Skip to content

Conversation

@tkatila
Copy link
Contributor

@tkatila tkatila commented Nov 19, 2025

  • Some cleanup (remove unused NFD consts)
  • Updates to levelzero components
  • More temperature limit options
  • Container size optimization for gpu_levelzero

Fixes #2166

Signed-off-by: Tuomas Katila <tuomas.katila@intel.com>
@tkatila tkatila requested a review from eero-t November 19, 2025 11:42
Copy link
Contributor

@eero-t eero-t left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Some nits / comments.

apt-get update && apt-get install --no-install-recommends -y ocl-icd-libopencl1 && \N
rm /runtime/level-zero-devel_*.deb && \N
cd /runtime && dpkg -i *.deb && rm -rf /runtime && \N
apt-get update && apt-get install --no-install-recommends -y ocl-icd-libopencl1 wget ca-certificates && \N
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I suspect the main size reduction from this duplication comes actually from removing the accidentally left (large) downloaded deb files, not from dropping l0-dev, wget, certs & their deps. Did you check that?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It mainly comes from this:
COPY --from=builder /runtime /runtime
The runtime deb packages are copied from the build to the final phase, and while they are removed after the install the copy creates a large unnecessary layer. This is evident if you open the container in dive.

Would be nice if one could install packages directly from the build phase.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

docker does not support host volumes for builds (needs extension), but podman does. What if packages were on a host tmp volume (-v $(mktemp -d):/temporary:rw), I don't think those go to the final image?

Use the existing "temp-limit" as the global limit, and introduce GPU
and memory thresholds.

Signed-off-by: Tuomas Katila <tuomas.katila@intel.com>
Fix uninitialized variable that caused random behaviour.

Signed-off-by: Tuomas Katila <tuomas.katila@intel.com>
By re-downloading the components, we save on the overall container size.
While the build time increases slightly, the container size drops by
around 100M (520->420).

Signed-off-by: Tuomas Katila <tuomas.katila@intel.com>
Copy link
Contributor

@eero-t eero-t left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Approved. Additional container improvements don't need to be part of this PR.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Add Per-Temperature Health Checks in GPU Plugin

2 participants