Files
OpenResearch/scripts/test-ssh-container.sh
T
Daniel Kim b97c2346ae Share SSH monitoring and back off transport failures (OR-558) (#741)
* Share SSH monitoring connections and persist host retry backoff

* Fix explicit reconnect, growing logs, and long SSH setup

* Require idle SSH monitors before dev-slot data cleanup

* Show SSH connection and run monitoring diagnostics

* Preserve quoted SSH known-hosts filename lists

* Include shared SSH log files in run artifact cleanup

* Support Python 3.6 remote SSH helpers

* Finish Slurm runs despite unavailable logs

* Validate SSH log chunks during concurrent rewrites

* Detect full-prefix log rewrites and isolate legacy SSH monitors

* Preserve whitespace in interactive SSH credentials

* Reuse verified log digests and ignore unrelated obsolete SSH routes

* Keep pinned SSH connections stable across unrelated config edits

* Stream large SSH command input through bounded upload frames
2026-10-23 14:04:56 -07:00

36 lines
1.9 KiB
Bash
Executable File

#!/usr/bin/env bash
set -euo pipefail
# Only the uniquely named test containers are changed or removed.
fixture=$(mktemp -d)
export ORX_DATA_DIR="$fixture/data" XDG_CONFIG_HOME="$fixture/config" ORX_CACHE_DIR="$fixture/cache"
prefix="orx-ssh-test-$$"
cleanup() {
"${CARGO_TARGET_DIR:-target}/debug/orx" ssh-service stop >/dev/null 2>&1 || true
docker rm -f "$prefix-host" "$prefix-inner" >/dev/null 2>&1 || true
docker image rm "$prefix" >/dev/null 2>&1 || true
rm -rf "$fixture"
}
trap cleanup EXIT
ssh-keygen -q -t ed25519 -N '' -f "$fixture/key"
cat > "$fixture/Dockerfile" <<'DOCKER'
FROM docker:28-cli
RUN apk add --no-cache openssh bash util-linux coreutils procps python3 && ssh-keygen -A && mkdir -p /root/.ssh && chmod 700 /root/.ssh
COPY key.pub /root/.ssh/authorized_keys
COPY ssh-dispatch /usr/local/bin/ssh-dispatch
RUN chmod +x /usr/local/bin/ssh-dispatch && echo "ForceCommand /usr/local/bin/ssh-dispatch" >> /etc/ssh/sshd_config
RUN chmod 600 /root/.ssh/authorized_keys
ENTRYPOINT ["/usr/sbin/sshd", "-D", "-e"]
DOCKER
cp scripts/ssh-test-proxy.py "$fixture/ssh-dispatch"
docker build -q -t "$prefix" "$fixture"
docker run -d --name "$prefix-host" -p 127.0.0.1::22 -v /var/run/docker.sock:/var/run/docker.sock "$prefix"
docker run -d --name "$prefix-inner" --user 1000:1000 --env CONDA_ENVS_PATH=/tmp/conda-envs --env "HOME=/tmp/orx home'quoted" --entrypoint bash condaforge/miniforge3 -c 'mkdir -p "$HOME"; exec sleep infinity'
port=$(docker port "$prefix-host" 22/tcp)
export ORX_SSH_TEST_PORT="${port##*:}" ORX_SSH_TEST_KEY="$fixture/key" ORX_SSH_TEST_CONTAINER="$prefix-inner"
for attempt in {1..30}; do
if ssh -i "$fixture/key" -p "$ORX_SSH_TEST_PORT" -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null -o BatchMode=yes root@127.0.0.1 true 2>/dev/null; then break; fi
sleep 1
done
cargo build --locked
cargo test --locked ssh_container_lifecycle -- --ignored --nocapture