Frank
56fc899763
The RDNA4 offload campaign left three HIP probes and a driver sitting loose in $HOME, where the next agent cannot find them and a stray `rm -rf` ends them. They answer a recurring question on the R9700 box — is decode limited by the link or by the engine's read path — so they move into scripts/probes/ with a driver, tests, and a page. Two things changed in the code, not just the address: - The driver measures only after a guard that runs BEFORE anything is built: gpu_busy_percent over PCIE_PROBE_MAX_BUSY, or any process holding /dev/kfd, is a refusal (exit 3) rather than a measurement. A benchmark taken beside a live endpoint is both disruptive and worthless, and silently unloading a production service is not a tool's decision — --force is the human saying otherwise. The refusal-before-build ordering is pinned by a test, because the sysfs and kfd paths are overridable and a refusal is otherwise untestable off the card box. - hip_smoke.hip and pcie_probe.hip called hipGetDeviceProperties, which SEGFAULTS on this ROCm build even though hipGetDeviceCount works; only pcie_bw.hip avoided it, and that is the one that produced the campaign's numbers. Device identity now comes from the sysfs topology block the driver prints, so all three probes are runnable on the build we ship. Verified here: refusal on a real busy APU (exit 3), missing toolchain (exit 4), missing sources (exit 2). Compile-and-run still needs the box with hipcc. Refs #53
145 lines
5.0 KiB
Bash
Executable File
145 lines
5.0 KiB
Bash
Executable File
#!/usr/bin/env bats
|
|
# tests/pcie-probe.bats — black-box tests for scripts/pcie-probe.sh (Refs #53)
|
|
#
|
|
# Contract: measure host→device bandwidth on an RDNA4 box, and refuse to measure while the GPU is
|
|
# in use. Fleet law: never benchmark beside a live service — so the guard runs BEFORE anything is
|
|
# built or run, and the tool stops nothing and starts nothing (auto-stopping a production service is
|
|
# the thing it must not do unasked).
|
|
#
|
|
# Exit status: 0 measured · 2 usage · 3 refused (GPU busy) · 4 no toolchain / build failed.
|
|
#
|
|
# hipcc and the compiled probes are stubbed: this box has no HIP SDK (it is a client laptop) and a
|
|
# real measurement belongs on a machine with the cards, beside no running model.
|
|
|
|
setup() {
|
|
TEST_TMP="$(mktemp -d)"
|
|
SCRIPT="$BATS_TEST_DIRNAME/../scripts/pcie-probe.sh"
|
|
SRC="$TEST_TMP/src"
|
|
BUILD="$TEST_TMP/build"
|
|
SYSFS="$TEST_TMP/drm"
|
|
BIN="$TEST_TMP/bin"
|
|
mkdir -p "$SRC" "$BUILD" "$BIN" "$SYSFS/card0/device" "$SYSFS/card1/device"
|
|
|
|
# Fixtures stand in for the real sysfs files the driver reads.
|
|
printf '8\n' > "$SYSFS/card0/device/current_link_width"
|
|
printf '32.0 GT/s PCIe\n' > "$SYSFS/card0/device/current_link_speed"
|
|
printf '16\n' > "$SYSFS/card0/device/max_link_width"
|
|
printf '32.0 GT/s PCIe\n' > "$SYSFS/card0/device/max_link_speed"
|
|
printf '0\n' > "$SYSFS/card0/device/gpu_busy_percent"
|
|
printf '8\n' > "$SYSFS/card1/device/current_link_width"
|
|
printf '32.0 GT/s PCIe\n' > "$SYSFS/card1/device/current_link_speed"
|
|
printf '16\n' > "$SYSFS/card1/device/max_link_width"
|
|
printf '32.0 GT/s PCIe\n' > "$SYSFS/card1/device/max_link_speed"
|
|
printf '0\n' > "$SYSFS/card1/device/gpu_busy_percent"
|
|
|
|
# Probe sources: the real .hip files are shipped by the script's own directory, so the fixtures
|
|
# only need to exist for the build step to be invoked.
|
|
: > "$SRC/pcie_probe.hip"; : > "$SRC/pcie_bw.hip"; : > "$SRC/hip_smoke.hip"
