build-cran-binaries/.crow/backfill-flat-safety.yaml
pat-s 930a4acd12
fix(ci): install the R packages pipelines use instead of relying on the image
bincraft v5.5.1 dropped lubridate, dplyr, purrr, data.table and others from
its imports, so the pipelines' own calls now depend on whatever the build-env
image's site library or the shared R_LIBS_USER cache happens to hold. The arm64
redhat:9 image has no progressr under R 4.4.3, which fails every
process-cran-updates-redhat-9-arm64 run since v5.5.1.

- Install progressr and lubridate for process-updates, which call them inline.
- Install purrr for packages-to-build.R and data.table for the weekly audit.
- Drop the unused dplyr and progressr library() calls from packages-to-build.R.
- Install RPostgres in every pipeline that talks to the metadata DB, since
  bincraft silently skips the DB (and the per-minor index aborts) without it.
- Reinstall bincraft in the prune re-index step, whose /tmp library does not
  survive from the prune step.
2026-10-20 08:46:00 +00:00

176 lines
5.1 KiB
YAML

# Record, per flat-slot object, whether it loads under every supported R minor.
#
# `union_index_records()` keeps a carried flat record when that object is
# recorded safe and drops it otherwise. Objects uploaded before that record
# existed have no verdict, so they are dropped: a full re-index removed roughly
# 2000 records per per-minor index (16398 across the 4.4 indexes, 20076 across
# 4.5, 15532 across 4.6), each one resolving to CRAN source for clients the
# routing serves correctly.
#
# This inspects what is already in the bucket and writes the verdict, which is
# what restores that coverage. Decided by symbols rather than heuristics: a
# binary fails at dyn.load() under minor M exactly when it references a symbol M
# does not export, and the volatile set is derived by diffing the R builds in
# the image.
#
# Re-running is cheap; recorded objects are skipped.
#
# crow pipeline create devxy/build-cran-binaries --var flat_safety=all
variables:
# A manual pipeline creation instantiates every file in .crow/, so the default
# must match no matrix row.
flat_safety:
description: "Inspect target: a specific <os>-<arch>, 'all' for every slot, or 'none'."
options:
- none
- all
- alpine-323-amd64
- alpine-323-arm64
- alpine-324-amd64
- alpine-324-arm64
- redhat-8-amd64
- redhat-8-arm64
- redhat-9-amd64
- redhat-9-arm64
- redhat-10-amd64
- redhat-10-arm64
- ubuntu-2204-amd64
- ubuntu-2204-arm64
- ubuntu-2404-amd64
- ubuntu-2404-arm64
- ubuntu-2604-amd64
- ubuntu-2604-arm64
default: none
FLAT_SAFETY_LIMIT:
description: 'Inspect at most this many objects per slot (0 = no limit).'
default: '0'
when:
- event: manual
evaluate: 'flat_safety == "all" || flat_safety == "${OS}-${ARCH}"'
skip_clone: true
labels:
group: rpkgs-${ARCH}
matrix:
include:
- OS: alpine-323
ARCH: amd64
R_VERSION: 4.5.3
IMG: alpine:3.23
- OS: alpine-323
ARCH: arm64
R_VERSION: 4.5.3
IMG: alpine:3.23
- OS: alpine-324
ARCH: amd64
R_VERSION: 4.5.3
IMG: alpine:3.24
- OS: alpine-324
ARCH: arm64
R_VERSION: 4.5.3
IMG: alpine:3.24
- OS: redhat-8
ARCH: amd64
R_VERSION: 4.4.3
IMG: redhat:8
- OS: redhat-8
ARCH: arm64
R_VERSION: 4.4.3
IMG: redhat:8
- OS: redhat-9
ARCH: amd64
R_VERSION: 4.4.3
IMG: redhat:9
- OS: redhat-9
ARCH: arm64
R_VERSION: 4.4.3
IMG: redhat:9
- OS: redhat-10
ARCH: amd64
R_VERSION: 4.5.3
IMG: redhat:10
- OS: redhat-10
ARCH: arm64
R_VERSION: 4.5.3
IMG: redhat:10
- OS: ubuntu-2204
ARCH: amd64
R_VERSION: 4.4.3
IMG: ubuntu:jammy
- OS: ubuntu-2204
ARCH: arm64
R_VERSION: 4.4.3
IMG: ubuntu:jammy
- OS: ubuntu-2404
ARCH: amd64
R_VERSION: 4.4.3
IMG: ubuntu:noble
- OS: ubuntu-2404
ARCH: arm64
R_VERSION: 4.4.3
IMG: ubuntu:noble
- OS: ubuntu-2604
ARCH: amd64
R_VERSION: 4.4.3
IMG: ubuntu:resolute
- OS: ubuntu-2604
ARCH: arm64
R_VERSION: 4.4.3
IMG: ubuntu:resolute
steps:
- name: 'Inspect flat objects and record safety'
image: reg.devxy.io/rpkgs/build-env-${IMG}
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
# bincraft reads the DESCRIPTION of every new or replaced tarball from
# the CRAN mirror on raw.githubusercontent.com, and authenticates with
# this token when it is set. A slot whose published index cannot be read
# is re-read in full, ~25k requests, which the anonymous rate limit would
# cut short.
GITHUB_PAT:
from_secret: GITHUB_PAT
GIT_USER: pat-s
R_LIBS_USER: /tmp/R-pkgs
FLAT_SAFETY_ARCH: ${ARCH}
FLAT_SAFETY_LIMIT: ${FLAT_SAFETY_LIMIT}
commands:
- git clone -q https://pat-s:$$REPO_RO_TOKEN@git.devxy.io/devxy/build-cran-binaries.git .
- mkdir -p /tmp/R-pkgs
- /opt/R/$R_VERSION/bin/Rscript local/install-bincraft.R
- UVR_R_BIN=/opt/R/$R_VERSION/bin/R local/uvr-install.sh RPostgres
- |
set -eu
LIMIT=""
if [ "$$FLAT_SAFETY_LIMIT" != "0" ]; then
LIMIT="$$FLAT_SAFETY_LIMIT"
fi
# The codename comes from the image's /etc/os-release, exactly as the
# re-index step derives it, so it cannot drift from the matrix.
CODENAME=$(/opt/R/$R_VERSION/bin/Rscript -e 'cat(bincraft::set_codename(NULL))')
echo "slot: $$FLAT_SAFETY_ARCH/$$CODENAME"
/opt/R/$R_VERSION/bin/Rscript local/backfill-flat-safety.R \
"$$FLAT_SAFETY_ARCH" "$$CODENAME" $$LIMIT
backend_options:
docker:
resources:
requests:
memory: 4Gi
cpu: 1000m