Avoid recursively walking guest short VHPT
- Anthony
guest_vhpt_walk.patch
Description: guest_vhpt_walk.patch
___
Xen-ia64-devel mailing list
Xen-ia64-devel@lists.xensource.com
http://lists.xensource.com/xen-ia64-devel
Hi all,
At xen-ia64-unstable:13867, the serial console connected to my Tiger4
machine outputs no messages. Do anyone have any ideas?
Cset:13773 is good.
My setting:
append=dom0_mem=2G com2=115200,8n1 console=com2,vga tbuf_size=8 \
dom0_max_vcpus=2 -- console=tty0
Hi, David
Okay got some more information this is kinda odd...
If you look it does see the two cpu's but later theres a line about
Dom0 max_vcpus=1.
How did this get set? is this default? could I set this on the commandline
to 2?
Hmmm, this seems where it's being set... so all I'd have to
On Thu, Feb 08, 2007 at 05:29:34PM +0900, KUWAMURA Shin'ya wrote:
Hi all,
At xen-ia64-unstable:13867, the serial console connected to my Tiger4
machine outputs no messages. Do anyone have any ideas?
Cset:13773 is good.
My setting:
append=dom0_mem=2G com2=115200,8n1 console=com2,vga
Hi, Isaku
Thank you for your suggestion.
Do you have any idea to consolidate steal time for various arch?
Thanks
Atsushi SAKAI
Isaku Yamahata [EMAIL PROTECTED] wrote:
On Wed, Feb 07, 2007 at 05:55:23PM +0900, Atsushi SAKAI wrote:
This patch intends to consider steal time accounting.
/20070208/broken_out/README
http://www.vergenet.net/linux/kexec/ia64-xen/20070208/broken_out/BUILD
This release is based on:
xen-ia64-unstable, version 13867 (the latest checkout as of writing!)
kexec-tools-testing 20061214
linux 2.6.20
I'm more than happy for people to help
Hi All,
The dma-mapping.h include header file of i386 architecture.
・linux-2.6-xen-sparse/include/asm-ia64
12 /* Needed for arch/i386/kernel/swiotlb.c */
13 #include asm-i386/mach-xen/asm/swiotlb.h
The swiotlb.h file has already been added to the ia64 architecture.
On Thu, 2007-02-08 at 17:29 +0900, KUWAMURA Shin'ya wrote:
Hi all,
At xen-ia64-unstable:13867, the serial console connected to my Tiger4
machine outputs no messages. Do anyone have any ideas?
Cset:13773 is good.
My setting:
append=dom0_mem=2G com2=115200,8n1 console=com2,vga
Yes.
If you alloc two vcpus to dom0, you must add dom0_max_vcpus=2 to
command line of xen. If you don't add dom0_max_vcpus, xen alloc one
vcpu to dom0. This is default as you said the above.
e.g. my elilo.conf
image=vmlinuz-2.6.18-xen
vmm=xen.gz
label=xen
On Thu, 2007-02-08 at 11:24 +0800, Xu, Anthony wrote:
Alex Williamson write on 2007年2月8日 4:00:
Hi Anthony,
I think I found a bug in this patch. After saving and restoring a
PV domain a few times, I seem to be getting here with
v-arch.privregs == NULL. I'll see if I can figure out
All of the CPUs exposed to dom0 and domUs are virtual CPUs. Xen
schedules virtual CPUs across the physical CPUs just like a bare metal
OS schedules processes across physical CPUs. The xm top output shows
vCPU processor usage across all the vCPUs in a domain. The CPU% shown
is the percentage
On Thu, 2007-02-08 at 15:42 -0800, David Brown wrote:
So, my dual itanium 2 box running dom0 and 8 domU's, and xm top is
showing that the dom0 and one of the domU's are using %40 each and the
other 7 domU's are showing 10% (this almost sounds like a high school
math problem ;)) is not
You can tune the Xen credit scheduler to effectively do what you're
asking (I think). AFAIK, dom0 already has some scheduling priority.
See here for details on tweaking the credit scheduler:
http://wiki.xensource.com/xenwiki/CreditScheduler
Thanks, I'll take a look at this, for sure...
On Thu, 2007-02-08 at 09:10 -0800, David Brown wrote:
Okay thanks, so this may seem like a dumb question but, if I have 8
other domUs running all with one vcpu is the xen kernel still going to
use the other cpus? and does `xm top` show the current cpu usage for
the system then (all xen cpus)
Hi,
This patch adds localtime setting for PV/IA64 domain.
This will work if xen-unstable 13835 patch is applied.
http://xenbits2.xensource.com/xen-unstable.hg?rev/d609929f1408
Signed-off-by: Atsushi SAKAI [EMAIL PROTECTED]
Any comments are appreciated.
Thanks
Atsushi SAKAI
15 matches
Mail list logo