Panic Mode On (83) Server Problems?

Message boards : Number crunching : Panic Mode On (83) Server Problems?
Message board moderation

To post messages, you must log in.

Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 · 8 . . . 21 · Next

AuthorMessage
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13722
Credit: 208,696,464
RAC: 304
Australia
Message 1358786 - Posted: 20 Apr 2013, 5:08:37 UTC - in response to Message 1358785.  

Actually that should have read "167.6120/sec" but for some reason the 1st digit went AWOL.

Yeah, i knew what you meant.
:-)


I'm wondering if it was an actual value, or just an anomaly? You'd expect a small beuffer to develop with that sort of output. But i guess if it was brief enough, whatever was produced would be gone before the next query & so wouldn't show up in the ready-to-send numbers.
Grant
Darwin NT
ID: 1358786 · 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: 22160
Credit: 416,307,556
RAC: 380
United Kingdom
Message 1358790 - Posted: 20 Apr 2013, 5:19:03 UTC

Strangely enough, despite the apparent lack of work I've been bouncing off the limits on all three of my crunchers. I just don't understand what's going on with the splitters and downloads. Has DA done something and not told anyone??
Bob Smith
Member of Seti PIPPS (Pluto is a Planet Protest Society)
Somewhere in the (un)known Universe?
ID: 1358790 · Report as offensive
Profile Wiggo
Avatar

Send message
Joined: 24 Jan 00
Posts: 34744
Credit: 261,360,520
RAC: 489
Australia
Message 1358791 - Posted: 20 Apr 2013, 5:19:49 UTC - in response to Message 1358786.  

It must be all those 4-5min shorties that we've been chewing through lately (I'm reporting 12 every 5mins across my 2 rigs just off their video cards alone).

Cheers.
ID: 1358791 · Report as offensive
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13722
Credit: 208,696,464
RAC: 304
Australia
Message 1358793 - Posted: 20 Apr 2013, 5:21:41 UTC - in response to Message 1358790.  

Strangely enough, despite the apparent lack of work I've been bouncing off the limits on all three of my crunchers. I just don't understand what's going on with the splitters and downloads. Has DA done something and not told anyone??

The problem is to do with the Seti servers, not the BOINC clients.
Grant
Darwin NT
ID: 1358793 · Report as offensive
Lionel

Send message
Joined: 25 Mar 00
Posts: 680
Credit: 563,640,304
RAC: 597
Australia
Message 1358799 - Posted: 20 Apr 2013, 5:54:16 UTC - in response to Message 1358793.  


It was the first 0 (zero) I have seen in that field, sort of prophetic at the moment.


ID: 1358799 · Report as offensive
Profile Bernie Vine
Volunteer moderator
Volunteer tester
Avatar

Send message
Joined: 26 May 99
Posts: 9954
Credit: 103,452,613
RAC: 328
United Kingdom
Message 1358822 - Posted: 20 Apr 2013, 7:10:37 UTC - in response to Message 1358793.  

Strangely enough, despite the apparent lack of work I've been bouncing off the limits on all three of my crunchers. I just don't understand what's going on with the splitters and downloads. Has DA done something and not told anyone??

The problem is to do with the Seti servers, not the BOINC clients.

Which strangely isn't a problem here, all my machines have max WU's and are staying that way.

Odd.
ID: 1358822 · Report as offensive
Profile Donald L. Johnson
Avatar

Send message
Joined: 5 Aug 02
Posts: 8240
Credit: 14,654,533
RAC: 20
United States
Message 1358825 - Posted: 20 Apr 2013, 7:17:40 UTC - in response to Message 1358771.  
Last modified: 20 Apr 2013, 7:21:53 UTC

The problem is the databse & the only real fix will probably be to re-design it from scratch.

One database for the in progress work- Waiting to be sent WUs, WUs returned waiting for valiadtion etc & another for the the work that has been completed & validated. The second database will continue to grow over time, the first will only ever be as as large as the amount of work that is in progress. That will allow people to have large caches, and the Scheduler & the databse won't be stuggling with the huge number of entires it needs to manage at present.

