AWS EKS tutorial change to new terraform script (#463)

* Extracts certain values to variables

* Adds TF variables for AWS EKS tutorial, generalizes userdata.sh script

* Adds some small corrections

* Modifies aws-eks-tutorial to use the deploy/aws terraform script

* Removes comments from variables.tf

* Adds step in tutorial introduction

* Adds explanation why scaling out is done with terraform

* Adds warning about instance types breaking user data setup

* Changes tutorial instace types of monitor and tidb to not use local ssd

* Updates tutorial docs to reflect instances in tutorial var file

deploy/aws/README.md

@@ -23,7 +23,7 @@ The default setup will create a new VPC and a t2.micro instance as bastion machi
 
 ``` shell
 $ git clone https://github.com/pingcap/tidb-operator
-$ cd tidb-operator/cloud/aws
+$ cd tidb-operator/deploy/aws
 $ terraform init
 $ terraform apply
 ```

deploy/aws/aws-tutorial.tfvars

@@ -0,0 +1,11 @@
+pd_instance_type = "c5d.large"
+tikv_instance_type = "c5d.large"
+tidb_instance_type = "c4.large"
+monitor_instance_type = "c5.large"
+
+pd_count = 1
+tikv_count = 1
+tidb_count = 1
+
+cluster_name = "aws_tutorial"
+tikv_root_volume_size = "50"

deploy/aws/main.tf

@@ -99,31 +99,31 @@ module "eks" {
       key_name = "${module.key-pair.key_name}"
       # WARNING: if you change instance type, you must also modify the corresponding disk mounting in pd-userdata.sh script
       # instance_type = "c5d.xlarge" # 4c, 8G, 100G NVMe SSD
-      instance_type = "m5d.xlarge" # 4c, 16G, 150G NVMe SSD
+      instance_type = "${var.pd_instance_type}" # m5d.xlarge 4c, 16G, 150G NVMe SSD
       root_volume_size = "50" # rest NVMe disk for PD data
       public_ip = false
       kubelet_extra_args = "--register-with-taints=dedicated=pd:NoSchedule --node-labels=dedicated=pd"
       asg_desired_capacity = "${var.pd_count}"
       asg_max_size  = "${var.pd_count + 2}"
-      additional_userdata = "${file("pd-userdata.sh")}"
+      additional_userdata = "${file("userdata.sh")}"
     },
     { # tikv
       name = "tikv_worker_group"
       key_name = "${module.key-pair.key_name}"
       # WARNING: if you change instance type, you must also modify the corresponding disk mounting in tikv-userdata.sh script
-      instance_type = "i3.2xlarge" # 8c, 61G, 1.9T NVMe SSD
+      instance_type = "${var.tikv_instance_type}" # i3.2xlarge 8c, 61G, 1.9T NVMe SSD
       root_volume_type = "gp2"
       root_volume_size = "100"
       public_ip = false
       kubelet_extra_args = "--register-with-taints=dedicated=tikv:NoSchedule --node-labels=dedicated=tikv"
       asg_desired_capacity = "${var.tikv_count}"
       asg_max_size = "${var.tikv_count + 2}"
-      additional_userdata = "${file("tikv-userdata.sh")}"
+      additional_userdata = "${file("userdata.sh")}"
     },
     { # tidb
       name = "tidb_worker_group"
       key_name = "${module.key-pair.key_name}"
-      instance_type = "c4.4xlarge" # 16c, 30G
+      instance_type = "${var.tidb_instance_type}" # c4.4xlarge 16c, 30G
       root_volume_type = "gp2"
       root_volume_size = "100"
       public_ip = false
@@ -134,7 +134,7 @@ module "eks" {
     { # monitor
       name = "monitor_worker_group"
       key_name = "${module.key-pair.key_name}"
-      instance_type = "c5.xlarge" # 4c, 8G
+      instance_type = "${var.monitor_instance_type}" # c5.xlarge 4c, 8G
       root_volume_type = "gp2"
       root_volume_size = "100"
       public_ip = false

deploy/aws/userdata.sh

@@ -0,0 +1,35 @@
+# set ulimits
+cat <<EOF > /etc/security/limits.d/99-tidb.conf
+root        soft        nofile        1000000
+root        hard        nofile        1000000
+root        soft        core          unlimited
+root        soft        stack         10240
+EOF
+# config docker ulimit
+cp /usr/lib/systemd/system/docker.service /etc/systemd/system/docker.service
+sed -i 's/LimitNOFILE=infinity/LimitNOFILE=1048576/' /etc/systemd/system/docker.service
+sed -i 's/LimitNPROC=infinity/LimitNPROC=1048576/' /etc/systemd/system/docker.service
+systemctl daemon-reload
+systemctl restart docker
+
+# format and mount nvme disk
+if grep nvme0n1 /etc/fstab || grep nvme1n1 /etc/fstab; then
+    echo "disk already mounted"
+else
+    if mkfs -t ext4 /dev/nvme1n1 ; then
+
+        mkdir -p /mnt/disks/ssd1
+        cat <<EOF >> /etc/fstab
+/dev/nvme1n1 /mnt/disks/ssd1 ext4 defaults,nofail,noatime,nodelalloc 0 2
+EOF
+        mount -a
+    else
+        mkfs -t ext4 /dev/nvme0n1
+        mkdir -p /mnt/disks/ssd1
+        cat <<EOF >> /etc/fstab
+/dev/nvme0n1 /mnt/disks/ssd1 ext4 defaults,nofail,noatime,nodelalloc 0 2
+EOF
+        mount -a
+    fi
+fi
+

deploy/aws/variables.tf

@@ -83,3 +83,25 @@ variable "tikv_count" {
 variable "tidb_count" {
   default = 2
 }
+
+// Be careful about changing the instance types, it may break the user data and local volume setup
+variable "pd_instance_type" {
+  default = "m5d.xlarge"
+}
+
+variable "tikv_instance_type" {
+  default = "i3.2xlarge"
+}
+
+variable "tidb_instance_type" {
+  default = "c4.4xlarge"
+}
+
+variable "monitor_instance_type" {
+  default = "c5.xlarge"
+}
+
+variable "tikv_root_volume_size" {
+  default = "100"
+}
+