climateprediction.net home page
Posts by ktf

Posts by ktf

1) Message boards : Number crunching : OpenIFS tasks : make sure boinc client option 'Leave non-GPU tasks in memory' is selected! (Message 67633)
Posted 13 Jan 2023 by ktf
Post:
Hi all,

I have a 4-core CPU with 8GB of memory, no swap file. BOINC regularly crashes when it chooses to run 3 or more OpenIFS tasks concurrently. Is there any way to instruct BOINC never to run more than one Climateprediction task concurrently, even if other projects have no work available?

I'd like to run a little Climateprediction alongside other projects, but I can't seem to find a way to make this work.
2) Message boards : Number crunching : Like ghost work unit (Message 51390)
Posted 10 Feb 2015 by ktf
Post:
Okay, if it poses no problem for the science I'm fine with it :)
3) Message boards : Number crunching : Like ghost work unit (Message 51388)
Posted 10 Feb 2015 by ktf
Post:
I have got the same problem: I have three WUs that show up here, but do not show up on my computer.

http://climateapps2.oerc.ox.ac.uk/cpdnboinc/result.php?resultid=17725337
http://climateapps2.oerc.ox.ac.uk/cpdnboinc/result.php?resultid=17725346
http://climateapps2.oerc.ox.ac.uk/cpdnboinc/result.php?resultid=17760457

I think it is a good idea to 'free these' in some way, because I have no way to finish these, it is only going to slow down the final outcome this way :)

Luckily, this computer hasn't been offline in the meantime, so I've captured the error messages. Maybe they can be of some use?
332: 12-Jan-2015 06:18:16 (low) [climateprediction.net] Sending scheduler request: To fetch work.
333: 12-Jan-2015 06:18:16 (low) [climateprediction.net] Requesting new tasks for CPU
334: 12-Jan-2015 06:18:19 (internal error) [climateprediction.net] [error] Can't parse file info in scheduler reply: file name is empty or has '..'
335: 12-Jan-2015 06:18:19 (internal error) [climateprediction.net] [error] Can't parse file info in scheduler reply: file name is empty or has '..'
336: 12-Jan-2015 06:18:19 (internal error) [climateprediction.net] [error] Can't parse file info in scheduler reply: file name is empty or has '..'
337: 12-Jan-2015 06:18:19 (internal error) [climateprediction.net] [error] Can't parse file info in scheduler reply: file name is empty or has '..'
338: 12-Jan-2015 06:18:19 (low) [climateprediction.net] Scheduler request completed: got 1 new tasks
339: 12-Jan-2015 06:18:19 (low) [climateprediction.net] No work can be sent for the applications you have selected
340: 12-Jan-2015 06:18:19 (low) [climateprediction.net] No work is available for UK Met Office Coupled Model Full Resolution Ocean
341: 12-Jan-2015 06:18:19 (low) [climateprediction.net] Your preferences allow work from applications other than those selected
342: 12-Jan-2015 06:18:19 (low) [climateprediction.net] Sending work from other applications
343: 12-Jan-2015 06:18:19 (internal error) [climateprediction.net] [error] State file error: missing file
344: 12-Jan-2015 06:18:19 (internal error) [climateprediction.net] [error] Can't handle task hadam3p_eu_zfk5_2013_0_009400872_2 in scheduler reply
345: 12-Jan-2015 07:18:55 (low) [climateprediction.net] Sending scheduler request: To fetch work.
346: 12-Jan-2015 07:18:55 (low) [climateprediction.net] Requesting new tasks for CPU
347: 12-Jan-2015 07:18:58 (internal error) [climateprediction.net] [error] Can't parse file info in scheduler reply: file name is empty or has '..'
348: 12-Jan-2015 07:18:58 (internal error) [climateprediction.net] [error] Can't parse file info in scheduler reply: file name is empty or has '..'
349: 12-Jan-2015 07:18:58 (internal error) [climateprediction.net] [error] Can't parse file info in scheduler reply: file name is empty or has '..'
350: 12-Jan-2015 07:18:58 (internal error) [climateprediction.net] [error] Can't parse file info in scheduler reply: file name is empty or has '..'
351: 12-Jan-2015 07:18:58 (low) [climateprediction.net] Scheduler request completed: got 1 new tasks
352: 12-Jan-2015 07:18:58 (low) [climateprediction.net] No work can be sent for the applications you have selected
353: 12-Jan-2015 07:18:58 (low) [climateprediction.net] No work is available for UK Met Office Coupled Model Full Resolution Ocean
354: 12-Jan-2015 07:18:58 (low) [climateprediction.net] Your preferences allow work from applications other than those selected
355: 12-Jan-2015 07:18:58 (low) [climateprediction.net] Sending work from other applications
356: 12-Jan-2015 07:18:58 (internal error) [climateprediction.net] [error] State file error: missing file
357: 12-Jan-2015 07:18:58 (internal error) [climateprediction.net] [error] Can't handle task hadam3p_eu_zfji_2013_0_009400849_1 in scheduler reply
[...]
384: 12-Jan-2015 17:57:32 (low) [climateprediction.net] Sending scheduler request: To fetch work.
385: 12-Jan-2015 17:57:32 (low) [climateprediction.net] Requesting new tasks for CPU
386: 12-Jan-2015 17:57:35 (internal error) [climateprediction.net] [error] Can't parse file info in scheduler reply: file name is empty or has '..'
387: 12-Jan-2015 17:57:35 (internal error) [climateprediction.net] [error] Can't parse file info in scheduler reply: file name is empty or has '..'
388: 12-Jan-2015 17:57:35 (internal error) [climateprediction.net] [error] Can't parse file info in scheduler reply: file name is empty or has '..'
389: 12-Jan-2015 17:57:35 (internal error) [climateprediction.net] [error] Can't parse file info in scheduler reply: file name is empty or has '..'
390: 12-Jan-2015 17:57:35 (low) [climateprediction.net] Scheduler request completed: got 1 new tasks
391: 12-Jan-2015 17:57:35 (low) [climateprediction.net] No work can be sent for the applications you have selected
392: 12-Jan-2015 17:57:35 (low) [climateprediction.net] No work is available for UK Met Office Coupled Model Full Resolution Ocean
393: 12-Jan-2015 17:57:35 (low) [climateprediction.net] Your preferences allow work from applications other than those selected
394: 12-Jan-2015 17:57:35 (low) [climateprediction.net] Sending work from other applications
395: 12-Jan-2015 17:57:35 (internal error) [climateprediction.net] [error] State file error: missing file
396: 12-Jan-2015 17:57:35 (internal error) [climateprediction.net] [error] Can't handle task hadam3p_eu_zvyg_2013_0_009435278_0 in scheduler reply
4) Message boards : Number crunching : Task wont restart (Message 46566)
Posted 2 Jul 2013 by ktf
Post:
Hi,

