fix(frank-dragoon): mount the distro XRT at the third prefix the NPU child searches

The lane's child dlopens libxrt_core.so.2 from /opt/xilinx/lib/<multiarch>/
as well; our mounts filled only /opt/xilinx/xrt/lib and the install path.
Since the host's libxrt2 was reconfigured 2026-10-20 the child dies naming
the missing prefix ('No such library
/opt/xilinx/lib/x86_64-linux-gnu/libxrt_core.so.2') and the engine
supervisor takes the WHOLE container down on a dead lane — measured
2026-10-21: frank-dragoon boot-looped 88 times with chat dead while the
GPU lines looked healthy.

Each XRT library now mounts THREE times from the same real file (never a
symlink); the multiarch name derives from FRANK_DRAGOON_XRT_DIR's basename
so the bats fixture proves the derivation. Proven end-to-end before commit:
production-shaped scratch boot + the three extra mounts answers the full
boot ledger, npu_api buckets u0..u9, and /health ok at the 262144 ceiling.

A dead lane is not survivable on this engine — arm it only with all three
prefixes (page law updated).
This commit is contained in:
Frank committed 2026-10-21 02:21:53 -07:00
1 parent 688928d489
commit c6e2887f94
4 files changed
+48 -23

No files matched your search

+19 -11
View File
@@ -430,9 +430,12 @@ npu_fixture() {
# the stock root:render 0660 mode, and the serve gate checks exactly that.
touch "$TEST_TMP/accel0"
chmod 666 "$TEST_TMP/accel0"
mkdir -p "$TEST_TMP/xrt"
# basename carries a multiarch shape: the third mount prefix is derived
# from the XRT dir's basename (the NPU child searches
# /opt/xilinx/lib/<multiarch>/, measured 2026-10-21).
mkdir -p "$TEST_TMP/x86_64-linux-gnu"
for l in libxrt_coreutil.so.2 libxrt_core.so.2 libxrt_driver_xdna.so.2; do
touch "$TEST_TMP/xrt/$l"
touch "$TEST_TMP/x86_64-linux-gnu/$l"
done
mkdir -p "$TEST_TMP/npu/qwen3-embedding-0.6b/devices"
mkdir -p "$TEST_TMP/sys/class/drm/card1/device"
@@ -442,7 +445,7 @@ npu_fixture() {
"HALOGEN_NPU_MODELS=qwen3-embedding-0.6b"
"FRANK_DRAGOON_NPU_DIR=$TEST_TMP/npu"
"FRANK_DRAGOON_DEV_ACCEL=$TEST_TMP/accel0"
"FRANK_DRAGOON_XRT_DIR=$TEST_TMP/xrt"
"FRANK_DRAGOON_XRT_DIR=$TEST_TMP/x86_64-linux-gnu"
"FRANK_DRAGOON_SYSFS=$TEST_TMP/sys"
)
}
@@ -472,11 +475,15 @@ $(cat "$TEST_TMP/serve.log")"
! grep -q 'accel0' "$TEST_TMP/serve.log"
}
@test "the lane arms the accel node, the staged model dir and each XRT library twice" {
# Each library mounts at the image's XRT path AND at its own path: the
# distro libraries find each other where they were installed, and an
# /opt/xilinx/xrt of symlinks into the system dir dangles inside the
# container (the vendor calls that out by name).
@test "the lane arms the accel node, the staged model dir and each XRT library three times" {
# Each library mounts at the image's XRT path, at its own path (the distro
# libraries find each other where they were installed), and at
# /opt/xilinx/lib/<multiarch>/ — the prefix the NPU child searches and
# names when it is missing (`No such library
# '/opt/xilinx/lib/x86_64-linux-gnu/libxrt_core.so.2'`, measured
# 2026-10-21: the lane died and the supervisor took the whole container
# with it, 88-restart loop). An /opt/xilinx/xrt of symlinks into the
# system dir dangles inside the container (the vendor calls that out).
podman_stub
good_env
npu_fixture
@@ -491,8 +498,9 @@ $(cat "$TEST_TMP/serve.log")"
[[ "$output" != *":/models/npu"* ]]
[[ "$output" == *"-e HALOGEN_NPU_MODELS=qwen3-embedding-0.6b"* ]]
for l in libxrt_coreutil.so.2 libxrt_core.so.2 libxrt_driver_xdna.so.2; do
[[ "$output" == *"-v $TEST_TMP/xrt/$l:/opt/xilinx/xrt/lib/$l:ro"* ]]
[[ "$output" == *"-v $TEST_TMP/xrt/$l:$TEST_TMP/xrt/$l:ro"* ]]
[[ "$output" == *"-v $TEST_TMP/x86_64-linux-gnu/$l:/opt/xilinx/xrt/lib/$l:ro"* ]]
[[ "$output" == *"-v $TEST_TMP/x86_64-linux-gnu/$l:$TEST_TMP/x86_64-linux-gnu/$l:ro"* ]]
[[ "$output" == *"-v $TEST_TMP/x86_64-linux-gnu/$l:/opt/xilinx/lib/x86_64-linux-gnu/$l:ro"* ]]
done
# The Flash payload still rides the same container: the lane is additive.
[[ "$output" == *"-e HALOGEN_CHECKPOINT=/models/qwen.hgn"* ]]
@@ -567,7 +575,7 @@ $(cat "$TEST_TMP/serve.log")"
podman_stub
good_env
npu_fixture
rm "$TEST_TMP/xrt/libxrt_driver_xdna.so.2"
rm "$TEST_TMP/x86_64-linux-gnu/libxrt_driver_xdna.so.2"
run_with_log
[ "$status" -ne 0 ]
[[ "$output" == *"libxrt_driver_xdna.so.2 missing"* ]]