Trac November 2010

trac@lists.einsteintoolkit.org

1 participants
70 discussions

[Einstein Toolkit] #116: Submitting an existing simulation on Kraken does not introduce the required job dependency
by Einstein Toolkit 07 Jan '11

07 Jan '11

#116: Submitting an existing simulation on Kraken does not introduce the required job dependency ------------------------+--------------------------------------------------- Reporter: hinder | Owner: mthomas Type: defect | Status: new Priority: major | Milestone: Component: SimFactory | Version: Keywords: | ------------------------+--------------------------------------------------- When I submit a simulation several times: sim2 --remotemachine kraken submit parfiles/cptest.par 12 1:00:00 sim2 --remotemachine kraken submit parfiles/cptest.par sim2 --remotemachine kraken submit parfiles/cptest.par the queue state on Kraken is Q for all jobs. It should be Q for the first and H for the second and third if the job dependency has been correctly applied. [hinder@kraken-pwd4 simulations]$ qstat -u hinder nid00016: Kraken (UT/NICS Cray XT5) Req'd Req'd Elap Job ID Username Queue Jobname SessID NDS Tasks Memory Time S Time 866498.nid00016 hinder small cptest -- -- 12 -- 01:00 Q -- 866499.nid00016 hinder small cptest -- -- 12 -- 24:00 Q -- 866500.nid00016 hinder small cptest -- -- 12 -- 24:00 Q -- -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/116> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 1

[Einstein Toolkit] #115: Remote submission does not pass on required options
by Einstein Toolkit 07 Jan '11

07 Jan '11

#115: Remote submission does not pass on required options ------------------------+--------------------------------------------------- Reporter: hinder | Owner: mthomas Type: defect | Status: new Priority: major | Milestone: Component: SimFactory | Version: Keywords: | ------------------------+--------------------------------------------------- On my laptop, I execute a sim submit command with a --remotemachine argument and a --config argument. The --config argument does not get added to the remote command. MacBook:llama ian$ sim2 --remotemachine damiana submit --config sim2 parfiles/cptest.par 4 1:00:00 DEBUG: Simfactory command: simfactory2/sim "--remotemachine" "damiana" "submit" "--config" "sim2" "parfiles/cptest.par" "4" "1:00:00" DEBUG: Version r992 The Simulation Factory: manage and submit cactus jobs defs: /Users/ian/Cactus/llama/simfactory2/etc/defs.ini defs.local: /Users/ian/Cactus/llama/simfactory2/etc/defs.local.ini Managing for remote machine: damiana Executing: /bin/bash -c "{ :; } && { :; } && ssh -Y ianhin@login- damiana.aei.mpg.de \"/bin/bash -c '{ :; } && /home/ianhin/Cactus/llama/simfactory2/sim submit "parfiles/cptest.par" "4" "1:00:00" '\"" Warning: No xauth data; using fake authentication data for X11 forwarding. DEBUG: Simfactory command: /home/ianhin/Cactus/llama/simfactory2/sim "submit" "parfiles/cptest.par" "4" "1:00:00" DEBUG: Version r950 The Simulation Factory: manage and submit cactus jobs defs: /home/ianhin/Cactus/llama/simfactory2/etc/defs.ini defs.local: /home/ianhin/Cactus/llama/simfactory2/etc/defs.local.ini Cactus Directory: /home/ianhin/Cactus/llama Current Working directory does not match Cactus sourcetree, changing to /home/ianhin/Cactus/llama SimEnvironment.COMMAND: submit Executing command: submit Parfile: parfiles/cptest.par Simulation Name: cptest Procs: 4 Walltime: 1:00:00 Warning: simulation "cptest" does not exist or is not readable Parameter file: /home/ianhin/Cactus/llama/parfiles/cptest.par Configuration name not specified -- using default configuration "sim" Configuration name not specified -- using default configuration "sim" Warning: empty submit script for configuration sim Error: empty/missing run script for configuration sim Error 256 occured while executing command "/bin/bash -c "{ :; } && { :; } && ssh -Y ianhin(a)login-damiana.aei.mpg.de \"/bin/bash -c '{ :; } && /home/ianhin/Cactus/llama/simfactory2/sim submit "parfiles/cptest.par" "4" "1:00:00" '\""" -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/115> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 1

