Skip to content

ci: make the gate resilient to transient upstream (apt/registry) flakes — retry infra steps only, never tests #664

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
baron-3dl wants to merge 1 commit into
base: main
Choose a base branch
from
Open

ci: make the gate resilient to transient upstream (apt/registry) flakes — retry infra steps only, never tests #664

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
44 changes: 32 additions & 12 deletions .github/workflows/ci.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -621,8 +621,16 @@ jobs:
# sources instead of 126, and stops refusing.
- name: Install build dependencies
run: |
sudo apt-get update -qq
sudo apt-get install -y --no-install-recommends \
# Infra-only retry (vms CI resilience): GitHub's apt mirrors flake
# transiently. This wraps ONLY the package-fetch/setup step -- there
# is no test or build-correctness command here, so a retry cannot
# mask a real failure. Acquire::Retries retries apt's own network
# fetches; the loop retries a whole failed `update` with backoff.
for i in 1 2 3 4 5; do
sudo apt-get -o Acquire::Retries=5 update -qq && break
echo "apt-get update failed (attempt $i/5); backing off" >&2; sleep $((i * 5))
done
sudo apt-get -o Acquire::Retries=5 install -y --no-install-recommends \
cmake gcc make libc6-dev libreadline-dev strace libcap2-bin \
libssh-dev musl-tools

Expand Down Expand Up @@ -1053,7 +1061,7 @@ jobs:
-v ${{ github.workspace }}/dist/release-a/ovmx-distrib.img:/boot/ovmx-distrib.img:ro \
-v ${{ github.workspace }}/tests/qemu/test_distrib_boot.sh:/test.sh:ro \
ubuntu:24.04 \
bash -c "apt-get update -qq && apt-get install -y --no-install-recommends qemu-system-x86 qemu-system-arm qemu-efi-aarch64 cpio >/dev/null 2>&1 && bash /test.sh"
bash -c "apt-get -o Acquire::Retries=5 update -qq && apt-get -o Acquire::Retries=5 install -y --no-install-recommends qemu-system-x86 qemu-system-arm qemu-efi-aarch64 cpio >/dev/null 2>&1 && bash /test.sh"

# -----------------------------------------------------------------------
# Job 2c: install -> UPGRADE -> boot (vms-f05, epic vms-a84 RELEASE ENGINEERING)
Expand Down Expand Up @@ -2396,8 +2404,12 @@ jobs:

- name: Install clang (NetBSD cross target)
run: |
sudo apt-get update -qq
sudo apt-get install -y -qq --no-install-recommends clang
# Infra-only retry (vms CI resilience) -- setup step, no test here.
for i in 1 2 3 4 5; do
sudo apt-get -o Acquire::Retries=5 update -qq && break
echo "apt-get update failed (attempt $i/5); backing off" >&2; sleep $((i * 5))
done
sudo apt-get -o Acquire::Retries=5 install -y -qq --no-install-recommends clang

# Cache the extracted NetBSD kernel sources, keyed on the pinned release
# (netbsd_version.env carries NETBSD_SYSSRC_URL/_SHA512). No OVMX-source
Expand Down Expand Up @@ -2455,8 +2467,12 @@ jobs:

- name: Install clang (NetBSD cross target)
run: |
sudo apt-get update -qq
sudo apt-get install -y -qq --no-install-recommends clang
# Infra-only retry (vms CI resilience) -- setup step, no test here.
for i in 1 2 3 4 5; do
sudo apt-get -o Acquire::Retries=5 update -qq && break
echo "apt-get update failed (attempt $i/5); backing off" >&2; sleep $((i * 5))
done
sudo apt-get -o Acquire::Retries=5 install -y -qq --no-install-recommends clang

# Same cache + key as the executive cross-compile job (netbsd_version.env
# pins the release); a source change never re-downloads the headers.
Expand Down Expand Up @@ -3338,8 +3354,8 @@ jobs:
-v "${{ github.workspace }}/tests/conformance/vms_programs:/tests/vms_programs:ro" \
ubuntu:24.04 bash -c '
set -e
apt-get update -qq
apt-get install -y --no-install-recommends cmake gcc make libc6-dev libreadline-dev
apt-get -o Acquire::Retries=5 update -qq
apt-get -o Acquire::Retries=5 install -y --no-install-recommends cmake gcc make libc6-dev libreadline-dev
cmake -B build -DCMAKE_BUILD_TYPE=Debug -DCMAKE_INSTALL_PREFIX=/ -DBUILD_TOOLS=ON
cmake --build build --parallel "$(nproc)"
bash /src/tests/conformance/run_conformance.sh
Expand Down Expand Up @@ -3396,7 +3412,7 @@ jobs:
-v "${{ github.workspace }}":/src -w /src \
ubuntu:24.04 bash -c '
set -e
{ apt-get update -qq && apt-get install -y --no-install-recommends cmake gcc make libc6-dev libreadline-dev; } >&2
{ apt-get -o Acquire::Retries=5 update -qq && apt-get -o Acquire::Retries=5 install -y --no-install-recommends cmake gcc make libc6-dev libreadline-dev; } >&2
{ cmake -B build -DCMAKE_BUILD_TYPE=Debug -DCMAKE_INSTALL_PREFIX=/ -DBUILD_TOOLS=ON; } >&2
{ cmake --build build --parallel "$(nproc)"; } >&2
bash /src/tests/conformance/run_corpus.sh /src/tests/conformance/corpus_baseline.json
Expand Down Expand Up @@ -3478,8 +3494,12 @@ jobs:

- name: Install dependencies
run: |
sudo apt-get update -qq
sudo apt-get install -y --no-install-recommends \
# Infra-only retry (vms CI resilience) -- setup step, no test here.
for i in 1 2 3 4 5; do
sudo apt-get -o Acquire::Retries=5 update -qq && break
echo "apt-get update failed (attempt $i/5); backing off" >&2; sleep $((i * 5))
done
sudo apt-get -o Acquire::Retries=5 install -y --no-install-recommends \
cmake gcc make libc6-dev libreadline-dev \
clang-tidy cppcheck

Expand Down
Loading