1) Questions and Answers : Unix/Linux : Double Wammy (Message 13716) Posted 4 Aug 2004 by UWP (Udo Wolter) Post: Yes, Linux ist faster but it depends on how good the program is written. It seems that the seti client itself is not really optimized, even compiling with optimization brings just 5% more speed. There is one thing you can do. As you said right, the credits are calculated by the speed but it's not the only thing. There's also the integer & floating point measuring which comes into this calculation too. In this case you can optimize the boinc client by just compiling it from source and using as much optimization as possible. I doubled my floating points and increased my integer calculations about 50%. In this case the work unit might last as long as before until it's finished but the calculation gets up straight. At least linux machines are hanging only 25% behind the windows machines if you use this method. But this 25% less speed is something what should be done in the seti client. As long as it is that poor optimized we will stay behind the windows machines...:( Mermgfurt, Udo

2) Message boards : Number crunching : no work from project AGAIN!!! (Message 11155) Posted 22 Jul 2004 by UWP (Udo Wolter) Post: I'm beginning to be suspicious. Maybe the Seti guys have been infiltrated by aliens? They sure don't want to be found so we can all be their slaves! Ok, I just brought this sentence because that's the only discussion format we haven't had yet... (who is writing this? I wanted to write something else! :)) Back to a discussion without flames I'd prefer. > This is kind of BS. If the Seti project administrators know there's going to > be an abundance of processing power and shortage of work then they're not > doing their jobs. They should make the work fit the processors. They should Hm, how should they do that? > perform more sophisticated processor intensive analysis so as to more > appropriately match supply and demand. Yes, it would be nice but maybe they're thinking about this? > I joined S@H to find aliens. I could give a f*** less about prime numbers or > protiens or how many clowns can fit in one of those little tiny cars. Full ACK. > Plus, BOINC is fine for me - I don't mind searching web sites and figuring out > how to configure things, but it seems too complicated for the average user. Yes, I also tried a lot of compiles to make the linux client faster etc. > I'd really hate for the magic, the attraction of this project to get > dissipated, or lost in a crowd of other projects. But: the current seti way is only one method of finding alien signals. There will be more ideas of how to search for signals in the future. I'd also like to participate in such projects. And I think, if the current problems have been gone there will be a big mass of users coming to seti again, so that's not the problem. > Seti is special, and it's more important than any other network computing > project. I don't want a multi-project attitude. I want Seti to have a more > aggressive attitude. Right at this time I'd like them to fix the bugs and to generate more work for my clients (which only get 1 WU a day, sometimes not even that). I'd say the project itself is getting better when rumours like "it works" will find their way. But at this time we can only wait for WUs and hope that there will be more data in the future. BTW, if this situation won't get better in the next half a year and I can not even process 1 WU per day (normally I have upto 10 machines, classic was at 18700 results for me until today) I have to say: that was it. In this case Seti is useless, I won't give any computer time (and power, seti itself costs me more than 500 Euros the last years just for electric power, you always forget how much the user has to pay for the bills if he's willing to compute and let the machines run day & night) anymore. But I doubt that our machines are that powerful that we can scan every signal from the sky in such a short time that there's no work anymore. The sky is too big for that and the tapes from the antenna will get more in the future (I mean: you won't stop to scan the sky?). Mermgfurt, Udo

3) Message boards : Number crunching : no work from project AGAIN!!! (Message 10206) Posted 20 Jul 2004 by UWP (Udo Wolter) Post: > How many of you have actually written a single piece of software? I am a > computer programmer and understand that the way you design a piece of software > is not how it turns out in the end. The classic seti took a few months to get > all the bugs worked out too. Software on this scale takes a while to work out > all the bugs and get every single possible scenario worked out. Ok, I'm criticizing the linux software because it's much slower than the windows one but this is not my main point of critics. The main point is the plan behind the new project. It should have been clear that after announcing the new project on the website there will be lots of people come and try it. And in my opinion this software isn't even beta, it's more like alpha, so it was much too early to make the whole bunch of users swap to the new one. At the main page there was also the hint that the clasic seti will shut down sometime. This brings pressure to a lot of people to switch which leads to overcrowding of the new servers. No, normally you should have chosen some way of smooth change to the new seti or maybe some kind of way how to connect them or mix them so you could also use the classic servers for balancing the pressure. Now it seems as if the classic has all the resources and the new one has not enough power to stand the pressure. That's what I'm critizing: it looks like there is almost no plan, I can only see chaos which is getting bigger. Mermgfurt, Udo

