Adding kh-gke-ml-dev cluster to the dev environment.

ml-platform/02_gke/backend.tf

@@ -15,6 +15,6 @@
 terraform {
   backend "gcs" {
     prefix = "02_gke"
-    bucket = "YOUR_STATE_BUCKET"
+    bucket = "kh-gkebatchexpce3c8dcb-tf-state"
   }
 }

ml-platform/02_gke/variables.tf

@@ -15,13 +15,13 @@
 variable "project_id" {
   type        = map
   description = "The GCP project where the resources will be created. It is a map with environments a skeys and project_ids s values"
-  default     = {}
+  #default     = {}
   #Below is an example of not null project_id variable
-  #default    = { "dev" : "project_id1", "staging" : "project_id2", "prod" : "project_id3" }
+  default    = { "dev" : "gkebatchexpce3c8dcb", "staging" : "gkebatchexpce3c8dcb", "prod" : "gkebatchexpce3c8dcb" }
 }
 
 variable "network_name" {
-  default = "ml-vpc"
+  default = "kh-ml-vpc"
   description = "VPC network where GKE cluster will be created"
   type = string
 }
@@ -31,7 +31,7 @@ variable "routing_mode" {
   type = string
 }
 variable "subnet_01_name" {
-  default = "ml-vpc-subnet-01"
+  default = "kh-ml-vpc-subnet-01"
   description = "Name of the first subnet in the VPC network."
   type = string
 }
@@ -51,7 +51,7 @@ variable "subnet_01_description" {
   type = string
 }
 variable "subnet_02_name" {
-  default = "gke-vpc-subnet-02"
+  default = "kh-gke-vpc-subnet-02"
   description = "Name of the second subnet in the VPC network."
   type = string
 }
@@ -74,12 +74,12 @@ variable "subnet_02_description" {
 variable "lookup_state_bucket" {
   description = "GCS bucket to look up TF state from previous steps."
   type = string
-  default = "YOUR_STATE_BUCKET"
+  default = "kh-gkebatchexpce3c8dcb-tf-state"
 }
 
 variable "cluster_name" {
   description = "Name of the GKE cluster"
-  default = "gke-ml"
+  default = "kh-gke-ml"
   type = string
 }
 variable "reserved_taints" {

ml-platform/03_configsync/backend.tf

@@ -15,6 +15,6 @@
 terraform {
   backend "gcs" {
     prefix = "03_config_sync_prerequisite"
-    bucket = "YOUR_STATE_BUCKET"
+    bucket = "kh-gkebatchexpce3c8dcb-tf-state"
   }
 }

