40C under load on a P4 is just fine. That's cooler than any of my overclocked CPU's have ever run in fact.
Printable View
40C under load on a P4 is just fine. That's cooler than any of my overclocked CPU's have ever run in fact.
I don't think that's too hot at all. My opterons stay at 45-50C all the time. The core2's stay about that hot too :)
I have a AMD 2500+ and it rarely goes above 100F. Of course, I got a HUGE heat sink on it too. I have seen some that run a lot hotter than that and do fine. Shouldn't be a problem unless that specific CPU has a heat issue.
:D :D :D :D
Ok gents, I'm headed for the top 3! The data says Ill be there at around 6 months. But I'm ordering a new server today and I suspect thats gonna drop considerably.
The new machine will have 2x Quad core 2.33Ghz so I should be able to do a bit more units per week.
BTW, has there been any benchmarking on the types of proc/mem/32/64 combinations that crunch those units the fastest? Id be curious.
The server is for work so I wouldn't change it (well. . .).
Cheers
Mike
They go into great depth about benchmarking and optimizing over at the folding forums.
I have the new server up and running and the results show its cranking out the points pretty well.
http://folding.extremeoverclocking.c...hp?s=&u=187463
I actually have another 2way barebones server to add too, so as soon as I get the procs and ram well really be cookin. Are you guys with PS3's out there running the Folding client?
Thanks for the tip on the forums JeFro.
Cheers
Mike
Holy crap! 16000+ points this week and its only Tuesday. This new server is crankin! First place in 3.4 months and I think thats gonna drop too.
m
how do you get started with this stuff I downloaded a folding program but dont know how to get it running
Start here: http://folding.stanford.edu/
Make sure you join team 36480.
Its very simple to start running it. Let us know if you have any trouble.
Cheers
Mike
I think it's as simple as editing your client.cfg file and launching
./foldingathome
bump
I'm still folding.
It's sad to see us slip in the standings. I've watched us move from like 127th place to 170th something place.
Not to worry... it's cyclical. I still think we'll hit the top 100 someday :)
Well, I aquired a Dell Vostro computer with a 64bit E2410(I think), or maybe E2140, core 2 duo processor. It has Winders Vister on it. I bought another hard drive and installed it and then installed Ubuntu 7.10 64bit on that. I go out to folding.stanford.edu and download the 64bit console file. It's a .tgz file. I untarred it, 'tar xzvf', and chmod +x the fah6 file that unzipped. Then I 'chmod 777 fah6'. Then I 'chmod 777 mpi*'.
No matter what I did, I still get 'No such file...." :confused:
It's right there!! :rolleyes:
Any ideas??Code:bs@bs-ubuntu64:~/Desktop/fah64$ ls -la
total 476
drwxr-xr-x 2 bs bs 4096 2008-03-30 16:45 .
drwxr-xr-x 3 bs bs 4096 2008-03-30 16:40 ..
-rwxrwxrwx 1 bs bs 252868 2008-03-26 04:49 fah6
-rw-r--r-- 1 bs bs 139606 2008-03-30 16:40 FAH6.02beta1-Linux.tgz
-rwxrwxrwx 1 bs bs 68492 2007-07-17 06:02 mpiexec
bs@bs-ubuntu64:~/Desktop/fah64$ ./fah6 -smp
bash: ./fah6: No such file or directory
bs@bs-ubuntu64:~/Desktop/fah64$ ./fah6
bash: ./fah6: No such file or directory
bs@bs-ubuntu64:~/Desktop/fah64$
I bet the file's there, but the interpreter isn't, or something like that. What's the first line of the fah6 file, assuming it's a script?
If it isn't a script (file will be useful ;)), then I'm going to guess that since you're using a 64-bit system, you didn't install the 32-bit compatibility stuff, so the runtime linker that the fah6 program is trying to use doesn't exist. But that's just a guess; to find out for sure, you can use readelf -l /path/to/fah6 | grep interpreter, and make sure the interpreter that it requests actually exists on your system. If it's looking for /lib*/ld-linux-x86_64.so.2, then it should be fine, but if it's looking for /lib/ld-linux.so.2, then you'll need to install some 32-bit compatibility packages if you haven't already.
(I don't know how well (or whether) Ubuntu does multi-lib. It may do some kind of crazy chroot setup. You'd have to check their documentation on running 32-bit binaries in their 64-bit setup. Hopefully it'd be easy to do, since there's lots more than just F@H that distributes binaries only, but you never know.)
Thanks for the info bwkaz. The folding console is their 64bit version. The download is tagged like this: Linux (x86-64 bit, only) SMP client console version 6.02 beta1
I wouldn't think I would need any 32bit compatability stuff, but...
