feat(iso): split the live medium into semantic SquashFS layers
Booting via BMC virtual CD reads the ~2.8 GB filesystem squashfs sequentially during the live-boot toram copy; a mid-read drop of the redirected medium loses the whole copy and fails the boot (v14). Split the rootfs into self-contained semantic layers so a retry re-reads at most one ~500-700 MiB layer, not everything. This is a resilience / reduced-re-read mechanism, not a fix for the virtual-media instability. NVIDIA variants now ship 7 layers (00-base, 05-firmware, 08-desktop, 10-nvidia-driver, 20-nvidia-platform, 30-nvidia-cuda-libs, 40-nvidia-dcgm-cuda) plus an explicit live/filesystem.module that fixes their OverlayFS order; amd/nogpu keep a single squashfs. - lib/squashfs-layers.sh: deterministic classifier (dpkg file ownership plus explicit rules for build.sh-injected files, never a path substring), per-layer mksquashfs, 800 MiB hard ceiling, unsquashfs -s plus strict extraction of every layer, merged-rootfs bootability check. - build.sh: split the monolith after the full lb build, verify and merge, write the module file, delete the monolith only then; abort before ISO assembly on any failure. Runs the builder test suites up front. - fast-path: force a full build for a multi-layer medium; fast_path_repack_squashfs hard-refuses (it would drop layers). - iso-validation.sh: validate_iso_squashfs_layers (module vs layer set match, size ceiling, no lone giant squashfs) and validate_iso_media_integrity (xorriso -check_media). - bee-install: honour filesystem.module order, abort on any layer failure. - 9013-toram-retry: record the real rsync exit code (it printed a false rc=0) and correct the "resumes the tail" comment (rsync without --partial keeps only fully-copied layers). No unsafe partial resume. - tests: test-squashfs-layers.sh plus a multi-layer guard in test-build-libs.sh; both run at the top of every build. - docs: bible-local architecture and decision, iso/README, iso-build-rules. Verified by a full nvidia build: 7 layers 622/199/256/466/37/567/562 MiB, every validator passes, xorriso -check_media good, merged rootfs bootable. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
Mikhail Chusavitin
co-authored by
Claude Sonnet 5
Claude Sonnet 5
parent
bc57b85d3f
commit
b8c45d54c1
@@ -0,0 +1,187 @@
|
||||
#!/bin/sh
|
||||
# test-squashfs-layers.sh - regression tests for lib/squashfs-layers.sh.
|
||||
#
|
||||
# Builds a synthetic mini-rootfs, splits it, and asserts the semantic layer
|
||||
# contract holds. Requires mksquashfs / unsquashfs / rsync; skips cleanly when
|
||||
# they are not installed (e.g. on a developer macOS box).
|
||||
set -eu
|
||||
|
||||
BUILDER_DIR="$(CDPATH= cd -- "$(dirname "$0")" && pwd)"
|
||||
. "$BUILDER_DIR/lib/squashfs-layers.sh"
|
||||
|
||||
for tool in mksquashfs unsquashfs rsync; do
|
||||
command -v "$tool" >/dev/null 2>&1 || {
|
||||
echo "test-squashfs-layers: $tool not available, skipping"
|
||||
exit 0
|
||||
}
|
||||
done
|
||||
|
||||
T="$(mktemp -d)"
|
||||
trap 'rm -rf "$T"' EXIT INT TERM HUP
|
||||
ROOT="$T/root"
|
||||
|
||||
mk() { mkdir -p "$(dirname "$ROOT/$1")"; printf '%s' "${2:-x}" > "$ROOT/$1"; }
|
||||
mkbig() { mkdir -p "$(dirname "$ROOT/$1")"; head -c "${2:-1048576}" /dev/urandom > "$ROOT/$1"; }
|
||||
listf() { mkdir -p "$ROOT/var/lib/dpkg/info"; printf '%s\n' "$@" > "$ROOT/var/lib/dpkg/info/$1.list"; }
|
||||
|
||||
# --- base rootfs ---
|
||||
mk usr/lib/systemd/systemd "#!systemd"
|
||||
( cd "$ROOT/usr" && mkdir -p sbin && ln -s ../lib/systemd/systemd sbin/init )
|
||||
mk usr/local/bin/bee "#!bee"
|
||||
mk etc/hostname "easy-bee"
|
||||
mk usr/bin/true "#!true"
|
||||
mk usr/bin/dmidecode "#!dmi"
|
||||
( cd "$ROOT" && ln -s usr/bin bin && ln -s usr/bin sbin && ln -s usr/lib lib && ln -s usr/lib lib64 )
