ops(nh3-dev): grow root into the 378 GB disk online; swap moved to /swapfile

Prime grew VM 102's scsi0 from 250 to 378 GB after the root alert hit 85% twice in 14 h. The swap partition sat right after sda1 and blocked growth, so the playbook moves swap to a 4 GB /swapfile, deletes sda5/sda2, grows sda1 in place (start sector unchanged) and ext4 online, and sets initramfs RESUME=none so boots don't wait for the vanished swap. Root is 372 GB, 58%.
2026-10-02 07:33:36 -07:00
parent 01c356e7fb
commit 6ec76bf35c
3 changed files with 112 additions and 0 deletions
@@ -0,0 +1,104 @@
+# Grow nh3-dev's root filesystem into space added to its disk in Proxmox (VM 102 on nh3-pve).
+# First used 2026-10-02: Prime grew scsi0 250G -> 378G after the 85% root alert fired twice in 14 h.
+#
+# The obstacle: the Debian installer put swap (sda5, inside extended sda2) right AFTER sda1, so
+# sda1 cannot grow until that swap partition is gone. This playbook moves swap to /swapfile, deletes
+# sda5 and sda2, grows sda1 in place (start sector unchanged) and grows ext4 online. No reboot.
+#
+# Take a VM snapshot on nh3-pve FIRST (qm snapshot 102 <name>). The partition table is also dumped to
+# /var/backups/nh3-dev-rootgrow-<stamp>/sda-ptable.sfdisk, which `sfdisk /dev/sda < dump` restores (sda1's data is untouched
+# either way: only its end moves).
+#
+# RESUME: initramfs-tools points resume-from-hibernation at the old swap UUID. With that partition
+# gone, every boot would wait ~30 s for it, so RESUME is set to none and all initrds are rebuilt.
+#
+#   scripts/elway infra-ops@10.100.10.50 --playbook playbooks/nh3-dev-grow-root.yaml
+vars:
+  stamp: "20261002"
+  old_swap_uuid: 97bca850-bf72-4881-ae33-23d9b68315b6
+  swapfile_size: 4G
+
+steps:
+  - name: Back up the partition table, fstab and the resume config
+    sudo: true
+    shell: |
+      set -e
+      install -d -m 755 /var/backups/nh3-dev-rootgrow-{{ stamp }}
+      cp -p /etc/fstab /etc/initramfs-tools/conf.d/resume /var/backups/nh3-dev-rootgrow-{{ stamp }}/
+      /usr/sbin/sfdisk -d /dev/sda > /var/backups/nh3-dev-rootgrow-{{ stamp }}/sda-ptable.sfdisk
+    # guards run as infra-ops, so the marker lives where infra-ops can see it (not under /root)
+    creates: /var/backups/nh3-dev-rootgrow-{{ stamp }}/sda-ptable.sfdisk
+
+  - name: Install growpart (cloud-guest-utils)
+    sudo: true
+    shell: DEBIAN_FRONTEND=noninteractive apt-get install -y -q cloud-guest-utils
+    creates: /usr/bin/growpart
+
+  - name: Create and enable /swapfile ({{ swapfile_size }}) BEFORE dropping the swap partition
+    sudo: true
+    shell: |
+      set -e
+      fallocate -l {{ swapfile_size }} /swapfile
+      chmod 600 /swapfile
+      /usr/sbin/mkswap /swapfile
+      /usr/sbin/swapon /swapfile
+    creates: /swapfile
+
+  - name: Add /swapfile to fstab
+    sudo: true
+    shell: echo '/swapfile none swap sw 0 0' >> /etc/fstab
+    when: "! grep -q '^/swapfile ' /etc/fstab"
+
+  - name: Turn off the old swap partition (its pages move to RAM or /swapfile)
+    sudo: true
+    shell: /usr/sbin/swapoff /dev/sda5
+    when: "/usr/sbin/swapon --show=NAME --noheadings | grep -qx /dev/sda5"
+
+  - name: Drop the old swap partition from fstab
+    sudo: true
+    shell: sed -i '/^UUID={{ old_swap_uuid }} /d' /etc/fstab
+    when: "grep -q '^UUID={{ old_swap_uuid }} ' /etc/fstab"
+
+  - name: Point initramfs resume at nothing and rebuild every initrd
+    sudo: true
+    shell: |
+      set -e
+      echo 'RESUME=none' > /etc/initramfs-tools/conf.d/resume
+      update-initramfs -u -k all
+    when: "! grep -qx 'RESUME=none' /etc/initramfs-tools/conf.d/resume"
+
+  - name: Delete partitions 5 (old swap) and 2 (the extended partition holding it)
+    sudo: true
+    shell: |
+      set -e
+      /usr/sbin/sfdisk --no-reread --force --delete /dev/sda 5
+      /usr/sbin/sfdisk --no-reread --force --delete /dev/sda 2
+      partx -d --nr 5 /dev/sda || true
+      partx -d --nr 2 /dev/sda || true
+    when: "sudo -n /usr/sbin/sfdisk -d /dev/sda | grep -q '^/dev/sda2 '"
+
+  - name: Grow partition 1 to the end of the disk (start sector unchanged)
+    sudo: true
+    shell: growpart /dev/sda 1
+    when: "sudo -n growpart --dry-run /dev/sda 1 >/dev/null 2>&1"
+
+  - name: Grow the ext4 filesystem online
+    sudo: true
+    shell: /usr/sbin/resize2fs /dev/sda1
+
+verify:
+  - name: Only sda1 remains, still starting at sector 2048
+    sudo: true
+    shell: |
+      test "$(/usr/sbin/sfdisk -d /dev/sda | grep -c '^/dev/sda')" = 1 && /usr/sbin/sfdisk -d /dev/sda | grep -q '^/dev/sda1 : start= *2048,'
+    changed_when: "false"
+  - name: Root filesystem is now over 350 GB
+    shell: test "$(df -BG --output=size / | tail -1 | tr -dc 0-9)" -gt 350
+    changed_when: "false"
+  - name: /swapfile is the active swap and the old partition is gone from fstab
+    sudo: true
+    shell: /usr/sbin/swapon --show=NAME --noheadings | grep -qx /swapfile && ! grep -q '{{ old_swap_uuid }}' /etc/fstab
+    changed_when: "false"
+  - name: Root is still mounted by its UUID in fstab
+    shell: grep -q '^UUID=689f8c0c-1230-43a5-93c2-6baf76867d70 / ' /etc/fstab
+    changed_when: "false"