Message boards :
Number crunching :
Panic Mode On (89) Server Problems?
Message board moderation
Previous · 1 . . . 9 · 10 · 11 · 12 · 13 · 14 · 15 . . . 24 · Next
Author | Message |
---|---|
TBar Send message Joined: 22 May 99 Posts: 5204 Credit: 840,779,836 RAC: 2,768 |
Well, that's it. One of my GPUs is now Idle even though the server has sent the Host over 30 new CPU tasks that it didn't need. The Server Refuses to send my ATI cards work....almost just like on SETI Beta, http://setiweb.ssl.berkeley.edu/beta/forum_thread.php?id=2182&postid=52223#52223 Not Good...Time for the Drop Kick. !!!!!!!!!!!!!!!!!!!!!!!! Now look at my Windows 8.1 Host, http://setiathome.berkeley.edu/results.php?hostid=6796475 BTW, it Does have an nVidia card running MBs. It has 100 MBs. Up until a few minutes ago it too was receiving only CPU APs even though the ATI card was down to just 8 GPU tasks. Now the ATI card has just 13 APs yet this is what it's reporting; 9/3/2014 23:32:07 | SETI@home | Sending scheduler request: To report completed tasks. 9/3/2014 23:32:07 | SETI@home | Reporting 1 completed tasks 9/3/2014 23:32:07 | SETI@home | Requesting new tasks for CPU and NVIDIA and ATI 9/3/2014 23:32:09 | SETI@home | Scheduler request completed: got 0 new tasks 9/3/2014 23:32:09 | SETI@home | No tasks sent 9/3/2014 23:32:09 | SETI@home | No tasks are available for AstroPulse v6 9/3/2014 23:32:09 | SETI@home | This computer has reached a limit on tasks in progress Then 5 minutes later it says; 9/3/2014 23:37:15 | SETI@home | Sending scheduler request: To fetch work. 9/3/2014 23:37:15 | SETI@home | Requesting new tasks for CPU and NVIDIA and ATI 9/3/2014 23:37:17 | SETI@home | Scheduler request completed: got 5 new tasks... Now it looks like it's going to download ATI GPU tasks...maybe BTW, it's Not a Mac. |
Cosmic_Ocean Send message Joined: 23 Dec 00 Posts: 3027 Credit: 13,516,867 RAC: 13 |
Well there's a whole pile of low-numbered tapes now. So the candlelight vigil continues... Linux laptop: record uptime: 1511d 20h 19m (ended due to the power brick giving-up) |
S@NL Etienne Dokkum Send message Joined: 11 Jun 99 Posts: 212 Credit: 43,822,095 RAC: 0 |
seems the server changes implied 2 weeks ago result in feeding everyone's CPU needs first and even though you're out of GPU tasks it will feed them later. 2 hours after reaching 100 CPU AP tasks I'm rising steadily on GPU AP's so no need to worry here... The WU's will come in sooner or later. |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13736 Credit: 208,696,464 RAC: 304 |
And AP work is being split once again. And channels are ending in error like there's a sale on errored channels. Grant Darwin NT |
juan BFP Send message Joined: 16 Mar 07 Posts: 9786 Credit: 572,710,851 RAC: 3,799 |
I still not understand how when you split a WU it could end on error for AP and splits normaly for MB if theoricaly both have the same data. Something must be wrong/changed in the AP splitting programs since the problem starts in the last week AP fest. |
kittyman Send message Joined: 9 Jul 00 Posts: 51468 Credit: 1,018,363,574 RAC: 1,004 |
I still not understand how when you split a WU it could end on error for AP and splits normaly for MB if theoricaly both have the same data. Yes... The problem is with the AP splitting program. They are aware of it and are working on it. It's not the datasets. "Freedom is just Chaos, with better lighting." Alan Dean Foster |
betreger Send message Joined: 29 Jun 99 Posts: 11361 Credit: 29,581,041 RAC: 66 |
seems the server changes implied 2 weeks ago result in feeding everyone's CPU needs first and even though you're out of GPU tasks it will feed them later. 2 hours after reaching 100 CPU AP tasks I'm rising steadily on GPU AP's so no need to worry here... The WU's will come in sooner or later. So that's what happened, I thought it was odd. |
Jord Send message Joined: 9 Jun 99 Posts: 15184 Credit: 4,362,181 RAC: 3 |
We might have a solution:There was a bug in the new server code that prevented it from sending jobs to pre-6.7 clients. I checked in a fix (4 lines in sched/sched_types.h). Jeff, can you deploy this in beta and public?Could those affected keep an eye on this, and let us know what transpires - pro or anti? Thanks. Eric built the new scheduler and it's been deployed on here and at beta. So try again, with 6.2.19 or whichever old 5.xx/6.xx version you want. |
HAL9000 Send message Joined: 11 Sep 99 Posts: 6534 Credit: 196,805,888 RAC: 57 |
