upgrade 1.1

Author: falconlee236

README.md

@@ -58,6 +58,7 @@ If you are running this script, you will get this cloud resource just after 10 m
 - GCP CLI configured
 - Github SSH key
 - Dockerhub configured
+- Bash >= 4.2
 ```
 
 ## 📂 Repository Structure
@@ -77,6 +78,7 @@ If you are running this script, you will get this cloud resource just after 10 m
     ├── main.tf
     ├── provider.tf
     ├── storage.tf
+    ├── output.tf
     ├── modules
     │   ├── vpc
     │   │   ├── main.tf

create_server_with_dynamic_zones.sh

@@ -22,6 +22,9 @@ done
 for zone in "${zones[@]}"; do
   # 존(zone)에서 맨 뒤 두 글자를 제거하여 지역(region) 생성
   region=${zone::-2}
+  if [[ -z "$zone" || "$zone" == "ZONE" ]]; then
+    continue
+  fi
 
   echo "존(zone): $zone, 지역(region): $region 에서 make 명령어를 실행합니다..."
 
@@ -34,8 +37,8 @@ for zone in "${zones[@]}"; do
 
   # make 명령어의 종료 상태 확인
   if [ $? -ne 0 ]; then
-    echo "존 $zone 에서 make 명령어가 실패했습니다. 10초 후에 make clean을 실행합니다..."
-    sleep 30
+    echo "존 $zone 에서 make 명령어가 실패했습니다. 100초 후에 make clean을 실행합니다..."
+    sleep 100
     make clean
   else
     echo "존 $zone 에서 make 명령어가 성공적으로 완료되었습니다."

docs/SCRIPT_INFO.md

@@ -46,6 +46,7 @@ This script streamlines the process of deploying GCP Compute Engine instances eq
     ├── main.tf                          # Terraform main config
     ├── provider.tf                      # Terraform provider config
     ├── storage.tf                       # Google cloud storage config
+    ├── output.tf                       # Google cloud storage config output
     ├── modules                          # Terraform modules
     │   ├── vpc
     │   │   ├── main.tf

docs/USAGE.md

@@ -8,8 +8,6 @@
 | ssh_file | SSH public key path | string | "../.ssh/id_ed25519.pub" | yes |
 | ssh_file_private | SSH private key path | string | "../.ssh/id_ed25519" | yes |
 | env_file | Environment file path | string | "../.env" | yes |
-| git_ssh_url | Git clone URL | string | "https://github.com/OptiMaps/TrainRepo" | yes |
-| git_clone_dir | Directory path for cloned repository | string | "TrainRepo" | yes |
 | credentials_file | GCP credentials file path | string | "../credentials.json" | yes |
 | project | GCP project name | string | "optimap-438115" | yes |
 | region | GCP region name | string | "asia-east1" | yes |
@@ -96,6 +94,11 @@ ACTIVE  ACCOUNT
 > [!IMPORTANT]
 > your credentials.json must be root directory and must follow that name.
 
+set project to glcoud cli
+```bash
+glcoud config set project ${project-name}
+```
+
 #### 3. set .ssh file
 In previous setting section, move root directory to create pub key and private key wrapping .ssh directory in chapter 4
 ```bash
@@ -224,6 +227,11 @@ Open ./variables.tf, change default value (project, username) to your own enviro
 > [!CAUTION]
 > project name must specify numbers after project name dash (-)
 
