Panic Mode On (47) Server problems?


log in

Advanced search

Message boards : Number crunching : Panic Mode On (47) Server problems?

Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 · 8 . . . 11 · Next
Author Message
AndrewM
Volunteer tester
Send message
Joined: 5 Jan 08
Posts: 361
Credit: 33,872,609
RAC: 0
Australia
Message 1112111 - Posted: 1 Jun 2011, 18:20:47 UTC

I wonder if data storage is being moved off Thumper? It was a temporary solution/measure after all

Profile [seti.international] Dirk SadowskiProject donor
Volunteer tester
Avatar
Send message
Joined: 6 Apr 07
Posts: 7086
Credit: 60,363,377
RAC: 15,362
Germany
Message 1112637 - Posted: 3 Jun 2011, 13:07:02 UTC
Last modified: 3 Jun 2011, 13:08:35 UTC

I guess I don't need to mention the current probs with UL/DL..

I'm surprised about the following message of BOINC which come from time to time since ~ 00:42 UTC: 'Scheduler request failed: Timeout was reached' - after ~ 60 secs, IIRC normal this happened ~ 600 secs in past..

My machine (BOINC DEV-V6.12.28) is the only one which have current probs to reach the scheduler?


- Best regards! - Sutaru Tsureku, team seti.international founder. - Optimize your PC for higher RAC. - SETI@home needs your help. -
____________
BR

SETI@home Needs your Help ... $10 & U get a Star!

Team seti.international

Das Deutsche Cafe. The German Cafe.

Richard HaselgroveProject donor
Volunteer tester
Send message
Joined: 4 Jul 99
Posts: 8510
Credit: 50,013,374
RAC: 49,311
United Kingdom
Message 1112647 - Posted: 3 Jun 2011, 13:22:32 UTC - in response to Message 1112637.

No, you won't be the only one getting timeouts. I've probably got some too, though I can't be bothered to look.

We were discussing 'impossible deadlines' yesterday, linked to the resending of lost VLAR results. Every 'lost result' event almost always starts with a server timeout - they're common, especially when the comms link is busy.

For those who haven't got it bookmarked yet, here's a live view of the Cricket Graph.



When it's all green like that, you can be sure that the scheduler is issuing tasks, and the download servers are working flat out. Beyond that, it's just the luck of hitting a quiet millisecond in the conversation, so you can get your request in. I've managed it a few times this morning: each time, I've got mostly shorties. The congestion will last until they hit a tape with lower ARs: or they run out of APs to split: or people turn down their cache requests a bit. Until then, sit back and enjoy the show.

DJStarfox
Send message
Joined: 23 May 01
Posts: 1040
Credit: 547,492
RAC: 168
United States
Message 1112648 - Posted: 3 Jun 2011, 13:24:07 UTC

Very strange DL issues....

A new connection gets about 64k then stalls. Repeat for all connections. I think the DL server just needs a reboot.

Richard HaselgroveProject donor
Volunteer tester
Send message
Joined: 4 Jul 99
Posts: 8510
Credit: 50,013,374
RAC: 49,311
United Kingdom
Message 1112650 - Posted: 3 Jun 2011, 13:25:35 UTC - in response to Message 1112648.

I think the DL server just needs a reboot.

I think it just needs a rest and a long, cool drink.

Profile HAL9000
Volunteer tester
Avatar
Send message
Joined: 11 Sep 99
Posts: 4195
Credit: 114,932,676
RAC: 148,949
United States
Message 1112657 - Posted: 3 Jun 2011, 13:37:33 UTC - in response to Message 1112650.

I think the DL server just needs a reboot.

I think it just needs a rest and a long, cool drink.

A liquid cooled OC48 network connection... I would be OK with that as well. :)
____________
SETI@home classic workunits: 93,865 CPU time: 863,447 hours

Join the BP6/VP6 User Group today!

Profile John Neale
Volunteer tester
Avatar
Send message
Joined: 16 Mar 00
Posts: 514
Credit: 3,117,894
RAC: 2,204
South Africa
Message 1112673 - Posted: 3 Jun 2011, 14:35:09 UTC - in response to Message 1112647.

For those who haven't got it bookmarked yet, here's a live view of the Cricket Graph.



Where's the duck? ;)

____________

Profile HelliProject donor
Volunteer tester
Avatar
Send message
Joined: 15 Dec 99
Posts: 703
Credit: 87,985,912
RAC: 70,754
Germany
Message 1112676 - Posted: 3 Jun 2011, 14:47:04 UTC - in response to Message 1112673.
Last modified: 3 Jun 2011, 14:47:45 UTC

For those who haven't got it bookmarked yet, here's a live view of the Cricket Graph.



Where's the duck? ;)


Yup, it's time for Richard's Rubber Ducky. :D

May i post the Link, Richard?



Helli

Richard HaselgroveProject donor
Volunteer tester
Send message
Joined: 4 Jul 99
Posts: 8510
Credit: 50,013,374
RAC: 49,311
United Kingdom
Message 1112677 - Posted: 3 Jun 2011, 14:50:42 UTC - in response to Message 1112673.

Richard HaselgroveProject donor
Volunteer tester
Send message
Joined: 4 Jul 99
Posts: 8510
Credit: 50,013,374
RAC: 49,311
United Kingdom
Message 1112687 - Posted: 3 Jun 2011, 15:19:30 UTC - in response to Message 1112680.


