mirror of
https://github.com/jmcorgan/fips.git
synced 2026-10-05 11:08:25 +00:00
Johnathan Corgan
0c3c0c79c0
Image builds in CI pull base images from Docker Hub and ghcr.io and fetch packages from distribution mirrors, and each has failed a leg for a few seconds at a time: a registry dial timeout, a 502, an apt file truncated mid-fetch. A single failed build failed the leg, and a rerun of the whole workflow was the only recovery. Add retry_build to testing/lib/image-build.sh: up to three attempts with 10 s and then 20 s between them, whole-build so the base is resolved again and every package-fetching RUN step runs again. It is quiet on a first-attempt success, prints each failed attempt and a recovery to stderr, and on GitHub Actions also raises a warning on the run summary when a build recovered, so recovered failures remain countable. It never wraps a test or a container start. Use it for the shared test images in the integration job, the deb-install and dns-resolver runtime images, and the package builder image. Each deb-install and dns-resolver attempt prints its captured output on failure, so a recovered failure still shows its cause. The NAT, nostr publish-consume and STUN fault suites built their lab images inside `docker compose up --build`: the relay image from ghcr.io and Alpine, the STUN server from the Python image, and the routers from Debian with apt. Build the profile's images first through retry_build, then bring the lab up with --no-build. The start is not retried, since a container that fails to start is a test result; only the build is.