Common Snapshot File System Optimizations for Low I/O Latency

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing multi-site distributed storage systems experience significant latency spikes during common snapshot creation due to I/O operations, which can disrupt business operations and exceed networking protocol timeouts, especially in high availability pairs with synchronous replicated datasets.

Innovation Solution

Optimizations such as batch forming synchronous replicated datasets, CP coalescing, asynchronous CP utilization, and snapshot tag meta file growth are employed to minimize I/O latency during common snapshot creation, maintaining file system consistency and utilizing multithreading for faster resynchronization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If common snapshot creation is performed in synchronous replicated datasets, then data consistency between primary and secondary storage sites is ensured, but I/O latency increases significantly

Engineering Contradiction:

Improvedata consistencyVSAvoidI/O latency

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system segments the common snapshot creation process into multiple independent threads, each handling a portion of the storage objects. This allows parallel processing of snapshot operations across different data sets, reducing the total time I/O operations are blocked while maintaining consistency across all segments through coordinated completion signals.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by pre-allocating resources and preparing thread pools before snapshot creation begins. Metadata structures are pre-initialized and resource locks are pre-acquired where possible, so that when snapshot creation starts, the system can immediately begin parallel processing without additional setup overhead that would increase I/O latency.

Inventive Principle:

Principle #10Preliminary action

2Productivity

If batch snapshot create operation is performed in parallel multiple threads, then processing speed is improved, but system complexity increases

Engineering Contradiction:

Improveprocessing speedVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system merges multiple thread management operations into a unified thread pool framework. All parallel snapshot creation threads share common resource pools, synchronization mechanisms, and completion tracking structures. This consolidation reduces the overhead of managing separate thread structures for each snapshot operation while maintaining high parallel processing speed.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The snapshot creation system implements universal, reusable data structures and functions that serve multiple purposes across different snapshot operations. Metadata structures are designed to be generic and can handle various types of storage objects, and the thread management system can handle different snapshot scenarios with the same core logic, reducing overall system complexity despite high parallelism.

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Adaptability or versatility

If independent workflow is initiated for each storage object, then snapshot creation flexibility is improved, but coordination overhead increases

Engineering Contradiction:

Improvesnapshot creation flexibilityVSAvoidcoordination overhead

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system implements feedback mechanisms where each independent thread workflow reports its status, resource requirements, and completion state to a central coordinator. This feedback allows the coordinator to dynamically adjust resource allocation and synchronize completion across all workflows without requiring rigid pre-coordination, reducing overhead while maintaining flexibility. The coordinator receives completion signals and triggers the next phase of snapshot creation only when all workflows are ready.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20250363014A1Methods and systems to reduce latency of input/output (i/o) operations based on file system optimizations during creation of common snapshots for synchronous replicated datasets of a primary copy of data at a primary storage system to a mirror copy of the data at a cross-site secondary storage system

Publication Date: 2025.11.27 NETAPP INC

AI summary

Multi-site distributed storage systems and computer-implemented methods are described for improving a resumption time of input/output (I/O) operations during a common snapshot process for storage objects. A computer-implemented method comprises performing a baseline transfer from at least one storage object of a first storage node to at least one replicated storage object of a second storage node, starting the common snapshot process including stop processing of I/O operations, performing a snapshot create operation on the primary storage site for the at least one storage object of the first storage node, resuming processing of I/O operations, and assigning a new universal unique identifier (UUID) to the at least one storage object of the second storage node after resuming processing of I/O operations with the new UUID to identify when file system contents are different than the baseline transfer.