Panic Mode On (23) Server problems

Message boards : Number crunching : Panic Mode On (23) Server problems
Message board moderation

To post messages, you must log in.

Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 . . . 13 · Next

AuthorMessage
Profile Sutaru Tsureku
Volunteer tester

Send message
Joined: 6 Apr 07
Posts: 7105
Credit: 147,663,825
RAC: 5
Germany
Message 929112 - Posted: 27 Aug 2009, 20:21:51 UTC


@ Eric

Thanks a lot for jump in here in this thread.. :-)


@ Mark

Yes, will do.. you know.. I'm a 'crazy' SETIan.. maybe - like you? ;-)

ID: 929112 · Report as offensive
zpm
Volunteer tester
Avatar

Send message
Joined: 25 Apr 08
Posts: 284
Credit: 1,659,024
RAC: 0
United States
Message 929113 - Posted: 27 Aug 2009, 20:27:11 UTC - in response to Message 929112.  


@ Eric

Thanks a lot for jump in here in this thread.. :-)


@ Mark

Yes, will do.. you know.. I'm a 'crazy' SETIan.. maybe - like you? ;-)


with an rac of 53,000, the answer to that is a YES!!!!!

I recommend Secunia PSI: http://secunia.com/vulnerability_scanning/personal/
Go Georgia Tech.
ID: 929113 · Report as offensive
Profile Sutaru Tsureku
Volunteer tester

Send message
Joined: 6 Apr 07
Posts: 7105
Credit: 147,663,825
RAC: 5
Germany
Message 929116 - Posted: 27 Aug 2009, 20:45:57 UTC - in response to Message 929113.  

with an rac of 53,000, the answer to that is a YES!!!!!


You have also some nVIDIA GPUs?

Your RAC could be also little bit more higher here.. ;-)

ID: 929116 · Report as offensive
Profile startrekforever

Send message
Joined: 5 Dec 99
Posts: 36
Credit: 17,772,420
RAC: 0
United States
Message 929120 - Posted: 27 Aug 2009, 20:52:59 UTC

Thanks Eric. This sounds like my current issue for machine ID 5019936, but unsure. Posted in thread 'Client detached - but not', partially repeated here:

"Right now I am seeing 'Scheduler request failed: Error 403' and have 569 tasks that are not going up."

Is the issue being worked on going to correct my 403 error, which I do not see on any of my other machines?

Should I detach and re-attach? Wouldn't I lose my 569 tasks though?

Thanks.


ID: 929120 · Report as offensive
Eric Korpela Project Donor
Volunteer moderator
Project administrator
Project developer
Project scientist
Avatar

Send message
Joined: 3 Apr 99
Posts: 1382
Credit: 54,506,847
RAC: 60
United States
Message 929149 - Posted: 27 Aug 2009, 23:02:41 UTC - in response to Message 929120.  

Hi Al,

You shouldn't need to detach. I'll check our upload server. It's possible that something is wrong with it.

The fix to allow more WUs to machines should be enabled, but it may take a while to clear out the current counts.

Eric
@SETIEric@qoto.org (Mastodon)

ID: 929149 · Report as offensive
Fred W
Volunteer tester

Send message
Joined: 13 Jun 99
Posts: 2524
Credit: 11,954,210
RAC: 0
United Kingdom
Message 929287 - Posted: 28 Aug 2009, 18:14:17 UTC

Hmmmm... Here we go towards the weekend and it looks like the Server Status page is frozen again (@ 11:20:11 UTC)

F.
ID: 929287 · Report as offensive
kittyman Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Jul 00
Posts: 51468
Credit: 1,018,363,574
RAC: 1,004
United States
Message 929317 - Posted: 28 Aug 2009, 20:37:01 UTC - in response to Message 929287.  

Hmmmm... Here we go towards the weekend and it looks like the Server Status page is frozen again (@ 11:20:11 UTC)

F.

Still frozen in time....
Hopefully it is like the last time that there were no updates for over a day and the splitters, scheduler, and server stay active and work keeps flowing.

