Welcome to MilkyWay@home

post milkyway_i686-pc-linux-gnu problems here

Message boards : Number crunching : post milkyway_i686-pc-linux-gnu problems here
Message board moderation

To post messages, you must log in.

Previous · 1 · 2 · 3

AuthorMessage
cwhyl

Send message
Joined: 11 Nov 07
Posts: 41
Credit: 1,000,181
RAC: 0
Message 7588 - Posted: 10 Dec 2008, 0:18:48 UTC
Last modified: 10 Dec 2008, 0:48:28 UTC

Got 8 of these errors today when network connection was capped and boinc is sending a Sheduler request, same thing happened 2-3 days ago, process gets killed when trying to connect. Boinc 6.2.15
Task ID 57511334
Name nm_stripe86_r8_29498_1228841620_0
Workunit 57695184
Created 9 Dec 2008 16:53:48 UTC
Sent 9 Dec 2008 17:08:01 UTC
Received 9 Dec 2008 22:39:12 UTC
Server state Over
Outcome Client error
Client state Compute error
Exit status 11 (0xb)
Computer ID 18333
Report deadline 12 Dec 2008 17:08:01 UTC
CPU time 216.566076
stderr out

<core_client_version>6.2.15</core_client_version>
<![CDATA[
<message>
process got signal 11
</message>
<stderr_txt>
Unrecognized XML in parse_init_data_file: computation_deadline
Skipping: 1228666081.000000
Skipping: /computation_deadline
Unrecognized XML in GLOBAL_PREFS::parse_override: mod_time
Skipping: /mod_time
Unrecognized XML in GLOBAL_PREFS::parse_override: max_ncpus_pct
Skipping: 100.000000
Skipping: /max_ncpus_pct

</stderr_txt>
]]>

Validate state Invalid
Claimed credit 1.27301137603241
Granted credit 0
application version 0.07


Looked like this in the commandline on 4 of the ones:
08-Dec-2008 22:03:29 [Milkyway@home] Temporarily failed upload of nm_stripe86_r7_23373_1228836170_0_0: connect() failed
08-Dec-2008 22:03:29 [Milkyway@home] Backing off 1 min 0 sec on upload of nm_stripe86_r7_23373_1228836170_0_0
08-Dec-2008 22:04:51 [Milkyway@home] Sending scheduler request: To report completed tasks. Requesting 1752190 seconds of work, reporting 3 completed tasks
08-Dec-2008 22:04:51 [Milkyway@home] Started upload of nm_stripe86_r7_23373_1228836170_0_0
08-Dec-2008 22:04:51 [Milkyway@home] Computation for task nm_stripe79_r8_23663_1228836645_0 finished
08-Dec-2008 22:04:51 [Milkyway@home] Output file nm_stripe79_r8_23663_1228836645_0_0 for task nm_stripe79_r8_23663_1228836645_0 absent
08-Dec-2008 22:04:51 [Milkyway@home] Starting nm_stripe79_r7_29506_1228842124_0
08-Dec-2008 22:04:51 [Milkyway@home] Starting task nm_stripe79_r7_29506_1228842124_0 using milkyway version 7
08-Dec-2008 22:04:52 [Milkyway@home] Computation for task nm_stripe82_r7_23691_1228836646_0 finished
08-Dec-2008 22:04:52 [Milkyway@home] Output file nm_stripe82_r7_23691_1228836646_0_0 for task nm_stripe82_r7_23691_1228836646_0 absent
08-Dec-2008 22:04:52 [Milkyway@home] Starting nm_stripe79_r7_29522_1228842125_0
08-Dec-2008 22:04:52 [Milkyway@home] Starting task nm_stripe79_r7_29522_1228842125_0 using milkyway version 7
08-Dec-2008 22:04:53 [Milkyway@home] Temporarily failed upload of nm_stripe86_r7_23373_1228836170_0_0: connect() failed
08-Dec-2008 22:04:53 [Milkyway@home] Backing off 1 min 0 sec on upload of nm_stripe86_r7_23373_1228836170_0_0
08-Dec-2008 22:04:53 [Milkyway@home] Computation for task nm_stripe79_r8_23634_1228836644_0 finished
08-Dec-2008 22:04:53 [Milkyway@home] Output file nm_stripe79_r8_23634_1228836644_0_0 for task nm_stripe79_r8_23634_1228836644_0 absent
08-Dec-2008 22:04:53 [Milkyway@home] Starting nm_stripe86_r7_29345_1228841617_0
08-Dec-2008 22:04:53 [Milkyway@home] Starting task nm_stripe86_r7_29345_1228841617_0 using milkyway version 7
08-Dec-2008 22:04:54 [Milkyway@home] Computation for task nm_stripe82_r8_23760_1228836648_0 finished
08-Dec-2008 22:04:54 [Milkyway@home] Output file nm_stripe82_r8_23760_1228836648_0_0 for task nm_stripe82_r8_23760_1228836648_0 absent
08-Dec-2008 22:04:54 [Milkyway@home] Starting nm_stripe86_r8_29446_1228841619_0
08-Dec-2008 22:04:54 [Milkyway@home] Starting task nm_stripe86_r8_29446_1228841619_0 using milkyway version 7
08-Dec-2008 22:04:56 [Milkyway@home] Scheduler request failed: Couldn't connect to server


