Brief introduction:From May 20 to 22, the 13th China Systems Architects Conference (SACC2021) was webcast on the cloud with the theme of “Digital Transformation, Architecture Remolding”. Jiang Cen, the original technical expert of Aliyun Edge Cloud, shared the exploration and practice of Aliyun Edge Cloud, and elaborated the core competitiveness of the product from the aspects of coping with technical challenges and system architecture design, so as to drive the business development with innovative technology.

From May 20 to 22, the 13th China Systems Architects Conference (SACC2021) was webcast on the cloud with the theme of “Digital Transformation, Architecture Remolding”. Jiang Cen, the original technical expert of Aliyun Edge Cloud, shared the exploration and practice of Aliyun Edge Cloud, and elaborated the core competitiveness of the product from the aspects of coping with technical challenges and system architecture design, so as to drive the business development with innovative technology.

Cloud native development and status quo

With the maturity of cloud computing technology, most enterprises choose cloud computing to quickly deploy operational business. 5G commercialization on a large scale will facilitate the networking of tens of billions of terminal devices around the world. Customers’ demand for near-end quasi-real-time computing with low delay and large bandwidth will increase greatly. On the one hand, the growth of the marginal cloud computing market scale comes from the sinking edge of the central business, and on the other hand, the emergence and development of various marginal innovative business scenarios, such as cloud games and smart cities.

Jiang Cen believes that the cloud on the enterprise business system, whether it is the upper center cloud or the edge cloud, will experience three stages:

The migration of self-built IDC, based on stability, disaster preparedness and other factors, will not make major adjustments to the business architecture, and most of them only use the most basic cloud services, such as ECS, SLB, VPC, etc.

On the whole business cloud, from the perspective of comprehensive reuse of cloud capabilities and efficiency and cost reduction, the evolution of cloud architecture has also gradually begun gray application.

When all is in place, businesses are embracing cloud nativism in a big way.

And the present stage, a lot of cloud business has been in large-scale advance cloud original biochemical.

The concept of cloud native originated from CNCF Cloud Native Computing Foundation, the Kubernetes platform incubated by Google. Founded at the end of 2015, CNCF has incubated a large number of high-quality projects in line with cloud native standards, whose core modules include database, messaging middleware, application scheduling, CICD continuous integration, RPC, service grid, container services, cloud native network, and so on.

Today, cloud native technology is no longer limited to the container /Kubernetes domain, and is becoming the standard architecture for the majority of cloud vendor neutral hardware and software infrastructure. Edge computing is a technology gradually emerging in the recent 3-5 years with the application of 5G and Internet of Things technologies. Its technology maturity is still far lower than that of central cloud computing. At present, there are few projects involving edge computing on CNCF. With the improvement of edge scenes and supporting capabilities, a large number of businesses in the center sink to the edge, and edge innovation scenes continue to emerge, which will inevitably give birth to cloud native technologies in line with edge characteristics at the edge.

The challenges of marginal cloud native evolution

Jiang cites three technical challenges when talking about how cloud-native technologies will evolve to the margins:

  • From the perspective of resources, the edge is different from the large-scale centralized layout of the center, and mainly aims at distributed construction and high regional coverage. In addition to the central standard cloud server, there are also a large number of heterogeneous resources on the edge, including Internet of Things devices, MEC, cooperative joint construction nodes, and so on. Cloud native technology has clear requirements on the deployment environment, so it needs to make flexible adaptation to the massive heterogeneous resources on the edge. In addition, the edge nodes are small and many, so the key is to improve the reuse rate of resources, which requires flexible and elastic scheduling according to the ability of resource pooling and resource performance.
  • From the point of technical ability, edge of cloud infrastructure, cloud native ability to sink application directly to the edge, in addition to the need to provide the equivalent performance indicators in the center of the disaster, safety isolation, autonomy, architecture, cognitive ability, also need to constantly improve cloud edge and edge high-speed channel construction, raise the construction difficulty coefficient.
  • When resource adaptation and technical capabilities are available, maintaining a consistent user experience can be a big challenge. From a user perspective, the center is a long process, the sinking process of the business for a single business center and edge may be in the condition of long-term coexistence, capacity building, on the edge of the cloud is likely to exist, most of the inconsistent to the user should be non-inductive, so how to packaging products, in cost, function, performance, stability and so on various aspects to achieve consistent experience cloud edge, It’s very challenging.

Primary System Construction of Aliyun Edge Cloud

Relying on more than 2800 edge cloud nodes around the world, Ali Cloud provides users with secure, stable and reliable edge computing and content distribution acceleration services, and builds the edge cloud infrastructure closest to users. A single node is a small IDC, ranging in size from a few servers to dozens of servers. In the early stage, the strategy of establishing edge cloud nodes was to build points separately and independently from CDN, resulting in the inability to share resources and the lack of business. The current construction strategy is to promote the integrated production of CDN ON ENS resources and integrate the edge computing power resources. After the integration, it also brings greater possibilities for time-sharing reuse of resources.