In any case, I suspect the boyz are still in the lab and would kick something if it really presented a problem.
"Freedom is just Chaos, with better lighting." Alan Dean Foster

ID: 929317 · Report as offensive
Profile [B^S] madmac
Volunteer tester
Avatar

Send message
Joined: 9 Feb 04
Posts: 1175
Credit: 4,754,897
RAC: 0
United Kingdom
Message 929448 - Posted: 29 Aug 2009, 13:18:03 UTC

Now getting the no new work message again, well it is the weekend again and it is slow to get onto the boards as well
ID: 929448 · Report as offensive
Profile Labbie
Avatar

Send message
Joined: 19 Jun 06
Posts: 4083
Credit: 5,930,102
RAC: 0
United States
Message 929456 - Posted: 29 Aug 2009, 14:27:13 UTC

I just got about 90 WUs across two machines, but it took several tries. The WUs are being created, but they're all shorties, so they're getting picked up quickly.


Calm Chaos Forum...Join Calm Chaos Now
ID: 929456 · Report as offensive
Claggy
Volunteer tester

Send message
Joined: 5 Jul 99
Posts: 4654
Credit: 47,537,079
RAC: 4
United Kingdom
Message 929459 - Posted: 29 Aug 2009, 15:19:31 UTC - in response to Message 929019.  


What's going on in Berkeley?

Why they disabled the 500 WUs/GPU ????



Well the WUs/GPU seems to have changed again, it's now 800 WUs/GPU !!!!

Claggy
ID: 929459 · Report as offensive
Profile Vistro
Avatar

Send message
Joined: 6 Aug 08
Posts: 233
Credit: 316,549
RAC: 0
United States
Message 929465 - Posted: 29 Aug 2009, 16:04:04 UTC - in response to Message 929459.  

You really think a GPU can digest that many units in a day?

Then again, you guys probably invested in one of those standalone-shoebox-sized machines.

Is there like a table or list somewhere of the different CUDA cards and the a) approximate time to plow through a MB WU (per instance) and b) how many WUs can it plow through at one time (number of instances)?

Would really help me decide which one I want to save up for.
30+ Computers heading our way! Currently at the "Zomg we need to talk to our tech expert at the co-op about this first!!!" stage. 16 Lab machines and 14+ Staff machines each with 2.2Ghz CPUs and 256MB ram. Think they balance? The RAM certainly is bad
ID: 929465 · Report as offensive
kittyman Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Jul 00
Posts: 51468
Credit: 1,018,363,574
RAC: 1,004
United States
Message 929467 - Posted: 29 Aug 2009, 16:16:53 UTC - in response to Message 929465.  

You really think a GPU can digest that many units in a day?

Then again, you guys probably invested in one of those standalone-shoebox-sized machines.

Is there like a table or list somewhere of the different CUDA cards and the a) approximate time to plow through a MB WU (per instance) and b) how many WUs can it plow through at one time (number of instances)?

Would really help me decide which one I want to save up for.

The GTX395 CO OP that I bought is really snappy......
It's got my 920 rig up to the #13 spot or so........
Not a cheap card, but my oh my it does crunch.
"Freedom is just Chaos, with better lighting." Alan Dean Foster

ID: 929467 · Report as offensive
Profile Vistro
Avatar

Send message
Joined: 6 Aug 08
Posts: 233
Credit: 316,549
RAC: 0
United States
Message 929472 - Posted: 29 Aug 2009, 16:25:22 UTC
Last modified: 29 Aug 2009, 16:26:50 UTC

Well heres the thing:

The rig in the basement was meant to be a video editing stuido and now also functions as a audio recording station. We spent $3,000 on the microphone alone.

Because we were to be doing HD video editing, we got the most expensive card NVIDIA had at the time. This was about two years ago, around September '07. Apparently, CUDA did not exist then. The card we purchased had one thing in particular we needed: 4 monitors, with only two 'slots' taken up. All of the two monitor cards took up two 'slots' and all of the slots were full with other equipment. So we ended up getting the top-of-the-line NVIDIA Quadro FX 4500 X2. Had we waited a few more months, we could have gotten the 4700 X2. Both are $2,000+ cards.

The current one works just fine, but dad found out that Adobe products can use the CUDA cards, too. So when the economy improves and everyone has a job, we might get a 4700. Supposedly the best card available.

How fast can a 4700 X2 plow through a WU, and how many can it do concurrently?