Have some old boincies in storage, 5.2.13 was nice :)
ID: 7588 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Hefto99

Send message
Joined: 29 Dec 07
Posts: 9
Credit: 100,140,182
RAC: 0
Message 7636 - Posted: 12 Dec 2008, 7:30:54 UTC
Last modified: 12 Dec 2008, 8:02:10 UTC

Some WUs run extremely long time, I have aborted this one after over 18 hours:

http://milkyway.cs.rpi.edu/milkyway/result.php?resultid=57580672

[edit]I use official application[/edit]
ID: 7636 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
cwhyl

Send message
Joined: 11 Nov 07
Posts: 41
Credit: 1,000,181
RAC: 0
Message 7645 - Posted: 12 Dec 2008, 10:49:47 UTC - in response to Message 7636.  

Some WUs run extremely long time, I have aborted this one after over 18 hours:

http://milkyway.cs.rpi.edu/milkyway/result.php?resultid=57580672

Yup, same here, I have three nm_stripe_79_fr1 running for over four hours and only 45% done.
Well I don't mind if they are long, the longer the better..
ID: 7645 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile speedimic
Avatar

Send message
Joined: 22 Feb 08
Posts: 260
Credit: 57,387,048
RAC: 0
Message 7678 - Posted: 12 Dec 2008, 19:57:21 UTC - in response to Message 7645.  
Last modified: 12 Dec 2008, 19:57:58 UTC

Some WUs run extremely long time, I have aborted this one after over 18 hours:

http://milkyway.cs.rpi.edu/milkyway/result.php?resultid=57580672

Yup, same here, I have three nm_stripe_79_fr1 running for over four hours and only 45% done.
Well I don't mind if they are long, the longer the better..


Those are broken.
Look here: Bad set of WUs !
mic.


ID: 7678 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Conan
Avatar

Send message
Joined: 2 Jan 08
Posts: 122
Credit: 69,475,989
RAC: 2,912
Message 7792 - Posted: 16 Dec 2008, 12:00:45 UTC

Just curious (and this has probably been stated before, maybe even by me in a thread I can't find), why does my Linux Opteron 285 machine take over 10 minutes longer to process a MilkyWay work unit than my Windows Opteron 285 machine ???

On average my Windows machine takes around 2,600 seconds but my Linux box takes around 3,300 seconds.

They are the same specifications bar different hard drives.

Is it just a compiling thing, as in a compiler more suited to Linux might change things ??
ID: 7792 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
ebahapo
Avatar

Send message
Joined: 6 Sep 07
Posts: 66
Credit: 636,861
RAC: 0
Message 7797 - Posted: 16 Dec 2008, 16:56:02 UTC - in response to Message 7792.  

Just curious (and this has probably been stated before, maybe even by me in a thread I can't find), why does my Linux Opteron 285 machine take over 10 minutes longer to process a MilkyWay work unit than my Windows Opteron 285 machine ???

On average my Windows machine takes around 2,600 seconds but my Linux box takes around 3,300 seconds.

They are the same specifications bar different hard drives.

Is it just a compiling thing, as in a compiler more suited to Linux might change things ??

True, different compilers, different results. But most importantly, Linux keeps the CPU at the lowest frequency when just running low-priority BOINC applications, whereas Windows throws the CPU at the highest frequency for them too. See more details here.

HTH

ID: 7797 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile Conan
Avatar

Send message
Joined: 2 Jan 08
Posts: 122
Credit: 69,475,989
RAC: 2,912
Message 7817 - Posted: 17 Dec 2008, 8:35:52 UTC - in response to Message 7797.  
Last modified: 17 Dec 2008, 9:26:21 UTC

Thanks Augustine, I will try and check this out.