4) Message boards : Number crunching : no work from project AGAIN!!! (Message 10030) Posted 19 Jul 2004 by UWP (Udo Wolter) Post: > Just got to keep on trying. Easy for me to say cause I'm on broadband. It must > be really frustrating for those with a modem. It's not easy, even for people with DSL lines. It's useless having the machine up all day just for waiting for data. Ok, a little bit other stuff is running as well but the CPU is mostly idling when there's no seti running. I downgraded today from seti 4.00 to seti 3.08 (because no credits from 4.00 has been counted and someone in another thread told me that only 3.08 results will be counted) and still have not even one WU the whole day on 2 machines. If I recall the last weeks I'd say that there was half a week of computing and the rest was only waiting for WUs. What a messy project is growing out of the relatively good working classic seti...:( Mermgfurt, Udo

5) Questions and Answers : Unix/Linux : Why has the linux client gotten so slow (Message 10022) Posted 19 Jul 2004 by UWP (Udo Wolter) Post: > Well, if it were a RedHat project the old seti1 would not be supported and the > new project would be "borrowed" from open source but we would have to buy it > and pay a subscription to get updates. Yeah, you might be damn right. BTW: now I'm running boinc 3.20 & seti 3.08 and getting no WUs at all. With seti 4.00 I even got some WUs even though they didn't seem to add to my credits. Now I'm also getting no credits but I can't even calculate WUs...:( This might be a boinc problem again because there has been no credits calculated from my windows machine and this machine is still running, calculating etc. No credits at all again. *big sigh* BTW, it's nice not to be alone with such problems. Let's do something like the "ASA": Anonymous Seti Addicts. We can only discuss our problems but we can't do anything to solve them. Mermgfurt, Udo

6) Questions and Answers : Unix/Linux : Why has the linux client gotten so slow (Message 9675) Posted 19 Jul 2004 by UWP (Udo Wolter) Post: > I read in another thread that someone else noticed they were running > slower using the -ffast-math parameter, so I dropped that and tried again. It I'll test that. > On the number crunching board, one of the developers informed me that there is > no public work coded yet for the 4.0 versions, as they're still in alpha. If > you have work units already, they would likely run, but Rom said the scheduler > won't give any work to 4.0 yet (and also may not be giving any credit either, > but that's just a guess on my part). My seti client that I'm working with on > this system is 3.10 and it's only getting new work sporadically, while my 3.08 > hosts are getting new work consistently. All have boinc 3.20. Interesting hints. Why do they never say this somewhere on their webpages ? This project seems to change into a big bubble of trash where it's almost impossible to get informations. Another strange thing: you need to extract the cvs versions in order to get the version number. I now tried the version from June, 30, 2004. It's the last 3.08 version, the next day it's 3.10. *sigh* What happened to a good project like seti ? Is it changing to a complete windows-project ? No docs, no workung units (after the change to 3.08 I'm not getting anything anymore), no good programmers (slow seti linux version, bad compiled boinc), this looks very much like the typical windows chaos. What will come next ? Do we calculate viruses instead of radio signals ? Ok, at least the users help each other. Thanx ! Mermgfurt, Udo

7) Questions and Answers : Unix/Linux : Why has the linux client gotten so slow (Message 9615) Posted 19 Jul 2004 by UWP (Udo Wolter) Post: > Yes, that's the main reason. Anyway, by optimizing the seti client (I used > this one: seti_boinc-client-cvs-2004-07-16.zip), it seems that we can get at > least a little push. But sure: it's not enough. The linux machines will be > slower than the windows ones and that's bad. Ok, going on with my monologue: In my first attempt I forgot to add -O3 to the compilation parameters. For the boinc client it's no problem, here it was inserted before from the standard compile options. But for the seti client it's a little bit better. The client is getting another 10% faster. But even here it's far away from the windows machines which compute results in almost half of the time. BTW, since I'm using the new selfcompiled clients (boinc 3.20 & seti 4.00) there has been no new credit for me. Is there someone else who has a similar problem and knows what's going on ? Or is there something I have to do after a version change ? Mermgfurt, Udo

