Merge pull request #1502 from kinvolk/kai/bare-metal-reprovisioning

pothos · web-flow · commit b0da2a105b23 · 2021-06-22T16:14:52.000+02:00
baremetal: integrate automated (re-)provisioning logic
diff --git a/assets/terraform-modules/bare-metal/flatcar-linux/kubernetes/controller.tf b/assets/terraform-modules/bare-metal/flatcar-linux/kubernetes/controller.tf
@@ -13,8 +13,22 @@ module "controller" {
   set_standard_hostname  = false
   clc_snippets = concat(lookup(var.clc_snippets, var.controller_names[count.index], []), [
     <<EOF
+filesystems:
+  - name: root
+    mount:
+      device: /dev/disk/by-label/ROOT
+      format: ext4
+      wipe_filesystem: true
+      label: ROOT
 storage:
   files:
+    - path: /ignition_ran
+      filesystem: root
+      mode: 0644
+      contents:
+        inline: |
+          Flag file indicating that Ignition ran.
+          Should be deleted by the SSH step that checks it.
     - path: /etc/hostname
       filesystem: root
       mode: 0644
diff --git a/assets/terraform-modules/bare-metal/flatcar-linux/kubernetes/controller_profiles.tf b/assets/terraform-modules/bare-metal/flatcar-linux/kubernetes/controller_profiles.tf
@@ -1,19 +1,25 @@
 module "controller_profile" {
   source                   = "../../../matchbox-flatcar"
   count                    = length(var.controller_names)
+  asset_dir                = var.asset_dir
   node_name                = var.controller_names[count.index]
   node_mac                 = var.controller_macs[count.index]
+  node_domain              = var.controller_domains[count.index]
   download_protocol        = var.download_protocol
   os_channel               = var.os_channel
   os_version               = var.os_version
   http_endpoint            = var.matchbox_http_endpoint
   kernel_args              = var.kernel_args
   kernel_console           = var.kernel_console
+  installer_clc_snippets   = lookup(var.installer_clc_snippets, var.controller_names[count.index], [])
   install_disk             = var.install_disk
   install_to_smallest_disk = var.install_to_smallest_disk
   container_linux_oem      = var.container_linux_oem
   ssh_keys                 = var.ssh_keys
   ignition_clc_config      = module.controller[count.index].clc_config
   cached_install           = var.cached_install
   wipe_additional_disks    = var.wipe_additional_disks
+  ignore_changes           = true
+  pxe_commands             = var.pxe_commands
+  install_pre_reboot_cmds  = var.install_pre_reboot_cmds
 }
diff --git a/assets/terraform-modules/bare-metal/flatcar-linux/kubernetes/ssh.tf b/assets/terraform-modules/bare-metal/flatcar-linux/kubernetes/ssh.tf
@@ -81,7 +81,12 @@ resource "null_resource" "copy-controller-secrets" {
     ]
   }
 
+
+  # Triggered when the Ignition Config changes (used to recreate a controller)
   triggers = {
+    clc_config       = module.controller[count.index].clc_config
+    kernel_console   = join(" ", var.kernel_console)
+    kernel_args      = join(" ", var.kernel_args)
     etcd_ca_cert     = module.bootkube.etcd_ca_cert
     etcd_server_cert = module.bootkube.etcd_server_cert
     etcd_peer_cert   = module.bootkube.etcd_peer_cert
diff --git a/assets/terraform-modules/bare-metal/flatcar-linux/kubernetes/variables.tf b/assets/terraform-modules/bare-metal/flatcar-linux/kubernetes/variables.tf
@@ -61,6 +61,12 @@ variable "clc_snippets" {
   default     = {}
 }
 
