Trac September 2016

trac@lists.einsteintoolkit.org

1 participants
106 discussions

[Einstein Toolkit] #1622: Cannot log in to Blue Waters
by Einstein Toolkit 06 Oct '16

06 Oct '16

#1622: Cannot log in to Blue Waters ------------------------+--------------------------------------------------- Reporter: eschnett | Owner: eschnett Type: defect | Status: new Priority: major | Milestone: Component: SimFactory | Version: development version Keywords: | ------------------------+--------------------------------------------------- With the new gsissh mechanism in Simfactory, I receive the error below when I try to log in. {{{ $ ./bin/sim --verbose login bluewaters Info: Simfactory command: ./bin/../simfactory/lib/sim.py "--verbose" "login" "bluewaters" Info: Version 2356M Info: The Simulation Factory: Manage Cactus simulations Info: defs: /Users/eschnett/Cvanilla/simfactory/etc/defs.ini Info: defs.local: /Users/eschnett/Cvanilla/simfactory/etc/defs.local.ini Info: Executing command: login Info: Logging into remote machine bluewaters Info: executing command: /bin/bash -c '{ :; } && { { mkdir -p /Users/eschnett/Cvanilla/.globus && : >> /Users/eschnett/Cvanilla/.globus/proxy-tfca-ncsa && chmod go-rwx /Users/eschnett/Cvanilla/.globus/proxy-tfca-ncsa && export X509_USER_PROXY=/Users/eschnett/Cvanilla/.globus/proxy-tfca-ncsa && : mkdir -p /Users/eschnett/Cvanilla/.globus/certificates-tfca-ncsa && : export X509_CERT_DIR=/Users/eschnett/Cvanilla/.globus/certificates-tfca- ncsa && { { grid-proxy-info -issuer -file /Users/eschnett/Cvanilla/.globus/proxy-tfca- ncsa 2>/dev/null | grep "^/C=US/O=National Center for Supercomputing Applications/" >/dev/null 2>&1 && test $(grid-proxy-info -timeleft -file /Users/eschnett/Cvanilla/.globus /proxy-tfca-ncsa 2>/dev/null) -gt 0 2>/dev/null } || { { grid-proxy-destroy 2>/dev/null || true; } && myproxy-logon -p 7512 -s tfca.ncsa.illinois.edu -T -l eschnett -o /Users/eschnett/Cvanilla/.globus/proxy-tfca-ncsa } } && { globus-update-certificate-dir >/dev/null 2>&1 || true; }; } && gsissh -o UserKnownHostsFile=/Users/eschnett/Cvanilla/simfactory/etc/ssh_known_hosts -t eschnett(a)h2ologin.ncsa.illinois.edu '\''cd /u/sciteam/eschnett/Cvanilla || echo "Could not change to directory /u/sciteam/eschnett/Cvanilla"; $SHELL -l'\''; }' Enter MyProxy pass phrase: Failed to receive credentials. Failed writing buffer to BIO Failed unpacking proxy certificate from buffer Error accepting delegated credentials: Failed writing buffer to BIO Failed unpacking proxy certificate from buffer Error while executing command "/bin/bash -c '{ :; } && { { mkdir -p /Users/eschnett/Cvanilla/.globus && : >> /Users/eschnett/Cvanilla/.globus/proxy-tfca-ncsa && chmod go-rwx /Users/eschnett/Cvanilla/.globus/proxy-tfca-ncsa && export X509_USER_PROXY=/Users/eschnett/Cvanilla/.globus/proxy-tfca-ncsa && : mkdir -p /Users/eschnett/Cvanilla/.globus/certificates-tfca-ncsa && : export X509_CERT_DIR=/Users/eschnett/Cvanilla/.globus/certificates-tfca- ncsa && { { grid-proxy-info -issuer -file /Users/eschnett/Cvanilla/.globus/proxy-tfca- ncsa 2>/dev/null | grep "^/C=US/O=National Center for Supercomputing Applications/" >/dev/null 2>&1 && test $(grid-proxy-info -timeleft -file /Users/eschnett/Cvanilla/.globus /proxy-tfca-ncsa 2>/dev/null) -gt 0 2>/dev/null } || { { grid-proxy-destroy 2>/dev/null || true; } && myproxy-logon -p 7512 -s tfca.ncsa.illinois.edu -T -l eschnett -o /Users/eschnett/Cvanilla/.globus/proxy-tfca-ncsa } } && { globus-update-certificate-dir >/dev/null 2>&1 || true; }; } && gsissh -o UserKnownHostsFile=/Users/eschnett/Cvanilla/simfactory/etc/ssh_known_hosts -t eschnett(a)h2ologin.ncsa.illinois.edu '\''cd /u/sciteam/eschnett/Cvanilla || echo "Could not change to directory /u/sciteam/eschnett/Cvanilla"; $SHELL -l'\''; }'": Command returned exit status 1 eschnett@Redshift:~/Cvanilla (16:40:03) $ ./bin/sim login bluewaters Enter MyProxy pass phrase: Failed to receive credentials. Failed writing buffer to BIO Failed unpacking proxy certificate from buffer Error accepting delegated credentials: Failed writing buffer to BIO Failed unpacking proxy certificate from buffer }}} -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1622> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 1

