File System File-Level Directories Fast Purge
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current file systems, especially in Content Delivery Networks (CDNs), face performance bottlenecks due to inefficient file organization and purging processes, which lead to delays in responding to incoming requests as they require multiple traversals to identify and manage files, particularly when dealing with large volumes of content and variants.
Innovation Solution
The introduction of file-level directories that isolate files associated with similar content, allowing operations to be performed on these directories instead of individual files, thereby eliminating the need for secondary traversals and optimizing file-level operations such as purging by using a single traversal and delayed purge mechanisms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If traditional directory structures are used to organize files, then files can be stored and accessed, but multiple traversals are required to identify and manage files, leading to performance bottlenecks
Solution Approach 1:
The patent segments the file system by creating file-level directories that group files associated with the same content together. This segmentation eliminates the need for multiple traversals by organizing files into content-based groups, where each file-level directory contains a root file, its variants, and supporting files. When a file needs to be accessed or managed, the system can directly navigate to the relevant file-level directory rather than searching through multiple directories.
2Productivity
If files are organized in common directories, then storage space is utilized, but purging operations require file-by-file traversal affecting other files and causing delays
Solution Approach 1:
The patent segments files into content-based groups using file-level directories. Each directory contains only files associated with a specific content item (root file, variants, and supporting files). This segmentation enables the purging operation to target an entire file-level directory with a single operation, eliminating the need for file-by-file traversal and preventing interference with other unrelated files in the system.
Solution Approach 2:
The patent merges related files (root file, variants, and supporting files) into a single file-level directory structure. By combining these associated files into one organized unit, the system can perform purging operations on the entire group simultaneously through a single directory operation, significantly improving purge speed and efficiency.
3Measurement precision
If multiple traversals are performed to identify files for operations, then accurate file identification is achieved, but system responsiveness decreases during peak hours
Solution Approach 1:
The patent segments the file system into content-based file-level directories, where each directory is dedicated to a specific content item and contains only files associated with that content. This segmentation maintains accurate file identification because the directory structure itself encodes the content association, eliminating the need for multiple traversals to identify which files belong together. The system can directly navigate to the correct file-level directory and perform operations with high accuracy and improved responsiveness.
Data Source
AI summary
Some embodiments provide a file system for purging content based on a single traversal of the file system that identifies the directory containing the content without performing a secondary traversal within the directory to target the operation to only the file that are associated with content such that other files contained in the directory are unaffected. The file system supplements traditional directory structures with file-level directories. Each file-level directory is created to contain a root file associated with particular content, different variants of the particular content, and supporting files. Consequently, the file system can complete an operation targeting particular content by performing that operation on the file-level directory containing the particular content, thereby eliminating the need to conduct a file-by-file traversal of the containing directory as a prerequisite to identifying the files associated with the particular content and performing the operation on the files individually.