Changes between Initial Version and Version 1 of gscc

Timestamp:

12/09/20 13:54:46 (4 years ago)

Author:

downs

Comment:

--

gscc

@@ +1 @@
+== Getting an account ==
+
+First, you need to send an email to the system administrators of Greenplanet (email: hpcops [at] ps.uci.edu) and request an account (desired username or ucinetid, and email address). More info here: https://ps.uci.edu/greenplanet/
+
+== ssh configuration ==
+
+You can add the following lines to `~/.ssh/config` on your local machine:
+{{{
+#!sh
+Host gp greenplanet gplogin1.ps.uci.edu gplogin2.ps.uci.edu
+  HostName gplogin1.ps.uci.edu
+  User YOURGREENPLANETUSERNAME
+  HostKeyAlias gplogin1.ps.uci.edu
+  HostbasedAuthentication no
+}}}
+and replace `YOURGREENPLANETUSERNAME` by your greenplanet username.
+
+Once this is done, you can ssh green planet by simply doing:
+
+{{{
+#!sh
+ssh gp
+}}}
+
+Obs.: `gplogin2.ps.uci.edu` is preferred over `gplogin1.ps.uci.edu` (gplogin2 is faster, has 48 cores and new nodes, and allows to access the DFS-B disk which has a faster i/o). See the partitions here (ideally submit jobs on 'ilg2.3'): https://ps.uci.edu/greenplanet/Partitions-new-names.
+
+== Password-less ssh ==
+
+Once you have the account, you can setup a public key authentification in order to avoid having to input your password for each run. 
+You need to have a SSH public/private key pair. If you already have one, you can skip their creation described below. If you do not, you can create a SSH public/private key pair by typing the following command and following the prompts (no passphrase necessary):
+{{{
+#!sh
+$your_localhost% ssh-keygen -t rsa
+Generating public/private rsa key pair.
+Enter file in which to save the key (/Users/username/.ssh/id_rsa):RETURN
+Enter passphrase (empty for no passphrase):RETURN
+Enter same passphrase again:RETURN
+Your identification has been saved in /Users/username/.ssh/id_rsa.
+Your public key has been saved in /Users/username/.ssh/id_rsa.pub.
+}}}
+
+Two files were created: your private key `/Users/username/.ssh/id_rsa`, and the public key `/Users/username/.ssh/id_rsa.pub`. The private key is read-only and only for you, it is used to decrypt all correspondence encrypted with the public key. The contents of the public key need to be copied to `~/.ssh/authorized_keys` on your greenplanet account:
+
+{{{
+#!sh
+$your_localhost%scp ~/.ssh/id_rsa.pub username@your_remotehost:~
+}}}
+
+Now on '''Greenplanet''', copy the content of id_rsa.pub:
+
+{{{
+#!sh
+$your_remotehost%cat ~/id_rsa.pub >> ~/.ssh/authorized_keys
+$your_remotehost%rm ~/id_rsa.pub
+}}}
+
+== Environment ==
+
+On '''Greenplanet''', add the following lines to `~/.bashrc`:
+{{{
+#!sh
+export ISSM_DIR=PATHTOTRUNK
+source $ISSM_DIR/etc/environment.sh
+ml intel/2018.3 openmpi/3.1.2-slim
+}}}
+
+''Log out and log back in'' to apply this change.
+
+== Installing ISSM on Greenplanet ==
+
+Greenplanet will ''only'' be used to run the code, you will use your local machine for pre and post processing, you will never use Greenplanet's Matlab. You can check out ISSM and install the following packages:
+ - autotools (the one provided by default is too old)
+ - PETSc 3.14
+ - m1qn3
+
+Use the following configuration script (adapt to your needs):
+
+{{{
+#!sh
+./configure \
+ --prefix=$ISSM_DIR \
+ --with-wrappers=no \
+ --with-kriging=no \
+ --with-kml=no \
+ --with-bamg=no \
+ --without-Love \
+ --with-metis-dir="$ISSM_DIR/externalpackages/petsc/install" \
