Skip to content

[CI] Import the DCGM exporter via enroot registry syntax / 用 enroot registry 语法导入 DCGM exporter #2735

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
edwingao28 wants to merge 2 commits into
base: main
Choose a base branch
from
+19 −3
Open

[CI] Import the DCGM exporter via enroot registry syntax / 用 enroot registry 语法导入 DCGM exporter #2735

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
dbea7ea
fix(ci): import the DCGM exporter via enroot registry syntax
edwingao28 Aug 26, 2026
800c874
fix(ci): keep the plain exporter ref where enroot_uri_for_image converts
edwingao28 Aug 26, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion runners/launch_gb300-nv.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,12 +180,14 @@ POWER_SRT_SLURM_PIN="6fc1bed01a0b82dae0088a105c03ce0cfb353443"

if [[ "$USES_DCGM_POWER" == "1" ]]; then
DCGM_EXPORTER_IMAGE="nvcr.io/nvidia/k8s/dcgm-exporter:4.6.0-4.8.3-distroless"
# enroot resolves bare paths against Docker Hub; nvcr.io pulls need the registry# form
DCGM_EXPORTER_ENROOT_REF="${DCGM_EXPORTER_IMAGE/nvcr.io\//nvcr.io#}"
DCGM_EXPORTER_SQSH="/data/home/sa-shared/gharunners/squash/$(echo "$DCGM_EXPORTER_IMAGE" | sed 's/[\/:@#]/_/g').sqsh"
# Note (wenyao): import_squash treats an existing unsquashfs-valid file
# as a cache hit but does not re-validate a fresh import, so check
# explicitly — on a compute node, like the import itself (login node is
# x86, nodes aarch64).
import_squash "$DCGM_EXPORTER_SQSH" "$DCGM_EXPORTER_IMAGE"
import_squash "$DCGM_EXPORTER_SQSH" "$DCGM_EXPORTER_ENROOT_REF"
test -r "$DCGM_EXPORTER_SQSH" || { echo "Error: DCGM exporter squash not readable: $DCGM_EXPORTER_SQSH" >&2; exit 1; }
srun --account="$SLURM_ACCOUNT" --partition="$SLURM_PARTITION" --exclusive --time=30 bash -c "unsquashfs -l \"$DCGM_EXPORTER_SQSH\" > /dev/null" || { echo "Error: DCGM exporter squash invalid: $DCGM_EXPORTER_SQSH" >&2; exit 1; }
sha256sum "$DCGM_EXPORTER_SQSH" > "$GITHUB_WORKSPACE/exporter-image.sha256"
Expand Down
4 changes: 3 additions & 1 deletion runners/launch_h200-dgxc-slurm.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -207,6 +207,8 @@ if [[ "$IS_MULTINODE" == "true" ]]; then

if [[ "$USES_DCGM_POWER" == "1" ]]; then
DCGM_EXPORTER_IMAGE="nvcr.io/nvidia/k8s/dcgm-exporter:4.6.0-4.8.3-distroless"
# enroot resolves bare paths against Docker Hub; nvcr.io pulls need the registry# form
DCGM_EXPORTER_ENROOT_REF="${DCGM_EXPORTER_IMAGE/nvcr.io\//nvcr.io#}"
DCGM_EXPORTER_SQSH="/data/gharunners/containers/$(echo "$DCGM_EXPORTER_IMAGE" | sed 's/[\/:@#]/_/g').sqsh"
if ! unsquashfs -l "$DCGM_EXPORTER_SQSH" >/dev/null 2>&1; then
DCGM_EXPORTER_LOCK="${DCGM_EXPORTER_SQSH}.lock"
Expand All @@ -223,7 +225,7 @@ if [[ "$IS_MULTINODE" == "true" ]]; then
rm -f \"$DCGM_EXPORTER_SQSH\"
export ENROOT_CACHE_PATH=\${HOME}/.cache/enroot
mkdir -p \"\$ENROOT_CACHE_PATH\"
enroot import -o \"$DCGM_EXPORTER_SQSH\" docker://$DCGM_EXPORTER_IMAGE
enroot import -o \"$DCGM_EXPORTER_SQSH\" \"docker://$DCGM_EXPORTER_ENROOT_REF\"
"
fi
test -r "$DCGM_EXPORTER_SQSH" || { echo "Error: DCGM exporter squash is not readable: $DCGM_EXPORTER_SQSH" >&2; exit 1; }
Expand Down
6 changes: 5 additions & 1 deletion utils/test_gb200_power_official_contract.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,7 +87,6 @@ def assert_pinned_clone_contract(launcher):

def assert_exporter_provisioning(launcher):
assert f'DCGM_EXPORTER_IMAGE="{EXPORTER_IMAGE}"' in launcher
assert 'import_squash "$DCGM_EXPORTER_SQSH" "$DCGM_EXPORTER_IMAGE"' in launcher
assert 'test -r "$DCGM_EXPORTER_SQSH"' in launcher
assert (
'sha256sum "$DCGM_EXPORTER_SQSH" > "$GITHUB_WORKSPACE/exporter-image.sha256"'
Expand Down Expand Up @@ -130,6 +129,11 @@ def test_launcher_detects_power_lane_from_recipe():
def test_launcher_provisions_exporter_through_squash_dir_cache():
launcher = GB200_LAUNCHER.read_text()
assert_exporter_provisioning(launcher)
# import_squash routes through enroot_uri_for_image, which already emits
# the registry# form for nvcr.io refs — pass the plain image, not a
# pre-converted ref, or the helper double-parses it.
assert 'import_squash "$DCGM_EXPORTER_SQSH" "$DCGM_EXPORTER_IMAGE"' in launcher
assert 'enroot_uri=$(enroot_uri_for_image "$image")' in launcher
assert 'DCGM_EXPORTER_SQSH="${SQUASH_DIR}/' in launcher
assert 'unsquashfs -l "$DCGM_EXPORTER_SQSH"' in launcher

Expand Down
8 changes: 8 additions & 0 deletions utils/test_gb300_power_official_contract.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -187,6 +187,14 @@ def test_launcher_detects_power_lane_from_recipe():
def test_launcher_provisions_exporter_through_shared_squash_path():
launcher = LAUNCHER_PATH.read_text()
assert_exporter_provisioning(launcher)
# This import_squash passes docker://$image straight to enroot, which
# resolves bare paths against Docker Hub — the nvcr.io pull needs the
# pre-converted registry# ref.
assert (
'DCGM_EXPORTER_ENROOT_REF="${DCGM_EXPORTER_IMAGE/nvcr.io\\//nvcr.io#}"'
in launcher
)
assert 'import_squash "$DCGM_EXPORTER_SQSH" "$DCGM_EXPORTER_ENROOT_REF"' in launcher
# No SQUASH_DIR var here; the /data/ mount avoids the /home NFS ELOOP bug.
assert 'DCGM_EXPORTER_SQSH="/data/home/sa-shared/gharunners/squash/' in launcher
assert 'srun --account="$SLURM_ACCOUNT" --partition="$SLURM_PARTITION" --exclusive --time=180' in launcher
Expand Down