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
5 changed files with 838 additions and 36 deletions
--- a/.crow/weekly-rebuild-missing.yaml
+++ b/.crow/weekly-rebuild-missing.yaml
@ -1,12 +1,21 @@
 # Consolidated weekly-rebuild-missing pipeline (all platforms, both arches).
-# One matrix row per OS/arch replaces the former per-platform files.
+# Three matrix rows per OS/arch, one per shard of that slot's rebuild list.
 # Routing is preserved 1:1:
 #   - cron:   each existing `weekly-rebuild-missing-<os>-<arch>` cron fires only
-#             its matching matrix row (via the per-row `cron:` name filter).
+#             its matching matrix rows (via the per-row `cron:` name filter),
+#             which is now all three shards of that slot.
 #   - manual: `weekly_rebuild_missing` dropdown, default "all" (matches the
 #             previous bare manual trigger that ran every os/arch); pick a
 #             single <os>-<arch> to run just one.
 # Arch placement is handled by the group label (rpkgs-amd64, rpkgs-arm64).
+#
+# The shard picks up its own slice and re-derives what is still outstanding
+# from the bucket, so a restart resumes rather than replaying; see
+# local/rebuild-missing.R.
+#
+# Re-indexing and the CDN purge deliberately do NOT live here. Three shards
+# writing one slot's PACKAGES concurrently would race, so they moved to
+# .crow/weekly-rebuild-reindex.yaml, which depends on this pipeline.
 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
@ -53,74 +62,326 @@ matrix:
      ARCH: amd64
      R_VERSION: 4.5.3
      IMG: alpine:3.22
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 1
+    - OS: alpine-322
+      ARCH: amd64
+      R_VERSION: 4.5.3
+      IMG: alpine:3.22
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 2
+    - OS: alpine-322
+      ARCH: amd64
+      R_VERSION: 4.5.3
+      IMG: alpine:3.22
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 3
    - OS: alpine-322
      ARCH: arm64
      R_VERSION: 4.5.3
      IMG: alpine:3.22
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 1
+    - OS: alpine-322
+      ARCH: arm64
+      R_VERSION: 4.5.3
+      IMG: alpine:3.22
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 2
+    - OS: alpine-322
+      ARCH: arm64
+      R_VERSION: 4.5.3
+      IMG: alpine:3.22
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 3
    - OS: alpine-323
      ARCH: amd64
      R_VERSION: 4.5.3
      IMG: alpine:3.23
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 1
+    - OS: alpine-323
+      ARCH: amd64
+      R_VERSION: 4.5.3
+      IMG: alpine:3.23
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 2
+    - OS: alpine-323
+      ARCH: amd64
+      R_VERSION: 4.5.3
+      IMG: alpine:3.23
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 3
    - OS: alpine-323
      ARCH: arm64
      R_VERSION: 4.5.3
      IMG: alpine:3.23
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 1
+    - OS: alpine-323
+      ARCH: arm64
+      R_VERSION: 4.5.3
+      IMG: alpine:3.23
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 2
+    - OS: alpine-323
+      ARCH: arm64
+      R_VERSION: 4.5.3
+      IMG: alpine:3.23
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 3
    - OS: alpine-324
      ARCH: amd64
      R_VERSION: 4.5.3
      IMG: alpine:3.24
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 1
+    - OS: alpine-324
+      ARCH: amd64
+      R_VERSION: 4.5.3
+      IMG: alpine:3.24
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 2
+    - OS: alpine-324
+      ARCH: amd64
+      R_VERSION: 4.5.3
+      IMG: alpine:3.24
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 3
    - OS: alpine-324
      ARCH: arm64
      R_VERSION: 4.5.3
      IMG: alpine:3.24
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 1