8) Questions and Answers : Unix/Linux : Why has the linux client gotten so slow (Message 9358) Posted 18 Jul 2004 by UWP (Udo Wolter) Post: > But how did you get the seti client to compile with optimizations? Everything > in the other thread that was successful was only the boinc binary - the seti > binary fails with optimizations. No, it got compiled with the same optimizations: CFLAGS & CXXFLAGS had been set to this before doing autoconf & configure: "-msse2 -funroll-loops -fomit-frame-pointer -ffast-math -mmmx -msse -s -static -fexpensive-optimizations -m3dnow -march=pentium4 -mcpu=pentium4" The compiling stopped sometimes because of missing include files (assert.h) and a missing minor version (just put it hard into it: minor = 0). After these changes it compiled normally and it runs the whole time. After using it I must say that the sti client itself hasn't got much faster though. Normally I needed 5:30 hrs for one WU I now need approximately 5:00 hrs for it. This looks like the seti client itself is written very poor for the linux community. Here you can optimize whatever you want, the windows boxes will be faster. :( > While most of it is way over my head, my understanding is that getting the > benchmark up by optimizing the boinc software will only change the amount of > credit asked for. The seti binary actually does the work, and if it can't be > optimized it won't actually do the work any faster. Correct? Yes, that's the main reason. Anyway, by optimizing the seti client (I used this one: seti_boinc-client-cvs-2004-07-16.zip), it seems that we can get at least a little push. But sure: it's not enough. The linux machines will be slower than the windows ones and that's bad. Mermgfurt, Udo

9) Questions and Answers : Unix/Linux : Why has the linux client gotten so slow (Message 9143) Posted 17 Jul 2004 by UWP (Udo Wolter) Post: > The good site: with the old seti it wasn't that obvious that the linux clients > are that poor programmed. Here it is quite obvious, the linux code is > unacceptable slow. Ok, today I tried to compile it myself with full optimizations which has been discussed here: http://setiweb.ssl.berkeley.edu/forum_thread.php?id=1212 The effect is amazing. The float value has been more than doubled and the integer value has gone up about 60-80% (it seems this depends on the machine/cpu, I tested it on 2 of my machines). The discussion also lead to some strange results: the fastest method is to run the windows client unter linux with wine. But by optimizing the client by hand you came nearly to the windos results. Anyway, I'd say that compiling with the intel compiler might get even faster binaries. But I never used the intel compilers before, IMHO it won't be easy. Strange that the standard GCC 3.x is trying to just optimze the compatibility but not the speed. So I must apologize: it's not a problem of the seti guys, it's a compiler problem. To get speed you have to bake your own binary with full optimizations. Mermgfurt, Udo (I hope someone is still reading this thread also)

10) Questions and Answers : Unix/Linux : Why has the linux client gotten so slow (Message 9020) Posted 17 Jul 2004 by UWP (Udo Wolter) Post: It's true, the Windows machines are a lot faster. I have a 1700 MHz Intel Mobile which is only half as fast as a windows 2000 machine (Intel Celeron) with 700 MHz. Even though the calculation with windows started some days later it's now higher in the statistics than the linux laptop (in total AND recent). The good site: with the old seti it wasn't that obvious that the linux clients are that poor programmed. Here it is quite obvious, the linux code is unacceptable slow. Mermgfurt, Udo

11) Message boards : Number crunching : Total credit zero ? (Message 4807) Posted 6 Jul 2004 by UWP (Udo Wolter) Post: > Hang in there my credit jumped from 34plus to almost a 1000 yesterday.... Ok, but why my machine stats say that my last connects to them are days ago even though I connected some hours ago? The whole statistics behind boinc or maybe the webstuff doesn't seem to work right. Mermgfurt, Udo

12) Questions and Answers : Unix/Linux : No Results, no connection to server? (Message 4802) Posted 6 Jul 2004 by UWP (Udo Wolter) Post: I'm using setiboinc for almost 2 weeks now. There has been a time where it was hard to get work units but it seems that those problems have been gone. Now my computations are running and I even upload results. But: There is nothing to see in the statistics. Even in the computer statistics on one of both machines it say it has last contacted july 1st. This is'n true, it was today. The other one say it has only connected at july 4th. Also not true, it has connected today. Even in the client file I can't find anything. All results, total or pending are stated at 0. Don't get me wrong, I like this project, but to get result statistics is a nice point to make the whole think more fun and more competitive. So: why my results never have been counted yet? Thanx, Udo

 
©2024 University of California
 
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.