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 · 6 · 7 · 8 . . . 24 · Next

AuthorMessage
Profile cliff
Avatar

Send message
Joined: 16 Dec 07
Posts: 625
Credit: 3,590,440
RAC: 0
United Kingdom
Message 1613162 - Posted: 13 Dec 2014, 5:25:38 UTC - in response to Message 1613140.  

Hi Speedy,
Lucky you:-)
This is what I just got:-/

13/12/2014 05:23:07 | SETI@home | Requesting new tasks for NVIDIA GPU
13/12/2014 05:23:10 | SETI@home | Scheduler request completed: got 0 new tasks
13/12/2014 05:23:10 | SETI@home | No tasks sent
13/12/2014 05:23:10 | SETI@home | No tasks are available for AstroPulse v7
13/12/2014 05:23:10 | SETI@home | Tasks for CPU are available, but your preferences are set to not accept them

Summats still up in server land!!

Regards,
Cliff,
Been there, Done that, Still no damm T shirt!
ID: 1613162 · Report as offensive
Profile cliff
Avatar

Send message
Joined: 16 Dec 07
Posts: 625
Credit: 3,590,440
RAC: 0
United Kingdom
Message 1613409 - Posted: 13 Dec 2014, 18:18:26 UTC
Last modified: 13 Dec 2014, 18:21:29 UTC

Hi All,
And once again its the weekend:-/
And once again its servers going doolalli:-)
After succeeding in a getting a few WU, [mb] now once again its:--

13/12/2014 18:13:03 | SETI@home | Sending scheduler request: Requested by user.
13/12/2014 18:13:03 | SETI@home | Reporting 1 completed tasks
13/12/2014 18:13:03 | SETI@home | Requesting new tasks for NVIDIA GPU
13/12/2014 18:13:05 | SETI@home | Scheduler request completed: got 0 new tasks
13/12/2014 18:13:05 | SETI@home | No tasks sent
13/12/2014 18:13:05 | SETI@home | No tasks are available for SETI@home Enhanced
13/12/2014 18:13:05 | SETI@home | No tasks are available for AstroPulse v6
13/12/2014 18:13:05 | SETI@home | No tasks are available for AstroPulse v7
13/12/2014 18:13:05 | SETI@home | Tasks for CPU are available, but your preferences are set to not accept them

I dunno what the devil Carolyn is playing at, but she needs a good sort out if she cant do the simple task of dishing out WU that are showing as available in stats...

[edit]

And I turn my back for a minute or two to post here and...

13/12/2014 18:18:10 | SETI@home | Sending scheduler request: To fetch work.
13/12/2014 18:18:10 | SETI@home | Requesting new tasks for NVIDIA GPU
13/12/2014 18:18:14 | SETI@home | Scheduler request completed: got 42 new tasks


Regards,
Cliff,
Been there, Done that, Still no damm T shirt!
ID: 1613409 · Report as offensive
Profile Michael W.F. Miles
Avatar

Send message
Joined: 24 Mar 07
Posts: 268
Credit: 34,410,870
RAC: 0
Canada
Message 1613417 - Posted: 13 Dec 2014, 18:30:13 UTC

I find that Astropulse is the only thing worth spending hydro crunching on.
What is the problem now. It was going great and now I can't get any new tasks. GPU is out. As far as other projects I'm not interested.
So do we wait until after Tuesday again before the splitters are back up. There is a ton of AP to do, so lets do them
ID: 1613417 · 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 1613482 - Posted: 13 Dec 2014, 19:33:09 UTC - in response to Message 1613417.  

There is a ton of AP to do, so lets do them


Can't do them if the system(s) that distribute them aren't working. Which seems to be the problem.

Just like:

A car with a dead battery isn't going anywhere even though it is sitting there all gassed up.
ID: 1613482 · Report as offensive
Profile Wiggo
Avatar

Send message
Joined: 24 Jan 00
Posts: 34744
Credit: 261,360,520
RAC: 489
Australia
Message 1613488 - Posted: 13 Dec 2014, 19:40:26 UTC - in response to Message 1613409.  

