svn commit: r258632 - in head: cddl/contrib/opensolaris/cmd/ztest cddl/contrib/opensolaris/lib/libzpool/common/sys sys/cddl/compat/opensolaris/sys sys/cddl/contrib/opensolaris/uts/common/fs/zfs sys...

[Andriy Gapon]

on 26/11/2013 18:18 Steven Hartland said the following:
> ----- Original Message ----- From: "Andriy Gapon" <avg at FreeBSD.org>
> 
> 
>> on 26/11/2013 14:34 Steven Hartland said the following:
>>> Can I ask why choose priority now for TRIM, does this not change the flow of
>>> free requests quite significantly?
>>
>> Sorry, I couldn't grok the question...
>> Also, please take into account that I know nothing about TRIM nor TRIM + ZFS.
>>
>> BTW, I appreciate the review but a timely review[*] would be appreciated even
>> more :-)
> 
> Erm did I miss something, this only got commited a few hours ago which is
> the first I knew about it. Did you ask for reviews somewhere I'm not aware of?

Did you trim too much of my reply?
There was a "footnote" with a reference.

>>> Also as we have rotational information available should we apply
>>> the following change which makes the active queue timestamp sorted
>>> instead of offset sorted?
>>>
>>> An AVL as a FIFO queue seems like quite an expensive option.
>>
>> I've just merged the upstream change, perhaps badly.
>> Any improvement are appreciated.
> 
> Will look in more depth at this one as it touches the mirror code I commited
> recently.

Thank you!

-- 
Andriy Gapon