Replication Target Host Mapping for Triggered Replica Promotion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage systems face inefficiencies in managing data replication and storage operations, particularly in flash storage systems, where lower-level processes often perform redundant tasks, leading to increased latency and reduced reliability.
Innovation Solution
Implementing a direct-mapped flash storage system where higher-level processes initiate and control operations directly on flash drives without address translation by lower-level controllers, utilizing non-volatile RAM for data buffering and proactive data management across multiple storage nodes to enhance reliability and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional storage controllers perform address translation and data operations, then data access is simplified for hosts, but redundant write operations occur and system efficiency decreases
Solution Approach 1:
The patent extracts the address translation function from traditional storage controllers and places it directly in the host system. This allows the host to manage flash drive addresses directly, eliminating the redundant address translation operations performed by controllers and thereby improving storage system efficiency while maintaining simplified data access through host-level control.
Solution Approach 2:
The patent introduces a host-based address translation layer as an intermediary between the host file system and flash drives. This intermediary performs address translation at the host level rather than through storage controllers, reducing redundant write operations and improving overall system productivity while preserving ease of operation.
2Reliability
If storage systems perform frequent write operations to maintain data redundancy, then data reliability improves, but unnecessary write operations increase and wear on flash memory accelerates
Solution Approach 1:
The patent implements preliminary actions by having the host system proactively manage data placement and redundancy across flash drives before write operations occur. The host performs address translation and data distribution in advance, allowing the system to maintain data reliability through careful planning while minimizing unnecessary write operations that would accelerate flash memory wear.
Solution Approach 2:
The patent enables flash drives to serve themselves through host-managed address translation and data placement. The host system directly manages data operations on flash drives without requiring intermediary controllers, allowing the system to maintain data integrity through self-service mechanisms while reducing redundant writes and extending flash memory lifespan.
3Quantity of substance
If distributed file systems manage data across multiple storage devices, then storage capacity and reliability improve, but coordination overhead and system complexity increase
Solution Approach 1:
The patent merges the address translation and data management functions into the host system, combining previously separate controller and host responsibilities. This consolidation allows the host to directly manage distributed data across multiple flash drives, improving storage capacity utilization while reducing system coordination overhead by eliminating intermediary controller layers.
4Ease of operation
If storage controllers mediate all data operations between hosts and flash drives, then data access is simplified, but controller bottleneck and latency increase
Solution Approach 1:
The patent extracts the address translation and data management functions from storage controllers and places them directly in the host system. This eliminates the controller bottleneck by allowing hosts to directly manage data operations on flash drives, significantly reducing data access latency while maintaining simplified access through host-level control.
Data Source
AI summary
A method of managing host mappings for replication endpoints, the method including: identifying a target storage system replicating a source dataset of a source storage system, wherein a first host is mapped to the source dataset on the source storage system; providing, to the target storage system and in dependence upon a mapping of the first host to the source dataset, configuration information for connecting to a second host; and implementing, in response to a triggering event, a mapping of the second host to a replica dataset on the target storage system.