[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] Xentrace on Xilinx ARM

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 by dom0, correcting the MFN->PFN translations, adding
> the trace buffer initialization to setup.c (init_trace_bufs), and correcting 
> the
> get_cycles() call to provide the system TSC. For the get_cycles() call I
> gathered that was supposed to return the raw tick count, not a translated
> ticks->real time timestamp. I then had to call xenalyze with the core 
> frequency
> defined so the timestamps made sence.

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 xentrace / xenalyze anyway, you might think about adding that to
your "to-do" list -- it doesn't seem conceptually like it would be that

The other thing that might be useful is information about the
architecture you're running on -- right now it assumes intel, and will
crash tracing a file generated on an AMD box unless you specify
--svm-mode.  Adding a trace record that indicates "Intel / AMD / ARM"
would also make things a lot easier.

> I plan to push they changes in as a patch to the mainline if that seems
> reasonable to everyone.

Yes, please. :-)


Xen-devel mailing list



Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.