Posts by RAMen
log in
1) Message boards : Number crunching : linux 64 WU erroring (Message 721)
Posted 8 Oct 2012 by Profile RAMen
Detaching comp ID#179 as its producing next to no useful results in last 36 hours

Outcome Computation error
Client state Compute error
Exit status -177 (0xffffffffffffff4f) ERR_RSC_LIMIT_EXCEEDED

Stderr output

<core_client_version>6.10.59</core_client_version>
<![CDATA[
<message>
Maximum elapsed time exceeded
</message>
<stderr_txt>
wrapper: starting
18:46:18 (2240): wrapper: running fit_sed (1 filters.dat observations.dat)
18:59:42 (2240): wrapper: running fit_sed (2 filters.dat observations.dat)
19:12:54 (2240): wrapper: running fit_sed (3 filters.dat observations.dat)
19:25:59 (2240): wrapper: running fit_sed (4 filters.dat observations.dat)
19:38:36 (2240): wrapper: running fit_sed (5 filters.dat observations.dat)
19:50:59 (2240): wrapper: running fit_sed (6 filters.dat observations.dat)
20:11:14 (2240): wrapper: running fit_sed (7 filters.dat observations.dat)
20:24:40 (2240): wrapper: running fit_sed (8 filters.dat observations.dat)

</stderr_txt>
]]>
2) Message boards : Number crunching : linux 64 WU erroring (Message 720)
Posted 8 Oct 2012 by Profile RAMen
Outcome Computation error
Client state Compute error
Exit status -177 (0xffffffffffffff4f) ERR_RSC_LIMIT_EXCEEDED
3) Message boards : Number crunching : linux 64 WU erroring (Message 718)
Posted 8 Oct 2012 by Profile RAMen
Have updated linux from Ubuntu repository.
Restarted machine.
and reset the project.

Machine ID #179 is still creating errors

CPU type GenuineIntel
Intel(R) Core(TM)2 Quad CPU Q9400 @ 2.66GHz [Family 6 Model 23 Stepping 10]
Number of processors 4
Coprocessors NVIDIA GeForce GTX 260 (895MB)
Operating System Linux
2.6.38-16-generic
BOINC version 6.10.59

cpu 50% Asteroids
cpu 50% POGS
gpu 100% Einstein
4) Message boards : Number crunching : linux 64 WU erroring (Message 716)
Posted 8 Oct 2012 by Profile RAMen
Host ID #177 since 8:03 am Perth time has been producing correct results
Host ID #179 has continued to produce errors
5) Message boards : Number crunching : linux 64 WU erroring (Message 703)
Posted 7 Oct 2012 by Profile RAMen
Tasks starting with "PGC" seem to be erroring out

This is happening on both LINUX 64 machines

below example extracted from boincview messages window

Host Project Date Message Ubuntu64 pogs 7/10/2012 3:52:18 PM Aborting task PGC1191673_area206224_0: exceeded elapsed time limit 457.18 (331000.00G/724.00G) Ubuntu64 pogs 7/10/2012 3:52:19 PM Computation for task PGC1191673_area206224_0 finished Ubuntu64 pogs 7/10/2012 3:52:19 PM Output file PGC1191673_area206224_0_0 for task PGC1191673_area206224_0 absent Ubuntu64 pogs 7/10/2012 3:52:19 PM Starting task PGC1109092_area206241_1 using magphys_wrapper version 300 in slot 2 Ubuntu64 pogs 7/10/2012 4:03:53 PM Aborting task PGC1109092_area206241_1: exceeded elapsed time limit 685.09 (496000.00G/724.00G) Ubuntu64 pogs 7/10/2012 4:03:54 PM Computation for task PGC1109092_area206241_1 finished Ubuntu64 pogs 7/10/2012 4:03:54 PM Output file PGC1109092_area206241_1_0 for task PGC1109092_area206241_1 absent Ubuntu64 pogs 7/10/2012 4:03:54 PM Starting task PGC1191673_area206225_0 using magphys_wrapper version 300 in slot 2 Ubuntu64 pogs 7/10/2012 4:15:26 PM Aborting task PGC1191673_area206225_0: exceeded elapsed time limit 685.09 (496000.00G/724.00G) Ubuntu64 pogs 7/10/2012 4:15:28 PM Computation for task PGC1191673_area206225_0 finished Ubuntu64 pogs 7/10/2012 4:15:28 PM Output file PGC1191673_area206225_0_0 for task PGC1191673_area206225_0 absent Ubuntu64 pogs 7/10/2012 4:15:28 PM Starting task PGC1191673_area206223_0 using magphys_wrapper version 300 in slot 2 Ubuntu64 pogs 7/10/2012 4:30:04 PM Aborting task PGC1191673_area206170_0: exceeded elapsed time limit 4116.04 (2980000.00G/724.00G) Ubuntu64 pogs 7/10/2012 4:30:05 PM Computation for task PGC1191673_area206170_0 finished Ubuntu64 pogs 7/10/2012 4:30:05 PM Output file PGC1191673_area206170_0_0 for task PGC1191673_area206170_0 absent Ubuntu64 pogs 7/10/2012 4:30:05 PM Starting task PGC1109092_area206246_1 using magphys_wrapper version 300 in slot 3 Ubuntu64 pogs 7/10/2012 4:42:17 PM Aborting task PGC1191673_area206223_0: exceeded elapsed time limit 1600.84 (1159000.00G/724.00G) Ubuntu64 pogs 7/10/2012 4:42:18 PM Computation for task PGC1191673_area206223_0 finished Ubuntu64 pogs 7/10/2012 4:42:18 PM Output file PGC1191673_area206223_0_0 for task PGC1191673_area206223_0 absent Ubuntu64 pogs 7/10/2012 4:42:18 PM Starting task PGC1191673_area206174_0 using magphys_wrapper version 300 in slot 2