Code:bs@bs-ubuntu64:~/Desktop/fah/fah64$ file fah6
fah6: ELF 32-bit LSB executable, Intel 80386, version 1 (SYSV), for GNU/Linux 2.0.0, dynamically linked (uses shared libs), stripped
Code:bs@bs-ubuntu64:~/Desktop/fah/fah64$ readelf -l /home/bs/Desktop/fah/fah64/fah6 | grep interpreter
[Requesting program interpreter: /lib/ld-linux.so.2]
So, I see that it's not telling me that the fah6 file doesn't exist, but rather the /lib/ld-linux.so.2 file doesn't exist.Code:bs@bs-ubuntu64:/lib$ ls -l ld-*
-rwxr-xr-x 1 root root 123376 2007-10-01 11:51 ld-2.6.1.so
lrwxrwxrwx 1 root root 11 2008-03-30 23:05 ld-linux-x86-64.so.2 -> ld-2.6.1.so
I'll have to check around about this 32bit compatability thing.
And... this is a Beta version of the folding console. :rolleyes:
Thanks again... You're always very helpful and detailed.
oh... and so is je_fro! :D
You must have the 32bit libraries installed to execute the fah6 64 bit client. There are details as to why on the FAH site but just do an "apt-get install ia32-libs" and then run it again. Ubuntu has no multi lib issues like mentioned.
The general consensus on dual core procs is to not run the "-smp" option but if you have a quad core the run it like "./fah6 -smp" and it will work on all cores.
Cheers
Mike
Ah, good. Debian used to only support multiple bit-width binaries using a chroot setup (I'm not sure if it still does only work that way though); it's good to see that Ubuntu natively supports multilib via /lib and /lib64. :)Quote:
Originally Posted by techwise
Ok everyone, we are on the threshold of 10,000,000 points for the JL folding team.
Unfortunately we keep loosing ground in the team rankings. I know we can do better. Spread the word and make sure you have folding running on any available idle procs you can get your hands on and maybe we can gain some ground in the team ranks. Remember, it's for a good cause.
Grand Score 9990884
Cheers
Mike
I'll be firing up my new quad core as soon as I find the right overclock, and that should increase my point production quite a bit.
Hey....
I just noticed also that we are about to pass the 10,000,000 milestone. :cool:
I am on my latest acquisition, a notebook with a Core 2 Duo Extreme X7900 2.8Ghz. It's a Dell M1730. (M for Massive!) ;)
It has Windows Vister Ultimate. I'm testing Ubuntu 64bit on another machine. Once I get that sorted out, I may go that route on this machine.
But, I'll never catch mhanson at this rate! :rolleyes:
Hmmm...Quote:
Originally Posted by techwise
I assume this is a repository issue, and I don't know much about repositories with Ubuntu 7.10 64bit. I guess I need to select one or more of the check boxes below. I threw the DVD in but it still didn't find it.Code:bs@bs-ubuntu64:~$ sudo apt-get install ia32-libs
[sudo] password for bs:
Reading package lists... Done
Building dependency tree
Reading state information... Done
E: Couldn't find package ia32-libs
bs@bs-ubuntu64:~$
This is from the Synaptic Package Manager:
http://forums.justlinux.com/images/i.../2008/04/4.jpg
Well, I'm in business. I selected the top 2. Did a Reload in Synaptic. Went from somewhere around 1600 files to over 22,000!! :eek:
ia32-libs was there.
Now I have this: The CPUs seems to be playing pong with the cycles.
http://forums.justlinux.com/images/i.../2008/04/3.jpg
Let me start over, since I misinterpreted what you were asking last time. :)Quote:
Originally Posted by bs_texas
You have two CPUs (well, probably two cores, but close enough). You have a single process running the F@H stuff. That process is bouncing between CPUs from time to time, because that's what Linux does (you can prevent this by setting the affinity of the process, but that can cause bad stuff to happen too, so I wouldn't recommend it).
You have two lines on that graph, one for each CPU. When one isn't running, the other one is (for the most part: there are a few points where some other process wakes up and runs for a short time). That generally just means that a single process is running on each CPU in turn.
If you want to see both of them running at 100% all the time, you can either start another instance of fah6 (if it lets you do that), or tell it to run multiple jobs in parallel on its own. (I don't see any reason they'd recommend against doing this on a dual-core machine, actually. There is no difference (to the OS or user programs anyway) between two "full" CPUs and a single package with two cores in it. So it shouldn't matter one bit.)
Sorry for the delay in getting back to this. But, as I posted in another thread the other day, I found some instructions at the folding website and now both processors (well, cores) are running near 100%, depending on what else is going on.
I have another Core 2 Duo computer on the way. I'll have it up and folding before long. I ordered some Rocks Cluster CD's the other day through linuxcd.org. I'm going to try and cluster my 4 older computers together to work as one.
Here's how we look today:
http://forums.justlinux.com/images/i.../2008/04/1.jpg
I would post the actual link, but for some reason I can't get to folding.extremeoverclocking.com through our proxy. I have to go through pagewash first.
Looks bad for je_fro. ;) But, I'm assuming it's just a lull in the action.
I'll have to shut down for a couple of weeks soon, as I move from Kwajalein to Roi-Namur.
:cool:
Hehe... it's just a lull I assure you! :D
je_fro, at the first of this thread you mentioned clustering 4 P-133's together.
