Panic Mode On (111) Server Problems?

Message boards : Number crunching : Panic Mode On (111) Server Problems?
Message board moderation

To post messages, you must log in.

Previous · 1 . . . 28 · 29 · 30 · 31

AuthorMessage
Profile Wiggo
Avatar

Send message
Joined: 24 Jan 00
Posts: 34744
Credit: 261,360,520
RAC: 489
Australia
Message 1930779 - Posted: 19 Apr 2018, 0:34:37 UTC - in response to Message 1930777.  

. . Well there's Einstein@home, they give good credit and are doing useful work.

Yep I'm there and maintain a RAC ~500K, as an aside a couple of days ago Richard posted that he thought E@H probably was truest to the cobblestone credit issue but I don't crunch there for the credit.

Before CreditScrew there wasn't a great deal of difference between crunching here or over at E@H credit wise, but you can certainly see a huge difference these days.

Cheers.
ID: 1930779 · 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 1930781 - Posted: 19 Apr 2018, 0:48:49 UTC - in response to Message 1930772.  

. . Yep, exactly what I have found, on good GPUs running a special sauce form of CUDA you do better with tasks other than AP. But Keith is also running Windows boxes and I think that is where he is benefitting.


Yep, exactly. Primary benefit are the 3 Windows Hosts, not the 2 CUDA90 Hosts. Two of the Windows hosts are not speed demons in any way.
Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)
ID: 1930781 · 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 1930787 - Posted: 19 Apr 2018, 2:41:39 UTC
Last modified: 19 Apr 2018, 2:42:18 UTC

Not realy a panic:
Results ready to send	0	6	710,223

ID: 1930787 · Report as offensive
Ghia
Avatar

Send message
Joined: 7 Feb 17
Posts: 238
Credit: 28,911,438
RAC: 50
Norway
Message 1930834 - Posted: 19 Apr 2018, 8:03:08 UTC - in response to Message 1930764.  

All this may be true. But I just have a big bother with inefficiency. It just bugs me to see a cpu core tied up for 4 hours with a AP task when it could be done in 12 minutes on the gpu. As you say, it likely is hurting my RAC. And it definitely is messing with the cpu APR.

Exactly what I was trying to say. And when inefficiency even hurts your RAC...
I could be doing 20 APs on the GPU in the same time it takes to do 1 on the CPU.
Humans may rule the world...but bacteria run it...
ID: 1930834 · Report as offensive
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13720
Credit: 208,696,464
RAC: 304
Australia
Message 1930837 - Posted: 19 Apr 2018, 8:11:51 UTC - in response to Message 1930834.  

All this may be true. But I just have a big bother with inefficiency. It just bugs me to see a cpu core tied up for 4 hours with a AP task when it could be done in 12 minutes on the gpu. As you say, it likely is hurting my RAC. And it definitely is messing with the cpu APR.

Exactly what I was trying to say. And when inefficiency even hurts your RAC...
I could be doing 20 APs on the GPU in the same time it takes to do 1 on the CPU.

But the same thing applies to the MB work as well. Why spend 2 hours processing a WU on the CPU when the GPU can do it in 5?
For all the time it takes to do a single AP WU, you get more Credit for doing that 1 AP WU than for all the MB WUs you would have processed over the same period, whether you do them on the CPU or the GPU.
Grant
Darwin NT
ID: 1930837 · 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 1930843 - Posted: 19 Apr 2018, 8:23:36 UTC - in response to Message 1930777.  

. . Well there's Einstein@home, they give good credit and are doing useful work.

Yep I'm there and maintain a RAC ~500K, as an aside a couple of days ago Richard posted that he thought E@H probably was truest to the cobblestone credit issue but I don't crunch there for the credit.


. . As you said before, if it was all about the credit I wouldn't be here :). As Sirius B said, everybody wants to be the 1st to find E.T. :)

Stephen

:)
ID: 1930843 · 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 1930844 - Posted: 19 Apr 2018, 8:24:32 UTC - in response to Message 1930779.  

. . Well there's Einstein@home, they give good credit and are doing useful work.

Yep I'm there and maintain a RAC ~500K, as an aside a couple of days ago Richard posted that he thought E@H probably was truest to the cobblestone credit issue but I don't crunch there for the credit.

Before CreditScrew there wasn't a great deal of difference between crunching here or over at E@H credit wise, but you can certainly see a huge difference these days.

Cheers.


+1

Stephen

:)
ID: 1930844 · Report as offensive
Grant (SSSF)
Volunteer tester

Send message
Joined: 19 Aug 99
Posts: 13720
Credit: 208,696,464
RAC: 304
Australia
Message 1930846 - Posted: 19 Apr 2018, 8:35:24 UTC

Given how much the server load has dropped off with all the AP work & Arecibo VLARs going to NVidia GPUs now, maybe Seti could re-enable Resend lost tasks? Even if it was only for a few hours a day it would help clear Ghosts out of the system much faster than waiting for them to time out, and help reduce the load of the database even further.
Grant
Darwin NT
ID: 1930846 · 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 1930847 - Posted: 19 Apr 2018, 8:37:19 UTC - in response to Message 1930846.  

