Panic Mode On (50) Server problems?

Message boards : Number crunching : Panic Mode On (50) Server problems?
Message board moderation

To post messages, you must log in.

1 · 2 · 3 · 4 . . . 10 · Next

AuthorMessage
Profile genfoch01
Avatar

Send message
Joined: 23 Jun 99
Posts: 4
Credit: 1,626,500
RAC: 0
United States
Message 1114227 - Posted: 7 Jun 2011, 11:20:52 UTC

are there still server issues? I am still getting communication deferred when I try to update the seti@home project and I have no tasks running. Ok, I know that means the server is down, I just wanted to verify it was the server not my client.
ID: 1114227 · 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 1125953 - Posted: 8 Jul 2011, 16:37:35 UTC

Welcome to the 50th rendition of this thread!!!!!!!

Please continue.

ID: 1125953 · Report as offensive
Profile rebest Project Donor
Volunteer tester
Avatar

Send message
Joined: 16 Apr 00
Posts: 1296
Credit: 45,357,093
RAC: 0
United States
Message 1126005 - Posted: 8 Jul 2011, 18:51:33 UTC

Uh oh! Server status indicates we're about to run out of new work.

Join the PACK!
ID: 1126005 · Report as offensive
Highlander
Avatar

Send message
Joined: 5 Oct 99
Posts: 167
Credit: 37,987,668
RAC: 16
Germany
Message 1126062 - Posted: 8 Jul 2011, 21:14:43 UTC - in response to Message 1126005.  

Uh oh! Server status indicates we're about to run out of new work.


Oh, your right, it's weekend again :-)
- Performance is not a simple linear function of the number of CPUs you throw at the problem. -
ID: 1126062 · 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 1126065 - Posted: 8 Jul 2011, 21:22:54 UTC

Well, I hope they can figure out the AP processing problems soon and get that back on track.
There must be more than a few datasets lying around right now that have all the MB crunched out of them but not the AP work.
"Freedom is just Chaos, with better lighting." Alan Dean Foster

ID: 1126065 · 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 1126103 - Posted: 8 Jul 2011, 22:33:33 UTC - in response to Message 1126099.  
Last modified: 8 Jul 2011, 22:34:03 UTC

So, Replica finally seems to be online for real, and not only "Green" on the Server status page. As of now though, it's 256,106 seconds (71 hours) behind Master.

Let's see if it will work this time, and actually catch up and stay online.

And 2 new datasets have been added for MB splitting.

Funny, but for some reason the Cricket graphs don't seem to have picked up on that fact yet, and ready to send is climbing.

Caches couldn't be full yet, could they?
Naw....
"Freedom is just Chaos, with better lighting." Alan Dean Foster

ID: 1126103 · Report as offensive
Profile Slavac
Volunteer tester
Avatar

Send message
Joined: 27 Apr 11
Posts: 1932
Credit: 17,952,639
RAC: 0
United States
Message 1126109 - Posted: 8 Jul 2011, 22:55:04 UTC - in response to Message 1126105.  

I'm needing about 4000 tasks to fill mine up and am getting nada.

Interestingly, with no AP work, my system picked up an epic boat load of 6.03 tasks. Wish it wouldn't have done that.


Executive Director GPU Users Group Inc. -
brad@gpuug.org
ID: 1126109 · Report as offensive
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13400
Credit: 208,696,464
RAC: 304
Australia
Message 1126111 - Posted: 8 Jul 2011, 23:02:06 UTC - in response to Message 1126103.  
Last modified: 8 Jul 2011, 23:07:41 UTC

Funny, but for some reason the Cricket graphs don't seem to have picked up on that fact yet, and ready to send is climbing.

Caches couldn't be full yet, could they?
Naw....

Not here, and they've still got a long way to go.
The actual number of Work Units needed to fill the caches isn't that big, but because of the rate at which i return work, and the Ready to Send numbers not withstanding, the majority of requests for work result in No work available or No work sent messaages. Lately it's mostly been No work sent.

