Token State Management Across Storage Processors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional offloaded data transfer technologies face inefficiencies in managing token states across multiple storage processors, leading to premature cancellation of write using token operations, especially when these operations take longer than the predefined expiration time, resulting in incomplete data transfers despite intact source data.
Innovation Solution
Implementing a method to manage token states across multiple storage processors by monitoring token states across all processors, only expiring tokens if they are idle on all processors, thereby preventing premature cancellation of write using token operations and allowing them to complete even if they exceed the predefined time period.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If a storage processor expires tokens that are idle for more than a predefined time period to reclaim token resources, then token resource management is improved, but write using token operations in progress may be prematurely canceled
Solution Approach 1:
The patent segments token state management by creating separate token state sets for each storage processor (first SP-controlled set and second SP-controlled set). Each SP tracks token states independently, allowing the first SP to manage token expiration based on its own observations without being affected by the second SP's token state, thus preventing premature cancellation of operations
Solution Approach 2:
The patent implements preliminary action by having storage processors proactively set token states to 'busy' before write using token operations begin and maintain these states throughout the operation duration. This preliminary marking prevents other processors from expiring the token during the operation, ensuring operation completion while still allowing resource reclamation after operations finish
2Ease of operation
If a storage processor monitors token idle time from its own perspective to determine expiration, then token expiration decision-making is simplified, but operations in progress on other processors may be incorrectly canceled
Solution Approach 1:
The patent divides token state information into separate sets controlled by different storage processors. Each processor maintains its own view of token states (first SP-controlled set and second SP-controlled set), allowing independent monitoring without interference. This segmentation enables each processor to make expiration decisions based on local observations while preserving operations on other processors
Solution Approach 2:
Each storage processor applies local quality by maintaining token state information specific to its own perspective and operations. The first SP monitors token states from its local viewpoint without being constrained by the second SP's observations, enabling localized expiration decisions that are accurate for that processor while preserving operations elsewhere in the system
Data Source
AI summary
A technique manages token states across multiple storage processors (SPs) of a data storage array. The technique involves using a token, by a first SP, to identify particular data stored on the array. The technique further involves updating, by the first SP, a first SP-controlled set of token state information for the token, the first SP-controlled set of token state information including (i) a first token state which indicates whether the token is “idle” or “busy” from a perspective of the first SP and (ii) a second token state which indicates whether the token is “idle” or “busy” from a perspective of a second SP. The technique further involves expiring, by the first SP, the token in response to the first SP-controlled set of token state information indicating that the token has remained “idle” for at least a predefined amount of time.