Skip to content

[pull] main from NVIDIA:main - #295

Merged
pull[bot] merged 6 commits into
TheTechOddBug:mainfrom
NVIDIA:main
Sep 25, 2026
Merged

pull[bot] merged 6 commits into
TheTechOddBug:mainfrom
NVIDIA:main

Conversation

@pull

@pull pull Bot commented Sep 25, 2026 •

Copy link
Copy Markdown

See Commits and Changes for more details.


Created by pull[bot] (v2.0.0-alpha.4)

Can you help keep this open source service alive? 💖 Please sponsor : )

politerealism and others added 6 commits September 24, 2026 20:16
…e CI gaps (#3690)

* test(podman): run driver-podman userns suite against rootful Podman too

The driver-specific-integration job only ran the driver-podman testsuite
(default/auto/keep-id/private userns reference checks) against
fedora-podman-rootless, leaving rootful behavior for this scenario
unverified even though the compute driver auto-detects and explicitly
supports rootful Podman.

The default-userns-baseline and userns-profile playbooks hard-asserted a
rootless tmachine gateway user, so pointing them at a rootful environment
would have failed that assertion immediately rather than exercising
anything. They now detect rootful vs. rootless via the existing
tmachine_container_runtime role and branch the reference-capture user
accordingly, while keeping the captured reference file itself owned by
tmachine, since the archived test binary that reads it back always runs
unprivileged as tmachine regardless of daemon mode.

Signed-off-by: politerealism <burdcat17@gmail.com>

* test(podman): add real-daemon coverage for resource limits and daemon failure

Neither the Podman driver's resource-limit enforcement nor its behavior
when the Podman daemon is unreachable had any test coverage against a
real daemon; both were only exercised through unit tests against a
mocked Podman client.

podman_resource_limits.rs creates a sandbox with --cpu/--memory flags and
reads /sys/fs/cgroup/memory.max and cpu.max from inside the sandbox
itself, verifying the limit is actually enforced rather than just echoed
back by the template API. Expected values are cross-checked against the
driver's own parse_cpu_to_microseconds/parse_memory_to_bytes and against
a real local `podman run --cpus/--memory` container.

podman_preflight.rs spawns the standalone openshell-driver-podman binary
against a guaranteed-nonexistent Podman socket and asserts it exits
non-zero within its bounded retry window with an actionable error naming
the socket path, rather than hanging or failing silently.

Signed-off-by: politerealism <burdcat17@gmail.com>

* test(podman): make rootful userns and cgroup checks pass

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* test(podman): match lifecycle containers by isolation role label

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* test(podman): accept non-expiring bootstrap tokens

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

---------

Signed-off-by: politerealism <burdcat17@gmail.com>
Signed-off-by: Drew Newberry <anewberry@nvidia.com>
Co-authored-by: Drew Newberry <anewberry@nvidia.com>
Signed-off-by: Piotr Mlocek <pmlocek@nvidia.com>
* fix(policy): restore policy.local and proposal conformance

Signed-off-by: Piotr Mlocek <pmlocek@nvidia.com>

* test(conformance): select policy scenarios by name

Signed-off-by: Piotr Mlocek <pmlocek@nvidia.com>

* test(conformance): reduce policy scenario timing flakes

Signed-off-by: Piotr Mlocek <pmlocek@nvidia.com>

* test(conformance): assert proposals target Bash

Signed-off-by: Piotr Mlocek <pmlocek@nvidia.com>

---------

Signed-off-by: Piotr Mlocek <pmlocek@nvidia.com>
* fix(sandbox): preserve exec output through channel close

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(exec): propagate output delivery failures before exit

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* docs(cli): clarify exec output delivery failures

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

---------

Signed-off-by: Drew Newberry <anewberry@nvidia.com>
* fix(cli): stream piped exec stdin across gRPC messages

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(cli): preserve small exec requests and surface stdin errors

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(cli): preserve exec stdin limit across gRPC streaming

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

---------

Signed-off-by: Drew Newberry <anewberry@nvidia.com>
* feat(cli): import provider profiles from HTTP URLs

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

* fix(cli): initialize crypto provider for remote profiles

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

---------

Signed-off-by: Drew Newberry <anewberry@nvidia.com>
@pull pull Bot locked and limited conversation to collaborators Sep 25, 2026
@pull pull Bot added the ⤵️ pull label Sep 25, 2026
@pull
pull Bot merged commit c93fd94 into TheTechOddBug:main Sep 25, 2026
1 of 7 checks passed
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants