michal/lab
1
0
Fork 0
Code Issues Pull Requests 3 Actions Packages Projects Releases Wiki Activity

test(bastion): add aarch64 network PXE integration test

Browse Source 
Covers what the boot-ISO ARM test never did: DHCP option 93 handing an
arm64 client an arm64 iPXE binary, dispatch serving an aarch64 kernel,
and `provision debug` reaching a rescue shell over SSH.

Split by cost. `arm-pxe` runs NBP handoff, discovery and rescue in about
20-30 minutes -- that is the path the DGX Sparks need. The full install
is another hour on top and only runs with ARM_PXE_FULL=1; an hour-plus
test that runs by default is a test nobody runs.

The suite fails fast if the arm64 iPXE build lacks LoadFile2, because the
symptom otherwise is a 30-minute boot ending in unknown-block(0,0) --
byte-identical to the DGX Spark bug this all started with, and easy to
misdiagnose as a reproduction of it.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015nRFZXpKwUVE4SRSHw6GjF
This commit is contained in:
Michal
2026-08-11 13:00:18 +01:00
parent e32c20ca5c
commit 3fab400a96
7 changed files with 568 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

71
bastion/scripts/test-provision.sh
View File

@@ -2,16 +2,18 @@
# Run PXE and/or ISO boot integration tests.
#
# Usage:
# sudo ./scripts/test-provision.sh # run PXE + ISO (x86_64)
# sudo ./scripts/test-provision.sh pxe # PXE only
# sudo ./scripts/test-provision.sh iso # ISO only (x86_64)
# sudo ./scripts/test-provision.sh arm # ARM ISO boot (emulated, SLOW ~60min)
# sudo ./scripts/test-provision.sh all # all tests including ARM
# sudo ./scripts/test-provision.sh # run PXE + ISO (x86_64)
# sudo ./scripts/test-provision.sh pxe # PXE only
# sudo ./scripts/test-provision.sh iso # ISO only (x86_64)
# sudo ./scripts/test-provision.sh arm # ARM ISO boot (emulated, SLOW ~60min)
# sudo ./scripts/test-provision.sh arm-pxe # ARM network PXE: NBP + discover + rescue (~20-30min)
# sudo ./scripts/test-provision.sh arm-pxe-full # ARM network PXE incl. full install (~60-90min)
# sudo ./scripts/test-provision.sh all # all tests including ARM
#
# Prerequisites:
# libvirtd, OVMF (edk2-ovmf), iPXE (ipxe-bootimgs-x86),
# dnsmasq, xorriso, mtools, virt-install, qemu-img
# ARM: qemu-system-aarch64, edk2-aarch64
# ARM: qemu-system-aarch64, edk2-aarch64, ipxe-bootimgs-aarch64
set -e
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
@@ -58,6 +60,10 @@ if [ ! -f /usr/share/edk2/ovmf/OVMF_CODE.fd ]; then
exit 1
fi
MODE="${1:-both}"
# iPXE binaries are per-architecture. x86_64 is always required (the dnsmasq config
# references it); arm64 only for the ARM network-PXE modes.
IPXE_EFI=""
for f in /usr/share/ipxe/ipxe-snponly-x86_64.efi /usr/share/ipxe/ipxe-snp-x86_64.efi /usr/share/ipxe/ipxe-x86_64.efi; do
[ -f "$f" ] && IPXE_EFI="$f" && break
@@ -67,6 +73,20 @@ if [ -z "$IPXE_EFI" ]; then
exit 1
fi
IPXE_EFI_ARM64=""
