Panic Mode On (112) Server Problems?

Message boards : Number crunching : Panic Mode On (112) Server Problems?
Message board moderation

To post messages, you must log in.

Previous · 1 . . . 28 · 29 · 30 · 31 · 32 · 33 · Next

AuthorMessage
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13722
Credit: 208,696,464
RAC: 304
Australia
Message 1946653 - Posted: 28 Jul 2018, 8:20:17 UTC

There is a single GBT splitter running on the last remaining OUMUAMUA file. Hopefully once it's fully errored out, the other splitters will fire up on the other data files.
Grant
Darwin NT
ID: 1946653 · Report as offensive
Speedy
Volunteer tester
Avatar

Send message
Joined: 26 Jun 04
Posts: 1639
Credit: 12,921,799
RAC: 89
New Zealand
Message 1946657 - Posted: 28 Jul 2018, 8:35:49 UTC - in response to Message 1946653.  

There is a single GBT splitter running on the last remaining OUMUAMUA file. Hopefully once it's fully errored out, the other splitters will fire up on the other data files.

I was thinking the same thing. I wonder how many tasks there are per channel? Currently work as been split at about 1.6 tasks per second. 96 tasks per minute
ID: 1946657 · 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 1946658 - Posted: 28 Jul 2018, 8:39:23 UTC - in response to Message 1946657.  

1.6 tasks per second ..
That is the amount of resends going through the system, not what is coming out of the splitters.
ID: 1946658 · Report as offensive
Speedy
Volunteer tester
Avatar

Send message
Joined: 26 Jun 04
Posts: 1639
Credit: 12,921,799
RAC: 89
New Zealand
Message 1946659 - Posted: 28 Jul 2018, 8:42:57 UTC - in response to Message 1946658.  

1.6 tasks per second ..
That is the amount of resends going through the system, not what is coming out of the splitters.

I wouldn't have thought they were counted because they are already within the system they are not being created but I could be wrong
ID: 1946659 · Report as offensive
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13722
Credit: 208,696,464
RAC: 304
Australia
Message 1946662 - Posted: 28 Jul 2018, 9:30:46 UTC - in response to Message 1946653.  

There is a single GBT splitter running on the last remaining OUMUAMUA file. Hopefully once it's fully errored out, the other splitters will fire up on the other data files.

That file has errored out, and the other splitters have started up.
It'll take a while before they start producing much work, but at least it's on it's way.
Grant
Darwin NT
ID: 1946662 · 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 1946695 - Posted: 28 Jul 2018, 17:47:31 UTC - in response to Message 1946659.  

I wouldn't have thought they were counted because they are already within the system they are not being created but I could be wrong
A new task (= result) is created, which is what the SSP says. But it's created from the old workunit, not from new data.
ID: 1946695 · Report as offensive
Speedy
Volunteer tester
Avatar

Send message
Joined: 26 Jun 04
Posts: 1639
Credit: 12,921,799
RAC: 89
New Zealand
Message 1946724 - Posted: 28 Jul 2018, 22:28:54 UTC - in response to Message 1946695.  

I wouldn't have thought they were counted because they are already within the system they are not being created but I could be wrong
A new task (= result) is created, which is what the SSP says. But it's created from the old workunit, not from new data.

Thanks Richard for the clarification. You learn something new every day I thought resends weren't included in that count
ID: 1946724 · Report as offensive
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13722
Credit: 208,696,464
RAC: 304
Australia
Message 1946725 - Posted: 28 Jul 2018, 22:34:51 UTC

I'm wondering if there's been a hardware failure with Carolyn, the replica's been down for a couple of weeks now.
Grant
Darwin NT
ID: 1946725 · Report as offensive
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 1947173 - Posted: 31 Jul 2018, 23:15:54 UTC

Late to go down and late to come back..
ID: 1947173 · Report as offensive
Profile Unixchick Project Donor
Avatar

Send message
Joined: 5 Mar 12
Posts: 815
Credit: 2,361,516
RAC: 22
United States
Message 1947174 - Posted: 31 Jul 2018, 23:29:22 UTC

wow... 7 hour outage... hope all is ok
ID: 1947174 · Report as offensive
Profile Keith Myers Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 29 Apr 01
Posts: 13161
Credit: 1,160,866,277
RAC: 1,873
United States
Message 1947176 - Posted: 31 Jul 2018, 23:55:21 UTC

Wonder if the SSP is really correct. Not getting any work on requests though the RTS shows 587K of tasks.
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 1947176 · Report as offensive
Profile Unixchick Project Donor
Avatar

Send message
Joined: 5 Mar 12
Posts: 815
Credit: 2,361,516
RAC: 22
United States
Message 1947178 - Posted: 1 Aug 2018, 0:03:16 UTC

They added a bunch of data and have 28 channels processing instead of the normal 14, so hopefully everyone will get new tasks to crunch once the traffic jam lessens.
ID: 1947178 · Report as offensive
juan BFP Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 16 Mar 07
Posts: 9786
Credit: 572,710,851
RAC: 3,799
Panama
Message 1947183 - Posted: 1 Aug 2018, 0:42:38 UTC
Last modified: 1 Aug 2018, 0:44:44 UTC

Nothing, Nada here too.

