Cloud OS, The Perfect Foundation for Enterprise Cloud Computing
An effective cloud computing system is expected to be powerful, reliable, flexible, and simple to use. The key to building such a system lies in a cloud operating system (OS). Huawei GalaxEngine is a good choice for customers. Huawei GalaxEngine provides powerful virtualization and resource pool management functions, cloud service components and tools, and open application programming interfaces (APIs). Huawei GalaxEngine supports legacy and new enterprise services, improves operating efficiency, and reduces IT costs.
An effective cloud computing system is expected to be powerful, reliable, flexible, and simple to use. The key to building such a system lies in a cloud operating system (OS). Huawei GalaxEngine is a good choice for customers. Huawei GalaxEngine provides powerful virtualization and resource pool management functions, cloud service components and tools, and open application programming interfaces (APIs). Huawei GalaxEngine supports legacy and new enterprise services, improves operating efficiency, and reduces IT costs.
Huawei GalaxEngine Architecture and Its Position in the Cloud System
Huawei GalaxEngine consists of a virtualization infrastructure, a cloud services and cloud management
- Virtualization infrastructure:
The virtualization infrastructure layer virtualizes computing, storage, and network resources and provides virtual resource pools for upper-layer applications. This layer provides virtual computing, virtual storage, virtual network, virtual resource scheduling, and virtual resource management.
- Cloud services:
The cloud service layer is composed of a range of cloud service modules. The cloud service layer schedules and manages lower-layer computing, storage, and network resources through the interfaces provided by the virtualization infrastructure. It also provides cloud services for upper-layer applications through open APIs and interfaces .Services provided by the cloud service layer include (1) basic services such as cloud computing , virtual private cloud , and backup/disaster recovery , and (2) advanced cloud services, such as MapReduce , complex event processing and database capabilities.
Flexible:
- Improves resource utilization by allocating resources on demand and dynamically scheduling resources.
- Supports large-scale deployment and operation.
- The current version supports a maximum of 20 clusters.
- Each cluster supports up to 128 physical servers.
- Huawei GalaxEngine supports more than 10,000 virtual machines (VMs).
- Provides multiple and flexible choices for customers.
- (Optional) Supports multi-tenancy and charging modules to facilitate cloud computing operation.
Secure:
- Uses a unified application management platform to ensure application security.
- Implements centralized data control and rights- and domain-based data management to ensure data security.
- Uses virtualized firewalls to ensure virtualization security.
- Uses a tailored and enhanced Hypervisor to provide optimal performance and high availability (HA).
Efficient:
- Supports quick deployment and improves O&M efficiency to reduce O&M costs.
- Improves IT resource utilization.
- The average utilization improves from less than 10% to more than 70%.
- Improves IT O&M efficiency by 2–10 times because of the usability design of Huawei GalaxEngine.
- Reduces IT operating costs by 30%–70% by highly integrating IT resources.
- Provides centralized management and analysis for massive data, supporting new growth opportunities for enterprises.
- Integration with Huawei hardware to provide optimal performance.
- Provides customized cloud solutions for customers.
Open:
- Provides open APIs.
- Can be integrated with other vendors’ servers, storage and network devices, OSs, and upper-layer application software.
- Supports VMs from multiple vendors.
- Complies with industry standards and de facto standards.
Core Functions:
Feature | Function |
---|---|
Hypervisor | |
Bare metal architecture | |
Support for high-performance physical servers | |
Large-capacity VMs | |
Rapid fault location | |
Computing Servers | |
VM life cycle management | |
Flexible VM creation | |
VM resource adjustment | |
VM login security management | |
CPU QoS | |
Memory QoS | |
VM multiple service groups | |
VM snapshots | |
Support for the Microsoft® Cluster Service | |
Storage services | |
IP SAN-based storage virtualization | |
IP SAN-based auto small-scale configuration | |
FC SAN-based storage virtualization | |
Network services | |
Security group | |
Virtual NIC | |
Elastic IP address | |
Scalability | |
Flexible volume expansion | |
A large number of VMs running on a physical server | |
Attachable large-capacity data volume | |
Support for multiple image types | |
Security | |
Access authentication | |
Transmission encryption | |
Management security | |
Web security | |
OS hardening | |
Compatibility | |
Storage compatibility | |
Server compatibility | |
Guest OS compatibility | |
HA | |
VM fault-based migration | |
VM live migration | |
VM OS fault detection | |
Serviceability | |
Automatic discovery of physical servers | |
Automatic installation of virtualization software | |
Small-scale configuration | |
Capacity expansion and reduction | |
Patch process management | |
Silent upgrade | |
Resource management | |
Resource management | |
Resource scheduling | |
Openness | |
ESC interface | |
Service provisioning interface | |
OM northbound interface | |
Operation and maintenance | |
Authority management | |
VDC management | |
Configuration management | |
Topology management | |
Log management | |
Alarm management | |
System monitoring | |
Server management | |
License management | |
Clock synchronization | |
Internationalization | |
Task center |
Core Capacities:
Category | Specifications |
---|---|
Capacity | |
Maximum number of computing nodes supported by a single cluster: 128 | |
Maximum number of VMs supported by a single cluster: 5120 | |
Maximum number of VMs supported by a single computing node (X6000): 60 | |
Maximum number of volumes (including system volumes) attached to a VM: 11 | |
System volume capacity: 5 GB–100 GB | |
User volume capacity: 1 GB–2 TB | |
VM memory capacity: 512 MB–1TB | |
Number of virtual CPUs (vCPUs): 1–32 | |
Disaster recovery | |
Periodical data backup for management nodes | |
Node redundancy protection | |
Redundant protection architecture for management nodes | |
Emergence recovery | |
Backup and restoration solutions for configuration data of management nodes | |
Software fault Detection and troubleshooting | |
Automatic recovery after fault Detection | |
Fault records and diagnosis during normal system operation | |
Hardware fault Detection and troubleshooting | |
Memory/NIC/Hard disk fault Detection and troubleshooting | |
Network Detection and recovery | |
Storage multipathing | |
Storage link disconnection protection |