build-cran-binaries/.crow/build-all-versions.yaml
pat-s e23bd3e539
Some checks failed
ci/crow/cron/auto-apply-patches Pipeline failed
ci/crow/cron/weekly-audit-missing/1 Pipeline was successful
ci/crow/cron/weekly-audit-missing/2 Pipeline was successful
ci/crow/cron/weekly-audit-missing/6 Pipeline was successful
ci/crow/cron/weekly-audit-missing/4 Pipeline was successful
ci/crow/cron/weekly-audit-missing/5 Pipeline was successful
ci/crow/cron/weekly-audit-missing/7 Pipeline was successful
ci/crow/cron/weekly-audit-missing/8 Pipeline was successful
ci/crow/cron/weekly-audit-missing/9 Pipeline was successful
ci/crow/cron/weekly-audit-missing/3 Pipeline was successful
ci/crow/cron/weekly-audit-missing/10 Pipeline was successful
ci/crow/cron/weekly-audit-missing/11 Pipeline was successful
ci/crow/cron/weekly-audit-missing/12 Pipeline was successful
ci/crow/cron/weekly-audit-missing/13 Pipeline was successful
ci/crow/cron/weekly-audit-missing/14 Pipeline was successful
ci/crow/cron/trial-build-registry/11 Pipeline was successful
ci/crow/cron/trial-build-registry/16 Pipeline was successful
ci/crow/cron/trial-build-registry/4 Pipeline was successful
ci/crow/cron/trial-build-registry/15 Pipeline was successful
ci/crow/cron/trial-build-registry/8 Pipeline was successful
ci/crow/cron/trial-build-registry/6 Pipeline was successful
ci/crow/cron/trial-build-registry/12 Pipeline was successful
ci/crow/cron/trial-build-registry/14 Pipeline was successful
ci/crow/cron/trial-build-registry/7 Pipeline was successful
ci/crow/cron/trial-build-registry/9 Pipeline was successful
ci/crow/cron/trial-build-registry/10 Pipeline was successful
ci/crow/cron/trial-build-registry/13 Pipeline was successful
ci/crow/cron/trial-build-registry/1 Pipeline was successful
ci/crow/cron/trial-build-registry/2 Pipeline was successful
ci/crow/cron/trial-build-registry/5 Pipeline was successful
ci/crow/cron/trial-build-registry/3 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/15 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/14 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/13 Pipeline was successful
ci/crow/cron/weekly-rebuild-reindex/5 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/19 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/20 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/3 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/1 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/2 Pipeline was successful
ci/crow/cron/weekly-rebuild-reindex/1 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/21 Pipeline was successful
ci/crow/cron/weekly-rebuild-reindex/7 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/25 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/27 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/26 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/17 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/4 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/16 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/32 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/37 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/31 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/5 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/6 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/33 Pipeline was successful
ci/crow/cron/weekly-rebuild-reindex/2 Pipeline was successful
ci/crow/cron/weekly-rebuild-reindex/9 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/18 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/39 Pipeline was successful
ci/crow/cron/weekly-rebuild-reindex/6 Pipeline was successful
ci/crow/cron/weekly-rebuild-reindex/11 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/22 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/23 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/38 Pipeline was successful
ci/crow/cron/weekly-rebuild-reindex/13 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/28 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/29 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/24 Pipeline was successful
ci/crow/cron/weekly-rebuild-reindex/8 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/34 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/36 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/35 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/30 Pipeline was successful
ci/crow/cron/weekly-rebuild-reindex/10 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/40 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/41 Pipeline was successful
ci/crow/cron/weekly-rebuild-reindex/12 Pipeline was successful
ci/crow/cron/weekly-rebuild-missing/42 Pipeline was successful
ci/crow/cron/weekly-rebuild-reindex/14 Pipeline was successful
ci/crow/cron/process-updates/2 Pipeline was successful
ci/crow/cron/process-updates/11 Pipeline was successful
ci/crow/cron/process-updates/8 Pipeline was successful
ci/crow/cron/process-updates/9 Pipeline was successful
ci/crow/cron/process-updates/13 Pipeline was successful
ci/crow/cron/process-updates/16 Pipeline was successful
ci/crow/cron/process-updates/15 Pipeline was successful
ci/crow/cron/process-updates/12 Pipeline was successful
ci/crow/cron/process-updates/14 Pipeline was successful
ci/crow/cron/process-updates/10 Pipeline was successful
ci/crow/cron/process-updates/4 Pipeline was successful
ci/crow/cron/process-updates/3 Pipeline was successful
ci/crow/cron/process-updates/5 Pipeline was successful
ci/crow/cron/process-updates/6 Pipeline was successful
ci/crow/cron/process-updates/7 Pipeline was successful
ci/crow/cron/process-updates/1 Pipeline was successful
perf: seed pure-R binaries into a new slot, interleave shards, and stop builds before the timeout (#242)
Speeds up the full rebuild for a new slot, e.g. the upcoming Alpine version.

