Alibaba GRTN is designed for streaming media cloud native, convenient for customers to build their own streaming media cloud native applications, so that streaming media services are everywhere.
In the recent distributed cloud theme report meeting, Ali Cloud senior technical expert Lu Ri delivered a wonderful speech entitled “GRTN to create the Best Streaming media scene practice of Ali Cloud Edge Cloud”.
Luge shared his insight on distributed cloud, saying that Gartner has listed distributed cloud as one of the top 10 technology trends globally for two years in a row and predicted that more than 50% of enterprises will use distributed cloud by 2025, which represents the future of cloud computing.
Distributed cloud can be divided into local public cloud, metropolitan area cloud, 5G mobile edge cloud, IoT edge cloud, network edge cloud, etc., respectively serving different user scenarios. Distributed cloud has been in the innovation-driven period, and the future is full of challenges, opportunities and imagination.
The cloud-edge-end collaborative system proposed by AliYun, in which cloud + end forms a cloud, happens to coincide with the concept of distributed cloud.
More and more ecological applications rely on cloud-edge-end collaboration. Edge cloud plays a connecting role in the system: on the one hand, it integrates various edge nodes to build ubiquitous edge coverage; On the other hand, based on the self-developed distributed operating system, to achieve unified management, unified scheduling.
GRTN, alibaba’s next generation streaming media network, is a typical distributed streaming media practice built under the cloud-edge-end coordination system. Lu Ri summed it up in nine words: one cloud, one network and integration.
A cloud refers to ali Cloud GRTN is built on the infrastructure of central cloud native and edge cloud native, and organically integrates technologies. By referring to the design concept of SDN, IT separates CDS, puts control in the center, and subsides data surface distribution to more than 2800 nodes of Ali cloud edge cloud.
A network has the capability of scenarioalized QOS, real-time communication within 400 milliseconds and ultra-low delay. GRTN also has the capability of full-link RTC and dynamic networking. These capabilities are typical characteristics of the next generation streaming media transmission network.
Integration: GRTN provides an integrated solution, which not only supports video cloud, video distribution streaming features, but also has distributed computing and distributed storage processing capabilities. GRTN can provide more easy-to-use and professional services for enterprises to build streaming media applications. Ali Cloud has developed GRTN into the original aPaaS service of streaming media cloud, with more agile computing, more real-time connection, more diversified resources, finer control, more scientific evaluation and other features.
More agile computing
Typical streaming media link is divided into seven links: acquisition, encoding, sending, distributing, receiving, decoding and rendering.
In traditional architecture, in order to build the enterprise application of streaming media cloud, developers often, it is itself a streaming media handlers and software or system deployment to the cloud center, edge calculating virtual machine or container, it is not only a waste of resources, to a certain extent will pay extra resources for research and development costs to the virtual machine deployment and scheduling.
In fact, what developers really need is a media processing software landing environment, not bundled with the operating system, CPU, disk, network card general facilities.
Therefore, Ali Cloud advocates the streaming media cloud native platform to provide developers with Serverless service for recomputing. Developers can use their self-developed media processing programs, which Lu Called Serverless streaming media operator. The streaming media cloud native platform can deploy and schedule operators as required. Operators can be divided into pre-processing operators and post-processing operators, which perform pre-processing and post-processing for media streams.
More real-time connectivity
Among the seven links, the middle three links are related to transmission and networking. The core indicators of this sub-field mainly include scale, such as whether tens of millions of levels of concurrency are supported or not, and some core QoE indicators, such as first screen, delay, lag, etc.
Lu said that in the future, low latency is bound to become a standard capability in all industries. Therefore, the network mode of convection media will put forward higher requirements.
On the one hand, more node resources need to be expanded in the construction; on the other hand, the system needs to strengthen the adaptability of various heterogeneous resources. In addition to providing high-quality link resources, the system is stable and easy to maintain.
Aliyun advocates Hybrid networking for streaming media cloud native platform, which can cover all scenarios in the future and adapt protocols for various scenarios oriented to terminals.
