At the end of June, a regular meeting of the IP Club was held, a community created by Huawei to exchange views and discuss innovations in the field of network technologies. The range of issues raised at it was quite wide: from global industry trends and business challenges facing customers, to specific products and solutions, as well as options for their implementation. At the meeting, experts from the Russian enterprise solutions division and from the company's headquarters presented its new product strategy for network solutions, as well as revealed details about recently released Huawei products.
Since we wanted to fit the maximum of useful information into the allotted few hours, the event turned out to be rich in information. In order not to abuse Habr's bandwidth and your attention, in the post we will share the main theses that were discussed at the IP Club's "river walk". Feel free to ask questions! Short answers will be given here. Well, we will reveal those requiring a more thorough approach in separate materials.
During the first part of the event, guests listened to presentations prepared by Huawei experts, primarily on the AI-powered Huawei AI Fabric solution for creating next-generation ultra-high-performance autonomous networks, as well as Huawei CloudCampus, which promises to accelerate the digital transformation of businesses through a new approach. to the organization of cloud computing. A separate block was a presentation with the nuances of Wi-Fi 6 technology used in our new products.
After the conference part, the club members moved on to free communication, dinner and watching the beauties of evening Moscow overboard. The general agenda turned out to be something like this - now let's move on to specific speeches.
Huawei strategy: all your own, all for your own
Arthur Wang, Head of Huawei Enterprise IP in Russia, presented the company's network product development strategy to the guests. First of all, he outlined the framework, based on which the company straightens course in a turbulent market situation (recall, in May 2019, the US authorities included Huawei in the so-called Entity List).
To begin with, a couple of paragraphs about the results achieved. Huawei has been investing more than a year in strengthening its position in the industry, and is investing systematically. Over 15% of the company's revenue is reinvested in R&D. More than 180 of Huawei's more than 80 employees are involved in R&D. Tens of thousands of specialists are engaged in the development of chips, industry standards, algorithms, artificial intelligence systems, and other innovative solutions. By the end of 2018, the number of Huawei patents exceeded 5100 in total.
Huawei surpasses other telecom vendors in the number of representatives in the Internet Engineering Task Force (IETF), which develops the architecture and standards of the Web. 84% of the draft versions of the SRv6 routing standard, which serves as the foundation for building next-generation 5G networks, were also prepared by Huawei experts. In the Wi-Fi 6 standards development groups, the company's specialists made about 240 proposals - more than any other player in the telecom market. As a result, back in 2018, Huawei released the first Wi-Fi 6 hotspot.
One of the main long-term advantages of Huawei in the future will be transition to chips completely of our own design. It takes 3-5 years to bring a single ih-house-made chip to market, with an investment of several billion dollars. So the company started the implementation of the new strategy in advance and is now demonstrating its practical results. For 20 years, Huawei has been improving the chips of the Solar series, and by 2019 this work was crowned with the creation of Solar S: on the basis of "esok" routers for data centers, security gateways, and enterprise-class routers of the AR series are produced. As an intermediate result of this strategic plan, the company released the world's first processor for high-performance routers, designed using a 7-nanometer process technology, a year and a half ago.
Another Huawei priority is development of own software and hardware platforms. Including the VRP (Versatile Routing Platform) complex, which helps to quickly implement new technologies in all product series.
Huawei is also betting on development and testing of new technologies, based on the integrated product development (IPD) cycle: it allows you to quickly implement new functionality in a wide variety of products. Among the main assets of Huawei here is a huge distributed “factory”, with facilities in Nanjing, Beijing, Suzhou and Hangzhou, for automated testing of solutions in the corporate sector. With an area of more than 20 thousand square meters. m. and more than 10 thousand ports allocated for testing, the complex allows you to work out over 200 thousand different scenarios for the operation of the equipment, covering 90% of the situations that may arise during its operation.
Huawei also focuses on the flexible interaction of parts of its ecosystem, on its own production facilities for the production of ICT equipment, as well as on the cloud service for DemoCloud customers and partners.
But most importantly, we repeat, Huawei is actively working to replace external hardware developments in its solutions with its own. The transformation is carried out according to the management methodology "”, thanks to which each process is clearly regulated. As a result, in the foreseeable future, the company's chips will completely replace third-party ones. 108 models of new products based on Huawei hardware will be introduced in the second half of 2019. Among them are industrial routers AR6300 and AR6280 with 100GE uplink ports, which will be released in October.
At the same time, Huawei has time to make the transition to in-house development: while the US authorities allowed Broadcom and Intel to supply chipsets to Huawei for another two years. During the presentation, Arthur Wang hastened to reassure the audience regarding the ARM architecture, which is used, in particular, in the AR series telecom equipment: the license for ARMv8 (for example, the Kirin 980 processor is built on it) is preserved, and by the time the ninth generation of ARM processors enters the scene, Huawei will have perfected its own designs.
Huawei CloudCampus Network Solution - Service Oriented Networks
Zhao Zhipeng, director of Huawei Campus Networks, shared his team's accomplishments. According to the statistics presented by him, Huawei CloudCampus Network Solution, solutions for service-oriented, campus networks, currently serves more than 1,5 thousand companies from large and medium-sized businesses.