+variable "installer_clc_snippets" {
+  type        = map(list(string))
+  description = "Map from machine names to lists of Container Linux Config snippets, applied for the PXE-booted installer OS"
+  default     = {}
+}
+
 variable "labels" {
   type        = map(string)
   description = "Map of labels for worker nodes."
@@ -221,3 +227,15 @@ variable "wipe_additional_disks" {
   description = "Wipes any additional disks attached, if set to true"
   default     = false
 }
+
+variable "pxe_commands" {
+  type        = string
+  default     = "echo 'you must (re)provision the node by booting via iPXE from http://MATCHBOX/boot.ipxe'; exit 1"
+  description = "shell commands to execute for PXE (re)provisioning, with access to the variables $mac (the MAC address), $name (the node name), and $domain (the domain name), e.g., 'bmc=bmc-$domain; ipmitool -H $bmc power off; ipmitool -H $bmc chassis bootdev pxe; ipmitool -H $bmc power on'"
+}
+
+variable "install_pre_reboot_cmds" {
+  type        = string
+  default     = "true"
+  description = "shell commands to execute on the provisioned host after installation finished and before reboot, e.g., docker run --privileged --net host --rm debian sh -c 'apt update && apt install -y ipmitool && ipmitool chassis bootdev disk options=persistent'"
+}
diff --git a/assets/terraform-modules/bare-metal/flatcar-linux/kubernetes/worker.tf b/assets/terraform-modules/bare-metal/flatcar-linux/kubernetes/worker.tf
@@ -12,8 +12,22 @@ module "worker" {
   set_standard_hostname  = false
   clc_snippets = concat(lookup(var.clc_snippets, var.worker_names[count.index], []), [
     <<EOF
+filesystems:
+  - name: root
+    mount:
+      device: /dev/disk/by-label/ROOT
+      format: ext4
+      wipe_filesystem: true
+      label: ROOT
 storage:
   files:
+    - path: /ignition_ran
+      filesystem: root
+      mode: 0644
+      contents:
+        inline: |
+          Flag file indicating that Ignition ran.
+          Should be deleted by the SSH step that checks it.
     - path: /etc/hostname
       filesystem: root
       mode: 0644
diff --git a/assets/terraform-modules/bare-metal/flatcar-linux/kubernetes/worker_profiles.tf b/assets/terraform-modules/bare-metal/flatcar-linux/kubernetes/worker_profiles.tf
@@ -1,19 +1,24 @@
 module "worker_profile" {
   source                   = "../../../matchbox-flatcar"
   count                    = length(var.worker_names)
+  asset_dir                = var.asset_dir
   node_name                = var.worker_names[count.index]
   node_mac                 = var.worker_macs[count.index]
+  node_domain              = var.worker_domains[count.index]
   download_protocol        = var.download_protocol
   os_channel               = var.os_channel
   os_version               = var.os_version
   http_endpoint            = var.matchbox_http_endpoint
   kernel_args              = var.kernel_args
   kernel_console           = var.kernel_console
+  installer_clc_snippets   = lookup(var.installer_clc_snippets, var.worker_names[count.index], [])
   install_disk             = var.install_disk
   install_to_smallest_disk = var.install_to_smallest_disk
   container_linux_oem      = var.container_linux_oem
   ssh_keys                 = var.ssh_keys
   ignition_clc_config      = module.worker[count.index].clc_config
   cached_install           = var.cached_install
   wipe_additional_disks    = var.wipe_additional_disks
+  pxe_commands             = var.pxe_commands
+  install_pre_reboot_cmds  = var.install_pre_reboot_cmds
 }
diff --git a/assets/terraform-modules/matchbox-flatcar/profiles.tf b/assets/terraform-modules/matchbox-flatcar/profiles.tf
@@ -18,7 +18,11 @@ resource "matchbox_profile" "flatcar-install" {
     var.kernel_args,
   ])
 
-  container_linux_config = templatefile("${path.module}/templates/install.yaml.tmpl", {
+  raw_ignition = data.ct_config.install-ignitions.rendered
+}
+
+data "ct_config" "install-ignitions" {
+  content = templatefile("${path.module}/templates/install.yaml.tmpl", {
     os_channel               = var.os_channel
     os_version               = var.os_version
     ignition_endpoint        = format("%s/ignition", var.http_endpoint)
@@ -29,9 +33,15 @@ resource "matchbox_profile" "flatcar-install" {
     kernel_console           = join(" ", var.kernel_console)
     kernel_args              = join(" ", var.kernel_args)
     wipe_additional_disks    = var.wipe_additional_disks
+    install_pre_reboot_cmds  = var.install_pre_reboot_cmds
     # only cached-container-linux profile adds -b baseurl
     baseurl_flag = ""
+    mac_address  = var.node_mac
   })
+
+  pretty_print = false
+
+  snippets = var.installer_clc_snippets
 }
 
