Panic Mode On (63) Server problems?
Message boards :
Number crunching :
Panic Mode On (63) Server problems?
Message board moderation
Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 · 8 . . . 9 · Next
| Author | Message |
|---|---|
|
BWX Send message Joined: 31 May 03 Posts: 36 Credit: 156,754,993 RAC: 24 
|
My interpretation of the Cricket graph is that in the last 12 hours, nearly all computers demanding tasks have reached their limit, and ths traffic is rapidly approaching maintaining completion volume level. This would leave significant potential bandwidth unused. If say the limits were raised slowly - say 5/CPU, 20/GPU per chunk - until the new limits are reached (and thr traffic drops again), then raise another chunk, then all caches would grow, and nobody would get left behind. A valid point has been made for the condition of outage recovery. Two options might be to: Do nothing - as long as the outages are reasonably short, saturation stops after half a day or so. Things would be back stability as in the past. Or: Make work requests more fair by somehow giving empty caches priority over machines with large (relative) reserves. Option one is likely easiest... ID: 1179512 ·  |
|
Treasurer Send message Joined: 13 Dec 05 Posts: 109 Credit: 1,569,762 RAC: 0 
|
Oh look, a couple of days later everything is running smoothly. All have their caches/limits full, upload bandwidth is bored. Welcome back "tent folders"! ID: 1179515 · |
 john3760  Send message Joined: 9 Feb 11 Posts: 334 Credit: 3,400,979 RAC: 0 
|
the crickets aren't maxed out now. edit: server status shows ok. there is something wrong edit2: oops it's tuesday. ID: 1179527 · |
Cosmic_Ocean  Send message Joined: 23 Dec 00 Posts: 3027 Credit: 13,516,867 RAC: 13
|
the crickets aren't maxed out now. Indeed. Bandwidth consumption is down, large majority have reached their cache limits. Just in time for the Tuesday outage where we will now go 6 days maxed out until the eve of the next maintenance day. Linux laptop: record uptime: 1511d 20h 19m (ended due to the power brick giving-up) ID: 1179562 · |
|
Claggy Send message Joined: 5 Jul 99 Posts: 4654 Credit: 47,537,079 RAC: 4
|
the crickets aren't maxed out now. I wonder how many Boinc 6.12.x hosts still have downloads backed off? Claggy ID: 1179566 · |
David S  Send message Joined: 4 Oct 99 Posts: 18352 Credit: 27,761,924 RAC: 12
|
My interpretation of the Cricket graph is that in the last 12 hours, nearly all computers demanding tasks have reached their limit, and ths traffic is rapidly approaching maintaining completion volume level. My interpretation of the Cricket graphs is that something went seriously wrong overnight again. I wish you were right, but I just don't believe it. David Sitting on my butt while others boldly go, Waiting for a message from a small furry creature from Alpha Centauri. ID: 1179567 · |
|
Horacio Send message Joined: 14 Jan 00 Posts: 536 Credit: 75,967,266 RAC: 0 
|
My interpretation of the Cricket graph is that in the last 12 hours, nearly all computers demanding tasks have reached their limit, and ths traffic is rapidly approaching maintaining completion volume level. LOL, sadly thats probably the best interpretation... But Ive seen something else here, in the last days Ive got some very long MB tasks whose estimated times were very short. I know that the estimations are far from perfect but this particular tasks were taking up to 4 times more than the estimation. This happened on all my rigs in both CPU and GPU tasks Im using flops tags and ussually my DCF is kept between 1.4 and 0.6, but due to this extremely bad estimated tasks the DCF rised above 4 and then all my rigs stopped to ask work... also as the DCF goes down very slowly Its taking long to recover and when the value goes to something more normal it finds another of those tasks and everything starts again... Do somebody else noticed this, now or in the past? 
ID: 1179571 · |
Dimly Lit Lightbulb 😀  Send message Joined: 30 Aug 08 Posts: 15399 Credit: 7,423,413 RAC: 1
|
the crickets aren't maxed out now. Probably all of 'em, lol.  Member of the People Encouraging Niceness In Society club. 
ID: 1179588 · |
jason_gee  Send message Joined: 24 Nov 06 Posts: 7489 Credit: 91,093,184 RAC: 0 
|
I wonder how many Boinc 6.12.x hosts still have downloads backed off? LoL, if the client types connection page is working I see none ;): Of the 9986 last connections to the scheduler: "Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions. ID: 1179591 · |
arkayn  Send message Joined: 14 May 99 Posts: 4438 Credit: 55,006,323 RAC: 0
|
the crickets aren't maxed out now. Not mine, both of them are running fine. 
