Re: 50% slowdown on 2 processor XEN 4.1.3 vs 1 processor system

[Dustin Marquess <dmarquess%gmail.com@localhost>]

Somewhat related, I have a Supermicro PDSMi-LN4 that lets you disable
EIST, and you want to, as if you enable it, it messes up the P-states
badly and the CPUs crawl!  No BIOS fix for that at all.

-Dustin

On Fri, Dec 21, 2012 at 5:40 PM, Harry Waddell
<waddell%caravaninfotech.com@localhost> wrote:
> Just a quick followup. It seems that although netbsd-GENERIC could
> control the cpu clock just fine, netbsd-XEN3_DOM0 defers this to the xen 
> kernel,
> which could not. There was also a bug in the MB bios, which would not let me
> disable EIST -- essentially, it always ran at the lowest, rather than the
> highest speed. I tried every motherboard and xen boot option I could think of,
> messed with xenpm, and nothing seemed to help.
>
> So, I convinced my supplier to let me swap it for something that I know
> works correctly, which wasn't hard as he seemed to feel that it was
> going to be very hard to get supermicro to fix this issue. So, if you
> plan to run netbsd and xen, avoid the supermicro X9DR3-F with AMI
> 2.14.x bios. If your case will hold an EE-ATX board, the supermicro
> X9DRi-LN4+ with AMI with 2.15.x bios seems to work as it should.
>
> Thanks to all who helped look into this.
>
> Harry Waddell
>
>
>
>
>
>
>
> On Mon, 26 Nov 2012 23:06:37 -0800
> Harry Waddell <waddell%caravaninfotech.com@localhost> wrote:
>
>> On Tue, 27 Nov 2012 00:09:32 -0600
>> "Cherry G. Mathew" <cherry.g.mathew%gmail.com@localhost> wrote:
>>
>> > On 26 November 2012 03:00, Harry Waddell 
>> > <waddell%caravaninfotech.com@localhost> wrote:
>> > >
>> > > I just built a new server with 2 x E5-2630 processors and was comparing 
>> > > the
>> > > performance to a nearly identical xen server with 1 x E5-1660 processor 
>> > > and
>> > > found that on a per core basis, instead of being about 50% faster ( as 
>> > > one would expect from the clock speed given that the architecture is 
>> > > nearly identical ), the E5-1660 system is %300 faster, so I ran some 
>> > > benchmarks and started looking for a pattern.
>> > >
>> > > Both systems run NetBSD amd64 6.0-STABLE with xen 4.1.3. The 2
>> > > processor system is running only 1/2 as fast with the XEN3_DOM0 kernel
>> >
>> > I hope you realise that NetBSD dom0 is not MP capable ?
>> >
>> > --
>> > ~Cherry
>> >
>>
>> Not only do I know that, but I believe your name is next to that goal on the 
>> xen roadmap. ;-) I did however setup a 24 vcpu domU just to see if it 
>> worked, and I'm glad to say it did.
>>
>> Anyway, yes, all the performance measures I gathered were single threaded. 
>> "top" showed that only one cpu core was engaged. The followup email I sent 
>> earlier today with some sysbench results show that I'm only running single 
>> threaded tests.
>>
>> Please let me know if you think of any info I can supply or any tests I can 
>> run.
>>
>> HW
>>
>>
>>
>>