I suspect the Ready to Send buffer is only growing because for some reason downloads are dropping off, but i doubt the demand for work is.
Grant
Darwin NT
ID: 1126111 · Report as offensive
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13400
Credit: 208,696,464
RAC: 304
Australia
Message 1126159 - Posted: 9 Jul 2011, 2:47:46 UTC


Looks like it's almost dead.
There are ready to send Work Units (not many, but they're there), yet the network traffic contiues to decline. And other than the odd Work Unit, most Scheduler requests result in "No work available" messages.
Grant
Darwin NT
ID: 1126159 · Report as offensive
Profile HAL9000
Volunteer tester
Avatar

Send message
Joined: 11 Sep 99
Posts: 6533
Credit: 196,805,888
RAC: 57
United States
Message 1126178 - Posted: 9 Jul 2011, 4:17:23 UTC - in response to Message 1126105.  

So, Replica finally seems to be online for real, and not only "Green" on the Server status page. As of now though, it's 256,106 seconds (71 hours) behind Master.

Let's see if it will work this time, and actually catch up and stay online.

And 2 new datasets have been added for MB splitting.

Funny, but for some reason the Cricket graphs don't seem to have picked up on that fact yet, and ready to send is climbing.

Caches couldn't be full yet, could they?
Naw....



Well Results out in the field is 6,502,907, so that's pretty high too. But half a million more and most caches would be filled I think.


Hmm I don't know about that. I just switched 2 of my GPU's at home back on since I am mostly finished moving into my new place. They are doing a fine job of slurping down tasks and spitting them back out in a hurry. Maybe another 5,000,000 out in the field will do :)
SETI@home classic workunits: 93,865 CPU time: 863,447 hours
Join the BP6/VP6 User Group today!
ID: 1126178 · 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: 21187
Credit: 416,307,556
RAC: 380
United Kingdom
Message 1126202 - Posted: 9 Jul 2011, 8:24:12 UTC

A few things to consider:
- the backup database is DAYS behind the master, so the various guestimates are more off than usual.
- its a weekend and at least one of the S@H servers will demand time off...
- the creation rate is very low, and probably unable to keep up with the demand rate
- its a weekend and at least one of the S@H servers will demand time off...
- the ready to use cache is very low (varies from 0-2,000, used to sit at around 250,000)
- its a weekend and at least one of the S@H servers will demand time off...

We do know there is a problem with the AP side of things, and that whole part of the system is turned off, but what we don't know is what side effects this is having on the other side of the fence...

Bob Smith
Member of Seti PIPPS (Pluto is a Planet Protest Society)
Somewhere in the (un)known Universe?
ID: 1126202 · Report as offensive
Profile S@NL - XP_Freak

Send message
Joined: 10 Jul 99
Posts: 99
Credit: 6,248,265
RAC: 0
Netherlands
Message 1126203 - Posted: 9 Jul 2011, 8:39:06 UTC

I thought maybe I can help the up/download servers a bit by downloading AP-wu's.
But with the assimilators down, I am the one who gets punnished for crunching AP-wu's. (No credit)

http://setiathome.berkeley.edu/workunit.php?wuid=753788639

Goodbye Seti Classic
ID: 1126203 · Report as offensive
Profile Link
Avatar

Send message
Joined: 18 Sep 03
Posts: 834
Credit: 1,807,369
RAC: 0
Germany
Message 1126206 - Posted: 9 Jul 2011, 9:26:23 UTC - in response to Message 1126203.  

http://setiathome.berkeley.edu/workunit.php?wuid=753788639

I'm sorry to tell you that, but IIRC in such case the last returned result won't get any credit, I had that once myself with a AP-result retuned shortly after the deadline.
ID: 1126206 · Report as offensive
Profile S@NL - XP_Freak

Send message
Joined: 10 Jul 99
Posts: 99
Credit: 6,248,265
RAC: 0
Netherlands
Message 1126214 - Posted: 9 Jul 2011, 10:26:32 UTC - in response to Message 1126206.  

http://setiathome.berkeley.edu/workunit.php?wuid=753788639

I'm sorry to tell you that, but IIRC in such case the last returned result won't get any credit, I had that once myself with a AP-result retuned shortly after the deadline.
Well, we will see.
I did not send it in too late, I just got it late.
Two results were send in on 13 June, and I got mine 27 June.