Links to WU errors on comp #177
PGC1191673_area206224_0
PGC1191673_area206223_0
PGC1109092_area206241_1

also errors on comp #179
PGC1082530_area206742_1
6) Message boards : Number crunching : Invalid tasks (Message 608)
Posted 20 Sep 2012 by Profile RAMen
@JugNut

Read here..
http://ec2-23-23-126-96.compute-1.amazonaws.com/pogs/forum_thread.php?id=97
7) Message boards : Number crunching : Downloads working - Uploads NOT working (Message 553)
Posted 13 Sep 2012 by Profile RAMen

Uploads not working for last 30 minutes

13/09/2012 1:19:02 PM Started upload of NGC4041_area91147_1_0
13/09/2012 1:19:04 PM [error] Error reported by file upload server: can't open log file '../log_ip-10-98-134-10/file_upload_handler.log' (errno: 9)
13/09/2012 1:19:04 PM Temporarily failed upload of NGC4041_area91147_1_0: transient upload error
13/09/2012 1:19:04 PM Backing off 28 min 30 sec on upload of NGC4041_area91147_1_0
8) Message boards : Number crunching : Cross validation (Message 491)
Posted 1 Sep 2012 by Profile RAMen
6 instances marked inconclusive (win v linux) where win instance validated against another win instance and linux marked invalid

http://ec2-23-23-126-96.compute-1.amazonaws.com/pogs/workunit.php?wuid=86267
http://ec2-23-23-126-96.compute-1.amazonaws.com/pogs/workunit.php?wuid=88266
http://ec2-23-23-126-96.compute-1.amazonaws.com/pogs/workunit.php?wuid=88265
http://ec2-23-23-126-96.compute-1.amazonaws.com/pogs/workunit.php?wuid=84885
http://ec2-23-23-126-96.compute-1.amazonaws.com/pogs/workunit.php?wuid=15114
http://ec2-23-23-126-96.compute-1.amazonaws.com/pogs/workunit.php?wuid=15096

1 instance marked inconclusive (win v linux) where linux instance validated against another linux instance and win marked invalid
http://ec2-23-23-126-96.compute-1.amazonaws.com/pogs/workunit.php?wuid=84860


Strangely the majority win vs linux do validate.
9) Message boards : News : Load Test Status (Message 468)
Posted 30 Aug 2012 by Profile RAMen
Three hundred something members with credit
A lot more on zero credit (total at time of writing =2123) wonder how to get them involved ...

thats 7 times the present crunching power !!!

http://ec2-23-23-126-96.compute-1.amazonaws.com/pogs/top_users.php?sort_by=expavg_credit&offset=2120

EDIT: ehhh @kashi beat me to it
10) Message boards : News : Load test time (Message 459)
Posted 29 Aug 2012 by Profile RAMen
I am also fine with the cache limit of 10 per core.
Unfortunately I was filling the caches with new work units from other projects as the new galaxies were being uploaded so will be a while before i can get back to full production at POGS.
currenntly:
693 valid WU
0 invalid WU
2 errors - both killed from the server
So few errors from a new project in development is exceptional. Well done !!
11) Message boards : Number crunching : Cannot upload last WU (Message 449)
Posted 29 Aug 2012 by Profile RAMen
My very last work unit won't upload and report.