## Changes

- **Seed pure-R binaries** (`local/seed-pure-r.R`, `local/seed-helpers.R`), opt-in via the new `SEED_FROM` variable on `build-all-versions-install-deps`.
  About 74% of the ~84k candidate versions have no compiled code and cost ~20s each to build; their R objects are identical across slots.
  Before the build list is computed, each donor candidate is downloaded and verified, then copied server-side:
  - donor must be the same OS family and arch;
  - DESCRIPTION has `Built` (not a CRAN source fallback) with an empty platform and no `libs/`;
  - built by the target's primary R minor;
  - bincraft's `tarball_abi_verdict()` calls it portable across every installed minor (unknown means no seed).

  Each copy gets the `single_builds` and `abi_flat_safety` rows an upload writes, so build-all skips it and the per-minor indexes keep it.
  Re-runs skip existing objects and rewrite rows idempotently.
- **Interleaved shards** in `local/build-all.R` via `shard_slice()`; contiguous alphabetical quarters ranged from 0.1h to 28h.
- **Shared build deadline**: `build-all-versions` sets `BUILD_DEADLINE` from `BUILD_BUDGET_HOURS` (44h, repo timeout 50h); `build-all.R` and `build-newer-r.R` stop cleanly when it passes, so archiving still runs.
- `codename_platform()` replaces the hard-coded codename-to-platform list.

## Testing

- New unit tests for the seed verdict, candidate filter, platform names and deadline; all `local/tests` pass.
- Verdicts checked on real amd64/alpine324 tarballs: R6 2.6.1/2.5.1 and jsonstat seeded, cli refused as compiled.
- `crow lint .crow/` passes.
- The seed has not run against B2/Postgres yet; the first bootstrap run is its end-to-end test.

## Usage

Trigger `build-all-versions` with `target_arch`, `OS`, `OS_VERSION` and `SEED_FROM="alpine324 alpine323"`.
The new Alpine version still needs adding to the `OS_VERSION` options once its image exists.

