On February 28, Kyligence announced the new launch of the localized cloud-native data base open source project Xuanwu (XUANWU) to help enterprises accelerate data platform migration to the cloud and achieve localization upgrades. Xuanwu (XUANWU) is a new generation of cloud-native big data base formed on the basis of containerization technology , aiming to provide a set of overall and standardized solutions to enable enterprises to quickly and efficiently apply data Data governance services to build and manage highly reliable, high-performance, scalable and secure data infrastructure in a cloud-native environment. At the same time, the project officially established an open source community and will operate based on the rules of the international open source community.
Kyligence was established by the core team of Apache Kylin, the first top Apache open source project from China. It is a leading provider of big data analysis and indicator platforms. It has independent and controllable core technologies and intellectual property rights, and has successfully assisted many Enterprises such as state-owned banks, insurance companies, and manufacturing companies have realized the upgrading of data platforms to the cloud and localization. Based on Kyligence's rich practice and accumulation in the field of data and cloud-native technology, Xuanwu (XUANWU) simplifies the complexity of the cloud-native data stack architecture. The project uses Spark as a unified computing engine and Hucang as a unified storage core, which is fully compatible with localized software and hardware systems. Compared with native Spark, its performance can be improved several times, and IT costs can be saved by nearly 40%.
Xuanwu (XUANWU) includes three modules : low-code development platform Byzer , vectorized execution engine Gluten , and resource and service management console XUANWU Manager . It has the following capabilities and advantages:
Functional Architecture Diagram of Kyligence Cloud Native Data Base Xuanwu (XUANWU)
-
Quick installation , complete the installation on Kubernetes with one line of command, and experience cloud-native data capabilities in 30 minutes
-
Run the TPC-H benchmark test with one click , and the cloud-native SparkSQL is about 20% faster than Hadoop
-
Experience elastic scaling with one click , quickly respond to business changes, and accurately respond to tidal peaks and valleys
-
Experience AI machine learning on a low-code platform to meet the full-link requirements from data preparation, model training, to model release
At present, the project has been put into use in many financial enterprise scenarios. Taking a financial institution as an example, the IT department of its data platform hopes to improve the resource utilization rate of the data warehouse platform, shorten the data processing time and query time, so as to deal with traffic peaks and valleys more easily, and achieve compatibility with localized software and hardware. There is no advantage in combining Hadoop HDFS, MapReduce, and YARN with container technology and object storage. After preliminary evaluation of financial production scenarios, the cloud-native architecture Xuanwu (XUANWU) has shown obvious effects and values:
-
The overall utilization rate of IT resources is increased by 20-50% , mainly benefiting from the underlying unified computing and storage, and resources can be flexibly allocated in a wider range of enterprises
-
The overall computing performance is improved by about 20% , mainly benefiting from the storage-computing separation architecture. Computing tasks are distributed more flexibly to more computing nodes and completed at high speed.
-
The cost of system operation and maintenance is greatly reduced , mainly benefiting from the advantages of the almost unlimited expansion capability and the unified base of multi-system integration
-
Localization, independent and controllable technology realization
Li Yang, co-founder and CTO of Kyligence, said: "More and more users are willing to accept upgrading the more traditional Hadoop data stack to a technology stack based on cloud-native technology. Kyligence will Continue to make positive contributions to the development of the industry and the localization of basic software by making use of our accumulated technical advantages in the field of big data!"
Kyligence cloud-native data base Xuanwu (XUANWU) has been officially released today, welcome to visit https://github.com/kyligence-xuanwu/document to experience it!
About Kyligence
Founded in 2016 by the founding team of Apache Kylin, Kyligence is a leading provider of big data analysis and indicator platforms, providing enterprise-level OLAP (multidimensional analysis) platform products Kyligence Enterprise and one-stop indicator platform Kyligence Zen, for Users provide enterprise-level business analysis capabilities, decision support systems and various data-driven industry solutions.
Kyligence has served many customers in banking, securities, insurance, manufacturing, retail, medical and other industries in China, the United States, Europe and Asia Pacific, including China Construction Bank, China Merchants Bank, Ping An Bank, Shanghai Pudong Development Bank, Bank of Beijing, Bank of Ningbo, Pacific Insurance, China UnionPay, SAIC, Changan Automobile, Yum China, Starbucks, Anta, Li Ning, AstraZeneca, UBS, MetLife and other world-renowned companies, and reached global partnerships with Microsoft, Amazon Cloud Technology, Huawei, Ernst & Young, Deloitte, etc. Kyligence has received multiple investments from institutions such as Redpoint, Broadband Capital, Shunwei Capital, Eight Roads Capital, Coatue, SPDB International, CICC Capital, Gopher Assets, and Guofang Capital.