|
|
|
|
# Stub toolchain: records that it was called, and emits a probe binary that records that IT ran.
|
|
cat > "$BIN/hipcc" <<'STUB'
|
|
#!/usr/bin/env bash
|
|
[ "${STUB_HIPCC_FAILS:-0}" = 1 ] && { echo "stub: no matching GPU target" >&2; exit 1; }
|
|
out=""
|
|
while [ $# -gt 0 ]; do [ "$1" = "-o" ] && out="$2"; shift; done
|
|
[ -n "$out" ] || exit 2
|
|
: > "$PCIE_PROBE_BUILD/.built"
|
|
{ echo '#!/usr/bin/env bash'
|
|
echo ': > "$PCIE_PROBE_BUILD/.ran"'
|
|
echo 'echo "PROBE RAN dev=${HIP_VISIBLE_DEVICES:-none} bin=$(basename "$0")"'
|
|
echo 'echo " slab 2.344 MiB: 31.4 GB/s"'
|
|
} > "$out"
|
|
chmod +x "$out"
|
|
STUB
|
|
cat > "$BIN/fuser" <<'STUB'
|
|
#!/usr/bin/env bash
|
|
[ -n "${STUB_KFD_PIDS:-}" ] && printf '%s\n' $STUB_KFD_PIDS
|
|
exit 0
|
|
STUB
|
|
chmod +x "$BIN/hipcc" "$BIN/fuser"
|
|
|
|
export PATH="$BIN:$PATH" PCIE_PROBE_SRC="$SRC" PCIE_PROBE_BUILD="$BUILD" \
|
|
PCIE_PROBE_SYSFS="$SYSFS" PCIE_PROBE_KFD="$TEST_TMP/kfd" PCIE_PROBE_HIPCC="$BIN/hipcc"
|
|
: > "$TEST_TMP/kfd"
|
|
}
|
|
|
|
teardown() { rm -rf "$TEST_TMP"; }
|
|
|
|
@test "a missing HIP toolchain is a loud failure, not a silent skip" {
|
|
run env PCIE_PROBE_HIPCC="$TEST_TMP/nope-hipcc" "$SCRIPT"
|
|
[ "$status" -eq 4 ]
|
|
[[ "$output" == *"hip"* ]]
|
|
[ ! -e "$BUILD/.built" ]
|
|
}
|
|
|
|
@test "a failed build is reported as a failure" {
|
|
run env STUB_HIPCC_FAILS=1 "$SCRIPT"
|
|
[ "$status" -eq 4 ]
|
|
[[ "$output" == *"build"* ]]
|
|
}
|
|
|
|
@test "a GPU held by another process refuses the measurement before anything is built" {
|
|
# Order is the contract: build-and-then-ask would already have loaded the card beside a live
|
|
# service. The .built marker proves the guard ran first.
|
|
run env STUB_KFD_PIDS="4242" "$SCRIPT"
|
|
[ "$status" -eq 3 ]
|
|
[[ "$output" == *"busy"* ]]
|
|
[ ! -e "$BUILD/.built" ]
|
|
}
|
|
|
|
@test "a busy GPU percent refuses too" {
|
|
printf '91\n' > "$SYSFS/card0/device/gpu_busy_percent"
|
|
run "$SCRIPT"
|
|
[ "$status" -eq 3 ]
|
|
[[ "$output" == *"card0"* ]]
|
|
[ ! -e "$BUILD/.built" ]
|
|
}
|
|
|
|
@test "--force overrides the guard for a deliberately contended measurement" {
|
|
run env STUB_KFD_PIDS="4242" "$SCRIPT" --force
|
|
[ "$status" -eq 0 ]
|
|
[ -e "$BUILD/.ran" ]
|
|
}
|
|
|
|
@test "an idle GPU builds and runs the probe" {
|
|
run "$SCRIPT"
|
|
[ "$status" -eq 0 ]
|
|
[ -e "$BUILD/.built" ]
|
|
[ -e "$BUILD/.ran" ]
|
|
[[ "$output" == *"PROBE RAN"* ]]
|
|
[[ "$output" == *"31.4 GB/s"* ]] # probe output passes through untouched
|
|
}
|
|
|
|
@test "--build-only compiles without touching the card" {
|
|
run "$SCRIPT" --build-only
|
|
[ "$status" -eq 0 ]
|
|
[ -e "$BUILD/.built" ]
|
|
[ ! -e "$BUILD/.ran" ]
|
|
}
|
|
|
|
@test "the link topology is reported from sysfs, current against max" {
|
|
run "$SCRIPT"
|
|
[[ "$output" == *"card0"*"x8"*"32.0 GT/s"* ]]
|
|
[[ "$output" == *"max x16"* ]]
|
|
}
|
|
|
|
@test "each requested device is measured separately" {
|
|
# One shared run cannot attribute bandwidth to a card; the whole point is per-card numbers.
|
|
run "$SCRIPT" --device 0 --device 1
|
|
[ "$status" -eq 0 ]
|
|
[[ "$output" == *"dev=0"* ]]
|
|
[[ "$output" == *"dev=1"* ]]
|
|
}
|
|
|
|
@test "no probe sources is a usage-level error, not an empty success" {
|
|
rm -f "$SRC"/*.hip
|
|
run "$SCRIPT"
|
|
[ "$status" -ne 0 ]
|
|
[[ "$output" == *"probe"* ]]
|
|
}
|
|
|
|
@test "an unknown flag is a usage error" {
|
|
run "$SCRIPT" --frobnicate
|
|
[ "$status" -eq 2 ]
|
|
}
|