DragonFly kernel List (threaded) for 2010-02
Re: kernel work week of 3-Feb-2010 HEADS UP
Matthew Dillon wrote:
> Yes, there are definitely management issues but wear life scales
> linearly with the amount of SSD storage (in terms of how much data
> you can write) and it is fairly easy to calculate.
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
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).
> One of things I will do when I get these SSDs in and get the basics
> working is intentionally wear out one of the Intel 40G drives to see
> how long it can actually go. That will be fun :-)
That will be very interesting.
Basically it seems that most MLC flash devices survive 10,000
writes per cell on average, while SLC does ten times more.
That's what most vendors specify.
Oliver Fromme, secnetix GmbH & Co. KG, Marktplatz 29, 85567 Grafing b. M.
Handelsregister: Registergericht Muenchen, HRA 74606, Geschäftsfuehrung:
secnetix Verwaltungsgesellsch. mbH, Handelsregister: Registergericht Mün-
chen, HRB 125758, Geschäftsführer: Maik Bachmann, Olaf Erb, Ralf Gebhart
FreeBSD-Dienstleistungen, -Produkte und mehr: http://www.secnetix.de/bsd