[Einstein Toolkit] #1964: Binary neutron star sample has poor OpenMP parallelization
by Einstein Toolkit 06 Oct '16

06 Oct '16

#1964: Binary neutron star sample has poor OpenMP parallelization -----------------------------------+---------------------------------------- Reporter: anonymous | Owner: Type: enhancement | Status: new Priority: unset | Milestone: Component: EinsteinToolkit thorn | Version: development version Keywords: NsNs | -----------------------------------+---------------------------------------- When running the sample from the ETK/gallery page the number of OpenMP threads seems to be limited to 2, showing only 200% in top, although 16 OMP threads were used. Other param files from /par go way beyond 1000%, showing that more threads are fully used. Could it be that there is a omp_set_num_threads(2) somewhere in the hydro code? http://einsteintoolkit.org/about/gallery/NsNsToHMNS/ Creating 1 MPI process per core fixes the issue, obviously, and the CPU is fully utilized -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1964> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 5

[Einstein Toolkit] #1968: Output time stamp in verbose build log
by Einstein Toolkit 04 Oct '16

04 Oct '16

#1968: Output time stamp in verbose build log -------------------------+-------------------------------------------------- Reporter: knarf | Owner: Type: enhancement | Status: new Priority: optional | Milestone: Component: Cactus | Version: development version Keywords: | -------------------------+-------------------------------------------------- Timestamp includes sub-second granularity when available, and uses Perl to do so in a more portable way than 'date' likely could. At the same time, don't let 'make' output the commands necessary to generate this debug output. This is not useful, except when debugging the debug output, which likely a user will never do. Pull-request at https://bitbucket.org/cactuscode/cactus/pull-requests/32 /output-time-stamp-in-verbose-build-log/diff -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1968> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 6

[Einstein Toolkit] #1962: OpenBlas fails to compile on modern laptop
by Einstein Toolkit 03 Oct '16

03 Oct '16

#1962: OpenBlas fails to compile on modern laptop -----------------------------------+---------------------------------------- Reporter: rhaas | Owner: Type: defect | Status: new Priority: blocker | Milestone: Component: EinsteinToolkit thorn | Version: development version Keywords: OpenBLAS | -----------------------------------+---------------------------------------- It seems as if the cpuid_x86.c in OpenBlas (0.2.13) does not recognize anything newer than Haswell CPUs so fails on my skylake laptop (i7-6500U). According to the changelong http://www.openblas.net/Changelog.txt we'd need at least Version 0.2.15 from Otctober 2015 to make this work. This is a blocker for affected systems since one cannot compile. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1962> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 8

[Einstein Toolkit] #1865: Automatically start SystemTopology
by Einstein Toolkit 03 Oct '16

03 Oct '16

#1865: Automatically start SystemTopology ---------------------------------+------------------------------------------ Reporter: dradice@… | Owner: eschnett Type: enhancement | Status: new Priority: major | Milestone: Component: Carpet | Version: development version Keywords: | ---------------------------------+------------------------------------------ Carpet used to load hwloc automatically and that would set thread affinities. Now this functionality is in the SystemTopology thorn, which is not automatically activated. This change could result in a significant performance regression on some systems (see discussion in #1850). Would it make sense to activate SystemTopology automatically? -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1865> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 14

[Einstein Toolkit] #1932: ML_BSSN: other_timelevels Parameter Not Respected
by Einstein Toolkit 03 Oct '16

