Panic Mode On (93) Server Problems?

Message boards : Number crunching : Panic Mode On (93) Server Problems?
Message board moderation

To post messages, you must log in.

Previous · 1 · 2 · 3 · 4 · 5 . . . 24 · Next

AuthorMessage
Dena Wiltsie
Volunteer tester

Send message
Joined: 19 Apr 01
Posts: 1628
Credit: 24,230,968
RAC: 26
United States
Message 1611485 - Posted: 10 Dec 2014, 1:47:02 UTC

It's no longer dead. The cricket graph went vertical at 450mb/second.
ID: 1611485 · Report as offensive
Profile Jimbocous Project Donor
Volunteer tester
Avatar

Send message
Joined: 1 Apr 13
Posts: 1853
Credit: 268,616,081
RAC: 1,349
United States
Message 1611495 - Posted: 10 Dec 2014, 2:02:04 UTC - in response to Message 1611485.  

It's no longer dead. The cricket graph went vertical at 450mb/second.

Much better, SSP back and slowdown on tasks is gone. Wonder if it was just a traffic slam?
ID: 1611495 · Report as offensive
Cruncher-American Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor

Send message
Joined: 25 Mar 02
Posts: 1513
Credit: 370,893,186
RAC: 340
United States
Message 1611508 - Posted: 10 Dec 2014, 2:33:48 UTC - in response to Message 1611269.  

God Bless CreditNew:

9 Dec 2014, 5:06:05 UTC Completed and validated 5.34 1.05 490.39 AstroPulse v7 Anonymous platform (NVIDIA GPU)



Just to quote myself here....

I now have FIVE of these APs validated (out of 30 or so validated, the others of which gave roughly similar credit, but ran in the 500-1500 second area).

What's going on? Has CreditNew suddenly grown a conscience, and decided to surreptitiously pay back for all the under-paid credit since it was started?

Good on him, if so!
ID: 1611508 · Report as offensive
Cosmic_Ocean
Avatar

Send message
Joined: 23 Dec 00
Posts: 3027
Credit: 13,516,867
RAC: 13
United States
Message 1611512 - Posted: 10 Dec 2014, 2:45:51 UTC

Well then, the crickets exploded into life and I've gotten two back-to-back work requests that gave me two APs each. And everything here on the website seems to respond a lot faster now.

I'm still guessing it was a DB query that was running in high-priority and slowing everything else down.

Actually, after checking the SSP again, and then pulling up the AP graphs, there was a sudden drop in both results and WUs "waiting for DB purge" at coincidentally the same time the cricket graph went vertical. That's what I'm thinking was happening. *nodnod*
Linux laptop:
record uptime: 1511d 20h 19m (ended due to the power brick giving-up)
ID: 1611512 · Report as offensive
Profile betreger Project Donor
Avatar

Send message
Joined: 29 Jun 99
Posts: 11361
Credit: 29,581,041
RAC: 66
United States
Message 1611516 - Posted: 10 Dec 2014, 2:49:24 UTC - in response to Message 1611512.  

I'm still guessing it was a DB query that was running in high-priority and slowing everything else down.

Yes it was slow now it is not.
ID: 1611516 · Report as offensive
David S
Volunteer tester
Avatar

Send message
Joined: 4 Oct 99
Posts: 18352
Credit: 27,761,924
RAC: 12
United States
Message 1611517 - Posted: 10 Dec 2014, 2:50:15 UTC

Hmm. Unintended consequences, I guess.

With reference to the "Need guidance" thread, with those 5 tasks suspended, now Boinc Manager won't ask for any more work. I kicked it to report some finished ones and there's a line that says "Not requesting tasks: some task is suspended via Manager".

I'm not sure what to do now. I don't know if it has enough to last until I have time to babysit it again. I'd rather not abort those APs until someone comes up with a different set of switches for me, though. I suppose I could just delete the switches and put back the blank text file.
David
Sitting on my butt while others boldly go,
Waiting for a message from a small furry creature from Alpha Centauri.