Host running dry, at least i save about 1/2 of kw per hr while that happening.
ID: 1947183 · Report as offensive
TBar
Volunteer tester

Send message
Joined: 22 May 99
Posts: 5204
Credit: 840,779,836
RAC: 2,768
United States
Message 1947194 - Posted: 1 Aug 2018, 1:52:27 UTC

Tasks are moving now.
Unfortunately, just as all previous times, the Splitters are not Splitting, thus, we will be Out of Work very shortly.
Why is it always the Same? The Splitters wait until the RTS is Empty Before they start ramping up?
Why can't they Start Before the RTS is Empty after an Outage?
ID: 1947194 · Report as offensive
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13722
Credit: 208,696,464
RAC: 304
Australia
Message 1947197 - Posted: 1 Aug 2018, 2:35:34 UTC - in response to Message 1947194.  
Last modified: 1 Aug 2018, 2:40:11 UTC

Tasks are moving now.
Unfortunately, just as all previous times, the Splitters are not Splitting, thus, we will be Out of Work very shortly.
Why is it always the Same? The Splitters wait until the RTS is Empty Before they start ramping up?
Why can't they Start Before the RTS is Empty after an Outage?

In the past the explanation has been that it can take up to a few hours for enough data to be read from disk and cached for the splitters to be able to pump out work at a reasonable rate.

Edit- at the moment actually getting work allocated, and then downloading it, is more problematic than it usually is after an outage.
Whatever is causing those issues many also be affecting the splitters ramping up their output, because the splitters are also struggling more than usual as well.
Grant
Darwin NT
ID: 1947197 · Report as offensive
Stephen "Heretic" Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 20 Sep 12
Posts: 5557
Credit: 192,787,363
RAC: 628
Australia
Message 1947208 - Posted: 1 Aug 2018, 4:09:28 UTC - in response to Message 1947174.  

wow... 7 hour outage... hope all is ok

. . After the 10 to 14 hour outages that had become the norm for a while 7 hours is not so bad. But it is a little longer than the recent norm of between 4 and 6 hours. It started pretty much on schedule , 2am AEST, but went for that extra hour or two. Are people apart from Keith getting work requests filled OK?

Stephen

? ?
ID: 1947208 · Report as offensive
Profile Jimbocous Project Donor
Volunteer tester
Avatar

Send message
Joined: 1 Apr 13
Posts: 1849
Credit: 268,616,081
RAC: 1,349
United States
Message 1947213 - Posted: 1 Aug 2018, 5:36:07 UTC - in response to Message 1947208.  

wow... 7 hour outage... hope all is ok

. . After the 10 to 14 hour outages that had become the norm for a while 7 hours is not so bad. But it is a little longer than the recent norm of between 4 and 6 hours. It started pretty much on schedule , 2am AEST, but went for that extra hour or two. Are people apart from Keith getting work requests filled OK?

Stephen

? ?

Cache filled right up here ...
ID: 1947213 · Report as offensive
Profile Keith Myers Special Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 29 Apr 01
Posts: 13161
Credit: 1,160,866,277
RAC: 1,873
United States
Message 1947218 - Posted: 1 Aug 2018, 7:01:58 UTC

I started getting bits of work a couple hours after the project came back. But only in batches of 60 tasks or so and I would run those dry before I got any more. I'm all full now on all crunchers.
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 1947218 · Report as offensive
Stephen "Heretic" Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor
Volunteer tester
Avatar

Send message
Joined: 20 Sep 12
Posts: 5557
Credit: 192,787,363
RAC: 628
Australia
Message 1947222 - Posted: 1 Aug 2018, 8:55:10 UTC - in response to Message 1947218.  

I started getting bits of work a couple hours after the project came back. But only in batches of 60 tasks or so and I would run those dry before I got any more. I'm all full now on all crunchers.

. . I do find it disconcerting how they load new tapes and these immediately pre-empt any other tapes currently splitting...

Stephen

:(
ID: 1947222 · Report as offensive
Profile Unixchick Project Donor
Avatar

Send message
Joined: 5 Mar 12
Posts: 815
Credit: 2,361,516
RAC: 22
United States
Message 1947286 - Posted: 1 Aug 2018, 15:46:06 UTC - in response to Message 1947222.  


. . I do find it disconcerting how they load new tapes and these immediately pre-empt any other tapes currently splitting...

Stephen

:(


I agree... it offends my OCD to not have them finish the previous data set before starting on a new one. The splitters do seem to do them in date order so they might be able to easily reorder the list on the server status page to make it a bit more orderly.

It is especially weird right now as they seem to have two sets of 14 processes running in two different sections of the data.
ID: 1947286 · Report as offensive
Previous · 1 . . . 28 · 29 · 30 · 31 · 32 · 33 · Next

Message boards : Number crunching : Panic Mode On (112) 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.