检测到您已登录华为云国际站账号，为了您更好的体验，建议您访问国际站服务网站 https://www.huaweicloud.com/intl/zh-cn
不再显示此消息
检测到您已登录华为云国际站账号，为了您更好的体验，建议您访问国际站服务网站 https://www.huaweicloud.com/intl/zh-cn
不再显示此消息
Suggestions on Instance Selection Overview Before purchasing a GaussDB instance, consider key factors such as cost, performance, workload capacity, and your intended use case.
High cost-effectiveness: CSS uses the Kunpeng computing power, separates cold and hot storage, and decouples computing and storage resources, achieving high performance and reducing costs by over 30%. Ease of use: Perform queries in a GUI editor.
Huawei cloud phones are virtual phones running on Kunpeng Bare Metal Servers (BMSs). They run native Android. Simply speaking, cloud phone server = cloud server + Android OS. You can remotely control a cloud phone in real time to run Android apps on the cloud.
Parent Topic: QingTian Enclave Overview
Table 1 Supported DB engines and versions Compatibility CPU Type DB Instance Type Storage Engine 5.0 x86 Kunpeng Cluster Replica set RocksDB 4.4 x86 Kunpeng Cluster Replica set RocksDB 4.2 x86 Kunpeng Cluster Replica set RocksDB 4.0 x86 Kunpeng Cluster Replica set WiredTiger 3.4 x86
It uses a professional embedded processor, small local flash memory, and simplified OS for desktop access. The TC sends the inputs of the mouse and keyboard to the background server for processing.
For details about how to log in to an ECS, see Login Overview (Linux) and Login Overview (Windows). Video Why ECS Rich specifications: A variety of ECS types with custom specifications are available for different scenarios.
MRS optimizes software and hardware based on Kunpeng processors to fully release hardware computing power and achieve cost-effectiveness.
Processors Conditions Parallel Processor Delay EDI Processor Variable Assignment Variable Updater Sorter Data Conversion Splitter Filter Script Message Logger Data Mapper Iterator Error Monitoring End Symmetric Encrypt/Decrypt Asymmetric Encrypt/Decrypt XML Verification
Volcano Scheduling Volcano Scheduling Overview Scheduling Workloads Resource Usage-based Scheduling Priority-based Scheduling AI Performance-based Scheduling Queue Scheduling NUMA Affinity Scheduling Pod Compaction Parent Topic: Scheduling
For more information about how to log in to a Windows ECS, see Login Overview (Windows). For more information about how to log in to a Linux ECS, see Login Overview (Linux).
Ultra-high Performance Computing ECSs Overview Ultra-high performance computing ECSs are designed to meet high-end computational needs, such as industrial simulation, molecular modeling, and computational fluid dynamics.
The following functions are provided: A processor node can collect data from one data source to multiple destinations. Tasks can be configured simply by dragging and dropping nodes. Data conversion modes include the mapping and script modes.
BMSs have x86 or Kunpeng CPUs. Huawei-developed high-performance physical servers with exclusive optimization algorithms provide a reliable hardware environment for the BMSs. You can choose from different BMS flavors based on your service requirements.
Function Overview ECS Features ECS provides secure, scalable, on-demand compute resources with flexible billing modes and easy O&M, greatly reducing your costs. Buy Console Documentation Kunpeng ECSs Kunpeng ECSs are powered by Kunpeng processors.
Large-Memory ECSs Overview Large-memory ECSs provide an even larger amount of memory than memory-optimized ECSs.
Table 2 Synchronous replication constraints Constraint Description Compute Constraints on server types: Kunpeng ECSs are not supported. x86-based, GPU-accelerated and FPGA-accelerated ECSs are not supported.
For details, see A Summary List of x86 ECS Specifications and A Summary List of Kunpeng ECS Specifications. For more constraints on using networks, see Notes and Constraints.
General Computing DeHs Overview General-computing DeHs can accommodate ECSs with regular workloads and short-term workload surges. They use a CPU-unbound scheduling scheme. vCPUs are randomly allocated to idle CPU hyper threads based on the system loads.
To prevent services from being affected by inconsistent processor names in the OS, the processors are named General Purpose Processor.