|
||||
listf base-files /etc/hostname /usr/bin/true
|
||||
listf dmidecode /usr/bin/dmidecode
|
||||
|
||||
# --- 05 firmware: non-NVIDIA device firmware. The bare "/lib" entry mimics the
|
||||
# real firmware-* .list files and must NOT drag the /lib symlink out of base.
|
||||
listf firmware-iwlwifi /lib /lib/firmware /lib/firmware/iwlwifi-cc-a0-77.ucode
|
||||
mk usr/lib/firmware/iwlwifi-cc-a0-77.ucode
|
||||
listf firmware-realtek /lib/firmware/rtl_nic/rtl8168h-2.fw
|
||||
mk usr/lib/firmware/rtl_nic/rtl8168h-2.fw
|
||||
|
||||
# --- 08 desktop ---
|
||||
listf chromium /usr/bin/chromium
|
||||
mk usr/bin/chromium "#!chromium"
|
||||
listf xserver-xorg-core /usr/bin/Xorg
|
||||
mk usr/bin/Xorg "#!Xorg"
|
||||
listf lightdm /usr/sbin/lightdm
|
||||
mk usr/sbin/lightdm "#!lightdm"
|
||||
listf libgl1-mesa-dri /usr/lib/x86_64-linux-gnu/dri/swrast_dri.so
|
||||
mk usr/lib/x86_64-linux-gnu/dri/swrast_dri.so
|
||||
listf fonts-dejavu-core /usr/share/fonts/truetype/dejavu/DejaVuSans.ttf
|
||||
mk usr/share/fonts/truetype/dejavu/DejaVuSans.ttf
|
||||
|
||||
# --- 10 driver: dpkg + injected ---
|
||||
listf firmware-nvidia-gsp /lib /lib/firmware /lib/firmware/nvidia/580.159.03/gsp_ga10x.bin
|
||||
mk usr/lib/firmware/nvidia/580.159.03/gsp_ga10x.bin
|
||||
mk usr/lib/firmware/nvidia/580.159.03/gsp_tu10x.bin
|
||||
listf nvidia-modprobe /usr/bin/nvidia-modprobe
|
||||
mk usr/bin/nvidia-modprobe
|
||||
mk usr/local/lib/nvidia/nvidia.ko
|
||||
mk usr/local/lib/nvidia/nvidia-uvm.ko
|
||||
mk usr/local/bin/nvidia-smi "#!nvidia-smi"
|
||||
mk usr/lib/libnvidia-ml.so.1
|
||||
mk usr/lib/libnvidia-ml.so.580.159.03
|
||||
mk usr/lib/libcuda.so.1
|
||||
mk etc/OpenCL/vendors/nvidia.icd "libnvidia-opencl.so.1"
|
||||
mk etc/systemd/system/bee-nvidia.service "[Unit]"
|
||||
mk usr/local/bin/bee-nvidia-load "#!load"
|
||||
|
||||
# --- 20 platform ---
|
||||
listf nvidia-fabricmanager /usr/bin/nv-fabricmanager /usr/lib/systemd/system/nvidia-fabricmanager.service
|
||||
mk usr/bin/nv-fabricmanager
|
||||
mk usr/lib/systemd/system/nvidia-fabricmanager.service "[Unit]"
|
||||
listf libnvidia-nscq /usr/lib/x86_64-linux-gnu/libnvidia-nscq.so.580.159.03
|
||||
mk usr/lib/x86_64-linux-gnu/libnvidia-nscq.so.580.159.03
|
||||
listf datacenter-gpu-manager-4-core /usr/bin/dcgmi /usr/bin/nv-hostengine
|
||||
mk usr/bin/dcgmi "#!dcgmi"
|
||||
mk usr/bin/nv-hostengine "#!nvh"
|
||||
mk etc/systemd/system/nvidia-fabricmanager.service.d/bee-nvswitch-check.conf "[Service]"
|
||||
|
||||
# --- 30 cuda libs (injected) ---
|
||||