Isn't that the way it is now? The Master BOINC database keeps track of all the work in progress, as well as User IDs & stats, and the Forums. Once a Work Unit is completed and validated, the canonical result is assimilated into the appropriate Science Database, and Work Unit and associated Tasks are deleted from the Master BOINC database.

It has been suggested that the Forums be moved into a separate database, but that idea was nixed, for reasons I don't recall...
Donald
Infernal Optimist / Submariner, retired
ID: 1358825 · 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 1358829 - Posted: 20 Apr 2013, 7:23:55 UTC - in response to Message 1358596.  

Am I glad that I am currently living in this part of the world. Electricity is included in the apartment rent, no matter how much I use. I pray it stays that way for a looooooong time.
______________


Hope your landlord does not get wind of this......LOL.
"Freedom is just Chaos, with better lighting." Alan Dean Foster

ID: 1358829 · 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 1358830 - Posted: 20 Apr 2013, 7:25:41 UTC - in response to Message 1358790.  

Strangely enough, despite the apparent lack of work I've been bouncing off the limits on all three of my crunchers. I just don't understand what's going on with the splitters and downloads. Has DA done something and not told anyone??

He often does...LOL.
At least not publicly.
Maybe in the dev forums, which are not frequented by most of us.
"Freedom is just Chaos, with better lighting." Alan Dean Foster

ID: 1358830 · 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 1358833 - Posted: 20 Apr 2013, 7:28:52 UTC - in response to Message 1358535.  

I can't afford to be cutting edge, my last power bill just arrived....
Over $550.00....for running all 9 rigs 24/7.


Wow, cheap. When I was running SETI flat out, many GPUs, >200,000 RAC my electric bill was over $1000 per month. That was years ago though with less efficient GPUs.

Impressive. Even the kitties have not been able to burn a hundred K electric bill.

Of course, that depends on the KWH rate.
Once this spring turns into summer, I will have to do any and all crunching at night rates. The heat will just not allow anything else.
"Freedom is just Chaos, with better lighting." Alan Dean Foster

ID: 1358833 · Report as offensive
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13722
Credit: 208,696,464
RAC: 304
Australia
Message 1358853 - Posted: 20 Apr 2013, 8:02:03 UTC - in response to Message 1358825.  

The problem is the databse & the only real fix will probably be to re-design it from scratch.

One database for the in progress work- Waiting to be sent WUs, WUs returned waiting for valiadtion etc & another for the the work that has been completed & validated. The second database will continue to grow over time, the first will only ever be as as large as the amount of work that is in progress. That will allow people to have large caches, and the Scheduler & the databse won't be stuggling with the huge number of entires it needs to manage at present.

Isn't that the way it is now? The Master BOINC database keeps track of all the work in progress, as well as User IDs & stats, and the Forums. Once a Work Unit is completed and validated, the canonical result is assimilated into the appropriate Science Database, and Work Unit and associated Tasks are deleted from the Master BOINC database.

Don't know.
There have been times in the past, for various reasons, where the number of results in progress was much higher than when they started to have issues with the databse. But back then, there were many less completed & validated results which would make a single databse much larger now than then. Having 2 databases, one of which being active would only grow with more clients/computing resources which hasn't changed that much over the years, which is why i thought the present database includes results that have already been validated.
Grant
Darwin NT
ID: 1358853 · 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 1358857 - Posted: 20 Apr 2013, 8:11:42 UTC

Like I have stated before the colo....
I did say that once things settled, there would be a new wrangling of bottlnecks.

This is not a bad thing, you see.

Once bandwidth has been removed from the equation, the true nature of things has been revealed.

If the kitties cannot get enough work to keep them busy, there will be a settling out of sorts, where all the work that the project can hand out will be crunched.