ID: 1611517 · Report as offensive
Profile cliff
Avatar

Send message
Joined: 16 Dec 07
Posts: 625
Credit: 3,590,440
RAC: 0
United Kingdom
Message 1611541 - Posted: 10 Dec 2014, 4:01:15 UTC - in response to Message 1611517.  
Last modified: 10 Dec 2014, 4:01:52 UTC

Hi David,
That's the way BM works with suspended tasks, the trick is to resume all tasks, then punch update, when you get the server to send some tasks, suspend any you want again:-)

Works OK for me, enables the running of part completed WU before those that going take the wingman days/weeks to complete, so faster wingmen get faster completions..

Regards,
Cliff,
Been there, Done that, Still no damm T shirt!
ID: 1611541 · Report as offensive
Dena Wiltsie
Volunteer tester

Send message
Joined: 19 Apr 01
Posts: 1628
Credit: 24,230,968
RAC: 26
United States
Message 1611547 - Posted: 10 Dec 2014, 4:24:21 UTC - in response to Message 1611495.  

It's no longer dead. The cricket graph went vertical at 450mb/second.

Much better, SSP back and slowdown on tasks is gone. Wonder if it was just a traffic slam?

Something didn't restart correctly. I was on the site when they dropped it and brought it right back up. It wasn't down for more than a few seconds.
ID: 1611547 · Report as offensive
Profile Julie
Volunteer moderator
Volunteer tester
Avatar

Send message
Joined: 28 Oct 09
Posts: 34053
Credit: 18,883,157
RAC: 18
Belgium
Message 1611613 - Posted: 10 Dec 2014, 8:17:23 UTC - in response to Message 1611459.  

It's dead Jim, it's dead...



I see the upload server is still working, maybe there's still hope...
rOZZ
Music
Pictures
ID: 1611613 · Report as offensive
Profile Wiggo
Avatar

Send message
Joined: 24 Jan 00
Posts: 34772
Credit: 261,360,520
RAC: 489
Australia
Message 1611628 - Posted: 10 Dec 2014, 9:08:13 UTC

All has been going well here, but I see that we have 4 AP splitters working on a single file again, 07jn14ab.

Cheers.
ID: 1611628 · Report as offensive
Profile Raistmer
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 16 Jun 01
Posts: 6325
Credit: 106,370,077
RAC: 121
Russia
Message 1611772 - Posted: 10 Dec 2014, 15:45:25 UTC

Server down, is it?
ID: 1611772 · Report as offensive
Profile Julie
Volunteer moderator
Volunteer tester
Avatar

Send message
Joined: 28 Oct 09
Posts: 34053
Credit: 18,883,157
RAC: 18
Belgium
Message 1611777 - Posted: 10 Dec 2014, 15:56:12 UTC - in response to Message 1611772.  

Server down, is it?


Yep, Bruno...
rOZZ
Music
Pictures
ID: 1611777 · Report as offensive
David S
Volunteer tester
Avatar

Send message
Joined: 4 Oct 99
Posts: 18352
Credit: 27,761,924
RAC: 12
United States
Message 1611980 - Posted: 10 Dec 2014, 23:55:19 UTC

Now what the heck is going on with my other cruncher? This is the one that runs only on its 630, no CPU work. It's suddenly showing 2 errors and an invalid. The invalid is an AP, but what numbers I can make out in its stderr look the same as what the other hosts got. The 2 errors are MBs and also have the same numbers in their stderrs, but they show ABORTED BY CLIENT or something like that.

I haven't made any changes to its settings.

...okay, this may be an issue with available hard drive space. I just freed some up, so we'll see if that takes care of it.
David
Sitting on my butt while others boldly go,
Waiting for a message from a small furry creature from Alpha Centauri.

ID: 1611980 · Report as offensive
Profile Julie
Volunteer moderator
Volunteer tester
Avatar

Send message
Joined: 28 Oct 09
Posts: 34053
Credit: 18,883,157
RAC: 18
Belgium
Message 1612147 - Posted: 11 Dec 2014, 8:32:10 UTC

I have a task here that keeps on waiting to run, should I abort it? It's almost finished tho, 96%

http://setiathome.berkeley.edu/workunit.php?wuid=1612898846
rOZZ
Music
Pictures
ID: 1612147 · Report as offensive
Profile Mike Special Project $75 donor
Volunteer tester
Avatar

Send message
Joined: 17 Feb 01
Posts: 34258
Credit: 79,922,639
RAC: 80
Germany
Message 1612163 - Posted: 11 Dec 2014, 9:20:16 UTC - in response to Message 1612147.  

