Non-Local Block Data Access Through Replicated Storage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The management of large-scale computing resources in complex computer networks, including data centers, is complicated by the need for efficient and secure provisioning and administration of physical and virtual computing resources, particularly in environments with diverse user needs and geographical distribution.
Innovation Solution
A block data storage service that utilizes multiple server storage systems to store block data reliably across networks, ensuring availability and reliability through mirroring and replication of data across geographically distributed data centers, with management by a Block Data Storage System Manager and Node Manager modules, and optional use of remote archival storage for long-term backups.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple server storage systems are used to store block data across geographically distributed data centers, then reliability and availability of data access is improved, but device complexity and management difficulty increase
Solution Approach 1:
The system segments storage management into separate components: a block data storage service that handles data placement across multiple server storage systems, and a virtual machine manager that handles VM-level operations. This segmentation allows each component to specialize in specific tasks, reducing overall system complexity while maintaining high reliability through distributed storage across geographically separated data centers.
Solution Approach 2:
The block data storage service acts as an intermediary between the virtual machine manager and the physical server storage systems. It provides a simplified interface for data access while managing the complexity of distributed storage operations, including data placement, replication, and availability across multiple geographically distributed data centers.
2Reliability
If block data is mirrored and replicated across geographically distributed data centers, then data consistency and availability during failures are improved, but loss of time for data synchronization increases
Solution Approach 1:
The system performs preliminary actions by pre-configuring multiple server storage systems in geographically distributed data centers before failures occur. The block data storage service maintains replicated copies of block data across these pre-positioned systems, enabling rapid failover and minimizing data loss time when failures happen.
Solution Approach 2:
Different data replication strategies are applied based on local requirements. The block data storage service determines which data blocks require replication and to which specific storage systems, optimizing synchronization time and data consistency for each local environment while maintaining overall system efficiency.
3Ease of operation
If a block data storage service manages access to non-local block data storage, then ease of operation for virtual machines is improved, but device complexity for managing storage resources increases
Solution Approach 1:
The block data storage service provides universal functionality by serving multiple virtual machines with diverse storage needs through a single unified interface. It handles various storage operations (read, write, access control) for block data across different server storage systems, simplifying operations for virtual machines while consolidating management complexity into a single service layer.
Data Source
AI summary
Techniques are described for managing access of executing programs to non-local block data storage. In some situations, a block data storage service uses multiple server storage systems to reliably store copies of network-accessible block data storage volumes that may be used by programs executing on other physical computing systems, and snapshot copies of some volumes may also be stored (e.g., on remote archival storage systems). A group of multiple server block data storage systems that store block data volumes may in some situations be co-located at a data center, and programs that use volumes stored there may execute on other computing systems at that data center, while the archival storage systems may be located outside the data center. The snapshot copies of volumes may be used in various ways, including to allow users to obtain their own copies of other users' volumes (e.g., for a fee).