On Sat, Dec 31, 2005 at 09:50:22AM +0100, Juraj Holtak wrote:
> new data:
>
> not forcing a sync mount for the guest makes the performance impact of
> disabling write cache very low.
>
> The question is: What`s the smaller evil???
With O_SYNC off, guests are vulnerable to data corruption
if the
new data:
not forcing a sync mount for the guest makes the performance impact of
disabling write cache very low.
The question is: What`s the smaller evil???
juraj
---
This SF.net email is sponsored by: Splunk Inc. Do you grep through log fil
Am Samstag, den 31.12.2005, 01:39 + schrieb Chris Lightfoot:
> On Sat, Dec 31, 2005 at 12:36:50AM +0100, Juraj Holtak wrote:
> > I still do not understand, why the guests became that much slow. Could
> > somebody explain me why?
>
> Very probably you're suffering from seeing the real seek
> pe
On Sat, Dec 31, 2005 at 12:36:50AM +0100, Juraj Holtak wrote:
> I still do not understand, why the guests became that much slow. Could
> somebody explain me why?
Very probably you're suffering from seeing the real seek
performance of the disks. Switching on the write cache
hides this, at the cost
Hi,
I`m not reporting a bug, just an experience.
My server UPS died today and I can`t get a replacement because the
highway is closed because of heavy heavy snowfall. :-) Of cause, a power
failure is preprogrammed under this conditions.
So in my paranoia, I disabled write caching for my harddriv