03 Oct '16

#1932: ML_BSSN: other_timelevels Parameter Not Respected --------------------------------+------------------------------------------- Reporter: zachetie@… | Owner: Type: defect | Status: new Priority: major | Milestone: Component: Other | Version: development version Keywords: | --------------------------------+------------------------------------------- At the Jun 27, 2016 ET telecon, we found the following bug in McLachlan/ML_BSSN: Inside the ET_2016_05 ML_BSSN/schedule.ccl, you'll notice the following lines: STORAGE: ML_Ham[timelevels] STORAGE: ML_mom[timelevels] STORAGE: ML_cons_detg[timelevels] STORAGE: ML_cons_Gamma[timelevels] STORAGE: ML_cons_traceA[timelevels] in all of these lines, "timelevels" should be replaced by "other_timelevels". This should result in significantly increased memory usage in the latest ML_BSSN (possibly at the 10-20% level), particularly in vacuum evolutions. Related to this problem, I noticed that in a previous version of McLachlan (2015_05, where the above issue does not exist), all constraints are being stored in checkpoint files, despite having only one timelevel. ML_BSSN_Helper is supposed to overwrite the ML_BSSN/interface.ccl request to set the Checkpoint="no" tag. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1932> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 10

[Einstein Toolkit] #1965: use CCTK_BOOLEAN for useSpatialBetaDriver in ML_BSSN
by Einstein Toolkit 30 Sep '16

30 Sep '16

#1965: use CCTK_BOOLEAN for useSpatialBetaDriver in ML_BSSN -----------------------------------+---------------------------------------- Reporter: rhaas | Owner: Type: enhancement | Status: new Priority: minor | Milestone: Component: EinsteinToolkit thorn | Version: development version Keywords: ML_BSSN | -----------------------------------+---------------------------------------- This parameter used to be a string keyword accepting "yes" and "no" and was changed to a CCTK_INT in the ML rewrite. Making it a CCTK_BOOLEAN won't change it's C type (both CCTK_INT and CCTK_BOOLEAN are ints in C++) but will let users use the same parfile with both pre and post-rewrite code (or alternative the same code with pre and post-rewrite parfiles). If we really cared about the speed we *may* consider making it a CCTK_REAL so that {{{ifthen(v==1, a,b)}}} could be written as {{{ifthen(v, a,b)}}} thus saving on the comparison operation required and on a int->real conversion. This would require adding support for Boolean Parameters to Kranc's Param.m which does not seem difficult. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1965> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 1

[Einstein Toolkit] #1969: Carpet::processor_topology = "recursive" does not work with one process
by Einstein Toolkit 29 Sep '16

29 Sep '16

#1969: Carpet::processor_topology = "recursive" does not work with one process ---------------------+------------------------------------------------------ Reporter: sbrandt | Owner: Type: defect | Status: new Priority: minor | Milestone: Component: Other | Version: development version Keywords: | ---------------------+------------------------------------------------------ If you set Carpet::processor_topology = "recursive" and use one mpi process, you get the following error: {{{ terminate called after throwing an instance of 'std::out_of_range' what(): vector::_M_range_check: __n (which is 0) >= this->size() (which is 0) Rank 0 with PID 19719 received signal 6 Writing backtrace to ./backtrace.0.txt Aborted (core dumped) }}} -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1969> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 0

[Einstein Toolkit] #1966: provide strerror() type function in Cactus
by Einstein Toolkit 25 Sep '16

25 Sep '16

#1966: provide strerror() type function in Cactus -------------------------+-------------------------------------------------- Reporter: rhaas | Owner: Type: enhancement | Status: new Priority: optional | Milestone: Component: Cactus | Version: development version Keywords: | -------------------------+-------------------------------------------------- It would be useful to have a {{{sterror()}}} like function in Cactus that could turn the error codes returned by the various flesh functions into user readable strings. This requires mostly that we consolidate all error codes into a single file to make sure there are no duplicates. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1966> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 0

[Einstein Toolkit] #1873: Parameter file parser cannot handle empty files
by Einstein Toolkit 25 Sep '16

25 Sep '16

#1873: Parameter file parser cannot handle empty files ----------------------+----------------------------------------------------- Reporter: eschnett | Owner: Type: defect | Status: new Priority: minor | Milestone: Component: Cactus | Version: development version Keywords: | ----------------------+----------------------------------------------------- I used a parameter file that was empty except for comments: {{{ # ActiveThorns = "PUGH" # ActiveThorns = "MultiThreading" # ActiveThorns = "FunHPC" }}} Cactus complais about this: {{{ Activating thorn Cactus...Success -> active implementation Cactus WARNING level 0 from host process 0 while executing schedule bin (none), routine (no thorn)::(no routine) in thorn cactus, file multithreading.par:1: -> ERROR IN PARAMETER FILE:In rule 'file::skipper' Line=3, Column=84 # ActiveThorns = "PUGH" # ActiveThorns = "MultiThreading" # ActiveThorns = "FunHPC" }}} -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/1873> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 2

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

Trac September 2016