Alexander Motin wrote:
Just to compare, my Core i7-870 with boxed cooler reports:
31C being idle with tuned power management,
53C being idle without any power management,
85C during `make -j16`.
That system did `make -j16 universe` in about 3 hours AFAIR.
Another data point and a comment about
I know it might seem a bit like overkill but have you put windows or
Linux on this box and tried some basic tests? Might be a way to
eliminate so sort of hardware failure and not something that's FreeBSD
specific?
Regards
Steve
This e.mail
Yay! I have solved the problem
I got a new BIOS from SuperMicro support, and it has resolved the
performance issues I was seeing. I also no longer have to disable
Legacy USB.
Here's the new improved times for buildworld buildkernel (with -
j12).
19 minutes for world and kernel (with all
Original Message -
From: Bryce br...@bryce.net
Yay! I have solved the problem
I got a new BIOS from SuperMicro support, and it has resolved the
performance issues I was seeing. I also no longer have to disable
Legacy USB.
Here's the new improved times for buildworld
Bryce wrote:
I don't think it is temperature, I have never seen temps above the low
60's C and the speed never goes down from 2.8 Ghz. This is what I see
when running your dd for a while:
br...@tahiti[~]sysctl -a | grep temperature
dev.cpu.0.temperature: 55.0C
dev.cpu.1.temperature: 55.0C
on 23/09/2010 11:26 Alexander Motin said the following:
PS: AFAIK dev.cpu.0.freq won't report you if frequency was lowered due
to overheating.
I think that you are correct about this.
And last I checked we simply ignored thermal throttling interrupt.
--
Andriy Gapon
On 23/09/2010, at 21:26, Andriy Gapon wrote:
on 23/09/2010 11:26 Alexander Motin said the following:
PS: AFAIK dev.cpu.0.freq won't report you if frequency was lowered due
to overheating.
I think that you are correct about this.
And last I checked we simply ignored thermal throttling
On Sep 22, 9:35 am, nickolas...@gmail.com wrote:
md5 -t is quite a small benchmark, even with his misfunctioning CPU it
took 6 seconds to complete.
If his problem is a misapplied heatsink/fan, then his CPU could be
throttling when it gets hot, the hotter it gets the more it throttles,
on 23/09/2010 15:37 Daniel O'Connor said the following:
On 23/09/2010, at 21:26, Andriy Gapon wrote:
on 23/09/2010 11:26 Alexander Motin said the following:
PS: AFAIK dev.cpu.0.freq won't report you if frequency was lowered due
to overheating.
I think that you are correct about this.
And
On Thu, 23 Sep 2010, Alexander Motin wrote:
Bryce wrote:
I don't think it is temperature, I have never seen temps above the low
60's C and the speed never goes down from 2.8 Ghz. This is what I see
when running your dd for a while:
br...@tahiti[~]sysctl -a | grep temperature
Ian Smith wrote:
So not looking much like overheating. But don't these messages requoted
below seem at all significant? At least, I've never seen them before:
est0: Enhanced SpeedStep Frequency Control on cpu0
est0: Invalid id16 (set, cur) = (20, 21)
est0: Can't check freq 2667, it may
On Thu, 23 Sep 2010, Alexander Motin wrote:
Date: Thu, 23 Sep 2010 19:42:29 +0300
From: Alexander Motin m...@freebsd.org
To: Ian Smith smi...@nimnet.asn.au
Cc: Bryce br...@bryce.net, FreeBSD Stable freebsd-stable@FreeBSD.org
Subject: Re: SuperMicro i7 (UP) - very slow performance
Just wanted to follow up and show what things looks like in the
'building everything' part of build world. It has been running almost
23 hours...
br...@tahiti[~]vmstat 1
procs memory pagedisks
faults cpu
r b w avmfre flt re pi pofr sr da0
On 2010-Sep-21 20:02:09 -0700, Bryce br...@bryce.net wrote:
On Sep 20, 6:17 am, peterjer...@acm.org (Peter Jeremy) wrote:
On 2010-Sep-18 08:32:32 -0500, Bryce Edwards br...@bryce.net wrote:
I have a Supermicro with the C7X58 motherboard and an i7 930 cpu, and
it is nowhere near the performance
On Wed, Sep 22, 2010 at 3:12 AM, Peter Jeremy peterjer...@acm.org wrote:
I think something is badly wrong here. That's less than 1/2 the speed
of my Athlon 4850e (2.5GHz) and only 60% more than my Atom N270. None
of the other figures you posted look anomolous. Are you sure the CPU
is
On Wed, Sep 22, 2010 at 03:30:33AM -0500, Adam Vande More wrote:
On Wed, Sep 22, 2010 at 3:12 AM, Peter Jeremy peterjer...@acm.org wrote:
I think something is badly wrong here. That's less than 1/2 the speed
of my Athlon 4850e (2.5GHz) and only 60% more than my Atom N270. None
of the
On 2010-Sep-22 01:43:10 -0700, Jeremy Chadwick free...@jdc.parodius.com wrote:
To the OP:
...