Hi All,
And once again its the weekend:-/
And once again its servers going doolalli:-)
After succeeding in a getting a few WU, [mb] now once again its:--

13/12/2014 18:13:03 | SETI@home | Sending scheduler request: Requested by user.
13/12/2014 18:13:03 | SETI@home | Reporting 1 completed tasks
13/12/2014 18:13:03 | SETI@home | Requesting new tasks for NVIDIA GPU
13/12/2014 18:13:05 | SETI@home | Scheduler request completed: got 0 new tasks
13/12/2014 18:13:05 | SETI@home | No tasks sent
13/12/2014 18:13:05 | SETI@home | No tasks are available for SETI@home Enhanced
13/12/2014 18:13:05 | SETI@home | No tasks are available for AstroPulse v6
13/12/2014 18:13:05 | SETI@home | No tasks are available for AstroPulse v7
13/12/2014 18:13:05 | SETI@home | Tasks for CPU are available, but your preferences are set to not accept them

I dunno what the devil Carolyn is playing at, but she needs a good sort out if she cant do the simple task of dishing out WU that are showing as available in stats...

[edit]

And I turn my back for a minute or two to post here and...

13/12/2014 18:18:10 | SETI@home | Sending scheduler request: To fetch work.
13/12/2014 18:18:10 | SETI@home | Requesting new tasks for NVIDIA GPU
13/12/2014 18:18:14 | SETI@home | Scheduler request completed: got 42 new tasks


Regards,

There are a lot of VLAR's around Cliff which is why you're seeing that.

Out of interest, what is your cache set at? Maybe increasing it would help you.

Cheers.
ID: 1613488 · Report as offensive
Profile cliff
Avatar

Send message
Joined: 16 Dec 07
Posts: 625
Credit: 3,590,440
RAC: 0
United Kingdom
Message 1613492 - Posted: 13 Dec 2014, 19:46:06 UTC - in response to Message 1613488.  

Hi Wiggo,

Tried increasing cache:-) No go.. but apparently ignoring the problem makes it go away:-)

Cant see why Carolyn refuses a user request, then within 5 mins honours a standard BM request.. Weird...

Regards,
Cliff,
Been there, Done that, Still no damm T shirt!
ID: 1613492 · Report as offensive
Profile Wiggo
Avatar

Send message
Joined: 24 Jan 00
Posts: 34744
Credit: 261,360,520
RAC: 489
Australia
Message 1613506 - Posted: 13 Dec 2014, 20:17:31 UTC - in response to Message 1613492.  

Hi Wiggo,

Tried increasing cache:-) No go.. but apparently ignoring the problem makes it go away:-)

Cant see why Carolyn refuses a user request, then within 5 mins honours a standard BM request.. Weird...

Regards,

Its just if the feeder at the time of your request is filled with VLAR's then the server will not send your them to your GPU/s and you'll just have to wait until it has the type of work that it can send to them.

Cheers.
ID: 1613506 · Report as offensive
Claggy
Volunteer tester

Send message
Joined: 5 Jul 99
Posts: 4654
Credit: 47,537,079
RAC: 4
United Kingdom
Message 1613512 - Posted: 13 Dec 2014, 20:23:28 UTC - in response to Message 1613409.  
Last modified: 13 Dec 2014, 20:24:27 UTC

Hi All,
And once again its the weekend:-/
And once again its servers going doolalli:-)
After succeeding in a getting a few WU, [mb] now once again its:--

13/12/2014 18:13:03 | SETI@home | Sending scheduler request: Requested by user.
13/12/2014 18:13:03 | SETI@home | Reporting 1 completed tasks
13/12/2014 18:13:03 | SETI@home | Requesting new tasks for NVIDIA GPU
13/12/2014 18:13:05 | SETI@home | Scheduler request completed: got 0 new tasks
13/12/2014 18:13:05 | SETI@home | No tasks sent
13/12/2014 18:13:05 | SETI@home | No tasks are available for SETI@home Enhanced
13/12/2014 18:13:05 | SETI@home | No tasks are available for AstroPulse v6
13/12/2014 18:13:05 | SETI@home | No tasks are available for AstroPulse v7
13/12/2014 18:13:05 | SETI@home | Tasks for CPU are available, but your preferences are set to not accept them

I dunno what the devil Carolyn is playing at, but she needs a good sort out if she cant do the simple task of dishing out WU that are showing as available in stats...