PS: I checked with NVIDIA, and the while the 4500 technically meets the CUDA specs, there is one little change that was made to the GPU between that and the 4700 and that difference is what made it not CUDA compatible. They would have to rewrite the engine and even then some CUDA functions would simply not work.
30+ Computers heading our way! Currently at the "Zomg we need to talk to our tech expert at the co-op about this first!!!" stage. 16 Lab machines and 14+ Staff machines each with 2.2Ghz CPUs and 256MB ram. Think they balance? The RAM certainly is bad
ID: 929472 · Report as offensive
Profile Sutaru Tsureku
Volunteer tester

Send message
Joined: 6 Apr 07
Posts: 7105
Credit: 147,663,825
RAC: 5
Germany
Message 929498 - Posted: 29 Aug 2009, 18:43:07 UTC
Last modified: 29 Aug 2009, 18:49:35 UTC


AFAIK, they have now 900 WUs/GPU enabled.

One of my 4 OCed GTX260-216 make an AR 0.44x WU in < 10 min.

Shorties in ~ 2 min.

0.44x WUs -> 144 WUs/day/GPU

Shorties -> x5 = 720 WUs/day/GPU

ID: 929498 · Report as offensive
Profile Sutaru Tsureku
Volunteer tester

Send message
Joined: 6 Apr 07
Posts: 7105
Credit: 147,663,825
RAC: 5
Germany
Message 929500 - Posted: 29 Aug 2009, 18:46:34 UTC


Ahh.. BTW..

Back to topic.. ;-)

Again.. 'no jobs available'.. :-(

ID: 929500 · Report as offensive
kittyman Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Jul 00
Posts: 51468
Credit: 1,018,363,574
RAC: 1,004
United States
Message 929502 - Posted: 29 Aug 2009, 18:50:24 UTC - in response to Message 929500.  


Ahh.. BTW..

Back to topic.. ;-)

Again.. 'no jobs available'.. :-(

Hard to say what's afoot, seeing as how the server status page is still on the fritz.

Hopefully, all is still running well in the background.
"Freedom is just Chaos, with better lighting." Alan Dean Foster

ID: 929502 · Report as offensive
Profile arkayn
Volunteer tester
Avatar

Send message
Joined: 14 May 99
Posts: 4438
Credit: 55,006,323
RAC: 0
United States
Message 929509 - Posted: 29 Aug 2009, 19:27:03 UTC

Looks like the stats dump is down as well.

ID: 929509 · Report as offensive
kittyman Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 9 Jul 00
Posts: 51468
Credit: 1,018,363,574
RAC: 1,004
United States
Message 929512 - Posted: 29 Aug 2009, 19:30:43 UTC - in response to Message 929509.  
Last modified: 29 Aug 2009, 19:31:55 UTC

Looks like the stats dump is down as well.

Ah well......they shall all be there when it's back up......

Keep 'em crunching.

Those silly arse stats dumps do raise hell with the Boincstats graphs tho....LOL.
"Freedom is just Chaos, with better lighting." Alan Dean Foster

ID: 929512 · Report as offensive
Cosmic_Ocean
Avatar

Send message
Joined: 23 Dec 00
Posts: 3027
Credit: 13,516,867
RAC: 13
United States
Message 929519 - Posted: 29 Aug 2009, 20:26:15 UTC

Cricket graph is bottomed out. With the server stats page being frozen and Cricket down on the floor, one would make the assumption that either the download server has locked up, or the splitters ran out of tapes to process.
Linux laptop:
record uptime: 1511d 20h 19m (ended due to the power brick giving-up)
ID: 929519 · Report as offensive
Profile Vistro
Avatar

Send message
Joined: 6 Aug 08
Posts: 233
Credit: 316,549
RAC: 0
United States
Message 929520 - Posted: 29 Aug 2009, 20:32:22 UTC - in response to Message 929519.  

Is there a particular cause this time? Parents just agreed to let CUDA run on their new laptop and it won't get any new tasks.
30+ Computers heading our way! Currently at the "Zomg we need to talk to our tech expert at the co-op about this first!!!" stage. 16 Lab machines and 14+ Staff machines each with 2.2Ghz CPUs and 256MB ram. Think they balance? The RAM certainly is bad
ID: 929520 · Report as offensive
Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 . . . 13 · Next

Message boards : Number crunching : Panic Mode On (23) Server problems


 
©2023 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.