for f in /usr/share/ipxe/arm64-efi/snponly.efi /usr/share/ipxe/arm64-efi/ipxe.efi; do
[ -f "$f" ] && IPXE_EFI_ARM64="$f" && break
done
case "$MODE" in
arm-pxe|arm-pxe-full|all)
if [ -z "$IPXE_EFI_ARM64" ] && [ "$MODE" != "all" ]; then
echo -e "${RED}arm64 iPXE binary not found.${RESET} Install: sudo dnf install ipxe-bootimgs-aarch64"
exit 1
fi
;;
esac
# Find SSH key
SSH_KEY=""
for name in id_ed25519 id_ecdsa id_rsa; do
@@ -83,10 +103,19 @@ fi
echo -e " User: ${BOLD}$REAL_USER${RESET}"
echo -e " SSH key: ${BOLD}$SSH_KEY${RESET}"
echo -e " iPXE: ${BOLD}$IPXE_EFI${RESET}"
echo -e " iPXE a64:${BOLD} ${IPXE_EFI_ARM64:-not installed}${RESET}"
echo ""
# --- Determine which tests to run ---
MODE="${1:-both}"
require_arm_emulation() {
if ! command -v qemu-system-aarch64 &>/dev/null; then
echo -e "${RED}qemu-system-aarch64 not found.${RESET} Install: sudo dnf install qemu-system-aarch64 edk2-aarch64"
exit 1
fi
if [ ! -f /usr/share/edk2/aarch64/QEMU_EFI.fd ]; then
echo -e "${RED}AAVMF firmware not found.${RESET} Install: sudo dnf install edk2-aarch64"
exit 1
fi
}
run_test() {
local name="$1" pattern="$2"
@@ -116,13 +145,22 @@ case "$MODE" in
run_test "ISO boot" "ISO boot" || FAILED=1
;;
arm|arm-iso)
if ! command -v qemu-system-aarch64 &>/dev/null; then
echo -e "${RED}qemu-system-aarch64 not found.${RESET} Install: sudo dnf install qemu-system-aarch64 edk2-aarch64"
exit 1
fi
require_arm_emulation
echo -e "${YELLOW}ARM emulation is ~10x slower than native. Expect 30-60 minutes.${RESET}"
run_test "ARM ISO boot" "ARM ISO" || FAILED=1
;;
arm-pxe)
require_arm_emulation
echo -e "${YELLOW}ARM emulation is ~10x slower than native. Expect 20-30 minutes.${RESET}"
echo -e "${YELLOW}Covers option 93 -> arm64 NBP, discovery, and rescue over SSH.${RESET}"
echo -e "${YELLOW}For the full install too, use: $0 arm-pxe-full${RESET}"
run_test "ARM PXE rescue" "ARM PXE rescue" || FAILED=1
;;
arm-pxe-full)
require_arm_emulation
echo -e "${YELLOW}ARM emulation is ~10x slower than native. Expect 60-90 minutes.${RESET}"
ARM_PXE_FULL=1 run_test "ARM PXE (rescue + install)" "ARM PXE" || FAILED=1
;;
both)
run_test "PXE boot" "PXE boot" || FAILED=1
run_test "ISO boot" "ISO boot" || FAILED=1
@@ -133,12 +171,17 @@ case "$MODE" in
if command -v qemu-system-aarch64 &>/dev/null; then
echo -e "${YELLOW}ARM emulation is ~10x slower than native.${RESET}"
run_test "ARM ISO boot" "ARM ISO" || FAILED=1
if [ -n "$IPXE_EFI_ARM64" ]; then
run_test "ARM PXE rescue" "ARM PXE rescue" || FAILED=1
else
echo -e "${YELLOW}Skipping ARM PXE test (ipxe-bootimgs-aarch64 not installed)${RESET}"
fi
else
echo -e "${YELLOW}Skipping ARM test (qemu-system-aarch64 not installed)${RESET}"
echo -e "${YELLOW}Skipping ARM tests (qemu-system-aarch64 not installed)${RESET}"
fi
;;
*)
echo "Usage: $0 [pxe|iso|arm|both|all]"
echo "Usage: $0 [pxe|iso|arm|arm-pxe|arm-pxe-full|both|all]"
exit 1
;;
esac