a secure container environment, describe some “gotchas” about containers, and debunk some of the security myths about containers.

Attendees will understand the fundamentals of container security when they leave.

Speakers
avatar for Thomas Cameron

Thomas Cameron

Senior Principal Cloud Engineer, Red Hat
Thomas Cameron is a senior principal cloud engineer at Red Hat. He has been in the information technology industry since 1993, and has been at Red Hat since 2005. Thomas is a Red Hat Certified Architect (RHCA) specializing in cloud technologies.


Monday June 25, 2018 14:10 - 14:50 CST
309B

14:10 CST

Apache OpenWhisk 101 - A Cloud-Native, Open Source, Serverless Platform Incubating at the ASF - Ying Chun (Daisy) Guo, IBM China Development Lab (slides attached)
The open source Apache OpenWhisk project (supported by IBM, Adobe, Red Hat, and others) provides a scalable and polyglot serverless platform for deploying cloud-native applications driven by data, message, and REST API call events. At this talk, you'll find out why serverless architectures are attractive for many emerging cloud workloads and when to consider OpenWhisk in particular for your next web, mobile, IoT, bot, or analytics project. You'll understand the architecture, installation, programming model, community status of OpenWhisk. You will also see how the resiliency and container lifecycle models compare against Platform-as-a-Service (Cloud Foundry) and container orchestration (Kubernetes) environments. Demos at this session include integration with public cloud services based on Apache Kafka (message streams), Apache CouchDB (NoSQL data), and LoopBack/OpenAPI (REST APIs).

Speakers
avatar for Ying Chun Guo

Ying Chun Guo

Software Engineer, IBM
Ying Chun Guo, known as “Daisy”, is an open source developer in IBM China development lab. She has several years experiences in open source communities, starting from OpenOffice, then OpenStack, and recently serverless platforms Apache OpenWhisk and Knative. Now she concentrates... Read More →



Monday June 25, 2018 14:10 - 14:50 CST
306B

14:10 CST

Retrofitting Memory Protection in the Zephyr OS - Wayne Ren & Huaqi Fang, Synopsys (slides attached)
Modern microcontrollers offer mechanisms to protect memory regions from being inadvertently accessed, either by programmer error or by malice. Until recently, Zephyr was not making use of it. This talk will present the work performed to retrofit memory protection in the Zephyr kernel, discussing the constraints, design decisions (affecting portability, security, and performance), its current state, and the next steps. We will discuss details on a novel method of tracking and validating kernel objects, techniques for defining system calls with a minimal amount of boilerplate code, details on our APIs for managing memory permissions, and details on the implementation of the protection feature for the ARC architecture.

Speakers
avatar for Wayne Ren

Wayne Ren

Software R&D manager, Synopsys
Wayne Ren is a senior software engineer at Synopsys and located at Wuhan, P.R. China. He is one of the maintainers for the ARC architecture in Zephyr, the architect of embARC project, special member of TOPPERS project, and contributor of several other open source project. His expertizes... Read More →

华启 方

高级研发工程师, Synopsys



Monday June 25, 2018 14:10 - 14:50 CST
306A
  IoT & M2M

14:10 CST

Using Docker in QEMU Testing - Fam Zheng, Red Hat (slides attached)
The QEMU project has adopted a Docker-based approach to run tests since a few years ago, and it works! In this talk, Fam will review this experience and explain why and how we did that, covering the interesting details, the benefits and the challenges we have had. He will then summarize how the tight integration of Docker-based testing, especially for Continuous Integration purposes, could apply generically to other projects.

Speakers
FZ

Fam Zheng

Senior Software Engineer, Red Hat
Fam Zheng is a senior software engineer in the Red Hat virtualization team. He worked on various aspects of QEMU and KVM in past years, and is now focused on VirtIO and block performance. and is a maintainer for a number of components of QEMU. Previously he has presented Userspace... Read More →



Monday June 25, 2018 14:10 - 14:50 CST
203AB
  KVM

14:10 CST

Bringing an Open Source Project to The Linux Foundation - Chris Aniszczyk, Cloud Native Computing Foundation (slides attached)
Speakers
avatar for Chris Aniszczyk

Chris Aniszczyk

CTO, Linux Foundation (CNCF)
Chris Aniszczyk is an open source executive and engineer with a passion for building a better world through open collaboration. He's currently a CTO at the Linux Foundation focused on developer relations and running the Open Container Initiative (OCI) / Cloud Native Computing Foundation... Read More →



Monday June 25, 2018 14:10 - 14:50 CST
310
  Open Source Leadership

14:10 CST

TARS Promoting Open Source Community - Chen Jiancong, Tencent
The Java programming language is a popular choice for implementing an internet service, that's the same in tencent MIG. We will review the implementation process of the micro-service architecture in internet service implement by java. Strategies and Case of the integration development of TARS and open source community.

Speakers
CJ

Chen Jiancong

Senior Technical Engineer, Tencent


Monday June 25, 2018 14:10 - 14:50 CST
VIP4-3

14:30 CST

15:00 CST

Introduction of Apollo - The Open Source Autonomous Driving Platform - Jie Liu, Baidu
This talk will mention the progress of Apollo open source platform as well as the developer community. Based on that, will present the architecture design and core modules, includes the deep learning technology applied in some critical scenarios.

Speakers

杰 刘

Principal R&D Architect, Baidu Inc.


Monday June 25, 2018 15:00 - 15:40 CST
311A

15:00 CST

Building Extensible Application Orchestration System with Helm - Deyuan Deng & Jun Zhang, Caicloud (slides attached)
Kubernetes has a large number of primitives to support container management, and also a helm ecosystem to help package these primitives into a single, deployable unit. The primary focus of helm is to provide an out-of-box solution for application package, as well as a unified experience for orchestrating and deploying charts. This architectural design choice makes helm less developer friendly and thus hard to build extensions on top of it. To remedy the problems, we built a release controller on top of helm, and a set of third-party systems around the controller. In this talk, we’ll first show how we use helm to manage all of our applications; then talk about the details of the problems we’ve encountered and how we tackle the problems using the release controller. We’ll also describe the unique properties of the design and how we equip it with all different kinds of extensions.

Speakers
YR

Yuquan Ren

Senior Software Engineer, Bytedance
Yuquan Ren is a senior software engineer at Bytedance focusing on kubernetes related work. 任玉泉现就职于字节跳动,主要从事和 kubernetes 相关的设计和开发工作。
JZ

Jun Zhang

Caicloud
Jun Zhang is currently cloud open source software engineer of Caicloud(https://caicloud.io). He also leads the research and development in application orchestration, configuration distribution, load balancing whithin Kubernetes ecology.


rudder pdf

Monday June 25, 2018 15:00 - 15:40 CST
309B

15:00 CST

Apache Pulsar: How a Segment-Oriented Architecture Delivers Better Performance - Jia Zhai, Streamlio (slides attached)
This talk introduces Apache Pulsar, a durable, distributed messaging system. Pulsar uses Apache BookKeeper as its storage layer for message persistence. In this talk, Jia will discuss how this layered architecture allows Pulsar to achieve a high level of scalability and performance. In particular, It will cover:

- Pulsar’s segment oriented architecture. This architecture allows easy elasticity for your messaging cluster without having to do cumbersome rebalancing operations.
- The benefits that this segment oriented architecture brings.
- A benchmark of throughput and latency of Pulsar messaging system.

In short, this talk will be a deep dive into the storage internals of a large scale, production validated distributed messaging system.

Speakers
avatar for Jia Zhai

Jia Zhai

Consultant Software Engineer, Streamlio
Jia is the core engineer of Streamlio, a company focused on building next generation real time processing engines. Streamlio mainly focus on 3 open source projects, which include Apache BookKeeper, Apache Pulsar, and Heron. Before Streamlio, Jia was the Principal Engineer at EMC Beijing... Read More →



Monday June 25, 2018 15:00 - 15:40 CST
306B

15:00 CST

Fast Iteration of Linux Kernel on Millions of Systems: Challenge and Practice @Alibaba - Juexiao, Alibaba
Currently, Alibaba is deploying Linux 4.x based kernel version on all systems, multiple iterations are made within one year to benefit from latest kernel improvement and bugfixes. As a huge Internet and cloud company, there are thousands of business applications running on millions of systems with a very strict requirement on reliability, it is a big challenge to make the process smooth and rapid in such a short period.

In this talk, Juexiao will show best practices of kernel CI/CD in Alibaba, and focus on highlights and innovations how it differs from traditional kernel quality assurance, integration, release, and deployment process, how to make it seamless and efficient in a large-scale cluster production environment, and what kind of challenge are being faced.

Speakers
Y

晓海 石

高级专家, 阿里巴巴集团
Juexiao is a veteran in Linux/Unix kernel development and test area. Currently he is leading kernel CI/CD program and quality infrastructure development in Alibaba OS department. Prior to that, he served for Oracle and Sun microsystem as a principle engineer, where he was a technical... Read More →


Monday June 25, 2018 15:00 - 15:40 CST
307A
  Infrastructure & Automation

15:00 CST

Haier Cosmoplat (First National-Class Industrial Internet Platform) Deep Dive and its Implementation - Hongbing Zhang, DaoCloud & Ding Ping Zhang, Haier Digital
As China largest home appliance maker, Haier is building its world's largest mass customized solution platform (Cosmoplat) and Cosmoplat was named as first national-class industrial internet platform approved by the National Development and Reform Commission.

To build a national wide large-scale system, Cosmoplat embraced various cutting-edge open source technologies like container/devops/microservice to provide all kinds of capabilities including: fast cloud native app development and whole life-cycle management, industrial middleware, services like big data analytics/IoT/blockchain/AI, etc...

In this session, Hongbing from DaoCloud and Bin from Haier will give a detailed introduction and tech deep dive about Cosmoplat, and address how to design and use open-source technologies together with our optimization and thinkings in the process of building Cosmoplat.

Speakers
avatar for Qiang Mei

Qiang Mei

Technical Architect, DaoCloud
QiangMei is technical Architect of DaoCloud, he led team to successfully enable quite a few top companies' digital transformation using cloud native technologies. Recently he engaged deeply in industrial IOT area.

定平 张

高工, 海尔数字科技有限公司


Monday June 25, 2018 15:00 - 15:40 CST
306A
  IoT & M2M

15:00 CST

VFIO Device Assignment Quirks and How to Avoid Them in Your Hardware - Alex Williamson, Red Hat (slides attached)
In order to assign a peripheral I/O device to a virtual machine, the device needs to be isolated from the host and aspects of the hardware may need to be virtualized for transparency to the guest. Some devices and platforms are better at this than others. Adherence to specifications and creative backdoors through hardware can present challenges to device assignment. In this presentation, Alex Williamson will provide case studies through various examples of troublesome configurations and the workarounds, or quirks, that are sometimes employed to enable them. These quirks are however not without pitfalls and can impose performance, maintenance, functionality, and time-to-market downsides. The goal of this talk is to share some of these common issues, expose the quirks available as workarounds, and discuss how they can be avoided entirely with well-informed hardware design.

Speakers
avatar for Alex Williamson

Alex Williamson

Sr Principal Software Engineer, Red Hat
Alex Williamson is a Senior Principal Software Engineer with Red Hat, maintainer of VFIO, Linux’s secure userspace driver framework, for both the kernel and QEMU components, and regular contributor to the Linux kernel IOMMU and PCI subsystems. Alex has given previous talks on VFIO... Read More →



Monday June 25, 2018 15:00 - 15:40 CST
203AB
  KVM

15:00 CST

The Flavors of Memory Supported by Linux, their Use and Benefit - Christoph Lameter, Jump Trading LLC (slides attached)
In recent years the types of memory supported by the Linux Operating system have multiplied. In addition to DRAM and NUMA systems we now have various forms of non volatile RAM, Memory areas on accelerators (f.e. on GPU, ManyCore and FPGAs) and more is on the horizon. This talk gives an overview of the memory technologies available, shows the advantages and explains how such memory is managed and handled in Linux.

Speakers
avatar for Christoph Lameter

Christoph Lameter

R&D Team Lead, Jump Trading LLC
Christoph Lameter is working as a lead in research and development for Jump Trading LLC (an algorithmic trading company) in Chicago and maintains the slab allocators and the per cpu subsystems in the Linux Kernel. He contributed to a number of Linux projects since the initial kernel... Read More →



Monday June 25, 2018 15:00 - 15:40 CST
307B
  Linux Systems

15:00 CST

Large-Scale RDMA Inside Alibaba Cloud: Challenge, Solution and Value in Data Center - Li Qiang, Alibaba
Due to low latency and high bandwidth with congestion, RDMA is adopted by many services of Alibaba Cloud, such as storage, HPC and so on. Compared to developed TCP in Linux kernel, developing RDMA in userspace encounters many challenges. First of all, RDMA is more difficult to share and monitor in userspace, and also hard to virtualize. Then, RDMA is more sensitive to performance, failure and cluster scale. Lastly, RDMA is unfriendly to program for software developers.

In spite of these challenges, Alibaba service like Pangu Storage has deployed a large scale cluster in production and development. In the presentation, we give our opinion about these challenges in Alibaba.

Speakers

强 李

技术专家, 阿里巴巴
Li Qiang is a senior engineer in Alibaba Cloud, whose work focuses on Pangu distributed storage system for large-scale service. He received and Ph.D. degrees in Institute of Computing Technology in 2012. Since 2012, he has been an associate professor in Institute of Computing Technology... Read More →


Monday June 25, 2018 15:00 - 15:40 CST
311B
  Networking & Orchestration

15:00 CST

Is There an Open Source Business Model: YES or NO? - Jeffrey Borek, IBM & Stephen Walli, Microsoft (slides attached)
The open source definition is over 20 years old. Red Hat is a multi-billion dollar company. MySQL and JBoss have had great acquisition exits. Cloudera and Hortonworks are well on their way to becoming the next billion-dollar software companies. But Stephen would like to observe that despite these successes, there is no open source business model. 

But wait, Jeff would beg to differ! From data centers to the cloud, from self-driving cars to drones - open source software is everywhere. Major companies that are bottom-line driven are starting to actively engage and contribute to open source projects. 

Join this lively session with Stephen and Jeff as they compare and contrast the current state of the ecosystem and debate what comes next.

Speakers
avatar for Jeffrey Borek

Jeffrey Borek

WW Program Director, IBM
Working to build a scalable and consistent supply chain security platform, while continuing to lead the consumption compliance Open Source Program Office (OSPO), including policy, execution and guidance. Working with IBM Government & Regulatory Affairs, Software, Systems, Cloud, Consulting... Read More →
avatar for Stephen Walli

Stephen Walli

Principal Program Manager, Microsoft
I'm a principal program manager at Microsoft in the Azure Office of the CTO. I've worked with Docker, been a Distinguished Technologist at Hewlett-Packard, technical director at the Outercurve Foundation, founded a start-up, and been a writer and consultant. I've been around open... Read More →



Monday June 25, 2018 15:00 - 15:40 CST
310
  Open Source Leadership

15:00 CST

The Way to the TARS Container - Mei Ping, Tencent
As a microservice architecture wide used by Tencent, Tars has always kept pace with the times. This session will introduce some thoughts and practices of Tars on the containerization road.

Speakers
MP

Mei Ping

Senior Technical Engineer, Tencent


Monday June 25, 2018 15:00 - 15:40 CST
VIP4-3

15:00 CST

Office Hours: Hui Deng, Chief NFV Strategy Officer, Huawei
Speakers
avatar for Hui Deng

Hui Deng

Director, Huawei
Hui DENG obtained his Doctor degree from Dept. Computer Science and Technology at Tsinghua University in 2002. He worked as chief researcher in Hitachi (China) R&D Cooperation from 2002 to 2007, and worked as Principal staff between 2007 and 2016 in China Mobile. He joined Huawei... Read More →


Monday June 25, 2018 15:00 - 16:00 CST
Level 3, Parkview Foyer

15:00 CST

Office Hours: Lingli Deng, Senior Project Manager, China Mobile
Speakers
avatar for Lingli Deng

Lingli Deng

Technical Manager, China Mobile
Lingli obtained her Doctorate in Computer Application Technology from the Institute of Software, Chinese Academy of Sciences and joined China Mobile in 2009.She is a core member of the Novonet project which drives SDN/NFV strategy for China Mobile, and has been working on evaluation... Read More →


Monday June 25, 2018 15:00 - 16:00 CST
Level 3, Parkview Foyer

15:00 CST

Office Hours: Stefano Stabellini, Principal System Software Engineer, Xilinx
Speakers
avatar for Stefano Stabellini

Stefano Stabellini

Principal Engineer, Xilinx
Stefano Stabellini serves as system software architect and virtualization lead at Xilinx, the world's largest supplier of FPGA solutions. Previously, at Aporeto, he created a virtualization-based security solution for containers and authored several security articles. As Senior Principal... Read More →


Monday June 25, 2018 15:00 - 16:00 CST
Level 3, Parkview Foyer

15:20 CST

15:30 CST

15:50 CST

Akraino: A Technical Overview - JF Ding, Intel (slides attached)
In the past decade, there has been a concerted effort among companies to move infrastructure to centralized clouds, enabled by virtualization. With the rise of IoT and explosion of device-generated data, the pendulum has begun to swing the other way, placing resources for analytics and specialized functions near the user end of the network.  IoT and 5G use cases demand performance determinism of computing, high network throughput with low latency and highly available services at the edge. The reach of these edge nodes will expand over the coming years as carriers update to 5G, amplifying the need for hardened infrastructure services. The Akraino Edge Stack aims to address this model of computing. 

Attend this session for an overview of the Akraino Edge Stack’s architecture, project organization, governance, and roadmap. You will also gain an understanding of how Akraino Edge Stack interoperates with other community projects sponsored by the Linux Foundation and OpenStack Foundation.

Speakers
avatar for JF Ding

JF Ding

Engineering Manager, Intel
Jianfeng(JF) Ding, from Open Source Technology Center of Intel Inc., is working on several open source cloud computing projects, such as OpenStack, Kubernetes, etc., as an engineering manager and technical leader.



Monday June 25, 2018 15:50 - 16:30 CST
311A

15:50 CST

Apache OpenWhisk + Kubernetes: A Perfect Match for Your Serverless Platform - Ying Chun Guo & Zhou Xing, IBM China Develop Lab (slides attached)
Serverless is a popular topic nowadays in cloud area. Some scenarios today, like IoT, web app or microservice based architecture, require using Serverless to handle requests. Apache OpenWhisk is a serverless, open source cloud platform that executes functions in response to events at any scale. Kubernetes is a well-known open-source system for automating deployment, scaling, and management of containerized applications. How well can Apache OpenWhisk and Kubernetes work together to build an enterprise level serverless platform? What are the best practices and gotchas? In this session, we will answer these questions. We will introduce how to design and deploy an Apache OpenWhisk based serverless solution over Kubernetes cluster. In addition, we want also to share some code patterns and demos on how to develop applications to this serverless platform.

Speakers
avatar for Ying Chun Guo

Ying Chun Guo

Software Engineer, IBM
Ying Chun Guo, known as “Daisy”, is an open source developer in IBM China development lab. She has several years experiences in open source communities, starting from OpenOffice, then OpenStack, and recently serverless platforms Apache OpenWhisk and Knative. Now she concentrates... Read More →
avatar for Zhou Xing

Zhou Xing

Software Engineer, IQiYi
Tom Xing, Graduated from Peking University in 2009 and joined IBM China Development Lab as a software engineer then. Tom now is working for IBM open source and open standards team and focusing on CloudFoundry project development. As an active open source contributor, Tom has great... Read More →



Monday June 25, 2018 15:50 - 16:30 CST
309A

15:50 CST

Getting Started with Logging in Kubernetes - Eduardo Silva, Treasure Data
A good practice when deploying applications in Kubernetes is to set proper instrumentation to gather insights and solve general monitoring needs. Logging is a fundamental piece of the instrumentation cycle and is continually evolving to solve pains associated with unstructured formats, performance, and monitoring.

In this presentation, you will learn the concepts involved in log processing for containerized applications. You will also be introduced to these hot new features in Logging: metering the logging pipeline with Prometheus, performance improvements, scalability and the ability to customize the log processor behavior through declarative resource annotations.

Speakers
avatar for Eduardo Silva

Eduardo Silva

Principal Engineer, Arm Treasure Data
Eduardo is a Principal Engineer at Arm Treasure Data, he is the author and maintainer of Fluent Bit Log Processor, a CNCF sub-project under the umbrella of Fluentd. He is an international speaker in Open Source conferences, he has participated in Scale California, LinuxConf AU, Linux... Read More →


Monday June 25, 2018 15:50 - 16:30 CST
309B

15:50 CST

Dubbo Open-Sourcing - Present and the Future - Liu Jun, Alibaba (slides attached)
Dubbo is a very popular open-source RPC framework with high performance and reliability. Having become an Apache Incubator gives dubbo a more active community; hope Dubbo will help increase the diversity of apache with its innovation. In this presentation, Liu Jun will give a brief introduction of the core features of Dubbo and its innovation in RPC area, review the recent events in meeting community requirements and enhancing dubbo, the challenges it faces, and the roadmap to address those challenges after entered apache community. In the end, the audience will have a glance at the amazing features expected to come soon on dubbo 3.0.

Speakers
LJ

Liu Jun

Engineer II, Alibaba
Working on middle ware dep. in Alibaba. Received master's degree from CAS in 2013. Initial committer of Dubbo project. Rich experiences in building basic infrastructures supporting distributed systems. Interested in high performance RPC, microservices and reactive.



Monday June 25, 2018 15:50 - 16:30 CST
306B
  Emerging Technologies & Wildcard

15:50 CST

How is Cloud Native Going at China Mobile? - Xuan Jia, China Mobile (slides attached)
Cloud Native concept has been accepted in telecom company. But how it is going in China Mobile? In this proposal,it will give a big picture of how many provinces are using container technology, the scale and the difficult problem we met in the past three years. From Mesos deployed in Zhejiang Province to Kubenetes deployed in many provinces, what is the challenge and how we solve the different technical stack? In China Mobile, how do we build our own PaaS and manage it in at lease 30+ data centers as each province should have their own data center to run specific services.

The cloud-native community calls 2018 the service mesh year. In this proposal, you will know how service mesh uses in China Mobile, it uses in not only web services, but also the traditional services, e.g. RCS, NFV, 5G.

Speakers
XJ

Xuan Jia

Edge Computing Architect, China Mobile
Jia Xuan , 5G edge computing platform architect in China Mobile, project manager, graduated from Tsinghua University, CNCF Ambassador. Buid 5G edge computing ecosystem, including edge application and releated technology. He has about 10 years experiences in Cloud Computing.



Monday June 25, 2018 15:50 - 16:30 CST
307A
  Infrastructure & Automation

15:50 CST

Let’s Make IoT OS Smarter in LPWA - Wang Daneng & Richard Lin, Huawei Technologies
Huawei LiteOS is an open source RTOS for IoT field. It is an IoT software stack with key capabilities such as lightweight, low power, fast startup, smart connectivity and security management. In this talk, we will introduce IoT operating system in Low Power Wide Area (LPWA), talk about the problems in this field and how we solve them with Huawei LiteOS and the technical ecosystem, industrial partners and developer community around it, such as NB-IoT solution and the APIs which offer low-power secure connectivity and access to IoT platforms (including Huawei and other IoT platforms) for terminal device vendors and developers. We also will use some real cases among meter reading, parking, street lighting, bicycle sharing and logistics to introduce. Finally, we will present our developer program for IoT and make the IoT + NB-IoT ecosystem smarter and more prosperous.

Huawei LiteOS 是一个面向物联网领域的开源实时操作系统。LiteOS 的关键特性是轻量级、低功耗、快速启动、智能传感和安全管理。本演讲中会介绍针对 LPWA 领域的物联网操作系统中所面对的问题以及如何通过 Huawei LiteOS 及其技术生态、行业伙伴及开发者社区的建设来解决,包含 NB-IoT 解决方案、LiteOS 提供的低功耗、安全连接能力和与物联网云平台的集成。本演讲也会选择实际商业落地案例来介绍不同场景下的应用情况。最后,我们将展示华为 IoT 开发者计划,让 IoT + NB-IoT 生态更加蓬勃发展。

Speakers
avatar for Richard Lin

Richard Lin

Operation Director, Huawei
Richard Lin has about 10 years experience in open source field in Mainland China and Taiwan, especial in establishing developer ecosystem, open source business model, open source intellectual property management and community governance. He currently works in Huawei Technologies... Read More →
XL

大能 王

产品总监&技术专家, 华为技术有限公司
Daneng Wang is Chief Engineer and project leader in Huawei LiteOS team. He devotes in researching and developing embedded operating system in IoT field for many years, especially in software and hardware collaboration in chip and OS, and IOT node device development. He is responsible... Read More →


Monday June 25, 2018 15:50 - 16:30 CST
306A
  IoT & M2M

15:50 CST

Storage Performance Tuning for FAST! Virtual Machines - Fam Zheng, Red Hat (slides attached)
There are many variables around how you could run your virtual machines. How to locate those that affect I/O performance of your virtual machine? What does each of these options mean and how do they relate to each other? What are the newcomers in the family and how can they help? In this talk, Fam Zheng will take you through the configuration stack of virtual storage devices, decipher the parameters and give suggestions on how to tune for the best performance on your systems.

