Trac April 2015

trac@lists.einsteintoolkit.org

1 participants
112 discussions

[Einstein Toolkit] #1751: [Pull request: CactusUtils/WatchDog] new thorn to automatically terminate jobs that hang
by Einstein Toolkit 01 May '15

01 May '15

#1751: [Pull request: CactusUtils/WatchDog] new thorn to automatically terminate jobs that hang -----------------------------------+---------------------------------------- Reporter: dradice@… | Owner: Type: enhancement | Status: new Priority: unset | Milestone: Component: EinsteinToolkit thorn | Version: development version Keywords: | -----------------------------------+---------------------------------------- WatchDog is thorn that terminates jobs that do not make progress over a user-defined time frame. Internally, WatchDog updates an internal timer at CCTK_ANALYSIS and uses the pthread library to spawn watcher thread that periodically checks if the timer has been updated. If the timer has not been updated for more than a user-defined time frame, the thread calls "exit()" to terminate the process (and the job). -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1751> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 13

[Einstein Toolkit] #1765: CarpetRegrid does not check for incorrect outer boundary size
by Einstein Toolkit 29 Apr '15

29 Apr '15

#1765: CarpetRegrid does not check for incorrect outer boundary size --------------------+------------------------------------------------------- Reporter: rhaas | Owner: eschnett Type: defect | Status: new Priority: unset | Milestone: Component: Carpet | Version: development version Keywords: | --------------------+------------------------------------------------------- The attached parfile trigger an assert for inconsistent grid structure inside of CarpetLib. The issue is that boundary_size is set to 1 instead of 3. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1765> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 1

[Einstein Toolkit] #1761: Problem with building on XC30 CFCA
by Einstein Toolkit 28 Apr '15

28 Apr '15

#1761: Problem with building on XC30 CFCA -----------------------------------+---------------------------------------- Reporter: maxim.barkov@… | Owner: Type: task | Status: new Priority: major | Milestone: Component: Cactus | Version: development version Keywords: | -----------------------------------+---------------------------------------- I try to compile ET on CFCA NAOJ cluster Cray XC30. I used as similar system edison in NERSC. So far I have problems with build procedure. CFCA is configured by default for Cray environment. In configuration file I switch programming enviroment to Intel and correct paths to actual ones. Unfortunately simfactory crashed. {{{ libtool: install: /usr/bin/install -c fftw-wisdom /home/barkovmm/ET/Cactus/configs/whisky/scratch/external/FFTW3/bin/fftw- wisdom Making install in m4 ~/ET/Cactus/configs/whisky/scratch FFTW3: Cleaning up... FFTW3: Done. Creating /home/barkovmm/ET/Cactus/configs/whisky/lib/libthorn_FFTW3.a make: *** [whisky] Error 2 }}} If I run comand on the cluster {{{make whisky_11}}} ET continue configuration and crushed on GSL {{{ icc: command line warning #10121: overriding '-xCORE-AVX2' with '-xHost' In file included from results.c(32): /usr/lib64/gcc/x86_64-suse-linux/4.3/include/varargs.h(4): error: #error directive: "GCC no longer implements <varargs.h>." #error "GCC no longer implements <varargs.h>." ^ In file included from results.c(32): /usr/lib64/gcc/x86_64-suse-linux/4.3/include/varargs.h(5): error: #error directive: "Revise your code to use <stdarg.h>." #error "Revise your code to use <stdarg.h>." ^ results.c(95): error #54: too few arguments in invocation of macro "va_start" va_start (ap); ^ results.c(95): error: expected an expression va_start (ap); ^ results.c(155): error #54: too few arguments in invocation of macro "va_start" va_start (ap); ^ results.c(155): error: expected an expression va_start (ap); ^ results.c(232): error #54: too few arguments in invocation of macro "va_start" va_start (ap); ^ results.c(232): error: expected an expression va_start (ap); ^ results.c(309): error #54: too few arguments in invocation of macro "va_start" va_start (ap); ^ results.c(309): error: expected an expression va_start (ap); ^ results.c(364): error #54: too few arguments in invocation of macro "va_start" va_start (ap); ^ results.c(364): error: expected an expression va_start (ap); ^ results.c(408): error #54: too few arguments in invocation of macro "va_start" va_start (ap); ^ results.c(408): error: expected an expression va_start (ap); ^ Internal error: null pointer compilation aborted for results.c (code 4) make[6]: *** [results.lo] Error 1 make[5]: *** [all-recursive] Error 1 make[4]: *** [all] Error 2 make[3]: *** [/work/barkovmm/ET/Cactus/configs/whisky_11/scratch/done/GSL] Error 2 make[2]: *** [make.checked] Error 2 make[1]: *** [/work/barkovmm/ET/Cactus/configs/whisky_11/lib/libthorn_GSL.a] Error 2 make: *** [whisky_11] Error 2 }}} Any help or suggestions are very welcome. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1761> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 1

[Einstein Toolkit] #1768: Output of distrib=constant arrays
by Einstein Toolkit 27 Apr '15

