iSCSI Block Cache for WAN Edge Storage Latency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional wide area file systems do not provide solutions for consolidating block level access to a centralized block storage data center, leading to issues such as high access latency and lack of offline access capabilities.
Innovation Solution
Implementing a block cache mechanism at local area networks to cache block data using block level protocols, allowing for efficient block level access operations over a wide area network, with caching models like Partial Local Caching and Full Local Caching to manage data access and storage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If block level access operations are performed over WAN to centralized block storage data center, then storage consolidation is achieved, but access latency increases
Solution Approach 1:
The patent implements a block cache mechanism at the WAN edge that pre-caches frequently accessed block data from the centralized block storage data center before actual access requests occur. This preliminary action stores data blocks in the block cache based on access patterns, so when access requests arrive, the data is already locally available, eliminating the WAN traversal delay and reducing access latency while maintaining storage consolidation benefits
Solution Approach 2:
The patent introduces a block cache mechanism as an intermediary component between the host and the centralized block storage data center. This intermediary caches block data locally at the WAN edge, allowing access requests to be satisfied from the local cache without traversing the WAN, thus reducing access latency while the cache itself communicates with the centralized storage to maintain data consistency
2Loss of time
If block data is cached at WAN edge, then access latency is reduced, but device complexity increases
Solution Approach 1:
The patent implements a block cache mechanism that can operate in multiple caching models (read-ahead caching, write-behind caching, and full local caching) within the same system framework. This multi-functional design allows the system to adapt to different workloads and requirements without requiring separate systems, managing complexity through a unified multi-purpose caching architecture that handles various access patterns and storage scenarios
3Reliability
If dirty data is tracked and written back to remote volume, then data consistency is maintained, but network bandwidth consumption increases
Solution Approach 1:
The patent implements a write-behind caching mechanism where dirty data in the block cache is periodically flushed back to the remote volume in batches rather than immediately upon each write operation. This periodic action accumulates multiple dirty blocks and transmits them together, reducing the frequency of network transactions and overall bandwidth consumption while maintaining data consistency through proper tracking and eventual synchronization of all dirty data to the remote volume
Data Source
AI summary
A technique is described for facilitating block level access operations to be performed at a remote volume via a wide area network (WAN). The block level access operations may be initiated by at least one host which is a member of a local area network (LAN). The LAN includes a block cache mechanism configured or designed to cache block data in accordance with a block level protocol. A block level access request is received from a host on the LAN. In response to the block level access request, a portion of block data may be cached in the block cache mechanism using a block level protocol. In at least one implementation, portions of block data in the block cache mechanism may be identified as “dirty” data which has not yet been stored in the remote volume. Block level write operations may be performed over the WAN to cause the identified dirty data in the block cache mechanism to be stored at the remote volume.