Speakers
FZ

Fam Zheng

Senior Software Engineer, Red Hat
Fam Zheng is a senior software engineer in the Red Hat virtualization team. He worked on various aspects of QEMU and KVM in past years, and is now focused on VirtIO and block performance. and is a maintainer for a number of components of QEMU. Previously he has presented Userspace... Read More →



Monday June 25, 2018 15:50 - 16:30 CST
203AB
  KVM

15:50 CST

PRCU: A New RCU Design with Low Synchronization Latency - Heng Zhang, Huawei (slides attached)
A read-copy update is a widely used synchronization mechanism in Linux kernel. Current RCU implementation eliminates the contention and memory fence on the reading side to achieve high performance but remains long synchronization latency for updates. It's not uncommon to see high-latency reports caused by RCU write side in the Linux kernel mailing list. We provide a new RCU implementation called Passive Read-copy update which achieves relatively low synchronization latency while keeping read side fence-free. The key idea of PRCU is allowing read side to actively report on synchronization and recording an accurate list of cpus on which the threads have done read lock and haven't been scheduled out. Thus the synchronization operations only need to communicate with the unreported but recorded cpus. I'll elaborate on how PRCU works and give out some benchmark result to show how well it works.

Speakers
HZ

Heng Zhang

SoftwareEngineer, Huawei
Software Engineer, Huawei Kernel Dep. He is now working in Huawei OS kernel lab. Before that, he worked in Microsoft IAT team for ~1 year. In this project, Heng is working on basic algorithm design and implementation.


prcu pdf

Monday June 25, 2018 15:50 - 16:30 CST
307B
  Linux Systems

15:50 CST

Network Service Optimization with VPP Platform - Jianyong Chen, Alibaba Cloud (slides attached)
VPP is a popular open source network operating system. It has a solid framework to support rich functions such as Ethernet interface management, route management, IPsec, ACL, and VXLAN. When it comes to enterprise-grade services, VPP falls short in IP fragmenting, IKEv2 support and BGP support. This tutorial will discuss these issues and provide the solution for optimization.

Speakers
avatar for Jianyong Chen

Jianyong Chen

Senior Manager of Network Technology Development, Alibaba
Jianyong is Senior Manager at Alibaba Cloud in charge of SD-WAN related technology and product development. He has 10+ years of experience in the network industry in roles such as software developer, system architect, and technical team management. Jianyong is specialized in network... Read More →



Monday June 25, 2018 15:50 - 16:30 CST
311B

15:50 CST

License Information Management: A Case Study - Kate Stewart, The Linux Foundation (slides attached)
License Information Management - Case Study (Steve Winslow and Kate Stewart, The Linux Foundation): For modern open source software projects, license compliance presupposes that a developer or distributor can determine what licenses are present in a codebase. Managing, locating and maintaining license information for a large open source project is often far more complex than simply posting a single LICENSE.txt file. In this tutorial, Steve Winslow and Kate Stewart will present real-world examples to demonstrate techniques and best practices for identifying applicable licenses, handling license compatibility, and communicating license information to a project's contributors and users.

Speakers
avatar for Kate Stewart

Kate Stewart

Senior Director of Strategic Programs, Linux Foundation
Kate Stewart is a Senior Director of Strategic Programs, responsible for Embedded and Open Compliance programs. Since joining The Linux Foundation, she has launched Real-Time Linux, Zephyr Project, CHAOSS, and ELISA.



Monday June 25, 2018 15:50 - 16:30 CST
310
  Open Source Leadership

15:50 CST

Some DevOps Practices on TARS - Li ZhaoYan, Tencent
With the explosion of microservice, users benefit, but it also brings a series of service management complexity, rising problems and requirements, basic resources and environment management, Interface /common lib management, continuous integration, testing, quality and safety control, service operation and maintenance hosting, etc. Tars control platform relies on Tencent's years of experience in the management of R&D operation of distributed microservices which is a complete R&D and operational integrated management and control solution that covers the whole lifecycle of service life. At the same time, the platform embraces open source, is an open ecosystem and provides basic services in a modular manner. Users can easily choose the appropriate service modules, easy integration of self-built or other open source services, have their own business One-stop DevOps control platform quickly with low cost.

Speakers
LZ

Li ZhaoYan

Senior Technical Engineer, Tencent


Monday June 25, 2018 15:50 - 16:30 CST
VIP4-3

15:50 CST

16:00 CST

16:00 CST

Office Hours: Doug Davis, STSM, IBM
Come chat about:
- Containers
- Docker
- CloudFoundry
- Open Service Broker API
- CNCF, Serverless Working Group, CloudEvents
- Serverless - IaaS vs CaaS vs PaaS vs FaaS...
- Kubernetes & ServiceCatalog
- Standards & OpenSource
- Little League Baseball and dogs!

Speakers
avatar for Doug Davis

Doug Davis

PM Microservices, Microsoft
Doug is currently focusing on improving the developer experience for cloud native computing in Azure Cloud. He’s been working on Cloud related technologies for many years and has worked on many of the most popular OSS projects, including OpenStack, CloudFoundry, Docker, Kubernetes... Read More →


Monday June 25, 2018 16:00 - 17:00 CST
Level 3, Parkview Foyer

16:00 CST

Office Hours: Jia Zhai, Consultant Software Engineer, Streamlio
Speakers
avatar for Jia Zhai

Jia Zhai

Consultant Software Engineer, Streamlio
Jia is the core engineer of Streamlio, a company focused on building next generation real time processing engines. Streamlio mainly focus on 3 open source projects, which include Apache BookKeeper, Apache Pulsar, and Heron. Before Streamlio, Jia was the Principal Engineer at EMC Beijing... Read More →


Monday June 25, 2018 16:00 - 17:00 CST
Level 3, Parkview Foyer

16:00 CST

Office Hours: Keeley Erhardt, Software Engineer, Improbable
Speakers
avatar for Keeley Erhardt

Keeley Erhardt

Software Engineer, Improbable
Keeley is a software engineer at Improbable, a London-based tech company focused on enabling massive-scale simulation. She graduated from MIT with a B.S. and an M.Eng in Computer Science. Keeley is passionate about distributed systems and open source and has contributed to a variety... Read More →


Monday June 25, 2018 16:00 - 17:00 CST
Level 3, Parkview Foyer

16:40 CST

AI Applications at DiDi: End-to-End Speech Systems - Xiangang Li, DiDi
At DiDi, there are around 30 million rides per day, which creates very big data for AI applications. AI is widely used to provide the best-in-class ride-sharing experience and the AI strategy of DiDi is “AI for transportation”. In this talk, the AI layout and applications will be briefly introduced. About the AI applications, this talk will focus on discussing the state-of-the-art end-to-end speech technologies and their applications at DiDi.

滴滴语音技术负责人

李先刚:滴滴语音负责人,他长期从事语音识别(Speech Recognition)、语音合成(Speech Synthesis)、说话人识别(Speaker Recognition)等方向的研究。曾参与Blizzard 2013国际语音合成比赛,搭建了当时最好的英语语音合成系统,在比赛中的各个性能衡量指标上都获得了第一。加入滴滴之前,他是某著名互联网公司的语音技术部的识别技术负责人之一,参与推动了多个端对端(end-to-end)语音系统的研发,包括DeepSpeech,DeepSpeaker等。

Speakers
avatar for Xiangang Li

Xiangang Li

DIDI Voice Technology Leader (滴滴语音技术负责人)
Mr. Li Xiangang, Head of Didi Voice, has been engaging in the research of speech recognition, speech synthesis, and speaker recognition. He participated in the Blizzard 2013 International Speech Synthesis Competition and he created the best English speech synthesis system during the... Read More →


Monday June 25, 2018 16:40 - 17:20 CST
311A

16:40 CST

A Practical Introduction to Kubernetes Federated HPAs - Irfan Ur Rehman & Shashidhara, Huawei Technologies
Kubernetes supports simple workload auto-scaling within a cluster using Horizontal Pod Autoscaling (HPA). Multi-cluster Federation enables binding multiple clusters into a cluster pool to overcome limitations imposed by single cluster and cloud-provider boundaries.
Intelligent workload autoscaling across multiple clusters opens up opportunities to safely solve some hard but critically important use cases, such as automated cloud bursting from on-premises to public cloud; follow-the-sun resource migration; and failure-aware global load balancing.

This talk showcases this important new feature. We will explain the design of this feature and demonstrate some compelling new use cases.

Speakers
ST

Shashidhara T D

Senior Software Engineer, Huawei
Shashi is a senior engineer with Huawei Technologies and is currently associated with the cloud platforms team. In his current role he is part of the engineering group that works as a bridge between the kubernetes open source project and Huawei's adaptation of the same in its cloud... Read More →
IU

Irfan Ur Rehman

Sr. Software Engineer, Turbonomic
Irfan is a senior engineer associated with the Advanced Engineering group at Turbonomic. In his current role he is tasked with drafting multi cluster capabilities for Turbonomic’s analytics platform. He has also been associated with SIG Multicluster, particularly Kubernetes Cluster... Read More →


Monday June 25, 2018 16:40 - 17:20 CST
309B

16:40 CST

Introducing the Kubernetes Policy WG - Zhipeng Huang, Huawei & Xuan Jia, China Mobile
As many large organizations move business-critical workloads onto Kubernetes, they bring diverse requirements around availability, performance, security, and governance.
Over time Kubernetes has added various features to address these requirements, one of such is that let administrators configure policies such as RBAC, admission control, NetworkPolicy, (anti-)affinity, etc. While these features can be combined to address some of the requirements from large enterprises, this is largely achieved through tribal knowledge in the most advanced segment of the user base and does not cover all of the requirements.
In this talk, we will introduce the newly formed Policy WG that aims to provide an overall architecture that unifies policy features. We will show how existing Kubernetes features can be leveraged to provide fine-grained policy-based control

Speakers
avatar for Zhipeng Huang

Zhipeng Huang

Director of Open Source, Huawei
Zhipeng Huang currently serve as Director of Open Source for Huawei Compute Product line, in charge of openEuler, MindSpore and openGauss community operation. Zhipeng is now the TAC member of LFAI, TAC and Outreach member of the Confidential Computing Consortium, co-lead of the Kubernetes... Read More →
XJ

Xuan Jia

Edge Computing Architect, China Mobile
Jia Xuan , 5G edge computing platform architect in China Mobile, project manager, graduated from Tsinghua University, CNCF Ambassador. Buid 5G edge computing ecosystem, including edge application and releated technology. He has about 10 years experiences in Cloud Computing.


Monday June 25, 2018 16:40 - 17:20 CST
309A

16:40 CST

Africa's AI Story: Opportunities for Open Source Projects - Opetunde Adepoju, ladoke Akintola University of Technology
When the whole world talks about innovation in artificial intelligence they usually don't mention Africa. Let's just give them a benefit of doubt and say they forgot about Africa in artificial intelligence innovation. But they are missing out on a huge market share opportunity which abounds in Africa.

In this talk, I will tell the story of AI technologies which have been built by Africans for Africa:
- the story of kudi.ai, lara.ng, delivery science, flyzipline.

I will highlight extensively on opportunities that abound in various fields which open source projects can help solve. I will dig deeper by giving various open source project ideas and a how to build a successful business model from such projects in relation to Africa's market and culture.

Lastly, I will prove with statistics the huge benefits companies who build solutions around Africa's opportunities stand to gain

Speakers
avatar for Opetunde Adepoju

Opetunde Adepoju

Data science student, ladoke Akintola University of Technology
Opetunde is a Global Women in Data Science Ambassador, an initiative of Stanford University and a lead community manager of Facebook Data Science community in Nigeria. She started her career in data science in 2017 and has delivered a speech on data science and Africa at pycon Nigeria... Read More →


Monday June 25, 2018 16:40 - 17:20 CST
306B
  Emerging Technologies & Wildcard

16:40 CST

K8s Cluster and Application Monitoring with Prometheus - Max Leonard Inden, CoreOS
Kubernetes is a powerful system to build and operate a modern cloud-native infrastructure. Monitoring with Prometheus ensures that Kubernetes stays healthy. Prometheus is a stateful application, so operating it in a cloud native environment can be a challenging task. The Prometheus Operator makes running highly available Prometheus clusters, and even an entire end to end monitoring pipeline, easily manageable. Max will explain the functionality of the Prometheus Operator and describe a desirable end-to-end monitoring stack, including alerts and dashboards.

Speakers
avatar for Max Leonard Inden

Max Leonard Inden

Software developer, CoreOS
Max is a software developer at CoreOS and member of the upstream Prometheus project, working both on Prometheus and Kubernetes. Previously hacking on data quality analysis, he decided to stop suppressing his interest for distributed systems at scale and joined CoreOS. Now he implements... Read More →


Monday June 25, 2018 16:40 - 17:20 CST
307A

16:40 CST

Connecting the Edge - Anshul Sharma, TIBCO Software
The Internet of Things (IoT) brings up 50 billion devices until 2020, which have to be connected somehow. Challenges include low bandwidth, high latency, non-reliable connectivity and the need for low network costs. Therefore, a gateway is needed remotely on site of the devices to filter, aggregate and send just relevant data into the cloud or data center.

The session will talk about challenges in IoT architecture and will introduce project Flogo: A 100% open source framework, which allows developing ultra-lightweight IoT integration applications with a zero-coding web user interface or design chatbot.The session will also focus on the need for machine learning at the edge and how Flogo can help.

Lastly, the session will also cover how Project Flogo can be used to develop applications at the edge as well as deploy the same in a serverless environment.

Speakers
avatar for Anshul Sharma

Anshul Sharma

Solutions Architect, TIBCO Software
Speaker Biography =================== Anshul is a Technology Evangelist and Solutions Architect at TIBCO who helps to spread the TIBCO connected intelligence message across partners and customers. He has worked in different groups such as Services, Pre- sales and Product over past... Read More →


Monday June 25, 2018 16:40 - 17:20 CST
306A
  IoT & M2M

16:40 CST

Better Live Migration on KVM/QEMU - Guangrong Xiao, Tencent Cloud (slides attached)
Live Migration plays a very important role in the cloud industry, e.g, it's a key component for high availability, load balance, etc. Currently Qemu/KVM gains some notable features to improve the performance of live migration, for example, it supports auto-converge, compress, xbzrle and post-copy, etc, however, in Tencent Cloud we met some challenges to enable them in our productions and realized that they do not work well as we expected in the real world.

In this presentation, we are going to present the issues & shortages we found on current KVM/QEMU, then show our solutions to resolve them which will include lockless multithread mode, better vCPU throttle algorithm, redesigning memory mode for compression and xbzrle and so on. Besides that, we will also share the new ideas we innovated to make live migration better.

Speakers
XG

Xiao Guangrong

Senior Software Engineer, Tencent Cloud
Xiao Guangrong is a Linux Kernel developer working on Ftrace, MM, Btrfs but his main interest is KVM. As a active contributor, he was invited to give some presentations at some conferences: Japan LinuxCon 2011, Japan LinuxCon 2012 China CLK 2012, KVM Forum 2016, 2017, 2018. He is... Read More →



Monday June 25, 2018 16:40 - 17:20 CST
203AB
  KVM

16:40 CST

A Major Overhaul of the APIC Initialization and Vector Allocation - Dou Liyang, Fujitsu (FNST) (slides attached)
Interrupt is one of the important mechanisms of the Linux kernel, vector and APIC tell the
kernel how to operate the interrupt.

With the development of the kernel, the old code leads to many problems, such as vector
space exhaustion, vector allocation chaos, kdump failure, Timer setup error, etc.,

Recently, Thomas Gleixner and Dou Liyang conducted a major overhaul. In this presentation,  Dou Liyang will describe the main process of interrupt initialization, discuss the challenges it faces, and introduce what does the overhaul do and explain how it may address those challenges.

Speakers
avatar for Dou Liyang

Dou Liyang

software engineer, Fujitsu(FNST)
Dou Liyang is a Linux kernel developer in Fujitsu Nanda. He primarily works on kernel initialization related technologies. He has contributed to CPU hotplug. Recently he focused on Interrupt initialization and has unified the APIC and interrupt mode setup for kernel.



Monday June 25, 2018 16:40 - 17:20 CST
307B
  Linux Systems

16:40 CST

Common Modeling Practice for Network Orchestration and Automation - Lingli Deng, China Mobile & Hui Deng, Huawei Technologies
ONAP is a model-driven platform for network automation. Common modeling for deployment, SDN, service configuration and close loop are key to align different modules to achieve decoupling from service/network design and service orchestration/management. ONAP R1 is mostly about the mapping of ECOMP IM/DM with OPENO ETSI/TOSCA based IM/DM due to time limitation. Starting from Release 2, ONAP modeling subcommittee is working on the merge into the unified IM/DM and taking into input from different SDOs (TMF, MEF, ETSI NFV) This speech will give an overview of the approach taken and a summary of current progress of ONAP modeling.

Speakers
avatar for Lingli Deng

Lingli Deng

Technical Manager, China Mobile
Lingli obtained her Doctorate in Computer Application Technology from the Institute of Software, Chinese Academy of Sciences and joined China Mobile in 2009.She is a core member of the Novonet project which drives SDN/NFV strategy for China Mobile, and has been working on evaluation... Read More →
avatar for Hui Deng

Hui Deng

Director, Huawei
Hui DENG obtained his Doctor degree from Dept. Computer Science and Technology at Tsinghua University in 2002. He worked as chief researcher in Hitachi (China) R&D Cooperation from 2002 to 2007, and worked as Principal staff between 2007 and 2016 in China Mobile. He joined Huawei... Read More →


Monday June 25, 2018 16:40 - 17:20 CST
311B

16:40 CST

Why You Need an Open Source Program Office - Chris Aniszczyk, Cloud Native Computing Foundation (slides attached)
Speakers
avatar for Chris Aniszczyk

Chris Aniszczyk

CTO, Linux Foundation (CNCF)
Chris Aniszczyk is an open source executive and engineer with a passion for building a better world through open collaboration. He's currently a CTO at the Linux Foundation focused on developer relations and running the Open Container Initiative (OCI) / Cloud Native Computing Foundation... Read More →



Monday June 25, 2018 16:40 - 17:20 CST
310
  Open Source Leadership

16:40 CST

TSeer: The Tencent Open Source Nameservice Framework - Yang Qiang, Tencent
Service discovery is a key component of distributed systems, and Tseer is such a component which is a rightful implementation of Tars name service. It’s been used by QQ browser, Yingyongbao, Tencent Literature, etc, has billions of daily throughput. This session will discuss the origin and rationale of TSeer, and its application in Tencent and China Literature.

Speakers
YQ

Yang Qiang

Senior Technical Engineer, Tencent


Monday June 25, 2018 16:40 - 17:20 CST
VIP4-3
 
Tuesday, June 26
 

08:00 CST

Breakfast
Tuesday June 26, 2018 08:00 - 09:00 CST
4F Foyer

08:00 CST

Registration
Tuesday June 26, 2018 08:00 - 17:00 CST
Main Lobby B

09:00 CST

Keynote: Digital Decoupling - Journey to Open - Sven Loberg, Managing Director, Emerging Technology, Accenture
Driven by new consumer and market expectations, companies want to execute and scale innovation using open source technologies. But, they are often challenged by their current enterprise landscape. Legacy systems can shackle the Enterprise to decades of technical debt making changes highly complex and expensive. Yet, there is no appetite for large investments in massive re-platforming or other “big bang” transformations of the past.

A reactive, event-driven architecture can help enable decoupling from the technical debt within legacy systems and enable innovation on top of the core. In addition, it allows us to simplify or even replace the legacy core gradually over time. This creates rapid business value and de-risks transforming to a more flexible and innovation-friendly platform of the future.

Speakers
avatar for Sven Loberg

Sven Loberg

Managing Director, Accenture
Sven Loberg is a Managing Director within Accenture's Emerging Technology practice with responsibility for Open Source and Software Innovation. In this role he works to promote the benefits and use of open source both at Accenture clients as well as within Accenture. Sven has worked... Read More →


Tuesday June 26, 2018 09:00 - 09:20 CST
Plenary Hall B

09:25 CST

Keynote: Unleash the Power of Open Source ( 释放开源价值) - Evan Xiao, Vice President, Strategy & Industry Development, Huawei
Speakers
avatar for Evan Xiao

Evan Xiao

Huawei Technologies Co., Ltd, Vice President, Strategy and Business Development
Mr. Evan Xiao is Vice President of Strategy and Business Development at Huawei Technologies Co., Ltd. He brings nearly twenty years of experience in the ICT industry to this role.Since joining Huawei in 1998, Mr. Xiao has held a number of management positions across various R&D, Marketing... Read More →


Tuesday June 26, 2018 09:25 - 09:40 CST
Plenary Hall B
  Keynote

09:45 CST

Keynote: Managing Open Source in Tencent, from the Bottom Up - Liu Xin, General Manager of Mobile Internet Group, Tencent
腾讯开源起始于2012年,但直到近两年才能够说步入正轨。腾讯的企业文化鼓励竞争,内部存在技术壁垒,在开源上缺少自上而下的战略规划。因此,腾讯开源的起步阶段面临很多困难。
但可以看到,从2016年开始,腾讯的开源逐渐有了起色,腾讯自主开源了50多个优质项目,有的是经典技术项目,例如像微服务框架Tars和名字发现框架TSeer,已经积累10年,经过100多个业务考验的。有的是热点领域,例如Angel、FeatureCNN等AI库和框架。与此同时,腾讯与开源基金会的合作更加密切,先后成为OpenStack、LF DP funding member和LF的白金会员并拥有董事席位,这证明了社区对于腾讯开源贡献的认可。

取得这些成就,腾讯开源的诀窍就是:自下而上社区化运作。通过树立标杆项目让公司了解如何参与和受益于开源发展,参与更广范围的开源社区合作。这些经验值得和所有对开源抱有疑惑的公司分享。

Tencent open source began in 2012, but it can not be said that it has been on the right track until the last two years. Unlike other companies, Tencent's corporate culture encourages competition, the internal technical barriers exist, and there is also a lack of top-down strategic planning in terms of open source. Therefore, Tencent's open source is facing many difficulties in its initial stage.

However, we can also see that since 2016, it has gradually improved. Tencent has independently opened more than 50 high-quality projects. Some are classic technical projects, such as the microservice framework Tars and service discovery framework TSeer, which has been verified by more than 100 business operations over 10 years in Tencent. Some are cutting-edge technologies such as AI libraries and frameworks, like Angel and FeatureCNN. At the same time, Tencent's cooperation with the Open Source Foundation has become closer. Tencent has become the LF Deep Learning funding member and the Platinum Member of the Linux Foundation, which shows the recognition of Tencent's contributions to the community.
To obtain these achievements, the key is: From the bottom up. The purpose is to let the company understand how to be involved in and benefit from the open source while participating in a wider range of open source community building, by establishing benchmarking projects. These experiences are worth sharing with all companies that have doubts about open source.