As the most mature application scenario of edge cloud, CDN has experienced long-term technical architecture evolution, and its infrastructure hardware and software architecture can be reused into edge cloud technology. The source station is usually the server built by the enterprise itself, which is relatively limited in scale and performance compared with the central cloud. It can operate normally at the early stage of the service launch, but with the growth of the business, faced with massive client requests, if there is no CDN, the enterprise can only increase resource input, otherwise it may cause response timeout of the server and even service paralysis. By means of multi-level caching and global DNS scheduling capability, CDN enables users to access the required resources (especially static resources such as pictures and videos) nearby, so as to avoid excessive pressure on the bandwidth of source stations and servers. Since CDN can meet the needs of users in different regions for nearby access, it can be considered that CDN naturally has the typical characteristics of edge cloud computing with low delay and large global bandwidth. Support CDN monitoring, data intelligence, configuration management and other systems, with standard edge mass data distribution, processing, as well as the ability to interact with the center, will gradually evolve into the edge cloud native supporting standard system.

According to the original capability model definition of Aliyun edge cloud, it can be seen that: On the resource side, heterogeneous resources (including traditional physical machines, cloud linked nodes, IoT/MEC devices, ARM array servers, etc.) are combined and clouded, on which edge cloud node operating systems are provided to virtualize computing, storage, and network resources. In addition, based on the native capabilities of container /K8S standard cloud, modular capacity construction is carried out and the corresponding edge standard ecological extension output community is extended. For example, the ability to manage and arrange the release of the whole network’s full set application life cycle is required for business, and the ability to define the edge CRD operator Edgeworkload is provided by AliCloud. Define OAM orchestration extensibility capabilities. For platform administrators, such as multi-cluster management, tenant isolation, metadata management, etc. also need corresponding ability customization in the scenario of mass data of marginal users. In addition, there are a large number of distributed and heterogeneous resources on the edge, and how to maximize the utilization of resources depends on the global container scheduler combined with the global traffic scheduling and distribution strategy related to the business. The elastomeric HPA/VPA scenario is also an edge-oriented distributed solution.

Ali Cloud has resources all over the world, so it is necessary to define subregional planning strategies for heterogeneous resource management modules and carry out planning access, which is carried out in the way of central control + marginal autonomy + multiple caching.

Considering the structural complexity of the edge cloud, the number of massive nodes, the difference of heterogeneous resources and other factors, Ariyun continuously improves the system observability and strengthens the DevOps operation and maintenance construction ability to improve the stability of the system.

At the same time, Aliyun edge cloud native has many technical advantages such as wide coverage of heterogeneous fusion, consistency of cloud edge experience, native compatibility of standard cloud, and global fluidity of computing power.

Typical edge cloud business application

In the early stage, CDN node architecture was mainly planned and deployed according to resources. Two LVS+ were less than four control machines, and the rest were all cache machines, which belonged to the deployment mode of planning first. There were a lot of idle resources and a waste of construction costs. The comprehensive promotion of CDN ON ENS edge fusion computing can greatly improve the efficiency of resource utilization.

Cloud on intelligent terminals is a very important scenario for large-scale access of IoT devices in the future, which involves the coordination of typical edge global container scheduling and traffic scheduling. The central control will apply for resources according to the estimated user size in advance, access the cluster, and deploy the container on the edge node. When the user requests to build the connection, the idle container on the edge will be obtained from the central control according to the predefined traffic scheduling strategy, and the user device will be bound to the server container. When the user disconnects, the new container is destroyed and rebuilt for the subsequent use of other businesses to avoid data leakage. The central control will dynamically expand the container capacity according to the concurrent requests and other core indicators in real time.

Center sinking business, the number of centers with large-scale regions is relatively limited, when the customer is very sensitive to delay, the first choice is to deploy the service at the nearest edge node and process customer requests. In order to ensure the consistent experience of cloud edge, the business central control system needs to obtain the service data of center and edge at the same time, and then distribute the traffic according to the user’s request. This can not only reduce the pressure on central bandwidth costs and resources, but also improve the user experience.

Finally, Jiang Cen said that Aliyun Edge Cloud native technology will continue to improve the scheduling, resources, collaboration and other capabilities, to provide the best cloud native application experience for industry customers and partners, and jointly create innovative edge cloud applications.

Copyright Notice:The content of this article is contributed by Aliyun real-name registered users, and the copyright belongs to the original author. Aliyun developer community does not own the copyright and does not bear the corresponding legal liability. For specific rules, please refer to User Service Agreement of Alibaba Cloud Developer Community and Guidance on Intellectual Property Protection of Alibaba Cloud Developer Community. If you find any suspected plagiarism in the community, fill in the infringement complaint form to report, once verified, the community will immediately delete the suspected infringing content.