Design and Implementation of a Log-Structured File System for Flash-Based Solid State Drives

2014 ◽  
Vol 63 (9) ◽  
pp. 2215-2227 ◽  
Author(s):  
Changwoo Min ◽  
Sang-Won Lee ◽  
Young Ik Eom
Author(s):  
Adnan Asad Vohra ◽  
Dr. Srividya P

In the day and age of data and information, the ability to retrieve the information becomes of paramount importance. The cutting edge technology in terms of data storage is currently Solid State Devices which use NAND gates to store data. This relatively new method of storing data presents numerous avenues of research and breakthroughs. The concept of Zoned Namespaces in SSD firmware is one such major avenue of ongoing research. The objective of this paper is to understand the need for higher data accessing speeds and envisioning the advancements made possible by improving basic read and write speeds in SSD's. The goal is to allow for writing sequential data in namespaces where the data related to each other holds a granularity of a single zone. The idea is achieved by implementing sequential read ahead where the sequential data is read ahead of time by anticipating host read request to that data. This gives the host, cache hit on requested data which greatly improves performance. The pre-fetched data is cleared from cache once the data has been read or any disabling condition occurs thus not hampering normal functioning of the drive. The implementation was tested on a 8 TB form factor SSD. The results for reads were 70 MB/s for ZNS before SRA and 275 MB/s after SRA enablement. Thus a very significant increase is observed which proves that the objective was achieved.


Electronics ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 486
Author(s):  
Yongjae Chun ◽  
Kyeore Han ◽  
Youpyo Hong

Owing to their advantages over hard disc drives (HDDs), solid-state drives (SSDs) are widely used in many applications, including consumer electronics and data centers. As erase operations are feasible only in block units, modification or deletion of pages cause invalidation of the pages in their corresponding blocks. To reclaim these invalid pages, the valid pages in the block are copied to other blocks, and the block with the invalid pages is initialized, which adversely affects the performance and durability of the SSD. The objective of a multi-stream SSD is to group data by their expected lifetimes and store each group of data in a separate area called a stream to minimize the frequency of wasteful copy-back and initialization operations. In this paper, we propose an algorithm that groups the data based on input/output (I/O) types and rewrite frequency, which show significant improvements over existing multi-stream algorithms not only for performance but also for effectiveness in covering most applications.


Author(s):  
Hyunchan Park ◽  
Cheol-Ho Hong ◽  
Younghyun Kim ◽  
Seehwan Yoo ◽  
Chuck Yoo

Sign in / Sign up

Export Citation Format

Share Document