Speakers
avatar for Xin liu

Xin liu

General Manager, Tencent
刘昕,现任腾讯移动网事业群运营部助理总经理,全面负责移动互联网事业群技术平台的研发和运营工作。领导团队进行架构设计与服务优化,打造微服务开发框架、名字服务、监控服务、数据缓存服务、分布式存储系统、消息中间件、机器学习平台,为腾讯手机浏览器、腾讯桌面浏览器、应用宝、腾讯手机管家、腾讯桌面管家以及腾讯地图、翻译君提供稳定可靠的运营服务。致力于腾讯开源社区建设工作,推动微服务开发框架TARS、轻量化名字服务TSeer开源,以及开源项目在业界应用。目前开始探索5G网络中IT技术应用和V2X、VR/AR、IoT、云游戏应用在5G网络部署与适配。Mr... Read More →


Tuesday June 26, 2018 09:45 - 10:00 CST
Plenary Hall B
  Keynote

10:05 CST

Keynote Panel: Cloud Native - Dan Kohn, Cloud Native Computing Foundation; Junjie Cai, Alibaba Cloud; Anni Lai, Huawei; Todd Moore, IBM; Michelle Noorali, Microsoft; Haifeng Liu, JD.com; Liu Xin, Tencent
Moderators
avatar for Dan Kohn

Dan Kohn

General Manager, Linux Foundation Public Health, Linux Foundation
Dan leads Linux Foundation Public Health, a new initiative to use open source software to help public health authorities combat COVID-19 and serves as VP, Strategic Programs for the Cloud Native Computing Foundation, which sustains and integrates open source technologies like Kubernetes... Read More →

Speakers
avatar for Junjie Cai

Junjie Cai

Senior Staff Engineer, Alibaba Cloud
Junjie (Jack) is the Chief Architect of the Elastic Compute Service at Alibaba Cloud. He has extensive experience with Cloud Computing across IaaS, PaaS and SaaS. His current focus is to make the IaaS controller more intelligent for better compute service availability, performance... Read More →
avatar for Anni Lai

Anni Lai

Head of Global Business Development, VP of Strategy & Business Development, Huawei
Anni leads the Operations of Huawei’s Cloud Open Source Development Team responsible for OpenStack, Containers, Open Storage, AI/Deep Learning, and other Cloud-related open source projects. Anni currently sits on both OpenStack and CNCF Boards. In addition, Anni is part of Huawei’s... Read More →
avatar for Xin liu

Xin liu

General Manager, Tencent
刘昕,现任腾讯移动网事业群运营部助理总经理,全面负责移动互联网事业群技术平台的研发和运营工作。领导团队进行架构设计与服务优化,打造微服务开发框架、名字服务、监控服务、数据缓存服务、分布式存储系统、消息中间件、机器学习平台,为腾讯手机浏览器、腾讯桌面浏览器、应用宝、腾讯手机管家、腾讯桌面管家以及腾讯地图、翻译君提供稳定可靠的运营服务。致力于腾讯开源社区建设工作,推动微服务开发框架TARS、轻量化名字服务TSeer开源,以及开源项目在业界应用。目前开始探索5G网络中IT技术应用和V2X、VR/AR、IoT、云游戏应用在5G网络部署与适配。Mr... Read More →
avatar for Haifeng Liu

Haifeng Liu

Chief Architect and Vice President of Technology, JD.com
Haifeng has always had a passion for building complex systems. He is the Chief Architect of JD.com, China’s largest retailer and the world’s third largest internet company by revenue. He is also Vice President of JD’s Technical Infrastructure department. Haifeng joined JD in 2013 and is responsible for the construction and optimization of the infrastructure that powers al... Read More →
avatar for Todd Moore

Todd Moore

Vice President - Open Technology, IBM Developer and Developer Advocacy, IBM
Open Source innovator, Agile and Business development strengths. Industry leader in open source community development. Extensive experience in creating HW and Software architectures for desktops, servers, middleware, and device middleware. Strong background in performance, performance... Read More →
avatar for Michelle Noorali

Michelle Noorali

Senior Software Engineer, Microsoft
Michelle Noorali is a Sr. Software Engineer at Microsoft and was Co-Chair for KubeCon+CloudNativeCon 2017. She is a member of the CNCF Technical Oversight Committee and serves as a developer representative on the CNCF Governing Board. Michelle is also a core maintainer of several... Read More →


Tuesday June 26, 2018 10:05 - 10:45 CST
Plenary Hall B
  Keynote

10:50 CST

Coffee Break
Tuesday June 26, 2018 10:50 - 11:20 CST
Plenary Hall A

10:50 CST

Sponsor Showcase
Tuesday June 26, 2018 10:50 - 16:00 CST
Plenary Hall A

11:00 CST

Office Hours: Max Leonard Inden, Software Developer, CoreOS
Speakers
avatar for Max Leonard Inden

Max Leonard Inden

Software developer, CoreOS
Max is a software developer at CoreOS and member of the upstream Prometheus project, working both on Prometheus and Kubernetes. Previously hacking on data quality analysis, he decided to stop suppressing his interest for distributed systems at scale and joined CoreOS. Now he implements... Read More →


Tuesday June 26, 2018 11:00 - 12:00 CST
Level 3, Parkview Foyer

11:00 CST

11:00 CST

Office Hours: Ria Bhatia, Program Manager, Microsoft
Speakers
avatar for Ria Bhatia

Ria Bhatia

Program Manager, Independent
Ria Bhatia was a Program Manager for Upstream Azure Compute within Microsoft. She's been working with the community on different ways to scale in Kubernetes and operate Kubernetes. She actively maintains Virtual Kubelet and has spoken at multiple meetups and conferences, including... Read More →


Tuesday June 26, 2018 11:00 - 12:00 CST
Level 3, Parkview Foyer

11:15 CST

11:20 CST

GenoStack: A Collection of Biotechnology Tools Using Containers - Chao Wang, CTO, xturing.inc (slides attached)
In this session, Mr. Wang will demonstrate how to use containers for large-scale analysis of biological data.

Speakers
avatar for Chao Wang

Chao Wang

CTO 首席技术官, X-Turing
Mr. Chao Wang is currently the CTO of X-Turing, a company for bioinformatics tools and big data platform for genomics. Mr. Wang has been working as a software engineer for 10+ years in many fields such as Linux, Cloud, Telecom NFV, Big Data, and AI. Now he spends all of his time to... Read More →



Tuesday June 26, 2018 11:20 - 11:45 CST
Plenary Hall B

11:20 CST

Extend Hyperledger Fabric to Support EVM Contract and Web3 Toolings - Jiannan Guo & Swetha Repakula, IBM (slides attached)
Hyperledger Fabric is a permissioned blockchain platform where people build applications to communicate and interact with deployed smart contracts. However, smart contracts and apps must be written in programming languages like Go or Javascript. Alternatively, Ethereum made it friendly to write smart contracts by inventing Contract-Oriented Languages, e.g. Solidity, and created a Web3 library that can be used to interact with smart contracts.
The talk will cover how an EVM has been integrated into Fabric, enabling users to write contracts in Contract-Oriented Languages as well as interact with them via the Web3 library. Developers familiar with Ethereum can easily develop on Fabric, leverage tools like Truffle & Remix, as well as migrate their Distributed Apps (DApps) with minimal effort. The talk will also describe use cases where permissioned blockchains are more desirable.

Speakers
JG

Jay Guo

Software Engineer, IBM
Jiannan (Jay) Guo is working for IBM China as software engineer. His main job is to contribute and advocate open source projects and he is currently maintainer of Hyperledger Fabric, a permissioned blockchain technology. He used to contribute to Apache Mesos, a container orchestration... Read More →
avatar for Swetha Repakula

Swetha Repakula

Open Source Contributor, IBM
Swetha Repakula is currently a software engineer at IBM’s Open Technologies and a member of the Technical Steering Committee at Hyperledger. For the last two years, she has been working on Hyperledger Fabric, specifically on its EVM integration. Previously she was a full time open... Read More →



Tuesday June 26, 2018 11:20 - 12:00 CST
311A
  Blockchain

11:20 CST

Best Practices for Containers in Production for Banking - Eric, Alibaba
Banking has its particular requirements and always seeks to speed up application delivery.
By introducing containers, we can apply an efficient micro-service and containerized architecture.

In this talk we will show a general roadmap, including how to rebuild workflow, and how to apply thoroughly container technology. However, as banks highly value the stability and reliability, and care about non-functional requirements than features, banking solution has some extra specialties, such as role-based authorization, flexible deployment across multiple network secure zone, image/container/node security scan, full control of resource allocation and isolation, full audit for logging and monitoring integration with existing IT system etc. And what’s more, we have learnt some precious lessons: It is a totally different story in private networking environment.

Speakers
avatar for Eric

Eric

Senior Architect, Alibaba
Senior Architect of Container service of Alibaba Cloud


Tuesday June 26, 2018 11:20 - 12:00 CST
309A

11:20 CST

Do Auto and Manual Instrumentation in Apache SkyWalking APM - Sheng Wu, Tetrate.io Inc (slides attached)
Today, microservices, cloud native and container-based (Docker, K8s, Mesos) architectures become popular. Ops people need to monitor and trace their distributed system. Apache SkyWalking based on auto instrumentation tracing core, helps people to trace and monitor system, and not need to change any source codes. At the same time, as an OpenTracing compatible tracer, user can do manual instrumentation by using OpenTracing APIs. All auto and instrumentation run in the same context. We will show you how this works.

Further, Apache SkyWalking 5.x provides full functional APM features and visualization. We will demonstrate our analysis, aggregation, alarm and trace capabilities in our UI, based on the tracing data.

Speakers
avatar for Sheng Wu

Sheng Wu

Founding Engineer, Tetrate.io Inc.
Tetrate.io Inc. Founding Engineer. Bitmain Inc. Technical expert.Apache SkyWalking (Incubating) creator, PPMC member, and committer. Microsoft MVP.CNCF OpenTracing member, OTSC&OTIAB memberW3C tracing context specification collaborator and contributor.Former Huawei, OneAPM.



Tuesday June 26, 2018 11:20 - 12:00 CST
309B

11:20 CST

How Good Is Our Code? Kubernetes, Cloud Native Development, and Continuous Integration - Dan Kohn, CNCF
Cloud Native computing, such as using Kubernetes, is defined as being a mix of containerization, orchestration, and microservices. In this talk, Dan will review cloud native architectures, and argue that continuous integration is actually the most important part of the cloud native architecture. He will discuss how testing in continuous integration is similar to entrepreneurship and science, in comparing idealized versions to objective reality.

Speakers
avatar for Dan Kohn

Dan Kohn

General Manager, Linux Foundation Public Health, Linux Foundation
Dan leads Linux Foundation Public Health, a new initiative to use open source software to help public health authorities combat COVID-19 and serves as VP, Strategic Programs for the Cloud Native Computing Foundation, which sustains and integrates open source technologies like Kubernetes... Read More →


Tuesday June 26, 2018 11:20 - 12:00 CST
310

11:20 CST

Opportunities and Innovation for Developers in the Chinese Open Source Ecosystem - Mark Ma, Forever Open Source Software Inc.

Open Source China, the largest Chinese open source community has been running gitee.com (the worldwide No. 2 largest clouding code base after Github) for 4 years. We will share the Chinese developers’ trends by analyzing 2 million users and 3 million projects in 2017 including hot technologies such as cloud computing, big data, DevOps, AI & Blockchain.

We will also give an overview of Chinese open source ecosystem like what “BAT” contributed to open source community; what’s the impact to the small and middle business and what happened to the individual developers. 


Speakers
SX

越 马

CEO, 开源中国
Founder and president of Forever Open Source Software Inc., CEO of Open Source China. Winner of Red Hat JBoss World Innovation Award in 2006.10+years of experience in enterprise software and open source technology development in the US. Mark Ma came back to China to become the pioneer... Read More →


Tuesday June 26, 2018 11:20 - 12:00 CST
306B

11:20 CST

How to Build Container Technology at Millions Scale in Alibaba - Hongliang Sun, Alibaba (slides attached)
Container technology Pouch has successfully supported 2017 Singles Day as the key technology that processes all online transactions smoothly on millions of containers. Hongliang will reveal the killing features of Pouch compared to other container solutions in the industry. Rich container, hypervisor-based container, P2P image distribution, better isolation abilities, kernel compatibilities are the fanciest points the industry would be interested in. In addition, Hongliang will introduce how to natively support Kubernetes in Pouch with CRI implementation. Now Pouch is an open source project. Hongliang will share experience on how to build Pouch in open source.

Speakers
AS

Allen Sun

Staff Engineer, Alibaba Cloud
Allen Sun, a Senior Engineer at Alibaba Group, is currently responsible for the open source construction of the PouchContainer project at Alibaba. I have been involved in cloud computing for over 5 years and is one of the first batch of researchers and practitioners of container technology... Read More →



Tuesday June 26, 2018 11:20 - 12:00 CST
307A

11:20 CST

Introduction to the Zephyr Project - Ryan Qian, NXP & Kate Stewart, The Linux Foundation (slides attached)
The Zephyr OS is a small, scalable, open source RTOS designed for microcontroller class devices across multiple architectures, and includes networking, connectivity and security features necessary for IoT products. This talk will provide an introduction to the Zephyr Project, highlight key features, and share upcoming development plans, including our first LTS release.

Speakers
JQ

Jianghao QIAN

Software Engineer, NXP
Now I'm working on MCUX SDK development and NPI enablement for Kinetis & i.MXRT family. Also have worked on Windows Embedded/Linux BSP driver development and validation for i.MX family from 2006
avatar for Kate Stewart

Kate Stewart

Senior Director of Strategic Programs, Linux Foundation
Kate Stewart is a Senior Director of Strategic Programs, responsible for Embedded and Open Compliance programs. Since joining The Linux Foundation, she has launched Real-Time Linux, Zephyr Project, CHAOSS, and ELISA.



Tuesday June 26, 2018 11:20 - 12:00 CST
306A
  IoT & M2M

11:20 CST

Three-Hot Technologies and Their Usages at Huawei's Public Cloud - Liu Jinsong, & Huang Zhichao, Huawei (slides attached)
In this proposal, Liu Jinsong introduces Huawei's three-hot technologies: hot-fix, hot-replacement, and hot-migration (live migration). It firstly analyses the online-update needs coming from Huawei's cloud infrastructure, then discusses the different usage models of three-hot technologies. It then introduces some key technical points of three-hot technologies, for example, how to hot-replace qemu/network/storage components of Huawei's public cloud, how to reduce CPU downtime (under big memory pressure) and network breaktime (reduce VPC breaktime from several minutes to less then 100ms) of live migration, and how to ensure 100% VM alive when live migration fails.

After introducing Huawei's three-hot technologies, it shows some usage models of three-hot technologies at Huawei's public cloud. For example, how Huawei solved Intel's security holes recently by using three-hot technologies.

Speakers
ZH

Zhichao Huang

Senior Software Engineer, Huawei
Zhichao Huang is a senior software engineer from Huawei. He has 12 years working experience on Linux/Virtualization.



Tuesday June 26, 2018 11:20 - 12:00 CST
203AB
  KVM

11:20 CST

Understanding Spectre v2 and How the Vulnerability Impact the Cloud Security - Gavin Guo, Canonical (slides attached)
Since the emerging of the OpenStack cloud computing platform in the Ubuntu community, increasing number of public/private cloud service providers choose to deploy it all over the world. Recently, Spectre and Meltdown have caused a panic in the world and the Spectre V2 is the only one which can attack the host system from the guest VM. It's vital to know the detailed process of the attack. Gavin Guo will give a detail explanation and an example of how to attack the host system.

Speakers
avatar for Gavin Guo

Gavin Guo

Engineering Technical Lead, Canonical
Gavin Guo is a Linux kernel developer in the Ubuntu community. He is the speaker of 2016 China Linux Kernel Conference. He is now working for Canonical in the Customer Success division. He is responsible for the kernel stability and performance tuning of the OpenStack platform especially... Read More →



Tuesday June 26, 2018 11:20 - 12:00 CST
307B
  Linux Systems

11:20 CST

SDN Practice and Implementation for Inspur Cloud Platform - Yanjun Li, Inspur (slides attached)
Scalability, complication, and security are three major problems in the current cloud computing network.

In order to provide agile and intelligent networking service for various applications,Inspur delivered an application-based network controller to deal with the matter, the core functions of Inspur controller are divided into four parts, which include cloud path, cloud chain, cloud controller, and cloud decision.

This presentation will describe Inspur SDN controller's architecture and implementation in detail.And in Inspur software-defined data center, its vision could not only offer optimal infrastructure for various workload but also achieve auto-scale operation efficiencies.
Inspur hopes to deliver its module and solution to corresponding open source community to make the whole ecosystem more prosperous.

Speakers
avatar for Yanjun Li

Yanjun Li

Technical Director, Inspur
He is from Inspur Cloud Service Group China, acts as technical director and chief architecture for Inspur public cloud platform. His interested area focuses on cloud network technology especially virtual networking management . Over the past few years, he has delivered many projects... Read More →



Tuesday June 26, 2018 11:20 - 12:00 CST
311B

11:50 CST

12:00 CST

Lunch
Tuesday June 26, 2018 12:00 - 13:30 CST
Plenary Hall A

12:15 CST

13:00 CST

Baidu Deep Learning Platform on Kubernetes
With the deep learning framework PaddlePaddle widely used in Baidu, PaddlePaddle platform based on Baidu private and public cloud also landed accordingly. In terms of technology selection, the traditional technology like Slurm cannot meet the fault tolerance and auto-scaling capacity of PaddlePaddle, and there is a lack of flexibility for the support of heterogeneous hardwares like GPU, FPGA, and RDMA. Therefore, we introduced Kubernetes in the next-generation platform design to achieve the platformization of the deep learning framework. In this session, we will share the architecture of Baidu's deep learning platform PaddleCloud and the series of work we have done at IaaS and CaaS.

Tuesday June 26, 2018 13:00 - 14:00 CST
207

13:00 CST

FD.io DMM Seminar
For More Information & Registration Details please visit: https://www.lfasiallc.com/events/lc3-2018/features-and-add-ons/co-located-events/ and https://www.wjx.top/m/22835806.aspx

26 June 2018, Huawei will hold one 2018 DMM technical seminar with FD.io Community and partners at the LC3 conference in Beijing. The theme of DMM seminar will focus on transport protocol stack acceleration in cloud networking. We would like to invite developers and users from the open source community to discuss the latest technologies of network protocol technology and trend.

DMM means dual Mode, Multi-Protocols,  Multi-Instances, it is a new open source protocol stack framework that Huawei unveiled at the 2018 North American ONS Summit and announced open source in the FD.io community. The DMM framework supports both kernel space and user space network protocol stacks, and allows multiple different protocol stacks to coexist, and runs multiple network protocol stack instances at the same time. This framework is flexible and makes it easy for developers of web applications and protocols to use different network stacks.
As a new member of the FD.io family, DMM combines Huawei network optimization experience to provide a more cost-effective solution for a variety of customers.

Seminar Information:
26 June, 2018  PM1:00 – PM 5:00
Place:Beijing National Convention Center
To give developers a better understanding about DMM, Huawei organized this seminar with the FD.io community, focusing on the following:
  • Network protocol stack optimization
  • User Space protocol stacks
  • Multiple Network stacks Deployment scenario
  • Container networks, etc.
So far, we have invited experts from academy, industry and community to share their latest research findings and insights. Some of these are listed below:

Empower network stack in the cloud networking via DMM   (DMM Project Manager Yalei Wang)
Abstract: This Session will focus on the technical details and framework features of DMM, including the latest DMM features, ongoing projects, and a road map for the future. In addition, we plan to show a Use Case, to help development and consumers understand how to connect the new protocol stack to the DMM framework, and make it easier to use DMM services for upper applications.

F-Stack: A Full User Space Network Service with DMM  (F-Stack Maintainer Hailong Wang)
Abstract: This presentation will introduce F-Stack latest feature, and describe how to build up a high performance user space stack to support Load balance, Web Server, etc. Finally speaker will share his experience and practice with the audiences, let us know how to utilize DMM framework to empower F-Stack scenarios .

Light: Research on High-Performance fully compatible user space Network Protocol Stack(Tsinghua University  Prof. Dan Li )
Abstract:This report mainly introduces one home-grown user space network protocol stack(Light). Light provides high compatibility interfaces with legacy kernel stack, and can run directly with Nginx and other applications without any modification. To compared with the latest version of Linux kernel protocol stack, the Nginx can achieve throughput 60% increased on Light . The tail delay can be reduced by an order of magnitude.

The practice of high-performance networking solutions for cloud on Arm platforms  (ARM Open Source Networking Manager: Song Zhu)
Abstract: This presentation will focus on the experience of networking solutions including data plane acceleration, VPP integration and transportation stack on Arm architecture. We have been working in the community to enable and optimize some key components for networking software stack on Arm. We will share some learning points from our practice.

SDWAN Implementation and WAN Optimization based on DMM(Huawei Senior Architect Yanfei Han)
Abstract: This Session focuses on the use case and benefit from DMM in WAN acceleration in SDWAN scenarios. To combined with the key business in Huawei SD-WAN, DMM provides flexible framework to integrate lead TCP congestion control algorithm and the high speed transmission Stack Fillp , which can effectively solve the pain point of the enterprise and the users in large files transportation.
You are welcome to sign up this Seminar and submit the topic and share your experience with us in the cloud network. We will provide free tickets for the Beijing LC3 Conference on June 25-27.  In addition, The LC3 is a major industry conference hosted by the Linux Foundation, and own a wide range of industry influence.  LC3 participants will be able to collaborate, share information and learn about the latest and most interesting open source technologies, including Linux, containers, cloud technologies, networks, micro services, etc.)

Tuesday June 26, 2018 13:00 - 17:00 CST
CNCC, E231

13:20 CST

Using TARS to Code in Golang - Chen Mingjie, Tencent
With the rise of containerization technology such as docker, k8s, etc, Go language has become popular. Go's coroutine concurrency mechanism makes Go is very suitable for large-scale high-concurrency back-end server program development. The Go language has near C/C++ performance and near python productivity. At Tencent, part of the existing C++ development gradually turned to Go development, and Tars as MIG's widely used RPC framework has now supported C + + / Java / Nodejs, and the combination with Go language has become a general trend. Therefore, in the voice of users, we launched Tarsgo, and we have applied to Tencent map application, application of commercialization of YingYongbao, Internet+ and other projects. This presentation mainly introduces the functional characteristics of Tarsgo, as well as the use cases, and the differences in writing habits of other versions of the Tars language.

Speakers
CM

Chen Mingjie

Senior Technical Engineer, Tencent


Tuesday June 26, 2018 13:20 - 14:00 CST
VIP4-3

13:30 CST

An Implementation of Blockchain Technology in Real Estate Industry: Asset Digitalization - Long Wu, FZG 360 (slides attached)
Blockchain technology has a large potential to transform business operating models in the long term. It is more a foundational technology—with the potential to create new foundations for global economic and social systems. In this presentation, Long Wu will review latest use case of blockchain in Real Estate industry(including a demonstration of an implementation of Real Estate Asset Digitalization Chain), discuss the potential that blockchain can change the current landscape of the Real Estate market, the challenges it faces, and look forward to how may those challenges be addressed.

Speakers
LW

Long Wu

R & D Head, FZG 360
Vanke Property Service, Center of data and information technology Department Head Leads the design, development and operation of app "Zhuzheer". Excegroup, Zhenglianhaodong technology Ltd,. General manager Leads the design, development and operation of app O+.



Tuesday June 26, 2018 13:30 - 14:10 CST
311A
  Blockchain

13:30 CST

Istio - Weaving, Securing and Observing Microservices - Lin Sun, IBM & Wencheng Lu, Google
With the rapid adoption of microservices, Istio has become the de facto framework to load-balance, route, secure and monitor the traffic that flows between microservices. Istio provides a common networking, security, policy and telemetry substrate for services that we call a ‘Service-Mesh’. Come learn how the service-mesh helps with the transition to microservices, to empower operations teams, to adopt security best-practices and much more. We’ll also cover the state and ecosystem of the project, where it’s headed and how you can get involved.

Speakers
avatar for Wencheng Lu

Wencheng Lu

Senior Staff Software Engineer, Google
Dr. Wencheng Lu is a senior staff software engineer at Google. He has been with Google for 12 years. He is currently a tech lead manager overseeing Istio Security.
avatar for Lin Sun

Lin Sun

Senior Technical Staff Member, IBM
Lin has been working on container and cloud-native since 2014 from Docker to Kubernetes to Service Mesh. She is currently an Istio maintainer, a member of the Istio steering committee and technical oversight committee. She is passionate about new technologies and loves to play with... Read More →


Tuesday June 26, 2018 13:30 - 14:10 CST
309A

13:30 CST

Kata Containers: When OCI Meets Virtuliazation - Tao Peng, HyperHQ Inc.
The presentation first gives an introduction to the OCI (Open Container Initiative) spec and the vm-based container runtime -- the kata containers project, focusing on its targeting threat model, high-level architecture and use cases. Then it dives deeper on how kata containers cope with limitations of the OCI (Open Container Initiative) spec that is the very basis of Docker containers, and how it manages to extend the spec for advanced features when integrating with kubernetes. Finally, a demo will be shown to the audiences.

Speakers
avatar for Peng Tao

Peng Tao

Staff Engineer, Ant Group
Kata Containers architecture committee member, Nydus maintainer, and Linux kernel developer.


Tuesday June 26, 2018 13:30 - 14:10 CST
309B

13:30 CST

Improving and Practicing Linux Kernel Education in China College - Yue Chen, Nanchang University & Ben Shushu, Technical Consultant (slides attached)
The Linux kernel is the worldwide popular operating system, and it gives huge job opportunities in China.

In last decades, it always uses Windows as Operating System course in China colleges, but recent years, more and more using Linux as the major operating system in the OS class. But the Linux kernel development remains extremely rapid, which very difficult for students to catch up. The kernel source size keeps growing rapidly, for example, Linux 4.x it is up to 22 million which too big for teaching and many students complaint it is very difficult to learn this course.

