* Re: Statistics at the host for network nic that was PCI-Passthrough
@ 2014-04-14 9:32 Shimon Zadok
2014-04-14 9:35 ` Ian Campbell
0 siblings, 1 reply; 7+ messages in thread
From: Shimon Zadok @ 2014-04-14 9:32 UTC (permalink / raw)
To: Ian Campbell; +Cc: Xen-Developement
-------- Original Message --------
Subject: Re: [Xen-devel] Statistics at the host for network nic that
was PCI-Passthrough
Date: 14-04-2014 12:30
From: Shimon Zadok <shimonz@startpo.co.il>
To: Ian Campbell <Ian.Campbell@citrix.com>
Is it possible to write an extension to pciback to load a module
specific to that h/w?
It could be a new driver for that hardware that operates by itself for
reading these statistics from the nic...
On 14-04-2014 12:10, Ian Campbell wrote:
> On Mon, 2014-04-14 at 11:16 +0300, Shimon Zadok wrote:
>> For the case of a network nic that was PCI-Passthrough to a VM.
>>
>> Does the pciback or some API can enable the read of ethtool-like
>> statistics?
>
> These stats are h/w specific so generally only the driver within the
> guest would know how to extract them.
>
> Ian.
>
>
>
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xen.org
> http://lists.xen.org/xen-devel
--
Shimon Zadok
Startpo
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: Statistics at the host for network nic that was PCI-Passthrough
2014-04-14 9:32 Statistics at the host for network nic that was PCI-Passthrough Shimon Zadok
@ 2014-04-14 9:35 ` Ian Campbell
2014-04-14 11:43 ` Shimon Zadok
0 siblings, 1 reply; 7+ messages in thread
From: Ian Campbell @ 2014-04-14 9:35 UTC (permalink / raw)
To: Shimon Zadok; +Cc: Xen-Developement
On Mon, 2014-04-14 at 12:32 +0300, Shimon Zadok wrote:
>
> -------- Original Message --------
> Subject: Re: [Xen-devel] Statistics at the host for network nic that
> was PCI-Passthrough
> Date: 14-04-2014 12:30
> From: Shimon Zadok <shimonz@startpo.co.il>
> To: Ian Campbell <Ian.Campbell@citrix.com>
>
> Is it possible to write an extension to pciback to load a module
> specific to that h/w?
> It could be a new driver for that hardware that operates by itself for
> reading these statistics from the nic...
Then you would have uncoordinated accesses to the hardware from two
domains. That might work for some hardware I suppose but it certainly
isn't a good idea in general.
You'd be better off building something in the domu to export the stats
e.g. via xenstore. It could be entirely userspace I expect.
Ian.
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: Statistics at the host for network nic that was PCI-Passthrough
2014-04-14 9:35 ` Ian Campbell
@ 2014-04-14 11:43 ` Shimon Zadok
2014-04-14 11:44 ` Ian Campbell
0 siblings, 1 reply; 7+ messages in thread
From: Shimon Zadok @ 2014-04-14 11:43 UTC (permalink / raw)
To: Ian Campbell; +Cc: Xen-Developement
[-- Attachment #1.1: Type: text/plain, Size: 1397 bytes --]
The guest is not in my control. Use case is: user uploads a Guest VM he made by himself...
It could be the case that I give him an sr-iov (vf) by pci-passthrough or a pci device (not vf). I would still like to get a sense of the pci at the host level...
On April 14, 2014 12:35:01 PM GMT+02:00, Ian Campbell <Ian.Campbell@citrix.com> wrote:
>On Mon, 2014-04-14 at 12:32 +0300, Shimon Zadok wrote:
>>
>> -------- Original Message --------
>> Subject: Re: [Xen-devel] Statistics at the host for network nic that
>> was PCI-Passthrough
>> Date: 14-04-2014 12:30
>> From: Shimon Zadok <shimonz@startpo.co.il>
>> To: Ian Campbell <Ian.Campbell@citrix.com>
>>
>> Is it possible to write an extension to pciback to load a module
>> specific to that h/w?
>> It could be a new driver for that hardware that operates by itself
>for
>> reading these statistics from the nic...
>
>Then you would have uncoordinated accesses to the hardware from two
>domains. That might work for some hardware I suppose but it certainly
>isn't a good idea in general.
>
>You'd be better off building something in the domu to export the stats
>e.g. via xenstore. It could be entirely userspace I expect.