[Einstein Toolkit] #111: Submitting an existing simulation does not take the walltime from the previous restart
by Einstein Toolkit 07 Jan '11

07 Jan '11

#111: Submitting an existing simulation does not take the walltime from the previous restart ------------------------+--------------------------------------------------- Reporter: hinder | Owner: mthomas Type: defect | Status: new Priority: major | Milestone: Component: SimFactory | Version: Keywords: | ------------------------+--------------------------------------------------- I have submitted a simulation several times: sim2 --remotemachine kraken submit parfiles/cptest.par 12 1:00:00 sim2 --remotemachine kraken submit parfiles/cptest.par sim2 --remotemachine kraken submit parfiles/cptest.par expecting the second and third jobs to inherit the walltime of the first one. However, they appear in the qstat output on Kraken with 24 hours (the default walltime). [hinder@kraken-pwd4 simulations]$ qstat -u hinder nid00016: Kraken (UT/NICS Cray XT5) Req'd Req'd Elap Job ID Username Queue Jobname SessID NDS Tasks Memory Time S Time -------------------- -------- -------- ---------------- ------ ----- ----- ------ ----- - ----- 866498.nid00016 hinder small cptest -- -- 12 -- 01:00 Q -- 866499.nid00016 hinder small cptest -- -- 12 -- 24:00 Q -- 866500.nid00016 hinder small cptest -- -- 12 -- 24:00 Q -- -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/111> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 1

[Einstein Toolkit] #89: --remote execute doesn't cd into source directory
by Einstein Toolkit 07 Jan '11

07 Jan '11

#89: --remote execute doesn't cd into source directory ------------------------+--------------------------------------------------- Reporter: eschnett | Owner: mthomas Type: defect | Status: new Priority: major | Milestone: Component: SimFactory | Version: Keywords: | ------------------------+--------------------------------------------------- The command sim --remote numrel02 execute pwd doesn't cd into the source directory before executing pwd; instead, it executed "pwd" in the home directory. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/89> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 2

[Einstein Toolkit] #121: Should not be able to have two jobs in the queue for the same simulation at the same time
by Einstein Toolkit 07 Jan '11

07 Jan '11

#121: Should not be able to have two jobs in the queue for the same simulation at the same time ------------------------+--------------------------------------------------- Reporter: hinder | Owner: mthomas Type: defect | Status: new Priority: major | Milestone: Component: SimFactory | Version: Keywords: | ------------------------+--------------------------------------------------- When a simulation is submitted, and there is a job in the queuing system (either in the Q or the R state), it should not be possible to submit the simulation again to run a concurrent job. Currently, a new job is created in the Q state. My approach would be to perform a qstat (or equivalent) and determine if there is already a job in the queuing system from this simulation (by checking the known job ids of the simulation against the output from qstat). If there is no job in the queueing system, I would submit a new job. If there are jobs in the queuing system, I would submit a "chained" job to run when the last existing one is finished. This means that you don't need new syntax to indicate that you want to chain. If it is considered that this would be too confusing for new users, the decision of whether to chain or abort when there is an existing job could be made optional with a boolean option in the configuration file. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/121> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 2

[Einstein Toolkit] #118: EinsteinToolkit wiki should require a login for editing pages
by Einstein Toolkit 06 Jan '11

06 Jan '11

#118: EinsteinToolkit wiki should require a login for editing pages -------------------------------------+-------------------------------------- Reporter: hinder | Owner: Type: enhancement | Status: new Priority: major | Milestone: Component: EinsteinToolkit website | Version: Keywords: | -------------------------------------+-------------------------------------- The simfactory advanced tutorial at http://docs.einsteintoolkit.org/et- docs/Simulation_Factory_Advanced_Tutorial was recently defaced. Since this is now a problem in general for public-write-access services on the web, I propose that the Einstein Toolkit wiki should require an account for editing. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/118> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 2

[Einstein Toolkit] #72: GetComponents misplace ML_BSSN_Test repo
by Einstein Toolkit 28 Dec '10

