Stripe Reassembly in Distributed Storage Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In distributed storage systems, the process of reassembling stripes often requires significant cross-node migration of valid data, which can be inefficient and impact system performance.
Innovation Solution
A method where a stripe server selects stripes with a maximum of one data chunk containing valid data on the same storage node, generates parity data for a new stripe, and stores it on a parity node, allowing valid data to remain on the same node without migration, while also identifying and managing garbage data for efficient resource reuse.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional stripe reassembling is performed by migrating valid data across storage nodes, then stripe reassembly can be completed, but system performance deteriorates due to cross-node data migration overhead
Solution Approach 1:
The patent extracts the valid data chunks from the reassembly process and keeps them in place on the same storage node, eliminating the need to migrate them across nodes. Only the necessary parity chunks are generated and stored, while valid data chunks are excluded from migration operations, thus resolving the contradiction between completing reassembly and maintaining performance
Solution Approach 2:
The patent segments the stripe reassembly process into two distinct parts: (1) identifying and retaining valid data chunks on their current storage nodes without migration, and (2) generating new parity chunks and storing them on appropriate nodes. This segmentation allows the system to complete reassembly while avoiding the performance penalty of migrating valid data across nodes
2Productivity
If valid data is migrated across storage nodes during stripe reassembly, then stripe reassembly can be completed, but data migration overhead increases
Solution Approach 1:
The patent extracts valid data chunks from the migration process entirely, keeping them on their original storage nodes. The reassembly operation only involves generating new parity chunks and storing them on target nodes, eliminating the energy-consuming cross-node migration of valid data while still achieving stripe reassembly completion
Data Source
AI summary
A stripe reassembling technique includes a stripe server that selects stripes; uses data chunks including valid data in the stripes S1, S2, and S3 as data chunks in a new stripe S4, and generates data of a parity chunk for data of the data chunks in S4 according to an erasure coding (EC) algorithm the same as that of S1, S2, and S3 ; and stores the parity data of the parity chunk on a parity storage node.