In this presentation, we will introduce our experience and ideas on how to teach Linux kernel effectively in college such as new methods of teaching reform, optimizes the teaching content, problem-driven method.Those experience can extend to other colleges and let more and more students love Linux kernel.

Speakers
avatar for Ben shushu

Ben shushu

technical consultant, Running Linux Kernel Group
Benshushu is a technical consultant in China, he wrote a linux kernel analysis book on 2017 which is popular in China. On 2019, he published a new book about linux kernel and education.
CY

chen yue

Associate professor, Nanchang University
Doctor of Computer Science ,Associate professor ,Graduated from the Fudan University in 2013,Worked in Nanchang University ,His research interests include Artificial intelligence, algorithm and operating system.



Tuesday June 26, 2018 13:30 - 14:10 CST
306B
  Emerging Technologies & Wildcard

13:30 CST

Augmented Humanity and AI Driven Smart Services: What Happens When The Machines Take Over - R. Ray Wang, Principal Analyst, Founder & Chairman, Constellation Research
Searching for a competitive advantage and fearful of disruption, boardrooms and CXO’s have rushed to artificial intelligence as the next big thing.  The investment in pilots for AI’s subsets of machine learning, deep learning, natural language processing, and cognitive computing have moved from science projects to new digital business models powered by smart services.  This unifying force for digital transformation in customer journeys, Internet of Things, future of work, commerce, and distributed ledger blockchain technology revolves around the creation of AI-driven smart services.

Learn how to bring immersive experiences, mass personalization at scale, and value exchange to create an orchestration of trust.  Understand how these smart services will drive seven outcomes from artificial intelligence and jump-start growth in every industry.  While these smart services will dominate the landscape over the next decade, learn what rules and ethics need to be applied to not only augment humanity but also keep humanity safe.

Join R “Ray” Wang (@rwang0), head of Silicon Valley-based Constellation Research and best-selling author of the Harvard Business Review Press book, Disrupting Digital Business, as he shares practical guidance on how to jump-start growth with AI driven smart services.

Speakers
avatar for R Ray Wang

R Ray Wang

Principal Analyst, Founder and Chairman, Constellation Research
R "Ray" Wang (pronounced WAHNG) is the Principal Analyst, Founder, and Chairman of Silicon Valley-based Constellation Research, Inc.  He's also the author of the popular business strategy and technology  blog "A Software Insider’s Point of View". With viewership in the 10's of millions of page views a year, his blog provides insight into how disruptive technologies and new business models such as digital transformation impact brands, enterprises, and organizations.  Wang has held executive roles in product, marketing, strategy... Read More →


Tuesday June 26, 2018 13:30 - 14:10 CST
Plenary Hall B

13:30 CST

Kubernetes for Edge Computing across Inter-Continental Haier Production Sites - Julia Han & Jiyuan Tang, Caicloud (slides attached)
Cloud computing has become the de facto IT best practice and Kubernetes is defining the new norm to this end. Yet to the contrary, edge computing is creating buzz as it offloads processing from centralized server farms to peripheral devices closer to users, catering to enterprises with geographically distributed users.

Alas, edge computing involves heterogeneous and distant nodes causing mayhem for operators and a far cry from uniform management. Haier, a global manufacturer giant, is plagued by the pain as it delivers online services to inter-continental users via limp edge nodes at over a hundred sites, each incapable of running a Kubernetes cluster. We present an edge computing extension on top of Kubernetes with a success story in Haier, where we use one multi-tenant Kubernetes control plane to manage distributed satellite devices and nodes for efficient and unified management.

Speakers
avatar for Julia Han, Ph.D

Julia Han, Ph.D

COO 首席运营官, Caicloud
Julia is co-founder and COO at Caicloud that provides Kubernetes based toolings and K8s + ML platform for enterprises in production in China since 2015. As the very initial evangelist of Kubernetes in China, she has served as CNCF global ambassador and organized dozens of K8S meetups... Read More →
JT

Jiyuan Tang

Technical Director, Caicloud
...



Tuesday June 26, 2018 13:30 - 14:10 CST
307A
  Infrastructure & Automation

13:30 CST

Moving Fast and Slow at the Same Time: Lifecycle Commitments Across Major OS Releases - Adam Samalik, Red Hat (slides attached)
Modularity brings multiple versions of applications and language stacks to Fedora — so you can choose the right version you need for your application. Multiple versions allow for life cycles that go beyond a single release of a distribution.  This could allow you to stay on older versions across major versions of the underlying operating system.

Fedora 28 Server is the first deployment ready Fedora release including Modularity. Come and learn what it means and see how you can benefit from a server OS that gives you the ability to move both fast and slow at the same time. Containers included, but not required.

Speakers
avatar for Adam Samalik

Adam Samalik

Principal Software Engineer, Red Hat
Computer and automation enthusiast. Enjoys cooking, baking, and biking. Appreciates good coffee, clever design, and walkable cities. Tinkers with Linux for a living at Red Hat.



Tuesday June 26, 2018 13:30 - 14:10 CST
310
  Infrastructure & Automation

13:30 CST

Pushing the Kubernetes Experience to IoT Devices - Erno Aapa, Eliot (slides attached)
Containers have changed how we develop, ship and manage software in the cloud. Now is time to take IoT to the next level. While building automated drone inspection solution, Erno faced the problem that current IoT device management tools are coming far behind comparing to nowadays cloud tools and best practices.

To make IoT development, shipping and management easy, he started a new open source project, called Eliot. It takes latest state-of-the-art container technology to the edge and provides Kubernetes like developer-friendly interface to make the device software management easy, fast and fun again!

Speakers
avatar for Erno Aapa

Erno Aapa

Founder/CTO, Eliot
Erno Aapa is a Co-Founder of Polar Squad, Founder of Eliot IoT container platform and founder of Finnish DevOps community with over ten years experience from development, operations, and team leading in the software industry and over five years from DevOps. He is constantly researching... Read More →



Tuesday June 26, 2018 13:30 - 14:10 CST
306A
  IoT & M2M

13:30 CST

Intel’s Next Generation Hardware Virtualization Technologies to Make Cloud more Secure and Scalable with High Performance - Yu Zhang, Intel (slides attached)
Intel’s upcoming processor is providing  support for huge memory, more security enhancements, and extended performance tuning capabilities for cloud computing.

To support huge memory systems, the new platform is introducing 5-level paging in both hypervisor and VMs, which extends both the linear and physical address width for Intel's new memory technologies. For performance, Intel is delivering new instructions like AVX512 to accelerate AI computing. Meanwhile, features like Intel PT will empower VMs with advanced performance tuning capabilities, and can be used to enhance control flow integrity. For security, we are offering UMIP to prevent some sensitive instructions from user mode execution, as well as EPT-based SPP to allow fine-grained write-permission for VM introspection.

In this presentation, Yu will give an introduction to these fantastic features, their respective usage models, and current status.

Speakers
YZ

Yu Zhang

Virtualization Developer, Intel
Yu is a virtualization developer from Intel's virtualization team. He had 10+ years’ experiences in virtualization areas from I/O to CPU/memory virtualization, from performance tuning to security enhancements. Yu’s public presentation experience includes Xen summit/LC3 conference/Intel... Read More →



Tuesday June 26, 2018 13:30 - 14:10 CST
203AB
  KVM

13:30 CST

Diary of a Drive by Coder: Tips and Tricks for Working with Upstream - James Bottomley, IBM (slides attached)
Most of the community talks emphasize how to join the community and become an ongoing part of it, but what if you simply want to get a feature upstream and then move on to the next task? This behavior is called "Drive by Coding" and can be seriously frowned on by some communities who value ongoing community participation, but at the same time, it's the essence of the open source "scratch your own itch" principle.

This talk will showcase the experiences of an experienced kernel developer trying to do ecosystem enabling for kernel features via what is effectively driven by coding in the projects that should consume the feature. We will start off by talking about our first Drive By coding experience: trying to get support in PulseAudio for using the UE Boom 2 Stick as a highly efficient conference phone and move on to our later work on TPM enabling the cryptography and key handling (ssh and gnupg) infrastructure in Linux. This talk will show a range of community behaviors varying from hostile to extremely welcoming, and detail the successes and sometimes spectacular failures. We'll derive lessons learned including how to smooth the path, how to get upstream to like you but also how to recognize when community hostility is intractable and what to do in this case.

Speakers
avatar for James Bottomley

James Bottomley

Distinguished Engineer, IBM
James Bottomley is a Distinguished Engineer at IBM Research where he works on Cloud and Container technology. He is also Linux Kernel maintainer of the SCSI subsystem. He has been a Director on the Board of the Linux Foundation and Chair of its Technical Advisory Board. He went to... Read More →


Tuesday June 26, 2018 13:30 - 14:10 CST
307B

13:30 CST

Zero-Copy Optimization for DPDK vhost-user Receiving - Jing Chen, Alibaba Cloud (slides attached)
Virtio-net, a para-virtualized technology and De-Facto standard network interface today, is not officially supported by NIC vendors. vSwitch plus virtio-net is a golden combination considering its popularity, while performance is an important consideration.

This tutorial will introduce the solution that offloads the vSwitch function into smart NICs and discuss the data transformation issue between vendor-specific interface and virtio-net. To fix the issue, a light-weight application based on DPDK is introduced to perform simple packet forwarding. To ensure high-performance and low latency, a zero-copy receiving approach is developed. NIC DMA packets received from the network are transmitted into guest memory directly. Th approach re-constructs the memory pool to make the zero-copy process transparent to both NIC and virtio-net drivers without modifying any NIC or virtio-net driver.

Speakers
JC

Jing Chen

Staff engineer, Aliyun
Jing is a veteran in driver development and system optimization with more than a decade of experience. As a technical lead at Apsara Networking product team, Jing is leading the network product optimization work and smart NIC development. Before Joining Alibaba Cloud, Jing worked... Read More →



Tuesday June 26, 2018 13:30 - 14:10 CST
311B

13:30 CST

Huawei LiteOS Workshop
For More Information & Registration Details please visit: https://www.lfasiallc.com/events/lc3-2018/features-and-add-ons/co-located-events/ and http://www.huodongxing.com/event/8444183050600

Huawei LiteOS is an Internet of Things real-time operating system. It is developed by Huawei and open sourced on GitHub. Since 2017, LiteOS has started to hold activities for IoT developers on a large scale. In 2018, LiteOS 2.0 open source version was introduced to focus on the development of IoT devices in the LPWA field.
- Introduction to Huawei IoT Solutions
- Architecture and Key Function of Huawei LiteOS
- Huawei LiteOS to Cloud
- Huawei LiteOS + NB-IoT + OceanConnect Tutorial

更多信息或者注册请访问: https://www.lfasiallc.com/events/lc3-2018/features-and-add-ons/co-located-events/ and http://www.huodongxing.com/event/8444183050600

Huawei LiteOS 是一个物联网实时操作系统,由华为公司领导项目、自主研发并开源于 GitHub。2017 年起,LiteOS 开始大规模面向物联网开发者进行技术交流和办理开发活动,18 年更推出 LiteOS 2.0 开源版本,聚焦 LPWA 领域的物联网设备开发。
- 华为物联网解决方案介绍
- Huawei LiteOS架构、关键技术
- Huawei LiteOS端云方案介绍
- Huawei LiteOS + NB-IoT + OceanConnect物联网平台实战训练

Tuesday June 26, 2018 13:30 - 17:00 CST
211

13:40 CST

14:00 CST

Design & Practice with Cloud Services of Baidu Function Computing
Smart devices have become more and more widely used today, and user scenes such as the Internet of Things(IoT) require a backend with complex computing capabilities. The traditional backend deployment relied on a cloud server. Until Baidu Function Computing came out, function invoking is so easy and the price is so low so that a cloud server is unnecessary. In addition, Baidu DuerOS Ecology, Internet of Things(IoT) Ecology, and Edge Computing have increased the ability of CFC. This session share the architecture of CFC and the practice of combining usage with Baidu's AI ecology.

Tuesday June 26, 2018 14:00 - 15:00 CST
207

14:00 CST

Office Hours: Erno Aapa, Founder/CTO, Eliot
Speakers
avatar for Erno Aapa

Erno Aapa

Founder/CTO, Eliot
Erno Aapa is a Co-Founder of Polar Squad, Founder of Eliot IoT container platform and founder of Finnish DevOps community with over ten years experience from development, operations, and team leading in the software industry and over five years from DevOps. He is constantly researching... Read More →


Tuesday June 26, 2018 14:00 - 15:00 CST
Level 3, Parkview Foyer

14:00 CST

Office Hours: Michael Hrivnak, Principal Software Engineer, Red Hat, Inc.
Speakers
avatar for Michael Hrivnak

Michael Hrivnak

Principal Software Engineer, Red Hat, Inc.
Michael Hrivnak is a Principal Software Engineer at Red Hat. During his time as Team Lead for the Pulp project, he became involved in solving real-world container orchestration problems. He now works in that domain as part of the Automation Broker project. With experience in both... Read More →


Tuesday June 26, 2018 14:00 - 15:00 CST
Level 3, Parkview Foyer

14:10 CST

Using TARS to Code in Java - Chen Yu, Tencent
Using TARS to Code in Java. 

Speakers
CY

Chen Yu

Senior Technical Engineer, Tencent


Tuesday June 26, 2018 14:10 - 14:50 CST
VIP4-3

14:20 CST

Big Data Global Practice and Arch Evolution in Lenovo - Yu Chentao, Lenovo (slides attached)
Introducing Lenovo's seven years of big data platform practices, gradually expanding from departmental support to supporting Lenovo's hundreds of millions of products and users worldwide, extending from China to global coverage, and how to address the global data privacy protection and large-scale data cross-regional Access and multiple mixed computing issues.

By expanding open source technology, the open source big data platform has been gradually equipped with ten thousand computing tasks graphical management and scheduling, fine-grained layered security control, comprehensive metadata management capabilities, and flexible computing and scheduling capacities based on docker technology. At the same time, how to build a unified data lake and expand the big data computing engine to support the CRUD and stored procedure of traditional data warehouses in a typical large-scale manufacturing enterprise so that open source big data technology begins to gradually replace the traditional OLAP Scene, becomes the foundation of new IT architecture.

Speakers
avatar for Yu Chentao

Yu Chentao

Executive Director, Distinguished Researcher, Lenovo
Yu Chentao as the executive director, distinguished researcher of Lenovo big data business had applied more than 110 patents in Lenovo. He is also the leading talents of Zhongguangcun and professor-level engineer. He had designed the global manufacturing support platform which help... Read More →



Tuesday June 26, 2018 14:20 - 15:00 CST
310

14:20 CST

14:20 CST

Blockchain Practice on Public Service - Michael Dong, ChainNova
The future vision of Blockchain is to become the infrastructure of a nation and a city. From its own characteristics, it has the ability to store and circulate credible information for all kinds of public services. Currently, ChainNova is committed to the research and practice of blockchain on public services including supply chain, shipping, logistics, and electric power industry, etc, and is collaborating with some of the top 500 companies in the world. ChainNova is also dedicated to promote the application of blockchain technology in the field of public service jointly with International Telecommunications Union as the champion of Focus Group-DLT public service and government group.

Speakers

Tuesday June 26, 2018 14:20 - 15:00 CST
311A
  Blockchain

14:20 CST

A Day in the Java Developer’s Life, with a Taste of Kubernetes - Arun Gupta & Peter Dalbhanjan, AWS
Deploying your Java application in a Kubernetes cluster could feel like Alice in Wonderland. You keep going down the rabbit hole and don’t know how to make that ride comfortable. This no-slide and code-only session will explain how a Java application consisting of different microservices can be deployed in a Kubernetes cluster. Specifically, it will explain the following: -Show a Java application with three microservices -How this application is packaged as a Docker image -Create Kubernetes manifests -How Helm charts are created and hosted in a Helm repository -Test in a local environment such as minikube -Attach debugger (may need to find out if tooling exists in this area) -Install Istio in k8s, show service visibility -Install k8s on AWS -Migrate application from a local cluster to a cluster in the Cloud -Setup deployment pipeline -Use an Alexa skill to scale the application -Change application, show A/B using Istio

PLEASE VISIT: https://github.com/arun-gupta/java-k8s  

Speakers
avatar for Arun Gupta

Arun Gupta

Head of the Open Source Program Office, Apple
Arun Gupta is head of the Open Source Program Office at Apple and chairperson of CNCF Governing Board. Previously, he worked at Amazon, partnering  with multiple engineering teams to help define their open source strategy. He has spent over a decade at Sun Microsystems and Oracle... Read More →


Tuesday June 26, 2018 14:20 - 15:00 CST
309A

14:20 CST

Secure, Controllable and Reliable Container Image Management and Distribution - Jia Zou & Haining (Henry) Zhang, VMware (slides attached)
As the footstone of containerized platforms, container image management plays a very import role in the cloud native ecosystem. In this presentation, we will focus on the container image management and distribution by using the open source enterprise-grade image registry Project Harbor. Common practice is discussed on how to make the container image management secure, controllable and reliable to meet the needs of enterprises.

The session will cover:
1) Introduction of image management and open source image registry – Project Harbor;
2) Secure image management through RBAC, digital signature and vulnerability scanning;
3) Controllable and reliable container image distribution, including remote replication, control policy , Helm Chart deployment and serving as an image registry of Kubernetes;
4) Case study on image management in DevOps pipeline.

Speakers
avatar for Henry Zhang

Henry Zhang

FATE TSC member, VMware
Haining Henry Zhang is a Technical Director at VMware China R&D, where he leads the development and incubation of projects on emerging technologies such as AI/ML, cloud native applications, and blockchain. He is the founder of CNCF's graduated project, Harbor, and currently serves... Read More →
avatar for Steven Zou

Steven Zou

Harbor Maintainer, VMware
Jia Zou (Steven) is a staff engineer of VMware China R&D. He is now working on the open-source Project Harbor that is an enterprise-class cloud-native artifact registry as a core maintainer and architect. He previously has worked in HPE, IBM, and Agilent as software engineer for many... Read More →



Tuesday June 26, 2018 14:20 - 15:00 CST
309B

14:20 CST

Comparisons of Cloud Native Communities - Swetha Repakula & Morgan Bauer, IBM (slides attached)
Day by day, the number of open source projects continues to increase. Each project has unique communities and practices different development methodologies. This talk will focus on the Docker, Kubernetes and Cloud Foundry cultures and outline their main differences and commonalities. The projects have different review processes from the pair programming model to the LGTM process, an interesting artifact of GitHub. Becoming a committer on CF relies on the Dojo, while Docker establishes a meritocracy of peers and Kubernetes behaves similarly with individual sponsors.

Morgan will share his journey of becoming a maintainer on the core Docker Engine and a founding member of the Kubernetes Service Catalog. Swetha will tell her story of becoming a contributor to the Diego team and what she has learned from Cloud Foundry. By sharing their experiences, they hope to encourage others to participate.

Speakers
avatar for Morgan

Morgan

Sr Software Engineer, IBM
After contributing to Docker & Kubernetes for 3 years, Morgan has gained valuable insight into the varying culture around open source container technology. Pivoting towards blockchain technologies has landed Morgan in Hyperledger Fabric. Morgan is a maintainer on the core Docker Engine... Read More →
avatar for Swetha Repakula

Swetha Repakula

Open Source Contributor, IBM
Swetha Repakula is currently a software engineer at IBM’s Open Technologies and a member of the Technical Steering Committee at Hyperledger. For the last two years, she has been working on Hyperledger Fabric, specifically on its EVM integration. Previously she was a full time open... Read More →



Tuesday June 26, 2018 14:20 - 15:00 CST
306B

14:20 CST

Panel Discussion: Deep Learning - Moderated by Jim Zemlin, Executive Director, The Linux Foundation
Moderators
avatar for Jim Zemlin

Jim Zemlin

Executive Director, The Linux Foundation
Jim Zemlin’s career spans three of the largest technology trends to rise over the last decade: mobile computing, cloud computing, and open source software. Today, as executive director of The Linux Foundation, he uses this experience to accelerate innovation in technology through... Read More →

Speakers
avatar for Dr. Junlan Feng

Dr. Junlan Feng

Chief Scientist, China Mobile Research Institute
Junlan Feng is Vice Chairman of the China Artificial Intelligence Industry Alliance, Chief Scientist at China Mobile, General Manager of AI and Intelligent Operation R&D Center, Board Chair of Linux Foundation Network.Dr. Feng received her Ph.D. on Speech Recognition from Chinese... Read More →
avatar for Peixin Hou

Peixin Hou

Chief Architect of Open Software and Systems, Huawei
Peixin Hou is currently serving as the Chief Architect of Open Software and Systems in the Central Software Institute, Huawei. He has been working in the software industry for over 20 years and has experience in operating systems, mobile software, media processing, and cloud computing. Peixin... Read More →
avatar for Dr. Huan Jun

Dr. Huan Jun

Head of Baidu Beijing Big Data Lab, Baidu
avatar for Todd Moore

Todd Moore

Vice President - Open Technology, IBM Developer and Developer Advocacy, IBM
Open Source innovator, Agile and Business development strengths. Industry leader in open source community development. Extensive experience in creating HW and Software architectures for desktops, servers, middleware, and device middleware. Strong background in performance, performance... Read More →
avatar for Dr. Xiaolong Zhu

Dr. Xiaolong Zhu

Senior AI Architect of Tencent and Member of LF Deep Learning TAC, Tencent
Dr. Xiaolong Zhu is a senior AI architect of Tencent and Member of LF Deep Learning TAC. Xiaolong Zhu engages in deep learning related application research and development. He has participated in the distributed training of speech recognition, art filter, gesture recognition and other... Read More →


Tuesday June 26, 2018 14:20 - 15:00 CST
Plenary Hall B

14:20 CST

Kubernetes Security Best Practices - Ian Lewis, Google
Containers give developers the ability to isolate applications from one another, but that’s not enough. Resource isolation is much different than security isolation. How do we make applications deployed in containers more secure? How do we apply existing tools like SELinux and AppArmor, and seccomp to our containers running in Kubernetes? How can we apply the policy to our network and services to make sure applications only have access to what they need and nothing more?

In this talk, attendees will learn about the risks and attack surfaces and see tools like PodSecurityPolicy, SELinux, AppArmor, and seccomp in action to improve the security of containers deployed in Kubernetes. We’ll then go up the stack and learn how to apply network policy to containers to further improve security.

Speakers
avatar for Ian Lewis

Ian Lewis

Software Engineer, Google
Ian is an engineer at Google working on Supply Chain Security. Ian has been living in Tokyo since 2006 and has had various developer and operations roles throughout his career while staying active in the open-source developer community. Ian is a contributor to the SLSA framework and... Read More →


Tuesday June 26, 2018 14:20 - 15:00 CST
307A

14:20 CST

ACRN Hypervisor - Yu Wang, Intel (slides attached)
Today’s connected devices are increasingly expected to support a range of hardware resources, operating systems, and software tools/applications. Virtualization is key to meeting these broad needs, however, existing solutions don’t offer the right size and flexibility for IoT. Data center hypervisor code is too big, doesn’t offer safety-critical capabilities, and requires too much overhead for embedded development. Proprietary solutions are expensive and make it difficult to deliver long-term product support. In this presentation, Yu Wang will introduce a flexible, lightweight reference hypervisor, built with real-time and safety-criticality in mind, optimized to streamline embedded development through an open source platform. Its name is ACRN which is a Linux Foundation project.

Speakers
avatar for Yu Wang

Yu Wang

Technical Leader, Intel
Yu Wang is from Intel as software engineer, and working on ACRN hypervisor project as sub-maintainer now. Yu presented "ACRN™: A Big Little Hypervisor for IoT Development" session in 2018 LC3 and 2018 WG1 as primary speaker(no co-speaker). Besides, Yu have lots of speaking experience... Read More →



Tuesday June 26, 2018 14:20 - 15:00 CST
306A
  IoT & M2M

14:20 CST

Accelerating NVMe I/Os in Virtual Machine via SPDK vhost - Ziye Yang & Changpeng Liu, Intel (slides attached)
SPDK (storage performance development kit, http://spdk.io) is an open source library used to accelerate the storage service (e.g., file, block) especially those service built on PCIe SSDs (e.g., 3D XPoint SSDs).

In this presentation, we would like to introduce SPDK user space vhost* solution (i.e., vhost-scsi/blk/NVMe), which can be used together with QEMU/KVM to accelerate virtio-scsi, virtio-blk and even emulated NVMe controller inside Guest OS for VMs. Relying on SPDK vhost* solution, the performance of I/Os inside VMs can be greatly improved compared (e.g., I/O IOPS increasing, I/O latency decreasing ) with an existing solution (e.g., original QEMU emulation solution, kernel vhost* solution). Moreover, SPDK vhost* solution is adopted by many cloud service providers (e.g., Alibaba).