28 Dec '10

#72: GetComponents misplace ML_BSSN_Test repo ---------------------+------------------------------------------------------ Reporter: bmundim | Owner: Type: defect | Status: new Priority: major | Milestone: Component: Other | Version: Keywords: | ---------------------+------------------------------------------------------ Hi, I just ran the following to get my thornlist updated: ./GetComponents --root ET_2010_11 -a -u einsteintoolkit.th and despite GetComponents returning successful: 0 components checked out successfully. 164 components updated successfully. it checked out ML_BSSN_Test again and misplaced it at the same level as the $ROOT directory: ls einsteintoolkit.th ET_2010_11 GetComponents ML_BSSN_Test Thanks, Bruno. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/72> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 5

[Einstein Toolkit] #109: Restart fails
by Einstein Toolkit 23 Dec '10

23 Dec '10

#109: Restart fails ------------------------+--------------------------------------------------- Reporter: anonymous | Owner: mthomas Type: defect | Status: new Priority: blocker | Milestone: Component: SimFactory | Version: Keywords: | ------------------------+--------------------------------------------------- A simulation restart with SimFactory failed with the following error message: DEBUG: checkpoint file: /work/eschnett/philip/simulations/d3.0-mclachlan-i0031/output-0000/d3.0-mclachlan/checkpoint.chkpt.it_0.h5 file=/work/eschnett/philip/simulations/d3.0-mclachlan-i0031/output-0000/d3.0-mclachlan/checkpoint.chkpt.it_0.h5 dfile=/work/eschnett/philip/simulations/d3.0-mclachlan-i0031/output-0001/d3.0-mclachlan/checkpoint.chkpt.it_0.h5 DEBUG: linking /work/eschnett/philip/simulations/d3.0-mclachlan-i0031/output-0000/d3.0-mclachlan/checkpoint.chkpt.it_0.h5 to /work/eschnett/philip/simulations/d3.0-mclachlan-i0031/output-0001/d3.0-mclachlan/checkpoint.chkpt.it_0.h5 before link Error: Could not link checkpoint file /work/eschnett/philip/simulations/d3.0-mclachlan-i0031/output-0000/d3.0-mclachlan/checkpoint.chkpt.it_0.h5 to /work/eschnett/philip/simulations/d3.0-mclachlan-i0031/output-0001/d3.0-mclachlan/checkpoint.chkpt.it_0.h5 -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/109> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 3

[Einstein Toolkit] #94: Add CCTK_VECTGFINDEX3D and friends...
by Einstein Toolkit 22 Dec '10

22 Dec '10

#94: Add CCTK_VECTGFINDEX3D and friends... -------------------------+-------------------------------------------------- Reporter: eschnett | Owner: Type: enhancement | Status: new Priority: major | Milestone: Component: Cactus | Version: Keywords: | -------------------------+-------------------------------------------------- ... but wait until after the release. See <http://cactuscode.org/pipermail/patches/attachments/20091204/57952527> for the patch and the surrounding discussion. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/94> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 5

[Einstein Toolkit] #79: Running on Damiana fails
by Einstein Toolkit 21 Dec '10

21 Dec '10

#79: Running on Damiana fails --------------------------------------+------------------------------------- Reporter: barry.wardell@… | Owner: mthomas Type: defect | Status: new Priority: blocker | Milestone: Component: SimFactory | Version: Keywords: | --------------------------------------+------------------------------------- The compute nodes on Damiana are named nodeXXX, which does not match the aliaspattern for Damiana in the mdb. The quick fix is to change the aliaspattern to: aliaspattern = ^(((login-)?damiana)|(sl-\d\d)|node\d\d\d)(\.aei\.mpg\.de|\.damiana\.admin)?$ although this might interfere with other machines which also have their compute nodes named nodeXXX. A better fix would probably be to add a --machine=... option when running so that SimFactory does not need to guess which machine it's on from the aliaspattern. I believe a similar problem also affects Kraken. -- Ticket URL: <https://trac.einsteintoolkit.org/ticket/79> Einstein Toolkit <http://einsteintoolkit.org> The Einstein Toolkit

1 4

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

Trac November 2010