19 Commits

Author SHA1 Message Date
Mikhail Chusavitin
c850b39b01 feat: v3.10 GPU stress and NCCL burn updates 2026-03-31 11:22:27 +03:00
Mikhail Chusavitin
6dee8f3509 Add NVIDIA stress loader selection and DCGM 4 support 2026-03-31 11:15:15 +03:00
09fe0e2e9e feat(iso): add nogpu variant (no NVIDIA, no AMD/ROCm)
- build.sh: accept --variant nogpu; skips all GPU build steps, removes
  both nvidia-cuda and rocm archives, strips bee-nvidia-load and
  bee-nvidia.service from overlay
- build-in-container.sh: add nogpu to --variant flag; all variant
  includes nogpu; --clean-build wipes live-build-work-nogpu
- 9000-bee-setup hook: nogpu path enables no GPU services
- bee-nogpu.list.chroot: empty GPU package list

Output: easy-bee-nogpu-vX.iso

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-30 22:49:25 +03:00
ace1a9dba6 feat(iso): split into nvidia and amd variants, fix KVM graphics and PATH
- build.sh: add --variant nvidia|amd; separate work dirs per variant
  (live-build-work-nvidia / live-build-work-amd); GPU-specific steps
  (modules, NCCL, cuBLAS, nccl-tests) run only for nvidia; deb package
  cache synced back to shared location after each lb build so second
  variant reuses downloaded packages; ISO output named
  easy-bee-{variant}-v{ver}-amd64.iso
- build-in-container.sh: add --variant nvidia|amd|all (default: all);
  runs build.sh twice in one container for 'all'; --clean-build wipes
  both variant work dirs
- package-lists: remove GPU packages from bee.list.chroot; add
  bee-nvidia.list.chroot (DCGM) and bee-amd.list.chroot (ROCm)
- 9000-bee-setup hook: read /etc/bee-gpu-vendor; enable bee-nvidia.service
  and DCGM only for nvidia; set up ROCm symlinks only for amd
- auto/config: --iso-volume uses BEE_GPU_VENDOR_UPPER env var
- grub.cfg: add nomodeset to EASY-BEE and EASY-BEE (load to RAM) entries
  — fixes X/lightdm on BMC KVM (ASPEED AST chip requires nomodeset for
  fbdev to work; NVIDIA H100 compute does not need KMS)
- bee.sh / smoketest.sh: add /usr/sbin to PATH so dmidecode, smartctl,
  nvme are found
- 9100-memtest hook: add diagnostic listing of chroot/boot/memtest* files

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-30 22:24:37 +03:00
889fe1dc2f fix: IPMI access for bee user + remove chart legend
- Add udev rule: /dev/ipmi0 readable by 'ipmi' group (no sudo needed)
- Add 'ipmi' group creation and bee user membership in chroot hook
- Remove legend from all charts (data shown in GPU table below)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-29 11:03:35 +03:00
a03312c286 feat: AMD GPU compute stress via rocm-validation-suite GST (GEMM)
- Add rocm-validation-suite, rocblas, rocrand, hip-runtime-amd,
  hipblaslt, comgr to ISO (~700MB, needed for HIP compute)
- RunAMDStressPack: run RVS GST (SGEMM ~31 TFLOPS/GPU) + bandwidth test
- Add rvs symlink in chroot setup hook
- Pin all new package versions in VERSIONS

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-29 10:56:32 +03:00
e69e9109da fix(iso): set bash as default shell for bee user
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-29 10:49:18 +03:00
413869809d feat(iso): add rocm-bandwidth-test for AMD GPU burn-in
- Add rocm-bandwidth-test package to ISO
- Add bee user to 'render' group (/dev/kfd, /dev/dri/renderD* access)
- Add rocm-bandwidth-test symlink alongside rocm-smi