Speakers
avatar for Changpeng Liu

Changpeng Liu

Cloud Software Engineer, Intel
Changpeng is a Cloud Software Engineer in Intel. He has been working on Storage Performance Development Kit since 2014. Currently, Changpeng is a core maintainer for the SPDK. His areas of expertise include NVMe, I/O Virtualization, and storage offload on IPU.
avatar for Ziye Yang

Ziye Yang

Staff Cloud software engineer, Intel
Ziye Yang is a staff software engineer at Intel and is currently involved in cloud native related projects. Before that, Ziye worked at EMC for 4.5 years. Ziye is interested in system virtualization, file system and storage related research and development work. Ziye currently has... Read More →



Tuesday June 26, 2018 14:20 - 15:00 CST
203AB
  KVM

14:20 CST

Shared Virtual Addressing - Yisheng Xie & Bob Liu, Huawei (slides attached)
Shared Virtual Addressing (SVA) means share process address spaces with devices. It is also called Shared Virtual Memory(SVM) by OpenCL and some IOMMU architectures. Sharing process address spaces with devices allows to rely on core kernel memory management for DMA, i.e. after apply SVA, device is able to perform DMA on buffers obtained with simple malloc by using the points it return, which highly remove some complexity from application and device drivers, especially when device DMA buffer use the advance data structure like list, tree or graph. Meanwhile, based on device’s IO page fault, the device can use memory on demand, which can reduce the use of memory.

Speakers
BL

Bob Liu

Principal Engineer, Huawei
Software Architect of Huawei OS Kernel lab. He is now working in Huawei OS lab team, before that he has worked in Oracle for more than 7+ years on memory management, KVM projects. In this project, Bob is working on SVA solution architecture design.
YX

Yisheng Xie

Principal Engineer, Huawei
Principal Engineer, Huawei Kernel Dep. He is now working in Huawei Kernel team. Before that he has works for samsung for 5+ years on drivers and smart phone sulotion projects. In this project, Yisheng is working on SVA solution design, implement and integration.



Tuesday June 26, 2018 14:20 - 15:00 CST
307B
  Linux Systems

14:20 CST

Multiple Networks and Isolation in Kubernetes - Michael Xie & Kaveh Shafiee, Huawei Technologies (slides attached)
Kubernetes currently only supports one network interface per pod, and the entire cluster has one flat network plane. In this presentation, we will share our implementation on enabling multiple networks and network isolation for NFV customers. Which includes physical network abstraction to enable the ability for pods to select physical network, and logical network for users to define network namespace and isolation. In addition, we enabled multiple plugin support at runtime, Kubernetes cluster can be deployed without binding to any specific network plugin, pods can choose network plugin in their own spec.

Speakers
KS

Kaveh Shafiee

Cloud Architect, Huawei Technologies
Cloud architect at Huawei Seattle office. He has been involved in numerous open-source projects. His topics of interest are container networking, container orchestration frameworks, multi-tenancy, distributed development platforms. Prior to joining Huawei, he was an architect at WindRiver... Read More →
avatar for Haibin Michael Xie

Haibin Michael Xie

Principal Architect, Huawei Technologies
Michael Xie is Principal Architect at Huawei PaaS team, working on container networking, container orchestration framework, PaaS platform and middleware services. Prior to joining Huawei he was a pricipal software engineer at AOL ads and senior software engineer at Microsoft working... Read More →



Tuesday June 26, 2018 14:20 - 15:00 CST
311B

15:00 CST

Coffee Break
Tuesday June 26, 2018 15:00 - 15:30 CST
Plenary Hall A

15:00 CST

15:00 CST

Using TARS to Code in PHP - Liang Chen, China Literature
Introduction of basic Design principle of TARS; Introduction of 3 different ways of using Client;
Remote log automatic address caller stat report abilities of Client Server solution, including a Tcp and Http server;
 Flexibility of Server communication protocol, tars and user-defined supported;
 Timer ability of Server;
Multiple components of TARS-PHP, you can use it on-demand; PHP Extension to improve performance; 
Automatic code generate tool to improve efficiency; 
Practice of this solution in China Literature. 

Speakers
LC

Liang Chen

Senior Software Developer, China Literature


Tuesday June 26, 2018 15:00 - 15:40 CST
VIP4-3

15:00 CST

PaddlePadele Fluid: Toward a Deep Learning Programming Language
Many deep learning frameworks use Python as the frontend language binding and CPP to build backend execution engine, but Python has many limitations such as its poor speed.

PaddlePaddle fluid is designed as a new deep learning programming language, it uses ProgramDesc as IR to describe the execution process of a neural network. ProgramDesc is composed by blocks, a block is a sequence of operations, each block will have its own scope, just like the stack, but they are different because backward pass needs to use the forward scope. Control flow operations like if/else/while is first class citizens in Fluid.

PaddlePaddle fluid tries to build a new deep learning programming language to make it easy to describe and train the neural network.


Tuesday June 26, 2018 15:00 - 16:00 CST
207

15:00 CST

Office Hours: Ben Shushu, Technical Consultant
Speakers
avatar for Ben shushu

Ben shushu

technical consultant, Running Linux Kernel Group
Benshushu is a technical consultant in China, he wrote a linux kernel analysis book on 2017 which is popular in China. On 2019, he published a new book about linux kernel and education.


Tuesday June 26, 2018 15:00 - 16:00 CST
Level 3, Parkview Foyer

15:00 CST

Office Hours: Ian Lewis, Developer Advocate, Google
Speakers
avatar for Ian Lewis

Ian Lewis

Software Engineer, Google
Ian is an engineer at Google working on Supply Chain Security. Ian has been living in Tokyo since 2006 and has had various developer and operations roles throughout his career while staying active in the open-source developer community. Ian is a contributor to the SLSA framework and... Read More →


Tuesday June 26, 2018 15:00 - 16:00 CST
Level 3, Parkview Foyer

15:30 CST

Flowchain - A Hybrid Blockchain for the IoT and Tokenized Hardware - Jollen Chen, Flowchain.co (slides attached)
The IoT blockchain has become an emerging technology in the IT industry. Despite a myriad of studies on the IoT blockchain, it is still a challenge that how an IoT blockchain system is investigated to benefit the IoT and hardware industry. In this presentation, Jollen will show a hybrid blockchain technology based on Flowchain and Hyperledger Fabric for both the IoT and hardware industry to utilize the "tokenized hardware" scheme to facilitate such technical challenges. Tokenized hardware can gain viable benefits such as security, privacy, and decentralization by associating cryptocurrency tokens to hardware devices.

Speakers
avatar for Jollen Chen

Jollen Chen

CEO, Flowchain
Jollen Chen is the founder and lead developer of Flowchain



Tuesday June 26, 2018 15:30 - 16:10 CST
311A
  Blockchain

15:30 CST

A Novel Flow Network Graph Based Scheduling Approach in Kubernetes - Zefeng (Kevin) Wang, Huawei (slides attached)
Today’s Kubernetes clusters can comprise of 5,000-10,000 nodes, increase by an order of magnitude from original design specs. The default Kubernetes scheduler dates back from earlier more modest deployments. It is queue-based, processing unscheduled pods in a sequential fashion. For a large Kubernetes cluster, such scheduler processing logic can introduce long, even unbounded scheduling latencies, negatively affecting overall throughput for workload deployments.

This talk outlines how Kubernetes is a victim of its own success, scheduling-wise. It lays out the current pod queuing challenges and describes a novel scheduling approach based on Flow Network Graph technique, enabling low workload scheduling latencies at scale. The presentation details the resulting extreme efficiencies and high-quality placement decisions of such an approach and the accompanying pluggable scheduling policies.

Speakers
avatar for Kevin Wang

Kevin Wang

Lead of Cloud Native Open Source Team, Huawei Cloud
Kevin Wang is a contributor in the CNCF community since its beginning, leader of the cloud native open source team at Huawei, and co-founder of the CNCF KubeEdge, Volcano and Karmada projects.Kevin has contributed to Kubenretes upstream for years and now spends 100% of his work and... Read More →



Tuesday June 26, 2018 15:30 - 16:10 CST
309B

15:30 CST

Cloudbursting with Kubernetes - Irfan Ur Rehman & Quinton Hoole, Huawei Technologies
Cloudbursting is one of the most useful features of cloud computing for applications with high traffic volumes during only some hours in a day, or only during some days in a month.
Kubernetes as of release 1.9 supports both application auto-scaling based on metrics such as CPU utilization and cluster node auto-scaling based on application workload (pods) needs.

Kubernetes also supports cluster federation, which enables binding of multiple clusters into a single observable unit from the point of view of a user.

This presentation will discuss how we’ve used these features to reliably burst from a priority/ low-cost cloud cluster to another, using Kubernetes. We’ll introduce a possible spec, a reference design, discuss the missing pieces and a provide a demo.

Speakers
avatar for Quinton Hoole

Quinton Hoole

Technical Vice President, Futurewei
https://www.linkedin.com/in/quintonhoole/YouTube me for previous presentations.CNCF TOC Member
IU

Irfan Ur Rehman

Sr. Software Engineer, Turbonomic
Irfan is a senior engineer associated with the Advanced Engineering group at Turbonomic. In his current role he is tasked with drafting multi cluster capabilities for Turbonomic’s analytics platform. He has also been associated with SIG Multicluster, particularly Kubernetes Cluster... Read More →


Tuesday June 26, 2018 15:30 - 16:10 CST
309A

15:30 CST

Practicing Container and Microservice in Huawei Cloud - Yang Zhao, Huawei (slides attached)
In Huawei, cloud computing plays as a key part of emerging business, and leveraging open source technology is a principle in cloud business. In this session, I will share the cases from real customers, who are embracing open source projects such as Kubernetes, Docker, and ServiceComb to build and expand their business in Huawei cloud platform.

Speakers
avatar for Yang Zhao

Yang Zhao

Lead Solution Architect, Huawei Technologies
Yang Zhao is in charge of solution design and key account delivery of application services in Cloud Business Unit of Huawei Technologies. His technical focus includes container, microservice, cache, message queue and API gateway. The target customers span across Huawei Cloud, Deutsche... Read More →



Tuesday June 26, 2018 15:30 - 16:10 CST
310

15:30 CST

MultiDroid: A Novel Solution to Consolidate Interactive Physical Android Clients on One Single Computing Platform - Bin Yang & Shoumeng Yan, Intel R&D Center Shanghai (slides attached)
Beyond smartphone, Android has been used as interactive devices in other scenarios such as retailer shops and connected cars. These scenarios require multiple or even many standalone Android devices to provide uncompromised Android experience for every single user. Meanwhile, computing capacity grows fast even on relatively low-cost computing platforms. To save the total cost of ownership, this presentation presents MultiDroid, a container based virtualization architecture running multiple standalone Android clients simultaneously with native hardware device performance and UI experience on a single physical device in an isolated and secure manner. A prototype of MultiDroid that runs three real clients on a single Intel platform has been implemented and performance data demonstrates that Multi-Droid imposes only minor runtime over-head.

Speakers
SY

Shoumeng Yan

Senior Staff Research Scientist, Intel Labs China
Shoumeng is a senior staff research scientist at Intel Labs China, with a focus on isolation and containerization technologies. Shoumeng is combining security together with safety towards secured safety for autonomous machines including robots, drones and self-driving cars. Shoumeng... Read More →
BY

Bin Yang

OS Architect, Intel
Bin is OS architecture in Intel cooperation. He focuses on Android internal, Container, virtualization, persistent memory, cloud computing, cloud gaming, and cloud IOT. He got computer science master from Zhejiang University in 2004. He holds multiple US patents and academic international... Read More →



Tuesday June 26, 2018 15:30 - 16:10 CST
306B

15:30 CST

Panel Discussion: Real-life Case Studies of how Blockchain is being Adopted into the Real Economy in China - Moderated by Ling Shao, CTO, Easy Visible Supply Chain Management Co Ltd

You will hear firsthand from Dr. Yu Jianing, Director of The Institute of Industrial Economics at the Ministry of Industry and Information Technology, who authored the Information Center of the Ministry’s recently released Blockchain Industry White Paper. Dr. Yu will discuss the view of blockchain in China, where it is now and how it will develop in the coming years. You will also hear from industry experts involved in the development of leading permissioned blockchain applications in China about their progress, opportunities and challenges, and how blockchain is being integrated into many sectors.


Moderators
Speakers
DY

Dr. Yang Yue Feng

Dr. Yang Yue Feng is at the Bank of Jiangsu.
DY

Dr. Yu Jianing

Dr. Yu Jianing is the director of The Institute of Industrial Economics at the Ministry of Industry and Information Technology
HB

Hai Bo Sun

Hai Bo Sun is the Director of Blockchain R&D at JD.com.
avatar for Spark Zhang

Spark Zhang

Blockchain Strategic Expert, Huawei
张小军是华为区块链战略专家,在华为工作15年,从2003年加入华为工作。2003年-2005年主要在网络产品线做开发工作,负责路由器、防火墙的软件开发,2005年到2009年进入战略Marketing部门,负责网络解决方案的设计与营销,2009年进入华为公司战略部,并曾经做过两年日本区域战略部主任。张小军学士学位,毕业于华北电力大学  Xiaojun... Read More →


Tuesday June 26, 2018 15:30 - 16:10 CST
Plenary Hall B

15:30 CST

Containerized Monitoring: Adaption to Different Infrastructures and Verification Schemes - Yang (Gabriel) Yu, Huawei & Emma Foley, Intel
In this presentation, monitoring with its containerized solutions to different infrastructures and verification schemes are discussed which are developed in OPNFV community. Monitoring of the system behaviors establishes a common basis and provides standardized metrics sets for different applications. It helps developers, system maintainers, etc., to locate the root causes, to alarm for malfunctions, to analyze the system behaviors, etc. Containerized monitoring solutions are proved to be more isolated and more adaptive to different systems.

Demonstrations of how developing or configuring containerized monitoring adaptions to different OPNFV OpenStack deployments, different K8S applications, different verification schemes are presented. Questions about automation, visualizing bottlenecks, multi-dimension dashboarding, etc., are also discussed in the presentation.

Speakers
EF

Emma Foley

Software Engineer, Intel
Emma is a Software Engineer in the Network Platforms Group in Intel. Emma has worked on Service Assurance, making more statistics available for the OpenStack cloud, by enabling collectd stats and events to be used in OpenStack. She is committer to the OPNFV Barometer project, and... Read More →
YG

Yang (Gabriel) Yu

Project Manager, Huawei
Gabriel is a project manager on Open Source Development Team at Huawei. He is currently involved in LF Edge as SPC member and LF Networking as PTL of the OPNFV Bottlenecks project. His experience also includes leading testing working group and long duration testing initiative in OPNFV... Read More →


Tuesday June 26, 2018 15:30 - 16:10 CST
307A
  Infrastructure & Automation

15:30 CST

Multimodal Operating System - Bridge Traditional and Software-Defined Infrastructure - Kai Dupke & Raj Meel, SUSE (slides attached)
As organizations around the world transform their enterprise systems to embrace modern and agile technologies, multiple infrastructures for different workloads and applications are needed. This often means integrating cloud-based platforms into enterprise systems, merging containerized development with traditional development, or combining legacy applications with microservices. To bridge traditional and software-defined infrastructure, a multimodal operating system is needed. In this session you will learn about multimodal IT and the design requirements of an operating system to support multimodal IT environment.

Speakers
KD

Kai Dupke

Senior Product Manager, SUSE
Kai Dupke is Senior Product Manager at SUSE. He is responsible for the SUSE flagship product SUSE Linux Enterprise Server 15. In the past, he has also led High Availability, Real Time, and High-Performance Computing. Before joining SUSE, Kai Dupke was head of Linux, Open Source, and... Read More →
RM

Raj Meel

Global Product Marketing Manager, SUSE
Raj is a Global Product Marketing Manager at SUSE. Raj is responsible for marketing of SUSE Linux Enterprise Server, SUSE Live Patching and Container technologies. In the past, he also launched SUSE CaaS Platform. Raj is a passionate technologist with 25+ years of IT expertise as... Read More →



Tuesday June 26, 2018 15:30 - 16:10 CST
306A

15:30 CST

Runtime VM Protection By Intel Multiple Key Total Memory Encryption - Kai Huang, Intel Corporation (slides attached)
Today cloud data protection is a critical requirement, and it will be even more important in the future as we have more in-depth and sensitive data in the cloud for new types of workloads (such as IoT and machine learning). Since VMs (Virtual Machines) are the key container of such data, it is crucial to protect VMs at rest (as in storage), in-transit (as in network), and during execution.

Encryption is considered as the foundation technology for VM protection, and there are established encryption technologies for VMs at rest and in-transit. Intel Multiple Key Total Memory Encryption (MK-TME) is Intel platform's new hardware feature which supports VM encryption during runtime, thus completes VM protection in VM's entire lifecycle. In this presentation, we give you an introduction to Intel MK-TME, including its hardware architecture, Linux/KVM design, and typical deployment in the cloud.

Speakers
avatar for Kai Huang

Kai Huang

Software Engineer, Intel Corporation
Software engineer working on Linux/KVM enabling for Intel's latest virtualization technologies.



Tuesday June 26, 2018 15:30 - 16:10 CST
203AB
  KVM

15:30 CST

LKP-tests: A Comprehensive Performance Analysis Tool for Linux - Ying Huang, Intel Corporation
Nowadays there are many scattered benchmarks and tools for different Linux kernel sub-systems, which leads to a barrier to understanding the intricate details of the system. LKP-tests tool (LKP stands for Linux Kernel Performance) is an open source standalone tool, that allows to evaluate and analyze Linux kernel performance in a thorough way. It was originally used to run the benchmarks, analyze the results, and reproduce the issues in the famous 0-Day Linux kernel test service. Now, it helps us much in our Linux kernel performance optimization work. In this presentation, we will introduce the framework and main components of LKP-tests tool, how to use it to build, install, and run various benchmarks and test cases, and how to do analysis and comparison with various performance analysis tools. We will also illustrate how we use it to optimize performance for Linux kernel with examples.

Speakers
YH

Ying Huang

Senior Software Engineer, Intel Corporation
Ying Huang is a senior software engineer in Intel's Open Source Technology Center (OTC). At Intel over 10 years, he's worked on Linux kernel, including x86 boot, kexec, RAS, etc. And now, he is working on 0day Linux kernel performance testing and memory management subsystem performance... Read More →



Tuesday June 26, 2018 15:30 - 16:10 CST
307B
  Linux Systems

15:30 CST

Kubernetes Application Management Based on Helm and Operator - Peng Jiang, Rancher Labs (slides attached)
Kubernetes offers a variety of resource description types based on service granularity. Describing an application system, especially microservice architecture system, requires a combination of a large number of Kubernetes resources. For stateful applications, complex operation and maintenance management operations and more domain knowledge are often required. This talk shows you how to use Helm, a community-driven approach to Kubernetes application management, to simplify deployment and management of applications, how to create application templates, build Kubernetes application stores, and how to automate the operation and maintenance of applications using operators.

Speakers
avatar for Peng Jiang

Peng Jiang

Technical Director of Rancher Labs in Greater China, Rancher Labs
Peng Jiang, Technical Director of Rancher Labs in Greater China. Former Microsoft Senior Technical Project Manager and Solution Specialist, Citrix's Chief Consultant. More than 10 years' work experience in unified communications, application delivery, virtualization, cloud computing... Read More →



Tuesday June 26, 2018 15:30 - 16:10 CST
311B

15:40 CST

15:50 CST

Using TARS to Code in NodeJS - Zheng Subo, Tencent
Speakers
ZS

Zheng Subo

Senior Technical Engineer, Tencent


Tuesday June 26, 2018 15:50 - 16:30 CST
VIP4-3

16:00 CST

Streaming Computation in Baidu
As the big data era comes, computing endless data in real-time has become a necessity in many scenarios. Take Baidu as an example, trillions of data comes to real-time computation platform everyday. From the year of 2011, DStream, a true streaming computation engine with its own scheduler system have been proposed, implemented and put into practice. It supports low-level but flexible API and configuration. Moreover, it support logging / monitoring / paging / tracing / releasing / dictionary / etc., which are crucial in production. Along the time, as DStream are for developers and needs learning curve, Spark Streaming are introduced for data scientists. Our team follows the Spark community. Moreover, best practices with DStream in production complexity are contributed back to SparkStreaming. We adapt Baidu home-brewed storage, messaging system, PaaS, etc., to Spark Streaming. In this session, we’d like to share our experience with DStream and Spark Streaming in Baidu.

Tuesday June 26, 2018 16:00 - 17:00 CST
207

16:20 CST

The Application and Case Sharing of Blockchain + Regtech - William Zuo, Shanghai Gingkoo Financial Technology Co.,Ltd (slides attached)
In the speech, starting from the dialectical and unified relationship between financial supervision and financial innovation, this paper points out the necessity and urgency of the supervision of regulatory science and technology development. Citing actually landed applications and cases of Gingkoo Financial Technology in blockchain + regtech, such as using blockchain technology to create a credit alliance chain solution for SME financing, the paper put forward the use of blockchain technology to develop regtech, and innovatively put forward more and bigger application scenarios of blockchain in supervision and compliance, thus promoting the financial innovation and regulation to form a good interactive relationship, which can further promote the healthy development of China's financial industry.

Speakers
avatar for Peng Zuo

Peng Zuo

CEO, Shanghai Gingkoo Financial Technology Co.,Ltd
Gingkoo Financial Technology is one of the first batch of enterprises to enter the technology ecology of blockchain in China. Especially in the area of blockchain supervision and compliance, the company has done a lot of exploration and accumulated a wealth of industry-leading application... Read More →



Tuesday June 26, 2018 16:20 - 17:00 CST
311A
  Blockchain

16:20 CST

Accelerate DevOps for Cloud Native Application on Kubernetes with Open Source Tools - Rome Li, Microsoft (slides attached)
When migrating applications to the cloud or developing cloud native applications, how do you accelerate DevOps for Kubernetes? Newcomers to DevOps on Kubernetes may experience a steep learning curve. We will share how to use tools in development environment to streamline the development, deployment and debugging processes in a Kubernetes cluster running on top of cloud. We will also introduce popular CI/CD tools (Jenkins, Ansible) to help infrastructure developers automate application build, cloud provisioning and Kubernetes deployments. Welcome join us and enjoy live demos with a common cloud native Java application.

Speakers
avatar for Rome Li

Rome Li

Senior Software Engineering Manager, Microsoft
Rome Li works in Microsoft on Visual Studio team. He’s now focusing on building tools to support Java development in all kinds of environments including Visual Studio Code, Eclipse, IntelliJ, and Maven. His team is now working on several open source projects including Java language... Read More →



Tuesday June 26, 2018 16:20 - 17:00 CST
310

16:20 CST

Securing Your Serverless Endpoint with Webtask - Md. Shahbaz Alam, Mozilla / Auth0 (slides attached)
The way we write APIs is changing. SPA frameworks like Angular are shifting the paradigm of API consumption and to be effective developers we have to keep up. We often dedicate a lot of time in crafting powerful APIs that interact with many different clients but overlook proper security measures that can come back to haunt us.In this talk, we'll look at the proper way to secure our API's with JSON Web Tokens. We'll go from learning what JSON Web Tokens are, why they're the driving force in API security, and to put theory into practice actually build a real-world implementation using Node.js and Angular where we'll show common best practices.
Webtask allows you to build applications without thinking about infrastructure. Simply write your server-side logic, deploy your functions via the Webtask CLI, and access your serverless backend over HTTP.

Speakers
avatar for Md. Shahbaz Alam

Md. Shahbaz Alam

Technical Evangelist, Auth0 / Mozilla
I am a co-founder of a Startup where we built products based on emerging technologies. Technical Evangelist at Mozilla and Auth0. Love spreading the knowledge. I am an open source enthusiast, volunteer for many organizations, Mozilla, Auth0, Brave, DuckDuckGo to name few. I believe... Read More →



Tuesday June 26, 2018 16:20 - 17:00 CST
309B

16:20 CST

Using Scale-Out Data Replication for Disaster Recovery Planning at NTT - Luwei He, Huawei
Disaster Recovery (DR) planning is crucial to any business and especially service providers such as NTT, whose core business is based on SLA’s. Replication which is the simple concept of copying data from one system to another across sites, has matured over the years, providing better Recovery Time Objective (RTO) and Recovery Point Objective (RPO) for DR. In this session, we will show how OpenSDS is enabling replication for Kubernetes clusters across sites and can scale out to match the needs of cloud-native applications. Besides, we will talk about DR planning at NTT - architecture and design, RTO and RPO and other requirements, and consideration in adopting OpenSDS scale-out data replication and other replication technologies.

