Posts by Dagorath

1) Message boards : Number crunching : Intel or Amd? (Message 983)
Posted 12 Mar 2014 by Dagorath
Post:
Which CPU is best for this project?


My friend's AMD is about 3X faster than his Intel on this project. The AMD's clock speed is a tad slower than the Intel's.

Warning: Generalizations such as the one in your question will get you all sorts of meaningless answers.
2) Message boards : News : Subfield #17 complete (Message 944)
Posted 1 Jan 2014 by Dagorath
Post:
Your regular announcements are sweet music, not a broken record. Happy New Year to the project devs/admins and all the crunchers who keep the sweet music flowing.
3) Message boards : News : Badges are here (Message 789)
Posted 13 Feb 2013 by Dagorath
Post:
The stock home page you are using is busy enough as it is for many people's taste but it's up to you. IMHO clicking on a badge to see the badge legend is the perfect solution. I dunno, when I see something for which I want more info the very first thing I do is hover my mouse cursor on it to see it it's clickable or see if a tooltip pops up with more info. The entire graphical web paradigm is built on that "if curious about it see if it's clickable" kind of inquisitiveness.

Regarding the tooltip that pops up for the badges... they show the min. credits required to get the badge which is good but often people want to know the min. the credits for the next badge so they can get an idea of how many more credits they need to get it. So if you hover on the silver badge it would say like " > 100,000, next badge is gold at > 200,000". Like when people look at a clock they don't always want to know just the time, they often want to know how many more minutes/hours until event X happens.
4) Message boards : Number crunching : Super long estimated times (Message 782)
Posted 22 Jan 2013 by Dagorath
Post:
Doh! My mistake. frankhagen is right, 10% per day or less. Eric, I thought you were talking about the <fpops_bound> (sp?) tasks property when you said "bounded app".
5) Message boards : Number crunching : Super long estimated times (Message 780)
Posted 22 Jan 2013 by Dagorath
Post:
We rarely use the bounded property so a quick reduction doesn't hurt much. A tenfold decrease in the flops estimate, however, throws a big wobbly into the scheduler. On the other other hand... when are people gonna learn to keep a small cache <sigh>
6) Message boards : News : Subfield #9 is now complete. (Message 769)
Posted 10 Jan 2013 by Dagorath
Post:
Congratulations to everybody.

40 more? piece 'o lassie loaf!!
7) Message boards : News : Another milestone reached. (Message 763)
Posted 21 Nov 2012 by Dagorath
Post:
Wonderful! Slow steady go...
8) Message boards : Number crunching : now who is this again? (Message 760)
Posted 31 Oct 2012 by Dagorath
Post:
It's my cousin Vinny's porno server. 4 physical CPU sockets times 8 cores per CPU = 32 processors in BOINC's books. What's fishy about that? You're just jealous. OK, I'm jealous too.
9) Message boards : News : SPAM Attacks (Message 754)
Posted 26 Oct 2012 by Dagorath
Post:
A friend attached to this project but all of his tasks crash. I can't figure out what's wrong, all his other projects run OK. He wants to post a request for help but he has 0 RAC and 0 credits. What can he do?
10) Message boards : News : Problem with client version 7.0.24 on ubuntu. (Message 653)
Posted 17 May 2012 by Dagorath
Post:
yikes!!! not even I post like that and I've been banished from more projects than most crunchers have joined. Screwed up not f@*%~$ up.
11) Message boards : News : Problem with client version 7.0.24 on ubuntu. (Message 651)
Posted 15 May 2012 by Dagorath
Post:
7.0.26 is a Berkeley build, in other words a build from the BOINC developers. They build BOINC on the latest Ubuntu LTS release which was, until recently, Ubuntu 10.x. Now the LTS is Ubuntu 12.04 but there is no guarantee the BOINC developers have switched to 12.04, they may still be using 10.x. If you're running 12.04 and the BOINC devs are building on 10.x then there is a good chance BOINC 7.0.26 from Berkeley (the BOINC site) won't work for you. In that case you need to follow the instructions in this post from the SETI forums and install 7.0.27 which works for Frank, me and many others running Ubuntu 12.04. I suppose another option might be to drop back to a 6.x.x BOINC but you might run into a problem with missing shared libs if you do.
12) Message boards : Number crunching : outch! (Message 647)
Posted 10 May 2012 by Dagorath
Post:
I'm in the process of updating to Ubuntu 12.04 so I don't know if this fix actually works.