mk usr/lib/libcudart.so.13
|
||||
mk usr/lib/libcublas.so.13
|
||||
mk usr/lib/libcublasLt.so.13
|
||||
mk usr/lib/libnccl.so.2
|
||||
mk usr/local/bin/all_reduce_perf "#!arp"
|
||||
mk usr/local/lib/bee/bee-gpu-burn-worker "#!worker"
|
||||
|
||||
# --- 40 dcgm cuda ---
|
||||
listf datacenter-gpu-manager-4-cuda13 /usr/bin/dcgmproftester12
|
||||
mkbig usr/bin/dcgmproftester12 3145728
|
||||
mk usr/local/bin/bee-dcgmproftester-staggered "#!stag"
|
||||
|
||||
# a plain "nvidia" in the path must NOT be enough on its own: an unowned,
|
||||
# unruled file under an nvidia dir stays in base.
|
||||
mk usr/share/doc/nvidia-random/README "notes"
|
||||
|
||||
fail() { echo "FAIL: $*" >&2; exit 1; }
|
||||
in_layer() { LC_ALL=C grep -qx "$2" "$WD/$1.files" || fail "expected $2 in layer $1"; }
|
||||
|
||||
MONO="$T/filesystem-v14.99.squashfs"
|
||||
mksquashfs "$ROOT" "$MONO" -comp zstd -noappend -no-progress -no-xattrs >/dev/null
|
||||
|
||||
R2="$T/r2"; unsquashfs -d "$R2" "$MONO" >/dev/null
|
||||
WD="$T/cls"
|
||||
bee_layer_classify "$R2" nvidia "$WD"
|
||||
|
||||
in_layer 00-base usr/sbin/init
|
||||
in_layer 00-base usr/lib/systemd/systemd
|
||||
in_layer 00-base usr/local/bin/bee
|
||||
in_layer 00-base etc/hostname
|
||||
in_layer 00-base usr/bin/dmidecode
|
||||
in_layer 00-base bin
|
||||
in_layer 00-base sbin
|
||||
in_layer 00-base lib
|
||||
in_layer 00-base lib64
|
||||
in_layer 05-firmware usr/lib/firmware/iwlwifi-cc-a0-77.ucode
|
||||
in_layer 05-firmware usr/lib/firmware/rtl_nic/rtl8168h-2.fw
|
||||
in_layer 08-desktop usr/bin/chromium
|
||||
in_layer 08-desktop usr/bin/Xorg
|
||||
in_layer 08-desktop usr/sbin/lightdm
|
||||
in_layer 08-desktop usr/lib/x86_64-linux-gnu/dri/swrast_dri.so
|
||||
in_layer 08-desktop usr/share/fonts/truetype/dejavu/DejaVuSans.ttf
|
||||
in_layer 10-nvidia-driver usr/local/lib/nvidia/nvidia.ko
|
||||
in_layer 10-nvidia-driver usr/local/bin/nvidia-smi
|
||||
in_layer 10-nvidia-driver usr/lib/libnvidia-ml.so.1
|
||||
in_layer 10-nvidia-driver usr/lib/libcuda.so.1
|
||||
in_layer 10-nvidia-driver usr/lib/firmware/nvidia/580.159.03/gsp_ga10x.bin
|
||||
in_layer 10-nvidia-driver etc/OpenCL/vendors/nvidia.icd
|
||||
in_layer 10-nvidia-driver etc/systemd/system/bee-nvidia.service
|
||||
in_layer 10-nvidia-driver usr/bin/nvidia-modprobe
|
||||
in_layer 20-nvidia-platform usr/bin/nv-fabricmanager
|
||||
in_layer 20-nvidia-platform usr/lib/x86_64-linux-gnu/libnvidia-nscq.so.580.159.03
|
||||
in_layer 20-nvidia-platform usr/bin/dcgmi
|
||||
in_layer 20-nvidia-platform usr/bin/nv-hostengine