Speakers

Tuesday June 26, 2018 16:20 - 17:00 CST
309A

16:20 CST

Why Does the Obstacle of Enterprise Adoption in OSS Come from Engineers? - Li Jiansheng, OCSelected (slides attached)
Open-source software has impacted nearly every product, every project, every data center, and every interaction that we have with technology today. But a lot of company just use OSS and don't participate or contribute to upstream. So, they are not maximizing the use of good open source software.ultimately, OSS  become  the business‘ burden. the organization lose.

So what is the obstacle to enterprise adoption in OSS? It's engineer! The speaker tried to figure out the reasons for it through years of observation and analysis. and give advance methods to resolve this.

Speakers
avatar for Li Jiansheng

Li Jiansheng

Open Source Community Manager, QingCloud
LiJiansheng,Network ID is 适兕,Open Source believer,QingCloud Open Source Community Manager, KaiYuanShe Executive Committee & Chief Editor, The writer of OCSelected(http://www.ocselected.org/) which is collector article of the way of open source , over 10 years open source developing... Read More →



Tuesday June 26, 2018 16:20 - 17:00 CST
306B
  Emerging Technologies & Wildcard

16:20 CST

Convergence of Virtual Machines and Containers Orchestration using KubeVirt - Chunfu Wen, Red Hat (slides attached)
Whenever in order to implement and manage cloud: IASS and CASS, two separate orchestration tool, namely libvirt and Kubernetes respectively, are used.
Customers need to take care of both of them in two infrastructure stacks even sometimes they are built on each other.

Wouldn't it be better if we can manage VMs and containers using the same API? KubeVirt, a Kubernetes add-on to manage virtual machines, is one way to satisfy it.

This talk aims to introduce KubeVirt, a common ground for virtualization solutions on top of Kubernetes, its design, and implementation, and finally present one live demo.

Speakers
avatar for Chunfu Wen

Chunfu Wen

principal software quality engineer, Red Hat
I am an open source contributor and promoter.I work at Red Hat, and have 17+ years working experiences in various companies such as:Oracle, Motorola, Siemens.



Tuesday June 26, 2018 16:20 - 17:00 CST
307A
  Infrastructure & Automation

16:20 CST

vhost Dataplane in Qemu - Jason Wang, Red Hat (slides attached)
Several limitations were spotted for the popular vhost-user protocol in recent years. Most are due to the design of a split device model which tries to offload datapath out of qemu: 1) the protocol was tightly coupled with virtio which brings extra complexity of implementing new features 2) datapath was offloaded completely which will lead poor performance (e.g the vIOMMU integration, 3) the increase of attack surface. So in this presentation, a new kind of vhost that was implemented through qemu IOThread was introduced to try to address all the above drawbacks. The talks will first discuss the design of vhost dataplane and how it addresses the above limitations. Then A prototype implementation and detailed comparison between vhost data plane vs vhost-user will be presented. At last the performance numbers and future work will be discussed.

Speakers
JW

Jason Wang

Senior Principal Software Engineer, Red Hat
Co-maintainer of kernel virtio, vdpa and vhost drivers. Maintainer of Qemu networking subsystems. Author of vDPA support in Kernel.



Tuesday June 26, 2018 16:20 - 17:00 CST
203AB
  KVM

16:20 CST

Advanced Disk Activity Tracking Tool - iotrace - Ahao Mu & Gavin Shan, Alibaba Inc (slides attached)
This topic presents the necessity to track disk IO activities from the perspective of processes, reveals the design of the advanced tracking tool - "iotrace", which bases on trace events. The audience will benefit to acknowledge the necessity to track disk IO activities, hands-on experience to use the tool.

Speakers
AM

Ahao Mu

Software Engineer, Alibaba Inc
Ahao Mu has been working for operating system department of Alibaba Inc after acquiring a bachelor degree in computer science. Currently, Ahao Mu works on Linux kernel development work, especially filesystem, block layer, NVMe etc to improve their performance and thus cost down for... Read More →
GS

Gavin Shan

Senior Software Engineer, Redhat
Gavin is currently employed by Redhat to work on KVM support for arm64. The most intrested areas spans from memory management to live migration and QEMU etc. Prior to that, Gavin has been working on Linux kernel and driver for over 10 years, used to be employed by IBM to maintain... Read More →



Tuesday June 26, 2018 16:20 - 17:00 CST
307B
  Linux Systems

16:20 CST

Light Weight Computing for IOT/Edge Using Pulsar Functions - Sijie Guo, Streamlio
IOT/Edge Computing has grown up considerably with sensors becoming ubiquitous everywhere. Because these deployments are often very resource constrained, the resource footprint of any IOT solution is a very important criteria. And since these deployments are numerous in number, their manageability is also very important.

Apache Pulsar providing both durable messaging as well as lightweight computing in the form of Pulsar functions is an ideal solution to these above environments. Since functions can be embedded within the broker, it provides end-to-end collect/store/compute/send functionality all within a single jar. Thus the deployment/management footprint becomes very simple. A Rest based interface makes management a breeze.

In this talk, he will talk about Apache Pulsar Functions, its expressibility and demonstrate the ease with which you can write an application.

Speakers
avatar for Sijie Guo

Sijie Guo

Co-Founder, Streamlio
Sijie Guo is the cofounder of Streamlio, a company focused on building next generation real time processing engines. Streamlio mainly focus on 3 open source projects, which include Apache BookKeeper, Apache Pulsar, and Heron. Previously, he was the tech lead for messaging group... Read More →


Tuesday June 26, 2018 16:20 - 17:00 CST
311B
  Networking & Orchestration

16:20 CST

Panel Discussion: Why Open Source Marketing Matters: For Projects, Users and Vendors - Moderated by Melissa Logan, Cloud Foundry Foundation

When people think of an open source “contributor” they are likely picturing the developers who contribute code. But open source projects require a variety of contributions--from development to documentation to release management to marketing. The role of marketing in open source is critical but often overlooked and misunderstood. Marketing underpins the success of many open source communities, and when marketing strategy is executed proficiently, it enables these open source communities to thrive. Successful open source marketing builds a stronger ecosystem that bolsters the success of all involved, including project, vendors, and users. In this panel, open source marketing leaders will discuss the role of marketing, provide examples of open source projects powered by marketing, and offer insight into how marketing teams from both enterprises and open source projects can partner together to achieve greater results.


Moderators
avatar for Melissa Logan

Melissa Logan

The Linux Foundation
The Linux Foundation has been leading the open source software revolution since 2000. Melissa Logan joined in 2012 and launched and lead marketing for the LF's first hosted open source project in 2013. Since then the LF has become the home to hundreds of open source projects that... Read More →

Speakers
avatar for Lingli Deng

Lingli Deng

Technical Manager, China Mobile
Lingli obtained her Doctorate in Computer Application Technology from the Institute of Software, Chinese Academy of Sciences and joined China Mobile in 2009.She is a core member of the Novonet project which drives SDN/NFV strategy for China Mobile, and has been working on evaluation... Read More →
avatar for Dee Kumar

Dee Kumar

Vice President, Developer Marketing, Linux Foundation
Dee Kumar has more than 15 years of cloud computing experience. Her work at CNCF is focused on working with the developer and IT pro communities to advance open source projects at scale. Most recently, Kumar was Director of Product Marketing at Docker where she built and launched... Read More →
avatar for Anni Lai

Anni Lai

Head of Global Business Development, VP of Strategy & Business Development, Huawei
Anni leads the Operations of Huawei’s Cloud Open Source Development Team responsible for OpenStack, Containers, Open Storage, AI/Deep Learning, and other Cloud-related open source projects. Anni currently sits on both OpenStack and CNCF Boards. In addition, Anni is part of Huawei’s... Read More →


Tuesday June 26, 2018 16:20 - 17:00 CST
306A
  Open Source Leadership

16:40 CST

Actual Operations on the PC - TARS Team
Actual Operations on the PC

Tuesday June 26, 2018 16:40 - 17:20 CST
VIP4-3

17:15 CST

BoF: Build Container Instance Service With Kata Container - Zhiguo Hong, Tencent (slides attached)
Container Instance Service eliminates the burden of VM and presents flexibility of container.This presentation shows how Tencent build Container Instance Service based on existing mature kubernetes and Tencent vstation. The v2 roadmap with kata container is also discussed.

Speakers
WH

洪志国 Hong Zhiguo

腾讯云专家 工程师 Tencent Cloud Expert engineer, Tencent
Zhiguo Hong is a staff engineer at Tencent Cloud, focusing on Cloud-Native platform. He dived into container technology at early 2013 as he joined Tencent. Before that, he worked at Siemens (networking sw engineering) and EMC (storage sw engineering). Zhiguo Hong is also an active... Read More →



Tuesday June 26, 2018 17:15 - 18:15 CST
203AB
  BoF

17:15 CST

BoF: How to Port a New Arch (nds32) to the Linux Mainline - Greentime Hu, Andes (slides attached)
  • Introductions
  1. About me 
  2. What is nds32(Andes) 
  3. Stories of nds32 Linux 
  • Porting Linux to a new processor 
  1. Prerequisite to port an arch to Linux mainline 
  2. What should you port for your arch 
  • How to upstream your patchset
  1. Development cycle 
  2. Ready to mainline 
  3. Send the pull request to Linus 
  • Reflections and Implications 
  • Thanks
  • Q and A

Speakers
avatar for Greentime Hu

Greentime Hu

Manager, Andes
2013/3 - present, Andestech, Manager2012/1 - 2013/3, Mediatek, Software Engineer2008-2012, Andestech, Staff Engineer2005-2007 National Cheng Kung University, Taiwan Master degree, Engineering Science2001-2005 National Chengchi University, Taiwan Bachelor degree, Computer Science



Tuesday June 26, 2018 17:15 - 18:15 CST
307B
  BoF

17:15 CST

BoF: Not One Size Fits All, How to Size Kubernetes Clusters - Guang Ya Liu & Sahdev Zala, IBM (Watson and Cloud Platform)
Sizing Kubernetes clusters, at best, can be compared to throwing darts at a dartboard, in the dark. However, our enterprise-tested rules and tips can shine a little light on the dartboard and help you have enough capacity for your apps. In this lightning talk, we will go over some tips to help you throw a bullseye for sizing your clusters. A unique demo will accompany this talk. Don't throw darts in the dark -- Kube at scale is possible.

Speakers
avatar for Guangya Liu

Guangya Liu

Senior Technical Staff Member, IBM
Guang Ya Liu is a Senior Technical Staff Member and Technical Function Manager in IBM RTP and now focusing on cloud computing, data center operating system and container technology, he is also a Member of IBM Academy of Technology. Starting from 2013, Guang Ya act as an OpenStack... Read More →
avatar for Sahdev P. Zala

Sahdev P. Zala

Senior Software Engineer, IBM
Sahdev P. Zala is a senior software engineer and open source developer at IBM. He is a CNCF etcd project maintainer, Kubernetes contributor and co-lead of Kubernetes Provider IBM Cloud. Previously, Sahdev was a core contributor in OpenStack and a Technical Committee member of OASIS... Read More →



Tuesday June 26, 2018 17:15 - 18:15 CST
307A
  BoF

17:15 CST

BoF: OpenMessaging: New Messaging Standard Under Linux Foundation - Von Gosling, Alibaba Group
OpenMessaging, which includes the establishment of industry guidelines and messaging, streaming specifications to provide a common framework for finance, e-commerce, IoT and big-data area. The design principles are the cloud-oriented, simplicity, flexibility, and language independent in distributed heterogeneous environments. Conformance to these specifications will make it possible to develop a heterogeneous messaging application across all major platforms and operating systems. Von Gosling, original initiator of OpenMessaging standard will review standards in the messaging community, discuss why to create the OpenMessaging, the challenges it faces, and look forward to how the OpenMesaging may address those challenges and its future.

Speakers
avatar for Von Gosling

Von Gosling

Staff Engineer, Alibaba Group
Von Gosling is a long time senior technologist now working at Alibaba Group. He has rich industry software development experience, especially in distributed tech., reliable web architecture and performance tuning. He holds many patents in the distributed system, recommendation etc.Von... Read More →


Tuesday June 26, 2018 17:15 - 18:15 CST
306B

17:15 CST

 
Wednesday, June 27
 

08:00 CST

Breakfast
Wednesday June 27, 2018 08:00 - 09:00 CST
4F Foyer

08:00 CST

Registration
Wednesday June 27, 2018 08:00 - 16:00 CST
Main Lobby B

09:00 CST

Keynote: Alibaba Cloud and Cloud Native - Tao Ma, Principal Engineer, Alibaba Cloud
Speakers
TM

Tao Ma

Principal Software Engineer 首席软件工程师, Alibaba Cloud
Tao Ma had his first Linux box in the late 1990s. He played with Linux from then on and found his first job of C programming on Linux. He had his first commit in Linux kernel in 2007 and began his journey in Linux kernel development. Most of his contribution was related to file system... Read More →


Wednesday June 27, 2018 09:00 - 09:15 CST
Plenary Hall B

09:25 CST

Keynote: Shaping the Cloud Native Future - Abby Kearns, Executive Director, Cloud Foundry Foundation

Cloud Foundry is an integral part of the movement creating interoperability among the open source, cloud-native ecosystem. Complementary, interlocking open source technologies like Cloud Foundry, Kubernetes, and the Open Service Broker API are shifting the way industries function. These technologies weave together flexibility and application development for virtually any type of business.

What began as a grassroots movement among developers has mushroomed into a massive collaborative community. Linux laid the groundwork in 1991, and the Linux Foundation continues to host the world’s leading open source projects. Today projects like Cloud Foundry and Cloud Native Computing Foundation, as well as standards like the Open Container Initiative, effectively serve as the voice of the people. The developers creating these projects are defining the next generation of technology infrastructure.

In this talk, Abby Kearns will discuss the importance of interoperability, and how it is critical to the future success of technologies. Abby will also discuss the role that open source plays in cloud technologies -- delivering a flexible, scalable strategy to drive the future of business.


Speakers
avatar for Abby Kearns

Abby Kearns

Executive Director, Cloud Foundry Foundation


Wednesday June 27, 2018 09:25 - 09:45 CST
Plenary Hall B
  Keynote

09:50 CST

Keynote: Simplify Multimodal IT: Bridge Traditional and Software-defined Infrastructure - Alan Clark, Director, CTO Office, SUSE
Many organizations find themselves undergoing a journey of IT transformation. They have a traditional IT infrastructure with physical servers or virtualized servers, running monolithic or N-tier applications and use waterfall development processes. As they transform, some of the on-premise workloads and servers get moved to the cloud. The legacy apps are containerized directly or get converted to microservices. As a result, the organization finds itself using a mix of traditional infrastructure and software-defined infrastructure, which is essentially a multimodal IT scenario.

During the keynote, we will look at Multimodal IT scenarios, the challenges and needs of Multimodal IT and open source architectures that can help derive benefits from today’s mixed-IT deployments.

Speakers
avatar for Alan Clark

Alan Clark

CTO Office, SUSE


Wednesday June 27, 2018 09:50 - 10:05 CST
Plenary Hall B
  Keynote

10:10 CST

Keynote: Spectre, Meltdown, & Linux - Greg Kroah-Hartman, Fellow, The Linux Foundation
This talk will give a brief overview of the recently announced Meltdown and Spectre security problems that were announced early in 2018.  It will cover how the Linux kernel security community addressed these problems, and how all Linux users can be sure they are protected from problems like these with the latest security fixes.

Speakers
avatar for Greg Kroah-Hartman

Greg Kroah-Hartman

Fellow, Linux Foundation
Greg Kroah-Hartman is among a distinguished group of software developers who maintain Linux at the kernel level. In his role as a Linux Foundation Fellow, he continues his work as the maintainer for the Linux stable kernel branch and a variety of subsystems while working in a fully... Read More →


Wednesday June 27, 2018 10:10 - 10:40 CST
Plenary Hall B
  Keynote

10:40 CST

Keynote: Deep Learning Panel Discussion - Peixin Hou, Huawei; Dr. Feng Junlan, China Mobile Research Institute; and Jim Zemlin, The Linux Foundation
Moderators
avatar for Jim Zemlin

Jim Zemlin

Executive Director, The Linux Foundation
Jim Zemlin’s career spans three of the largest technology trends to rise over the last decade: mobile computing, cloud computing, and open source software. Today, as executive director of The Linux Foundation, he uses this experience to accelerate innovation in technology through... Read More →

Speakers
avatar for Dr. Junlan Feng

Dr. Junlan Feng

Chief Scientist, China Mobile Research Institute
Junlan Feng is Vice Chairman of the China Artificial Intelligence Industry Alliance, Chief Scientist at China Mobile, General Manager of AI and Intelligent Operation R&D Center, Board Chair of Linux Foundation Network.Dr. Feng received her Ph.D. on Speech Recognition from Chinese... Read More →
avatar for Peixin Hou

Peixin Hou

Chief Architect of Open Software and Systems, Huawei
Peixin Hou is currently serving as the Chief Architect of Open Software and Systems in the Central Software Institute, Huawei. He has been working in the software industry for over 20 years and has experience in operating systems, mobile software, media processing, and cloud computing. Peixin... Read More →


Wednesday June 27, 2018 10:40 - 11:00 CST
Plenary Hall B

10:45 CST

Sponsor Showcase
Wednesday June 27, 2018 10:45 - 14:00 CST
Plenary Hall A

11:00 CST

Coffee Break
Wednesday June 27, 2018 11:00 - 11:30 CST
4F Foyer

11:00 CST

Office Hours: Arun Gupta, Principal Open Source Technologist, AWS
Speakers
avatar for Arun Gupta

Arun Gupta

Head of the Open Source Program Office, Apple
Arun Gupta is head of the Open Source Program Office at Apple and chairperson of CNCF Governing Board. Previously, he worked at Amazon, partnering  with multiple engineering teams to help define their open source strategy. He has spent over a decade at Sun Microsystems and Oracle... Read More →


Wednesday June 27, 2018 11:00 - 12:00 CST
Level 3, Parkview Foyer

11:00 CST

Apache ServiceComb (Incubating) Day
The microservices open source project - Apache ServiceComb (incubating) will host an Open Day Meetup at the China National Convention Center (Beijing, China) from 11:00am to 18:00pm on Wednesday, June 27th.

The Open Day will focus on the following aspects and discuss the technology and direction of microservices with enterprises, users, and developers.
  • Interpretation of the Apache community
  • Business Microservices Commercial Case Sharing
  • State of affairs and Future of Microservice Open Source Community
  • Overview of ServiceComb Community and Technology Sharing
  • Domain-Driven Design (DDD) in Microservices
Get more real-time updated information about the event here: http://servicecomb.incubator.apache.org/docs/apache-servicecomb-incubating-day/

Event Date/Time
: Wednesday, June 27, 2018, 11:00 – 18:00pm
Event Location: China National Convention Center, Beijing, China
Event Cost: Complimentary
 About Apache ServiceComb (incubating) project:
The main code of the Apache ServiceComb (incubating) Project was donated by Huawei Cloud. The project is dedicated to helping enterprises easily build cloud-native applications and help build microservices from traditional enterprise business. By providing a series of solutions, Apache ServiceComb (incubating) helps users to develop microservices quickly and operate maintenance efficiently of these microservices applications, with a full microservices technology stack, without vendor lock-in. Currently, ServiceComb is following the “Apache Way”. It is used in HUAWEI businesses such as Consumer Cloud, Cloud EI, Cloud Security, Cloud Core Network, also popular in non-HUAWEI users. The developers are also increasingly diversified.
This is a free Open Meetup organized by the Apache ServiceComb (incubating) community and sponsored by Huawei Cloud. We have invited several experts and engineers from commercial enterprises, Apache Foundation, ServiceComb community and HUAWEI to share their experiences. Some of the topics as follows:

How Apache Works

Speaker: Jean-Baptiste Onofré; Apache Member and fellow of Talend, who started work on the Apache Software Foundation in 2004, and PMC member of 20+ Apache projects such as Karaf, Camel, and Carbondata.
Abstract: 
In-depth interpretation of the world's largest open source software foundation – Apache Software Foundation. Introduce what is the “Apache Way” and its attraction, the whole process from open source to incubation and then graduated combined with the actual project. Besides, it will introduce the current incubating status of ServiceComb.

How Smart City Microserviced Based on ServiceComb from iSoftStone

Speaker: Bao Yongwei; VP of iSoftStone Smart City Business, focusing on implementation and innovations in smart city related to cloud computing and big data.
Abstract:
iSoftStone Smart City Business involves a large number of systems with complex interactions. During the process of microservices implementation, it faced inappropriate microservices granularity, high code duplication rate, and difficulty in the deployment of large application microservices. This speech will introduce how iSoftStone use ServiceComb, especially ServiceComb’s Swagger API, to resolve the pain points of the microservices process, enable interoperability and decoupled chimney systems to meet the challenges of microservices diversity in smart city.

Millions Users Solution Based on ServiceComb Microservices from Huawei Consumer Cloud

Speaker: Li Linfeng, microservices architect for Huawei's Consumer Cloud application market, who has years of experience in designing and developing platform middleware, cloud platforms, and microservices. Author of “Netty authoritative guide” and “The principle and practice of distributed service framework”.
Abstract:
Huawei Consumer Cloud services provide high-quality cloud services for hundreds of millions of Huawei end users in more than 100 countries. In order to support the rapid development of the business, it is necessary to drive delivery of value requirements efficiently and agilely through the microservices architecture. By using SpringMVC and transparent RPC development model from ServiceComb, the existing business code can be migrated to the new microservices architecture at a low cost. Besides, the business implements full-stack asynchronous transformation using the Reactive asynchronous programming model from ServiceComb. Compared with the traditional synchronous blocking service call, the performance is improved several times, but the resource loss is greatly reduced. More practical cases will be shown on this topic.

Domain Driven Design (DDD) in Microservices

Speaker: Wang Lei, pioneer of microservices in China, author of "Microservices Architecture and Practice", Huawei Microservices Expert, and former ThoughtWorks Chief Consultant.
Abstract:
As a new architecture style, microservice has been widely adopted by the industry. It has become a fulfillment tool for the concept of DDD-driven design. This topic shares how to practice microservice with Domain Driven Design philosophy friendly.
Besides, Huawei Microservices open source expert, former Red Hat chief software engineer, and ServiceComb project leader - Jiang Ning is going to introduce the details about ServiceComb community and technology together with PMCs.

Wednesday June 27, 2018 11:00 - 18:00 CST
211

11:30 CST

Performance Optimization for Content Recommendation Workload on Large-scale Distributed GPU VM Nodes on Alibaba Cloud - Liang You, Alibaba Cloud (slides attached)
In this presentation, we will introduce the recommended technical architecture for content recommendation scenario on Alibaba Cloud and we will introduce the performance optimization work and the results for this scenario on large-scale distributed GPU VM nodes in Alibaba Cloud. We need to train about 20 billion samples within an hour, which is a very challenge goal to reach. The model has high communication-computing ratio and is implemented with Tensorflow, which has very bad scalability for large-scale distributed nodes and especially bad on the Cloud Computing virtual network. What’s more, the performance is very blocked by the distributed file reading. We optimized the performance both on communication and IO aspects and get over 14x speedup on 64 GPU VMs than the original implementation and finally trained over 20 billion samples within an hour on the 64 GPU VMs in Alibaba Cloud.

Speakers

亮 游

高级技术专家, 阿里云
Liang is in charge of the Elastic Artificial Intelligence Team at Alibaba Cloud, a subsidiary of Alibaba Group. He focuses on AI platform solution and performance optimization for both large-scale distributed deep learning training and inferencing on GPU platform of Alibaba Cloud... Read More →



Wednesday June 27, 2018 11:30 - 12:10 CST
306A
  AI & Deep Learning

11:30 CST

The Practice of Security Deployment and Management for Hyperledger Fabric - Fengfeng Shi, dianrong.com (slides attached)
Hyperledger Fabric designed a complete security architecture system. In actual use, how to make good use of this system to ensure the security and convenience of the deployment and management of the blockchain is a very flexible and complex matter. We will briefly introduce the security principles of Hyperledger Fabric and the specific practices of the blockchain as a service platform in Dianrong.

Speakers
avatar for Fengfeng Shi

Fengfeng Shi

Blockchain expert, dianrong.com
Fengfeng Shi comes from Dianrong, an online marketplace lending leader, in China.



