Panic Mode On (90) Server Problems?

Message boards : Number crunching : Panic Mode On (90) Server Problems?
Message board moderation

To post messages, you must log in.

Previous · 1 . . . 18 · 19 · 20 · 21 · 22 · 23 · 24 · Next

AuthorMessage
Profile Zalster Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 27 May 99
Posts: 5517
Credit: 528,817,460
RAC: 242
United States
Message 1586818 - Posted: 14 Oct 2014, 21:38:46 UTC - in response to Message 1586813.  

Definite lag on the trying to view my computers or tasks. Hmm....
ID: 1586818 · Report as offensive
Profile Wiggo
Avatar

Send message
Joined: 24 Jan 00
Posts: 34744
Credit: 261,360,520
RAC: 489
Australia
Message 1586826 - Posted: 14 Oct 2014, 22:00:54 UTC

Well my tasks are being reported, according to the servers, though my rigs don't seem to think so with only timeouts being reported at this end.

Cheers.
ID: 1586826 · 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 1586828 - Posted: 14 Oct 2014, 22:10:42 UTC

What works for me (well, it has worked in the past) is to do a first 'report only' update with NNT set:

14/10/2014 23:05:39 | SETI@home | Reporting 73 completed tasks
14/10/2014 23:05:39 | SETI@home | Not requesting tasks: "no new tasks" requested via Manager
14/10/2014 23:07:11 | SETI@home | Scheduler request completed
14/10/2014 23:07:11 | SETI@home | [sched_op] handle_scheduler_reply(): got ack for task 26jn11aa.28779.24772.244813135879.12.113_0
...

Once those are out of the way, I can think about getting new work as a separate exercise.
ID: 1586828 · 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 1586833 - Posted: 14 Oct 2014, 22:23:50 UTC - in response to Message 1586830.  

Same connection issues as after every outage. Nothing new about that. After a couple of hours, it will be fine again, as usual.

They've usually managed to put it back together by the time I get back from the pub...

That minute-and-a-half to process a report-only RPC is certainly outside the normal range, even (I'd say) for a Tuesday.
ID: 1586833 · Report as offensive
Profile Wiggo
Avatar

Send message
Joined: 24 Jan 00
Posts: 34744
Credit: 261,360,520
RAC: 489
Australia
Message 1586875 - Posted: 15 Oct 2014, 0:00:48 UTC

That trick worked for me this time Richard and now I'm finally getting some new work (as small as the amount is and after all the Windows updates were installed here). ;-)

Cheers.
ID: 1586875 · Report as offensive
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13720
Credit: 208,696,464
RAC: 304
Australia
Message 1587019 - Posted: 15 Oct 2014, 7:44:28 UTC - in response to Message 1586875.  

I'm reporting & getting work OK, but it's taking around 10 seconds or so to get a response from the Scheduler. Usually it's 5 or less.
And My Account page is slow to load, as are looking at any tasks.
Grant
Darwin NT
ID: 1587019 · Report as offensive
Cosmic_Ocean
Avatar

Send message
Joined: 23 Dec 00
Posts: 3027
Credit: 13,516,867
RAC: 13
United States
Message 1587058 - Posted: 15 Oct 2014, 9:30:13 UTC - in response to Message 1587019.  

I'm reporting & getting work OK, but it's taking around 10 seconds or so to get a response from the Scheduler. Usually it's 5 or less.
And My Account page is slow to load, as are looking at any tasks.

I reported a couple of finished v6's a little while ago and it took nearly 90 seconds for the scheduler to reply. It seems to be getting hammered pretty hard, or something is gumming up the works.
Linux laptop:
record uptime: 1511d 20h 19m (ended due to the power brick giving-up)
ID: 1587058 · 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 1587062 - Posted: 15 Oct 2014, 9:37:51 UTC - in response to Message 1587058.  

I'm reporting & getting work OK, but it's taking around 10 seconds or so to get a response from the Scheduler. Usually it's 5 or less.
And My Account page is slow to load, as are looking at any tasks.

I reported a couple of finished v6's a little while ago and it took nearly 90 seconds for the scheduler to reply. It seems to be getting hammered pretty hard, or something is gumming up the works.

