Panic Mode On (98) Server Problems?

Message boards : Number crunching : Panic Mode On (98) Server Problems?
Message board moderation

To post messages, you must log in.

Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 · 8 . . . 32 · Next

AuthorMessage
Profile JaundicedEye
Avatar

Send message
Joined: 14 Mar 12
Posts: 5375
Credit: 30,870,693
RAC: 1
United States
Message 1692447 - Posted: 17 Jun 2015, 3:59:08 UTC

Why Stanford decided to go it alone is known only to them. :(


Blame John Elway.....

"Sour Grapes make a bitter Whine." <(0)>
ID: 1692447 · Report as offensive
Profile Zalster Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 27 May 99
Posts: 5516
Credit: 528,817,460
RAC: 242
United States
Message 1692471 - Posted: 17 Jun 2015, 4:55:40 UTC - in response to Message 1692447.  

Back to Beta it is...

Sidenote.. I am liking that OpenCl for VLARs 18 minutes. Now if they only validate..

Cuda 50 for the VLARs are taking about 53 minutes give or take. Of course the cuda50 is only using 13% of a core as opposed to 95% with the OpenCL but hey, I don't usually use the Cores for anything else anyway, lol

Happy Crunching...

Zalster
ID: 1692471 · Report as offensive
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13334
Credit: 208,696,464
RAC: 304
Australia
Message 1692517 - Posted: 17 Jun 2015, 6:55:34 UTC - in response to Message 1692471.  

It would appear the splitters are on strike.
One is running, the rest aren't- looks like they didn't get the wakeup call after the weekly outage.
End result, I should be out of GPU work in the next hour or so.
Grant
Darwin NT
ID: 1692517 · Report as offensive
Profile Cactus Bob
Avatar

Send message
Joined: 19 May 99
Posts: 209
Credit: 10,924,287
RAC: 29
Canada
Message 1692524 - Posted: 17 Jun 2015, 7:07:28 UTC

I guess bitching about AP's at this point is kinda mute. I am chewing up my GPU MB's rather quick and will have an excess of CPU MB's soon. At least a couple days worth. I spent a few bucks on my GPU though in hopes of continue crunching.

Not sure what happened that both AP's and MB's dried up. Someone give the server a Fonzie bonk. just need more CL's for my GPU.

Bob
Sometimes I wonder, what happened to all the people I gave directions to?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
SETI@home classic workunits 4,321
SETI@home classic CPU time 22,169 hours
ID: 1692524 · Report as offensive
Profile JaundicedEye
Avatar

Send message
Joined: 14 Mar 12
Posts: 5375
Credit: 30,870,693
RAC: 1
United States
Message 1692527 - Posted: 17 Jun 2015, 7:14:22 UTC

Depending on the 'morn in Berkeley, I will run one cruncher out of work and cut back the percentage of usage on the main unit. Hopefully it won't come to that.

"Sour Grapes make a bitter Whine." <(0)>
ID: 1692527 · Report as offensive
Grumpy Swede (I stand with Ukraine)
Volunteer tester
Avatar

Send message
Joined: 1 Nov 08
Posts: 8931
Credit: 49,849,242
RAC: 65
Sweden
Message 1692532 - Posted: 17 Jun 2015, 7:22:02 UTC

Strange...
I have a strange feeling of emptiness.
ID: 1692532 · Report as offensive
Profile ivan
Volunteer tester
Avatar

Send message
Joined: 5 Mar 01
Posts: 783
Credit: 348,560,338
RAC: 223
United Kingdom
Message 1692545 - Posted: 17 Jun 2015, 8:41:12 UTC - in response to Message 1692532.  

Strange...
I have a strange feeling of emptiness.

Mmm. Came in this morning to find my wall of gkrellm monitors largely black. Well, the 12-core is down at the moment; I tried finally to put it and the dual-20-core servers into a rack yesterday, but it seems when I rebuilt the rack I put the uprights fractionally closer than the standard rack dimensions, and the 10C's rack rails are about 5mm too long, fully collapsed, to fit.
But one 20C's display is blank, and the other shows only three jobs running.
After a bit of panicking, I eventually realised the fault was in Berkeley, not North Heathrow. Should be a trifle quieter in the server room today.
ID: 1692545 · Report as offensive
qbit
Volunteer tester
Avatar

Send message
Joined: 19 Sep 04
Posts: 630
Credit: 6,868,528
RAC: 0
Austria
Message 1692549 - Posted: 17 Jun 2015, 9:04:50 UTC

Folks, whats happening there? Maintenance done, SSP shows tapes beeing split but theres no work available and no word from any official?
ID: 1692549 · Report as offensive
Richard Haselgrove Project Donor
Volunteer tester

Send message
Joined: 4 Jul 99
Posts: 14474
Credit: 200,643,578
RAC: 874
United Kingdom
Message 1692550 - Posted: 17 Jun 2015, 9:07:09 UTC - in response to Message 1692549.  

Folks, whats happening there? Maintenance done, SSP shows tapes beeing split but theres no work available and no word from any official?