We might have a solution:There was a bug in the new server code that prevented it from sending jobs to pre-6.7 clients. I checked in a fix (4 lines in sched/sched_types.h). Jeff, can you deploy this in beta and public?Could those affected keep an eye on this, and let us know what transpires - pro or anti? Thanks. I do find it odd that the issue they found should effect versions before 6.7.x but 6.6.33 worked. The exact version isn't really the issue. 6.2.19 does indeed get work upon request now. SETI@home classic workunits: 93,865 CPU time: 863,447 hours Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[ |
Richard Haselgrove Send message Joined: 4 Jul 99 Posts: 14650 Credit: 200,643,578 RAC: 874 |
We might have a solution:There was a bug in the new server code that prevented it from sending jobs to pre-6.7 clients. I checked in a fix (4 lines in sched/sched_types.h). Jeff, can you deploy this in beta and public?Could those affected keep an eye on this, and let us know what transpires - pro or anti? Thanks. A host I'm monitoring with v5.10.45 has received new work too, and it's reporting CPU time for finished work again. |
HAL9000 Send message Joined: 11 Sep 99 Posts: 6534 Credit: 196,805,888 RAC: 57 |
Well there's a whole pile of low-numbered tapes now. So the candlelight vigil continues... Alas poor 31mr08ag. I imagine it will be there for quite a long time as well. SETI@home classic workunits: 93,865 CPU time: 863,447 hours Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[ |
betreger Send message Joined: 29 Jun 99 Posts: 11361 Credit: 29,581,041 RAC: 66 |
No APs are being split, that run didn't last very long. |
HAL9000 Send message Joined: 11 Sep 99 Posts: 6534 Credit: 196,805,888 RAC: 57 |
No APs are being split, that run didn't last very long. I imagine they loaded less data to see how the splitting would go. Possibly trying to work out the issue with the errors while splitting. SETI@home classic workunits: 93,865 CPU time: 863,447 hours Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[ |
OTS Send message Joined: 6 Jan 08 Posts: 369 Credit: 20,533,537 RAC: 0 |
The good news is not only the "CPU Time" back after a couple of weeks absence but the "Run Time" that I have not seen in months, possibly years, is also back. The values of both are the same which is a bit strange but I am not going quibble over that. The bad news is that I am still not receiving any AP work for my CPU for version 6.2.14 despite many attempts since Ageless reported a new scheduler was being deployed. It might be that it is just the luck of the draw since everyone is trying to obtain fresh AP units, but normally when there is a good number of WUs ready to send, I am able to snag at least a few. Time will tell. |
Chris Adamek Send message Joined: 15 May 99 Posts: 251 Credit: 434,772,072 RAC: 236 |
TBar, When I see that happening, I just use a profile that doesn't accept CPU WU's until I'm full up there and then switch back to my normal GPU+CPU profile... But yeah, I've noticed it happening too lately... Chris |
betreger Send message Joined: 29 Jun 99 Posts: 11361 Credit: 29,581,041 RAC: 66 |
We are out of APs now we will have to live off of resends, |
Cosmic_Ocean Send message Joined: 23 Dec 00 Posts: 3027 Credit: 13,516,867 RAC: 13 |
Eric built the new scheduler and it's been deployed on here and at beta. So try again, with 6.2.19 or whichever old 5.xx/6.xx version you want. Success! My 6.2.19 host has a full ~3.5-day cache again. Glad this issue got resolved. Thanks to all who went through the channels to report it as an issue. Linux laptop: record uptime: 1511d 20h 19m (ended due to the power brick giving-up) |
kittyman Send message Joined: 9 Jul 00 Posts: 51468 Credit: 1,018,363,574 RAC: 1,004 |
Eric built the new scheduler and it's been deployed on here and at beta. So try again, with 6.2.19 or whichever old 5.xx/6.xx version you want. Yes, it's a good thing we have some in these forums who recognize and deal with trouble reports on behalf of the many who don't even visit the forums. "Freedom is just Chaos, with better lighting." Alan Dean Foster |
Speedy Send message Joined: 26 Jun 04 Posts: 1643 Credit: 12,921,799 RAC: 89 |
I am pleased you have sorted out the issue. I must say your OS choice for that machine surprised me. I am guessing you run a server of some description |
OTS Send message Joined: 6 Jan 08 Posts: 369 Credit: 20,533,537 RAC: 0 |
The good news is not only the "CPU Time" back after a couple of weeks absence but the "Run Time" that I have not seen in months, possibly years, is also back. The values of both are the same which is a bit strange but I am not going quibble over that. I never received a single WU before they ran out. Anyone else running 6.2.14? I am curious if something has changed at my end or if it is time to try a version that is known to work with the recent changes. |
©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.