 // Flatcar Container Linux Install profile (from matchbox /assets cache)
@@ -56,7 +66,11 @@ resource "matchbox_profile" "cached-flatcar-linux-install" {
     var.kernel_args,
   ])
 
-  container_linux_config = templatefile("${path.module}/templates/install.yaml.tmpl", {
+  raw_ignition = data.ct_config.cached-install-ignitions.rendered
+}
+
+data "ct_config" "cached-install-ignitions" {
+  content = templatefile("${path.module}/templates/install.yaml.tmpl", {
     os_channel               = var.os_channel
     os_version               = var.os_version
     ignition_endpoint        = format("%s/ignition", var.http_endpoint)
@@ -67,9 +81,15 @@ resource "matchbox_profile" "cached-flatcar-linux-install" {
     kernel_console           = join(" ", var.kernel_console)
     kernel_args              = join(" ", var.kernel_args)
     wipe_additional_disks    = var.wipe_additional_disks
+    install_pre_reboot_cmds  = var.install_pre_reboot_cmds
     # profile uses -b baseurl to install from matchbox cache
     baseurl_flag = "-b ${var.http_endpoint}/assets/flatcar"
+    mac_address  = var.node_mac
   })
+
+  pretty_print = false
+
+  snippets = var.installer_clc_snippets
 }
 