Carolyn isn't playing at anything, If the feeder is full of VLARs (Which aren't sent to GPUs), and you only ask for GPU work, you'll get no work,
ask for CPU work, and you'll rotate those VLARs out of those feeder slots, they may be replaced with more VLARs, or maybe with non-VLARs,

Hopefully when you host asks for work again, another host has already asked for CPU work, got VLAR work, and then hopefully the feeder slots then get filled with non-VLARs, and when your host ask for GPU work your host gets those non-VLARs, my i7-2600K's CPU tasks at present are all VLARs.

Claggy
ID: 1613512 · Report as offensive
Cosmic_Ocean
Avatar

Send message
Joined: 23 Dec 00
Posts: 3027
Credit: 13,516,867
RAC: 13
United States
Message 1613523 - Posted: 13 Dec 2014, 20:43:45 UTC

Well, I'm glad I was able to get a full 10-day AP cache in the short time it was up and running. Hopefully this time, I don't run dry before it comes back, but even if I do, that's not really a problem.
Linux laptop:
record uptime: 1511d 20h 19m (ended due to the power brick giving-up)
ID: 1613523 · 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 1613541 - Posted: 13 Dec 2014, 21:13:41 UTC - in response to Message 1613512.  


I dunno what the devil Carolyn is playing at, but she needs a good sort out if she cant do the simple task of dishing out WU that are showing as available in stats...

Well, somebody's definitely playing, and not just trouble in AP world. SSP shows 14 PFB(MB) splitters in work on channels right now, interesting as there are only 7 available to split.
ID: 1613541 · Report as offensive
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13720
Credit: 208,696,464
RAC: 304
Australia
Message 1613547 - Posted: 13 Dec 2014, 21:23:22 UTC - in response to Message 1613541.  

Well, somebody's definitely playing, and not just trouble in AP world. SSP shows 14 PFB(MB) splitters in work on channels right now, interesting as there are only 7 available to split.

Been that way for several days now.
Grant
Darwin NT
ID: 1613547 · Report as offensive
Profile Jord
Volunteer tester
Avatar

Send message
Joined: 9 Jun 99
Posts: 15184
Credit: 4,362,181
RAC: 3
Netherlands
Message 1613614 - Posted: 14 Dec 2014, 0:05:18 UTC

I think mine is much cooler:

14/12/2014 00:56:40 | SETI@home | Requesting new tasks for AMD/ATI GPU
14/12/2014 00:56:40 | SETI@home | [sched_op] CPU work request: 0.00 seconds; 0.00 devices
14/12/2014 00:56:40 | SETI@home | [sched_op] AMD/ATI GPU work request: 9599.84 seconds; 0.00 devices
14/12/2014 00:56:42 | SETI@home | Scheduler request completed: got 0 new tasks
14/12/2014 00:56:42 | SETI@home | [sched_op] Server version 705
14/12/2014 00:56:42 | SETI@home | No tasks sent
14/12/2014 00:56:42 | SETI@home | No tasks are available for AstroPulse v7
14/12/2014 00:56:42 | SETI@home | Tasks for CPU are available, but your preferences are set to not accept them
14/12/2014 00:56:42 | SETI@home | Tasks for NVIDIA GPU are available, but your preferences are set to not accept them
14/12/2014 00:56:42 | SETI@home | Tasks for Intel GPU are available, but your preferences are set to not accept them

:)
ID: 1613614 · 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 1613830 - Posted: 14 Dec 2014, 12:54:35 UTC - in response to Message 1613512.  