>
>Ian.
>
>
>
>_______________________________________________
>Xen-devel mailing list
>Xen-devel@lists.xen.org
>http://lists.xen.org/xen-devel
--
Sent from my Android phone with K-9 Mail. Please excuse my brevity.
[-- Attachment #1.2: Type: text/html, Size: 1913 bytes --]
[-- Attachment #2: Type: text/plain, Size: 126 bytes --]
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: Statistics at the host for network nic that was PCI-Passthrough
2014-04-14 11:43 ` Shimon Zadok
@ 2014-04-14 11:44 ` Ian Campbell
2014-04-14 11:52 ` Andrew Cooper
0 siblings, 1 reply; 7+ messages in thread
From: Ian Campbell @ 2014-04-14 11:44 UTC (permalink / raw)
To: Shimon Zadok; +Cc: Xen-Developement
Please don't top post.
On Mon, 2014-04-14 at 14:43 +0300, Shimon Zadok wrote:
> The guest is not in my control. Use case is: user uploads a Guest VM
> he made by himself...
> It could be the case that I give him an sr-iov (vf) by pci-passthrough
> or a pci device (not vf). I would still like to get a sense of the pci
> at the host level...
I'm afraid that AFAIK this is not possible without guest (admin)
cooperation.
Ian.
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: Statistics at the host for network nic that was PCI-Passthrough
2014-04-14 11:44 ` Ian Campbell
@ 2014-04-14 11:52 ` Andrew Cooper
0 siblings, 0 replies; 7+ messages in thread
From: Andrew Cooper @ 2014-04-14 11:52 UTC (permalink / raw)
To: Ian Campbell; +Cc: Shimon Zadok, Xen-Developement
On 14/04/14 12:44, Ian Campbell wrote:
> Please don't top post.
>
> On Mon, 2014-04-14 at 14:43 +0300, Shimon Zadok wrote:
>> The guest is not in my control. Use case is: user uploads a Guest VM
>> he made by himself...
>> It could be the case that I give him an sr-iov (vf) by pci-passthrough
>> or a pci device (not vf). I would still like to get a sense of the pci
>> at the host level...
> I'm afraid that AFAIK this is not possible without guest (admin)
> cooperation.
>
> Ian.
For some SRIOV devices, there is vf accounting available from the pf,
but this is hardware and driver dependent.
For non SRIOV, all bets are off in this regard.
~Andrew
^ permalink raw reply [flat|nested] 7+ messages in thread
* Statistics at the host for network nic that was PCI-Passthrough
@ 2014-04-14 8:16 Shimon Zadok
2014-04-14 9:10 ` Ian Campbell
0 siblings, 1 reply; 7+ messages in thread
From: Shimon Zadok @ 2014-04-14 8:16 UTC (permalink / raw)
To: xen-devel
For the case of a network nic that was PCI-Passthrough to a VM.
Does the pciback or some API can enable the read of ethtool-like
statistics?
--
Shimon Zadok
Startpo
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: Statistics at the host for network nic that was PCI-Passthrough
2014-04-14 8:16 Shimon Zadok
@ 2014-04-14 9:10 ` Ian Campbell
0 siblings, 0 replies; 7+ messages in thread
From: Ian Campbell @ 2014-04-14 9:10 UTC (permalink / raw)
To: Shimon Zadok; +Cc: xen-devel
On Mon, 2014-04-14 at 11:16 +0300, Shimon Zadok wrote:
> For the case of a network nic that was PCI-Passthrough to a VM.
>
> Does the pciback or some API can enable the read of ethtool-like
> statistics?
These stats are h/w specific so generally only the driver within the
guest would know how to extract them.
Ian.
^ permalink raw reply [flat|nested] 7+ messages in thread
end of thread, other threads:[~2014-04-14 11:52 UTC | newest]
Thread overview: 7+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2014-04-14 9:32 Statistics at the host for network nic that was PCI-Passthrough Shimon Zadok
2014-04-14 9:35 ` Ian Campbell
2014-04-14 11:43 ` Shimon Zadok
2014-04-14 11:44 ` Ian Campbell
2014-04-14 11:52 ` Andrew Cooper
-- strict thread matches above, loose matches on Subject: below --
2014-04-14 8:16 Shimon Zadok
2014-04-14 9:10 ` Ian Campbell
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.