Re: CPU temp -- LONG
From: Floyd L. Davidson (floyd_at_barrow.com)
Date: 10/30/04
- Previous message: Michael Heiming: "Re: ext3 remount read-only"
- In reply to: Jean-David Beyer: "Re: CPU temp -- LONG"
- Next in thread: Jean-David Beyer: "Re: CPU temp -- LONG"
- Reply: Jean-David Beyer: "Re: CPU temp -- LONG"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Date: Fri, 29 Oct 2004 16:01:39 -0800
Jean-David Beyer <jdbeyer@exit109.com> wrote:
>Floyd L. Davidson wrote:
>> Jean-David Beyer <jdbeyer@exit109.com> wrote:
...
>> First, look in /sys/bus/{i2c | isa}/drivers, to find
>> essentially
>> a list of drivers which have been correctly loaded to supply
>> information that lm_sensors can read. (Assuming a 2.6 kernel
>> and the sysfs pseudo filesystem is mounted.)
>
>Both assumptions incorrect.
>
>$ uname -r
>2.4.21-20.ELsmp
It was the OP who said he was running a 2.6 kernel. You clearly
are not.
Upgrade, and we'll talk about this tomorrow??? ;-)
>Do you mean in here?
>$ ls -l /proc/bus
I don't remember now the exact setup for a 2.4 kernel. I don't
recall that there is a /proc file to obtain the data from, and
seem to recall that sensors was only able to read from a device
special file?? It wasn't nearly as nice as 2.6 is...
Obviously I'm not much help at all with a 2.4 lm_sensors setup.
>My motherboard is SuperMicro X5DP8-G2.
>
>http://www.supermicro.com/products/motherboard/Xeon/E7501/X5DP8-G2.cfm
Hmmmm... as you are well aware, they aren't very informative in
their documentation! It doesn't mention the chip nor does it
even mention the i2c or smbus. Worse yet, I did a bit of
searching, and found nothing except you and I discussing this in
August. (I learned a whole bunch since then, because you got me
interested in lm_sensors again... :-)
The only indication that I could find which suggests there is
more to it than you have discovered is the fact that they claim
there are 6 fans with tachometer monitoring. That is odd simply
because the W83627HF chip can't monitor 6 fans..., only 3. It
also appears they are controlling 3 or 4 fans, but that chip can
only control 2. The number of voltages monitored is within the
range of one chip. I'm not sure what they have. You might want
to take a look some time and see if there is another winbond
chip on the board...
>$ cat /proc/modules
>w83781d 22672 0
>i2c-proc 9232 0 [w83781d]
>i2c-isa 1836 0 (unused)
>i2c-core 19300 0 [w83781d i2c-proc i2c-isa]
That is interesting. There are some differences between the
modules for 2.4 kernels and 2.6 kernels. I'm not sure that I
remember all the details though.
>> Hence, if a given setup for lm_sensors is only measuring two
>> fans and two temperatures, but there are data files for four of
>> each and the BIOS is reporting four... the right configuration
>> for modules and for /etc/sensors.conf will provide more
>> information.
>
>Two fans, three temperatures.
The manual says it has 6 fans with tachometer monitoring. I'm
at a loss to see how they do that, without another chip.
>I have a crontab entry that runs "sensors" every 15 minutes and
>appends them to a file that I trim off the old stuff from time
>to time. The "System" temperature does not seem to vary much for
>a constant room temperature. I did note that the power supply
>fans, and the processor fans did speed up considerably
>(temperature controlled fans) when the main input fan seized
Are those fans controlled by the motherboard, or do they have
onboard sensors?
The W83627HF can monitor 3 fans and control 2, so they could all
be handled that way, even though there are only 3 temperature
sensing inputs on the W83627HF
>up. I do not think the sensors are drifting all that much.
But all totaled, between the thermistor drift, the chip drift,
etc., it can add up to a noticeable variation.
>> What I'm doing is plotting graphs of all voltages and
>> temperatures. Under the directory "tellerstats" in the
>> lm_sensors distribution is an example using gnuplot to generate
>> a web page. I've modified that and enhanced it significantly,
>> and the results, plus a link to the scripts that produced these
>> graphs, are shown at this URL,
>> http://web.newsguy.com/floyd_davidson/sensors/
>
>I am curious about the 1-hour "spikes" in all the temperatures...
Hee hee. A forced air furnace. The 12volt rail and all of the
temperatures march up and down in lock step!
>> That looks pretty good. I'd recommend changing the fan divisor
>> to 8 though. You'll get better resolution, particularly at
>> lower speeds.
