NANVM Node-Local Data Caching for Jitter Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing Network Attached Storage (NAS) systems face inefficiencies in data migration, leading to application jitter and high resource utilization due to bulk data movement and lack of data compartmentalization and resource reservation without external tools.
Innovation Solution
A system and method utilizing Network-Attached Non-Volatile Memories (NANVM) for efficient node-local data caching, which decouples data placement from access patterns and reserves storage partitions based on application requirements, allowing only valid clients to access data, thereby minimizing bulk data movement and optimizing resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If bulk data movement is used to migrate data to specific node-local storage devices, then data access speed is improved, but application jitter increases and system performance deteriorates
Solution Approach 1:
The system performs preliminary data placement in the caching layer before data access requests are made. Data is pre-positioned in optimal locations based on predicted access patterns, so when applications need data, it is already in place and can be accessed immediately without causing application jitter or performance degradation.
Solution Approach 2:
The patent introduces a caching layer as an intermediary between the storage system and applications. This caching layer handles data movement and placement operations, decoupling them from the main data access paths. The intermediary absorbs the impact of data migration activities, preventing them from causing jitter in application performance.
2Ease of operation
If data is stored in a centralized location for easy access, then data sharing is simplified, but data compartmentalization and security are reduced
Solution Approach 1:
The storage system is segmented into multiple caching layers and storage tiers. Data is divided and distributed across these segments, with the caching layer providing localized access points. This segmentation enables both simple access within each segment and security isolation between segments, as each caching layer can enforce access policies independently.
Solution Approach 2:
Different parts of the storage system have different qualities and access characteristics. The caching layer provides fast, localized access with high security, while the underlying storage provides bulk capacity. Each layer is optimized for its specific function, allowing the system to provide simple access where needed while maintaining security compartmentalization through layered architecture.
3Reliability
If external tools and services are used for resource reservation and data compartmentalization, then data security is improved, but system complexity increases
Solution Approach 1:
The patent merges the functions of data compartmentalization, resource reservation, and security management into the caching layer itself. Instead of requiring separate external tools and services, the caching layer integrates these capabilities natively, reducing system complexity while maintaining security and compartmentalization through unified management.
Solution Approach 2:
The caching layer provides self-service capabilities for resource reservation and data compartmentalization. It automatically manages data placement, access rights, and resource allocation based on predefined policies, eliminating the need for external management tools and reducing operational complexity while maintaining security requirements.
Data Source
AI summary
The system and routine for data caching leverages the properties of Network-Attached Non-Volatile Memories (NANVMs) to provide virtualized secure node-local storage services to the network users with reduced data movement across the NANVMs. The caching routine reserves storage resources (storage partitions) on NANVM devices, migrates data required for the target application execution to the allocated storage partitions, and directs the network clients to dynamically “mount” to the storage partitions based on application data requirements. Only those clients and applications that present valid credentials and satisfactory computing capabilities can access the data in the specific storage partitions. Several clients can have an access to the same storage partitions without duplication or replicating the data. A Global Data Indexing sub-system supports the efficient operation of the subject system. The Global Data Indexing Sub-System provides mapping between the storage partitions, data sets, applications, client nodes, as well as their credentials/capabilities.