Virtual Storage Journal Flushing for Ephemeral Storage Data Loss

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Virtual storage systems in cloud environments lack non-volatile memory or persistent storage with NVRAM-like performance, leading to data loss during shutdown or reboot scenarios due to the unreliability of ephemeral storage.

Innovation Solution

A virtual storage system maintains an operation log in vNVRAM and flushes it to both ephemeral and persistent storage during shutdown to minimize data loss, ensuring data durability and low latency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If ephemeral storage is used as backing storage for journaling, then write performance and latency are improved, but data durability during shutdown or reboot is worsened

Engineering Contradiction:
Improvewrite performanceVSAvoiddata durability
Core Design Contradiction:
SpeedVSReliability

Solution Approach 1:

The system segments the backing storage into two distinct components: ephemeral storage for high-speed journaling operations and persistent storage for durability. This segmentation allows each component to serve its specific function optimally without compromising the other.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system introduces a mediator mechanism that monitors the ephemeral storage and automatically flushes journal entries to persistent storage when shutdown or reboot is detected. This intermediary protection layer prevents data loss while maintaining the performance benefits of ephemeral storage.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If persistent storage is used as backing storage for journaling, then data durability is improved, but write performance and latency are worsened

Engineering Contradiction:
Improvedata durabilityVSAvoidwrite performance
Core Design Contradiction:
ReliabilityVSSpeed

Solution Approach 1:

The system divides the storage function into two segments: ephemeral storage handles high-speed write operations, while persistent storage ensures durability. Each segment performs its specialized function without interfering with the other's performance characteristics.

Inventive Principle:
Principle #1Segmentation

3Loss of time

If vNVRAM is used for operation log, then low latency is achieved, but data loss occurs during rehosting scenarios

Engineering Contradiction:
ImprovelatencyVSAvoiddata loss
Core Design Contradiction:
Loss of timeVSLoss of information

Solution Approach 1:

The system performs preliminary action by flushing the operation log from vNVRAM to persistent storage before shutdown or reboot occurs. This advance preparation ensures that critical data is preserved even if rehosting happens, preventing information loss while maintaining low latency during normal operation.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20250342088A1Reducing potential data-loss scenarios when using ephemeral storage as backing storage for journaling by a virtual storage system
Publication Date: 2025.11.06 NETAPP INC
  • US20250342088A1 patent drawing
  • US20250342088A1 patent drawing
  • US20250342088A1 patent drawing

AI summary

Systems and methods for flushing an operation log journal to both ephemeral storage and persistent storage during a shutdown sequence of a virtual storage system to minimize data-loss scenarios are provided. According to one embodiment, the shutdown or reboot scenarios that result in loss of data are minimized by using persistent storage as a backup to ephemeral storage when the scenario results in rehosting of virtual storage system. For example, responsive to an event indicative of an imminent shutdown or reboot of the virtual storage system, vNVRAM memory may be flushed to both ephemeral storage and persistent storage (e.g., a boot disk). In this manner, when the virtual storage system is rehosted after an unplanned shutdown or reboot resulting from an unrecoverable host error (other than an unrecoverable hardware failure), the operation log journal may be recovered from persistent storage to facilitate vNVRAM replay and avoid data loss.