build-cran-binaries/.crow/prune-stale-flat-binaries.yaml

# Remove flat-slot binaries recorded unable to load under some R minor, then
# re-index.
#
# The list comes from `abi_flat_safety`, so it names the objects the binaries
# themselves report as broken, not the ones a source heuristic suspects. That
# distinction is the whole cost of the operation: the heuristic calls 93% of
# compiled packages risky and would delete roughly 3000 objects per slot to fix
# about 230.
#
# `upload_single_binary()` has written a non-portable package only to the
# per-minor slot since v5.3.0, so this is a one-time cleanup of what was
# uploaded before that. The flat slot is what every client that cannot be
# routed by R minor receives, and such a binary was built under whichever R was
# primary at the time, so it dies at load under any minor that dropped a symbol
# it uses:
#
#   base64enc.so: undefined symbol: SETLENGTH
#
# Deleting the flat object does not create a hole. The source fallback
# republishes the CRAN source under the same key, so the package stays
# installable everywhere and compiles against the client's own R, while routed
# clients keep getting the per-minor binary.
#
# Dry run unless PRUNE_APPLY is 'yes'. Start with an explicit package list:
#
#   crow pipeline create devxy/build-cran-binaries \
#     --var prune_flat=ubuntu-2604-amd64 \
#     --var PRUNE_PACKAGES="base64enc lobstr" \
#     --var PRUNE_APPLY=yes

variables:
  # A manual pipeline creation instantiates every file in .crow/, so the default
  # must match no matrix row.
  prune_flat:
    description: "Prune 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
  PRUNE_PACKAGES:
    description: 'Space-separated package names. Empty means every package the classifier cache calls risky.'
    default: ''
  PRUNE_APPLY:
    description: "Set to 'yes' to actually delete. Anything else is a dry run."
    options:
      - 'no'
      - 'yes'
    default: 'no'

when:
  - event: manual
    evaluate: 'prune_flat == "all" || prune_flat == "${OS}-${ARCH}"'

skip_clone: true

labels:
  group: rpkgs-${ARCH}

matrix:
  include:
    - OS: alpine-323
      ARCH: amd64
      CODENAME: alpine323
      IMG: alpine:3.23
    - OS: alpine-323
      ARCH: arm64
      CODENAME: alpine323
      IMG: alpine:3.23
    - OS: alpine-324
      ARCH: amd64
      CODENAME: alpine324
      IMG: alpine:3.24
    - OS: alpine-324
      ARCH: arm64
      CODENAME: alpine324
      IMG: alpine:3.24
    - OS: redhat-8
      ARCH: amd64
      CODENAME: rhel8
      IMG: redhat:8
    - OS: redhat-8
      ARCH: arm64
      CODENAME: rhel8
      IMG: redhat:8
    - OS: redhat-9
      ARCH: amd64
      CODENAME: rhel9
      IMG: redhat:9
    - OS: redhat-9
      ARCH: arm64
      CODENAME: rhel9
      IMG: redhat:9
    - OS: redhat-10
      ARCH: amd64
      CODENAME: rhel10
      IMG: redhat:10
    - OS: redhat-10
      ARCH: arm64
      CODENAME: rhel10
      IMG: redhat:10
    - OS: ubuntu-2204
      ARCH: amd64
      CODENAME: jammy
      IMG: ubuntu:jammy
    - OS: ubuntu-2204
      ARCH: arm64
      CODENAME: jammy
      IMG: ubuntu:jammy
    - OS: ubuntu-2404
      ARCH: amd64
      CODENAME: noble
      IMG: ubuntu:noble
    - OS: ubuntu-2404
      ARCH: arm64
      CODENAME: noble
      IMG: ubuntu:noble
    - OS: ubuntu-2604
      ARCH: amd64
      CODENAME: resolute
      IMG: ubuntu:resolute
    - OS: ubuntu-2604
      ARCH: arm64
      CODENAME: resolute
      IMG: ubuntu:resolute

steps:
  - name: 'Prune stale flat binaries'
    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
      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
      GIT_USER: pat-s
      R_LIBS_USER: /tmp/R-pkgs
      # Pipeline variables are substituted into the YAML, not exported, so they
      # have to be bound here to be readable as env vars in the script below.
      PRUNE_ARCH: ${ARCH}
      PRUNE_CODENAME: ${CODENAME}
      PRUNE_PACKAGES: ${PRUNE_PACKAGES}
      PRUNE_APPLY: ${PRUNE_APPLY}
    commands:
      - git clone -q https://pat-s:$$REPO_RO_TOKEN@git.devxy.io/devxy/build-cran-binaries.git .
      - mkdir -p /tmp/R-pkgs
      - /opt/R/4.5.3/bin/Rscript local/install-bincraft.R
      - |
        set -eu
        APPLY=""
        if [ "$$PRUNE_APPLY" = "yes" ]; then
          APPLY="--apply"
        fi
        /opt/R/4.5.3/bin/Rscript local/prune-stale-flat-binaries.R \
          "$$PRUNE_ARCH" "$$PRUNE_CODENAME" $$APPLY $$PRUNE_PACKAGES
    backend_options:
      docker:
        resources:
          requests:
            memory: 3Gi
            cpu: 1000m

  # Deleting objects without re-indexing is worse than leaving them: the
  # published index keeps naming files that no longer exist, so every client
  # gets a 404 instead of a working source fallback. The re-index is what
  # republishes them as CRAN source, so it belongs in the same run.
  - name: 'Re-index the slot'
    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
      B2_S3_ACCESS_KEY:
        from_secret: B2_S3_ACCESS_KEY
      B2_S3_SECRET_KEY:
        from_secret: B2_S3_SECRET_KEY
      PGPASS:
        from_secret: PGPASS
      R_LIBS_USER: /tmp/R-pkgs
      PRUNE_APPLY: ${PRUNE_APPLY}
    commands:
      - |
        set -eu
        if [ "$$PRUNE_APPLY" != "yes" ]; then
          echo "Dry run: nothing was deleted, so there is nothing to re-index."
          exit 0
        fi
        /opt/R/4.5.3/bin/R -q -e 'library(bincraft); upload_package_index(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/4.5.3/bin/R -q -e "library(bincraft); upload_package_index(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: 3Gi
            cpu: 1000m

  # The edge caches indexes for ~370 days, so without this the deletion is
  # invisible to clients and they keep being handed the removed binary.
  - name: 'Purge CDN cache'
    image: reg.devxy.io/docker.io/library/alpine:3.24
    environment:
      BUNNYNET_API_KEY:
        from_secret: BUNNYNET_API_KEY
      # Same zones as reindex.yaml: the production pull zone id, the alliance
      # hostname and the staging zone, which shares the B2 origin.
      BUNNY_PULLZONES: '3857050 cran.allianceswisspass.devxy.io cran-rpkgs-test.b-cdn.net'
      PRUNE_APPLY: ${PRUNE_APPLY}
    commands:
      - |
        set -eu
        if [ "$$PRUNE_APPLY" != "yes" ]; then
          echo "Dry run: nothing changed at the origin, so no purge is needed."
          exit 0
        fi
        apk add --no-cache -q bash curl jq
        bash scripts/purge_cdn_zone.sh "$BUNNYNET_API_KEY" $BUNNY_PULLZONES
    # Run it even when a per-minor re-index above failed: the generic index
    # and the objects were still replaced, and a stale edge keeps them hidden.
    when:
      - status: [success, failure]