Edit added:

It seems like there's always trouble with the Linux builds. The builds from the BOINC site work *only* on the version of Ubuntu the BOINC devs use. They use only the current LTS version. The repositories are usually several months behind the recommended BOINC version. Well I've had enough of that nonsense so I'm going to learn how to build BOINC myself, write up the procedure and make it available to all.

This message from the T4T forum has a link to instructions for compiling on Fedora. The instructions are in French but they translate well at online translators. They explain how to get the latest source, how to setup the directories and run the compiler. Someone in the thread has tried the instructions on Ubuntu with some success, got the client to compile but not the manager. I've tried and get the same results, client compiles but not manager. Does anybody know what one has to do to get the manager to compile?
13) Message boards : Number crunching : FUBAR! (Message 454)
Posted 8 Mar 2012 by Dagorath
Post:
that's not the problem. i am currently running most of them on a laptop which has only a few hours of spare time for boinc.


That's one of the reasons the deadline (not the grace period but the actual deadline because THAT, not the grace period, is all 99% of people see) needs to be increased. Add the confusion and uncertainty the scheduler throws into the mix and you end up with a lot of people who won't crunch tasks that run longer than 24 hours. Lots of people reason that the longer a task runs the more chance it has of crashing and not receiving credit so they don't like long tasks to begin with. Add another straw (short deadlines) and the camel quits. Again, a long grace period is irrelevant as 99% of people have no idea a grace period exists or, if they do know, they have no idea how long the period is. Why don't they ask? It's easier to just click No New Tasks, detach the project or select only the short tasks. There are some things people just will not do no matter how many worthless credits you give them so you best remove as many impediments as possible. Do you really need results back that quickly? Some project admins admit that short deadlines are no help and that it's all driven by resource share and numbers of volunteers. That makes sense. If you double the deadline you'll wait twice as long for the first result to return but once the ball gets rolling the results come back just as quickly as with a short deadline because it's all driven by resource share and number of volunteers. A short deadline does not mean a result returns sooner, it means the host will wait longer before downloading a task. If a host's resource share allows for 1 of your tasks per week than you'll get 1 result per week regardless of what the deadline is though if it's too short for the user's liking he'll just boot your project to the curb. The tortoise versus the hare.
14) Message boards : Number crunching : Runnitme discrepancy (Message 424)
Posted 10 Dec 2011 by Dagorath
Post:
Yikes! Those are mine! Did you see the stderr? Says "we r anonymous all ur creds r belong 2 us free Julian Asange". Looks like that machine has been taken over by that Anonymous hacker group. I'll clean it up and beef up security.
15) Message boards : Number crunching : Runnitme discrepancy (Message 420)
Posted 9 Dec 2011 by Dagorath
Post:
They're both showing Linux as the OS but they have different kernel versions. Maybe QEMU somehow alters the kernel version for virtual CPUs? They could indeed be the same host. Maybe Eric can see the IP address and/or email address for both.


I did look into this last night. I need to be careful with what I say though, because users expect their information to remain private. But I will say that there is some truth to what Frank says and these particular hosts don't appear to be cheating.

Eric


I suggested looking at their addresses but would never ask you to reveal user information. That wasn't my intention.

A stock i5-2500K CPU @ 3.30GHz doesn't earn benchmarks like host 1461 reports and I doubt very much one can be overclocked high enough to produce those numbers. Then there's the fact his run times are so much higher than his CPU times. That's neither a bug nor a glitch. However, I couldn't care less if he's cheating or not. Other can press the point if they want to.
16) Message boards : Number crunching : Runnitme discrepancy (Message 417)
Posted 9 Dec 2011 by Dagorath
Post:
They're both showing Linux as the OS but they have different kernel versions. Maybe QEMU somehow alters the kernel version for virtual CPUs? They could indeed be the same host. Maybe Eric can see the IP address and/or email address for both.
17) Message boards : Number crunching : Runnitme discrepancy (Message 415)
Posted 8 Dec 2011 by Dagorath
Post:
Credits is all about competition. They exist to encourage competition because we all know none of us will do a bloody thing unless there is some competition involved. Altruism, charity and all that other nonsense never existed and never will. The problem is, competing for credits is as boring as listening to grass grow. If you feel like you're being walked all over on the playing field you go out and buy the fastest rig you can get, maybe just buy the parts and build your own so you can have 2 plus a smokin fast GPU for the price of 1, you plug it in and a week later you realize other than the thrill of pricing and plugging in some new hardware, you're still bored stiff with crunching. You realize all it takes is more silicon, not a lot of skill or finesse and there's so many guys out there who have their boss's big network on BOINC, you're never going to get close to the top anyway. So... what makes it interesting and competitive? Finding out how to cheat the system is what. See who can discover the back door and scoop a bunch of credits without being caught. That's competitive and it's not boring. And it's not stealing because credits don't cost projects anything anyway. Besides, some projects give out half a million of them for 10 seconds of CPU time so they're worthless and meaningless from the get go. Oh yes, I'll take cheaters before CreditNew any day. I admire their innovation, the research and work they put into it and the elegance of some of their methods. Hey, the community must have competition and that's exactly what it's got. I think cheaters should be graded and given little stars, gold for the year's best, red for second best and so on.

