On 08/02/2018 03:05 PM, Denis V. Lunev wrote:
On 08/02/2018 12:50 PM, Dr. David Alan Gilbert wrote:
* Denis V. Lunev (address@hidden) wrote:
I don't quite understand the last two paragraphs.
we are thinking right now to eliminate delay on regular IO
for migration. There is some thoughts and internal work in
progress. That is why I am worrying.
What downtime are you typicaly seeing and what are you aiming for?
It would be good if you could explain what you're planning to
fix there so we can get a feel for it nearer the start of it
rather than at the end of the reviewing!
Dave
The ultimate goal is to reliable reach 100 ms with ongoing IO and
you are perfectly correct about reviewing :)
Though the problem is that right now we are just trying to
invent something suitable :(
Den
Yeah, I gotcha -- please give me just a little time. I'm not against
using Vlad's series, it just surprised me. David and I have talked about
what you're trying to do and we are in agreement that it is the right
thing to do for now.
I have some more questions about Vlad's series, but I want to test it a
bit myself before I waste time asking them. I'll stage a working version
as soon as I can.
--js