Reviewed-on: #242
2026-10-24 02:04:06 +00:00

232 lines
9.9 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:
# Gates this pipeline. A manual pipeline creation instantiates every file in
# .crow/, and a declared default is applied even when the run never passed
# this variable, so the default must be a value that matches no matrix row.
target_arch:
description: 'Architecture to build, or "none" to run nothing.'
options:
- none
- amd64
- arm64
default: none
OS:
description: 'Base OS image name.'
options:
- alpine
- redhat
- ubuntu
default: alpine
OS_VERSION:
description: 'OS image tag. Must match OS (alpine: 3.24; redhat: 8/9/10; ubuntu: jammy/noble).'
options:
- '3.23'
- '3.24'
- '8'
- '9'
- '10'
- 'jammy'
- 'noble'
- 'resolute'
default: '3.24'
R_VERSION:
# The slot's *primary* R minor: what `local/build-all.R` builds into the
# generic slot. The loop below already runs `--sensitive-only` for every
# other installed minor, so filling a non-primary minor's gap needs this
# left alone, not changed.
#
# 4.6.0 was briefly offered here (#183) and removed: selecting it for a
# slot whose generic binaries are 4.5-built would publish 4.6 binaries
# into the generic slot and break every 4.5 client.
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-${ARCH}
# Empty UVR_CACHE_DIR/UVR_PACKAGES_DIR fall back to uvr's container-local
# ~/.uvr defaults; amd64 deliberately does not persist them (as with the
# pkgcache dir it replaces), arm64 does.
matrix:
include:
- ARCH: amd64
UVR_CACHE_DIR: ''
UVR_PACKAGES_DIR: ''
SPLIT_INTO: 4
SPLIT_INDEX: 1
- ARCH: amd64
UVR_CACHE_DIR: ''
UVR_PACKAGES_DIR: ''
SPLIT_INTO: 4
SPLIT_INDEX: 2
- ARCH: amd64
UVR_CACHE_DIR: ''
UVR_PACKAGES_DIR: ''
SPLIT_INTO: 4
SPLIT_INDEX: 3
- ARCH: amd64
UVR_CACHE_DIR: ''
UVR_PACKAGES_DIR: ''
SPLIT_INTO: 4
SPLIT_INDEX: 4
- ARCH: arm64
UVR_CACHE_DIR: /mnt/cache/uvr/cache
UVR_PACKAGES_DIR: /mnt/cache/uvr/packages
SPLIT_INTO: 4
SPLIT_INDEX: 1
- ARCH: arm64
UVR_CACHE_DIR: /mnt/cache/uvr/cache
UVR_PACKAGES_DIR: /mnt/cache/uvr/packages
SPLIT_INTO: 4
SPLIT_INDEX: 2
- ARCH: arm64
UVR_CACHE_DIR: /mnt/cache/uvr/cache
UVR_PACKAGES_DIR: /mnt/cache/uvr/packages
SPLIT_INTO: 4
SPLIT_INDEX: 3
- ARCH: arm64
UVR_CACHE_DIR: /mnt/cache/uvr/cache
UVR_PACKAGES_DIR: /mnt/cache/uvr/packages
SPLIT_INTO: 4
SPLIT_INDEX: 4
depends_on:
- build-all-versions-install-deps
steps:
- name: 'Build binaries'
image: 'reg.devxy.io/rpkgs/build-env-${OS}:${OS_VERSION}'
pull: true
environment:
OTEL_R_TRACES_EXPORTER: none
OTEL_R_LOGS_EXPORTER: none
OTEL_R_METRICS_EXPORTER: none
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
# set the location of uvr's caches, which persist the R package
# dependencies needed to install the packages themselves
UVR_CACHE_DIR: ${UVR_CACHE_DIR}
UVR_PACKAGES_DIR: ${UVR_PACKAGES_DIR}
R_LIBS_USER: /mnt/cache/R-pkgs
CCACHE_DIR: /mnt/cache/ccache
NCPUS: 2
# Whole hours the build passes below may use, measured from the step's
# start. The repo timeout is 50h; the remainder is left for archiving the
# missed packages, so a long run ends cleanly instead of being killed.
BUILD_BUDGET_HOURS: 44
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 .
- . local/compiler-cache.sh
# One deadline shared by every build pass in this step, read by
# local/build-all.R and local/build-newer-r.R before each package.
- export BUILD_DEADLINE=$(( $(date +%s) + BUILD_BUDGET_HOURS * 3600 ))
- mkdir -p /mnt/cache/uvr/cache /mnt/cache/uvr/packages /mnt/cache/R-pkgs /mnt/cache/ccache /mnt/cache/packages
# The primary pass must not rely on build-all-versions-install-deps having
# run on *this* agent: depends_on only orders the steps, but the cache
# volume is per-agent, so a job landing on an agent where install-deps did
# not run would otherwise use a stale bincraft (which resolves `platform`
# to a zero-length value and breaks every metadata query and the sysdeps
# install). Pin bincraft here, exactly like the R-minor pass below.
- rm -rf /mnt/cache/R-pkgs/00LOCK-*
- /opt/R/$R_VERSION/bin/Rscript local/install-bincraft.R
# The dependency-prep job may run on another agent whose cache volume is
# not visible here. Install the packages needed to recompute the snapshot
# and query build metadata in every build job.
- UVR_R_BIN=/opt/R/$R_VERSION/bin/R local/uvr-install.sh RPostgres s3fs data.table future jsonlite purrr
- XVFB=$(command -v xwfb-run 2>/dev/null || command -v xvfb-run); XVFB_ARGS="-a"; 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")/Rscript" local/install-bincraft.R || true
R_LIBS_USER="$LIB" UVR_R_BIN="$RBIN" local/uvr-install.sh RPostgres || true
R_LIBS_USER="$LIB" $XVFB $XVFB_ARGS -n $SPLIT_INDEX -- "$(dirname "$RBIN")/Rscript" local/build-all.R --sensitive-only $SPLIT_INTO $SPLIT_INDEX $NCPUS 2>&1 || true
# Also build current packages whose required dependency tree needs a newer R.
R_LIBS_USER="$LIB" $XVFB $XVFB_ARGS -n $SPLIT_INDEX -- "$(dirname "$RBIN")/Rscript" local/build-newer-r.R "$R_VERSION" $SPLIT_INTO $SPLIT_INDEX
done
# archive missed packages; first arg is the codename (e.g. "alpine324"),
# derived via bincraft like the upload step, not paste(OS, OS_VERSION).
- /opt/R/$R_VERSION/bin/R -q -e "bincraft::process_unarchived_pkgs(bincraft::set_codename(NULL), Sys.getenv('ARCH'), 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'), 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:
OTEL_R_TRACES_EXPORTER: none
OTEL_R_LOGS_EXPORTER: none
OTEL_R_METRICS_EXPORTER: none
B2_S3_ACCESS_KEY:
from_secret: B2_S3_ACCESS_KEY
B2_S3_SECRET_KEY:
from_secret: B2_S3_SECRET_KEY
# A per-minor index reads the ABI classifier cache and the flat-object
# safety table from the build database, and is not republished without it.
PGPASS:
from_secret: PGPASS
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 = '$CODENAME', s3_endpoint = 'https://s3.eu-central-003.backblazeb2.com', s3_region = 'eu-central-003', s3_bucket = 'devxy-rpkgs-binaries', s3_access_key_id = Sys.getenv('B2_S3_ACCESS_KEY'), s3_secret_access_key = Sys.getenv('B2_S3_SECRET_KEY'))"
FAILED_MINORS=""
for RBIN in /opt/R/[0-9]*/bin/R; do
RMINOR=$(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'), metadata_db_host = 'r-binaries.devxy.io', metadata_db_name = 'build_metadata', metadata_db_port = 15432L, metadata_db_user = 'rpkgs', metadata_db_password = Sys.getenv('PGPASS'), metadata_db_sslmode = 'verify-full')" || FAILED_MINORS="$FAILED_MINORS $RMINOR"
done
if [ -n "$FAILED_MINORS" ]; then
echo "Could not republish the per-minor index for:$FAILED_MINORS" >&2
exit 1
fi
backend_options:
docker:
resources:
requests:
memory: 5Gi
cpu: 1000m
limits:
memory: 20Gi
cpu: 2000m