LX-SSD: Enhancing the Lifespan of NAND Flash- based Memory via Recycling Invalid Pages
نویسندگان
چکیده
NAND flash-based SSDs utilize out-of-place update to prevent erase operations from blocking regular requests, in the meanwhile, out-of-place update creates a huge amount of invalid pages. Traditional FTLs perceive these invalid pages as useless data and discard them during garbage collection. But given value locality, certain values are likely to appear afterward, resulting in abundant invalid pages being still useful. In this paper, we propose a content-aware FTL to explore such locality and recycle invalid pages to achieve Lifetime eXtension SSD (LX-SSD), which is hereafter named as Recyclable SSD. Such recycling invalid pages enables an SSD to recycle invalid pages at the page granularity and without involving block erase operation. Since block erasures serve as a criterion for quantifying the lifespan of SSDs, the reduced block erasures could result in lifespan extension. In order to retain high performance, we design a set of acceleration techniques to reduce the overhead of extra computational costs. We also modify the GC algorithm to delay certain useful invalid pages from being erased. We evaluate LX-SSD on real-world workloads, with content information, and the results show that our Recyclable SSD can achieve 10.5%-18.4% write reduction and 40.6%-58.9% reduction in block erasures, which results in 10.5%18.4% overall reduction in I/O response time, and significant lifespan extension.
منابع مشابه
2LGC: An Atomic-Unit Garbage Collection Scheme with a Two-Level List for NAND Flash Storage
In NAND flash memory devices, pages marked “invalid” can remain in blocks and occupy flash space. Therefore, it is necessary to physically eliminate invalid pages and collect valid pages from the victim blocks in order to sustain flash write performance and storage lifespan. Although there have been many research studies on efficient garbage collection techniques, research has focused on victim...
متن کاملSaving SSD Erase Costs Using WOM Codes
NAND flash, used in modern SSDs, is a write-once medium, where each memory cell must be erased prior to writing. The lifetime of an SSD is limited by the number of erasures allowed on each cell. Thus, minimizing erasures is a key objective in SSD design. A promising approach to eliminate erasures and extend SSD lifetime is to use write-once memory (WOM) codes, designed to accommodate additional...
متن کاملReorder the Write Sequence by Virtual Write Buffer to Extend SSD's Lifespan
The limited lifespan is the Achilles’s heel of Solid State Drive (SSD) based on NAND flash memory. NAND flash has two drawbacks that degrade SSD’s lifespan. One is the out-of-place update. Another is the sequential write constraint within a block. To extend the lifespan, SSD usually employs a write buffer to reduce write traffic to flash memory. However, existing write buffer schemes only pay a...
متن کاملState-based Die Binding for Enhancing SSD Internal Parallelism
Solid state drives (SSDs) implement large capacity, high performance storage devices by connecting multiple NAND flash memory chips in parallel using multiple channels. Channels can transfer data simultaneously, and each NAND package is composed of multiple dies, which can independently perform NAND operations such as read, write, and erase. Therefore, maximizing the parallel processing capabil...
متن کاملFMMU: A Hardware-Automated Flash Map Management Unit for Scalable Performance of NAND Flash-Based SSDs
NAND flash-based Solid State Drives (SSDs), which are widely used from embedded systems to enterprise servers, are enhancing performance by exploiting the parallelism of NAND flash memories. To cope with the performance improvement of SSDs, storage systems have rapidly adopted the host interface for SSDs from Serial-ATA, which is used for existing hard disk drives, to high-speed PCI express. Si...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2017