Shanghai, China
June 24–26, 2019
Click here for more information and registration

Simultaneous translation will be provided for all keynote and breakout sessions.

To view the Chinese version of this schedule please go here.

Venue + Sponsor Showcase Map
场馆 + 赞助商展示区地图

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

KC+CNC - Networking [clear filter]
Tuesday, June 25


Topology-Aware Service Routing for Kubernetes is Coming Soon! - Jun Du, Huawei
There are 3 topology-awareness areas in Kubernetes, e.g. scheduling, storage and service. Topology-aware scheduling and volume provision have already been supported, while topology-aware service routing is not supported yet. As we know, cross-zone network traffic being charged, while in-zone is not. Suppose an user only want to visit service backends that are in the same zone with client. Kube-scheduler can constraint the Pods to run on a particular zone, but kube-proxy may choose an endpoint which is in the different zone. In order to get rid of such paint points, sig-network is leading a new feature development in community - topology-aware service routing.
The feature owner will dive into the design and challenges in implementing topology-aware service routing. Future direction of this feature will be covered as well, including what's on the table for beta and graduation criteria.

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 →

Tuesday June 25, 2019 16:00 - 16:35


Cloud Native Load Balancing From Scratch - Fangyuan Li, VMware
Load balancing is required by all modern distributed systems, which can be done in many places and multiple layers. With all the options on the table, eg: gRPC, Envoy, IPVS/BPF, have you been curious of when and how any one of them will fit into your stack and scale your system as traffic grows?

Aiming to “demystify” load balancing in K8s, I’d like to share my experience utilizing these cloud-native load balancing techniques, discussing their tradeoffs and applicable scenarios.

The journey starts with a simple VIP iptable implementation. Then we dive deeper and examine from client to server, kernel to userspace, going up from IP to HTTP. We’ll draw the big picture and demonstrate the use of different tools in plain Bash scripts. With these building blocks in mind, we’ll summarize by comparing them across K8s(clusterIP/nodePort), Docker(routing mesh), Envoy, and a number of CNI plugins.

avatar for Fangyuan Li

Fangyuan Li

Software Engineer, VMware
Peking University is my Alma Mater where I received Bachelor in Mathematics. After graduation, I went to Stony Brook University to study Computer Science.I currently work for VMware, in Cloud Native Business Unit, as one of the early members of PKS project. Our team works on the integration... Read More →

Tuesday June 25, 2019 16:45 - 17:20


Network Flow Monitoring in Kubernetes with Contiv/VPP CNI and Elastic Stack - Rastislav Szabo, Pantheon Technologies
Although most of the Kubernetes cluster administrators do not care about the network traffic in their clusters while everything works, visibility into the network flows in the cluster (both in real time and in history) is crucial for debugging networking issues, identifying the bottlenecks in the deployments, or investigation of security incidents.

This talk showcases how a powerful network flow monitoring & analysis tool for Kubernetes can be built by integrating of several existing open-source components:

- Contiv/VPP CNI plugin, which uses FD.io VPP (Vector Packet Processing) stack with enabled IP Flow Information Export (IPFIX),
- Logstash for collecting and post-processing of the network flows,
- Elasticsearch which acts as the storage and search engine for the flows,
- Kibana for easy observability of the stored flows.

avatar for Rastislav Szabo

Rastislav Szabo

Staff Enginner, PANTHEON.tech
Rastislav is an enthusiastic and motivated professional with more than ten years of software development experience, recently working mostly on networking-related and cloud-native projects. He is a Staff Engineer at PANTHEON.tech with primary focus on SDN, NFV and Cloud-Native VNFs... Read More →

Tuesday June 25, 2019 17:30 - 18:05


Hybrid Cloud and Multi-Cluster Service Connectivity - Sridhar Gaddam & Aswin Suryanarayanan, Red Hat
Hybrid Cloud is becoming a common deployment these days. When your kubernetes clusters are spread across a mix of on-prem/public clouds, and you want your cluster local services (i.e., non-publicly accessible services) to be made available to services in a different cluster, there are number of things to be considered like Cluster Connectivity, Service Discovery, Security etc.

In this presentation we would like to present a solution that is
1. Cloud Agnostic: works on both on-premise and public clouds
2. CNI Agnostic: works with any of the kubernetes CNI networking plugins
3. Tunnel Management and Health-check: includes mechanisms to connect two/more clusters and periodically perform health-checks
4. Service discovery and Service reachability: expose cluster-IP services to other clusters
5. Inter-Cluster Network Policy: provides mechanisms to explicitly allow/deny traffic

avatar for Sridhar Gaddam

Sridhar Gaddam

Senior Principal Software Engineer, Red Hat
Sridhar Gaddam works for Red Hat as a Principal Software Engineer and has more than 16 years of experience. Sridhar has been working on OpenStack, OpenDaylight (core member) and OPNFV projects for the last couple of years and is primarily focused in the areas of Networking.
avatar for Aswin Suryanarayanan

Aswin Suryanarayanan

Senior Software Engineer, Red Hat
Aswin is a developer with experience in software-defined networking and cloud application. He is a committer in Opendaylight Netvirt project and contributor to Opendaylight and Openstack open source communities.  He recently started working in hybrid cloud use cases in Openshift... Read More →

Tuesday June 25, 2019 18:15 - 18:50
Wednesday, June 26


Porter - An Open Source Load Balancer for Bare Metal Kubernetes - Xuetao Song & Fang Du, Beijing Yunify Technology Co., Ltd.
As we know, the backend workload can be exposed externally using service of type "LoadBalancer" in Kubernetes cluster. Cloud vendors often provide cloud LB plugins for Kubernetes which requires the cluster to be deployed on a specific IaaS platform. However, many enterprise users usually deploy Kubernetes clusters on bare meta especially for production use. For the on-premise bare meta clusters, Kubernetes does not provide LB implementation. Porter, an open-source project, is the right solution for such issue.
This session will focus on the network technologies to help expose service and EIP management for bare meta Kubernetes


Fang Du

QingCloud Solution Architect, Beijing Yunify Technology Co., Ltd.
Fang Du(Flora), QingCloud Solution ArchitectFlora is a Solution Architect at QingCloud(Yunify), who focuses on cloud-native, service mesh and DevOps, and has rich experience in financial solution area, and used to provide solutions to many bank and insurance companies. In her free... Read More →

Xuetao Song

senior software engineer, Beijing Yunify Technology Co., Ltd.
Xuetao Song is a software engineer at yunify, responsible for the network and CI/CD of container platforms . He believes that containerization is an inevitable trend. He also loves open source , often submits commits to the kubernetes community in his free time. 宋雪涛是yuni... Read More →

Wednesday June 26, 2019 11:20 - 11:55