build-cran-binaries/.crow/build-all-versions.yaml
pat-s 0f4330c05c fix(ci): make build-all self-sufficient on agents without install-deps (#96)
## Summary

Fixes the recurring `build-all-*` failure on agents where `build-all-versions-install-deps` did **not** run.

Both symptoms in the logs — `Parameter 3 does not have length 1` (repeated, in the metadata DB queries) and `argument is of length zero` (system-dependency install) — were the same bug: inside bincraft, `platform` was zero-length. `local/build-all.R` calls `build_binary_package()` without passing `platform`, so bincraft resolves it from the container codename. The primary build step never (re)installed/pinned bincraft and relied on whatever sat in the **per-agent** cache volume; `depends_on` only orders steps, it does not co-locate them on the same agent, so a job landing where install-deps never ran got a stale bincraft that left `platform` empty.

## Changes

- **`build-all-versions.yaml`**: pin bincraft `@v4.2.3` in the primary build step (mirroring the R-minor pass and `process-updates.yaml`), so every agent uses a known-good bincraft regardless of where install-deps ran.
- Align the R-minor pass `v4.2.2 → v4.2.3`.
- Export `OS`/`OS_VERSION`/`ARCH` as runtime env vars — previously only available for `${...}` interpolation, so `build-all.R`'s already-built dedup query matched platform `"-"` and skipped nothing.
- Fix the unarchive call: pass the codename via `bincraft::set_codename(NULL)` instead of the malformed `paste(OS, OS_VERSION)` (`"alpine 3.24"`), matching `archive-missed-packages.yaml`.
- **`build-all-versions-install-deps.yaml`**: pin install-deps to `@v4.2.3` (was installing HEAD), so the precomputed snapshot and per-agent library stay consistent pipeline-wide.