It's just turned round one of mine in 3 seconds:

15/10/2014 10:34:29 | SETI@home | Reporting 4 completed tasks
15/10/2014 10:34:32 | SETI@home | Scheduler request completed: got 9 new tasks

There is sometimes extra delay - I think at around this time of day - when the database is busy preparing the daily statistics export.
ID: 1587062 · Report as offensive
Cosmic_Ocean
Avatar

Send message
Joined: 23 Dec 00
Posts: 3027
Credit: 13,516,867
RAC: 13
United States
Message 1587181 - Posted: 15 Oct 2014, 15:53:44 UTC

That's interesting. I'm looking through the last few v6's that I'm finishing and reporting, and this one that was a _5 task was sent to be a tie-breaker.

wu 1604968226

I found 4 singles and 10 repetitive. The nvidia GPU found 0/10. I don't know what the stock linux CPU app found, but all three of us got credit. I didn't think credit was supposed to be granted when the number of pulses found didn't even match. I know it'll validate if they are "close enough," but I guess the 10 repetitive the GPU found matched what us two CPU apps found?
Linux laptop:
record uptime: 1511d 20h 19m (ended due to the power brick giving-up)
ID: 1587181 · Report as offensive
Profile HAL9000
Volunteer tester
Avatar

Send message
Joined: 11 Sep 99
Posts: 6534
Credit: 196,805,888
RAC: 57
United States
Message 1587188 - Posted: 15 Oct 2014, 16:24:39 UTC
Last modified: 15 Oct 2014, 16:31:33 UTC

I got a little excited when I looked at some of my machines and saw 200 valid. However it looks like AP v7 taste are not being purged. Which could very well be on purpose, but it may not. The dates on the valid tasks go back to October 10th & anything reported prior to that looks to be purged.
SETI@home classic workunits: 93,865 CPU time: 863,447 hours
Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[
ID: 1587188 · Report as offensive
Josef W. Segur
Volunteer developer
Volunteer tester

Send message
Joined: 30 Oct 99
Posts: 4504
Credit: 1,414,761
RAC: 0
United States
Message 1587277 - Posted: 15 Oct 2014, 18:45:36 UTC - in response to Message 1587181.  

That's interesting. I'm looking through the last few v6's that I'm finishing and reporting, and this one that was a _5 task was sent to be a tie-breaker.

wu 1604968226

I found 4 singles and 10 repetitive. The nvidia GPU found 0/10. I don't know what the stock linux CPU app found, but all three of us got credit. I didn't think credit was supposed to be granted when the number of pulses found didn't even match. I know it'll validate if they are "close enough," but I guess the 10 repetitive the GPU found matched what us two CPU apps found?

Correct, to get credit on the "weakly similar" basis only half the signals have to match. The _0 AstroPulse v6 v6.03 task was declared canonical and assimilated, so all its signals matched yours.

The _2 NVIDIA GPU task was run on a GT 330 (Compute Capability 1.2) with the 340.52 drivers, so it isn't surprising there were no single pulses found. The @Pre-FERMI nVidia GPU users: Important warning applies to AP v6 as much as AP v7.
                                                                  Joe
ID: 1587277 · Report as offensive
Cosmic_Ocean
Avatar

Send message
Joined: 23 Dec 00
Posts: 3027
Credit: 13,516,867
RAC: 13
United States
Message 1587390 - Posted: 15 Oct 2014, 20:52:23 UTC - in response to Message 1587277.  

The _2 NVIDIA GPU task was run on a GT 330 (Compute Capability 1.2) with the 340.52 drivers, so it isn't surprising there were no single pulses found. The @Pre-FERMI nVidia GPU users: Important warning applies to AP v6 as much as AP v7.
                                                                  Joe

Thanks Joe. I went ahead and PMed the owner of the GT 330 to let them know. I've sent out a couple of PMs in the past week along the lines of "your machine [id#] is producing a significant amount of errors. If you are not aware there is a problem or what it could be, post over in Number Crunching and ask for help. The resident experts there will get your problem sorted out."

I have not gotten any replies, but I haven't followed up on any of those machines though. I hear that's pretty much par for the course.
Linux laptop:
record uptime: 1511d 20h 19m (ended due to the power brick giving-up)
ID: 1587390 · Report as offensive
Darth Beaver Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Avatar

Send message
Joined: 20 Aug 99
Posts: 6728
Credit: 21,443,075
RAC: 3
Australia
Message 1587995 - Posted: 16 Oct 2014, 21:29:37 UTC

Is any body having trouble downloading units ??
ID: 1587995 · Report as offensive
Claggy
Volunteer tester

Send message
Joined: 5 Jul 99
Posts: 4654
Credit: 47,537,079
RAC: 4
United Kingdom
Message 1588005 - Posted: 16 Oct 2014, 21:47:44 UTC - in response to Message 1587995.  

