Abstract
In NAND flash storages, the invalidated pages could occupy the storage space until being erased. In order to preserve sustained write performance and storage capacity, the storage controller must eliminate these pages through garbage collection operations. However, the garbage collection operations may cause high computation overhead while selecting victim blocks, thereby resulting in the host system suffering from unendurable storage-access latency as well as performance degradation. In this paper, we propose an efficient garbage collection mechanism, which not only eliminates the computation overhead in victim block selection, but also improves responsiveness to the host requests by making the garbage collection operation preemptive.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
