NAS-144884 / 28.0.0-BETA.1 / truenas-appliance-runner: spare-nics adds NICs with nothing on the other end, for interface changes

.github/actions/truenas-appliance-runner/action.yml

@@ -69,6 +69,13 @@
       alike cannot give, such as a disk big enough to mirror the boot pool
       onto. Not for an HA pair.
     default: ''
+  spare-nics:
+    description: >-
+      NICs besides the one the API is reached on, 0 to 9, each alone on a
+      qemu hub: no DHCP, no route, nothing on the other end. For a suite to
+      apply interface changes on without cutting itself off. Their MACs,
+      52:54:00:e2:e0:01 and up, are in TN_SPARE_NICS. Not for an HA pair.
+    default: '0'
   ssh:
     description: '`true` enables ssh for the admin, on TN_SSH.'
     default: 'false'
@@ -114,6 +121,7 @@
         APPLIANCE_DATA_DISKS: ${{ inputs.data-disk-count }}
         APPLIANCE_DATA_DISK_GB: ${{ inputs.data-disk-gb }}
         APPLIANCE_EXTRA_DISK_GB: ${{ inputs.extra-disk-gb }}
+        APPLIANCE_SPARE_NICS: ${{ inputs.spare-nics }}
         APPLIANCE_SSH: ${{ inputs.ssh }}
         APPLIANCE_DISK_INPUT: ${{ inputs.disk }}
         EXPORT_ENV: ${{ inputs.export-env }}
@@ -128,6 +136,10 @@
           echo "::error::extra-disk-gb is for one appliance; an HA pair has only the data-disk-count disks its nodes share"
           exit 1
         fi
+        if [ "$HA" = true ] && [ "${APPLIANCE_SPARE_NICS:-0}" != 0 ]; then
+          echo "::error::spare-nics is for one appliance; ha.sh wires an HA pair's NICs itself"
+          exit 1
+        fi
         export APPLIANCE_DIR="$RUNNER_TEMP/truenas-appliance"
         # The password is made here, so it is masked before anything can
         # print it.

.github/actions/truenas-appliance-runner/appliance.sh

@@ -37,6 +37,10 @@
 #   APPLIANCE_DATA_DISKS  10         APPLIANCE_DATA_DISK_GB 10 (sparse)
 #   APPLIANCE_EXTRA_DISK_GB  more sparse disks after those, one per size in
 #                         GB, space-separated: "32", "12 12 15" (default none)
+#   APPLIANCE_SPARE_NICS  0: NICs after the one the API is reached on, each
+#                         alone on a qemu hub of its own, so no DHCP, no
+#                         route and no peer: for a suite to reconfigure
+#                         without cutting itself off
 #   APPLIANCE_HTTP_PORT   8080       APPLIANCE_HTTPS_PORT   8443
 #   APPLIANCE_SSH_PORT    2222       APPLIANCE_SSH          false
 #   APPLIANCE_BASELINE    fresh-install: the snapshot start takes; empty
@@ -49,7 +53,8 @@
 # start prints TN_PROFILE, TN_HOST (host:https port), TN_HOST_HTTP,
 # TN_USERNAME, TN_PASSWORD, TN_DOMAIN, TN_BASELINE (the suite's contract,
 # as the lab's claim action gives it, less its TN_GUEST_ISO), TN_SSH when
-# APPLIANCE_SSH is true, and what it measured:
+# APPLIANCE_SSH is true, TN_SPARE_NICS (the spare NICs' MAC addresses,
+# space-separated) when there are any, and what it measured:
 # APPLIANCE_BOOT_SECONDS, APPLIANCE_SNAPSHOT_SECONDS.
 
