feat(rebuild): shard the weekly rebuild and make each shard resumable

Split every OS/arch row of weekly-rebuild-missing into three shards and move the build loop out of the inline R one-liner into local/rebuild-missing.R. A shard re-derives its outstanding set from the bucket on every start: an object whose ETag equals CRAN's published MD5sum is still a source fallback and needs building. That is bincraft's check_s3_root_package() evaluated in bulk, so a restart resumes rather than replaying thousands of per-package HEADs, and it stays correct when a sibling shard or a process-updates run finishes work in the meantime. No progress file, no volume, no database cursor. Give each shard a 20h wall-clock budget so it exits cleanly instead of having to be killed. A kill matches neither success nor failure, which is how pipeline 10910 skipped its CDN purge and left ~4600 rebuilt binaries behind stale edge copies. Move re-indexing and the purge into weekly-rebuild-reindex.yaml, which depends on the rebuild and runs on success or failure. Three shards writing one slot's PACKAGES concurrently would race: update_PACKAGES lists the live bucket, so an early lister that uploads last publishes an index missing its siblings' work.
2026-08-12 08:27:45 +00:00 · 2026-08-12 08:27:45 +00:00 · c072b780b2
commit c072b780b2
parent 02e3966523
1 changed files with 838 additions and 36 deletions
--- a/.crow/weekly-rebuild-reindex.yaml
+++ b/.crow/weekly-rebuild-reindex.yaml
@ -0,0 +1,193 @@
+# Re-index and purge after weekly-rebuild-missing.
+#
+# weekly-rebuild-missing runs three shards per slot. Each of them replaces
+# objects in place, so the slot's index still advertises the old MD5 and, for
+# anything that had been served from source, no Built stamp. Re-indexing from
+# inside a shard would mean three concurrent `upload_package_index()` calls on
+# one prefix: `cranlike::update_PACKAGES()` lists the live bucket, so an early
+# lister that uploads last publishes an index missing its siblings' work.
+#
+# So it happens exactly once per slot, here, after every shard has finished.
+# `runs_on: [success, failure]` keeps that true when a shard fails; only an
+# explicit cancel skips it, and this pipeline can then be triggered on its own.
+
+variables:
+  # Mirrors the gate on weekly-rebuild-missing so a manual run re-indexes
+  # exactly the slots it rebuilt. A manual pipeline creation instantiates every
+  # file in .crow/, so the default must match no matrix row.
+  weekly_rebuild_missing:
+    description: "Manual run target: a specific <os>-<arch>, 'all' for every os/arch, or 'none' to run nothing."
+    options:
+      - none
+      - all
+      - alpine-322-amd64
+      - alpine-322-arm64
+      - 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
+
+when:
+  - event: cron
+    cron: weekly-rebuild-missing-${OS}-${ARCH}
+  - event: manual
+    evaluate: 'weekly_rebuild_missing == "all" || weekly_rebuild_missing == "${OS}-${ARCH}"'
+
+depends_on:
+  - weekly-rebuild-missing
+
+runs_on: [success, failure]
+
+skip_clone: true
+
+labels:
+  group: rpkgs-${ARCH}
+
+matrix:
+  include:
+    - OS: alpine-322
+      ARCH: amd64
+      R_VERSION: 4.5.3
+      IMG: alpine:3.22
+    - OS: alpine-322
+      ARCH: arm64
+      R_VERSION: 4.5.3
+      IMG: alpine:3.22
+    - OS: alpine-323
+      ARCH: amd64
+      R_VERSION: 4.5.3
+      IMG: alpine:3.23
+    - OS: alpine-323
+      ARCH: arm64
+      R_VERSION: 4.5.3
+      IMG: alpine:3.23
+    - OS: alpine-324
+      ARCH: amd64
+      R_VERSION: 4.5.3
+      IMG: alpine:3.24
+    - OS: alpine-324
+      ARCH: arm64
+      R_VERSION: 4.5.3
+      IMG: alpine:3.24
+    - OS: redhat-8
+      ARCH: amd64
+      R_VERSION: 4.4.3
+      IMG: redhat:8
+    - OS: redhat-8
+      ARCH: arm64