Goodbye Seti Classic
ID: 1126214 · Report as offensive
Profile Mike Special Project $75 donor
Volunteer tester
Avatar

Send message
Joined: 17 Feb 01
Posts: 33595
Credit: 79,922,639
RAC: 80
Germany
Message 1126219 - Posted: 9 Jul 2011, 11:08:10 UTC


They will get credit probably so long its not returned by third host.



With each crime and every kindness we birth our future.
ID: 1126219 · Report as offensive
Profile S@NL - XP_Freak

Send message
Joined: 10 Jul 99
Posts: 99
Credit: 6,248,265
RAC: 0
Netherlands
Message 1126225 - Posted: 9 Jul 2011, 11:15:01 UTC - in response to Message 1126219.  


They will get credit probably so long its not returned by third host.

I was the third host, and I did return de result yesterday.

Goodbye Seti Classic
ID: 1126225 · Report as offensive
Profile Link
Avatar

Send message
Joined: 18 Sep 03
Posts: 834
Credit: 1,807,369
RAC: 0
Germany
Message 1126227 - Posted: 9 Jul 2011, 11:23:50 UTC - in response to Message 1126219.  


They will get credit probably so long its not returned by third host.

The problem with AP is (unless they fixed it), that the first two results validate against each other and the third one gets something like "could not validate" or something like that, even if returned in time.
ID: 1126227 · 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: 21187
Credit: 416,307,556
RAC: 380
United Kingdom
Message 1126231 - Posted: 9 Jul 2011, 11:48:13 UTC

Certainly something strange with the way that AP wu was sent out a third time, before the initial expiry date. Is this a symptom of the problems that are upsetting the AP process, or is it something totally unrelated? (my guess is its a symptom...)
Bob Smith
Member of Seti PIPPS (Pluto is a Planet Protest Society)
Somewhere in the (un)known Universe?
ID: 1126231 · Report as offensive
Profile Sutaru Tsureku
Volunteer tester

Send message
Joined: 6 Apr 07
Posts: 7105
Credit: 147,663,825
RAC: 5
Germany
Message 1126233 - Posted: 9 Jul 2011, 12:18:01 UTC - in response to Message 1126231.  
Last modified: 9 Jul 2011, 12:20:55 UTC

http://setiathome.berkeley.edu/workunit.php?wuid=753788639

Certainly something strange with the way that AP wu was sent out a third time, before the initial expiry date. Is this a symptom of the problems that are upsetting the AP process, or is it something totally unrelated? (my guess is its a symptom...)


The deadline of the first two results was 27 Jun 2011 - 4:26:56 UTC.

The 2nd result came in time (13 Jun 2011 - 17:24:07 UTC).
The 1st not, so a 3rd WU was sent out.
But in the meantime the 1st result came (2 Jul 2011 - 6:11:09 UTC), and the two results got the Cr.
The 3rd result is (maybe) for nothing.


BTW. The S@h crew know about this strange AP behavior?


BTW. I thought BOINC delete a WU if it will not finish before deadline, so the 1st results haven't calculated.


- Best regards! - Sutaru Tsureku, team seti.international founder. - Optimize your PC for higher RAC. - SETI@home needs your help. -
ID: 1126233 · Report as offensive
Profile S@NL - XP_Freak

Send message
Joined: 10 Jul 99
Posts: 99
Credit: 6,248,265
RAC: 0
Netherlands
Message 1126245 - Posted: 9 Jul 2011, 13:08:22 UTC - in response to Message 1126233.  

http://setiathome.berkeley.edu/workunit.php?wuid=753788639

The 1st not, so a 3rd WU was sent out.
But in the meantime the 1st result came (2 Jul 2011 - 6:11:09 UTC)


You are right. I did misinterprid.

But mine should not have started on July 8, it should have been deleted before my machine startedto crunch this one, for there were already two retults validated.


Goodbye Seti Classic
ID: 1126245 · Report as offensive
1 · 2 · 3 · 4 . . . 10 · Next

Message boards : Number crunching : Panic Mode On (50) 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.