Mailing List Archive


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [tlug] SSD filesystem



On Sun, Jun 7, 2009 at 22:41, Francois Cartegnie<fcartegnie@example.com> wrote:
> Le dimanche 7 juin 2009, Clemens Schwaighofer a écrit :
>> I guess they are all the same like HDs, who in the world wants to
>> override the automatic badblock system in a normal HD?
>
> Hi clemens,
>
> No override for this, wear levelling and badblocks accounting/reindexing are
> totally different.

Yeah, but why would you want to override wear levelling? The makers
wont give out detailed information on when and how their maximum wear
level is reached. I see this more a disk/controller thing. Better to
do there than in the kernel itself.

>> FS need to change for that, so there will be some major rewrite to
>> address the difference between oldschool HDs and SSDs, but that will
>> take some time. SSDs are by fair a common good. Pricey for the good
>> ones, and real crappy slow for the bad ones.
>
> There's an opinion following linus recent remark about SSDs:
> http://ldn.linuxfoundation.org/blog-entry/should-filesystems-be-optimized-ssd%E2%80%99s
>
> I see more and more MLC devices appearing on the market with, or with more,
> RAM memory to improve performances (256..512MB...). That way you keep your
> frequent writes in ram (fs logs) and increase the reliability of those cheap
> dumb ssd devices for a low additional cost.

Well, cheap dumb SSDs are often worse than a normal harddisk in terms
of speed. I see this on my eeepc, good SSDs that can compete with
harddisks in write/read/etc are just more expensive and eventually
they will drop in price. Already they are much cheaper than any kind
of SSD was some years ago.

> If you look back how RAID made it to the market instead of the specialized
> expensive replicated disks, you don't have the guarantee that priceys ones
> will be the answer.

Which is of course logical, it was just cheaper to have 4~5 cheap
disks than one or super hyper expensive ones.

> And there's still a need for geeks (?) doing SSD disks with regular flash
> devices (compact flash, SDHC: you can even find multiple raid 0/1 controller
> for those ones). Most current embedded devices uses a read only FS for wear
> levelling reasons.

there is need? Well, perhaps I am just not geeky enough, but for me
SSD is something I would want to get, to have some very fast, a bit
more reliable disk device. But as I always need enormous amount of
disk space, SSD is anyway out of the question for me at the moment.

> The kernel might need to end up with uniformization for SSD access, and SSD
> makers firmware to provide a way to tune parameters, the way you can do with
> scsi disks (or in a limited way with sata).

This will come, I think, as more and more SSDs appear in mobile
devices where Linux has some usage already, or when SSDs might make a
big come to servers.

-- 
Clemens Schwaighofer
gullevek@example.com / gullevek@example.com
http://www.flickr.com/photos/gullevek/


Home | Main Index | Thread Index

Home Page Mailing List Linux and Japan TLUG Members Links