about fragmentation (of free disk space)

[Justin C. Walker]

On Oct 10, 2015, at 12:06 , René J.V. Bertin wrote:

> On Saturday October 10 2015 14:45:43 Daniel J. Luke wrote:
> 
>> random access time for a SSD is 1-3 orders of magnitude less than for a rotational drive.
>> 
>> As with anything, you need to measure ‘real world use’ to be certain, but it’s probably not an issue for SSDs at all.
> 
> I'm not expecting it to be in real world usage, of course. OTOH, frequent defragmenting is probably not a good idea on SSDs.
> 
>> Which API lets you know if you have a contiguous file or not / how do you ‘require’ a contiguous file on disk?
> 
> Not sure, but I seem to recall it is possible. That said, I may just have observed that in ... defragmentation utilities (which tend not to work on files they cannot move to a contiguous bit of disk space).

I'm not convinced that defragging is a necessity on modern (rotational) drives, and for SSDs I don't think it makes sense As Daniel suggests).  These days, don't most drives do a lot of caching?  Also, OS X in recent incarnations does a pretty good job of detecting when you are streaming a file and doing a lot of prefetching.

Justin

PS: A better place to ask this is on the Darwin Kernel mailing list (hosted by Apple).  There are disk/FS experts that may be able to give you some pretty good answers.

--
Justin C. Walker, Curmudgeon at Large
Institute for the Absorption of Federal Funds
-----------
I'm beginning to like the cut of his jibberish.
-----------