+set project to glcoud cli
+```bash
+glcoud config set project ${project-name}
+```
+
 #### 4. create terraform.prod.tfvars 
 create `terraform.prod.tfvars` in root directory and contents is following
 ```hcl

src/.terraform.lock.hcl

@@ -29,8 +29,6 @@ module "training_worker" {
 
     ssh_file = var.ssh_file
     ssh_file_private = var.ssh_file_private
-    git_ssh_url = var.git_ssh_url
-    git_clone_dir = var.git_clone_dir
     machine_type = var.machine_type
     gpu_type = var.gpu_type
     gpu_count = var.gpu_count
@@ -40,5 +38,8 @@ module "training_worker" {
     dockerhub_id = var.dockerhub_id
     dockerhub_pwd = var.dockerhub_pwd
 
+    # output 처리
+    artifact_bucket = google_storage_bucket.artifact_bucket.name
+
     depends_on = [ module.vpc_network, google_storage_bucket.artifact_bucket ]
 }

src/main.tf

@@ -85,14 +85,12 @@ resource "google_compute_instance" "gpu_instance" {
             "sudo apt update && sudo apt upgrade -y",
             "mkdir /home/${var.username}/gcs-bucket", // create mount path for our bucket
             "sudo chown ${var.username}: /home/${var.username}/gcs-bucket",
-            "sudo gcsfuse -o allow_other -file-mode=777 -dir-mode=777 rl-artifact-bucket /home/${var.username}/gcs-bucket", // mount our bucket
+            "sudo gcsfuse -o allow_other -file-mode=777 -dir-mode=777 ${var.artifact_bucket} /home/${var.username}/gcs-bucket", // mount our bucket
             "sudo /opt/deeplearning/install-driver.sh", // install required GPU drivers
             "sudo apt install -y git",
             "chmod 400 /home/${var.username}/.ssh/id_ed25519", // allow git to use our ssh key
             "echo 'Host github.com' >> ~/.ssh/config",
             "echo '    StrictHostKeyChecking no' >> ~/.ssh/config",
-            "git clone ${var.git_ssh_url}", // clone our application repository
-            "cd ~/${var.git_clone_dir}",
             "sudo apt remove docker docker-engine docker.io containerd runc", ## - Old Version Remove
             "sudo apt update && sudo apt upgrade -y", # set up
             "sudo apt install -y apt-transport-https ca-certificates curl software-properties-common",
@@ -103,8 +101,6 @@ resource "google_compute_instance" "gpu_instance" {
             "sudo systemctl start docker",
             "sudo systemctl enable docker",
             "echo ${var.dockerhub_pwd} | docker login -u ${var.dockerhub_id} --password-stdin", # dockerhub login
-            "docker pull falconlee236/rl-image:parco-cuda123", # pull train docker image,
-            "git clone https://github.com/OptiMaps/TrainRepo", # 새로 추가한 부분, 문제 있으면 이거 지우기
          ]
          connection {
             type = "ssh"

src/modules/worker/main.tf

@@ -2,10 +2,6 @@ variable "ssh_file" {}
 
 variable "ssh_file_private" {}
 
-variable "git_ssh_url" {}
-
-variable "git_clone_dir" {}
-
 variable "machine_type" {}
 
 variable "gpu_type" {}
@@ -20,4 +16,6 @@ variable "env_file" {}
 
 variable "dockerhub_id" {}
 
-variable "dockerhub_pwd" {}
+variable "dockerhub_pwd" {}
+
+variable "artifact_bucket" {}

src/modules/worker/variables.tf

@@ -0,0 +1,4 @@
+# 무작위 ID 출력
+output "bucket_name" {
+    value = google_storage_bucket.artifact_bucket.name
+}

src/output.tf

@@ -1,6 +1,11 @@
+# 무작위 ID 생성
+resource "random_id" "bucket_suffix" {
+    byte_length = 4
+}
+
 resource "google_storage_bucket" "artifact_bucket" {
     # bucket name must be globally unique with all users
-    name = "rl-artifact-bucket"
+    name = "rl-artifact-bucket-${random_id.bucket_suffix.hex}"
     location = var.region
 
     force_destroy = true

src/storage.tf

@@ -16,18 +16,6 @@ variable "env_file" {
     default = "../.env"
 }
 
-variable "git_ssh_url" {
-    description = "git clone url"
-    type = string
-    default = "https://github.com/OptiMaps/TrainRepo"
-}
-
-variable "git_clone_dir" {
-    description = "directory path"
-    type = string
-    default = "TrainRepo"
-}
-
 variable "credentials_file" {
     description = "credentials file"
     type = string