>
>I changed it to 4 for a while. My log has not yet picked it up,
>but here is what it normally looks like, for one fan:
>
>CPU0 fan: 2909 RPM (min = 1500 RPM, div = 2)
>CPU0 fan: 2934 RPM (min = 1500 RPM, div = 2)
Here's the problem. This is a table found in the
.../doc/fan-divisors or the lm_sensors package for the 2.6
kernel,
Fan Divisor Minimum RPM Maximum RPM
----------- ----------- -----------
1 5314 1350000
2 2657 675000 default on most chips
4 1328 337500
8 664 168750
16 332 84375 not supported on most chips
32 166 42187 ""
64 83 21093 ""
128 41 10546 ""
With a divisor of 2 you *can't* read anything less than 2657
rpm. The maximum rpm is way up there, but that isn't exactly
useful! The max that can be set is 8, giving a range of 664 to
168750, which is still a waste on the high end, but at least
gives a more reasonable low end.
>I am not sure if more resolution is any use, though. OK: here
>are the latest readings:
>
>CPU0 fan: 2722 RPM (min = 750 RPM, div = 4)
>CPU1 fan: 2192 RPM (min = 750 RPM, div = 4)
Two things: obviously you *do* want to see values lower than
2657! But also note the subtle bug in the program! The minimum
rpm limit is also changed by the divisor. With the package for
the 2.6 kernel that was fixed, and it will stay the same
regardless of the divisor.
I'd set that to 8, and adjust the minimum rpm limits
accordingly. When you upgrade to a 2.6 kernel that will change.
>> It appears that you are loading the w83627hf module, and thus
>> using the LPC (ISA) bus to access the W83627HF chip. Is that
>> necessary, or is it also connected to the i2c bus? The w83781d
>> module will provide W83627HF data via the i2c bus. I would
>> suspect that if your BIOS is seeing more than lm_sensors you
>> might find that there is either a second W83627HF Super I/O chip
>> or more likely an additional dedicated hardware monitor chip
>> like the W83782D (I.e., the same arrangement Tyan boards use.)
>> In any case, accessing via the i2c bus is probably preferred,
>> even though accessing it can be more complicated (especially
>> if there are multiple chips to access).
>>
>I could not get it to work that way. It was a fight to get them
>to work at all. A needed module would not load, and I could not
>figure out what parameters it would need to get it to load, so I
>gave up on that.
I recall having fun getting it to work prior to the 2.6 kernel.
It was a pain. The new interface is nice.
>> I assume you are talking about the "System" temperature, as
>> opposed to the CPU temps. The fan speed should be controlled by
>> the cpu temperature. The exhaust temperature is of little
>> value...
>>
>The fans are 60mm x 38mm fans supplied by Intel. The sensor is
>in the usual place for such fans, so they measure the air
>temperature going into the fan (and from there to the heat
>sink), which is probably closely related to system temperature
>(I do not know where the sensor is).
I don't know what "the usual place for such fans" is! I've never
seen a fan with an embedded temperature sensor. Only ones with
tachometer outputs and with LEDs to make the look cute.
The sensor that lm_sensors is reading is inside the CPU core
itself, and that is probably what is being used to control the
fans.
...
>coming out of the heat sinks. But the measured CPU temperatures
>does not seem to vary much as the System temperature goes
>up. But the CPU fans sure do speed up.
That sounds as if the W83627HF chip is using the core temperature
of the CPU's to control the fan speed, and it is working quite well!
Well enough that even when the "System" probe gets warmer (perhaps
meaning that the ambient temperature is warmer), the fans still keep
the CPU's at the same temperature by running faster... just like
they are supposed to do.
>> Interesting! I'm not set up to monitor power, and maybe that
>> would be useful to add. Right now I have the onboard hardware
>> monitoring chips, plus a Crystalfontz CFA-633 temperature monitor
>> and fan controller device (a *great* toy!).
>
>The way I measure power consumption is that my APC Smart-UPS
>2200 will give the percent capacity it is running at, and the
>computer runs at about 23.4% of capacity when four setiathome
>processes are running (that is what it is doing now). If I stop
>them, it drops to 14.5%. So the power changes A LOT depending on
Maybe I'll poke around a bit and see what it would take to
inductively sample the incoming AC line. It certainly could
be done, it's just a matter of if it can be done for peanuts or
if it would cost me an arm or a leg.
>CPU load. Also the temperature of the air coming out the exhaust
>fans of the box are noticeably warmer with the processors fully
>loaded. I was wrong when I thought it was 30% more; seems it is
>about 60% more. Those two 90 watt processors sure take a lot of
>power. I think I was right to put a fan in every fan location in
>the box. The box is AddTronics 7896A.
If it doesn't make more noise than you can stand... you don't
have enough fan! (I'm about to water cool the noisiest of my
two Tyan boards. I probably won't be able to go to sleep for
a week when I turn those jet engines off... ;-)
-- FloydL. Davidson <http://web.newsguy.com/floyd_davidson> Ukpeagvik (Barrow, Alaska) floyd@barrow.com
- Previous message: Michael Heiming: "Re: ext3 remount read-only"
- In reply to: Jean-David Beyer: "Re: CPU temp -- LONG"
- Next in thread: Jean-David Beyer: "Re: CPU temp -- LONG"
- Reply: Jean-David Beyer: "Re: CPU temp -- LONG"
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Relevant Pages
|