Given how much the server load has dropped off with all the AP work & Arecibo VLARs going to NVidia GPUs now, maybe Seti could re-enable Resend lost tasks? Even if it was only for a few hours a day it would help clear Ghosts out of the system much faster than waiting for them to time out, and help reduce the load of the database even further.


+1 there as well.

Stephen

:)
ID: 1930847 · Report as offensive
Profile Kissagogo27 Special Project $75 donor
Avatar

Send message
Joined: 6 Nov 99
Posts: 715
Credit: 8,032,827
RAC: 62
France
Message 1930863 - Posted: 19 Apr 2018, 9:58:11 UTC - in response to Message 1930734.  


Without a link to the tasks cited, it is impossible to say why the difference. Most likely the amount of blanking was different between the tasks. The higher the blanking, the longer to compute and the higher the credit awarded.
I'm seeing results that seem to imply AP tasks run against CPUs award much lower credit than those run by Two GPUs. There is a bit of blanking, but at first look it seems some of the longer CPU tasks also pay less credit. I brought my ATI cards out of retirement just to run some APs, but it seems they are getting robbed. The blanked tasks take longer on the ATIs, but if the CPU takes a short time then the ATIs get much less credit for a longer task. Take a look at some of the run-times verses credit, https://setiathome.berkeley.edu/results.php?hostid=6796475&offset=60&appid=20
This one is more depressing than most, it's a longer than normal time, but scores a faction of normal;
  Task    Computer	        Sent	             Time reported                 Status                Run time   CPU time    Credit	                 Application
6573740896 8260247   18 Apr 2018, 1:17:28 UTC  18 Apr 2018, 7:47:00 UTC   Completed and validated 	14,620.79   14,551.17   163.35    AstroPulse v7 v7.03 (sse2) windows_x86_64
6573740897 6796475   18 Apr 2018, 1:17:28 UTC  18 Apr 2018, 6:51:54 UTC   Completed and validated        2,132.81      441.49   163.35    AstroPulse v7 Anonymous platform (ATI GPU)

Blah! 131.04 pts for a normal AP, https://setiathome.berkeley.edu/workunit.php?wuid=2941091313[/quote]


2938647197
6565741678	7019416	14 Apr 2018, 11:41:37 UTC	18 Apr 2018, 18:32:46 UTC	Terminé et validé	99,246.44	90,508.01	467.80	
AstroPulse v7 Plateforme anonyme (CPU)

6565741679	7432785	14 Apr 2018, 11:41:37 UTC	15 Apr 2018, 16:24:38 UTC	Terminé et validé	1,669.14	174.03	            467.80	
AstroPulse v7 v7.07 (opencl_ati_mac) x86_64-apple-darwin


first GPU mine second CPU , nice credit ..

2936686975
6561641219	8363701	12 Apr 2018, 19:54:27 UTC	18 Apr 2018, 23:43:09 UTC	Terminé et validé	11,626.94	10,786.14	186.73
AstroPulse v7 v7.03 (sse) windows_intelx86
6561641220	7019416	12 Apr 2018, 19:54:29 UTC	14 Apr 2018, 21:14:16 UTC	Terminé et validé	2,116.25	183.27	186.73
AstroPulse v7 Plateforme anonyme (GPU ATI)


another one with less credit, same order GPU first (mine) and CPU second ...

it's more a WU dépendent credit than CPU or GPU order ..

2940701359 CPU first -> 494cr
ID: 1930863 · Report as offensive
Profile Kissagogo27 Special Project $75 donor
Avatar

Send message
Joined: 6 Nov 99
Posts: 715
Credit: 8,032,827
RAC: 62
France
Message 1930864 - Posted: 19 Apr 2018, 9:59:37 UTC - in response to Message 1930863.  

I'm seeing results that seem to imply AP tasks run against CPUs award much lower credit than those run by Two GPUs. There is a bit of blanking, but at first look it seems some of the longer CPU tasks also pay less credit. I brought my ATI cards out of retirement just to run some APs, but it seems they are getting robbed. The blanked tasks take longer on the ATIs, but if the CPU takes a short time then the ATIs get much less credit for a longer task. Take a look at some of the run-times verses credit, https://setiathome.berkeley.edu/results.php?hostid=6796475&offset=60&appid=20
This one is more depressing than most, it's a longer than normal time, but scores a faction of normal;
  Task    Computer	        Sent	             Time reported                 Status                Run time   CPU time    Credit	                 Application
6573740896 8260247   18 Apr 2018, 1:17:28 UTC  18 Apr 2018, 7:47:00 UTC   Completed and validated 	14,620.79   14,551.17   163.35    AstroPulse v7 v7.03 (sse2) windows_x86_64
6573740897 6796475   18 Apr 2018, 1:17:28 UTC  18 Apr 2018, 6:51:54 UTC   Completed and validated        2,132.81      441.49   163.35    AstroPulse v7 Anonymous platform (ATI GPU)