As the core of such an infrastructure, Huawei today offers the CloudEngine series switches, and primarily the CloudEngine S12700E for organizing non-blocking data forwarding in the network. It has a very high switching capacity (57,6 Tbps) and the highest (among comparable solutions) 100GE port density. Also CloudEngine S12700E is able to support wireless connections of more than 50 thousand users and 10 thousand wireless access points. At the same time, the fully programmable Solar chipset allows you to update services without replacing hardware. It also enables smooth evolution of the network from the traditional routing architecture that has historically been adopted in the data center to an adaptive network based on software-defined networking (SDN) technology: a service-oriented network allows gradual evolution.
In an infrastructure based on CloudEngine switches, wired and wireless networks converge easily: they are managed using a single controller.
In turn, the telemetry system allows you to monitor network devices in real time and visually visualize the activity of each user. And the CampusInsight network analyzer, through the processing of big data, helps to quickly identify possible malfunctions and establish their root causes. The AI-based operation and maintenance system greatly reduces the speed of responding to problems - sometimes up to several minutes.
One of the main features of the infrastructure with the CloudEngine S12700E "at the core" is the deployment of isolated virtual networks for several organizations.
Among the technical innovations that define the benefits of a network based on the CloudEngine S12700E, three stand out:
- Dynamic turbo. A technology based on the concept of "slicing" network resources adopted in 5G networks for various types of traffic. Due to hardware solutions based on Wi-Fi 6 and its own algorithms, it allows you to reduce the delay for applications with a high network priority to 10 ms.
- Lossless data transmission. DCB (Data Center Bridging) technology prevents packet loss.
- "Smart Antenna". Eliminates "failures" in the coverage area and is able to expand it by 20%.
Huawei AI Fabric: artificial intelligence in the "genome" of the network
For their part, King Tsui, Chief Engineer of Huawei Enterprise's Networking and Solutions Department, and Peter Zhang, Marketing Director of Data Center Solutions in the same department, each presented solutions that the company helps to deploy modern data centers.
Standard Ethernet networks are increasingly failing to provide the network bandwidth required by modern computing systems and data storage systems. These requirements are growing: according to experts, by the mid-2020s, the industry will be dominated by autonomous intelligent systems based on more and more sophisticated artificial intelligence and, possibly, using quantum computing.
In the work of data centers, three main trends are now distinguished:
- Ultra-high-speed transmission of huge data streams. A standard XNUMX-gigabit switch will not be able to cope with a twenty-fold increase in traffic. And today such a reserve becomes necessary.
- Automation in the deployment of services and applications.
- "Smart" O&M. Solving user problems in manual or semi-automatic mode takes hours, which is unacceptable by the standards of 2019, not to mention the near future.
To meet them, Huawei has created an AI Fabric solution to deploy next-generation networks capable of transmitting data without loss and with very low latency (at the level of 1 µs). The central idea of AI Fabric is the transition from a TCP / IP infrastructure to a RoCE converged network. Such a network provides remote direct memory access (RDMA), moreover, is compatible with conventional Ethernet and can exist "on top" of the network infrastructure of old-style data centers.
At the heart of AI Fabric is the industry's first data center switch powered by an AI chip. Its iLossless algorithm optimizes network processes based on the specifics of traffic and ultimately significantly improves the efficiency of computing in data centers.
With three technologies for accurate congestion identification, dynamic peak load adjustment, and high-speed backflow control, Huawei AI Fabric reduces infrastructure latency, virtually eliminates packet loss, and expands network throughput. Thus, Huawei AI Fabric is well suited for distributed storage systems, AI solutions, and high-load computing.
The industry's first AI-embedded switch is the Huawei CloudEngine 16800, equipped with a 400-port 48GE network card and AI-enabled chip, and has the potential for autonomous infrastructure management. With CloudEngine 16800's built-in analysis system and centralized network analyzer FabricInsight, it's possible to identify network failures and their causes in seconds. AI system performance on CloudEngine 16800 reaches 8 Tflops.
Wi-Fi 6 as the basis for innovation
Among Huawei's top priorities is the development of the Wi-Fi 6 standard, which underpins most future-proof solutions. In his mini-report, Alexander Kobzantsev told in detail why the company made a bet on 802.11ax. In particular, he explained the benefits of Orthogonal Frequency Division Multiple Access (OFDMA), which makes the network deterministic, reduces the possibility of network collisions, and ensures stable performance even in conditions of multiple connections.
Conclusion
Judging by how reluctantly the IP Club regulars dispersed and how many questions from them fell on the members of the Huawei team, the meeting was a success. Those who wanted to continue highly concentrated communication about the future of network technologies with like-minded people were interested in where and when the next meeting of the club would take place. True, this information is so secret that it is not yet available even to the organizers. As soon as the time and place of the meeting become known, we will make an announcement.
But what is absolutely certain is that very soon we will write a post about the implementation of CloudCampus with details from our engineers - stay tuned for Huawei blog updates. By the way, perhaps you yourself want to know something specifically about CloudCampus? Ask in the comments!
Source: habr.com