From 5a8bf279367abf6e45cc4f9ad54af5a464d60cd1 Mon Sep 17 00:00:00 2001
From: Kerem Kayabay <kerem.kayabay@hlrs.de>
Date: Fri, 5 Jan 2024 16:25:02 +0100
Subject: [PATCH] multiple node test successful

---
 README.md                             | 10 +++++++---
 deployment_scripts/submit-ray-job.pbs |  2 +-
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/README.md b/README.md
index fd58623..59386fa 100644
--- a/README.md
+++ b/README.md
@@ -131,14 +131,16 @@ Then, launch Firefox web browser using the configured profile. Open `localhost:8
 
 ## Launch a Ray Cluster in Batch Mode
 
-1. Add execution permissions to `start-ray-worker.sh`
+Let us [estimate the value of π](https://docs.ray.io/en/releases-2.8.0/ray-core/examples/monte_carlo_pi.html) as an example application. 
+
+**Step 1.** Add execution permissions to `start-ray-worker.sh`
 
 ```bash
 cd deployment_scripts
 chmod +x start-ray-worker.sh
 ```
 
-2. Submit a job to launch the head and worker nodes.
+**Step 2.** Submit a job to launch the head and worker nodes.
 
 You must modify the following lines in `submit-ray-job.sh`:
 - Line 3 changes the cluster size. The default configuration launches a 3 node cluster.
@@ -155,4 +157,6 @@ qstat -anw # Q: Queued, R: Running, E: Ending
 ls -l # list files after the job finishes
 cat ray-job.o... # inspect the output file
 cat ray-job.e... # inspect the error file
-```
\ No newline at end of file
+```
+
+If you need to delete the job, use `qdel <job-id>`. If this doesn't work, use the `-W force` option: `qdel -W force <job-id>`
\ No newline at end of file
diff --git a/deployment_scripts/submit-ray-job.pbs b/deployment_scripts/submit-ray-job.pbs
index e0b6caa..0083d64 100644
--- a/deployment_scripts/submit-ray-job.pbs
+++ b/deployment_scripts/submit-ray-job.pbs
@@ -40,7 +40,7 @@ ray start --disable-usage-stats \
 export NUM_NODES=$(sort $PBS_NODEFILE |uniq | wc -l)
 
 for ((i=1;i<$NUM_NODES;i++)); do
-        pbsdsh -n $i -- bash -l -c "'$DEPLOYMENT_SCRIPTS/ray-start-worker.sh' '$WS_DIR' '$ENV_ARCHIVE' '$RAY_ADDRESS' '$REDIS_PASSWORD' '$OBJECT_STORE_MEMORY'" &
+        pbsdsh -n $i -- bash -l -c "'$DEPLOYMENT_SCRIPTS/start-ray-worker.sh' '$WS_DIR' '$ENV_ARCHIVE' '$RAY_ADDRESS' '$REDIS_PASSWORD' '$OBJECT_STORE_MEMORY'" &
 done
 
 python3 $PYTHON_FILE