Is any body having trouble downloading units ??

Not really:

16/10/2014 22:46:50 | SETI@home | Started download of ap_16no11af_B3_P1_00330_20141016_26664.wu
16/10/2014 22:46:59 | SETI@home | Finished download of ap_16no11af_B3_P1_00330_20141016_26664.wu


Claggy
ID: 1588005 · Report as offensive
Profile HAL9000
Volunteer tester
Avatar

Send message
Joined: 11 Sep 99
Posts: 6534
Credit: 196,805,888
RAC: 57
United States
Message 1588089 - Posted: 17 Oct 2014, 2:13:28 UTC - in response to Message 1577814.  

I can also confirm this, if you have the "Don't' move sticky posts to the top" box ticked.

If I disable Don't move sticky posts to top it also goes away & returns once enabled again.

Thanks both, I can reproduce that here. I'll pass it on. David is taking a breather after yesterday, so it may take a little while - it doesn't seem to be a fatal problem, just untidy.

And he's just fixed it. I sincerely hope that was the last batch.

I found 2 other minor cosmetic issues on Main & Beta.

On the team management page:
http://setiathome.berkeley.edu/team_manage.php?teamid=30229
Other resources for BOINC team admins are available from a third-party site, http://www.boincteams.com

The link to www.boincteams.com is out of date. The site now seems to be a personal blog.

On the team forum management page:
http://setiathome.berkeley.edu/team_forum.php?teamid=30229&cmd=manage
Notice: Undefined variable: tokens in /disks/carolyn/b/home/boincadm/projects/sah/html/user/team_forum.php on line 91
SETI@home classic workunits: 93,865 CPU time: 863,447 hours
Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[
ID: 1588089 · 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 1588161 - Posted: 17 Oct 2014, 6:34:52 UTC - in response to Message 1588089.  



On the team management page:
http://setiathome.berkeley.edu/team_manage.php?teamid=30229
Other resources for BOINC team admins are available from a third-party site, http://www.boincteams.com

The link to www.boincteams.com is out of date. The site now seems to be a personal blog.


Actually it looks like it was swooped up by one of the lovely spammers as it all ads in danish.

ID: 1588161 · Report as offensive
Profile Julie
Volunteer moderator
Volunteer tester
Avatar

Send message
Joined: 28 Oct 09
Posts: 34041
Credit: 18,883,157
RAC: 18
Belgium
Message 1588166 - Posted: 17 Oct 2014, 6:41:59 UTC

I completed a 40 second AstroPulse v7 v7.00 this morning, while I was drinking my coffee:)

http://setiathome.berkeley.edu/results.php?hostid=7271690&offset=0&show_names=0&state=0&appid=20
rOZZ
Music
Pictures
ID: 1588166 · Report as offensive
Thomas
Volunteer tester

Send message
Joined: 9 Dec 11
Posts: 1499
Credit: 1,345,576
RAC: 0
France
Message 1588168 - Posted: 17 Oct 2014, 6:42:33 UTC
Last modified: 17 Oct 2014, 6:43:39 UTC

Little question : on the SSP, this is a few days that the number of AP's ready to send is always zero while AP's are generated :(
Normal or not ?
ID: 1588168 · Report as offensive
woohoo
Volunteer tester

Send message
Joined: 30 Oct 13
Posts: 972
Credit: 165,671,404
RAC: 5
United States
Message 1588169 - Posted: 17 Oct 2014, 6:44:09 UTC - in response to Message 1588166.  

some are even shorter than that
ID: 1588169 · Report as offensive
woohoo
Volunteer tester

Send message
Joined: 30 Oct 13
Posts: 972
Credit: 165,671,404
RAC: 5
United States
Message 1588174 - Posted: 17 Oct 2014, 6:50:08 UTC - in response to Message 1588168.  

I think a lot of people ran their tasks down to zero, installed the new Lunatics and are now filling their caches again. High demand and low supply. I want to do the same thing but I'm waiting until I run dry. They keep loading new tapes to top me off.

Also since blanking for GPU tasks is done on the GPU now, people are getting done with their tasks faster and asking for more.
ID: 1588174 · Report as offensive
Previous · 1 . . . 18 · 19 · 20 · 21 · 22 · 23 · 24 · Next

Message boards : Number crunching : Panic Mode On (90) 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.