Wednesday June 27, 2018 11:30 - 12:10 CST
311A
  Blockchain

11:30 CST

Best Practices of Building an Application with Millions of QPS Based on Kubernetes - Chao Liu, Netease
It is challenging to build cloud-native applications with millions of QPS, and we have lots of such online systems with high throughput as The Netease Cloud Music and Kaola-the biggest oversea E-commerce platform. All these systems are running on the Netease Cloud Platform based on kubernetes, so we would like to share our best practices of 1) how to improve the scalability of kubernetes to 30000+ nodes to support a large cluster of microservice applications2) how to do operations and maintenance of applications in more than 30, 000+ containers 3) how to improve the performance of key components of kubernetes such as ingress, networking, storage, services to support applications with 1000, 0000+ DAUs.

Speakers
avatar for Chao Liu

Chao Liu

Chief Architect of Cloud Computing Technology Department, Netease
Chao Liu has 15 years of experience in the development and architecture of cloud computing. He is very passionate about open source. He loves to code, write, and share.He has published . He is also an InfoQ star lecturer. Chao Liu has written lots of articles about open source projects:Lucene... Read More →


Wednesday June 27, 2018 11:30 - 12:10 CST
310

11:30 CST

Full scalable Media Cloud Solution with Kubernetes Orchestration on GPU - Zhenyu Wang & Xin (Owen) Zhang, Intel Corp. (slides attached)
Large portion of media workloads in network e.g video host service, live streaming and broadcast etc. require massive power for media encoding, decoding and transcoding support in cloud server. Intel GPU's media hardware and full open sourced "Media Server Studio" (MSS) software provide high performance media acceleration support which meet media processing requirement with great performance per energy.

This will show how we apply MSS software in cloud environment on GPU hardware with container and Kubernetes orchestration. It will show how to utilize GPU hardware in container for MSS media workload with resource control based on GPU cgroup. Also about device manager for Intel GPU which hook up to new Kubernetes device plugin for easy manage and schedule GPU on pods via Kubelet. Final results are presented for complete media cloud solution with full scalability and orchestration.

Speakers
ZW

Zhenyu Wang

Software engineer, Intel Corp.
Zhenyu Wang, from Open Source Technology Center of Intel Corp. He has been working on Intel open source graphics driver stack for many years, experience from low level hardware feature enabling to high level userspace 2D/3D drivers. And now focus more on how to fully apply GPU utilization... Read More →
OZ

Owen Zhang

Software Engineer, Intel
Zhang, Xin (Owen), Software engineer in Intel Data Center Group (DCG). Currently he works on media module driver development, and GPU container enablement for DCG customer deployment. He made one speaking for Container with Media Server Studio integration in DCG NPG Asia summit 2... Read More →



Wednesday June 27, 2018 11:30 - 12:10 CST
309A

11:30 CST

Topology-aware Service Routing in Kubernetes Boots a Smarter Service Discovery - Jun Du, Huawei (slides attached)
It's a pain point for multi-zone clusters deployment since cross-zone network traffic being charged, while in-zone is not. In addition, cross-node traffic may carry sensitive metadata from other nodes. Therefore, users always prefer the service backends that close to them, e.g. same zone, rack and host etc. for security, performance and cost concerns.
Kubernetes scheduler can constraining a pod to only be able to run on particular nodes/zones. However, Kubernetes service proxy just randomly picks an available backend for service routing and this one can be very far from the user, so we need a topology-aware service routing solution in Kubernetes. Basically, to find the nearest service backend.
This talk will be a deep dive of how Huawei Cloud achieve this sort of topology guarantee in a generic and Kubernetes-native way, no matter what kind of topological level.

Speakers
avatar for Jun Du

Jun Du

Senior Software Engineer, Huawei
Jun Du is one of the CNCF TOC Contributors and the author of two books on cloud-native area, e.g. "docker--containers and cloud”and“etcd in-depth interpretation". He is the maintainer and owner of some notable features of Kubernetes, e.g. IPVS-based kube-proxy and pod traffic... Read More →



Wednesday June 27, 2018 11:30 - 12:10 CST
309B

11:30 CST

How Habitat Enables Cloud Native Applications and DevOps Teams - Lingshuang Chen, Chef Software (slides attached)
Delivering applications is hard, and today most businesses are caught in several concurrent shifts: from monoliths to microservices, bare metal to containers, datacenter to the cloud. Hybrid is the standard operating model and will be for at least a long time given the pace of technology innovation. This means that automation that copes with extreme heterogeneity is needed to lessen the burden on modern app teams. This is why Chef built Habitat, an open source application automation engine that can be used to build, deploy, and manage any application in any environment - from traditional to cloud-native architectures. This talk will go over the shifting landscape to Cloud Native, and how Habitat can help enabling it in your organization.

Speakers
avatar for Lingshuang Chen

Lingshuang Chen

UX Designer, Chef Software
Lingshuang(Liz) is a user experience designer for Habitat.sh, an open source framework for building, running, and deploying applications in a 12-factor, cloud-native friendly way - that works for both legacy and net new applications and services. She holds a Master of Science degree... Read More →



Wednesday June 27, 2018 11:30 - 12:10 CST
307A
  Infrastructure & Automation

11:30 CST

EdgeX Foundry - A Microservice Approach to IoT Edge Computing - Jim White, Dell (slides attached)
Flexibility and interoperability in the field of IoT software is a paramount objective.  The mix of platforms, “things”, applications, intelligence, etc. which are connected in an IoT deployment is extensive and ever growing.  How do you create a software platform that connects to a variety of old & new, greenfield and brownfield devices and sensors, allows the incorporation of various edge analytics, communicates to a diverse set of cloud and enterprise platforms like Azure IoT Hub, Google IoT Core, AWS IoT, etc.?  The solution, as exhibited in EdgeX Foundry (an open source, vendor neutral IoT platform hosted by the Linux Foundation), is to use a microservice architecture.  In this session, come learn about EdgeX Foundry, how it works, and see how its microservices architecture can help:
  • Address the challenges of dealing with the IoT protocol soup (Modbus, BACnet, BLE, Zigbee, ZWave, MQTT, OPC-UA, etc.)
  • Solve the issues of “your data model/format is not my model/format” when connecting the edge to applications in your enterprise
  • Facilitate organizations in incorporating use case specific edge analytics or event processing
  • Allow for the continual improvements and upgrades of various parts of the IoT solution without requiring a redo of the entire platform
  • Allow for value additions into your IoT solution in order to allow return on investment
  • Maximize the utilization of available resources, which tend to be more constrained at the edge
  • Incorporate best of breed solutions for any part of the IoT solution that already exist or may exist in the future.
No software architecture is a silver bullet.  The presentation will also explore additional challenges (and lessons learned) that a microservices IoT architecture introduce and that must be addressed to include dealing with orchestration/deployment, security and additional communication latency.

Speakers
avatar for Jim White

Jim White

Distinguished Engineer, Dell Technologies
Jim White, Distinguished Engineer and Senior Software Architect for Dell’s End User Computing, Office of the CTO.  Jim is the chief architect and technical lead in Dell’s largest open source effort to date called EdgeX Foundry and is the Vice President of the TSC.  Jim has over... Read More →



Wednesday June 27, 2018 11:30 - 12:10 CST
306B
  IoT & M2M

11:30 CST

Intel® Scalable I/O Virtualization - Kevin Tian, Intel® (slides attached)
Intel® Scalable I/O Virtualization (Intel® Scalable IOV) is a new approach from Intel to hardware based I/O virtualization that enables highly-scalable and high-performance sharing of I/O devices across isolated domains (traditional VMs, containers, or application processes), while reducing their cost and complexity. 
 In this talk Kevin will first introduce the concept of Intel® Scalable IOV, specifically about a hybrid approach through innovations in both hardware and software components to achieve the advantages of both scalability, performance and composability. Following that comes an overview of Intel®Scalable IOV reference architecture in Linux, based on extensions to VFIO mediated device framework and IOMMU sub-system.
 

Speakers
KT

Kevin Tian

Principal Engineer, Intel
Kevin is a virtualization veteran from Intel with 16 years experience in open source virtualization projects (KVM, Xen, etc.), including multiple presentations in associated conferences. He is currently a software architect in Open source Technology Center of Intel, with current focus... Read More →



Wednesday June 27, 2018 11:30 - 12:10 CST
203AB
  KVM

11:30 CST

Intelligent Server Brain for Cloud Services Driven Power Management and Performance Optimization - Jun Song, Alibaba Group
Traditional Linux OSPM based Power and Performance (PnP) management does NOT address cloud applications' highly diversified dynamic needs. We developed a framework and various intelligent algorithms that replace Linux OSPM to do cloud server PnP modeling and control knobs (including parameters) selection. The PnP model automatically learns the server system's compute ingredients (e.g. CPU, GPU) behavior under various cloud loads, does comprehensive and progressive optimization, and outputs control recommendations. Examples: 1) the model predicts two threads' competition for shared cache or pipeline before the competition happens, and informs the OS scheduler to take actions; 2) it can manage use of deep C states (e.g. power gating state) to minimize or avoid performance penalty on latency sensitive workloads. We created an ASIC to enable out-of-band control and to accelerate prediction.

Speakers
JS

Jun Song

Chief Power Architect, Alibaba Group
Jun (Justin) Song is chief power architect of Alibaba Group responsible for server and data center power optimization and management. Before joining Alibaba Justin worked as a silicon, chip and platform architect with Intel for 14 years. Justin made technical presentations on public... Read More →


Wednesday June 27, 2018 11:30 - 12:10 CST
307B
  Linux Systems

11:30 CST

How Standards and Open Source Interworking can Resolve Challenges Slowing down the Massive Deployment of NFV - Nan Zhou & Kubi Gao, Huawei Technologies Co., Ltd. (slides attached)
The concept of Network Function Virtualization has been accepted by operators, equipment vendors, software vendors and other industrial players after it was introduced to the Telco industry in 2012. Even with loads of efforts, the NFV industry has just picked up the "low hanging fruits" that deploying NFV like traditional equipment procurement after five years and has not yet reached to the point of a fully decoupled NFV proposal.

A specific OPNFV practice of absorbing the standard elements in open source community to move the NFV forward will be presented in the talk, and presenters will give the solution leveraging open source and standards to help a quick and massive deployment of one technology in the carrier market. This will be beneficial for other communities to practice standards and open source interworking.

Speakers
LG

Liang Gao

开源项目经理, Shanghai HUAWEI Technologies Co. Ltd
Kubi Gao is the senior software developer in Huawei focusing on OPNFV. He worked in the community since its establishment from 2014, served as the committer and PTL in Yardstick, and the member in OPNFV Testing WG. Now he is the elected by all committers to be an OPNFV TSC repres... Read More →
NZ

Nan Zhou

Open Source Strategist, Huawei
Nan Zhou is the senior standards engineer in Huawei working in open source communities for more than 4 years. He manages the open source operations in different communities like CNCF, OPNFV and Linux Foundation, and serves as the Huawei representative in OCI Trademark Board and the... Read More →



Wednesday June 27, 2018 11:30 - 12:10 CST
311B
  Networking & Orchestration

12:00 CST

Office Hours: Eduardo Silva, Fluentd / Fluent Bit Maintainer
Speakers
avatar for Eduardo Silva

Eduardo Silva

Principal Engineer, Arm Treasure Data
Eduardo is a Principal Engineer at Arm Treasure Data, he is the author and maintainer of Fluent Bit Log Processor, a CNCF sub-project under the umbrella of Fluentd. He is an international speaker in Open Source conferences, he has participated in Scale California, LinuxConf AU, Linux... Read More →


Wednesday June 27, 2018 12:00 - 13:00 CST
Level 3, Parkview Foyer

12:10 CST

Lunch
Wednesday June 27, 2018 12:10 - 13:30 CST
Plenary Hall A

13:00 CST

Office Hours: Jim White, Distinguished Engineer, Dell Technologies
Speakers
avatar for Jim White

Jim White

Distinguished Engineer, Dell Technologies
Jim White, Distinguished Engineer and Senior Software Architect for Dell’s End User Computing, Office of the CTO.  Jim is the chief architect and technical lead in Dell’s largest open source effort to date called EdgeX Foundry and is the Vice President of the TSC.  Jim has over... Read More →


Wednesday June 27, 2018 13:00 - 14:00 CST
Level 3, Parkview Foyer

13:30 CST

Elastic Deep Learning with PaddlePaddle - Wu Yi, Baidu (slides attached)
Current Deep Leaning applications are facing problems to use larger clusters and saving the hardware cost. EDL provides a solution by providing fault-tolerant and scalable framework using the power of Kubernetes. We'll introduce how we design, implement and apply this technic to modern GPU container clusters.

Speakers
avatar for Wu Yi

Wu Yi

Develop Engineer, Baidu
The developer of PaddlePaddle opensource deep learning framework, work at Baidu. Primary developer of PaddlePaddle EDL (Elastic Deep Learning) and PaddlePaddle Fluid distributed framework. speaking experiences: * 2014 DTCC《百分点内存数据库架构演变》 * 2015... Read More →



Wednesday June 27, 2018 13:30 - 14:10 CST
306A
  AI & Deep Learning

13:30 CST

Panel Discussion: Blockchain and Innovation in Financial Services and Supply Chain - Moderated by Scott Long, Linux Foundation APAC

This session will explore how Hyperledger blockchain technology is being utilised in financial services and supply chain, creating platforms that reduce costs, streamline processes, improve efficiency and security and create new business models. You will hear from industry experts involved in the development of blockchain applications on their real world progress, opportunities and challenges.

区块链分论坛圆桌对话:区块链在金融服务和供应链的创新

 本次讨论将探讨Hyperledger区块链技术如何应用于金融服务和供应链,助力降低成本、简化流程、提高效率和安全性以及创建新的业务模式。您还将听到中国领先行业的专家讨论区块链在中国的应用进展、开发机遇和挑战。


Moderators
avatar for Scott Long

Scott Long

Community development manager, Linux基金会

Speakers
DY

Dr. Yang Yue Feng

Dr. Yang Yue Feng is at the Bank of Jiangsu.
avatar for Peng Zuo

Peng Zuo

CEO, Shanghai Gingkoo Financial Technology Co.,Ltd
Gingkoo Financial Technology is one of the first batch of enterprises to enter the technology ecology of blockchain in China. Especially in the area of blockchain supervision and compliance, the company has done a lot of exploration and accumulated a wealth of industry-leading application... Read More →


Wednesday June 27, 2018 13:30 - 14:10 CST
311A

13:30 CST

Host Kubernetes Within Kubernetes - Guangyou Yu, Tencent (slides attached)
As a cloud provider, Tencent faces enormous stability challenges when it comes to providing Kubernetes managed services. As the number of managed Kubernetes clusters increases, the load on Kubernetes' master nodes is also getting higher. Tencent deployed all the components of the customer cluster master node in a Kubernetes cluster and managed them to maximize the advantages of containers and the capabilities of Kubernetes itself.

1. Containerized master nodes which deployed in the Kubernetes cluster could quickly restart and upgrade without affecting the customer's business. In the case of high load, you could run more master containers support services. Some e-commerce clients take advantage of this architect to successfully handled the pressure of large-scale promotional activities and effectively saving costs
2. Use this solution to provide users with multiple versions of Kubernetes

Speakers

广游 于

高级工程师, Tencent
Guangyou Yu is now a senior engineer of Tencent cloud PAAS product center Now responsible for Tencent cloud container service architecture design and development work. Years of experience in the design and development of distributed systems and the assurance of availability. Previously... Read More →



Wednesday June 27, 2018 13:30 - 14:10 CST
309B

13:30 CST

How Hypervisors Provide Security in a Containerized World - Stefano Stabellini, Xen Project
Containers are the new industry standard for server applications. While traditional techniques to run container apps are under scrutiny due to their less-than-ideal isolation properties, thanks to the OCI specifications, now we have clear guidelines on the container packaging format and runtime environment. It is easier than ever to write new container runtimes able to interact with Kubernetes and the Docker Hub.

This talk will introduce a new approach to secure containers based on virtualization. It will go into details on the design and will show how it compares to traditional hypervisors and Linux namespaces regarding security, overhead, and performance. The presentation will explain why it is critical to monitor containers and will introduce a new paravirtualized protocol which allows detailed auditing of network traffic from the apps without compromising performance.

Speakers
avatar for Stefano Stabellini

Stefano Stabellini

Principal Engineer, Xilinx
Stefano Stabellini serves as system software architect and virtualization lead at Xilinx, the world's largest supplier of FPGA solutions. Previously, at Aporeto, he created a virtualization-based security solution for containers and authored several security articles. As Senior Principal... Read More →


Wednesday June 27, 2018 13:30 - 14:10 CST
309A

13:30 CST

Kubernetes Autoscaling on Azure - Pengfei Ni, Microsoft (slides attached)
Kubernetes is becoming standard to build and manage cloud native applications in production. However, when running kubernetes on public or private clouds, applications may still be broken by various issues. This talk will go over how autoscaling could help to solve node failure and lack of cluster capacity problem. Autoscaling could also help to reduce costs by removing unneeded nodes.

The topic will cover areas such as why autoscaling is important to keep kubernetes healthy, pros/cons of various autoscaling polices and how it is done on Azure. It also covers some subtle gotchas while autoscaling and what we should do to avoid them.

Speakers
avatar for Pengfei Ni

Pengfei Ni

Senior Software Engineer, Microsoft
Pengfei Ni is a senior software engineer at Microsoft Azure and maintainer of the kubernetes project. He has extensive experience in Cloud Computing, Kubernetes and Software Defined Networking (SDN). He has given presentations on KubeCon China 2018, ArchSummit 2018, LC3 2018, and... Read More →



Wednesday June 27, 2018 13:30 - 14:10 CST
310

13:30 CST

Operators: Extending Kubernetes with Custom Resources - Ian Lewis, Google
Kubernetes is a container orchestration system that provides a lot of built in functionality to deploy and manage applications using containers. But many types of applications, like stateful applications, require the ability to extend Kubernetes functionality to work in a dynamic environment.

In this talk, attendees will learn the concept of custom resources and how to use them to extend Kubernetes. We will walk through designing an operator for memcached that reacts automatically when memcached clusters change. Attendees will learn about the architecture of operators and how to use the Kubernetes Go client library to begin developing their own operators.

Speakers
avatar for Ian Lewis

Ian Lewis

Software Engineer, Google
Ian is an engineer at Google working on Supply Chain Security. Ian has been living in Tokyo since 2006 and has had various developer and operations roles throughout his career while staying active in the open-source developer community. Ian is a contributor to the SLSA framework and... Read More →


Wednesday June 27, 2018 13:30 - 14:10 CST
307A
  Infrastructure & Automation

13:30 CST

Accelerating VM Networking through XDP - Jason Wang, Red Hat (slides attached)
Compared to userspace networking data-path like dpdk, the performance of kernel datapath is poor. XDP was then invented to be a separated light weight data path for networking in kenrel. This talk will focues on using the XDP infrastructure to accelerate the VM networking. Firstly, the design and implementation of XDP will be described. Then the talk will discuss the idea of using XDP to accelreate VM networking which contains the design and implementation of XDP in both tun/tap and virtio-net. The performance numbers and future work will be then discussed at the end of the talk.

Speakers
JW

Jason Wang

Senior Principal Software Engineer, Red Hat
Co-maintainer of kernel virtio, vdpa and vhost drivers. Maintainer of Qemu networking subsystems. Author of vDPA support in Kernel.



Wednesday June 27, 2018 13:30 - 14:10 CST
203AB
  KVM

13:30 CST

LKL: Another Way to Reuse the Linux Kernel - Yu Li, Huawei (slides attached)
LKL (Linux Kernel Library) is a great work of reusing the Linux kernel code as extensively as possible with minimal effort and reduced maintenance overhead. It may be used on many potential interesting scenarios, e.g. to create a near full feature LibOS without reinvent wheels or to reuse mature network stack of Linux even in other OS. Internally, it provides a pseudo architecture that may be implemented under user space. However, it still lacks some important features so far, especially SMP support. We would like introduce to its internals and some highlights of our works : a try of adding SMP support on x86 and AArch64, which contains how to support IPI, across-CPU timing and tree RCU. Device drivers of Linux are great resources of open sources world, another interesting work is a try of reusing Linux device drivers by extending LKL. Lastly, we will show some drawbacks of LKL too.

Speakers
avatar for Yu Li

Yu Li

Principal Engineer, Huawei
Principal Engineer, Huawei OS/Kernel Lab. He is working on system software development. Before that, he worked in Alibaba kernel team for 5+ years. In this project, Yu worked on SMP support design and implementation.



Wednesday June 27, 2018 13:30 - 14:10 CST
307B
  Linux Systems

13:30 CST

Experience OPNFV on Arm - Yibo Cai, Arm (slides attached)
Arm server, as an emerging force in data center, takes OPNFV as an important frontier to impact the industry.
Compass4NFV is an official OPNFV installer which supports both OpenStack and Kubernetes.
Arm is collaborating with Compass4NFV project to make the experience of deploying OPNFV on Arm awesome.
This presentation introduces our work to support Arm for Compass4NFV and current status of OPNFV on Arm servers.

Speakers
avatar for Yibo Cai

Yibo Cai

Principal Software Engineer, Arm
Yibo is staff software engineer from Arm. He has been working in IT industry for 17 years, and he has rich experience in OpenStack and OPNFV development on Arm. Yibo presented "OpenStack on AArch64" at LinuxCon ContainerCon CloudOpen China, Jun-2017.



Wednesday June 27, 2018 13:30 - 14:10 CST
311B
  Networking & Orchestration

13:30 CST

How Open Invention Network Safeguards the Linux Ecosystem - Kevin Huang, Open Invention Network
Open source software is, same as any software, protected by trademarks, copyrights, patents, and licenses. Open source software industry may be just as notable for its nasty legal battles as for its many useful products, but for the past 10 years, the Open Invention Network has been quietly working to change all that.

Kevin Huang will provide the speech how OIN community works and why you, your projects and your companies should join it.

Speakers
avatar for Kevin Huang

Kevin Huang

Director of Licensing, Open Invention Network
Kevin Huang joined Open Invention Network in 2015 to promote patent non-aggression community for Linux System. Before joining OIN, Kevin Huang was responsible Canonical service business in Asia to promote Ubuntu Linux system. OIN’s community practices patent non-aggression in... Read More →


Wednesday June 27, 2018 13:30 - 14:10 CST
306B

14:00 CST

14:20 CST

International Energy Trade on Blockchain: A Sinochem Energy Pilot Project - Yongchun Zhu, Sinochem Energy Tech (slides attached)
Sinochem Group is one of the largest energy enterprise of the world, ranking 143 in Fortune 500. Sinochem Energy Tech accomplished a pilot project using hyperledger fabric blockchain infrastructure to facilitate the import or export of energy in order to improve effeciency and reduce cost.

In this sharing, a brief introduction of international energy trade will be presented firstly. Second will present the case study of Sinochem's utilizing blockchain technology in energy trade. Next will present the solution architecutre in this case, a Blockchain as a Service(BaaS) platform by Sinochem Energy Tech is also constructed during the project. Finally, future work will be presented.

Speakers
avatar for Yongchun Zhu

Yongchun Zhu

Director of Blockchain Tech Program, Sinochem Energy Tech
Sinochem Group is one of the largest energy enterprise of the world, ranking 143 in Fortune 500. Sinochem Energy Tech is a subsidiary of Sinochem Group which focuses on applying emerging technology in energy industry. Currently we are working on a pilot project using hyperledger... Read More →



Wednesday June 27, 2018 14:20 - 15:00 CST
311A
  Blockchain

14:20 CST

Disaster Recovery and Data Protection for Kubernetes Persistent Volumes - Xing Yang, Huawei Technologies & Rakesh Jain, IBM (slides attached)
Your storage hosting the persistent volumes serving the Kubernetes cluster is damaged by a fire. How do you recover from such a disaster?

In this session, we will provide some strategies on how to protect the critical data. We will discuss how to use OpenSDS, an open source Software Defined Storage project under Linux Foundation, to provision persistent volumes for Kubernetes using the CSI plugin, how to use a policy engine to periodically and asynchronously create snapshots as point-in-time protection for the Kubernetes persistent volumes, and how the array-based and host-based replication feature in OpenSDS can help protect the data residing on the persistent volumes in the case of a disaster.

Speakers
avatar for Rakesh Jain

Rakesh Jain

STSM and Researcher, SODA TOC Co-Chair, IBM
Rakesh Jain is an Architect and Researcher with IBM Almaden Research Center in San Jose CA. He is an expert in Cloud automation, Internet of Things, Storage Management and High Availability & Disaster Recovery technologies. He is also involved in the development of IBM's storage management... Read More →
avatar for Xing Yang

Xing Yang

Tech Lead, VMware
Xing Yang is a Tech Lead in the Cloud Native Storage team at VMware. She is a co-chair of CNCF Storage TAG, a co-chair of the Kubernetes Storage SIG, a co-chair of the Data Protection WG, and a maintainer in Kubernetes CSI. Before joining VMware, Xing was the Lead Architect of OpenSDS... Read More →



Wednesday June 27, 2018 14:20 - 15:00 CST
309B

14:20 CST

Bcache Stability: Improvement for Cloud Infrastructure - Coly (Yong) Li, SUSE (slides attached)
Bcache was merged as a block layer cache in Linux v3.10. Although there are bug reports time to time, it has been deployed in various systems of cloud infrastructure in the past five years.