ml-platform/03_configsync/log

@@ -0,0 +1,82 @@
+Download repo is config-sync-repo-486e34dfe60c60c14a9c
+ls -lrt before going into download repo is total 48
+drwxr-xr-x 3 kenthua primarygroup  4096 Mar  4 19:00 templates
+-rw-r--r-- 1 kenthua primarygroup 11509 Mar  4 19:00 README.md
+-rw-r--r-- 1 kenthua primarygroup  1036 Mar  4 19:00 providers.tf
+-rw-r--r-- 1 kenthua primarygroup   692 Mar  4 19:00 outputs.tf
+-rw-r--r-- 1 kenthua primarygroup  4183 Mar  4 19:00 main.tf
+-rwxr-xr-x 1 kenthua primarygroup  3150 Mar  4 19:00 create_cluster_yamls.sh
+-rw-r--r-- 1 kenthua primarygroup   702 Mar  4 22:54 backend.tf
+-rw-r--r-- 1 kenthua primarygroup  1397 Mar  4 22:54 variables.tf
+-rw-r--r-- 1 kenthua primarygroup    55 Mar  4 23:09 log
+ls -lrt in download repo is total 48
+drwxr-xr-x 3 kenthua primarygroup  4096 Mar  4 19:00 templates
+-rw-r--r-- 1 kenthua primarygroup 11509 Mar  4 19:00 README.md
+-rw-r--r-- 1 kenthua primarygroup  1036 Mar  4 19:00 providers.tf
+-rw-r--r-- 1 kenthua primarygroup   692 Mar  4 19:00 outputs.tf
+-rw-r--r-- 1 kenthua primarygroup  4183 Mar  4 19:00 main.tf
+-rwxr-xr-x 1 kenthua primarygroup  3150 Mar  4 19:00 create_cluster_yamls.sh
+-rw-r--r-- 1 kenthua primarygroup   702 Mar  4 22:54 backend.tf
+-rw-r--r-- 1 kenthua primarygroup  1397 Mar  4 22:54 variables.tf
+-rw-r--r-- 1 kenthua primarygroup   688 Mar  4 23:09 log
+not copying files
+In directory /usr/local/google/home/kenthua/work/ai/mlops/ai-on-gke/ml-platform/03_configsync
+level0 total 48
+drwxr-xr-x 3 kenthua primarygroup  4096 Mar  4 19:00 templates
+-rw-r--r-- 1 kenthua primarygroup 11509 Mar  4 19:00 README.md
+-rw-r--r-- 1 kenthua primarygroup  1036 Mar  4 19:00 providers.tf
+-rw-r--r-- 1 kenthua primarygroup   692 Mar  4 19:00 outputs.tf
+-rw-r--r-- 1 kenthua primarygroup  4183 Mar  4 19:00 main.tf
+-rwxr-xr-x 1 kenthua primarygroup  3150 Mar  4 19:00 create_cluster_yamls.sh
+-rw-r--r-- 1 kenthua primarygroup   702 Mar  4 22:54 backend.tf
+-rw-r--r-- 1 kenthua primarygroup  1397 Mar  4 22:54 variables.tf
+-rw-r--r-- 1 kenthua primarygroup  1418 Mar  4 23:09 log
+level1 total 28
+drwxr-xr-x 3 kenthua primarygroup 4096 Mar  4 19:00 01_gcp_project
+-rw-r--r-- 1 kenthua primarygroup 3879 Mar  4 19:00 README.md
+drwxr-xr-x 2 kenthua primarygroup 4096 Mar  4 19:00 06_operating_teams
+drwxr-xr-x 2 kenthua primarygroup 4096 Mar  4 19:00 05_setup_teams
+drwxr-xr-x 2 kenthua primarygroup 4096 Mar  4 19:00 04_setup_clusters
+drwxr-xr-x 4 kenthua primarygroup 4096 Mar  4 19:11 02_gke
+drwxr-xr-x 4 kenthua primarygroup 4096 Mar  4 23:09 03_configsync
+level2 total 120
+drwxr-xr-x  5 kenthua primarygroup  4096 Mar  4 19:00 applications
+drwxr-xr-x  4 kenthua primarygroup  4096 Mar  4 19:00 dcgm-on-gke
+lrwxrwxrwx  1 kenthua primarygroup    20 Mar  4 19:00 jupyter-on-gke -> applications/jupyter
+drwxr-xr-x  3 kenthua primarygroup  4096 Mar  4 19:00 jobset
+drwxr-xr-x  4 kenthua primarygroup  4096 Mar  4 19:00 gke-tpu-examples
+drwxr-xr-x  4 kenthua primarygroup  4096 Mar  4 19:00 saxml-on-gke
