George,
Thank you for all the information. I'll take a dive in and see what I can see.
I'd at least like to get the CPU core frequency detection in as that will
make things a lot easier for us as we port to multiple platforms with
different cores. Then we don't have to keep looking up core speeds.
Paul,
>see the patch attached. It's a bit dirty still (that's why it wasn't
>upstreamed
>long time ago), but you can obviously look through it and gain some
>information.
Thanks, I’ll take a look and compare it against
mine to make sure we capture everything.
Ben
Hi Ben,
see the patch attached. It's a bit dirty still (that's why it wasn't
upstreamed long time ago), but you can obviously look through it and gain
some information.
On 8 March 2016 at 22:51, Ben Sanda wrote:
> George,
>
> >FWIW, on my "to-do" list for xenalyze for years has been to have the
On Tue, 2016-03-08 at 18:32 +, Andrew Cooper wrote:
> On 08/03/16 18:28, Paul Sujkov wrote:
> > Regarding ARM build, I'm using xenalyze as both host tool (x86
> > build, e.g. for gnuplot scatterplot graphs) and target tool (ARM,
> > for fast summary check); but since we're working with Xen 4.5,
On 08/03/16 20:51, Ben Sanda wrote:
> George,
>
>> FWIW, on my "to-do" list for xenalyze for years has been to have the xentrace
>> process query something (either Xen or Linux) to find the hz rate, and then
>> write that at the beginning of the xentrace file, so that xenalyze could just
>> pick t
George,
>FWIW, on my "to-do" list for xenalyze for years has been to have the xentrace
>process query something (either Xen or Linux) to find the hz rate, and then
>write that at the beginning of the xentrace file, so that xenalyze could just
>pick that up and use it. Since you're doing some work
On 08/03/16 18:04, Ben Sanda wrote:
> All,
>
> To update to the current situation. I have been able to get xentrace() and
> xenalyze working completely (at least as far as I can tell) on ARM.
>
> For xentrace there were changes to the memory allocation routines to allow
> mapping of the Xen Heap
On 08/03/16 18:28, Paul Sujkov wrote:
> Hi Ben,
>
> looks like you've done everything I did. I'm far from my working
> laptop today, so I can post my work on this issue only tomorrow so you
> can look through the code, compare and estimate solutions.
>
> Regarding ARM build, I'm using xenalyze as b
Hi Ben,
looks like you've done everything I did. I'm far from my working laptop
today, so I can post my work on this issue only tomorrow so you can look
through the code, compare and estimate solutions.
Regarding ARM build, I'm using xenalyze as both host tool (x86 build, e.g.
for gnuplot scatter
On Tue, 2016-03-08 at 18:04 +, Ben Sanda wrote:
> All,
>
> To update to the current situation. I have been able to get
> xentrace() and
> xenalyze working completely (at least as far as I can tell) on ARM.
>
Great! :-)
> For xentrace there were changes to the memory allocation routines to
>
All,
To update to the current situation. I have been able to get xentrace() and
xenalyze working completely (at least as far as I can tell) on ARM.
For xentrace there were changes to the memory allocation routines to allow
mapping of the Xen Heap by dom0, correcting the MFN->PFN translations, add
[Adding (back?) George, which wrote and maintains xenalyze, and tracing
in general, and adding ARM people as well, because this is on ARM,
isn't it?]
On Mon, 2016-03-07 at 19:36 +, Ben Sanda wrote:
> it was in a mercurial repo here:
> http://xenbits.xensource.com/ext/xenalyze.hg
>
> but th
Paul,
Thank you very much for the reply. I’ll check out the fork for xenalyze.
I believe I have xentrace working now, mostly, but if possible I’d like to
see what you did on your build to get it working to compare. I
would like to push a patch into the mainline that agrees with both
of our effor
Dario,
I gleamed enough information from Paul's posts that I now have xentrace
outputting data (I don't know if it's correct data or gibberish yet though). To
discover this I tried to find the xenalyze tool but have not been able to figure
out how to get it built. According to the old documentatio
Hi Ben,
sorry for the delayed answer. There is xenalyze fork repo made by RT-Xen
author, Meng Xu:
https://github.com/PennPanda/xen-analyze
apart from some comments and logs it's quite the same tool as it was of Xen
4.5, you can use it while you have troubles with the code in the Xen repo.
Do you
]
Sent: 05 March, 2016 10:43
To: Ben Sanda ; xen-devel@lists.xen.org
Cc: Paul Sujkov
Subject: Re: [Xen-devel] Xentrace on Xilinx ARM
On Fri, 2016-03-04 at 20:53 +, Ben Sanda wrote:
> Hello,
>
Hello,
first of all, please, use plain text instead of HTML for emails to this list.
&
On Fri, 2016-03-04 at 20:53 +, Ben Sanda wrote:
> Hello,
>
Hello,
first of all, please, use plain text instead of HTML for emails to this
list.
> My name is Ben Sanda, I’m a kernel/firmware developer with
> DornerWorks
> engineering. Our team is working on support for Xen on the new Xilinx
Hello,
My name is Ben Sanda, I'm a kernel/firmware developer with DornerWorks
engineering. Our team is working on support for Xen on the new Xilinx
Ultrascale+ MPSoC platforms (ARM A53 core) and I've specifically been tasked
with characterizing performance, particularly that of the schedulers. I w
18 matches
Mail list logo