27 Apr '15

#1768: Output of distrib=constant arrays -------------------------+-------------------------------------------------- Reporter: hinder | Owner: eschnett Type: enhancement | Status: new Priority: minor | Milestone: Component: Carpet | Version: development version Keywords: | -------------------------+-------------------------------------------------- I have a Cactus array with size=1 and distrib=constant. I would like to see its value on all processes. According to http://cactuscode.org/pipermail/users/2014-March/003421.html, it has been observed that CarpetIOASCII (and CarpetIOHDF5) only output the data from process 0, whereas IOASCII outputs the data from all processes. The reason I need this is that I want to see the system swap usage on each process stored in SystemStatistics::process_memory_mb. The data is legitimately different on each process. {{{ REAL process_memory_mb TYPE=array DIM=1 SIZE=1 DISTRIB=constant TAGS='Checkpoint="no"' }}} How hard would it be to add support to CarpetIOASCII for outputting grid array data from all processes for distrib-constant arrays? It already does this for distrib=default. To use the current functionality, one way would be to increase the size of the array and then write code to replicate the data between processes. However, I don't think there is any way to specify that the array should have size=NPROCS, so you would have to specify this using a parameter, and this is a lot of work for something which would more naturally be done in CarpetIOASCII. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1768> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 0

[Einstein Toolkit] #1767: test system does not remove old test data before running new test
by Einstein Toolkit 24 Apr '15

24 Apr '15

#1767: test system does not remove old test data before running new test -----------------------+---------------------------------------------------- Reporter: anonymous | Owner: Type: defect | Status: new Priority: major | Milestone: Component: Cactus | Version: development version Keywords: | -----------------------+---------------------------------------------------- When running a test, the test system does not delete the old test output directory first which can hide missing files. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1767> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 0

[Einstein Toolkit] #1766: simfactory creates its log file in repos/log/simfactory.log rather than Cactus/log/simfactory.log
by Einstein Toolkit 24 Apr '15

24 Apr '15

#1766: simfactory creates its log file in repos/log/simfactory.log rather than Cactus/log/simfactory.log ------------------------+--------------------------------------------------- Reporter: rhaas | Owner: Type: defect | Status: new Priority: minor | Milestone: Component: SimFactory | Version: development version Keywords: | ------------------------+--------------------------------------------------- right now (I suspect after the switch to git) simfactory creates its log file in repos/log/simfactory.log (so 2 level upwards from its bin directory). -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1766> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 0

[Einstein Toolkit] #1756: Pull requests: staggered restriction/prolongation operators
by Einstein Toolkit 23 Apr '15

23 Apr '15

#1756: Pull requests: staggered restriction/prolongation operators -------------------------+-------------------------------------------------- Reporter: rhaas | Owner: eschnett Type: enhancement | Status: new Priority: major | Milestone: Component: Carpet | Version: development version Keywords: | -------------------------+-------------------------------------------------- Pull request https://bitbucket.org/eschnett/carpet/pull-request/3/staggered- restriction-prolongation/diff implements the staggered operators required for edge centred vector potential MHD evolutions. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1756> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 3

[Einstein Toolkit] #1211: CarpetIOScalar should write file info for restart files
by Einstein Toolkit 22 Apr '15

22 Apr '15

#1211: CarpetIOScalar should write file info for restart files --------------------+------------------------------------------------------- Reporter: knarf | Owner: eschnett Type: defect | Status: new Priority: minor | Milestone: Component: Carpet | Version: Keywords: | --------------------+------------------------------------------------------- Currently Carpet doesn't write file info for files created by a restarted simulation (from a checkpoint, writing into a new file). It should instead write the header if it created the file - which means it need to check whether it appends or created the file new. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1211> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 3

[Einstein Toolkit] #1282: Enable HDF5 compression by default in Carpet
by Einstein Toolkit 22 Apr '15

22 Apr '15

#1282: Enable HDF5 compression by default in Carpet -------------------------+-------------------------------------------------- Reporter: hinder | Owner: eschnett Type: enhancement | Status: new Priority: major | Milestone: Component: Carpet | Version: Keywords: | -------------------------+-------------------------------------------------- The current default for CarpetIOHDF5::compression_level is 0 (no compression). I have been using compression in most of my HDF5 files for years, and have never run into any problem. CPUs are typically much faster than storage nowadays. I propose that the compression level should default to 9. This would affect output and checkpoint files, and could lead to huge space savings. Apart from the checkpoint files being written and read quicker and taking less disk space, the user should not notice, as the HDF5 library handles compression transparently. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1282> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 8

[Einstein Toolkit] #1760: Update supported machines wiki page
by Einstein Toolkit 13 Apr '15

13 Apr '15

#1760: Update supported machines wiki page -------------------------------------+-------------------------------------- Reporter: rhaas | Owner: Type: task | Status: new Priority: minor | Milestone: Component: EinsteinToolkit website | Version: development version Keywords: | -------------------------------------+-------------------------------------- The wiki page detailed the supported machines https://docs.einsteintoolkit.org/et-docs/Supported_Machines should be updated. Ideally this should be done mechanically based on simfactories machine.ini files. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1760> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 1

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

Trac April 2015