 resource "matchbox_profile" "node" {
diff --git a/assets/terraform-modules/matchbox-flatcar/pxe-helper.sh.tmpl b/assets/terraform-modules/matchbox-flatcar/pxe-helper.sh.tmpl
@@ -0,0 +1,87 @@
+# (executed in-line, #!/... would be ignored)
+# Terraform template variable substitution:
+name=${name}
+domain=${domain}
+mac=${mac}
+asset_dir=${asset_dir}
+ignore_changes=${ignore_changes}
+kernel_args="${kernel_args}"
+kernel_console="${kernel_console}"
+ignition_endpoint="${ignition_endpoint}"
+# From now on use $var for dynamic shell substitution
+
+if test -f "$asset_dir/$mac" && [ "$(cat "$asset_dir/$mac")" = "$domain" ]; then
+  echo "found $asset_dir/$mac containing $domain, skipping PXE install"
+  node_exists=yes
+else
+  echo "$asset_dir/$mac does not contain $domain, forcing PXE install"
+  node_exists=no
+fi
+
+if [ $node_exists = yes ]; then
+  if $ignore_changes ; then
+    echo "Keeping old config because 'ignore_changes' is set."
+    exit 0
+  else
+    # run single commands that can be retried without a side effect in case the connection got disrupted
+    count=30
+    while [ $count -gt 0 ] && ! ssh -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null -o NumberOfPasswordPrompts=0 core@$domain sudo touch /boot/flatcar/first_boot; do
+      sleep 1
+      count=$((count - 1))
+    done
+    if [ $count -eq 0 ]; then
+      echo "error reaching $domain via SSH, please remove the $asset_dir/$mac file to force a PXE install"
+      exit 1
+    fi
+    echo "created the first_boot flag file to reprovision $domain"
+    count=5
+    while [ $count -gt 0 ] && ! ssh -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null -o NumberOfPasswordPrompts=0 core@$domain "printf 'set linux_append=\"$kernel_args ignition.config.url=$ignition_endpoint?mac=$mac&os=installed\"\\nset linux_console=\"$kernel_console\"\\n' | sudo tee /usr/share/oem/grub.cfg"; do
+      sleep 1
+      count=$((count - 1))
+    done
+    if [ $count -eq 0 ]; then
+      echo "error reaching $domain via SSH, please retry"
+      exit 1
+    fi
+    count=5
+    while [ $count -gt 0 ] && ! ssh -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null -o NumberOfPasswordPrompts=0 core@$domain sudo systemctl reboot; do
+      sleep 1
+      count=$((count - 1))
+    done
+    if [ $count -eq 0 ]; then
+      echo "error reaching $domain via SSH, please reboot manually"
+      exit 1
+    fi
+    echo "rebooted the $domain"
+  fi
+else
+  # the user may provide ipmitool commands or any other logic for forcing a PXE boot
+  ${pxe_commands}
+fi
+
+echo "checking that $domain comes up"
+count=600
+# check that we can reach the node and that it has the flag file which we remove here, indicating a reboot happened which prevents a race when issuing the reboot takes longer (both the systemctl reboot and PXE case)
+# Just in case the connection breaks and SSH may report an error code but still execute successfully, we will first check file existence and then delete with "rm -f" to be able to rerun both commands.
+# This sequence gives us the same error reporting as just running "rm" once.
+while [ $count -gt 0 ] && ! ssh -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null -o NumberOfPasswordPrompts=0 core@$domain test -f /ignition_ran; do
+  sleep 1
+  count=$((count - 1))
+done
+if [ $count -eq 0 ]; then
+  echo "error: failed verifying with SSH if $domain came up by checking the /ignition_ran flag file"
+  exit 1
+fi
+count=5
+while [ $count -gt 0 ] && ! ssh -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null -o NumberOfPasswordPrompts=0 core@$domain sudo rm -f /ignition_ran; do
+  sleep 1
+  count=$((count - 1))
+done
+if [ $count -eq 0 ]; then
+  echo "error: failed to remove the /ignition_ran flag file on $domain"
+  exit 1
+else
+  echo "$domain came up again"
+fi
+# only write the state file once the system is up, this allows to rerun lokoctl if the first PXE boot did not work and it will try again
+echo $domain > "$asset_dir/$mac"
diff --git a/assets/terraform-modules/matchbox-flatcar/ssh.tf b/assets/terraform-modules/matchbox-flatcar/ssh.tf
@@ -0,0 +1,14 @@
+resource "null_resource" "reprovision-node-when-ignition-changes" {
+  # Triggered when the Ignition Config changes
+  triggers = {
+    ignition_config = matchbox_profile.node.raw_ignition
+    kernel_args     = join(" ", var.kernel_args)
+    kernel_console  = join(" ", var.kernel_console)
+  }
+  # Wait for the new Ignition config object to be ready before rebooting
+  depends_on = [matchbox_group.node]
+  # Trigger running Ignition on the next reboot (first_boot flag file) and reboot the instance, or, if the instance needs to be (re)provisioned, run external commands for PXE booting (also runs on the first provisioning)
+  provisioner "local-exec" {
+    command = templatefile("${path.module}/pxe-helper.sh.tmpl", { domain = var.node_domain, name = var.node_name, mac = var.node_mac, pxe_commands = var.pxe_commands, asset_dir = var.asset_dir, kernel_args = join(" ", var.kernel_args), kernel_console = join(" ", var.kernel_console), ignition_endpoint = format("%s/ignition", var.http_endpoint), ignore_changes = var.ignore_changes })
+  }
+}
diff --git a/assets/terraform-modules/matchbox-flatcar/templates/install.yaml.tmpl b/assets/terraform-modules/matchbox-flatcar/templates/install.yaml.tmpl
@@ -49,7 +49,6 @@ storage:
             wipefs -f -a "$${disk}" || echo "error: failed to wipe $${disk}"
           done
           %{~ endif ~}
-          curl --retry 10 "${ignition_endpoint}?{{.request.raw_query}}&os=installed" -o ignition.json
           flatcar-install \
             %{~ if install_to_smallest_disk ~}
             -s \
@@ -59,16 +58,16 @@ storage:
             -C ${os_channel} \
             -V ${os_version} \
             -o "${container_linux_oem}" \
-            ${baseurl_flag} \
-            -i ignition.json
+            ${baseurl_flag}
           udevadm settle
           OEM_DEV="$(blkid -t "LABEL=OEM" -o device)"
           mkdir -p /tmp/oemfs
           mount "$${OEM_DEV}" /tmp/oemfs
           # append to file on newly created partition, do not remove the defaults
-          echo 'set linux_append="${kernel_args}"' >> /tmp/oemfs/grub.cfg
+          echo 'set linux_append="${kernel_args} ignition.config.url=${ignition_endpoint}?mac=${mac_address}&os=installed"' >> /tmp/oemfs/grub.cfg
           echo 'set linux_console="${kernel_console}"' >> /tmp/oemfs/grub.cfg
           umount /tmp/oemfs
+          ${install_pre_reboot_cmds}
           systemctl reboot
 passwd:
   users:
diff --git a/assets/terraform-modules/matchbox-flatcar/variables.tf b/assets/terraform-modules/matchbox-flatcar/variables.tf
@@ -67,6 +67,12 @@ variable "ignition_clc_config" {
   description = "Ignition CLC snippets to include in the configuration."
 }
 