+    - OS: alpine-324
+      ARCH: arm64
+      R_VERSION: 4.5.3
+      IMG: alpine:3.24
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 2
+    - OS: alpine-324
+      ARCH: arm64
+      R_VERSION: 4.5.3
+      IMG: alpine:3.24
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 3
    - OS: redhat-8
      ARCH: amd64
      R_VERSION: 4.4.3
      IMG: redhat:8
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 1
+    - OS: redhat-8
+      ARCH: amd64
+      R_VERSION: 4.4.3
+      IMG: redhat:8
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 2
+    - OS: redhat-8
+      ARCH: amd64
+      R_VERSION: 4.4.3
+      IMG: redhat:8
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 3
    - OS: redhat-8
      ARCH: arm64
      R_VERSION: 4.4.3
      IMG: redhat:8
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 1
+    - OS: redhat-8
+      ARCH: arm64
+      R_VERSION: 4.4.3
+      IMG: redhat:8
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 2
+    - OS: redhat-8
+      ARCH: arm64
+      R_VERSION: 4.4.3
+      IMG: redhat:8
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 3
    - OS: redhat-9
      ARCH: amd64
      R_VERSION: 4.4.3
      IMG: redhat:9
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 1
+    - OS: redhat-9
+      ARCH: amd64
+      R_VERSION: 4.4.3
+      IMG: redhat:9
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 2
+    - OS: redhat-9
+      ARCH: amd64
+      R_VERSION: 4.4.3
+      IMG: redhat:9
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 3
    - OS: redhat-9
      ARCH: arm64
      R_VERSION: 4.4.3
      IMG: redhat:9
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 1
+    - OS: redhat-9
+      ARCH: arm64
+      R_VERSION: 4.4.3
+      IMG: redhat:9
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 2
+    - OS: redhat-9
+      ARCH: arm64
+      R_VERSION: 4.4.3
+      IMG: redhat:9
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 3
    - OS: redhat-10
      ARCH: amd64
      R_VERSION: 4.5.3
      IMG: redhat:10
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 1
+    - OS: redhat-10
+      ARCH: amd64
+      R_VERSION: 4.5.3
+      IMG: redhat:10
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 2
+    - OS: redhat-10
+      ARCH: amd64
+      R_VERSION: 4.5.3
+      IMG: redhat:10
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 3
    - OS: redhat-10
      ARCH: arm64
      R_VERSION: 4.5.3
      IMG: redhat:10
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 1
+    - OS: redhat-10
+      ARCH: arm64
+      R_VERSION: 4.5.3
+      IMG: redhat:10
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 2
+    - OS: redhat-10
+      ARCH: arm64
+      R_VERSION: 4.5.3
+      IMG: redhat:10
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 3
    - OS: ubuntu-2204
      ARCH: amd64
      R_VERSION: 4.4.3
      IMG: ubuntu:jammy
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 1
+    - OS: ubuntu-2204
+      ARCH: amd64
+      R_VERSION: 4.4.3
+      IMG: ubuntu:jammy
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 2
+    - OS: ubuntu-2204
+      ARCH: amd64
+      R_VERSION: 4.4.3
+      IMG: ubuntu:jammy
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 3
    - OS: ubuntu-2204
      ARCH: arm64
      R_VERSION: 4.4.3
      IMG: ubuntu:jammy
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 1
+    - OS: ubuntu-2204
+      ARCH: arm64
+      R_VERSION: 4.4.3
+      IMG: ubuntu:jammy
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 2
+    - OS: ubuntu-2204
+      ARCH: arm64
+      R_VERSION: 4.4.3
+      IMG: ubuntu:jammy
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 3
    - OS: ubuntu-2404
      ARCH: amd64
      R_VERSION: 4.4.3
      IMG: ubuntu:noble
