Loading…
July 17-19 | Tokyo, Japan
View More Details  & Register Here

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

Open Networking & Edge Computing [clear filter]
Thursday, July 18
 

11:10

Recent Enhancements of Node-RED for Rapid Development of Large Scale and Robust IoT Applications - Hiroyasu Nishiyama, Hitachi, Ltd.
Node-RED is a GUI-based application development platform widely used for rapid creation of IoT applications. An application of Node-RED is a message driven program
called a flow/ It is created in a intuitive way by
connecting functional nodes.
In this presentation, we introduce enhancements recently incorporated in Node-RED and current proposals for future enhancements including:

- API for creating new UI widgets,
- feature for creating reusable flow components,
- testing support of flows,
- checking flows with validation rules.

These features will allow Node-RED users to create
large and robust IoT applications rapidly.

Speakers
HN

Hiroyasu Nishiyama

Chief Researcher, Research & Development Group, Hitachi, Ltd.
To be provided


Thursday July 18, 2019 11:10 - 11:50
Hall B (3) (Floor 4F)

12:00

Schema-Less Columnar Storage Format Yosegi - Yasunori Oto, Yahoo Japan
Flexibility and performance is a critical point in a big data analytics platform on distributed systems.
For flexibility, it is essential to apply a schema at the time of data analyzing. On this point, a strategy called schema-on-read is widely used. This strategy arrows us to accumulate various types of data without worrying about how to analyze them. Additionally, it simplifies the data platform by omitting the schema synchronization system between data collection tier and data query one. However, this method has a disadvantage in performance because such type of data format is not optimized for data analyzing.

For performance, using a columnar format can help us to improve the utilization of the CPU and memory at the time of data reading. Apache ORC and Apache Parquet are known as this kind of format. These formats adopt the schema-on-write strategy. This strategy is optimal for querying, but it requires to specify the scheme beforehand of data storing. This feature leads to the difficulty that we should have an intention of how we analyze data at the time of designing scheme. To alleviate this point, we can use map type for input data. However, this method spoils the effect of projection push-down as these formats deserialize all the data contained in the map type.

We developed "Yosegi" as a schema-less columnar format to obtain both of the benefits. At the time of storing, this format constructs the namespace for storage schema from input data, interprets map type data as struct type data consisting of the keys contained in this map and stores data on a columnar basis. At the time of reading, it assigns the fields in the analysis-time schema to the namespace and fetches the data by its field name. Those two devises of design realize the flexibility of schema-on-read and the performance of schema-on-write. The format is available as Apache 2.0 licensed OSS on https://github.com/yahoojapan/yosegi.

In this presentation, we introduce how the format writes and reads data, performance comparison with other columnar formats and how we leverage the format in our data platform.

Speakers
YO

Yasunori Oto

Data Engineer, Yahoo Japan


Thursday July 18, 2019 12:00 - 12:40
Hall B (3) (Floor 4F)

14:00

Identify Encrypted Application Protocols Based on VPP - Hongjun Ni & Xiang Wang, Intel
Because of port-independent and encrypted protocols, identifying application protocols within encrypted traffic becomes very difficult.
Hyperscan is a high-performance multiple regex matching library.
This talk will introduce a high performance Deep Packet Inspection solution based on VPP and Hyperscan.
It shows high protocol detection accuracy and efficiency, and also guarantees packet order.

It contains below key elements:
1) Implement a flow-based framework on VPP, which leverages Hardware flow offloading and Software mechanism.
2) Hardware flow offloading is supported to accelerate classifying flows.
3) Software flow mechanism provides more flexiblity and huge number of flows.
4) Parse and reassemble complete TLS certificate, even if they are splitted into many packets.
5) Leverage regex matching in Hyperscan to identify application protocols within SSL/TLS packets.

Speakers
XW

Xiang Wang

Senior Software Engineer, Intel
Xiang Wang is a senior software engineer and technical lead of Hyperscan at Intel. His major areas of focus include regular expression matching, Intel architecture-based algorithm optimizations and deep packet inspection related networking solutions including protocol/application... Read More →
avatar for Hongjun Ni

Hongjun Ni

Senior Software Engineer, Intel
Hongjun Ni is focusing on high performance data plane and Cloud Native Networking. _x000D_ He is FD.io VPP Maintainer, Sweetcomb Project Lead, NSH_SFC Project Lead and Hc2vpp Committer. _x000D_ He has fourteen years' rich experience on Cloud Native, SmartNIC, Wireless, Wireline and... Read More →


Thursday July 18, 2019 14:00 - 14:40
Meeting Room 1 (Floor 5F)

14:50

Serverless Without Containers - Shashank Mohan Jain & Gaurav Gupta, SAP Labs
In this talk, we will highlight an alternative way of doing serverless which doesn't depend on using Linux containers or docker. We talk of a very novel way on how functions can be created with minimal bootup time and consuming minimal resources and still having proper isolation in the context of multi-tenanted functions.
We look at the evolution of web assembly (WASM) and Web assembly system interface (WASI) as one of the ways in which functions can be built in languages like C, Nodejs, Rust and compiled to a WASM format and executed within a wasm runtime. The talk also compares the benefits of the approach over the approach of using containers and how this can change the game in the near future.
We will also highlight how multi-tenanted functions are run and how isolation of memory, CPU can be achieved. We also touch upon security aspects like using capability-based security can be achieved.

