Chrome Extension
WeChat Mini Program
Use on ChatGLM

Fast Reconstruction for Large Disk Enclosures Based on RAID2.0

International Conference on Parallel Processing (ICPP)(2021)CCF B

Univ Sci & Technol China | USTC

Cited 1|Views27
Abstract
In the era of explosive data growth, RAID2.0 architecture with dozens or even hundreds of disks is commonly used to provide large capacity data storage. Due to limited resources, such as memory and CPU, the reconstruction for disk failures in RAID2.0 is executed in batches. Traditional random data placement and recovery scheme make the I/O access highly skewed within a batch, which slows down the reconstruction speed. We propose DR-RAID, an efficient reconstruction scheme that balances local rebuilding workloads across all surviving disks within a batch. Instead of executing tasks sequentially from all pending recovery tasks, we dynamically select a batch of tasks with an almost balanced read load. Furthermore, we transform the problem of distributing the reconstructed data to surviving disks into a bipartite graph model, and achieve uniform write load distribution by finding a maximum matching in the graph. DR-RAID can be applied in a large disk pool with homogeneous or heterogeneous rebuilding bandwidth. We implemented DR-RAID into a pool of 50 disks and conducted extensive experiments. DR-RAID increases the rebuilding throughput by up to 61.90% compared with the random data placement scheme in offline rebuilding, and up to 59.28% with varied rebuilding bandwidth. DR-RAID accelerates rebuilding by effectively eliminating the local load imbalance within a batch, and greatly shortens the period of interference to user requests.
More
Translated text
Key words
RAID,RAID2.0,Disk Failure,Reconstruction
PDF
Bibtex
AI Read Science
AI Summary
AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.
Example
Background
Key content
Introduction
Methods
Results
Related work
Fund
Key content
  • Pretraining has recently greatly promoted the development of natural language processing (NLP)
  • We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
  • We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
  • The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
  • Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance
Try using models to generate summary,it takes about 60s
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Related Papers
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper
GPU is busy, summary generation fails
Rerequest