We just now need the ntpicker to sort it all.
"Freedom is just Chaos, with better lighting." Alan Dean Foster

ID: 1358857 · 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 1358860 - Posted: 20 Apr 2013, 8:16:34 UTC

Oh, and 327 million kittens can't be wrong, eh?
"Freedom is just Chaos, with better lighting." Alan Dean Foster

ID: 1358860 · Report as offensive
Lionel

Send message
Joined: 25 Mar 00
Posts: 680
Credit: 563,640,304
RAC: 597
Australia
Message 1358897 - Posted: 20 Apr 2013, 9:48:29 UTC - in response to Message 1358860.  

Oh, and 327 million kittens can't be wrong, eh?


Only 142 million Maine Coons here mate ...


ID: 1358897 · Report as offensive
Filipe

Send message
Joined: 12 Aug 00
Posts: 218
Credit: 21,281,677
RAC: 20
Portugal
Message 1358959 - Posted: 20 Apr 2013, 12:10:50 UTC

i'm for 10 time larger MB tasks


+1
ID: 1358959 · 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 1358961 - Posted: 20 Apr 2013, 12:40:11 UTC - in response to Message 1358897.  

Oh, and 327 million kittens can't be wrong, eh?


Only 142 million Maine Coons here mate ...


The biggest cat population on the planet........
And grrrwowing.
"Freedom is just Chaos, with better lighting." Alan Dean Foster

ID: 1358961 · Report as offensive
Richard Haselgrove Project Donor
Volunteer tester

Send message
Joined: 4 Jul 99
Posts: 14649
Credit: 200,643,578
RAC: 874
United Kingdom
Message 1358966 - Posted: 20 Apr 2013, 13:00:17 UTC

According to the new Haveland graphs, 'Results received in last hour' (the blue line on that page) hasn't dipped below 110K for 30 hours solid - in fact, it's averaged more than that for the whole of the last week. That's nearly 22 million results in the 8 days covered by the weekly graph.

And whatever gets returned, has to have been sent out first. That's one hell of a hammering the servers are getting - kudos to all involved.
ID: 1358966 · Report as offensive
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13722
Credit: 208,696,464
RAC: 304
Australia
Message 1359100 - Posted: 20 Apr 2013, 22:44:56 UTC - in response to Message 1358966.  

According to the new Haveland graphs, 'Results received in last hour' (the blue line on that page) hasn't dipped below 110K for 30 hours solid - in fact, it's averaged more than that for the whole of the last week. That's nearly 22 million results in the 8 days covered by the weekly graph.

And whatever gets returned, has to have been sent out first. That's one hell of a hammering the servers are getting - kudos to all involved.

And add to that the numbner of AP WUs in progress & the number returned per hour are approaching as high as they have ever been before as well.
That's a lot of work for the servers to handle.
Grant
Darwin NT
ID: 1359100 · Report as offensive
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13722
Credit: 208,696,464
RAC: 304
Australia
Message 1359165 - Posted: 21 Apr 2013, 4:07:15 UTC - in response to Message 1359100.  


Results returned in the last hour has fallen to 100,000 (still 30,000 more than usual), and the Ready-to-send buffer has actually started to recover.
Just had a look in my work queue & there are a few GPU units that will take more than 3min to crunch. Not many, but some.

So the shorty storm continues, but at least it's abated a bit.
Grant
Darwin NT
ID: 1359165 · Report as offensive
Profile James Sotherden
Avatar

Send message
Joined: 16 May 99
Posts: 10436
Credit: 110,373,059
RAC: 54
United States
Message 1359346 - Posted: 21 Apr 2013, 12:49:13 UTC

I just had a look in my hosts and the GPU's have a boatload of shorties. Have a lot of Ap's though. I like AP's especialy in the 550TI can run one in 4 hours.
[/quote]

Old James
ID: 1359346 · Report as offensive
Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 · 8 . . . 21 · Next

Message boards : Number crunching : Panic Mode On (83) Server Problems?


 
©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.