+lrwxrwxrwx  1 kenthua primarygroup    16 Mar  4 19:00 ray-on-gke -> applications/ray
+drwxr-xr-x 15 kenthua primarygroup  4096 Mar  4 19:00 modules
+drwxr-xr-x  6 kenthua primarygroup  4096 Mar  4 19:00 tutorials
+-rw-r--r--  1 kenthua primarygroup  5505 Mar  4 19:00 README.md
+-rw-r--r--  1 kenthua primarygroup  2832 Mar  4 19:00 Makefile
+-rw-r--r--  1 kenthua primarygroup 11357 Mar  4 19:00 LICENSE
+drwxr-xr-x  6 kenthua primarygroup  4096 Mar  4 19:00 benchmarks
+drwxr-xr-x  3 kenthua primarygroup  4096 Mar  4 19:00 gke-a100-jax
+-rw-r--r--  1 kenthua primarygroup  1068 Mar  4 19:00 contributing.md
+-rw-r--r--  1 kenthua primarygroup  6624 Mar  4 19:00 cloudbuild.yaml
+drwxr-xr-x  2 kenthua primarygroup  4096 Mar  4 19:00 best-practices
+drwxr-xr-x  9 kenthua primarygroup  4096 Mar  4 19:00 gke-batch-refarch
+drwxr-xr-x  2 kenthua primarygroup  4096 Mar  4 19:00 gke-dws-examples
+drwxr-xr-x  4 kenthua primarygroup  4096 Mar  4 19:00 gke-disk-image-builder
+drwxr-xr-x  3 kenthua primarygroup  4096 Mar  4 19:00 gke-online-serving-single-gpu
+drwxr-xr-x  4 kenthua primarygroup  4096 Mar  4 19:00 infrastructure
+drwxr-xr-x  2 kenthua primarygroup  4096 Mar  4 19:00 indexed-job
+drwxr-xr-x  8 kenthua primarygroup  4096 Mar  4 19:00 ml-platform
+drwxr-xr-x  8 kenthua primarygroup  4096 Mar  4 19:00 tpu-provisioner
+-rw-r--r--  1 kenthua primarygroup  5838 Mar  4 19:00 tutorial.md
+drwxr-xr-x  4 kenthua primarygroup  4096 Mar  4 19:00 training-single-gpu
+level3 total 4
+drwxr-xr-x 22 kenthua primarygroup 4096 Mar  4 19:00 ai-on-gke
+level4 total 40
+drwxr-xr-x  2 kenthua primarygroup 4096 Jan 27 01:15 finetuning-llama-7b-on-l4
+-rw-r--r--  1 kenthua primarygroup 4127 Jan 31 23:17 raycluster.yaml
+drwxr-x---  4 kenthua primarygroup 4096 Feb 21 07:18 gradio
+drwxr-xr-x  3 kenthua primarygroup 4096 Feb 23 16:36 a-b
+drwxr-xr-x  7 kenthua primarygroup 4096 Feb 24 23:43 gemma
+drwxr-xr-x  2 kenthua primarygroup 4096 Feb 27 00:37 ray-demo
+drwxr-xr-x 18 kenthua primarygroup 4096 Feb 28 01:20 kubernetes-engine-samples
+drwxr-xr-x 22 kenthua primarygroup 4096 Feb 28 20:21 ai-on-gke
+drwxr-xr-x  3 kenthua primarygroup 4096 Mar  4 18:59 mlops
+env is dev

ml-platform/03_configsync/variables.tf

@@ -15,7 +15,7 @@
 variable "lookup_state_bucket" {
   description = "GCS bucket to look up TF state from previous steps."
   type = string
-  default = "YOUR_STATE_BUCKET"
+  default = "kh-gkebatchexpce3c8dcb-tf-state"
 }
 
 variable "configsync_repo_name" {
@@ -27,17 +27,17 @@ variable "configsync_repo_name" {
 variable "github_user" {
   description = "GitHub user name."
   type = string
-  default = "YOUR_GIT_USER"
+  default = "kenthua"
 }
 variable "github_email" {
   description = "GitHub user email."
   type = string
-  default = "YOUR_GIT_USER_EMAIL"
+  default = "[email protected]"
 }
 variable "github_org" {
   type = string
   description = "GitHub org."
-  default = "YOUR_GIT_ORG"
+  default = "cloud-mlops"
 }
 variable "github_token" {
   type = string