I have this task running: http://climateapps2.oerc.ox.ac.uk/cpdnboinc/result.php?resultid=15813485

But it won't restart. I tried restarting my computer several times, but it is stuck at 25.097%. ps aux on my computers says

_user_ 3540 0.2 0.1 9836 7144 ? SNl 09:58 0:00 ../../projects/climateprediction.net/hadcm3n_6.07_i686-pc-linux-gnu hadcm3n_o4ep_1940_40_008382057 ocean_o4ep_1940_40_008382057_0 atmos_o4ep_1940_40_008382057_0 spec3a_sw_3_asol2c_hadcm3 spec3a_lw_3_asol2c_hadcm3 waterfix.ancil.be.32 NAT_VOLC DMSSO2NH3_1900_RCP sulpc_oxidants_19_A2_1990f SPARC_O3_rebuild_1900


It isn't using CPU resources so it isn't really running, as you can see CPU time is zero.

The last lines of stderr.txt (while still in 'running' state) in the slots directory are these

[...]
Signal 15 received, exiting...
Called boinc_finish
*** Error in `../../projects/climateprediction.net/hadcm3n_6.07_i686-pc-linux-gnu': double free or corruption (out): 0x09821548 ***
hadcm3n_6.07_i686-pc-linux-gnu: malloc.c:2369: sysmalloc: Assertion `(old_top == (((mbinptr) (((char *) &((av)->bins[((1) - 1) * 2])) - __builtin_offsetof (struct malloc_chunk, fd)))) && old_size == 0) || ((unsigned long) (old_size) >= (unsigned long)((((__builtin_offsetof (struct malloc_chunk, fd_nextsize))+((2 * (sizeof(size_t))) - 1)) & ~((2 * (sizeof(size_t))) - 1))) && ((old_top)->size & 0x1) && ((unsigned long)old_end & pagemask) == 0)' failed.
SIGABRT: abort called
Signal 1 received, exiting...
Called boinc_finish
Signal 1 received, exiting...
Called boinc_finish
Signal 15 received, exiting...
Called boinc_finish
*** Error in `../../projects/climateprediction.net/hadcm3n_6.07_i686-pc-linux-gnu': double free or corruption (out): 0x0a04b548 ***
hadcm3n_6.07_i686-pc-linux-gnu: malloc.c:2369: sysmalloc: Assertion `(old_top == (((mbinptr) (((char *) &((av)->bins[((1) - 1) * 2])) - __builtin_offsetof (struct malloc_chunk, fd)))) && old_size == 0) || ((unsigned long) (old_size) >= (unsigned long)((((__builtin_offsetof (struct malloc_chunk, fd_nextsize))+((2 * (sizeof(size_t))) - 1)) & ~((2 * (sizeof(size_t))) - 1))) && ((old_top)->size & 0x1) && ((unsigned long)old_end & pagemask) == 0)' failed.
SIGABRT: abort called
*** Error in `../../projects/climateprediction.net/hadcm3n_6.07_i686-pc-linux-gnu': double free or corruption (out): 0x09c36548 ***
hadcm3n_6.07_i686-pc-linux-gnu: malloc.c:2369: sysmalloc: Assertion `(old_top == (((mbinptr) (((char *) &((av)->bins[((1) - 1) * 2])) - __builtin_offsetof (struct malloc_chunk, fd)))) && old_size == 0) || ((unsigned long) (old_size) >= (unsigned long)((((__builtin_offsetof (struct malloc_chunk, fd_nextsize))+((2 * (sizeof(size_t))) - 1)) & ~((2 * (sizeof(size_t))) - 1))) && ((old_top)->size & 0x1) && ((unsigned long)old_end & pagemask) == 0)' failed.
SIGABRT: abort called


What should I do? Is there a way to start this one again? Should I abort? Is one of the devs interested in more information?
5) Message boards : Number crunching : Too many total results? (Message 35578)
Posted 22 Nov 2008 by ktf
Post:
Okay, thanks for that very fast reply ^^
6) Message boards : Number crunching : Too many total results? (Message 35576)
Posted 22 Nov 2008 by ktf
Post:
Hello,

I just got my first WU from Climateprediction.net, this one: http://climateapps2.oucs.ox.ac.uk/cpdnboinc/workunit.php?wuid=6253730 There are two peers with Compute Error, and I\'ve just spend 3 hours, with another 1300 to go. The WU page says:

max # of error/total/success tasks 3, 4, 1
errors Too many total results

Should I abort this task, or do I get that credit anyway?




©2024 climateprediction.net