|
||||
in_layer 20-nvidia-platform etc/systemd/system/nvidia-fabricmanager.service.d/bee-nvswitch-check.conf
|
||||
in_layer 30-nvidia-cuda-libs usr/lib/libcudart.so.13
|
||||
in_layer 30-nvidia-cuda-libs usr/lib/libcublasLt.so.13
|
||||
in_layer 30-nvidia-cuda-libs usr/lib/libnccl.so.2
|
||||
in_layer 30-nvidia-cuda-libs usr/local/bin/all_reduce_perf
|
||||
in_layer 30-nvidia-cuda-libs usr/local/lib/bee/bee-gpu-burn-worker
|
||||
in_layer 40-nvidia-dcgm-cuda usr/bin/dcgmproftester12
|
||||
in_layer 40-nvidia-dcgm-cuda usr/local/bin/bee-dcgmproftester-staggered
|
||||
in_layer 00-base usr/share/doc/nvidia-random/README
|
||||
|
||||
OUT="$T/out"
|
||||
bee_layer_build "$R2" "$WD" "$OUT" 14.99 nvidia
|
||||
bee_layer_verify_each "$OUT" 14.99 nvidia
|
||||
bee_layer_merge "$OUT" 14.99 nvidia "$T/merged"
|
||||
|
||||
MODLIVE="$T/live"; mkdir -p "$MODLIVE"
|
||||
cp "$OUT"/filesystem-v14.99-*.squashfs "$MODLIVE/"
|
||||
bee_layer_write_module_file "$MODLIVE" 14.99 nvidia
|
||||
expect_mod="filesystem-v14.99-00-base.squashfs
|
||||
filesystem-v14.99-05-firmware.squashfs
|
||||
filesystem-v14.99-08-desktop.squashfs
|
||||
filesystem-v14.99-10-nvidia-driver.squashfs
|
||||
filesystem-v14.99-20-nvidia-platform.squashfs
|
||||
filesystem-v14.99-30-nvidia-cuda-libs.squashfs
|
||||
filesystem-v14.99-40-nvidia-dcgm-cuda.squashfs"
|
||||
[ "$(cat "$MODLIVE/filesystem.module")" = "$expect_mod" ] || fail "module file order wrong"
|
||||
|
||||
# --- failure modes ---
|
||||
# missing layer -> merge fails
|
||||
rm -f "$OUT/filesystem-v14.99-20-nvidia-platform.squashfs"
|
||||
if bee_layer_merge "$OUT" 14.99 nvidia "$T/m2" >/dev/null 2>&1; then
|
||||
fail "merge succeeded with a missing layer"
|
||||
fi
|
||||
bee_layer_build "$R2" "$WD" "$OUT" 14.99 nvidia >/dev/null # restore
|
||||
|
||||
# size ceiling -> build fails
|
||||
if BEE_LAYER_MAX_MIB=0 bee_layer_build "$R2" "$WD" "$T/out0" 14.99 nvidia >/dev/null 2>&1; then
|
||||
fail "build ignored the size ceiling"
|
||||
fi
|
||||
|
||||
# incomplete partition -> classify fails
|
||||
rm -rf "$WD"; bee_layer_classify "$R2" nvidia "$WD"
|
||||
echo "usr/bin/does-not-exist" >> "$WD/10-nvidia-driver.files"
|
||||
_total=$(wc -l < "$WD/all.files")
|
||||
_sum=0
|
||||
for s in $(bee_layer_slugs_for_variant nvidia); do _sum=$((_sum + $(wc -l < "$WD/$s.files"))); done
|
||||
[ "$_sum" -ne "$_total" ] || fail "tampered partition should not still sum to the tree size"
|
||||
|
||||
echo "squashfs layer tests: OK"
|
||||
Reference in New Issue
Block a user