 set -euo pipefail
@@ -101,6 +106,7 @@ start() {
     local ndata="${APPLIANCE_DATA_DISKS:-10}" datagb="${APPLIANCE_DATA_DISK_GB:-10}"
     local extragb=()
     read -r -a extragb <<< "${APPLIANCE_EXTRA_DISK_GB:-}"
+    local nspare="${APPLIANCE_SPARE_NICS:-0}"
     local http="${APPLIANCE_HTTP_PORT:-8080}" https="${APPLIANCE_HTTPS_PORT:-8443}" sshp="${APPLIANCE_SSH_PORT:-2222}"
     local baseline="${APPLIANCE_BASELINE-fresh-install}"
     local password="${APPLIANCE_PASSWORD:-$(head -c 15 /dev/urandom | base64 | tr -d '/+=')}"
@@ -111,6 +117,7 @@ start() {
     for gb in "${extragb[@]}"; do
         [[ "$gb" =~ ^[1-9][0-9]*$ ]] || die "APPLIANCE_EXTRA_DISK_GB: \"$gb\" is not a whole number of GB"
     done
+    [[ "$nspare" =~ ^[0-9]$ ]] || die "APPLIANCE_SPARE_NICS: \"$nspare\" is not a number of NICs from 0 to 9"
     needs qemu-system-x86_64 qemu-system-x86 qemu-img qemu-utils python3 python3
     ovmf
     local accel="${APPLIANCE_ACCEL:-kvm}" cpu=host
@@ -157,9 +164,26 @@ start() {
         extrasaid=", and $nextra more of $(printf '%sG ' "${extragb[@]}")"
         extrasaid="${extrasaid% }"
     fi
+    # After the NIC the API is reached on, so that one keeps its PCI slot,
+    # and with it its name, whatever the count. Each on a hub with no other
+    # port: its link is up, and nothing ever answers on it. qemu warns
+    # "hub N is not connected to host network" for each, which is the
+    # point. The MACs are fixed, for a suite to tell these NICs apart by.
+    local nics=() spare_macs=()
+    for i in $(seq 1 "$nspare"); do
+        spare_macs+=("52:54:00:e2:e0:0$i")
+        nics+=(-netdev "hubport,id=spare$i,hubid=$i"
+               -device "virtio-net-pci,netdev=spare$i,mac=52:54:00:e2:e0:0$i")
+    done
+    local nicssaid=""
+    if [ "$nspare" -eq 1 ]; then
+        nicssaid=", 1 spare NIC"
+    elif [ "$nspare" -gt 1 ]; then
+        nicssaid=", $nspare spare NICs"
+    fi
 
     local booted t0
-    say "booting $disk as $name: ${memory} MB, $vcpus vCPUs, $ndata data disks of ${datagb}G$extrasaid"
+    say "booting $disk as $name: ${memory} MB, $vcpus vCPUs, $ndata data disks of ${datagb}G$extrasaid$nicssaid"
     t0=$(date +%s.%N)
     qemu-system-x86_64 -name "$name" -machine "q35,accel=$accel" -cpu "$cpu" -smp "$vcpus" -m "$memory" \
         -smbios "type=1,serial=$name" \
@@ -169,6 +193,7 @@ start() {
         -device "virtio-blk-pci,drive=os,serial=os,bootindex=0" \
         "${drives[@]}" \
         -nic "user,model=virtio-net-pci$(hostfwd 80 "$http")$(hostfwd 443 "$https")$(hostfwd 22 "$sshp")" \
+        "${nics[@]}" \
         -device virtio-rng-pci \
         -qmp "unix:$QMP,server=on,wait=off" \
         -display none -serial "file:$DIR/console.log" \
@@ -222,6 +247,9 @@ EOF
     if [ "${APPLIANCE_SSH:-false}" = true ]; then
         echo "TN_SSH=127.0.0.1:$sshp"
     fi
+    if [ "$nspare" -gt 0 ]; then
+        echo "TN_SPARE_NICS=${spare_macs[*]}"
+    fi
 }
 
 snapshot() {

README.md

@@ -555,6 +555,7 @@ jobs:
 | `memory-mb`, `vcpus` | `6144`, `4` | The appliance's; the runner's flavor needs room for it and the job |
 | `data-disk-count`, `data-disk-gb` | `10`, `10` | Sparse qcow2 files |
 | `extra-disk-gb` | none | More sparse disks after the data disks, one per size in GB: `'32'`, `'12 12 15'`. Not for an HA pair |
+| `spare-nics` | `'0'` | NICs after the one the API is reached on, each alone on a qemu hub: no DHCP, no route. For applying interface changes without losing the appliance. MACs `52:54:00:e2:e0:01` and up, in `TN_SPARE_NICS`. Not for an HA pair |
 | `ssh` | `'false'` | `true` enables ssh for the admin, on `TN_SSH` |
 | `disk` | the attached one | Found by its serial, `virtio-truenas_appliance`, where the box keeps it; TrueNAS replaces it, so otherwise the one disk besides the root disk that holds a ZFS `boot-pool` |
 | `export-env` | `'true'` | Write `TN_*` to the job environment |