Hi, chen
After I set up COLO between PVM and SVM.
I get this ERROR occasionally: qemu-system-x86_64: net/colo-compare.c:823:
colo_compare_handle_event: Assertion `event_unhandled_count > 0' failed, on
PVM side.
I think assert(event_unhandled_count ) should be protected by event_mtx in
co
These are the "compatibility" lists I know of:
- https://passthroughpo.st/vfio-increments/
-
https://docs.google.com/spreadsheets/d/1LnGpTrXalwGVNy0PWJDURhyxa3sgqkGXmvNCIvIMenk/view#gid=2
They are focused on desktop hardware and GPU passthrough, because that's
what most people use VFIO for s
Yes, I get it, thanks. Any way to find out if a given hardware supports
VFIO?
regards, Lars
On Wed, Apr 10, 2019, 20:56 Jakob Bohm wrote:
> As I wrote, qemu can pass disks (and disk partitions) through without
> passing the disk controller through. To qemu, a physical disk is just
> another vi
As I wrote, qemu can pass disks (and disk partitions) through without
passing the disk controller through. To qemu, a physical disk is just
another virtual disk storage format.
But if you want to pass through an entire PCI disk controller (with all
its disks) for faster I/O, then VFIO is needed.
I want to pass local disks to a VM in order to run freenas or similar.
Regards, Lars.
On Wed, Apr 10, 2019, 20:20 Jakob Bohm wrote:
> If you pass through the disk access to your SAN partitions as disk
> accesses to block devices (such as SAN client drivers) in the host
> machine, you don't need
If you pass through the disk access to your SAN partitions as disk
accesses to block devices (such as SAN client drivers) in the host
machine, you don't need VFIO for that. This can handle nearly
unlimited number of virtual machines without running out of PCI
slots in the host machine. This is t
But for sure I want passthru - for running virtualized SAN and such
Any unofficial list?
Regards, Lars.
On Wed, Apr 10, 2019, 18:58 Friedrich Oslage
wrote:
> As long as it's VT-x capable and can run Linux, you're good to go.
>
> It only gets tricky once you start using VFIO (direct passthrough
As long as it's VT-x capable and can run Linux, you're good to go.
It only gets tricky once you start using VFIO (direct passthrough of
host PCI devices to a VM, such as GPUs, NICs or NVMes for instance). You
need VT-d support for that and both the CPU and mainboard have to
support it. And not
Okay, more clear report:
$ lsblk -do NAME,ROTA,DISC-GRAN
El 10/4/19 a les 14:12, Pascal ha escrit:
> I would tend to say that "discard" is not related to "ssd" while "rotational"
> is...
>
> Le mer. 10 avr. 2019 à 14:06, Pascal a écrit :
>
>> lsblk -ndo ROTA /dev/sda
>>
>> sorry for the bad co
So I am coming from the VMware world (with comprehensive compatibillity
lists) but about to start a project with KVM/Qemu and I would like to setup
an inexpensive test setup for this purpose.
I am thinking of buying one of SuperMicros IoT-servers like
https://www.supermicro.com/products/system/Min
I would tend to say that "discard" is not related to "ssd" while "rotational"
is...
Le mer. 10 avr. 2019 à 14:06, Pascal a écrit :
> lsblk -ndo ROTA /dev/sda
>
> sorry for the bad copy.
>
> Le mer. 10 avr. 2019 à 12:52, Narcis Garcia a
> écrit :
>
>> Can be this rotational detection be affectin
lsblk -ndo ROTA /dev/sda
sorry for the bad copy.
Le mer. 10 avr. 2019 à 12:52, Narcis Garcia a
écrit :
> Can be this rotational detection be affecting in this case?
>
> https://lists.openvz.org/pipermail/users/2019-April/007564.html
> (Devuan 1.0 VM with distro kernel succeeds with lsblk and fs
Can be this rotational detection be affecting in this case?
https://lists.openvz.org/pipermail/users/2019-April/007564.html
(Devuan 1.0 VM with distro kernel succeeds with lsblk and fstrim)
How can I make guest OS to detect device as no rotational or true SSD?
El 10/4/19 a les 12:47, Narcis Gar
Pascal, I don't understand syntax you use for lsblk.
I see this with:
$ cat /sys/block/sda/queue/rotational
El 10/4/19 a les 12:38, Pascal ha escrit:
> it's ok with discard=unmap option (even if the disc is thick-provisioned)
> : the block used by the test file appears (VM side) or is reset (
it's ok with discard=unmap option (even if the disc is thick-provisioned)
: the block used by the test file appears (VM side) or is reset (host
side) at zero.
notice that lsblk "thinks" that the disc is a rotational disk (eg. not
really SSD) :
lsblk -ndo /dev/sda
1
thanks for explanations
15 matches
Mail list logo