Speakers
avatar for Gaurav Gupta

Gaurav Gupta

Developer, SAP Labs
Gaurav is a Software Engineer at SAP Labs, working with the Cloud Platform team. Gaurav is currently working on design and implementation of Service Brokers for SAP's Cloud Foundry and Kubernetes Cloud Platforms. He also has experience in Linux Kernel and User space profiling and... Read More →
SM

Shashank Mohan Jain

Chief Development Architect, SAP
Shashank works as a chief development Architect with SAP cloud platform. Shashank works primarily in the area of virtualization and containers. Shashank has been a speaker in multiple cloud foundry summit as well as with other known conferences.


Thursday July 18, 2019 14:50 - 15:30
Hall B (3) (Floor 4F)

16:00

Building Edge Analytics at the Edge with Open Source Components in Action - Hyokeun Choi, Samsung SDS
Internet-of-Things supports machines, computers and users to enable intelligent operations using advanced device management and data analytics. Growing massive volumes of data captured by IoT sensors and minimizing latency to improve response times are inevitably lead the edge computing and this implies the edge analytics process and analyze data at the source rather than sending that data back to the cloud. Although this data analysis at the edge offer a cost-effective and relatively efficient solution, building the edge analytics applications is hard to achieve under the limited computational and storage capabilities the IoT devices have.

Hyokeun Choi, a dev. leader of Brightics IoT platform at Samsung SDS, will introduce how to build performance efficient, portable edge analytics, demonstrate this benefits, and discuss the open source components while enabling this feature in Action.

Speakers
avatar for Hyokeun Choi

Hyokeun Choi

Senior Engineer, Samsung SDS
Hyokeun Choi is a passionate engineer, product manager, storytelling speaker and one of development leader of Brightics IoT platform at Samsung SDS. Hyo is responsible for building Edge Analytics Engine at the edge this year and has been contributing to open source softwares to drag... Read More →



Thursday July 18, 2019 16:00 - 16:40
Hall B (3) (Floor 4F)

16:50

A Step-by-step Guide to Building a True Composable Architecture for 5G/Edge - Tejas Nevrekar , Lumina Networks
The next generation infrastructure needs composable architecture to realize the needs of 5G/Edge requirements. This session provides an overview of the framework and Opensource tools to build a composable architecture. The session will touch upon Radio (SDN-R), Transport(Network Slicing) and Multicloud management and orchestration solutions (ONAP) the key building blocks of 5G and how cloudnative helps those areas. The session will also provide deep insights into Kubernetes Custom Resource (CRD) models and how it helps in defining a true cloud native architecture.

Speakers
avatar for Tejas Nevrekar

Tejas Nevrekar

Principal Engineer, Lumina Networks



Thursday July 18, 2019 16:50 - 17:30
Hall B (3) (Floor 4F)
 
Friday, July 19
 

11:50

Stream Processing on the Edge - Eduardo Silva, Arm / Treasure Data
In Data Analysis, Logging is one of the key components to collect and pre-process data, usually, a logging mechanism goes through the normal workflow of collect, parse, filter and centralize logs to a storage backend like a database, so data processing and analysis can be performed.

Data Processing usually happens after the data has been aggregated and stored, but for real-time analysis needs, process the data while is still in motion brings a lot of advantages and this kind of approach is called Stream Processing.

In this presentation, we will go further and present an extended approach called 'Stream Processing on the Edge', where data is processed on the edge service or device, in a lightweight mode empowering features like anomaly detection (in the order of milliseconds) and Machine Learning in a distributed way using pure Open Source software.

Speakers
avatar for Eduardo Silva

Eduardo Silva

Principal Engineer, Arm Treasure Data
Eduardo is a Principal Engineer at ARM / Treasure Data. He currently leads the efforts to make logging and data processing more friendly and scalable in Embedded and Containerized systems such as Kubernetes. Maintainer of Fluent Bit, a Fluentd open source sub-project.


