From 733a9651e90be66b1165a17fcd90365b87f973a0 Mon Sep 17 00:00:00 2001
From: sfux <samuel.fux@id.ethz.ch>
Date: Thu, 10 Nov 2022 07:24:11 +0000
Subject: [PATCH] Update start_vscode.sh
---
start_vscode.sh | 74 +++++++++++++++++++++++--------------------------
1 file changed, 35 insertions(+), 39 deletions(-)
diff --git a/start_vscode.sh b/start_vscode.sh
index be32a1c..9e609f2 100755
--- a/start_vscode.sh
+++ b/start_vscode.sh
@@ -6,12 +6,13 @@
# connect it with a local browser to it #
# #
# Main author : Samuel Fux #
-# Contributions : Andreas Lugmayr, Mike Boss #
+# Contributions : Andreas Lugmayr, Mike Boss, Nadia Marounina #
# Date : October 2021 #
# Location : ETH Zurich #
-# Version : 0.1 #
+# Version : 0.2 #
# Change history : #
# #
+# 24.10.2022 Added Slurm support #
# 19.05.2022 JOBID is now saved to reconnect_info file #
# 28.10.2021 Initial version of the script based on Jupyter script #
# #
@@ -22,7 +23,7 @@
###############################################################################
# Version
-VSC_VERSION="0.1"
+VSC_VERSION="0.2"
# Script directory
VSC_SCRIPTDIR=$(pwd)
@@ -59,6 +60,9 @@ VSC_WAITING_INTERVAL=60
# SSH key location default : no default
VSC_SSH_KEY_PATH=""
+# Batch system : Slurm
+VSC_BATCH_SYSTEM="SLURM"
+
###############################################################################
# Usage instructions #
###############################################################################
@@ -75,7 +79,7 @@ Options:
-n | --numcores NUM_CPU Number of CPU cores to be used on the cluster
-W | --runtime RUN_TIME Run time limit for the code-server in hours and minutes HH:MM
-m | --memory MEM_PER_CORE Memory limit in MB per core
- -b | --batchsys BATCH_SYS Batch system to use for the submission of this job to Euler (LSF/SLURM)
+ -b | --batchsys BATCH_SYS Batch system to use (LSF or SLURM)
Optional arguments:
@@ -84,15 +88,14 @@ Optional arguments:
-h | --help Display help for this script and quit
-i | --interval INTERVAL Time interval for checking if the job on the cluster already started
-k | --key SSH_KEY_PATH Path to SSH key with non-standard name
- -s | --shareholdergr SHAREHOLDERGR Shareholder group, mandatory when requesting GPUs with SLURM batch system
-v | --version Display version of the script and exit
Examples:
- ./start_vscode.sh -u sfux -n 4 -W 04:00 -m 2048
+ ./start_vscode.sh -u sfux -b SLURM -n 4 -W 04:00 -m 2048
- ./start_vscode.sh --username sfux --numcores 2 --runtime 01:30 --memory 2048
+ ./start_vscode.sh --username sfux --batchsys SLURM --numcores 2 --runtime 01:30 --memory 2048
./start_vscode.sh -c $HOME/.vsc_config
@@ -105,6 +108,7 @@ VSC_RUN_TIME="01:00" # Run time limit for the code-server in hours and mi
VSC_MEM_PER_CPU_CORE=1024 # Memory limit in MB per core
VSC_WAITING_INTERVAL=60 # Time interval to check if the job on the cluster already started
VSC_SSH_KEY_PATH="" # Path to SSH key with non-standard name
+VSC_BATCH_SYSTEM="SLURM" # Batch system to use (SLURM or LSF)
EOF
exit 1
@@ -169,11 +173,6 @@ do
shift
shift
;;
- -s|--shareholdergr)
- SHAREHOLDERGR=$2