Hi All,
And once again its the weekend:-/
And once again its servers going doolalli:-)
After succeeding in a getting a few WU, [mb] now once again its:--

13/12/2014 18:13:03 | SETI@home | Sending scheduler request: Requested by user.
13/12/2014 18:13:03 | SETI@home | Reporting 1 completed tasks
13/12/2014 18:13:03 | SETI@home | Requesting new tasks for NVIDIA GPU
13/12/2014 18:13:05 | SETI@home | Scheduler request completed: got 0 new tasks
13/12/2014 18:13:05 | SETI@home | No tasks sent
13/12/2014 18:13:05 | SETI@home | No tasks are available for SETI@home Enhanced
13/12/2014 18:13:05 | SETI@home | No tasks are available for AstroPulse v6
13/12/2014 18:13:05 | SETI@home | No tasks are available for AstroPulse v7
13/12/2014 18:13:05 | SETI@home | Tasks for CPU are available, but your preferences are set to not accept them

I dunno what the devil Carolyn is playing at, but she needs a good sort out if she cant do the simple task of dishing out WU that are showing as available in stats...

Carolyn isn't playing at anything, If the feeder is full of VLARs (Which aren't sent to GPUs), and you only ask for GPU work, you'll get no work,
ask for CPU work, and you'll rotate those VLARs out of those feeder slots, they may be replaced with more VLARs, or maybe with non-VLARs,

Hopefully when you host asks for work again, another host has already asked for CPU work, got VLAR work, and then hopefully the feeder slots then get filled with non-VLARs, and when your host ask for GPU work your host gets those non-VLARs, my i7-2600K's CPU tasks at present are all VLARs.

Claggy

Here's some anecdotal evidence in support of that. Earlier this morning, I noticed my NVidia machines were getting 'No tasks sent' on every request. I have a test machine (host 7118033) which processes VLARs very well on CPU, and which I normally keep on a short cache. So I bumped it...

14-Dec-2014 11:41:06 [SETI@home] [sched_op] Starting scheduler request
14-Dec-2014 11:41:06 [SETI@home] [work_fetch] request: CPU (549692.90 sec, 0.00 inst) Intel GPU (164772.18 sec, 0.00 inst)
14-Dec-2014 11:41:06 [SETI@home] Sending scheduler request: To fetch work.
14-Dec-2014 11:41:06 [SETI@home] Requesting new tasks for CPU and Intel GPU
14-Dec-2014 11:41:06 [SETI@home] [sched_op] CPU work request: 549692.90 seconds; 0.00 devices
14-Dec-2014 11:41:06 [SETI@home] [sched_op] Intel GPU work request: 164772.18 seconds; 0.00 devices
14-Dec-2014 11:41:09 [SETI@home] Scheduler request completed: got 74 new tasks
14-Dec-2014 11:41:09 [SETI@home] [sched_op] estimated total CPU task duration: 556491 seconds
14-Dec-2014 11:41:09 [SETI@home] [sched_op] estimated total Intel GPU task duration: 0 seconds

Every single one of those 74 tasks was a VLAR - and since I did that, my NVidia machines have started receiving new tasks again.

One swallow doesn't make a summer, but if other active users here have CPU-only machines, they might consider letting them do periodic 'feeder cleansing' operations like that.
ID: 1613830 · Report as offensive
Profile Mike Special Project $75 donor
Volunteer tester
Avatar

Send message
Joined: 17 Feb 01
Posts: 34253
Credit: 79,922,639
RAC: 80
Germany
Message 1613844 - Posted: 14 Dec 2014, 13:35:49 UTC

I have only VLARs on CPU but also enough tasks for my GPU.


With each crime and every kindness we birth our future.
ID: 1613844 · 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 1613851 - Posted: 14 Dec 2014, 13:51:10 UTC - in response to Message 1613844.  

I have only VLARs on CPU but also enough tasks for my GPU.

The point I was trying to make is that this might be one of the few cases where some careful micro-management of a single computer might be enough to help the smooth running of the project as a whole. But that one machine can only help out once every two or three days, because it takes that much time to burn off the excess cache. And the feeder gets polluted again much quicker than that - so having more volunteers to help with the process would be beneficial.
ID: 1613851 · Report as offensive
Profile HAL9000
Volunteer tester
Avatar

Send message
Joined: 11 Sep 99
Posts: 6534
Credit: 196,805,888
RAC: 57
United States
Message 1613854 - Posted: 14 Dec 2014, 13:59:14 UTC - in response to Message 1613851.  

I have only VLARs on CPU but also enough tasks for my GPU.