ID: 1179601 · |
|
Gundolf Jahn Send message Joined: 19 Sep 00 Posts: 3184 Credit: 446,358 RAC: 0
|
LoL, if the client types connection page is working I see none ;) Probably, it's not working: last updated: October 21 2010 12:25:01 I presume you omitted that line intentionally ;-) Gruß, Gundolf ID: 1179605 · |
Belthazor  Send message Joined: 6 Apr 00 Posts: 219 Credit: 10,373,795 RAC: 13 
|
I really want to whine about something, but after a full days work, I just can't find the energy to do it. Hey buddy, AP WUs are available just now! Catch them all! :-)  
ID: 1179668 · |
|
Belthazor Send message Joined: 6 Apr 00 Posts: 219 Credit: 10,373,795 RAC: 13
|
No doubt, they are Grinches :)) Not me at any rate, as I promised before, I am MB-only cruncher for now and keep my AP WUs for you :-)
ID: 1179694 · |
|
Dimly Lit Lightbulb 😀 Send message Joined: 30 Aug 08 Posts: 15399 Credit: 7,423,413 RAC: 1
|
I don't know about anybody else, but the astropulses are just flying through the bandwidth today. Boinc asketh, Boinc getteth thy tasks, often more than one at a time! Member of the People Encouraging Niceness In Society club.
ID: 1179854 · |
Mike   Send message Joined: 17 Feb 01 Posts: 34379 Credit: 79,922,639 RAC: 80
 |
I´m trying since 12 hours. Got none so far. With each crime and every kindness we birth our future. ID: 1179858 · |
|
Dimly Lit Lightbulb 😀 Send message Joined: 30 Aug 08 Posts: 15399 Credit: 7,423,413 RAC: 1
|
I´m trying since 12 hours. Sometimes it seems like that is happening, splitters online and doing their job, yet I get zilch. My Seti astropulse task (rain) dance doesn't seem to help either :) But today... it's worked :) *EDIT:When I say zilch, I mean nothing the entire time the splitters are active and I'm around to hammer the retry button. All I get is no tasks available and so on/EDIT* Member of the People Encouraging Niceness In Society club.
ID: 1179866 · |
Wiggo  Send message Joined: 24 Jan 00 Posts: 36781 Credit: 261,360,520 RAC: 489
|
Well all I can add here is that my 3 rigs are still bouncing on the limits as usual though I do have 99 Astropulses stockpiled. Cheers. ID: 1179867 · |
|
Mike Send message Joined: 17 Feb 01 Posts: 34379 Credit: 79,922,639 RAC: 80
|
I´m trying since 12 hours. True. When i look at my wingmen sometimes i´m questioning. It seems the slowest hosts gets the most APs. With each crime and every kindness we birth our future. ID: 1179874 · |
Fred J. Verster  Send message Joined: 21 Apr 04 Posts: 3252 Credit: 31,903,643 RAC: 0 
|
AstroPulse are very rare, I've seen 2 in the last months. Lots of shorties or AR=/;> 1.0 and higher. Running 3 hosts atm. even my LT, runs BOINC 6.12.34; x86 and SSE3 CPU optimized LUNATICs app.. And the I7-2600, does better/faster with SSE3 then SSSE3, HT=ON. I also run Rosetta, EINSTEIN, PrimeGrid, wich has send an absurt amount of work. I've set it to N.N.T.! Rosetta is memory hungry, 4 R and 4 SETI MB, also 1 on each ATI 5870. This conbination uses 7.4GByte RAM! And DLoads appear to be running smoother, but also can very quickly collapse or stall. Also work from SETI Bêta, ehh that's another task. Looking at the Date of the WUs, we could or should be able to process In Real Time, the Bandwidth issue isn't solved, yet. And the DATA from Arecibo to Berkeley, hard drives shipt to Berkeley. You're going to need a (WLAN+)transmittor, sending the DATA to Berkeley....... 
ID: 1179876 · |
|
Mike Send message Joined: 17 Feb 01 Posts: 34379 Credit: 79,922,639 RAC: 80
|
Its so funny. I got 2 APs in 4 weeks. Done in less than an hour. 20/30 and 30/30. I´m really a lucky guy. With each crime and every kindness we birth our future. ID: 1179880 · |
©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.