Hellooooooo, ducky!

I'd better not post a sailor picture, then :P

Dave
Avatar
Send message
Joined: 29 Mar 02
Posts: 774
Credit: 23,193,139
RAC: 0
United Kingdom
Message 1112799 - Posted: 3 Jun 2011, 20:46:58 UTC

Floating on a sea of green?

Surely floating on the blue line.

In a green atmosphere...

Maybe we have already found alien life - in the form of a duck that breaths green air!!!

Profile SciManStevProject donor
Volunteer tester
Avatar
Send message
Joined: 20 Jun 99
Posts: 4861
Credit: 81,833,493
RAC: 39,869
United States
Message 1112819 - Posted: 3 Jun 2011, 21:44:12 UTC

I really like that duck!

Steve
____________
Warning, addicted to SETI crunching!
Crunching as a member of GPU Users Group.
GPUUG Website

Richard HaselgroveProject donor
Volunteer tester
Send message
Joined: 4 Jul 99
Posts: 8510
Credit: 50,013,374
RAC: 49,311
United Kingdom
Message 1112840 - Posted: 3 Jun 2011, 23:45:53 UTC - in response to Message 1112637.

I'm surprised about the following message of BOINC which come from time to time since ~ 00:42 UTC: 'Scheduler request failed: Timeout was reached' - after ~ 60 secs, IIRC normal this happened ~ 600 secs in past..

I tested this with my 420M laptop, also running v6.12.28:

04/06/2011 00:33:22 | SETI@home | Sending scheduler request: To fetch work.
04/06/2011 00:33:22 | SETI@home | Reporting 7 completed tasks, requesting new tasks for CPU and NVIDIA GPU
04/06/2011 00:33:22 | SETI@home | [sched_op] CPU work request: 142292.84 seconds; 0.00 CPUs
04/06/2011 00:33:22 | SETI@home | [sched_op] NVIDIA GPU work request: 18929.68 seconds; 0.00 GPUs
04/06/2011 00:35:22 | SETI@home | Scheduler request completed: got 48 new tasks
04/06/2011 00:35:22 | SETI@home | [sched_op] estimated total CPU task duration: 157672 seconds
04/06/2011 00:35:22 | SETI@home | [sched_op] estimated total NVIDIA GPU task duration: 21611 seconds

So extactly two minutes, but no timeout. Of the 48 tasks, 39 were shorties.

Grant (SSSF)
Send message
Joined: 19 Aug 99
Posts: 5823
Credit: 59,078,163
RAC: 47,185
Australia
Message 1112863 - Posted: 4 Jun 2011, 1:56:21 UTC - in response to Message 1112840.


6 days down & now into the 7th day of full network load.
Usually the Results returned per hour are around 50,000 or so. Since the network storage problem outage it hasn't been below 60,000. For the last day it's been above 70,000 & it almost hit 80,000 at one stage.
The hardware is certainly taking a beating, and no end in sight. The last batch of work i got still contained a lot of shorties.
____________
Grant
Darwin NT.

tbretProject donor
Volunteer tester
Avatar
Send message
Joined: 28 May 99
Posts: 2795
Credit: 209,909,741
RAC: 104,060
United States
Message 1112890 - Posted: 4 Jun 2011, 5:01:52 UTC - in response to Message 1112863.


6 days down & now into the 7th day of full network load.
Usually the Results returned per hour are around 50,000 or so. Since the network storage problem outage it hasn't been below 60,000. For the last day it's been above 70,000 & it almost hit 80,000 at one stage.
The hardware is certainly taking a beating, and no end in sight. The last batch of work i got still contained a lot of shorties.


I wonder how much damage the project would suffer if the air conditioning went away under these circumstances?

Currently, "project backoff: 05:16:00"


____________

tbretProject donor
Volunteer tester
Avatar
Send message
Joined: 28 May 99
Posts: 2795
Credit: 209,909,741
RAC: 104,060
United States
Message 1112896 - Posted: 4 Jun 2011, 5:42:18 UTC - in response to Message 1112863.


The hardware is certainly taking a beating, and no end in sight. The last batch of work i got still contained a lot of shorties.


Oooops.

Grant, you and I forgot that the hardware is only working about 1/10th as hard as it was probably designed-for.
____________

Grant (SSSF)
Send message
Joined: 19 Aug 99
Posts: 5823
Credit: 59,078,163
RAC: 47,185
Australia
Message 1112922 - Posted: 4 Jun 2011, 7:31:06 UTC - in response to Message 1112890.

I wonder how much damage the project would suffer if the air conditioning went away under these circumstances?

No damage, but everything would shutdown.


Grant, you and I forgot that the hardware is only working about 1/10th as hard as it was probably designed-for.

Actually, due to the lack of the network storage, parts of it will be running pretty much at their limits.
____________
Grant
Darwin NT.

Dave
Avatar
Send message
Joined: 29 Mar 02
Posts: 774
Credit: 23,193,139
RAC: 0
United Kingdom
Message 1112925 - Posted: 4 Jun 2011, 7:47:40 UTC - in response to Message 1112819.
Last modified: 4 Jun 2011, 7:50:37 UTC

I really like that duck!

Steve


& for those of you that remember Orville on BBC1:

"I 'aaate that duck" ;)!

Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 · 8 . . . 11 · Next

Message boards : Number crunching : Panic Mode On (47) Server problems?

Copyright © 2014 University of California