Did you use a clustering distro or just hack out a solution on your own?
Thanks...
Well, I'm about to flat line it here for a couple of weeks while I move. I guess I should apologize in advance here for the sharp down spike we'll see. Maybe some new people can jump in and take up the slack! (hmmm... is there a pun in there?)
I was going to shut it all down today and box it up, but then I see I'm at over 497,000 points. If I can just hold off until tomorrow, maybe I'll hit the half a million points milestone! :eek: (Isn't core 2 duo fun?!)
I followed drobbins' openmosix tutorial over at ibm:Quote:
Originally Posted by bs_texas
http://www.ibm.com/developerworks/es...openmosix.html
Unfortunately openmosix died recently, and I don't know what comes next... those old dell 133's are collecting dust atm :(
Ok, after I fixed some trouble with the RAID array on "silverado", it has been crunching over a week now and I should be at #1 in a few days.
I now have 15 machines folding. Two of them are the workhorses that are made up of 16 cores and 12GB of RAM. And one PS3.
We need more crunchers! Our team keeps dropping positions. Im gonna put up a link on our LUG site and see if I can get some more folders.
Cheers
Mike
He's the Wiz and noooobody beats him!!
:D
My bunch-o-computers is back up and folding. I'll be your wing man...
So, I was contemplating the end of the universe today and then, you know, if there is an end to the universe then what's stopping it, and if there is something stopping it, then, you know, what's behind what's stopping it and ... *
No wait, that was the other day, today I was contemplating Points vs. Work Units. I know I could probably research this, and it may have been answered back up there somewhere in this 600 some odd posts (heck, I may have even already asked this before), but I'm curious about the -value- of points vs. the -value- of work units to the folding process. I assume points is fun to watch and compare, but I would think that completed work units is the thing.
500,000 points looks good, but next to only 2200 work units.... hmmmm...
Comments?
(* from Spinal Tap, of course)
Oh no!
I've lost my coveted 5th place spot which I held for so long.
http://fah-web.stanford.edu/teamstats/team36480.html
Just bumping this post for anyone who hasn't seen it lately.
I guess folding likes my new quad core.:)
/me grumbles....
I've been moving and changing jobs... :(
Looks like I've grabbed that coveted 5th spot. But, it might not last long with cybertron hot on my heels.
Cheer up je_fro. I moved not long ago but I got set back up in short order.
As a team, I've watched us move from about 147th place (as I recall) up to about 180th place. It's the wrong direction, but at least other teams are moving up and the work units are getting done for the folding project.
Adding 3 64bit machines to my arsenal has helped, the rest are older machines and my connection to the internet is 56K dial-up.
Hmmm... I don't know exxactly what happened, but my 2 dual core 64 bit vista machines were running fah in smp mode just fine (I think) then, it seems, all of a sudden I can't send in my results because the .dat files are over 20MB big! And I'm on a 56k dial up behind a proxy that disconnectes me every 4 hours!
I think I read that the smp option takes the big work units and there's no real option for smaller work units. I'd like to be able to punch 'em out quick and small, but apparently that's not happening anymore.
My ubuntu machine is 64 bit, but not dual core.
Anybody have some setup tips for this?
There has to be a way to hack out a solution. What about splitting that file, sending the pieces to a remote server with a bigger pipe one at a time and then joining them on the remote and sending them in from there?
It should even be scriptable. Cant you elect not to send completed units and continue to crunch units? This would keep you from having downtime on crunching and allow you to return the units at your speed, presumably as long as its prior to the deadlines.
bs_texas or anyone else using the smp client: Does it use anywhere near all of your CPU? Mine is currently using < 40% of my CPU. On a good day it maybe uses 70-80%, but it never uses 100% like I think it should. I may just go back to running four instances of the standard client since it would definitely get more work done.
I noticed the same thing with my new smp client, but after awhile it went back to using all the cpu. Perhaps it's just the WU's you're getting?
Quote:
Originally Posted by cybertron
How many procs/cores do you have? I remember FAH recommending to not use "-smp" on dual core machines. I think they recommend four or more for smp. Here is how mine look to top using 2 separate instances running in smp mode on a dual proc 8 core system. It has always run in this way for me.
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
5367 michael 39 19 81584 40m 1880 S 99 1.0 636:11.29 FahCore_a1.exe
6718 michael 39 19 47984 16m 1880 S 97 0.4 56:55.73 FahCore_a1.exe
5369 michael 39 19 77748 37m 1664 S 78 1.0 495:37.78 FahCore_a1.exe
5368 michael 39 19 77616 37m 1664 S 78 1.0 508:52.62 FahCore_a1.exe
5370 michael 39 19 78212 38m 1676 S 78 1.0 484:00.73 FahCore_a1.exe
6719 michael 39 19 46052 14m 1664 S 54 0.4 30:59.13 FahCore_a1.exe
6721 michael 39 19 46456 14m 1676 S 52 0.4 30:42.92 FahCore_a1.exe
6720 michael 39 19 45928 14m 1664 S 48 0.4 28:54.64 FahCore_a1.exe