Backup Server Selection via Data Commonality Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional backup systems do not optimize data placement based on content, leading to suboptimal storage efficiency despite performing deduplication, as they do not consider the commonality of data when directing host data to backup servers.
Innovation Solution
The improved technique involves computing hash values for data blocks, comparing these values between host and server data representations to calculate commonality scores, and selecting a backup server based on these scores for optimal deduplication and storage efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If backup servers perform deduplication on backup data, then storage efficiency is improved, but backup efficiency is still less than optimal because data placement is not optimized
Solution Approach 1:
The system computes hash values for data blocks before backup and uses these pre-computed hashes to determine optimal backup server selection. This preliminary action enables the broker to identify servers with matching data representations, allowing deduplication to occur more effectively and improve backup efficiency.
Solution Approach 2:
The broker computer receives data representations from backup servers and uses this feedback to make informed decisions about data placement. By continuously monitoring the content of data on backup servers and adjusting placement decisions based on commonality scores, the system optimizes both storage efficiency and backup efficiency.
2Ease of operation
If a broker computer performs load balancing operations, then data distribution is improved, but storage efficiency is lost because data content commonality is not considered
Solution Approach 1:
The system changes the parameter used for load balancing from simple metrics like storage capacity and network bandwidth to include data content commonality measured through hash value matching. This parameter change allows the broker to direct data to servers where deduplication will be most effective, improving storage efficiency while maintaining balanced data distribution.
Solution Approach 2:
The broker computer acts as an intermediary that mediates between the host computer and backup servers by computing commonality scores based on data representations. This intermediary function enables the system to optimize data placement decisions by considering data content similarity, thereby improving storage efficiency without compromising distribution balance.
3Device complexity
If backup servers store data without considering content commonality, then data placement is simplified, but deduplication opportunities are lost
Solution Approach 1:
The system replaces complex content analysis with a more efficient mechanism based on hash value comparison. Instead of analyzing actual data content, the broker uses cryptographic hash functions to generate data representations and compare them for similarity. This substitution maintains simplicity in the placement decision process while significantly improving deduplication efficiency.
Solution Approach 2:
The system changes the approach to content analysis by using hash values as a proxy for data content comparison. This parameter change transforms the complexity of content analysis into a simpler hash matching problem, maintaining data placement simplicity while enabling effective identification of deduplication opportunities through commonality scoring.
Data Source
AI summary
Techniques of backing up data stored on host computing devices involve selecting a backup server from among multiple servers on which to back up host data based on a measure of commonality between the host data and data stored in the backup servers. Prior to sending data for backup, a host sends a set of host data representations to a backup system. Each host data representation is based on a respective hash value computed from a respective block of the host data. The backup system compares the set of host data representations with server data representations for each backup server and computes a commonality score for each backup server. The backup system then selects a backup server on which to place the host data based at least in part on the commonality scores. Host data are then directed to the selected backup server for backup.