| 1 |
Am Sonntag, 26. August 2012, 13:41:09 schrieb Alex Schuster: |
| 2 |
> Frank Steinmetzger writes: |
| 3 |
> > On Thu, Aug 23, 2012 at 12:15:20PM +0200, Alex Schuster wrote: |
| 4 |
> >> The size of an erasable block of SSDs is even larger, usually 512K, it |
| 5 |
> >> would be best to align to that, too. A partition offset of 512K or 1M |
| 6 |
> >> would avoid this. |
| 7 |
> > |
| 8 |
> > Unless the filesystem knows this and starts bigger files at those 512 k |
| 9 |
> > boundaries (so really only one erase cycle is needed for files <=512 k), |
| 10 |
> > isn't this fairly superfluous? |
| 11 |
> |
| 12 |
> Yes, I think it is. When you search for SSD alignment, you read about |
| 13 |
> this alignment all the time, even on the German Wikipedia, and many |
| 14 |
> resources say that this can have a big impact on performance. But I |
| 15 |
> could not find a real explanation at all. |
| 16 |
> |
| 17 |
> Besides that, it's not so easy to do the alignment, at least when using |
| 18 |
> LVM. I read that LVM adds 192K header information, so even if you align |
| 19 |
> the partition start to an erasable block size of 512K, the actual |
| 20 |
> content is not aligned. See [*] for information how to overcome this. |
| 21 |
> That is, if you believe the alignment to erasable blocks is important, |
| 22 |
> personally I do not know what to think now. It wouldn't hurt, so why not |
| 23 |
> apply it, but it seems like snake oil to me now. |
| 24 |
> |
| 25 |
> Wonko |
| 26 |
> |
| 27 |
> http://tytso.livejournal.com/2009/02/20/ |
| 28 |
|
| 29 |
because erasing is slow. You can not overwrite data on a ssd. you have to |
| 30 |
erase first, then reprogramm. Also, erasing shortens lifetime. |
| 31 |
|
| 32 |
-- |
| 33 |
#163933 |
Archives