Page Replacement Algorithms for NAND Flash Memory Storages

Yoo, Yun-Seok; Lee, Hyejeong; Ryu, Yeonseung; Bahn, Hyokyung

doi:10.1007/978-3-540-74472-6_16

Cited by 27 publications

(17 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Five algorithms were included in our experiments: CASA, LRU (representing conventional buffer algorithms), and the flashaware algorithms represented by CFLRU, CCFLRU, and LRUWSR. We did not include the CFLRU variants [9] and CFDC [5], due to two reasons: 1. All of them require the tuning of a parameter controlling the sizes of two buffer regions-the same limitations represented by CFLRU; 2.…”

Section: Methodsmentioning

confidence: 99%

“…Although its authors have mentioned a dynamic version of CFLRU, which automatically adjusts the parameter "based on periodically collected information about flash read and write operations" [4], its control logics is not presented. Yoo et al proposed several variants of CFLRU [9], aiming at reducing the number of flash erase operations and improving wear-leveling. These variants have the same limitation as CFLRU and their design goals are different from ours.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Clean first or dirty first?

Härder

2010

Proceedings of the Fourteenth International Database Engineering &Amp; Applications Symposium on - IDEAS '10

View full text Add to dashboard Cite

Flash SSDs originate a disruptive change concerning storage technology and become a competitor for conventional magnetic disks in the area of persistent database stores. Compared to them, they provide a dramatic speed-up for random reads, but exhibit a distinct read/write (R/W) asymmetry, i.e., updates are more expensive than reads. Existing buffer management algorithms for those devices usually trade physical reads for physical writes to some extent. But they ignore the actual R/W cost ratio of the underlying device and the update intensity of the workload. Therefore, their performance advantage is sensitive to device and workload changes. We propose CASA (Cost-Aware Self-Adaptive), a novel buffer replacement policy, which makes the trade-off between physical reads and physical writes in a controlled fashion, depending on the R/W cost ratio, and automatically adapts itself to changing update intensities in workloads. Our experiments show that CASA outperforms previous proposals in a variety of cost settings and under changing workloads.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Clean first or dirty first?

Härder

2010

Proceedings of the Fourteenth International Database Engineering &Amp; Applications Symposium on - IDEAS '10

View full text Add to dashboard Cite

show abstract

“…The victim for the eviction is the page in the clean-first region. The CFLRU/C, CFLRU/E, and DL-CFLRU/E [41] added more flexibility in choosing the victim, by referencing the access frequency and block erase count. For example, in CFLRU/C, if no clean page is available for the eviction, then the dirty page with the lowest access frequency will be selected as a candidate.…”

Section: Related Studiesmentioning

confidence: 99%

HFM: Hybrid File Mapping Algorithm for SSD Space Utilization

No¹,

Choi²,

Park³

et al. 2014

Appl. Math. Inf. Sci.

View full text Add to dashboard Cite

Abstract:Although the technology of flash memory is rapidly improving, SSD usage is still limited due to the high cost per storage capacity. An alternative is to construct the hybrid structure where a small SSD partition is combined with the large HDD partition, to expand the file system space to HDD storage capacity while exploiting the performance advantage of SSD. In such a hybrid structure, increasing the space utilization of SSD partition is the critical aspect in generating high I/O performance. In this paper, we present HFM (Hybrid File Mapping) that has been implemented for the hybrid file system integrated with SSD. HFM enables to divide SSD partition into several, logical data sections with each composed of the different extent size. To minimize fragmentation overhead, HFM defines three different ways of partitioning functions based on the extent size of each data section. Furthermore, file allocations on the extent are performed on the partitioned unit (segment) of extents to reuse the remaining free space as much as possible. The experimental result of HFM using three public benchmarks shows that HFM can be effective in increasing the usage of SSD partition and enables to contribute to provide better I/O throughput.

show abstract

“…NAND Flash usually uses page as unit to read and to write, when it needs to write a page of data into Flash, the controller send the programming instructions, data memory address and 2KB, Flash chip inside the pages automatically complete the programming operation. In the automatic programming, Flash chip through an internal program to save the data from the data register to the designated storage space, the "R /" "B" port will be pulled low, which means that the chip is in a busy working condition, the process required typical time is 200μs, the maximum time is 700μs [6][7][8]. Under normal circumstances, the controller needs to wait at the end of Flash internal the page program, which can continue to store data to Flash.…”

Section: Information Management Systemmentioning

confidence: 99%

AMT Fault Information System Based on CAN Bus Gateway

Liu¹,

Liu²

2014

Proceedings of the 2014 International Conference on Mechatronics, Control and Electronic Engineering

View full text Add to dashboard Cite

AMT fault information system based on CAN bus power gateway is designed for the requirements of fault diagnosis in AMT system of vehicle. The functional intergration of data communication in gateway and management of AMT fault data are realized by adding chips of Flash, EEPROM, DS1302, etc. based on the hardware platform of gateway, meanwhile, improving relevant software program. It provides vast analysis data for fault diagnosis and also improves the accuracy of fault diagnosis. The real vehicle test indicates that the system is stable, reliable and practical. This system plays an important role in fault diagnosis of vehicle transmission and data communication of vehicle in motion.

show abstract

Page Replacement Algorithms for NAND Flash Memory Storages

Abstract: Experiments through simulation studies show that the proposed algorithms reduce the number of erase operations and improve the wear-leveling degree of flash memory compared to LRU and CFLRU.

Cited by 27 publications

References 5 publications

Clean first or dirty first?

Clean first or dirty first?

HFM: Hybrid File Mapping Algorithm for SSD Space Utilization

AMT Fault Information System Based on CAN Bus Gateway

Contact Info

Product

Resources

About