Re: kernel work week of 3-Feb-2010 HEADS UP

看板DFBSD_kernel作者時間16年前 (2010/02/05 10:32), 編輯推噓0(000)
留言0則, 0人參與, 最新討論串17/30 (看更多)
:All flash media (SSDs, CF cards, USB sticks) use wear-leveling :techniques that aim to distribute the number of write cycles :evenly over all cells. Here are two nice papers from Corsair :and Micron: : :http://www.corsair.com/_faq/FAQ_flash_drive_wear_leveling.pdf : :http://download.micron.com/pdf/technotes/nand/tn2942_nand_wear_leveling.pdf : :When you google for "flash wear leveling", you get a bunch of :other interesting hits, including papers from Samsung, Kingston, :Spansion and others. Most wear-leveling implementatios are :optimized for mostly linear writes, which is the reason that :special flash file systems exist (e.g. in Linux and Solaris). Very very interesting. So now the question is whether OCZ and Intel implement static wear leveling or not. My presumption is they must, but I can't find a definitive document on the issue. -Matt
文章代碼(AID): #1BQuCdde (DFBSD_kernel)
討論串 (同標題文章)
文章代碼(AID): #1BQuCdde (DFBSD_kernel)