+      R_VERSION: 4.4.3
+      IMG: redhat:8
+    - OS: redhat-9
+      ARCH: amd64
+      R_VERSION: 4.4.3
+      IMG: redhat:9
+    - OS: redhat-9
+      ARCH: arm64
+      R_VERSION: 4.4.3
+      IMG: redhat:9
+    - OS: redhat-10
+      ARCH: amd64
+      R_VERSION: 4.5.3
+      IMG: redhat:10
+    - OS: redhat-10
+      ARCH: arm64
+      R_VERSION: 4.5.3
+      IMG: redhat:10
+    - OS: ubuntu-2204
+      ARCH: amd64
+      R_VERSION: 4.4.3
+      IMG: ubuntu:jammy
+    - OS: ubuntu-2204
+      ARCH: arm64
+      R_VERSION: 4.4.3
+      IMG: ubuntu:jammy
+    - OS: ubuntu-2404
+      ARCH: amd64
+      R_VERSION: 4.4.3
+      IMG: ubuntu:noble
+    - OS: ubuntu-2404
+      ARCH: arm64
+      R_VERSION: 4.4.3
+      IMG: ubuntu:noble
+    - OS: ubuntu-2604
+      ARCH: amd64
+      R_VERSION: 4.4.3
+      IMG: ubuntu:resolute
+    - OS: ubuntu-2604
+      ARCH: arm64
+      R_VERSION: 4.4.3
+      IMG: ubuntu:resolute
+
+steps:
+  - name: 'Re-index the slot'
+    image: reg.devxy.io/rpkgs/build-env-${IMG}
+    pull: true
+    environment:
+      OTEL_R_TRACES_EXPORTER: none
+      OTEL_R_LOGS_EXPORTER: none
+      OTEL_R_METRICS_EXPORTER: none
+      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
+      REPO_RO_TOKEN:
+        from_secret: REPO_RO_TOKEN
+      GIT_USER: pat-s
+      R_LIBS_USER: /mnt/cache/R-pkgs
+      R_VERSION: ${R_VERSION}
+      PLATFORM: ${OS}
+      ARCH: ${ARCH}
+    commands:
+      - git clone -q https://pat-s:$$REPO_RO_TOKEN@git.devxy.io/devxy/build-cran-binaries.git .
+      - mkdir -p /mnt/cache/R-pkgs
+      - rm -rf /mnt/cache/R-pkgs/00LOCK-*
+      - /opt/R/$R_VERSION/bin/Rscript local/install-bincraft.R
+      # The codename is detected from the image's /etc/os-release.
+      - /opt/R/$R_VERSION/bin/R -q -e 'library(bincraft); upload_package_index(s3_endpoint = "https://s3.eu-central-003.backblazeb2.com", s3_region = "eu-central-003", s3_bucket = "devxy-rpkgs-binaries", s3_access_key_id = Sys.getenv("B2_S3_ACCESS_KEY"), s3_secret_access_key = Sys.getenv("B2_S3_SECRET_KEY"))'
+      - |
+        for RBIN in /opt/R/[0-9]*/bin/R; do
+          RMINOR=$(basename "$(dirname "$(dirname "$RBIN")")" | cut -d. -f1-2)
+          /opt/R/$R_VERSION/bin/R -q -e "library(bincraft); upload_package_index(r_minor = '$RMINOR', s3_endpoint = 'https://s3.eu-central-003.backblazeb2.com', s3_region = 'eu-central-003', s3_bucket = 'devxy-rpkgs-binaries', s3_access_key_id = Sys.getenv('B2_S3_ACCESS_KEY'), s3_secret_access_key = Sys.getenv('B2_S3_SECRET_KEY'))" || true
+        done
+
+  - name: Purge CDN cache
+    image: reg.devxy.io/docker.io/library/alpine:3.24
+    environment:
+      OTEL_R_TRACES_EXPORTER: none
+      OTEL_R_LOGS_EXPORTER: none
+      OTEL_R_METRICS_EXPORTER: none
+      BUNNYNET_API_KEY:
+        from_secret: BUNNYNET_API_KEY
+      REPO_RO_TOKEN:
+        from_secret: REPO_RO_TOKEN
+      # All hostnames on the zone share this id, so one purge covers
+      # cran.devxy.io, cran.allianceswisspass.devxy.io and cran.rpkgs.com.
+      BUNNY_PULLZONE: '3857050'
+    commands:
+      - apk add --no-cache -q bash curl git
+      - git clone -q https://pat-s:$$REPO_RO_TOKEN@git.devxy.io/devxy/build-cran-binaries.git .
+      - bash scripts/purge_cdn_zone.sh "$BUNNYNET_API_KEY" "$BUNNY_PULLZONE"
+    # Runs on every row rather than on one designated slot: a cron fires only
+    # its own slot's row, so gating on a named slot would leave every other
+    # slot unpurged. A manual "all" run therefore purges the zone 18 times,
+    # which is a cheap API call and rare.
+    #
+    # Run it even when the re-index above failed: the objects were still
+    # replaced, and a stale edge is exactly what keeps them hidden.
+    when:
+      - status: [success, failure]