I don't think CreditNew will stop a benchmark cheat but I could be wrong. I think the 2 aforementioned benchmark fudgers were cheating even before you turfed CreditNew. CreditNew does reduce the inflated run time cheat but doesn't totally eliminate it. My advice is neither cheaters nor CreditNew is as bad as a 20 ft. crocodile in your server closet so be happy.

After the current round of fun plays out, Eric, the next step for you (if you want to be part of the fun and we won't hold it against you if you would rather not) is to write some complicated "fixed on the server" type of system, debug it, deal with all the complaints that it doesn't give enough credit or doesn't deal with X equitably from the same crew who are never satisfied with the credits and then watch that bit of work get cheated too. Those are your gold star cheaters. Those are the guys I truly admire. It will take them weeks, months even but they'll cheat you in the end. Why? Well, why not? Why climb Everest? So, Eric, are you down?
18) Message boards : Number crunching : Runnitme discrepancy (Message 413)
Posted 7 Dec 2011 by Dagorath
Post:
I suspect they are faking the run times. It's easy to do. In fact it looks to me like the hosts in the top 3 positions (sorted by RAC) might all be bogus.

In position #1, host 1461 : I could be wrong but I don't think that CPU can be overclocked enough to give the benchmarks it's reporting. The owner has either altered the true benchmarks reported by the client or he's running a custom client designed to report bogus benchmarks. The fact that his run times are that much higher than his CPU times suggests to me that he is altering the run times reported by the client. It's very easy to do that by manually editing a few files the client uses. The procedure is not convenient when applied to more than a few results so I would say he's automated the job with a clever script. I suppose the high run times might be due to a bug but I don't think the high benchmarks are.

In position #2, host 1575 : Is this for real? A 48 core AuthenticAMD AMD Engineering Sample? The benchmarks look way too low but I doubt anybody would fake low benchmarks. I reserve judgement on this host.

In postion #3, , host 2507 : The benchmarks seem a little high but since it's a virtual CPU it's hard to say. Again, the huge discrepancy between run time and CPU time might be a bug but I doubt it.

I have a problem with my theory that #1406 and #2507 are faking the run times with a script. If I were to write such a script I would probably just multiply the CPU time by a number to get the run time and be done with it. The ratio of run time to CPU time would then be a constant. That's not the case with #1406 and #2507 so if the run times are the product of a script then it's a somewhat sophisticated script that generates a bound random CPU time multiplier. Or maybe the owner has a totally different method for arriving at the bogus run time. Or maybe he's not cheating at all.
19) Message boards : Number crunching : Use of HIGH PRIORITY (Message 397)
Posted 24 Nov 2011 by Dagorath
Post:
I'll answer your question when you answer my questions which I posted in response to your brilliant accusation.
20) Message boards : Number crunching : Use of HIGH PRIORITY (Message 391)
Posted 23 Nov 2011 by Dagorath
Post:
I crunch GPU tasks, CPU tasks and I run T4T@home tasks in a VM. BOINC runs just fine here, no problems, no worries, just sheer joy.

Wanna know why?

Because I know BOINC isn't perfect and it never will be perfect and instead of continually bleating like a sheep about it I use recommended workarounds and I use the recommended version of BOINC not some version Jesus Christ used before he became a carpenter.

If you don't use the recommended workarounds and insist on running fossil-ware then you're never going to find joy with BOINC. It really is that simple. And if you think you can do a better job developing BOINC then fork a branch and show DA how it should be done. It's all open source and just crying out for you to save it from DA's evil clutches.


Next 20


Main page · Your account · Message boards


Copyright © 2024 Arizona State University