EDIT: I am unable to find any folder or file relating to power that has any reference to 'Powersave'. So I am not sure if it exists with Fedora Core 3 or 6.
Throttling is not supported on the FC3 machine as far as I can tell.

(The computer having the slower run times runs Fedora Core 6, still another Opteron 285).
ID: 7817 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Profile YuRi

Send message
Joined: 27 Nov 07
Posts: 4
Credit: 9,698,836
RAC: 0
Message 7881 - Posted: 20 Dec 2008, 12:56:37 UTC
Last modified: 20 Dec 2008, 12:57:15 UTC

SUSE linux (2.6.5-7.191-smp), BOINC v.5.10.45

still get an error:

20/12/2008 14:52:50|Milkyway@home|Starting nm_stripe86_fr1_242469_1229776663_0
20/12/2008 14:52:50|Milkyway@home|Starting task nm_stripe86_fr1_242469_1229776663_0 using milkyway version 7
20/12/2008 14:52:54|Milkyway@home|Computation for task nm_stripe86_fr1_242469_1229776663_0 finished
20/12/2008 14:52:54|Milkyway@home|Output file nm_stripe86_fr1_242469_1229776663_0_0 for task nm_stripe86_fr1_242469_1229776663_0 absent


<core_client_version>5.10.45</core_client_version>
<![CDATA[
<message>
process exited with code 127 (0x7f, -129)
</message>
<stderr_txt>
milkyway_0.7_i686-pc-linux-gnu: error while loading shared libraries: libstdc++.so.6: cannot open shared object file: No such file or directory

</stderr_txt>
]]>
ID: 7881 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
cwhyl

Send message
Joined: 11 Nov 07
Posts: 41
Credit: 1,000,181
RAC: 0
Message 7897 - Posted: 21 Dec 2008, 5:02:02 UTC - in response to Message 7797.  
Last modified: 21 Dec 2008, 5:03:16 UTC


True, different compilers, different results. But most importantly, Linux keeps the CPU at the lowest frequency when just running low-priority BOINC applications, whereas Windows throws the CPU at the highest frequency for them too. See more details here.

HTH

No I don't believe in that
ID: 7897 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Emanuel

Send message
Joined: 18 Nov 07
Posts: 280
Credit: 2,442,757
RAC: 0
Message 7906 - Posted: 22 Dec 2008, 1:13:03 UTC - in response to Message 7897.  

No I don't believe in that

What do you mean? It's either true or it isn't - I don't know which and I don't feel like checking, but there is no magic here.
ID: 7906 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
cwhyl

Send message
Joined: 11 Nov 07
Posts: 41
Credit: 1,000,181
RAC: 0
Message 7977 - Posted: 24 Dec 2008, 2:23:44 UTC - in response to Message 7906.  

No I don't believe in that

What do you mean? It's either true or it isn't - I don't know which and I don't feel like checking, but there is no magic here.

My Linux boxen have always run at full speed for many years and there is no throttling at all.
ID: 7977 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
ebahapo
Avatar

Send message
Joined: 6 Sep 07
Posts: 66
Credit: 636,861
RAC: 0
Message 7978 - Posted: 24 Dec 2008, 4:50:52 UTC - in response to Message 7977.  

My Linux boxen have always run at full speed for many years and there is no throttling at all.

Your "boxen" have up-to-date processors and kernel, so you should be able to type "powersave -r" from the command-line when the system is idle to check the effective CPU frequency.

Most current standard Linux set ups come with default power management that's more sophisticated than old throttling.

HTH

ID: 7978 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
cwhyl

Send message
Joined: 11 Nov 07
Posts: 41
Credit: 1,000,181
RAC: 0
Message 8087 - Posted: 31 Dec 2008, 10:45:56 UTC - in response to Message 7978.  

My Linux boxen have always run at full speed for many years and there is no throttling at all.

Your "boxen" have up-to-date processors and kernel, so you should be able to type "powersave -r" from the command-line when the system is idle to check the effective CPU frequency.

Most current standard Linux set ups come with default power management that's more sophisticated than old throttling.

HTH

If an idle box can save power that's nice
Tested Fedora and Ubuntu renicing the app to 0 and there is no difference in runtimes

ID: 8087 · Rating: 0 · rate: Rate + / Rate - Report as offensive     Reply Quote
Previous · 1 · 2 · 3

Message boards : Number crunching : post milkyway_i686-pc-linux-gnu problems here

©2024 Astroinformatics Group