Friday July 19, 2019 11:50 - 12:30
Hall B (3) (Floor 4F)

14:00

BoF: Let's Play Small-mini-card-sized Computer Boards! - Masafumi Ohta, Japanese Raspberry Pi Users Group
There are tons of small, mini, card-sized computer boards have been released since Raspberry Pi was born to the production and lately you can see them everywhere to apply them to not only electric DIY personal/education use but also Enterprise/industrial use. In this session, Masafumi will discuss deep-dive topics :

1. Introduction: define those boards
2. Model concepts: why are they mini, small, card-sized and cheap?
3. Disk media: are they bearable for any use? (ex.SD)
4. Robustness: it is really robust ( circuits and etc..)?
5. Kernel: is it really fit on the boards?
6. Operating System: is it easy to handle?
7. Other tips and issues: USB, SoC thermo, Auto-deploy, Edge-AI and etc.. And Masafumi discuss many of use cases to look into deeply and learn some practices.
  • opportunities to use the boards
  • how to use the boards
  • how to manage the boards ( especially to overcome drawbacks )

Speakers
avatar for Masafumi Ohta

Masafumi Ohta

Founder and Representative, Japanese Raspberry Pi Users Group
Masafumi is leading Raspberry Pi community in Japan and volunteering Raspberry Pi Foundation from farthest east country, Japan,.He has helping their business and encourage Raspberry Pi related projects with Raspberry Pi Foundation. Masafumi has elected ARM INNOVATOR by ARM+Hackster.io... Read More →



Friday July 19, 2019 14:00 - 14:50
Hall B (3) (Floor 4F)

14:50

DPDK IPsec: A Scalable High Performance Library for Your IPsec Application - Fan Zhang, Intel
IPsec is the most commonly used security protocols in 4G-LTE, and is recognized as the method of securing control and data channels of 5G. For adapting the massive traffic encryption needs in 5G, we propose our DPDK IPsec library, a scalable, high performant, and modularized library with simple but comprehensive APIs to ease your IPsec application development. Moreover, DPDK IPsec library is designed with seamless adoption of different software and hardware security accelerators (lookaside and inline hardware), and can work in both native and virtual platforms without application change. In this presentation we will describe the modular architecture of the library and propose the integration of the library into data plane applications, including the performance indicators of different use-cases.

Speakers
FZ

Fan Zhang

Network Software Engineer, Intel
Zhang Fan, born in Changsha, Hunan province, holds a PhD. in Network Information Security from University of Limerick. He is now a network software engineer in Intel Ireland. Fan has published 3 international journals and conference papers indexed by SCI/EI and is one of the authors... Read More →


Friday July 19, 2019 14:50 - 15:30
Hall B (3) (Floor 4F)

16:00

Carrier-Grade Container Components in BBU for 5G - Hui Chen, Huawei
Container like docker has been widely used in the cloud computing environment, but for the embedded devices used in the base stations have totally different requeiremnts for the container infrastructure. Huawei has developed its own light container components(as known LCRD in Huawei) for the BBU environment, which could help the customers to quickly deploy businesses, also dynamically allocate the resources between 3/4/5G. LCRD has been used in our 5G products and make them competetive around the world.

Speakers
HC

Hui Chen

Principle Engineer, Huawei
Dr. Chen is the principle engineer in Huawei RTOS development team. He obtained his Ph.D degree from Gatech and BeiYou University co-cultivation program. He has given several talks at L3C and other community conferences.


Friday July 19, 2019 16:00 - 16:40
Hall B (3) (Floor 4F)

16:50

Kubernetes Native Infrastructure and CoreOS Operator Framework for 5G Edge Cloud Computing - Hyde Sugiyama, Red Hat
Launched in 2018, several blueprints are work in progress such as KNI(Kubernetes Native Infrastructure for Edge) project for 5G edge computing, in Akraino Edge Stack.

Service Providers started to explore for Container native Network Function such as 5GC, C-RAN and Edge computing, in Kuberntes(K8s) that is de facto container system environment in open source communities. They need not only legacy edge computing such as CDN service but also they will need Intelligent-edge platform providing AI platform, data lake and etc in scalable cloud manner.

Challenge of Edge computing in K8s environment at Telco edge is management scalability for many micro clouds over than 100-1000 edge sites.

This session will discuss K8s solutions and Telco Intelligent-edge possibilities by integrate with CoreOS Operator Framework that can manage CNFs, statefull and other stateless container applications.

Speakers
avatar for Hyde Sugiyama

Hyde Sugiyama

Chief Architect, Red Hat
Hidetsugu Sugiyama is Chief Architect at Red Hat and focus on Service Provider sector in Japan. Hidetsugu has been with Red Hat for six years, working on SDN/NFV/Edge Computing solutions development and joint GTM with NFV/SDN partners. He has 30+ years experience in the Information... Read More →



Friday July 19, 2019 16:50 - 17:30
Hall B (3) (Floor 4F)
  • Experience Level Any