- shift
- shift
- ;;
*)
echo -e "Warning: ignoring unknown option $1 \n"
shift
@@ -281,17 +280,19 @@ else
echo -e "Using SSH key $VSC_SSH_KEY_PATH"
fi
-#check in the case where GPUs are requested with SLURM whether the shareholder group is provided
-if [[ "$VSC_NUM_GPU" > "0" && $BATCH_SYS = "SLURM" && $SHAREHOLDERGR = "" ]]; then
- echo -e "Please provide the shareholder group if requesting GPUs with SLURM"
- display_help
-fi
-
-#if batch system has not been provided, default to LSF:
-if [ -z "$BATCH_SYS" ]; then
- BATCH_SYS="LSF"
-fi
+# check if VSC_BATCH_SYSTEM is set to SLURM or LSF
+case $VSC_BATCH_SYSTEM in
+ LSF)
+ echo -e "Using LSF batch system"
+ ;;
+ SLURM)
+ echo -e "Using Slurm batch system"
+ ;;
+ *)
+ echo -e "Error: Unknown batch system $VSC_BATCH_SYSTEM. Please either specify LSF or SLURM as batch system"
+ ;;
+esac
# put together string for SSH options
VSC_SSH_OPT="$VSC_SKPATH $VSC_USERNAME@$VSC_HOSTNAME"
@@ -324,7 +325,7 @@ ENDSSH
# run the code-server job on Euler and save the ip of the compute node in the file vscip in the home directory of the user on Euler
echo -e "Connecting to $VSC_HOSTNAME to start the code-server in a $BATCH_SYS batch job"
case $BATCH_SYS in
- "LSF" )
+ "LSF")
VSC_BJOB_OUT=$(ssh $VSC_SSH_OPT bsub -n $VSC_NUM_CPU -W $VSC_RUN_TIME -R "rusage[mem=$VSC_MEM_PER_CPU_CORE]" $VSC_SNUM_GPU<<ENDBSUB
module load $VSC_MODULE_COMMAND
export XDG_RUNTIME_DIR="\$HOME/vsc_runtime"
@@ -332,16 +333,14 @@ case $BATCH_SYS in
echo "Remote IP:\$VSC_IP_REMOTE" >> /cluster/home/$VSC_USERNAME/vscip
code-server --bind-addr=\${VSC_IP_REMOTE}:8899
ENDBSUB
- )
- ;;
-
- "SLURM" )
+) ;;
+ "SLURM")
VSC_RUN_TIME="${VSC_RUN_TIME}":00" "
if [ "$VSC_NUM_GPU" -gt "0" ]; then
- VSC_SNUM_GPU="-G $VSC_NUM_GPU -A $SHAREHOLDERGR"
+ VSC_SNUM_GPU="-G $VSC_NUM_GPU"
fi
@@ -355,18 +354,12 @@ code-server --bind-addr=\${VSC_IP_REMOTE}:8899
ENDBSUB
)
;;
- *)
- echo
- echo "Please specify either LSF or SLURM as your choice of the batch system"
- echo
- display_help
- ;;
-esac
-
-
+esac
-VSC_BJOB_ID=$(echo $VSC_BJOB_OUT | awk '/is submitted/{print substr($2, 2, length($2)-2);}')
+# TODO: get jobid for both cases (LSF/Slurm)
+# store jobid in a variable
+# VSC_BJOB_ID=$(echo $VSC_BJOB_OUT | awk '/is submitted/{print substr($2, 2, length($2)-2);}')
# wait until batch job has started, poll every $VSC_WAITING_INTERVAL seconds to check if /cluster/home/$VSC_USERNAME/vscip exists
# once the file exists and is not empty the batch job has started
@@ -409,6 +402,10 @@ VSC_LOCAL_PORT=$((3 * 2**14 + RANDOM % 2**14))
echo -e "Using local port: $VSC_LOCAL_PORT"
# write reconnect_info file
+#
+# FIXME: add jobid
+# BJOB ID : $VSC_BJOB_ID
+
cat <<EOF > $VSC_SCRIPTDIR/reconnect_info
Restart file
Remote IP address : $VSC_REMOTE_IP
@@ -416,7 +413,6 @@ Remote port : $VSC_REMOTE_PORT
Local port : $VSC_LOCAL_PORT
SSH tunnel : ssh $VSC_SSH_OPT -L $VSC_LOCAL_PORT:$VSC_REMOTE_IP:$VSC_REMOTE_PORT -N &
URL : http://localhost:$VSC_LOCAL_PORT
-BJOB ID : $VSC_BJOB_ID
EOF
# setup SSH tunnel from local computer to compute node via login node
--
GitLab