+variable "installer_clc_snippets" {
+  type        = list(string)
+  description = "List of Container Linux Config snippets."
+  default     = []
+}
+
 variable "node_name" {
   type        = string
   description = "Name of the node/machine."
@@ -82,3 +88,31 @@ variable "wipe_additional_disks" {
   description = "Wipes any additional disks attached, if set to true"
   default     = false
 }
+
+variable "ignore_changes" {
+  description = "When set to true, ignores the reprovisioning of the node (unless the MAC address flag file is removed to force a PXE install)."
+  type        = bool
+  default     = false
+}
+
+variable "asset_dir" {
+  description = "Path to a directory where generated assets should be placed (contains secrets)"
+  type        = string
+}
+
+variable "node_domain" {
+  type        = string
+  description = "Node FQDN (e.g node1.example.com)."
+}
+
+variable "pxe_commands" {
+  type        = string
+  description = "shell commands to execute for PXE (re)provisioning, with access to the variables $mac (the MAC address), $name (the node name), and $domain (the domain name), e.g., 'bmc=bmc-$domain; ipmitool -H $bmc power off; ipmitool -H $bmc chassis bootdev pxe; ipmitool -H $bmc power on'."
+  default     = "echo 'you must (re)provision the node by booting via iPXE from http://MATCHBOX/boot.ipxe'; exit 1"
+}
+
+variable "install_pre_reboot_cmds" {
+  type        = string
+  description = "shell commands to execute on the provisioned host after installation finished and before reboot, e.g., docker run --privileged --net host --rm debian sh -c 'apt update && apt install -y ipmitool && ipmitool chassis bootdev disk options=persistent'."
+  default     = "true"
+}
diff --git a/assets/terraform-modules/matchbox-flatcar/versions.tf b/assets/terraform-modules/matchbox-flatcar/versions.tf
@@ -2,6 +2,10 @@ terraform {
   required_version = ">= 0.13"
 
   required_providers {
+    ct = {
+      source  = "poseidon/ct"
+      version = "0.8.0"
+    }
     template = {
       source  = "hashicorp/template"
       version = "2.2.0"
diff --git a/ci/baremetal/baremetal-cluster.lokocfg.envsubst b/ci/baremetal/baremetal-cluster.lokocfg.envsubst
@@ -31,6 +31,7 @@ cluster "bare-metal" {
     "node2",
     "node3",
   ]
+  pxe_commands = "true" # The VMs are booted up outside of the CI Docker image at the right time already and we will not reprovision nor could do so because the VMs are managed at another level
   # Adds oidc flags to API server with default values.
   # Acts as a smoke test to check if API server is functional after addition
   # of extra flags.
diff --git a/docs/configuration-reference/platforms/baremetal.md b/docs/configuration-reference/platforms/baremetal.md
diff --git a/docs/quickstarts/baremetal.md b/docs/quickstarts/baremetal.md
diff --git a/pkg/assets/generated_assets.go b/pkg/assets/generated_assets.go
diff --git a/pkg/platform/baremetal/baremetal.go b/pkg/platform/baremetal/baremetal.go
diff --git a/pkg/platform/baremetal/template.go b/pkg/platform/baremetal/template.go

Original file line number	Diff line number	Diff line change
`@@ -81,7 +81,12 @@ resource "null_resource" "copy-controller-secrets" {`
`81`	`81`	`]`
`82`	`82`	`}`
`83`	`83`
	`84`	`+`
	`85`	`+ # Triggered when the Ignition Config changes (used to recreate a controller)`
`84`	`86`	`triggers = {`
	`87`	`+ clc_config = module.controller[count.index].clc_config`
	`88`	`+ kernel_console = join(" ", var.kernel_console)`
	`89`	`+ kernel_args = join(" ", var.kernel_args)`
`85`	`90`	`etcd_ca_cert = module.bootkube.etcd_ca_cert`
`86`	`91`	`etcd_server_cert = module.bootkube.etcd_server_cert`
`87`	`92`	`etcd_peer_cert = module.bootkube.etcd_peer_cert`