Reviewed-on: #96
2026-06-18 11:27:02 +00:00

171 lines
6.9 KiB
YAML

### Manual full rebuild of all CRAN binaries for one OS/arch.
# Set the variables below in the manual-run form (or via --var on the CLI).
# `target_arch` routes the matrix; OS/OS_VERSION/R_VERSION select the platform
# image and cache volume. Placement is via the group label (rpkgs-amd64/rpkgs-arm64).
# Skip list lives in local/excluded-packages.json (read by local/build-all.R).
variables:
target_arch:
description: "Architecture to build."
options:
- amd64
- arm64
default: amd64
OS:
description: "Base OS image name (e.g. alpine, redhat, ubuntu)."
default: alpine
OS_VERSION:
description: "OS version / image tag (e.g. 3.24, 9, jammy, noble)."
default: "3.24"
R_VERSION:
description: "Primary R version under /opt/R."
options:
- 4.5.3
- 4.4.3
default: 4.5.3
when:
- event: manual
evaluate: 'target_arch == "${ARCH}"'
skip_clone: true
labels:
platform: linux/${ARCH}
group: rpkgs-${ARCH}
matrix:
include:
- ARCH: amd64
R_PKG_CACHE_DIR: ''
SPLIT_INTO: 4
SPLIT_INDEX: 1
- ARCH: amd64
R_PKG_CACHE_DIR: ''
SPLIT_INTO: 4
SPLIT_INDEX: 2
- ARCH: amd64
R_PKG_CACHE_DIR: ''
SPLIT_INTO: 4
SPLIT_INDEX: 3
- ARCH: amd64
R_PKG_CACHE_DIR: ''
SPLIT_INTO: 4
SPLIT_INDEX: 4
- ARCH: arm64
R_PKG_CACHE_DIR: /mnt/cache/pkgcache
SPLIT_INTO: 4
SPLIT_INDEX: 1
- ARCH: arm64
R_PKG_CACHE_DIR: /mnt/cache/pkgcache
SPLIT_INTO: 4
SPLIT_INDEX: 2
- ARCH: arm64
R_PKG_CACHE_DIR: /mnt/cache/pkgcache
SPLIT_INTO: 4
SPLIT_INDEX: 3
- ARCH: arm64
R_PKG_CACHE_DIR: /mnt/cache/pkgcache
SPLIT_INTO: 4
SPLIT_INDEX: 4
depends_on:
- build-all-versions-install-deps
steps:
- name: 'Build binaries'
image: 'reg.devxy.io/rpkgs/build-env-${OS}:${OS_VERSION}'
pull: true
environment:
RED_HAT_DEV_PW:
from_secret: RED_HAT_DEV_PW
B2_S3_ACCESS_KEY:
from_secret: B2_S3_ACCESS_KEY
B2_S3_SECRET_KEY:
from_secret: B2_S3_SECRET_KEY
PGPASS:
from_secret: PGPASS
REPO_RO_TOKEN:
from_secret: REPO_RO_TOKEN
GITHUB_PAT:
from_secret: GITHUB_PAT
# normal env vars
GIT_USER: pat-s
# Export the platform selectors as runtime env vars. They are otherwise
# only available for ${...} interpolation (image/volume), so build-all.R's
# `Sys.getenv("OS")/("OS_VERSION")/("ARCH")` would be empty and its
# already-built dedup query would match platform "-" and skip nothing.
OS: ${OS}
OS_VERSION: ${OS_VERSION}
ARCH: ${ARCH}
# set the location of the 'pkgcache' cache dir which persists the R package dependencies needed to install the packages themselves
R_PKG_CACHE_DIR: ${R_PKG_CACHE_DIR}
R_LIBS_USER: /mnt/cache/R-pkgs
CCACHE_DIR: /mnt/cache/ccache
NCPUS: 2
volumes:
- ${ARCH}-binaries-r-dep-cache-${OS}-${OS_VERSION//./}:/mnt/cache
commands:
- git clone -q https://pat-s:$$REPO_RO_TOKEN@git.devxy.io/devxy/build-cran-binaries.git .
- mkdir -p /mnt/cache/pkgcache /mnt/cache/R-pkgs /mnt/cache/ccache /mnt/cache/packages
# The primary pass must not rely on build-all-versions-install-deps having
# run on *this* agent: depends_on only orders the steps, but the cache
# volume is per-agent, so a job landing on an agent where install-deps did
# not run would otherwise use a stale bincraft (which resolves `platform`
# to a zero-length value and breaks every metadata query and the sysdeps
# install). Pin bincraft here, exactly like the R-minor pass below.
- rm -rf /mnt/cache/R-pkgs/00LOCK-*
- /opt/R/$R_VERSION/bin/R -q -e 'if (!requireNamespace("bincraft", quietly = TRUE) || packageVersion("bincraft") != "4.2.3") pak::pak("git::https://codefloe.com/rpkgs/bincraft.git@v4.2.3")'
- XVFB=$(command -v xwfb-run 2>/dev/null || command -v xvfb-run); XVFB_ARGS=""; if command -v xwfb-run >/dev/null 2>&1; then dnf install -y -q weston 2>/dev/null; XVFB_ARGS="-c weston"; fi
- $XVFB $XVFB_ARGS -n $SPLIT_INDEX -- /opt/R/$R_VERSION/bin/Rscript local/build-all.R $SPLIT_INTO $SPLIT_INDEX $NCPUS 2>&1
- |
PRIMARY_MINOR=$(echo "$R_VERSION" | cut -d. -f1-2)
for RBIN in /opt/R/[0-9]*/bin/R; do
RV=$(basename "$(dirname "$(dirname "$RBIN")")")
RMINOR=$(echo "$RV" | cut -d. -f1-2)
[ "$RMINOR" = "$PRIMARY_MINOR" ] && continue
echo "=== R-minor-sensitive pass under R $RV ==="
LIB="/mnt/cache/R-pkgs-$RMINOR"
mkdir -p "$LIB"
R_LIBS_USER="$LIB" "$(dirname "$RBIN")/R" -q -e 'if (!requireNamespace("bincraft", quietly = TRUE) || packageVersion("bincraft") != "4.2.3") pak::pak("git::https://codefloe.com/rpkgs/bincraft.git@v4.2.3")' || true
R_LIBS_USER="$LIB" $XVFB $XVFB_ARGS -n $SPLIT_INDEX -- "$(dirname "$RBIN")/Rscript" local/build-all.R --sensitive-only $SPLIT_INTO $SPLIT_INDEX $NCPUS 2>&1 || true
done
# archive missed packages; first arg is the codename (e.g. "alpine324"),
# derived via bincraft like the upload step, not paste(OS, OS_VERSION).
- /opt/R/$R_VERSION/bin/R -q -e "bincraft::process_unarchived_pkgs(bincraft::set_codename(NULL), Sys.getenv('ARCH'), workers = $NCPUS)"
backend_options:
docker:
resources:
requests:
memory: 5Gi
cpu: 1000m
limits:
memory: 20Gi
cpu: 2000m
- name: 'Upload package indexes'
image: 'reg.devxy.io/rpkgs/build-env-${OS}:${OS_VERSION}'
pull: true
environment:
B2_S3_ACCESS_KEY:
from_secret: B2_S3_ACCESS_KEY
B2_S3_SECRET_KEY:
from_secret: B2_S3_SECRET_KEY
R_LIBS_USER: /mnt/cache/R-pkgs
volumes:
- ${ARCH}-binaries-r-dep-cache-${OS}-${OS_VERSION//./}:/mnt/cache
commands:
- |
CODENAME=$(/opt/R/$R_VERSION/bin/Rscript -e "cat(bincraft::set_codename(NULL))")
/opt/R/$R_VERSION/bin/R -q -e "bincraft::upload_package_index(codename = '$CODENAME', s3_endpoint = 'https://s3.eu-central-003.backblazeb2.com', s3_region = 'eu-central-003', s3_bucket = 'devxy-rpkgs-binaries', s3_access_key_id = Sys.getenv('B2_S3_ACCESS_KEY'), s3_secret_access_key = Sys.getenv('B2_S3_SECRET_KEY'))"
for RBIN in /opt/R/[0-9]*/bin/R; do
RMINOR=$(basename "$(dirname "$(dirname "$RBIN")")" | cut -d. -f1-2)
/opt/R/$R_VERSION/bin/R -q -e "bincraft::upload_package_index(codename = '$CODENAME', r_minor = '$RMINOR', s3_endpoint = 'https://s3.eu-central-003.backblazeb2.com', s3_region = 'eu-central-003', s3_bucket = 'devxy-rpkgs-binaries', s3_access_key_id = Sys.getenv('B2_S3_ACCESS_KEY'), s3_secret_access_key = Sys.getenv('B2_S3_SECRET_KEY'))" || true
done
backend_options:
docker:
resources:
requests:
memory: 5Gi
cpu: 1000m
limits:
memory: 20Gi
cpu: 2000m