when two virtual machines use sockets between one another on a single
local system, does that end up routed through the loopback interface?
-C
---
This SF.net email is sponsored by: Splunk Inc. Do you grep through log files
for problems? Stop!
On Thu, Dec 08, 2005 at 10:57:35AM -0600, Rob Landley wrote:
[...]
> What we really want are write barriers (which I don't believe Linux exposes
> to
> userspace but I'm not sure), and for UBD to propogate through actual fsync
> requests to the underlying OS.
I did some work on this six wee
On Thu, Dec 08, 2005 at 10:57:35AM -0600, Rob Landley wrote:
> What we really want are write barriers (which I don't believe Linux exposes
> to
> userspace but I'm not sure), and for UBD to propogate through actual fsync
> requests to the underlying OS.
The real problem is if the *host* crashes
On Wed, 7 Dec 2005, noel anderson murmured woefully:
> Am trying to compile kernel 2..6.7 with the equivlent patch 2.6.7-1. Any
> help is appreciated.
> I'm using FC4.
There's *very* little chance that a UML patch of such great age will
work reliably. IIRC, UML started working reliably around
On Thursday 08 December 2005 10:50, Joel Palmius wrote:
> Yup, makes a vast difference. XFS + not using synchronize is almost as
> fast as using ubd as loopback on host.
>
> Says in help one shouldn't do this if one cares about the data in the UBD
> though. Exactly how dangerous is it?
I _think_ t
Yup, makes a vast difference. XFS + not using synchronize is almost as
fast as using ubd as loopback on host.
Says in help one shouldn't do this if one cares about the data in the UBD
though. Exactly how dangerous is it?
// Joel
On Thu, 8 Dec 2005, Rob Landley wrote:
On Thursday 08 Dec
On Thursday 08 December 2005 08:06, Joel Palmius wrote:
> Are there any general recommendations for making throughput on UBDs more
> efficient? Such as kernel settings, recommended filesystems..?
>
> Doing an "emerge sync" inside an uml raises iowait to 100% and load to 7,
> making the machine more
On Thu, Dec 08, 2005 at 03:06:28PM +0100, Joel Palmius wrote:
> Are there any general recommendations for making throughput on UBDs more
> efficient? Such as kernel settings, recommended filesystems..?
>
> Doing an "emerge sync" inside an uml raises iowait to 100% and load to 7,
> making the mac
Are there any general recommendations for making throughput on UBDs more
efficient? Such as kernel settings, recommended filesystems..?
Doing an "emerge sync" inside an uml raises iowait to 100% and load to 7,
making the machine more or less inaccessible. Just wondering if it's me
having bad s
