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

Re: [Xen-devel] [PATCH RFC] x86/smpboot: Set safer __max_logical_packages limit



On 20/04/17 16:06, Peter Zijlstra wrote:
> On Thu, Apr 20, 2017 at 03:24:53PM +0200, Vitaly Kuznetsov wrote:
>> In this patch I suggest we set __max_logical_packages based on the
>> max_physical_pkg_id and total_cpus,
> So my 4 socket 144 CPU system will then get max_physical_pkg_id=144,
> instead of 4.
>
> This wastes quite a bit of memory for the per-node arrays. Luckily most
> are just pointer arrays, but still, wasting 140*8 bytes for each of
> them.
>
>> this should be safe and cover all
>> possible cases. Alternatively, we may think about eliminating the concept
>> of __max_logical_packages completely and relying on max_physical_pkg_id/
>> total_cpus where we currently use topology_max_packages().
>>
>> The issue could've been solved in Xen too I guess. CPUID returning
>> x86_max_cores can be tweaked to be the lowerest(?) possible number of
>> all logical packages of the guest.
> This is getting ludicrous. Xen is plain broken, and instead of fixing
> it, you propose to somehow deal with its obviously crack induced
> behaviour :-(

Xen is (and has been forever) plain broken in this specific regard. 
Fixing CPUID handling for guests has taken me 18 months and ~80 patches
so far, and it still isn't complete.

However, Linux needs to be able to function on existing production
systems (which is every instance of Xen currently running).

Linux shouldn't BUG() because something provided by the firmware looks
wonky.  This is conceptually no different from finding junk the APCI tables.

(I fully agree that we shouldn't have got to this state, but we are 12
years too late in this respect.)

~Andrew

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
https://lists.xen.org/xen-devel

 


Rackspace

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