From c2230177d28b11418da7128b1a94e0b12f408076 Mon Sep 17 00:00:00 2001
From: Kerem Kayabay <kerem.kayabay@hlrs.de>
Date: Fri, 5 Jan 2024 13:44:48 +0100
Subject: [PATCH] changes regarding environment creation and deployment

---
 README.md                        |  9 ++---
 deployment_scripts/create-env.sh |  2 -
 deployment_scripts/deploy-env.sh | 68 +++++++++++++++++---------------
 3 files changed, 40 insertions(+), 39 deletions(-)

diff --git a/README.md b/README.md
index 1c569af..6bb972a 100644
--- a/README.md
+++ b/README.md
@@ -41,8 +41,7 @@ cd deployment_scripts
 3. Package the environment and transfer the archive to the target system:
 
 ```bash
-(my_env) $ conda deactivate
-(base) $ conda pack -n my_env -o my_env.tar.gz # conda-pack must be installed in the base environment
+(base) $ conda pack -n <your-env> -o ray_env.tar.gz # conda-pack must be installed in the base environment
 ```
 
 A workspace is suitable to store the compressed Conda environment archive on Hawk. Proceed to the next step if you have already configured your workspace. Use the following command to create a workspace on the high-performance filesystem, which will expire in 10 days. For more information, such as how to enable reminder emails, refer to the [workspace mechanism](https://kb.hlrs.de/platforms/index.php/Workspace_mechanism) guide.
@@ -55,8 +54,8 @@ ws_find hpda_project # find the path to workspace, which is the destination dire
 You can send your data to an existing workspace using: 
 
 ```bash
-scp my_env.tar.gz <username>@hawk.hww.hlrs.de:<workspace_directory>
-rm my_env.tar.gz # We don't need the archive locally anymore.
+scp ray_env.tar.gz <username>@hawk.hww.hlrs.de:<workspace_directory>
+rm ray_env.tar.gz # We don't need the archive locally anymore.
 ```
 
 4. Clone the repository on Hawk to use the deployment scripts and project structure:
@@ -79,7 +78,7 @@ qsub -I -l select=1:node_type=rome -l walltime=01:00:00
 2. Go into the directory with all code:
 
 ```bash
-cd <source_directory>/deployment_scripts
+cd <project_directory>/deployment_scripts
 ```
 
 3. Deploy the conda environment to the ram disk:
diff --git a/deployment_scripts/create-env.sh b/deployment_scripts/create-env.sh
index 5b586a8..1d87727 100755
--- a/deployment_scripts/create-env.sh
+++ b/deployment_scripts/create-env.sh
@@ -20,6 +20,4 @@ else
 
   # Create Conda environment
   CONDA_SUBDIR=linux-64 conda env create --name $CONDA_ENV_NAME -f environment.yaml
-
-  conda clean -y --all --force-pkgs-dirs
 fi
\ No newline at end of file
diff --git a/deployment_scripts/deploy-env.sh b/deployment_scripts/deploy-env.sh
index 913269b..0fc23e3 100755
--- a/deployment_scripts/deploy-env.sh
+++ b/deployment_scripts/deploy-env.sh
@@ -1,41 +1,45 @@
 #!/bin/bash
 
-# Check if a destination and environment name are provided
-if [ "$#" -ne 2 ]; then
-    echo "Usage: $0 <environment_name> <destination_directory>"
-    exit 1
+export WS_DIR=<workspace_dir>
+
+# Get the first character of the hostname
+first_char=$(hostname | cut -c1)
+
+# Check if the first character is not "r"
+if [[ $first_char != "r" ]]; then
+        # it's not a cpu node.
+    echo "Hostname does not start with 'r'."
+    # Get the first seven characters of the hostname
+    first_seven_chars=$(hostname | cut -c1,2,3,4,5,6,7)
+    # Check if it is an ai node
+    if [[ $first_seven_chars != "hawk-ai" ]]; then
+                echo "Hostname does not start with 'hawk-ai' too. Exiting."
+        return 1
+    else
+        echo "GPU node detected."
+        export OBJ_STR_MEMORY=350000000000
+        export TEMP_CHECKPOINT_DIR=/localscratch/$PBS_JOBID/model_checkpoints/
+        mkdir -p $TEMP_CHECKPOINT_DIR
+    fi
+else
+        echo "CPU node detected."
 fi
 
-# Name of the Conda environment
-CONDA_ENV_NAME="$1"
-TAR_FILE="$CONDA_ENV_NAME.tar.gz"
+module load bigdata/conda
 
-# Check if the tar.gz file already exists
-if [ -e "$TAR_FILE" ]; then
-    echo "Using existing $TAR_FILE"
-else
-    # Pack the Conda environment if the file doesn't exist
-    conda pack -n "$CONDA_ENV_NAME" -o "$TAR_FILE"
-fi
+export RAY_DEDUP_LOGS=0
 
-# Parse the destination host and directory
-DESTINATION=$2
-IFS=':' read -ra DEST <<< "$DESTINATION"
-DEST_HOST="${DEST[0]}"
-DEST_DIR="${DEST[1]}"
+export ENV_ARCHIVE=ray_env.tar.gz
+export CONDA_ENVS=/run/user/$PBS_JOBID/envs
+export ENV_NAME=ray_env
+export ENV_PATH=$CONDA_ENVS/$ENV_NAME
 
-# Copy the environment tarball to the remote server
-scp "$TAR_FILE" "$DEST_HOST":"$DEST_DIR"
-scp deploy-dask.sh "$DEST_HOST":"$DEST_DIR"
-scp dask-worker.sh "$DEST_HOST":"$DEST_DIR"
+mkdir -p $ENV_PATH
 
-echo "Conda environment '$CONDA_ENV_NAME' packed and deployed to '$DEST_HOST:$DEST_DIR' as '$TAR_FILE'."
+tar -xzf $WS_DIR/$ENV_ARCHIVE -C $ENV_PATH
 
-# Ask the user if they want to delete the tar.gz file
-read -p "Do you want to delete the local tar.gz file? (y/n): " answer
-if [ "$answer" == "y" ]; then
-    rm "$TAR_FILE"
-    echo "Local tar.gz file deleted."
-else
-    echo "Local tar.gz file not deleted."
-fi
\ No newline at end of file
+source $ENV_PATH/bin/activate
+
+export CONDA_ENVS_PATH=CONDA_ENVS
+
+conda_unpack
\ No newline at end of file