Message boards : Number crunching : extreme long wu's
Message board moderation

To post messages, you must log in.

1 · 2 · 3 · 4 . . . 10 · Next

AuthorMessage
alex

Send message
Joined: 21 Feb 15
Posts: 64
Credit: 65,733,511
RAC: 0
Message 1849 - Posted: 28 Dec 2016, 10:21:56 UTC

I see on some of my pc's extreme long wu's with estimated runtime of > 2 days.
Faulty data or is it planned?
ID: 1849 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile ritterm
Avatar

Send message
Joined: 6 Mar 15
Posts: 28
Credit: 16,721,329
RAC: 0
Message 1850 - Posted: 28 Dec 2016, 12:06:59 UTC - in response to Message 1849.  

I just noticed that I've got one WU that's been running for 40 hours (with an estimated 3 hours left).
ID: 1850 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Jim1348

Send message
Joined: 28 Feb 15
Posts: 253
Credit: 200,562,581
RAC: 0
Message 1852 - Posted: 28 Dec 2016, 15:02:27 UTC - in response to Message 1850.  

I terminated one after 43 hours on 25 December. I doubt that it is a proper work unit.
ID: 1852 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile ritterm
Avatar

Send message
Joined: 6 Mar 15
Posts: 28
Credit: 16,721,329
RAC: 0
Message 1853 - Posted: 28 Dec 2016, 15:27:29 UTC - in response to Message 1852.  
Last modified: 28 Dec 2016, 15:28:10 UTC

I terminated one after 43 hours on 25 December. I doubt that it is a proper work unit.
I'm going to abort the long runner I have -- it's made no progress and the time remaining hasn't changed in over 3 hours.
ID: 1853 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Krzysztof Piszczek - wspieram ...
Project administrator
Project developer
Project tester
Avatar

Send message
Joined: 4 Feb 15
Posts: 847
Credit: 144,180,465
RAC: 0
Message 1854 - Posted: 28 Dec 2016, 17:41:58 UTC - in response to Message 1853.  

Linux or Windows?
Krzysztof 'krzyszp' Piszczek

Member of Radioactive@Home team
My Patreon profile
Universe@Home on YT
ID: 1854 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile ritterm
Avatar

Send message
Joined: 6 Mar 15
Posts: 28
Credit: 16,721,329
RAC: 0
Message 1855 - Posted: 28 Dec 2016, 18:34:23 UTC - in response to Message 1854.  

Linux or Windows?

For me, Linux (on this host). It doesn't show in the stderr output, but it had been running for about 43 hours when I aborted it.
ID: 1855 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
alex

Send message
Joined: 21 Feb 15
Posts: 64
Credit: 65,733,511
RAC: 0
Message 1857 - Posted: 28 Dec 2016, 21:43:26 UTC - in response to Message 1854.  

Linux or Windows?

Windows.
ID: 1857 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
adrianxw

Send message
Joined: 1 Oct 16
Posts: 32
Credit: 268,033
RAC: 0
Message 1858 - Posted: 29 Dec 2016, 15:16:52 UTC

I also have a long runner, 23+ hours in, the remaining is over 18 days, increasing rapidly, suspended for now.
ID: 1858 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Jim1348

Send message
Joined: 28 Feb 15
Posts: 253
Credit: 200,562,581
RAC: 0
Message 1859 - Posted: 29 Dec 2016, 15:22:15 UTC - in response to Message 1852.  
Last modified: 29 Dec 2016, 15:25:01 UTC

I terminated one after 43 hours on 25 December. I doubt that it is a proper work unit.

That is on Ubuntu 16.10, running on an i7-4790. Nothing is overclocked, at the CPU runs at a reasonable temperature (65 C).
ID: 1859 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
mmonnin

Send message
Joined: 2 Jun 16
Posts: 169
Credit: 317,253,046
RAC: 0
Message 1860 - Posted: 29 Dec 2016, 16:19:12 UTC

Is there a '10' in the task name near the end? They've been known to take several times as long as normal tasks.
ID: 1860 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
adrianxw

Send message
Joined: 1 Oct 16
Posts: 32
Credit: 268,033
RAC: 0
Message 1861 - Posted: 29 Dec 2016, 16:45:49 UTC
Last modified: 29 Dec 2016, 17:33:54 UTC

No, it is,

universe_bh2_160803_38_1_20000_1-999999_775000

Sorry, I had not seen the later post, my wu is the one I referred to in my earlier post. Windows 8.1, 4GHx i7 system, no overcvlock. It says it is 4.949% done, some loop after that point perhaps? It seems to have been completed by my wingman in just over two hours.
ID: 1861 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile ritterm
Avatar

Send message
Joined: 6 Mar 15
Posts: 28
Credit: 16,721,329
RAC: 0
Message 1862 - Posted: 29 Dec 2016, 17:08:55 UTC - in response to Message 1860.  

