Computational Storage Device File System Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In computational storage devices, the host must manage all operations due to its sole understanding of the disk structure, limiting local processing and requiring involvement in every operation, which restricts the ability of the drive to operate autonomously or remotely.
Innovation Solution
A computational storage device is enabled to understand the data layout by automatically detecting or being informed of the file system occupying a non-volatile memory express namespace, allowing it to interpret metadata and map file objects to block ranges, thereby enabling local processing without host intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the host manages all operations due to its sole understanding of the disk structure, then operational control is maintained, but local processing capability is limited and operational efficiency deteriorates
Solution Approach 1:
The CSD performs self-service by autonomously detecting the file system type (e.g., ext4, xfs, btrfs) occupying its namespace and independently interpreting the corresponding data structures. This enables the device to map file objects to block ranges without host intervention, allowing local processing of read-only operations while maintaining host control for write operations.
Solution Approach 2:
The patent segments operational control into two parts: the host retains management of write operations and overall control, while the CSD gains autonomy for read-only operations through local file system interpretation. This segmentation enables parallel processing where the host works on other tasks while the CSD independently processes read operations.
2Reliability
If the host is involved in every operation, then data access control is maintained, but data movement and processing burden on the host increases
Solution Approach 1:
The patent extracts read-only processing operations from the host system and relocates them to the CSD. The CSD independently interprets file system metadata and performs local processing of read operations, removing this processing burden from the host while maintaining host control for write operations and overall data access management.
3Productivity
If the CSD operates autonomously with local processing, then operational efficiency improves, but the complexity of understanding data layout increases
Solution Approach 1:
The patent applies preliminary action by having the CSD detect and interpret the file system type and its corresponding data structures in advance. The device loads the appropriate data structure interpretation for the detected file system (ext4, xfs, btrfs, etc.), enabling subsequent autonomous operations without requiring complex real-time analysis of data layouts.
4Measurement precision
If the host manages all file system operations, then data structure interpretation is accurate, but the ability of the drive to operate remotely deteriorates
Solution Approach 1:
The CSD performs self-service by autonomously detecting the file system type and independently interpreting the corresponding data structures. This enables the device to operate remotely without host intervention for read operations, while maintaining accurate data structure interpretation through built-in knowledge of multiple file system formats.
Data Source
AI summary
The technology disclosed herein pertains to a system and method for providing the ability for a computational storage device (CSD) to understand data layout based upon automatic detection or host identification of the file system occupying a non-volatile memory express (NVMe) namespace, the method including receiving, at a CSD, a request to process a file using a computation program stored on the CSD, detecting a filesystem associated with the file within a namespace of CSD, mounting the filesystem on the CSD, interpreting a data structure associated with the file within the namespace, and reading the physical data blocks associated with the file into a computational storage memory (CSM) of the CSD.