Fixed: The Linux Desktop Responsiveness Problem?

[phoronix]

Phoronix: Fixed: The Linux Desktop Responsiveness Problem?

One of the problems commonly talked about in our forums and elsewhere is the poor responsiveness of the Linux desktop when dealing with significant disk activity on systems where there is insufficient RAM or the disks are slow. The GUI basically drops to its knees when there is too much disk activity, which is far from being ideal. For many the problem has just been present for a year or two, but those experiencing these horrible responsiveness problems where it may take many seconds for a menu to appear when clicking on it or a half-minute to do a VT switch, there soon may be a fix...

http://www.phoronix.com/vr.php?view=ODQ3Mw

[blackshard]

This is a curious problem that lived too long for my tastes. Just copying a large file from a CD to the hard drive almost freezes my GUI while it is going to be flushed to disk.
This is not acceptable.

[xir_]

if this fixes the problem then I will find a way to send this man a beer.

[yoshi314]

i wonder how much does it help on amd64, because it's even worse in there.

i'll try backporting this to current stable at home. this just cannot wait for the next reelase.

[xir_]

i wonder how much does it help on amd64, because it's even worse in there.

i'll try backporting this to current stable at home. this just cannot wait for the next reelase.

is there anyway to benchmark this? It often seems to be an qualitative rather quantitative problem.

[V!NCENT]

Except for BSOD's the only bug I found in Windows is exactly the same, but then only with read and not write. So when my dad (hobby photographer) was so tired of this shit he encountered this stupid bug in Linux. It was even more frustrating with the quick/autosave in F.E.A.R. under Wine which kept him going with Windows 7 most of the time.

[kernelOfTruth]

if this fixes the problem then i will find a way to send this man a beer.

++ :d

i wonder how much does it help on amd64, because it's even worse in there.

I'll try backporting this to current stable at home. This just cannot wait for the next reelase.

++

[kraftman]

i'll try backporting this to current stable at home. this just cannot wait for the next reelase.

It should be backported to 2.6.32, so LTS one, because it's widely used and to 2.6.35, because it seems it will be also widely used - Ubuntu 10.10 etc.

[DeepDayze]

i wonder how much does it help on amd64, because it's even worse in there.

i'll try backporting this to current stable at home. this just cannot wait for the next reelase.

Sounds like an idea.

Report back how successful you are on this, as many people would love to see this problem vanish even in 2.6.35 or if in possible a 2.6.34 kernel

Edit...another poster suggesded 2.6.32 Sounds good

[piotr]

Hi.

Can anyone point me to another patch? I see there only one. I want put it in my 2.6.35 kernel.