+ --with-petsc-dir="$ISSM_DIR/externalpackages/petsc/install" \
+ --with-m1qn3-dir="$ISSM_DIR/externalpackages/m1qn3/install" \
+ --with-mpi-include="/sopt/OpenMPI/3.1.2/intel-2018.3-slim/include" \
+ --with-mpi-libflags="-L/sopt/OpenMPI/3.1.2/intel-2018.3-slim/lib -lmpi -lm -lmpi_mpifh" \
+ --with-mkl-libflags="-L/sopt/MKL/2018.3/lib -mkl=cluster" \
+ --with-mumps-dir=$ISSM_DIR/externalpackages/petsc/install/ \
+ --with-scalapack-dir=$ISSM_DIR/externalpackages/petsc/install/ \
+ --with-cxxoptflags="-O3 -fPIC -std=c++11" \
+ --with-vendor=intel-gp
+}}}
+== greenplanet_settings.m ==
+
+You have to add a file in `$ISSM_DIR/src/m` entitled `greenplanet_settings.m` with your personal settings:
+
+{{{
+#!m
+cluster.login='morlighem';
+cluster.queue='ilg2.3';
+cluster.port='';
+cluster.codepath='/DFS-B/DATA/morlighem/trunk-jpl/bin/';
+cluster.executionpath='/DFS-B/DATA/morlighem/trunk-jpl/execution/';
+}}}
+
+Use your username for the `login` and enter your `codepath` and `executionpath`. These settings will be picked up automatically by Matlab when you do `md.cluster=greenplanet()`
+
+== Running jobs on Greenplanet ==
+
+On Greenplanet, you can use up to 30 cores per node (partition `ilg2.3`). The more nodes and the longer the requested time, the more you will have to wait in the queue. Per job you can only request up to 125GB of RAM. So choose your settings wisely:
+
+ {{{
+#!m
+md.cluster=greenplanet('numnodes',1,'cpuspernode',8);
+md.cluster.time=10;
+}}}
+
+to have a maximum job time of 10 minutes and 8 cores on one node. If the run lasts longer than 10 minutes, it will be killed and you will not be able to retrieve your results.
+
+Now if you want to check the status of your job and the queue you are using, type in the bash on '''Greenplanet''' session:
+
+ {{{
+#!sh
+squeue -u username
+}}}
+
+You can delete your job manually by typing:
+
+{{{
+#!sh
+scancel JOBID
+}}}
+
+where `JOBID` is the ID of your job (indicated in the Matlab session). Matlab indicates too the directory of your job where you can find the files `JOBNAME.outlog` and `JOBNAME.errlog`. The outlog file contains the information that would appear if you were running your job on your local machine and the errlog file contains the error information in case the job encounters an error. 
+
+If you want to load results from the cluster manually (for example if you have an error due to an internet interruption), you find in the information Matlab gave you `$ISSM_DIR/execution/LAUNCHSTRING/JOBNAME.lock`, you copy the LAUNCHSTRING and you type in Matlab:
+
+{{{
+#!m
+md=loadresultsfromcluster(md,'LAUNCHSTRING','JOBNAME');
+}}}
+
+Obs.: in the case where `md.settings.waitonlock`>0 and you need to load manually (e.g., internet interruption), it is necessary to set `md.private.runtimename=LAUNCHSTRING;` before calling `loadresultsfromcluster`.
+
+== slurm ==
+
+A comparison of PBS to slurm commands can be found here: http://slurm.schedmd.com/rosetta.pdf 
+
+Useful commands:
+
+Graphical overview over greenplanet usage:
+{{{
+sview
+}}}
+
+Get number of idle nodes:
+{{{
+sinfo --states=idle
+}}}
+
+See jobs of <username>:
+{{{
+squeue -u <username>
+}}}
+
+Get more information on jobs of user:
+{{{
+sacct -u <username> --format=User,JobID,account,Timelimit,elapsed,ReqMem,MaxRss,ExitCode
+}}}
+
+Get information on partition (here ilg2.3):
+{{{
+scontrol show partition=ilg2.3
+}}}
+
+Get sorted list of users on partition:
+{{{
+squeue  | grep -i ilg2.3 | awk '{print $4}' | sort | uniq -c | sort -rn
+}}}