Well, not actually "being" split - no dark green markers, and most splitters 'not running'. S**t happens - they'll sort it out when they get into the lab.
ID: 1692550 · Report as offensive
raydar115

Send message
Joined: 6 Oct 02
Posts: 17
Credit: 16,305,128
RAC: 0
United States
Message 1692556 - Posted: 17 Jun 2015, 9:16:51 UTC

Yep here we go into another dry spell with no explanations in the technical news of what the holdup is.
Just a quick note of what the problem is like---(sorry folks having problems with the database again were working on it)--- or just something easy and simple like that would do it and would let us know that there are aware of a problem and are working on it.
That would be all it would take to satisfy me.
I do sincerely appreciate all the work they do, and time that they voluntarily put into this hopefully they'll let us know something soon before I run out of work that way I will know whether I should start crunching backup on one of my other secondary projects that will keep my computer busy and my volunteer work for humanity going.
ID: 1692556 · Report as offensive
qbit
Volunteer tester
Avatar

Send message
Joined: 19 Sep 04
Posts: 630
Credit: 6,868,528
RAC: 0
Austria
Message 1692559 - Posted: 17 Jun 2015, 9:25:33 UTC

Thx Richard. Looks like there are many problems lately and communication seems to be a bit low. But ok, its 2 in the morning there, lets see how things develop when they start to work in a few hours.
ID: 1692559 · Report as offensive
Profile Zalster Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 27 May 99
Posts: 5516
Credit: 528,817,460
RAC: 242
United States
Message 1692565 - Posted: 17 Jun 2015, 9:31:32 UTC - in response to Message 1692556.  

It's always a good thing just to have a back up project with resources set to 0 so what if you run out of work, it will pick up automatically and crunch that project.

When Seti comes back up, that back up will go to standby and seti will resume.

Also, remember it's 2 am in California right now. This thing started to go down somewhere around 9-10 pm last night? They had already spent the day working on it when it decided to take a nap on us.

I'm sure they will attend to it when they get to work today. Probably 8-9 am Pacific time.

While an inconvenience, it is certainly not an emergency. My back ups have been happily crunching away for several hours.

I for one, would prefer to allow them to get some rest and approach this with well rested eyes in the morning. Unlike me, who finds myself on the night shift, lol

Zalster
ID: 1692565 · Report as offensive
qbit
Volunteer tester
Avatar

Send message
Joined: 19 Sep 04
Posts: 630
Credit: 6,868,528
RAC: 0
Austria
Message 1692573 - Posted: 17 Jun 2015, 9:58:03 UTC

Zalster, I know it's in the morning there and ofc I don't expect them to post at this time, but overall theres not much communication between the team and us lately, at least thats my impression.
ID: 1692573 · Report as offensive
Profile Zalster Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 27 May 99
Posts: 5516
Credit: 528,817,460
RAC: 242
United States
Message 1692584 - Posted: 17 Jun 2015, 10:55:54 UTC - in response to Message 1692573.  
Last modified: 17 Jun 2015, 10:56:20 UTC

Many replies came to mind..

No full time staff...
Part time project...
Communication takes away from repair...
Lack of $$ for intern...


Finally decided on

If it's a major FUBAR they will tell us, if it's a hiccup then they won't.

(Side note) I wonder if the VLAR storm that started just before it went down has anything to do with the failure?

I've noticed the last work units I was getting were all VLARs and Beta is nothing but VLARs at the moment.

Could just be a coincidence. But it does make me wonder..


Zalster
ID: 1692584 · Report as offensive
rob smith Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer moderator
Volunteer tester

Send message
Joined: 7 Mar 03
Posts: 20791
Credit: 416,307,556
RAC: 380
United Kingdom
Message 1692588 - Posted: 17 Jun 2015, 11:07:21 UTC

Beta are testing new/updated CUDA/OpenCL VLAR app, so nothing to do with the VLARs that were coming out on main.
Bob Smith
Member of Seti PIPPS (Pluto is a Planet Protest Society)
Somewhere in the (un)known Universe?
ID: 1692588 · Report as offensive
Profile William
Volunteer tester
Avatar

Send message
Joined: 14 Feb 13
Posts: 2037
Credit: 17,689,662
RAC: 0
Message 1692593 - Posted: 17 Jun 2015, 11:25:29 UTC

Beta and Main run different splitters. Having VLAR on both is a coincidence (or Murphy)

Beta are testing a bunch of new OpenCL apps, not specifically VLAR.
There probably needs to be a more sophisticated approach than the blanket 'no VLAR for NV unless CC 3+' so as to allow the OpenCL NV app to have a try, but that's rather delicate code. (IOW I doubt Eric has the time to fiddle with it).
A person who won't read has no advantage over one who can't read. (Mark Twain)
ID: 1692593 · Report as offensive
Profile Brent Norman Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester

Send message
Joined: 1 Dec 99
Posts: 2786
Credit: 685,657,289
RAC: 835
Canada
Message 1692599 - Posted: 17 Jun 2015, 11:40:25 UTC

I sent 4 Escorts to the lab, first person that fixed the uploads gets a breakfast to remember :)
ID: 1692599 · Report as offensive
Profile Oz
Avatar

Send message
Joined: 6 Jun 99
Posts: 233
Credit: 200,655,462
RAC: 212
United States
Message 1692628 - Posted: 17 Jun 2015, 13:21:06 UTC - in response to Message 1692599.  

Four? We want to encourage them, not kill them!
Member of the 20 Year Club



ID: 1692628 · Report as offensive
Profile Brent Norman Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester

Send message
Joined: 1 Dec 99
Posts: 2786
Credit: 685,657,289
RAC: 835
Canada
Message 1692634 - Posted: 17 Jun 2015, 13:29:21 UTC - in response to Message 1692628.  

Yes but then you want to see someone leave work and say ... DAMN I DID GOOD TODAY :D
ID: 1692634 · Report as offensive
Profile Zalster Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 27 May 99
Posts: 5516
Credit: 528,817,460
RAC: 242
United States
Message 1692741 - Posted: 17 Jun 2015, 17:27:08 UTC - in response to Message 1692634.  

looks like 3 of the spitters are back online...
ID: 1692741 · Report as offensive
Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 · 8 . . . 32 · Next

Message boards : Number crunching : Panic Mode On (98) Server Problems?


 
©2022 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.