The point I was trying to make is that this might be one of the few cases where some careful micro-management of a single computer might be enough to help the smooth running of the project as a whole. But that one machine can only help out once every two or three days, because it takes that much time to burn off the excess cache. And the feeder gets polluted again much quicker than that - so having more volunteers to help with the process would be beneficial.

Most of my machines are CPU only. They are not exactly fast, but slurp up the overrun of VLAR tasks happily.
SETI@home classic workunits: 93,865 CPU time: 863,447 hours
Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[
ID: 1613854 · Report as offensive
Claggy
Volunteer tester

Send message
Joined: 5 Jul 99
Posts: 4654
Credit: 47,537,079
RAC: 4
United Kingdom
Message 1613869 - Posted: 14 Dec 2014, 14:31:15 UTC - in response to Message 1613851.  
Last modified: 14 Dec 2014, 14:56:30 UTC

I have only VLARs on CPU but also enough tasks for my GPU.

The point I was trying to make is that this might be one of the few cases where some careful micro-management of a single computer might be enough to help the smooth running of the project as a whole. But that one machine can only help out once every two or three days, because it takes that much time to burn off the excess cache. And the feeder gets polluted again much quicker than that - so having more volunteers to help with the process would be beneficial.

Got my C2D E8500 to ask for CPU work, got 27 VLARs, got it to ask for CPU work again, got 71 VLARs (Total 98 VLARs), just finishing off my last two CPU non VLARs.

Edit: A quick runthrough of those VLARs found me 8 overflows, the next work request gave me 8 replacement VLARs.

Claggy
ID: 1613869 · Report as offensive
Profile cliff
Avatar

Send message
Joined: 16 Dec 07
Posts: 625
Credit: 3,590,440
RAC: 0
United Kingdom
Message 1613933 - Posted: 14 Dec 2014, 18:43:20 UTC - in response to Message 1613851.  

I have only VLARs on CPU but also enough tasks for my GPU.

The point I was trying to make is that this might be one of the few cases where some careful micro-management of a single computer might be enough to help the smooth running of the project as a whole. But that one machine can only help out once every two or three days, because it takes that much time to burn off the excess cache. And the feeder gets polluted again much quicker than that - so having more volunteers to help with the process would be beneficial.


I could have sworn, that on several occasions I'd been told that there were NO device specific WU, that a task could be either GPU or CPU..

Seems I was mistaken, there are apparently device specific WU, VLAR's it seems are CPU specific..

Ah well you live and learn:-)

Regards,
Cliff,
Been there, Done that, Still no damm T shirt!
ID: 1613933 · Report as offensive
Wedge009
Volunteer tester
Avatar

Send message
Joined: 3 Apr 99
Posts: 451
Credit: 431,396,357
RAC: 553
Australia
Message 1613940 - Posted: 14 Dec 2014, 19:17:05 UTC

Tasks are still not CPU or GPU specific, but for quite some time now WUs identified as being VLAR are prevented from being sent to GPUs. At the time this started, NV GPUs really had trouble processing such tasks (sometimes with longer run-times than corresponding CPU processing, or even causing display lag/crashes). AMD GPUs also struggled with VLAR WUs, but generally not as severely as their NV counterparts. So the server filters these tasks from being sent to GPUs - they are not 'CPU-specific' as such.
Soli Deo Gloria
ID: 1613940 · Report as offensive
Profile cliff
Avatar

Send message
Joined: 16 Dec 07
Posts: 625
Credit: 3,590,440
RAC: 0
United Kingdom
Message 1613980 - Posted: 14 Dec 2014, 20:45:21 UTC - in response to Message 1613940.  

Hi Wedge009,

Ahh, that jibes with my sometimes flakey memory:-) Because I seem to recall getting several VLAR's that went to my GPU's, didn't find a problem AFAIR.
Certainly no display crashes, seen a bit of display 'jitter' but not from S@H tasks as such.
Cliff,
Been there, Done that, Still no damm T shirt!
ID: 1613980 · Report as offensive
Previous · 1 · 2 · 3 · 4 · 5 · 6 · 7 · 8 . . . 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.