4) Check the CPU core temperature (via coretemp(4) or similar) and make
sure the heatsink is correctly attached.
--
Peter Jeremy
pgp049hzGw1N5.pgp
Description: PGP signature
On Wed, 22 Sep 2010 18:12:30 +1000, Peter Jeremy wrote:
On 2010-Sep-21 20:02:09 -0700, Bryce br...@bryce.net wrote:
On Sep 20, 6:17 am, peterjer...@acm.org (Peter Jeremy) wrote:
On 2010-Sep-18 08:32:32 -0500, Bryce Edwards br...@bryce.net wrote:
I have a Supermicro with the C7X58
On Wednesday, September 22, 2010 4:43:10 am Jeremy Chadwick wrote:
On Wed, Sep 22, 2010 at 03:30:33AM -0500, Adam Vande More wrote:
On Wed, Sep 22, 2010 at 3:12 AM, Peter Jeremy peterjer...@acm.org wrote:
I think something is badly wrong here. That's less than 1/2 the speed
of my
On Wed, Sep 22, 2010 at 2:50 PM, Ian Smith smi...@nimnet.asn.au wrote:
It seems far more than just CPU performance is awry. Adam's data from
his i7 shows 2.7 times Bryce's speed for the md5 -t, maybe a lower EST
rate? - but that could no way account for buildworld taking 22.5 hours.
Recent
md5 -t is quite a small benchmark, even with his misfunctioning CPU it
took 6 seconds to complete.
If his problem is a misapplied heatsink/fan, then his CPU could be
throttling when it gets hot, the hotter it gets the more it throttles,
which could explain his massive buildworld walltime.
On Wed, 22 Sep 2010, Tom Evans wrote:
On Wed, Sep 22, 2010 at 2:50 PM, Ian Smith smi...@nimnet.asn.au wrote:
It seems far more than just CPU performance is awry. Adam's data from
his i7 shows 2.7 times Bryce's speed for the md5 -t, maybe a lower EST
rate? - but that could no way
On Sep 22, 11:43 am, smi...@nimnet.asn.au (Ian Smith) wrote:
On Wed, 22 Sep 2010, Tom Evans wrote:
On Wed, Sep 22, 2010 at 2:50 PM, Ian Smith smi...@nimnet.asn.au wrote:
It seems far more than just CPU performance is awry. Adam's data from
his i7 shows 2.7 times Bryce's speed for the
On Sep 22, 3:43 am, free...@jdc.parodius.com (Jeremy Chadwick) wrote:
On Wed, Sep 22, 2010 at 03:30:33AM -0500, Adam Vande More wrote:
On Wed, Sep 22, 2010 at 3:12 AM, Peter Jeremy peterjer...@acm.org wrote:
I think something is badly wrong here. That's less than 1/2 the speed
of my
On Wed, Sep 22, 2010 at 05:54:46PM -0700, Bryce wrote:
On Sep 22, 3:43 am, free...@jdc.parodius.com (Jeremy Chadwick) wrote:
On Wed, Sep 22, 2010 at 03:30:33AM -0500, Adam Vande More wrote:
On Wed, Sep 22, 2010 at 3:12 AM, Peter Jeremy peterjer...@acm.org wrote:
I think something is
On Sep 20, 6:17 am, peterjer...@acm.org (Peter Jeremy) wrote:
On 2010-Sep-18 08:32:32 -0500, Bryce Edwards br...@bryce.net wrote:
I have a Supermicro with the C7X58 motherboard and an i7 930 cpu, and
it is nowhere near the performance it should be. A buildworld just
took 22.5 hours!
That
On 2010-Sep-18 08:32:32 -0500, Bryce Edwards br...@bryce.net wrote:
I have a Supermicro with the C7X58 motherboard and an i7 930 cpu, and
it is nowhere near the performance it should be. A buildworld just
took 22.5 hours!
That does sound a bit poor. I presume the system was basically unloaded
I have a Supermicro with the C7X58 motherboard and an i7 930 cpu, and
it is nowhere near the performance it should be. A buildworld just
took 22.5 hours!
br...@tahiti[~]uname -a
FreeBSD tahiti.bryce.net 8.1-STABLE FreeBSD 8.1-STABLE #0: Tue Sep 7
22:45:38 CDT 2010
On Sat, Sep 18, 2010 at 08:32:32AM -0500, Bryce Edwards wrote:
I have a Supermicro with the C7X58 motherboard and an i7 930 cpu, and
it is nowhere near the performance it should be. A buildworld just
took 22.5 hours!
I use 5046A-XB with i7-930 as home workstation, running latest RELENG_8,
and
29 matches
Mail list logo