I have a task here that keeps on waiting to run, should I abort it? It's almost finished tho, 96%

http://setiathome.berkeley.edu/workunit.php?wuid=1612898846


Nope.

The deadline is still far off.
Boinc will go into panic mode before the deadline.


With each crime and every kindness we birth our future.
ID: 1612163 · Report as offensive
Profile Julie
Volunteer moderator
Volunteer tester
Avatar

Send message
Joined: 28 Oct 09
Posts: 34053
Credit: 18,883,157
RAC: 18
Belgium
Message 1612167 - Posted: 11 Dec 2014, 9:35:42 UTC - in response to Message 1612163.  

I have a task here that keeps on waiting to run, should I abort it? It's almost finished tho, 96%

http://setiathome.berkeley.edu/workunit.php?wuid=1612898846


Nope.

The deadline is still far off.
Boinc will go into panic mode before the deadline.



Ok, hope my wingman won't be angry with me:)
rOZZ
Music
Pictures
ID: 1612167 · Report as offensive
Profile cliff
Avatar

Send message
Joined: 16 Dec 07
Posts: 625
Credit: 3,590,440
RAC: 0
United Kingdom
Message 1612213 - Posted: 11 Dec 2014, 12:09:05 UTC - in response to Message 1612147.  

Hi Julie,
Any idea why its 'waiting'? Is it perhaps because BM has decided other WU need to be run 1st due to completion date?
If its not got long to run you 'could' override BM and simply suspend any/all other WU until it loads and runs, which should be immediately there is no other WU running, at which point you simply unsuspend all other WU and carry on as normal..

Regards,
Cliff,
Been there, Done that, Still no damm T shirt!
ID: 1612213 · Report as offensive
Cruncher-American Crowdfunding Project Donor*Special Project $75 donorSpecial Project $250 donor

Send message
Joined: 25 Mar 02
Posts: 1513
Credit: 370,893,186
RAC: 340
United States
Message 1612214 - Posted: 11 Dec 2014, 12:09:27 UTC

Looks now like credit granted for GPU AP7s is dropping.

Earlier in the rampup, I was getting roughly 500 credits for almost all AP7 GPU, regardless of wall clock time over a wide range from even a few seconds to 2000 secs. on my GTX 780s. Now, some of the shorter ones are granting only 100-200 credits.

Why would that happen?
ID: 1612214 · Report as offensive
Profile Mike Special Project $75 donor
Volunteer tester
Avatar

Send message
Joined: 17 Feb 01
Posts: 34258
Credit: 79,922,639
RAC: 80
Germany
Message 1612219 - Posted: 11 Dec 2014, 13:00:55 UTC - in response to Message 1612167.  

I have a task here that keeps on waiting to run, should I abort it? It's almost finished tho, 96%

http://setiathome.berkeley.edu/workunit.php?wuid=1612898846


Nope.

The deadline is still far off.
Boinc will go into panic mode before the deadline.



Ok, hope my wingman won't be angry with me:)


Your host hasn`t finnished its 11 vaidations with this app.
So thats quite normal.
OTOH if you`d abort it your wingman would have to wait longer.


With each crime and every kindness we birth our future.
ID: 1612219 · Report as offensive
Profile Julie
Volunteer moderator
Volunteer tester
Avatar

Send message
Joined: 28 Oct 09
Posts: 34053
Credit: 18,883,157
RAC: 18
Belgium
Message 1612222 - Posted: 11 Dec 2014, 13:36:15 UTC - in response to Message 1612219.  

I have a task here that keeps on waiting to run, should I abort it? It's almost finished tho, 96%

http://setiathome.berkeley.edu/workunit.php?wuid=1612898846


Nope.

The deadline is still far off.
Boinc will go into panic mode before the deadline.



Ok, hope my wingman won't be angry with me:)


Your host hasn`t finnished its 11 vaidations with this app.
So thats quite normal.
OTOH if you`d abort it your wingman would have to wait longer.


Oh! Good I didn't abort it then! Thanx Mike:)
rOZZ
Music
Pictures
ID: 1612222 · Report as offensive
Previous · 1 · 2 · 3 · 4 · 5 . . . 24 · Next

Message boards : Number crunching : Panic Mode On (93) 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.