Since 2017 we have more active developers (most of them are from China) to contribute many critical stability fixes. These fixes address issues from deadlock, I/O hang, kernel oops. Especially when cache or cached devices are failed or gone, bcache device can be stopped precisely and elegantly (panic on failure is unnecessary anymore). The stability of bcache has huge improvement, and it is ready for more work loads from large scaled could infrastructure for now days.

This presentation will share the information with audience how bcache becomes more stable and what issues people don't need to worry about, and how the stability of bcache is ready for large scaled cloud infrastructure.

Speakers
avatar for Coly (Yong) Li

Coly (Yong) Li

Software Engineer, SUSE
Linux kernel developer from SUSE Labs, working on block layer and maintain md/dm/bcache for SUSE Linux Enterprise Server kernel. In year 2010-2015, I initiated Linux kernel engineering team for Taobao Core Infrastructure and then led cold data storage development for Alibaba Site... Read More →



Wednesday June 27, 2018 14:20 - 15:00 CST
307A

14:20 CST

BOSH, A Platform For Running Platforms So You Can Run Platforms - Paul Czarkowski, Pivotal
Modern DevOps practices involve deploying applications to platforms. From basic IaaS to PaaS to serverless functions. But who runs those platforms and how?  At Pivotal we build and operate platforms, and we run those platforms on a platform designed to run complex distributed systems called Bosh which was inspired by google borg. Paul will talk through a couple of successful patterns for deploying and operating platforms as well as how to help your business determine which platform[s] are right for them and how to successfully get the business to adopt those platforms. 

Speakers
PC

Paul Czarkowski

Paul Czarkowski is a recovering Systems Administrator who has run infrastructure for longer than he cares to admit. After cutting his teeth in the ISP and Gaming industries Paul changed his focus to using (and contributing to) Open Source Software to improve the Operability of complex... Read More →


Wednesday June 27, 2018 14:20 - 15:00 CST
310

14:20 CST

Device Assignment with Nested Guests and DPDK - Peter Xu, Red Hat (slides attached)
I/O virtualization is one of the most important aspect of virtualization technology. Generally speaking we can have three types of I/O devices in a virtual machine: emulated, para-virtualized, and device assignment. Here device assignment plays a vital role in performance critical scenarios, which allows a guest to seamlessly manipulate a real hardware device. However that was never safe to run DPDK with such a device, and even impossible for nested virtualization. In this presentation, Peter Xu will introduce his work on QEMU/KVM vIOMMU to enable these scenarios. It will contain not only how new users can start using the new feature, but also technical details and challenges on the project.

Speakers
avatar for Peter Xu

Peter Xu

Senior Software Engineer, Red Hat
Peter Xu works for Red Hat virtualization team. He is working on QEMU/KVM project with vIOMMUs, migrations, interrupts and other miscelleneous stuff. He has given a talk in KVM Forum 2016 together with Wei Xu on vhost DMA Remapping.



Wednesday June 27, 2018 14:20 - 15:00 CST
203AB
  KVM

14:20 CST

Xen Project: After 15 years, What's Next? - George Dunlap, Citrix Systems R&D UK Ltd (slides attached)
The Xen Hypervisor is 15 years old, but like Linux, it is still undergoing significant upgrades and improvements. This talk will cover recent and upcoming developments in Xen on the x86 architecture, including the newly-released 'PVH' guest virtualization mode, the future of PV mode, qemu deprivileging, and more. We will cover why these new features are important for a wide range of environments, from cloud to embedded.

Speakers
avatar for George Dunlap

George Dunlap

Principal Software Engineer, Citrix Systems R&D UK Ltd
George Dunlap worked with the Xen project while a graduate student at the University of Michigan before receiving his PhD in 2006, then worked as a core Xen developer for many years for Citrix's open-source team in Cambridge, England. He is now community manager and chairman of the... Read More →



Wednesday June 27, 2018 14:20 - 15:00 CST
307B
  Linux Systems

14:20 CST

FPGA and Virtualization Technology in DPDK to Accelerating and Scaling the Cloud Networking - Tianfei Zhang & Rosen Xu, Intel (slides attached)
Many china e-market companies using cloud computing infrastructure to accelerate their business, and SDN and NVF are more popular deployed in internet companies. But how to make a software network scale to an era of 40/50+ Gigabit networks and provide great performance for network applications in cloud computing like Alibaba double 11 shopping spree?

In this presentation, we will introduce a new FPGA software framework using Intel Xeon+A10 FPGA to accelerating Linux workloads using SRIOV and virtualization technology. We will introduce OPAE (Open Programmable Acceleration Engine), and its integration with DPDK. We have developed SmartNICs which using OPAE and virtualization technology to accelerating cloud networking.

In the end, we will discuss the status of integration with DPDK community with OPAE to help accelerating and scaling the rapidly growing cloud networking.

Speakers
avatar for Rosen Xu

Rosen Xu

Senior Software Engineer, Intel
Rosen(Weihua) Xu is a senior software engineer at Intel Network Platforms Group (NPG). He has over ten years of experience in Linux Kernel, FPGA design, system virtualization and CPU acceleration.
D

天飞 张

senior software engineer, Intel



Wednesday June 27, 2018 14:20 - 15:00 CST
311B
  Networking & Orchestration

14:50 CST

15:10 CST

Hyperledger Caliper: A Performance Benchmark Framework for Multiple DLTs - Haojun Zhou, Huawei (slides attached)
Caliper is a blockchain benchmark framework which allows users to measure the performance of a blockchain system under test.  Caliper will produce reports containing a number of performance indicators, such as TPS (Transactions Per Second), transaction latency, resource utilization etc.

We will introduce the architecture of the framework, how to integrate with various blockchain systems, how to use caliper to define and run a test flow. 

Speakers
HZ

Haojun Zhou

Huawei
Haojun Zhou started working on Hyperledger since 2017 and he is the main contributor and maintainer of Hyperledger Caliper project



Wednesday June 27, 2018 15:10 - 15:50 CST
311A
  Blockchain
  • Experience Level Any

15:10 CST

Orchestrating Multi-service Applications on Kubernetes - Michael Hrivnak, Red Hat, Inc.
Many applications consist of multiple services, such as a database, API service, and frontend. Provisioning them as a single application in Kubernetes can be a challenge, especially if one or more services runs outside your cluster.

The Service Catalog provides a new way to publish, provision, and manage applications on Kubernetes through the use of Service Brokers. The Automation Broker allows users to leverage Ansible Automation to orchestrate simple to complex multi-service deployments.

In this session you will learn:
- How to provision a multi-service application on Kubernetes using the Automation Broker.
- How to include external service provisioning in your application’s deployment.
- How to package Ansible Playbooks into a single meta-container for orchestrating the deployment of your application.
- How to publish your own applications in the Kubernetes Service Catalog.

Speakers
avatar for Michael Hrivnak

Michael Hrivnak

Principal Software Engineer, Red Hat, Inc.
Michael Hrivnak is a Principal Software Engineer at Red Hat. During his time as Team Lead for the Pulp project, he became involved in solving real-world container orchestration problems. He now works in that domain as part of the Automation Broker project. With experience in both... Read More →


Wednesday June 27, 2018 15:10 - 15:50 CST
309B

15:10 CST

Run Linux Kernel as a Daemon - Lai Jiangshan, Hyper.sh
The presentation describes a specific linux kernel which runs in the userspace mode. It supplies all kernel services but with the threads and virtual memory management passing to the host kernel. It is able to run the unmodified code and existing binaries. It is a kind of light way sandboxing between linux namespace and VM that can be used for many situations such as Caas, Faas, Serverless.

Speakers
LJ

Lai Jiangshan

Senior Staff Engineer, AntGroup
2006-2015 Fujitsu: linux kernel developer As a speaker in Japan Linux Symposium 2009 As a speaker in Japan LinuxCom 2010 Attended 2013 linux kernel summit and made a short speech 2015-2018 Hyper.sh: linux kernel and container developer


Wednesday June 27, 2018 15:10 - 15:50 CST
309A

15:10 CST

Building a Serverless Container Cloud with OpenStack and Kubernetes - Kevin Zhao, Arm
Kubernetes makes it easier to deploy, manage and scale clusters of containers. However, running Kubernetes on OpenStack still requires users to manage the underlying infrastructure such as a cluster of virtual servers, and users need to take care of the initial capacity planning and the maintenance of the server clusters.

The emerging serverless container (zero server management) technologies such as AWS Fargate, Azure Container Instance (ACI) and OpenStack Zun can reduce such infrastructure management overhead. They provide a viable alternative to run containers on the cloud, which allows users to run containers without pre-creating or managing their own server (virtual machine) clusters.

In this presentation, we will talk about what serverless conainer cloud is, why it matters and how to implement serverless container cloud on top of OpenStack using Zun and Kubernetes.

Speakers
avatar for Kevin Zhao

Kevin Zhao

Software Engineer, Arm
Kevin Zhao is currently a Software Engineer in Arm Limited. Now, he is serving as the Core Reviewer for OpenStack Zun project. He is also an active contributor in Kolla and Nova, mainly focusing on making OpenStack work fine on AArch64. His expertise including container and Kubernetes... Read More →



Wednesday June 27, 2018 15:10 - 15:50 CST
307A
  Infrastructure & Automation

15:10 CST

Shared Virtual Memory in KVM - Yi Liu, Intel China Ltd Beijing Branch (slides attached)
Shared Virtual Memory in KVM (Liu Yi, Intel) - Shared Virtual Memory is a hardware extension which allows directly access CPU virtual address, thus enables fast workload submission on accelerators. This feature goes with PCI sig Process Address Space ID (PASID). Many hardware vendors (Intel, AMD, ARM, etc.) have made it a key feature in their platform. It has become a hot area about bringing aforementioned feature to a virtualized environment, which brings flexibility to the accelerator deployment in data center.

In this presentation, Yi Liu will first introduce basic concept of SVM and the hardware requirement of SVM. Then, the session would focus on the SVM virtualization(vSVM) and architecture design in KVM solution. There would be detail technical introduction to the overall flow of vSVM and IOMMU API extensions(new APIs like bind_pasid_tbl/sva_tlb_invalidate and general in-kernel fault report framework). In the end, there would be an update of the vSVM status in community and future work.

Speakers
avatar for Yi Liu

Yi Liu

Senior Software Engineer, Intel Corporation
Yi is a senior software engineer from Intel OTC. He focuses on I/O virtualization(Intel® VT-d) and is responsible for virtual IOMMU upstreaming work within Intel OTC VMM enabling team. As a well-recognized contributor, he represents Intel on IOMMU virtualization related discussions... Read More →



Wednesday June 27, 2018 15:10 - 15:50 CST
203AB
  KVM

15:10 CST

overlayfs: Current Status and Upcoming Future - Yi Zhang, Huawei (slides attached)
overlay filesystem is a kind of union-filesystem for Linux which has been widely used, such as container. It is
base on basic filesystem(s) and merge different layers(filesystems/directories) hierarchically into one, and share objects in basic layers between different overlay filesystems.
In the past year, a lot of defects have been repaired and some new features has been added into the Linux kernel upstream, such as "constant inode number", "prevent hardlink break" and "nfs export" by Amir Goldstein, and user space program fsck.overlay is under way now. However, there are still many drawbacks for various technical reasons.
This topic gives the description of the overlay filesystem, the merged features in the past year and the upcoming features have been proposed and discussed in the Linux community.

Speakers
YZ

Yi Zhang

software engineer, Huawei Technologies Co Ltd
Yi Zhang, Software engineer, Huawei Technologies Inc. Work in Huawei kernel team, focus on ext4 filesystem and overlay filesystem.



Wednesday June 27, 2018 15:10 - 15:50 CST
307B
  Linux Systems

15:10 CST

Provide Zero Downtime for Your Critical Applications, Including Container Deployments - Honglin Su & Frank Zhang, Oracle (slides attached)
As more customers adopt emerging technologies, like OpenStack, Docker, Kubernetes, and Blockchain, the ability to patch systems with critical security errata without downtime is crucial. 

Oracle Linux, engineered for open cloud, powers Oracle Cloud and tens of thousands of enterprise customers. Oracle Linux is the only Linux distribution that supports live, non-disruptive patching, both in the kernel space and in the user space. That means you can immediately apply security patches without impacting your production environment—and without rebooting. To date, more than one million patches have been delivered in this fashion through Ksplice. 

In this session you will learn
- How Ksplice delivers zero-downtime update for your core infrastructure
- How Oracle Linux provides a proven, secure, and reliable platform for the latest services offered by Oracle Cloud

Speakers
avatar for Honglin Su

Honglin Su

Sr. Director of Product Management, Oracle, Oracle
Honglin Su leads the product management for Oracle Linux and Virtualization to help customers transform their traditional data centers to the cloud. He has spoken at numerous conferences, in particular at LinuxCon + ContainerCon + CloudOpen in Beijing 2018 and several times at Oracle... Read More →
avatar for Frank Zhang 张国华

Frank Zhang 张国华

Principal Solution Consultant, Oracle
甲骨文资深系统架构师,十余年传统行业内开源产品和方案的应用经验,重点关注基础平台开源产品以及自动化运维和DevOps领域,主要服务于国内大型金融机构以及大型国有企业 Frank is a Principle Solution Architect from Oracle... Read More →



Wednesday June 27, 2018 15:10 - 15:50 CST
310

15:10 CST

Accelerate Network Protocol Stack Perforamance and Adoption in the Cloud Networking via DMM - Shui Cao, Huawei (slides attached)
With the development of network infrastructure, the network stack needs to be re-invented to meet the highly diversified and ultimate QoS/SLA requirements from the next generation Internet applications. There are some challenges as the following:
- Legacy TCP is best effort based, no performance guarantee.
- One-size-fits-all protocol or algorithm becomes less feasible.
- Complicated and heterogeneous network environments makes common optimization less possible.
- Growing concern on security on any given protocol.

Huawei designed a new open source protocol development kit - DMM(Dual-domain,Multi-protocol, Multi-instance), which provides an extendable transport protocol framework and runtime library, accelerate current transportation protocol performance and new protocol adaption. Huawei wants to share DMM with developers, build up an friendly ecosystem for network stack together.

Speakers
avatar for 曹水

曹水

Senior Researcher, 华为
Liang Wang and Jerry Li are senior architects from Huawei Cloud Network Lab. They focus on Smart NIC , vSwitch, have rich experiences on Packet Processing optimization and DPDK appliances.



Wednesday June 27, 2018 15:10 - 15:50 CST
311B

15:10 CST

Lessons Learned from Leading an Open-Source Project Supporting 30+ Programming Languages - William Cheng, REST United
Swagger Codegen, which is an open-source code generator for REST API, has become very popular in recent years. Many companies, from start-ups to IT conglomerates such as Cisco, IBM, VMWare, are using it in production to streamline the development process. The project covers a wide range of programming languages and server-side frameworks. How the project grows from less than 50 contributors to 850+ contributors from all around the world with 10000+ commits in 4 years? William Cheng, the top contributor of Swagger Codegen, will share the journey the community went through and the lessons learned from building a vibrant developer community.

Speakers
avatar for William Cheng

William Cheng

Core team and founding member of OpenAPI Generator, OpenAPITools.org
William Cheng is an experienced IT professional with 10+ years of experience in IT startups, academic research, a leading semiconductor equipment manufacturer and a top-tier global investment bank. He is also an entrepreneur, eBook author, conference speaker, and active open-source... Read More →


Wednesday June 27, 2018 15:10 - 15:50 CST
306B

15:10 CST

16:00 CST

Cryptographic Algorithms and Incentive Mechanics: From Blockchain to Maneuvering Data to Flow - Lilin Sun & Guo Wenjing, Juzix
Cryptographic algorithms are the basis of the entire digital world. Incentive mechanism is the basic motivation for the evolution of human society. Cryptographic algorithms and incentive mechanism are changing the way the digital world behaves. Hash algorithms and incentives mechanism create new ways to collaborate——through blockchain, consensus can be reached among different individuals who do not trust each other. With the dramatic growth in the amount of data in the digital world and the increasing need for data privacy protection, it has become crucial to be able to exchange data without compromising the ownership of data. The combination of multi-party computation and incentive mechanisms is the fundamental solution to this need. Incentive mechanisms aim to promote the flow of data, and multi-party computation aims to reinforce data sovereignty.

Speakers
avatar for Lilin Sun

Lilin Sun

CEO, JUZIX
2014.06—now, the founder& CEO of JUZIX; 2012—2014, the Deputy General Manager of Chinatvpay; 2007—2012, the Head of Strategy, Market Development of China Union Pay;Senior researcher in Strategic Development Department of China Union Pay. - Specially-invited expert of Xiongan... Read More →



Wednesday June 27, 2018 16:00 - 16:40 CST
311A
  Blockchain

16:00 CST

Distributing Stateful Workloads across Hybrid Clouds - Irfan Ur Rehman & Quinton Hoole, Huawei Technologies
Kubernetes Statefulsets are a great option for applications that need persistent stores and durable, unique identities for their replicas. However, Statefulsets are limited to a single cluster and cannot span multiple cloud providers.
Our team has been working on an approach to allow stateful replicas of such applications to span multiple, and even hybrid, cloud clusters. The capability, called Federated Statefulsets, is already in the roadmap of kubernetes federation project.
This talk will explain Federated Statefulsets use cases, discuss design alternatives considered, and describe the proposed solution. The presentation will also demonstrate the new feature solving some hard problems and discuss possible future enhancements.

Speakers
avatar for Quinton Hoole

Quinton Hoole

Technical Vice President, Futurewei
https://www.linkedin.com/in/quintonhoole/YouTube me for previous presentations.CNCF TOC Member
IU

Irfan Ur Rehman

Sr. Software Engineer, Turbonomic
Irfan is a senior engineer associated with the Advanced Engineering group at Turbonomic. In his current role he is tasked with drafting multi cluster capabilities for Turbonomic’s analytics platform. He has also been associated with SIG Multicluster, particularly Kubernetes Cluster... Read More →


Wednesday June 27, 2018 16:00 - 16:40 CST
309B

16:00 CST

Microservices Pattern Exploration in Enterprise Practice - Golfen Guo, DaoCloud Inc.
In the process of practicing microservices, many enterprises found that the design of application system will inevitable meet many difficulties of distributed system design. In the meanwhile, the differentiation and scale expansion of service components will further increase the difficulty of continuous integration and fast delivery.
Based on the rich hands-on enterprise practice, Golfen Guo have summed up several key patterns and anti-patterns of microservices implementation in enterprise. These patterns cover the full lifecycle of a microservices application, including domain design, system architecture, delivery, deployment, logging and monitoring, security and Iterative upgrade.
In this presentation, Golfen will share with audience about these patterns and anti-patterns. He will also introduce the real enterprise cases to practice these patterns and prevent from the anti-patterns.

Speakers
F

峰 郭

CTO, DaoCloud
DaoCloud is leading company focusing on container technology in China, has been committed to helping enterprise customers to build cloud-native capability, from Cloud platform/DevOps/Microservices perspectives. In recent 3 years, I leaded the NAT(Next-generation Application Transformation... Read More →


Wednesday June 27, 2018 16:00 - 16:40 CST
309A

16:00 CST

Use Hyper-V Enlightenments to Increase KVM VM Performance/Density - Chao Peng, Intel (slides attached)
Hyper-V designed a set of ‘enlightenments’ to reduce virtualization overhead. Some of the enlightenments has been implemented in KVM so KVM VM can also benefit from it. Recently Hyper-V added some more enlightenments for the VM-based so-called ‘Hyper-V containers’. However, till now these enlightenments are only available on Hyper-V and Windows. In this talk Chao will present we can implement the same enlightenments in KVM and the cooperative change in Linux, so not only Windows but also Linux can take advantages of these enlightenments when running on top of KVM. Especially, we can achieve similar effect for VM-based Linux container (e.g. increase the performance/density for Kata Containers).

Speakers
CP

Chao Peng

Senior Software Engineer, Intel
Chao Peng is a senior software engineer in Intel virtualization team. His responsibilities include enabling various hardware virtualization features in open source VMM/OS, as well as developing new usages models in virtualization and cloud environment. He was speaker in KVM forum/Xen... Read More →



Wednesday June 27, 2018 16:00 - 16:40 CST
203AB
  KVM

16:00 CST

Challenges and Opportunities for SD-WAN in China - Ziyi Lu, Tethrnet Technology (slides attached)
Recently, SD-WAN market have seen significant growth in the US and other countries, but there're several challenges in China market.
The first challenge is the communication quality of inter service providers, this makes endpoint to endpoint internet overlay tunnel communication unreliable (e.g. China Telecom endpoint to China Mobile endpoint), also missing public IP at endpoint puts additional difficulty on creating end to end overlay tunnel.
Secondly, China service provider expects seamless integration between traditional MPLS and internet based solution, i.e. branches may have both MPLS and internet access, or only one of them. SDWAN solution has to exchange routing information between traditional MPLS and internet based network.
This presentation provides solutions to these challenges. The solutions have been validated and deployed by several China service providers.

Speakers
avatar for Ziyi Lu

Ziyi Lu

CTO, Tethrnet Technology
Ziyi Lu is a cofounder and CTO of Tethrnet Technology Inc., who is focusing on innovative networking solution for enterprise and service provider – data center fabric, data center inter-connect fabric, WAN and cloud networking. He had authored number of US Patents regarding networking... Read More →



Wednesday June 27, 2018 16:00 - 16:40 CST
311B
  Networking & Orchestration

16:00 CST

Automatically Backup Module against Ransomware Attack - Kazuki Omo, SIOS Technology, Inc. (slides attached)
Automatically Backup Module against Ransomware Attack (Kazuki Omo) -

Ransomware attack is on-going nowadays, and lots of user is having trouble in Critical infrastructure. Not only Windows, but also Linux is facing from Ransomware threat. In Enterprise system, Linux is used as File Sharing server and facing Ransomware threat through NFS / Windows CIFS, and so on. In this presentation, Kazuki Omo will suggest several way to protect important file from Ransomware with developed Linux Security Module, and demonstrate it.

Speakers
avatar for Kazuki Omo

Kazuki Omo

Executive Officer, SIOS Technology Inc.
Over 20 years experience in Unix/Linux/Windows system and many of Security related product. Working for OSS community over 15 years. - Published SELinux and related security articles from 2004-2018. - Presentation on Open Source Summit Japan 2017 "OSS CVE Trends". - Presentation on... Read More →



Wednesday June 27, 2018 16:00 - 16:40 CST
307B
  Open Source Leadership

16:00 CST

Disclosure Policies in the World of Cloud: A Look Behind the Scenes - Lars Kurth, Citrix / Xen Project (slides attached)
The tech world does not live in silos: security vulnerabilities can impact an entire ecosystem (case in point Meltdown and Spectre). How do open source projects and companies alike ensure that their security disclosure policies are up to standards, especially in the world of cloud computing?

This session will introduce different patterns for managing the disclosure of security vulnerabilities in use today and explore their trade-offs and limitations. We will look at the interaction of open source projects and downstreams (distros, product vendors, cloud providers or a combination of them) from the discovery of a vulnerability to it being fixed. This talk will give you a glimpse into a quite extensive machinery which kicks into gear across different organisations when security vulnerabilities are discovered and fixed behind the scenes.

Speakers
avatar for Lars Kurth

Lars Kurth

Director Open Source / Project Chairperson The Xen Project , Citrix Systems UK Ltd.
Lars Kurth is a highly effective, passionate community manager with strong experience of working with open source communities (Symbian, Symbian DevCo, Eclipse, GNU) and currently is the community manager for the Xen Project. Lars has 12 years of experience building and leading engineering... Read More →



Wednesday June 27, 2018 16:00 - 16:40 CST
306B
  Open Source Leadership

16:00 CST

To Sustain Open Source Software Business - Yoshiya Eto, Fujitsu (slides attached)
Speakers
avatar for Yoshiya Eto

Yoshiya Eto

Principal Architect, Fujitsu Ltd.
Yoshiya Eto is a Principal Architect,open source business strategy, at Fujitsu and a Linux Foundation Fellow, enterprise technology and open source business strategy. He also served as Fujitsu’s representative to The Linux Foundation Board of Directors. He has been involved in operating... Read More →



Wednesday June 27, 2018 16:00 - 16:40 CST
307A
 
Filter sessions
Apply filters to sessions.