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-29 10:48:29 +03:00
911745e4da refactor(iso): replace chroot hooks for DCGM/ROCm with live-build apt sources
Move datacenter-gpu-manager and rocm-smi-lib from dynamic chroot hooks
into live-build's config/archives mechanism so lb caches the .deb files
in cache/packages.chroot/ between builds, eliminating repeated 900+ MB
downloads. Versions pinned via VERSIONS and substituted into package
lists at build time.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-28 13:01:10 +03:00
883592d029 feat(desktop): switch to LightDM for X startup (matches Ubuntu LiveCD)
startx from user shell has /dev/fb0 permission issues and is fragile.
LightDM starts Xorg as root — standard LiveCD approach that works
on server hardware / IPMI KVM with nomodeset + fbdev/vesa.

- Add lightdm package, configure autologin as bee/openbox session
- Add /usr/share/xsessions/openbox.desktop
- Remove startx from .profile (LightDM manages X lifecycle)
- Remove Xwrapper.config needs_root_rights workaround (no longer needed)
- Enable lightdm.service in setup hook

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-27 22:17:59 +03:00
a6dcaf1c7e fix(desktop): fix X permissions for server hardware (IPMI KVM)
- Add bee user to video,input groups (fixes /dev/fb0 permission denied)
- Add Xwrapper.config: needs_root_rights=yes (X gets hw access)
- Add xserver-xorg-video-vesa as fallback driver
- Remove dead bee-tui chmod from setup hook

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-27 22:07:25 +03:00
eea98e6d76 feat(dcgm): add NVIDIA DCGM diagnostics, fix KVM console
- Add 9002-nvidia-dcgm.hook.chroot: installs datacenter-gpu-manager
  from NVIDIA apt repo during live-build
- Enable nvidia-dcgm.service in chroot setup hook
- Replace bee-gpu-stress with dcgmi diag (levels 1-4) in NVIDIA SAT
- TUI: replace GPU checkbox + duration UI with DCGM level selection
- Remove console=tty2 from boot params: KVM/VGA now shows tty1
  where bee-tui runs, fixing unresponsive console

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-26 23:08:12 +03:00
Mikhail Chusavitin
d36e8442a9 Stabilize live ISO consoles and NVIDIA boot path 2026-03-25 19:05:18 +03:00
Mikhail Chusavitin
b25a2f6d30 feat: add support bundle and raw audit export 2026-03-16 18:20:26 +03:00
Mikhail Chusavitin
72cf482ad3 Embed Reanimator Chart web viewer 2026-03-15 22:07:42 +03:00
Mikhail Chusavitin
e32fa6e477 Use live-config autologin for bee user 2026-03-14 08:33:36 +03:00
Mikhail Chusavitin
caeafa836b Improve VM boot diagnostics and guest support 2026-03-14 07:51:16 +03:00
Mikhail Chusavitin
6aca1682b9 Refactor bee CLI and LiveCD integration 2026-03-13 16:52:16 +03:00
Mikhail Chusavitin
345a93512a migrate ISO build from Alpine to Debian 12 (Bookworm)
Replace the entire live CD build pipeline:
- Alpine SDK + mkimage + genapkovl → Debian live-build (lb config/build)
- OpenRC init scripts → systemd service units
- dropbear → openssh-server (native to Debian live)
- udhcpc → dhclient for DHCP
- apk → apt-get in setup-builder.sh and build-nvidia-module.sh
- Add auto/config (lb config options) and auto/build wrapper
- Add config/package-lists/bee.list.chroot replacing Alpine apks
- Add config/hooks/normal/9000-bee-setup.hook.chroot to enable services
- Add bee-nvidia-load and bee-sshsetup helper scripts
- Keep NVIDIA pre-compile pipeline (Option B): compile on builder VM against
  pinned Debian kernel headers (DEBIAN_KERNEL_ABI), inject .ko into includes.chroot
- Fixes: native glibc (no gcompat shims), proper udev, writable /lib/modules,
  no Alpine modloop read-only constraint, no stale apk cache issues

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-08 18:01:38 +03:00