Dynamic Resource Allocation for Virtualized Backup in Storage Arrays

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Modern storage systems face challenges in managing data migration and backup operations between deduplicated and non-deduplicated storage tiers, leading to thrashing issues due to the computationally intensive rehydration process and inefficient resource allocation, which affects performance and storage efficiency.

Innovation Solution

Implementing an enhanced Quality of Service (QoS) manager that tracks deduplication statistics and workload aggregation to intelligently manage data movements between tiers, dynamically reallocating resources and balancing performance and storage efficiency by considering deduplication ratios and I/O demands.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If data is migrated to deduplicated storage tier, then storage efficiency is improved, but access performance deteriorates due to rehydration overhead

Engineering Contradiction:
Improvestorage efficiencyVSAvoidaccess performance
Core Design Contradiction:
Quantity of substanceVSSpeed

Solution Approach 1:

The system pre-hydrates deduplicated data in advance of anticipated access needs by monitoring access patterns and proactively reconstructing deduplicated blocks before they are needed, thereby reducing the performance impact when access occurs

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts the balance between deduplication and rehydration based on real-time workload characteristics, access patterns, and system resources, migrating data flexibly between deduplicated and non-deduplicated tiers to optimize both storage efficiency and access performance

Inventive Principle:
Principle #15Dynamics

2Quantity of substance

If frequent data migration occurs between tiers, then storage optimization is improved, but system stability deteriorates due to thrashing

Engineering Contradiction:
Improvestorage optimizationVSAvoidsystem stability
Core Design Contradiction:
Quantity of substanceVSStability of the object's composition

Solution Approach 1:

The system implements periodic stability checks and migration rate limits that prevent excessive back-and-forth data movements by enforcing minimum intervals between migrations and detecting thrashing patterns, thereby stabilizing the system while maintaining storage optimization

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The system monitors migration patterns and system performance metrics in real-time, using feedback loops to detect and respond to thrashing conditions by adjusting migration policies, pausing migrations when instability is detected, and resuming when stability is restored

Inventive Principle:
Principle #23Feedback

3Reliability

If CPU resources are allocated for deduplication operations, then data protection capability is improved, but I/O performance deteriorates

Engineering Contradiction:
Improvedata protection capabilityVSAvoidI/O performance
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system dynamically allocates CPU resources between deduplication operations and I/O processing based on workload characteristics, prioritizing I/O performance during high-access periods while maintaining data protection capabilities during low-utilization periods

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system adjusts deduplication parameters such as chunk size, deduplication ratio thresholds, and compression levels to reduce CPU overhead while maintaining adequate data protection capability, optimizing the balance between reliability and productivity

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS11513902B1System and method of dynamic system resource allocation for primary storage systems with virtualized embedded data protection
Publication Date: 2022.11.29 EMC IP HLDG CO LLC
  • US11513902B1 patent drawing
  • US11513902B1 patent drawing
  • US11513902B1 patent drawing

AI summary

Embodiments provide for a primary storage array having multiple storage tiers. The multiple storage tiers include one or more performance tiers and at least one deduplicated storage tier storing deduplicated data. One embodiment provides for a data storage system including the storage array and an I/O engine to manage I/O requests for the storage array. The data storage system additionally includes a virtual execution environment to execute a virtual backup engine, the virtual backup engine to generate backup data for the one or more storage tiers of primary storage and deduplicate the backup data and a resource manager to manage a resource allocation to the virtual backup engine based on a hint received from the virtual backup engine, the hint associated with a backup operation that has a characterization selected from a set including computationally intensive and I/O intensive.