Storage System Extent Change Acknowledgement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Operations such as data copying and deletion in storage systems, especially involving large extents, can be time-consuming and cause significant latency due to the need to block access to affected address ranges during these processes.
Innovation Solution
A method is introduced where a storage system generates extent change operation information including an event counter and type of operation, allowing for immediate acknowledgement of operation completion even before the operation is finished, and provides expected content during ongoing extent change operations to manage read requests without waiting for operation completion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If access to affected address ranges is blocked during extent change operations, then data consistency is maintained, but read request latency increases significantly
Solution Approach 1:
The system performs preliminary actions by creating snapshots of the affected address ranges before extent change operations begin. These snapshots capture the data state at the time of the operation start, allowing read requests to be served from the snapshot rather than waiting for the operation to complete. This preliminary capture of data state enables concurrent reads without blocking, maintaining consistency while reducing latency.
Solution Approach 2:
The patent introduces snapshots as an intermediary mechanism between read requests and the storage medium during extent change operations. Instead of directly accessing the storage medium which is being modified, read requests are redirected to snapshot copies that represent the data state before modification. This intermediary layer allows reads and writes to proceed concurrently without interference, solving the contradiction between consistency and latency.
2Productivity
If extent change operations are completed before acknowledgment, then system throughput improves, but risk of inconsistent read data increases
Solution Approach 1:
The system implements feedback mechanisms where read requests check whether an extent change operation is currently in progress by examining operation logs or status flags. If an operation is detected, the system feedbacks control to redirect the read request to use the appropriate snapshot. This feedback loop ensures that reads automatically adapt to ongoing operations, maintaining consistency while allowing operations to complete asynchronously and improve throughput.
Solution Approach 2:
The system performs preliminary recording of extent change operations in operation logs before the actual data modification completes. This preliminary recording allows the system to track ongoing operations and make informed decisions about read request handling. By having this advance information about operations in progress, the system can serve reads from appropriate snapshots without waiting for operations to complete, thus improving throughput while maintaining consistency.
Data Source
AI summary
A method for responding to an extent change operation, the method may include receiving, by a storage system and from a requesting entity, a request to perform an extent content change operation that involves changing a content of a certain extent within a logical space supported by a storage system; generating, in response to the request, extent change operation information that comprises (a) an event counter indicative of a time of requested occurrence of the extent change operation, (ii) a type of extent change operation indicator, and (ii) logical addresses associated with the extent change operation; and sending to the requesting entity an acknowledgement indicative of a completion of the extent change operation before a completion of the extent change operation if an expected content of the certain extent is known before completion of the extent change operation.