Cloud Storage Write Request Batching and Drive Power Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud storage systems face high power consumption and latency due to frequent powering on and off of drives in response to individual write requests, which increases resource usage and delays data writing.
Innovation Solution
Implementing a system that stores pending write requests in a cache until a threshold of requests is reached or a drive is powered on, allowing for simultaneous writing of cached data to drives, thereby reducing the number of active drives and write time, and using prefetching for frequently accessed data to minimize latency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If drives are powered on and off for individual write requests, then data writing can be performed immediately, but power consumption and resource usage increase significantly
Solution Approach 1:
The patent merges multiple individual write requests into a single batch operation. Instead of processing each write request separately by powering on drives individually, the system accumulates multiple write requests and processes them together in a batch, thereby reducing the number of times drives need to be powered on and reducing overall power consumption.
Solution Approach 2:
The system performs preliminary actions by buffering and accumulating write requests before processing them. Rather than immediately processing each write request, the system holds requests in a buffer and processes them in batches after accumulation, allowing drives to remain powered off longer and reducing energy consumption.
2Use of energy by moving object
If drives are powered off during inactivity, then power consumption is reduced, but latency increases when write requests arrive
Solution Approach 1:
The system performs preliminary buffering of write requests in memory before processing them to drives. When write requests arrive, they are accumulated in a buffer structure rather than being immediately processed, allowing the system to batch multiple requests together and process them in a single drive operation, thereby reducing latency while keeping drives powered off during inactivity.
Solution Approach 2:
The patent introduces a buffer as an intermediary component between the write request interface and the drives. This buffer acts as a mediator that accumulates write requests and manages their batch processing, decoupling the arrival of write requests from the actual drive operations and enabling reduced latency through batching while maintaining drive power savings.
3Productivity
If multiple individual write requests are processed separately, then each request is handled immediately, but the number of active drives increases and resource usage increases
Solution Approach 1:
The patent combines multiple individual write requests into a single batch processing operation. Instead of processing each write request separately which would require multiple active drives, the system accumulates requests and processes them together in one operation, thereby reducing the number of drives that need to be active at any given time while maintaining productivity.
Solution Approach 2:
The system uses partial action by processing only the necessary batch of accumulated write requests together rather than processing every single request individually. This batching approach processes a subset of requests in each drive operation, reducing the total number of active drives needed while still making progress on all pending write requests.
Data Source
AI summary
Systems and methods are provided for managing write requests for drives in a cloud storage system. For example, a system can receive a plurality of write requests for writing a first set of data to a first drive of a plurality of drives. The first drive may be powered off. The system can write the first set of data to a cache in response to receiving the plurality of write requests. The system can determine that a number of the plurality of write requests exceeds a predetermined write request threshold. The system can power on the first drive in response to determining that the number of the plurality of write requests exceeds the predetermined write request threshold. The system can write the first set of data stored in the cache to the first drive.