Therefore, the rapid development and launch of streaming media protocols on streaming media cloud native platform have higher requirements. Media streaming is the basic unit of streaming media cloud native platform management. Aliyun provides a variety of networking modes that are compatible with rich streaming media protocols and pay attention to other indicators of the system while pursuing low latency. It is necessary to intelligently adapt to these different scenarios and business requirements and build a multi-dimensional streaming media orchestration system.
More diverse resources
In the field of cloud computing, multi-cloud mode has been widely accepted by many enterprises. Multi-cloud is a major trend, and multi-cloud has generated great value for customers.
When a supplier fails, it can quickly switch to another supplier to minimize service unavailability. Improving business stability is a typical multi-cloud value, so we can learn from multi-cloud ideas to improve the stability of cloud services. Aliyun streaming media cloud native platform can have more diversified resource hosting and scheduling capabilities.
As containerization technology matures, it can be used to layer services and isolate tenants to minimize the impact. Although new challenges are posed to software management and o&M deployment, the improvement of service stability is obvious.
The efficiency of business innovation and product iteration can be controlled flexibly depending on the situation of customers. At the same time, it can also improve the flexibility of the system, which has good business value.
Finer controls
In fact, traditional streaming media services have many limitations in terms of openness, autonomy and convenience. As a result, streaming media cloud manufacturers are pipelined and have low innovation ability. The link is long and costly.
Streaming media cloud native platform can provide finer control over the platform interior, including programmability, observability, scalability, and low code characteristics.
Internal need to build a variety of controllers, and can be divided into two categories, one is heavy computing controller, one is light computing controller. A typical light computing controller allows third party customers to programmatically extend their own QOS algorithms. Distributed Serverless video operator distribution platform can be classified as heavy computing controller, third party can also implant other operators.
In addition to service isolation, the security container technology needs to be further adopted to further reduce security risks caused by controller opening. The open and independent strategy can stimulate the innovation of streaming media, and operator shopping mall can be built in the future to spread valuable operators and algorithms in the industry.
More scientific evaluation
Quality optimization is one of the important work of streaming media providers. There are some common pain points in the process of quality optimization, such as excessive reliance on the experience of tuning engineers, which is difficult to precipitation and high cost of trial and error.
Ali Cloud streaming media cloud native platform can use the concept of A/B testing to build A more scientific, closed-loop testing system to achieve the purpose of continuous optimization and iteration of QOE. Programmable design can effectively reduce costs, drive and evaluate the tuning effect through data, and quickly approach the ceiling. In addition, the data platform also needs sand table simulation capability, which can make a priori prediction of tuning and reduce regression on the line.
GRTN short delay live RTS typical case
After the collaborative research and development of multiple ali teams and the polishing of various business scenarios, GRTN has been launched in many Apps and websites of Ali Group, including Taobao, Dingding, Youku, Lazada and so on.
It is worth mentioning that, compared with the traditional user experience of live broadcast, the delay of live broadcast on Taobao e-commerce in 2020 has been reduced by more than 80% and the fluency has been improved by more than 30%. This year’s Double 11 will further reduce the delay and improve the fluency and clarity.
In terms of external commercialization, GRTN provides thousands of domain names to help customers provide live audio-visual experience. For example, after a short video platform launched GRTN RTS live broadcast, the delay of live broadcast was reduced by more than 70%, and the video rendering lag was reduced by more than 40%.
Finally, Lu said that he hoped to take advantage of the great situation of distributed cloud computing to promote streaming media cloud services to be more inclusive, and to better empower traditional industries while continuing to serve the Internet industry, so as to find a balance between generality and convenience.
Alibaba GRTN is not only based on cloud native, but also designed for streaming media cloud native. It is committed to providing streaming media cloud native services, so that our customers can build their own streaming media cloud native applications and make streaming media services ubiquitous. Ali Cloud will work with colleagues to create the original ecology of Streaming media cloud of Pratt & Whitney, providing users with more real-time, smoother and clearer audio-visual experience.
“Video cloud technology” your most noteworthy audio and video technology public account, weekly push from Ali Cloud front-line practice technology articles, here with the audio and video field first-class engineers exchange exchange. You can join ali Cloud video cloud product technology exchange group, and the industry together to discuss audio and video technology, get more industry latest information.