Is there a '10' in the task name near the end? They've been known to take several times as long as normal tasks.

The one I aborted after about 43 hours was universe_bh2_160803_35_3_20000_1-999999_925000_1.
ID: 1862 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Jim1348

Send message
Joined: 28 Feb 15
Posts: 253
Credit: 200,562,581
RAC: 0
Message 1863 - Posted: 29 Dec 2016, 18:08:52 UTC - in response to Message 1860.  

Is there a '10' in the task name near the end? They've been known to take several times as long as normal tasks.

No, mine was BHspin v2 universe_bh2_160803_35_3_20000_1-999999_935000_0
ID: 1863 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
adrianxw

Send message
Joined: 1 Oct 16
Posts: 32
Credit: 268,033
RAC: 0
Message 1864 - Posted: 29 Dec 2016, 21:36:12 UTC
Last modified: 29 Dec 2016, 21:36:44 UTC

I released the wu, sometimes stopping and restarting gets things going, but all that happened was the % complete dropped to 4.940%, (checkpoint reload?), but nothing seemed to start, just increasing remaining time, at about 1 minute every 3 seconds. I've suspended it again, thoughts of things to try to help find this problem welcome.
ID: 1864 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
adrianxw

Send message
Joined: 1 Oct 16
Posts: 32
Credit: 268,033
RAC: 0
Message 1865 - Posted: 30 Dec 2016, 12:23:34 UTC

I'm doing some work on another machine and had to power this one off to swap power supplies. The wu started again from 0.0%, ran quickly up to 4.940% then stuck again.
ID: 1865 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile ritterm
Avatar

Send message
Joined: 6 Mar 15
Posts: 28
Credit: 16,721,329
RAC: 0
Message 1866 - Posted: 31 Dec 2016, 18:58:27 UTC

In case it helps with anything that can be identified, here's one I aborted after noticing it had been running for over two days on one of my Win10 hosts:

universe_bh2_160803_39_3_20000_1-999999_850000_1
ID: 1866 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
adrianxw

Send message
Joined: 1 Oct 16
Posts: 32
Credit: 268,033
RAC: 0
Message 1867 - Posted: 31 Dec 2016, 22:44:57 UTC

Weird isn't it? A collection of similar problems from different CPU's running under different operating systems, yet others are completing the same work units without problems in reasonable times. All at this, and only this, project. Interesting.
ID: 1867 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Jari Pyyluoma

Send message
Joined: 15 Sep 15
Posts: 2
Credit: 10,743,881
RAC: 0
Message 1868 - Posted: 1 Jan 2017, 23:58:10 UTC

A 35_1 and a 39_3 never seemed to finish for me. A restart brought down reported elapsed runtimes from about 20 hrs to 25 min and 9 min. I guess the wu:s got stuck at those elapsed times.

all else works fine.

happy new year!
ID: 1868 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
fruehwf

Send message
Joined: 5 Jul 16
Posts: 31
Credit: 18,447,833
RAC: 0
Message 1869 - Posted: 2 Jan 2017, 11:23:46 UTC

ID: 1869 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
adrianxw

Send message
Joined: 1 Oct 16
Posts: 32
Credit: 268,033
RAC: 0
Message 1871 - Posted: 5 Jan 2017, 8:31:20 UTC

I checked to see if it restarted again, but just the same, no suggestions for anything practical here. Aborted.
ID: 1871 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
1 · 2 · 3 · 4 . . . 10 · Next

Message boards : Number crunching : extreme long wu's




Copyright © 2024 Copernicus Astronomical Centre of the Polish Academy of Sciences
Project server and website managed by Krzysztof 'krzyszp' Piszczek