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