[Ksummit-2008-discuss] Suggested topic: possible

Eyal Shani Eyal.Shani at sandisk.com
Mon Aug 4 21:04:44 PDT 2008


David Woodhouse   wrote:
"We have software implementations of a few FTL layers in Linux already
which could implement 'trim' immediately and benefit from it. I've been
saying we need it for years (although I've also been saying that FTL is
the wrong approach and we should just write file systems to work on raw
flash, so fixing _one_ of the ways in which FTLs are suboptimal has
never real reached the top of my TODO list)."

For a second there I thought u meant SSD management should be left for the SSDs themselves.
However, I then continued reading, and understood you feel the opposite - you suggest writing FS for RAW flash..?!

This have been tried a few years ago, in the Cellular business, and worked OK for SLC - just until MLC came to ruin the dream.
The case in  PCs, with the complexity of SSD required bandwidth, makes that pretty hard to get.

Such an implementation would work, maybe, but for sure will not give optimized solution - performance & endurance.
There are just too many different internal architecture out there, with different focus & flash technologies, to have SW deal with it.

Eyal Shani @ SanDisk SSD

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.linux-foundation.org/pipermail/ksummit-2008-discuss/attachments/20080805/82b44991/attachment.htm 


More information about the Ksummit-2008-discuss mailing list