Experimental results

Experimental results

Postby adzm » 2010-11-19 00:03

Two viewers, same server, updating twice a second to eliminate CPU differences on bandwidth, running through a repeater.

I'll explain more once I have time, but it's much more exciting to just leave this here.

Image
[/img]
adzm
20
20
 
Posts: 63
Joined: 2009-04-29 18:59

Re: Experimental results

Postby redge » 2010-11-19 00:08

what is encoder XZ for receive 8.555Mb only ?

your own encoder ?
UltraVNC 1.0.9.6.1 (built 20110518)
OS Win: xp home + vista business + 7 home
only experienced user, not developer
redge
Super-Mod
Super-Mod
 
Posts: 6815
Joined: 2004-07-03 17:05
Location: Switzerland - Geneva

Re: Experimental results

Postby adzm » 2010-11-19 02:43

Yeah, basically compressing in an XZ stream using LZMA2. The parameters are tuned for the kind of data and network patterns VNC uses.

More CPU and RAM but much better compression. This works well for me since bandwidth is usually the limiting factor rather than server resources.

I'll probably have some volunteers help test and tune things before making anything official yet. I have been working on this for several months, but only this weekend found enough time to put together everything and see it in action.
adzm
20
20
 
Posts: 63
Joined: 2009-04-29 18:59

Re: Experimental results

Postby redge » 2010-11-20 16:11

I think you try already others encoders ?

lzo ?
how much increased latency screen update with xz format ?
UltraVNC 1.0.9.6.1 (built 20110518)
OS Win: xp home + vista business + 7 home
only experienced user, not developer
redge
Super-Mod
Super-Mod
 
Posts: 6815
Joined: 2004-07-03 17:05
Location: Switzerland - Geneva

Re: Experimental results

Postby kissson » 2010-11-20 18:23

don't just concern the transferred size, how about the responsiveness ?
compression does always affect responsiveness no matter how it is
kissson
8
8
 
Posts: 25
Joined: 2006-06-12 08:52


Return to 1.0.9.1 (stable)

Who is online

Users browsing this forum: No registered users and 2 guests