vh
46276611a7
draupnir review: the remote job dir was keyed on the basename alone, so two local dirs with the same name shared one remote dir, and a rerun inherited stale files. The dir is now <basename>-<8 hex of sha256(abs path)>, and it is mirrored with rsync --delete, confined to that one directory. There is no rm on a computed path. Verified: a file deleted locally is gone from the rerun's remote dir. The /defaults stderr line is documented as harmless noise.
75 lines
3.7 KiB
Bash
Executable File
75 lines
3.7 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# blender-run — one-shot HEADLESS Blender on fv-ml1 GPU 3, for scripted/CLI callers (draupnir etc.).
|
|
# The agent-driven, interactive path is scripts/blender-mcp; this is the batch path.
|
|
#
|
|
# scripts/blender-run [--job DIR] -- <blender args after -b>
|
|
# scripts/blender-run --job /mnt/smithy/draupnir/j42 -- --python render.py -- --out out.png
|
|
# scripts/blender-run -- --python-expr 'import bpy; print(bpy.app.version_string)'
|
|
#
|
|
# Each call is its own `docker run --rm` of the stacks/blender image (Blender 5.2.2 LTS, Python
|
|
# 3.13): no desktop, no MCP socket, gone when Blender exits. So it never collides with the on-demand
|
|
# GUI container, and GPU 3 goes back to 0 when the render ends. Always added: `-b --factory-startup
|
|
# --python-exit-code 1`. Without that last flag, Blender exits 0 even when a --python script raises
|
|
# (measured).
|
|
#
|
|
# ⚠ Give render.filepath an ABSOLUTE path (os.path.abspath). Blender does not resolve a relative
|
|
# output path against the working directory: "cannot save 'out.png'". Python file I/O and
|
|
# importers do use the cwd.
|
|
#
|
|
# Files: fv-ml1 does NOT mount /mnt/smithy. With --job DIR, DIR is mirrored to
|
|
# fv-ml1:/tank/blender/jobs/<basename>-<hash of DIR's absolute path>/, Blender runs WITH THAT AS ITS
|
|
# WORKING DIRECTORY, and new or changed files are copied back into DIR afterwards (nothing is ever
|
|
# deleted locally). Use relative paths inside the job. Running the SAME DIR twice concurrently
|
|
# still shares one remote dir, so don't do that. Remote job dirs are never swept: one copy is kept
|
|
# per distinct DIR (small files, on /tank). Without --job, the only paths Blender sees are under
|
|
# /work (= fv-ml1:/tank/blender).
|
|
#
|
|
# Budget: GPU 3 (96 GB, borrowed from the vLLM reserve: this ends if a full-size seat moves in).
|
|
# The container is capped at 64 GB RAM / 48 CPUs so a runaway render cannot starve the inference
|
|
# seats on the same host.
|
|
set -euo pipefail
|
|
|
|
HOST=${BLENDER_SSH_HOST:-infra-ops@10.251.50.54}
|
|
ENV_FILE=/opt/docker/compose/blender/.env
|
|
JOB=""
|
|
while [ $# -gt 0 ]; do
|
|
case "$1" in
|
|
--job) JOB=${2:?--job needs a directory}; shift 2 ;;
|
|
--) shift; break ;;
|
|
-h|--help) sed -n 2,23p "$0"; exit 0 ;;
|
|
*) echo "blender-run: unknown option $1 (blender args go after --)" >&2; exit 2 ;;
|
|
esac
|
|
done
|
|
|
|
WORKDIR=/work
|
|
if [ -n "$JOB" ]; then
|
|
[ -d "$JOB" ] || { echo "blender-run: --job $JOB is not a directory" >&2; exit 2; }
|
|
ABS=$(realpath "$JOB")
|
|
BASE=$(basename "$ABS")
|
|
[[ $BASE =~ ^[A-Za-z0-9._-]+$ ]] || { echo "blender-run: job dir name '$BASE' must be [A-Za-z0-9._-]" >&2; exit 2; }
|
|
# Keyed on basename + a hash of the ABSOLUTE local path (draupnir, 2026-09-28): two different
|
|
# dirs that share a basename no longer share a remote dir. `--delete` makes the remote an exact
|
|
# mirror of DIR, so a rerun never inherits an earlier run's leftovers. rsync removes only
|
|
# inside that one remote dir; there is no rm on a computed path.
|
|
NAME=$BASE-$(printf '%s' "$ABS" | sha256sum | cut -c1-8)
|
|
ssh -n -o BatchMode=yes "$HOST" "mkdir -p /tank/blender/jobs/$NAME"
|
|
rsync -a --delete "$JOB"/ "$HOST:/tank/blender/jobs/$NAME/"
|
|
WORKDIR=/work/jobs/$NAME
|
|
fi
|
|
|
|
# Arguments travel as one shell-quoted string: ssh flattens argv into a remote command line.
|
|
ARGS=$(printf '%q ' "$@")
|
|
set +e
|
|
ssh -n -o BatchMode=yes "$HOST" "IMG=\$(grep '^IMAGE=' $ENV_FILE | cut -d= -f2) && \
|
|
exec docker run --rm --name blender-run-\$\$ --runtime nvidia \
|
|
-e NVIDIA_VISIBLE_DEVICES=3 -e NVIDIA_DRIVER_CAPABILITIES=all \
|
|
--user 1002:1003 -e HOME=/tmp --memory 64g --cpus 48 \
|
|
-v /tank/blender:/work -w $WORKDIR --entrypoint /blender/blender \"\$IMG\" \
|
|
-b --factory-startup --python-exit-code 1 $ARGS"
|
|
RC=$?
|
|
set -e
|
|
if [ -n "$JOB" ]; then
|
|
rsync -a --update "$HOST:/tank/blender/jobs/$NAME/" "$JOB"/
|
|
fi
|
|
exit $RC
|