I was wondering (because the communication on this project has been so outstanding) If you were unaware the server was not working properly ... there has been no "NEWS" message saying there would be a service window (where the servers would be off-line).

scheduler ip-10-98-134-10 Not Running
feeder ip-10-98-134-10 Not Running
transitioner ip-10-98-134-10 Not Running
file_deleter ip-10-98-134-10 Not Running
/home/ec2-user/boinc-magphys/server/src/magphys_validator/magphys_validator ip-10-98-134-10 Not Running
assimilator ip-10-98-134-10 Not Running
assimilator ip-10-98-134-10 Not Running



Wed 29 Aug 2012 14:27:44 WST pogs update requested by user
Wed 29 Aug 2012 14:27:48 WST pogs Sending scheduler request: Requested by user.
Wed 29 Aug 2012 14:27:48 WST pogs Reporting 1 completed tasks, requesting new tasks for CPU and GPU
Wed 29 Aug 2012 14:27:51 WST pogs Scheduler request completed: got 0 new tasks
Wed 29 Aug 2012 14:27:51 WST pogs Message from server: Project is temporarily shut down for maintenance
12) Message boards : Number crunching : Which CPU is suitable for this project? (Message 406)
Posted 22 Aug 2012 by Profile RAMen
@Sajjad Imam
apologies...
I am the TURKEY in this ... managed to miss the 24 hours in the middle.
need to learn to read. :\
13) Message boards : Number crunching : Which CPU is suitable for this project? (Message 400)
Posted 22 Aug 2012 by Profile RAMen
@ Sajjid Imam
A check of the WU <stderr_txt>
here:
http://ec2-23-23-126-96.compute-1.amazonaws.com/pogs/result.php?resultid=36436
and here
http://ec2-23-23-126-96.compute-1.amazonaws.com/pogs/result.php?resultid=17687

shows
Intel: approx 7 hr 26 min activity with two breaks in processing (23 pixels)
AMD : approx 9 hr 40 min activity (yours) continuous processing (23 pixels)

A significant difference 2hr and 14 min but not as large as it appears to report.Your WU isn't the 20 hour monster it appears to be.
Work unit times are not working properly as yet for all OS. It is a project in development :)
14) Message boards : Number crunching : Which CPU is suitable for this project? (Message 395)
Posted 22 Aug 2012 by Profile RAMen
Went looking in my results found this:
Workunit: NGC1275_area11724
Workunit # 14195
Workunit URL http://ec2-23-23-126-96.compute-1.amazonaws.com/pogs/workunit.php?wuid=14195



Computers
1.Q9400
2.AMD Phenom 9550
OS
1.Linux Ubuntu 64 (11.04)
2.Win Vista 64

Standard Error Output
wrapper start
1. 05:46:45
2. 07:02:17
boinc finish
1. 10:50:33
2. 15:22:07
time to complete
1. 5h 3m 12s ( 18 192s) - for 19 steps
2. 8h 19m 50 s ( 29 990s) - for 19 steps

reported run time
1. 168,226.20s
2. 29,991.95s
minutes /pixel
1. 16 min (approx 61% of time taken for comp 2)
2. 26 min
all min/pixel steps consistent
1. yes
2. yes



Hmmm
Over 3 hour difference
Similar processors expect phenom to be slightly faster.
OS both 64 bit
Linux64 faster than Windows64 ????
AMD slower than Intel ???
Reported run time for linux way off times in stderr output
15) Message boards : News : New images (Message 330)
Posted 17 Aug 2012 by Profile RAMen
Impressive.

Is there a there a colour gradient available to indicate levels of activity?
I assume its blue > purple > red > orange > yellow >white.

Congrats ... never seen a project give participants feed back and results like this in such a short time frame since inception.
16) Message boards : Cafe : The Team (Message 310)
Posted 14 Aug 2012 by Profile RAMen
Thanks for this I had been wondering aboutwho runs the project and makes everything work so well....

Perhaps it needs to be on the front page under

[Link to page listing project personnel, and an email address]
17) Message boards : Number crunching : Version 2 Error while computing (Message 262)
Posted 11 Aug 2012 by Profile RAMen
I can confirm this behaviour on 3 linux work units
This work unit:
http://ec2-23-23-126-96.compute-1.amazonaws.com/pogs/result.php?resultid=11415

sent 10/08/2012 06:54:06
returned 10/08/2012 18:59:15
time spent on my HDD 12:05:09

run time reported as 43 509 sec .......thats 12 hours 5min and 9 sec
CPU time 886 249.20 sec
You are doing a great job with the project. Glad to be a tester here.
+1




Main page · Your account · Message boards


Copyright © 2017 The International Centre for Radio Astronomy Research