FIFO Cache Reaping Using Birth Time for Permission Enforcement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional cache reaping systems based on last modification and/or created time struggle to enforce security policy updates by allowing frequently accessed and/or modified objects to remain in the local cache for long periods, despite permission revocations at the cloud storage system.
Innovation Solution
Implementing birth time-based FIFO cache reaping by recording the 'birth time' of cached objects and flagging them for deletion when their storage time exceeds a specified threshold, independent of access frequency, ensuring timely enforcement of permission changes or revocations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional cache reaping based on last modification and/or created time is used, then frequently accessed and/or modified objects remain in the local cache for long periods, but security policy updates cannot be enforced
Solution Approach 1:
The patent changes the parameter used for cache reaping from last modification time or created time to birth time (when the object was first cached). This parameter change ensures that objects are evicted based on how long they have been in the cache rather than how frequently they are accessed or modified, thereby enforcing security policy updates while maintaining cache functionality.
2Speed
If objects are kept in local cache for quick access, then data retrieval speed improves, but permission revocations at cloud storage system cannot be enforced
Solution Approach 1:
The system performs preliminary action by recording the birth time when an object is first cached. This preliminary recording enables later enforcement of permission revocations by comparing current time against the stored birth time to determine if the object should be evicted, thus maintaining both fast access and reliable permission enforcement.
Solution Approach 2:
The system implements feedback by continuously monitoring cache storage time against a maximum threshold and automatically evicting objects that exceed it. This feedback mechanism ensures that permission changes at the cloud storage system are reflected in the local cache by removing stale objects that should no longer be accessible.
3Productivity
If cache storage time is extended for performance, then access speed improves, but security updates are delayed
Solution Approach 1:
The patent applies dynamics by making the cache retention period dynamic rather than static. Objects are retained for a maximum duration based on their birth time, after which they are automatically evicted. This dynamic approach balances cache access efficiency with security update timeliness by ensuring objects are not retained indefinitely regardless of their access patterns.
Data Source
AI summary
Techniques for birth time-based first in, first out (FIFO) cache reaping are provided. A method includes obtaining an object from a long-term storage (LTS) system; storing the object in a local cache such that the object is associated with a birth time for the object at which the storage at the local cache occurred; calculating a local cache storage time for the object based on the birth time for the object at which the storage at the local cache occurred; and flagging the object for deletion from the local cache responsive to the local cache storage time exceeding a maximum cache storage threshold.