Blah! 131.04 pts for a normal AP, https://setiathome.berkeley.edu/workunit.php?wuid=2941091313



2938647197
6565741678	7019416	14 Apr 2018, 11:41:37 UTC	18 Apr 2018, 18:32:46 UTC	Terminé et validé	99,246.44	90,508.01	467.80	
AstroPulse v7 Plateforme anonyme (CPU)

6565741679	7432785	14 Apr 2018, 11:41:37 UTC	15 Apr 2018, 16:24:38 UTC	Terminé et validé	1,669.14	174.03	            467.80	
AstroPulse v7 v7.07 (opencl_ati_mac) x86_64-apple-darwin


first GPU mine second CPU , nice credit ..

2936686975
6561641219	8363701	12 Apr 2018, 19:54:27 UTC	18 Apr 2018, 23:43:09 UTC	Terminé et validé	11,626.94	10,786.14	186.73
AstroPulse v7 v7.03 (sse) windows_intelx86
6561641220	7019416	12 Apr 2018, 19:54:29 UTC	14 Apr 2018, 21:14:16 UTC	Terminé et validé	2,116.25	183.27	186.73
AstroPulse v7 Plateforme anonyme (GPU ATI)


another one with less credit, same order GPU first (mine) and CPU second ...

it's more a WU dépendent credit than CPU or GPU order ..

2940701359 CPU first -> 494cr
ID: 1930864 · 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 1930866 - Posted: 19 Apr 2018, 10:07:25 UTC - in response to Message 1930864.  
Last modified: 19 Apr 2018, 10:09:09 UTC

@Kissagogo27

Welcome to the misteries of the Random number generator of CreditScrew.

The same happening with MB WU.
ID: 1930866 · Report as offensive
Profile Dimly Lit Lightbulb 😀
Volunteer tester
Avatar

Send message
Joined: 30 Aug 08
Posts: 15399
Credit: 7,423,413
RAC: 1
United Kingdom
Message 1930921 - Posted: 19 Apr 2018, 18:08:49 UTC - in response to Message 1930779.  

. . Well there's Einstein@home, they give good credit and are doing useful work.

Yep I'm there and maintain a RAC ~500K, as an aside a couple of days ago Richard posted that he thought E@H probably was truest to the cobblestone credit issue but I don't crunch there for the credit.

Before CreditScrew there wasn't a great deal of difference between crunching here or over at E@H credit wise, but you can certainly see a huge difference these days.

Cheers.

Stats from single GPU crunching.



Member of the People Encouraging Niceness In Society club.

ID: 1930921 · 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 1930959 - Posted: 19 Apr 2018, 22:44:19 UTC - in response to Message 1930764.  

All this may be true. But I just have a big bother with inefficiency. It just bugs me to see a cpu core tied up for 4 hours with a AP task when it could be done in 12 minutes on the gpu. As you say, it likely is hurting my RAC. And it definitely is messing with the cpu APR.
It depends how you look at it. 16 threads @ 240 minutes each = 15m/task overall.
[/quote]
ID: 1930959 · 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 1930965 - Posted: 19 Apr 2018, 23:57:52 UTC - in response to Message 1930921.  

[quote]
Yep I'm there and maintain a RAC ~500K, as an aside a couple of days ago Richard posted that he thought E@H probably was truest to the cobblestone credit issue but I don't crunch there for the credit.

Before CreditScrew there wasn't a great deal of difference between crunching here or over at E@H credit wise, but you can certainly see a huge difference these days.

Cheers.

Stats from single GPU crunching.

<graph omitted>

. . The numbers tell the story ... <shrug>

Stephen

:(
ID: 1930965 · 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 1930966 - Posted: 19 Apr 2018, 23:59:58 UTC - in response to Message 1930959.  
Last modified: 20 Apr 2018, 0:05:36 UTC

All this may be true. But I just have a big bother with inefficiency. It just bugs me to see a cpu core tied up for 4 hours with a AP task when it could be done in 12 minutes on the gpu. As you say, it likely is hurting my RAC. And it definitely is messing with the cpu APR.
It depends how you look at it. 16 threads @ 240 minutes each = 15m/task overall.
[/quote]

. . tsk, tsk ... you didn't allow for GPU support ... [ 12 threads for 240 mins = 20 mins per task, but since they take less than that, maybe 180 mins that would bring it back to 15 mins per task]

Stephen

:)
ID: 1930966 · Report as offensive
Profile Bernie Vine
Volunteer moderator
Volunteer tester
Avatar

Send message
Joined: 26 May 99
Posts: 9954
Credit: 103,452,613
RAC: 328
United Kingdom
Message 1930995 - Posted: 20 Apr 2018, 6:22:45 UTC

There is a new thread 112
ID: 1930995 · Report as offensive
Previous · 1 . . . 28 · 29 · 30 · 31

Message boards : Number crunching : Panic Mode On (111) 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.