Hello !

My (P4-HT) machine computes a sulphur model. It started with 4.09 s/TS on begin of phase 1 and have now reached 6.03 s/TS in the middle of phase 3 (see here: http://climateapps2.oucs.ox.ac.uk/cpdnboinc/trickle.php?resultid=1347636).

Question: Is this a normal behaviour of a sulphur model or should I make myself concerns about this machine?

Regards

Hi there,

I would suggest to suspend BOINC and do some maintanance like disk defragmentation, spyware/adware check etc. and resume BOINC.
It should help...

---

<i>phpBB forum for CPDN, all are </i><a href="http://www.climateprediction.net/board">invited</a>

It shouldn\'t really slow that much.
It\'s possible that there is dust accumulating in the computer, especially on the cpu heatsink. This will cause it to overheat, and the theraml protection circuitry
to cut in and decrease the power to the chip.

Have you cleaned it out lately?
If not, shut down the computer, take it outside, and use a vacuum cleaner to blow out the dust. Keep at it until no more is coming out. And don\'t forget the power supply case. Blowing straight at the top of the cpu heatsink will spin the fan rather fast, but I\'ve never had any problems after.
It only takes a small amount of dust on and in the cooling fins to raise the temperature several degrees.

do some maintanance like disk defragmentation, spyware/adware check etc. and resume BOINC.

Oh my god, it looks like a great \"tohuwabohu\" on the hard disk, spyware also found. Mmh, I thought, my Norton Antivirus Package already does this spyware check :-(

Ok, I will clear up the hard disk and watch the trickle time (hopefully) speeds up.

Thanx.

It shouldn\'t really slow that much.
It\'s possible that there is dust accumulating in the computer, especially on the cpu heatsink. This will cause it to overheat, and the theraml protection circuitry
to cut in and decrease the power to the chip.

I have an P4 550 processor (prescott), working on 3.4 GHz. As I understood the infos from the Intel WebSite, there is no such way of thermal protection mechanism for this particular processor stepping (F-3-4-D0) (or should I be missed something).

The cpu temperature is in the range from 59-62 degrees Celsius while working on CPDN model, I dont\'t know, if this is to hot.

Whatever, I will watch the trickles after my disk clean action is completed and if this will not help, I have to clean the box from dust.

Regards

Hello Honza and Les Bayliss!

Thank You alot for Your advices.

Whatever it came from, the slowdown is (nearly) away. I only cleared up my hard disk, no other change was made.

The last trickle (occured some minutes ago) showed me a sec/TS value of ca. 4.57, relative to the last trickle, which has 8.01 sec/TS.

I made some calculations, which show me an average 0.03458 sec/TS increase per trickle (total), the average increase relative to the pref trickle is 0.0688 sec/TS.

I can\'t imagine, that a defragmented disk make such a great difference. How many bytes are written to disk during checkpointing ?

Regards

Say the program needs to add a single result to the end of a large file.

First it has to read the file, following (say) 330 broken fragments around in different parts of the disk, then gets to the end, and spends a short time writing it\'s result.

The time spent trawling through the file is far greater than the time actually spent writing the result.

(330 isn\'t a random number - that\'s the number of fragments my CPDN results file was in before I defragged!)

Hence defragging can save an enormous amount of time.

My understanding is that the BBC model probably won\'t be affected so much, but I haven\'t run it yet so can\'t comment for sure.

---

I'm a volunteer and my views are my own.
News and Announcements and FAQ