Download presentation
Presentation is loading. Please wait.
Published byElvin Holmes Modified over 9 years ago
1
ExLRU : A Unified Write Buffer Cache Management for Flash Memory EMSOFT '11 Liang Shi 1,2, Jianhua Li 1,2, Chun Jason Xue 1, Chengmo Yang 3 and Xuehai Zhou 2 1 Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong 2 Department of Computer Science, University of Science and Technology of China, Hefei, China 3 Department of Electrical & Commputer Engineering, University of Delaware 2012. 01. 12 (Thu) Kwangwoon univ. SystemSoftware Lab. HoSeok Seo 1
2
Introduction Propose Write buffer management scheme for Flash memory Purpose of write buffer? Increase the write performance Reduce the number of erase operations on flash memory Why consider NAND Flash characteristics? Write operation time is longer than read operation NAND Flash has limited erase operation count Out-place-update 2
3
Background Previous study for NAND flash & Access patterns FAB, BPLRU, etc 3 Weak from sequential write patterns Weak from random write patterns
4
Motivation Previous schemes is Managed with the block-level information. Lack of the page-level information. Result in inappropriate eviction decisions, as follows: Slow retirement of large cold blocks. -Block size is big, but pages is cold. Early eviction of small hot blocks. -Block size is small, but pages is hot. Cold page retention in heat-imbalanced blocks. -Few pages is hot, but most pages is cold. Thus, ExLRU takes the page-level access information and the characteristics of flash memory. 4
5
Cost Model of ExLRU The page-level information and the block-level information 5
6
Cost Model of ExLRU Averaged Frequency of Pages (AFP) Averaged Frequency of Block (AFB) Unified eviction cost of block x (UC) 6
7
Cost Model of ExLRU Example Cost is 7
8
Efficient ExLRU The cost model of ExLRU has the overhead of O(n). Efficient ExLRU Proposed to reduce the overhead. Identify the block with UC value low enough, not the lowest. Pre-identify blocks during the idle time between two write requests Cost is 8
9
Efficient ExLRU Two processes Scanning process and victim block selection process 9 (WR)(ER)
10
Efficient ExLRU In scanning process. Work in time between two write requests, if the number of blocks in ER is smaller than a threshold N min. Move blocks into ER, if UC < T UC In victim block selection process. Select a block at LRU position of ER when the buffer is full. If block miss in ER, UC values of blocks decrease. If hit in ER, re-compute UC, and move a block WR or not. If page miss in ER, add pages a block, and re-compute UC, and move a block MRU position of ER 10
11
Experimental Methodology Use event-driven Simulator SSD capacity : 8GB A page size : 2KB A block size : 64 pages FTL algorithm : FAST Trace : Financial, PC 11
12
Experimental Results Average Size and Number of Evicted Blocks 12 ExLRU_S : T UC is static ( 0.1 x 10-5 ) ExLRU_D : T UC is dynamic 19.7% decrease19.1% increase
13
Experimental Results Write and Erase Reduction in Financial trace 13 Best case 10.4% decrease Average 3% decrease
14
Experimental Results Write and Erase Reduction in Financial trace 14
15
Parameter Sensitive Studies 15 N min : Min number of blocks of ER T UC : Max value for ER T SCAN. : Max number of blocks at scan
16
Conclusion This scheme is designed to improve the write performance and reduce the number of erase operations Care about diverse type of access patterns. Exploit the page-level information and the block size 16
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.