hd firecuda

[RW]

On Wed, 20 Dec 2017 10:53:00 +0800
Erich Dollansky wrote:

> Hi,
> 
> On Tue, 19 Dec 2017 14:46:06 +0000
> RW via freebsd-questions <freebsd-questions at freebsd.org> wrote:
. On long writes, this space will also be filled.       
> > 
> > It's unlikely that it would fall back to discarding useful cache in
> > the SSD *after* filling the larger non-shingled area of the drive.
> > If that bit of extra buffering made a useful difference they'd just
> > increase the size of the non-shingled area.  
> 
> how to increase the non-shingled area without shrinking the drive's
> available size?

They'd design it with the right size in the first place using their
experience with ordinary shingled drives. 


> > IMO what you are seeing is consistent with selective read caching
> > plus write caching into the non-shingled area.    
> 
> How do you explain then the deep breath? What do I call a deep breath?
> An access which takes more than a minute. It only happens when huge
> amounts of data is written to the drive like updating sources and
> ports tree and then starting to compile them.

Any explanation you have involving buffering writes through flash also
fits buffering through the non-shingled area.