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 1
+    - OS: ubuntu-2404
+      ARCH: amd64
+      R_VERSION: 4.4.3
+      IMG: ubuntu:noble
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 2
+    - OS: ubuntu-2404
+      ARCH: amd64
+      R_VERSION: 4.4.3
+      IMG: ubuntu:noble
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 3
    - OS: ubuntu-2404
      ARCH: arm64
      R_VERSION: 4.4.3
      IMG: ubuntu:noble
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 1
+    - OS: ubuntu-2404
+      ARCH: arm64
+      R_VERSION: 4.4.3
+      IMG: ubuntu:noble
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 2
+    - OS: ubuntu-2404
+      ARCH: arm64
+      R_VERSION: 4.4.3
+      IMG: ubuntu:noble
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 3
    - OS: ubuntu-2604
      ARCH: amd64
      R_VERSION: 4.4.3
      IMG: ubuntu:resolute
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 1
+    - OS: ubuntu-2604
+      ARCH: amd64
+      R_VERSION: 4.4.3
+      IMG: ubuntu:resolute
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 2
+    - OS: ubuntu-2604
+      ARCH: amd64
+      R_VERSION: 4.4.3
+      IMG: ubuntu:resolute
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 3
    - OS: ubuntu-2604
      ARCH: arm64
      R_VERSION: 4.4.3
      IMG: ubuntu:resolute
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 1
+    - OS: ubuntu-2604
+      ARCH: arm64
+      R_VERSION: 4.4.3
+      IMG: ubuntu:resolute
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 2
+    - OS: ubuntu-2604
+      ARCH: arm64
+      R_VERSION: 4.4.3
+      IMG: ubuntu:resolute
+      SPLIT_INTO: 3
+      SPLIT_INDEX: 3

 steps:
  - name: 'Rebuild missing binaries'
@ -153,6 +414,12 @@ steps:
      PLATFORM: ${OS}
      ARCH: ${ARCH}
      NCPUS: 2
+      SPLIT_INTO: ${SPLIT_INTO}
+      SPLIT_INDEX: ${SPLIT_INDEX}
+      # Wall clock after which the shard stops cleanly instead of having to be
+      # killed. A kill matches neither `success` nor `failure`, so it would skip
+      # the dependent re-index and leave rebuilt binaries behind a stale edge.
+      REBUILD_BUDGET_HOURS: 20
    commands:
      - git clone -q https://pat-s:$$REPO_RO_TOKEN@git.devxy.io/devxy/build-cran-binaries.git .
      - mkdir -p /mnt/cache/uvr/cache /mnt/cache/uvr/packages /mnt/cache/R-pkgs /mnt/cache/ccache /mnt/cache/packages
@ -162,18 +429,7 @@ steps:
      - 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
      - UVR_R_BIN=/opt/R/$R_VERSION/bin/R local/uvr-install.sh httr2
      - /opt/R/$R_VERSION/bin/R -q -e 'source("local/fetch-rebuild-packages-from-issue.R")'
-      - $XVFB $XVFB_ARGS -- /opt/R/$R_VERSION/bin/R -q -e "sink(stdout(), type = 'message'); options(crayon.enabled = TRUE, Ncpus = $NCPUS, future.globals.onReference = NULL); pkgs <- readLines('/tmp/rebuild_pkgs.txt'); if (length(pkgs) == 0) { cat('Nothing to rebuild\n'); q('no') }; excluded <- jsonlite::fromJSON('local/excluded-packages.json')[['package']]; pkgs <- setdiff(pkgs, excluded); cat(sprintf('Rebuilding %d packages\n', length(pkgs))); n <- length(pkgs); for (i in seq_along(pkgs)) { x <- pkgs[i]; cat(sprintf('[%d/%d] %s\n', i, n, x)); tryCatch(bincraft::build_binary_package(x, tag_limit = 1L, patches = 'local/patches', 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_table = 'single_builds', metadata_db_user = 'rpkgs', metadata_db_password = Sys.getenv('PGPASS'), metadata_db_sslmode = 'require', metadata_db_port = 15432, archive = TRUE, upload = TRUE, store_build_metadata = TRUE), error = function(e) cat(sprintf('ERROR building %s - %s\n', x, conditionMessage(e)))) }" 2>&1
-      # A rebuild 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-index here rather than waiting for the next process-updates
-      # run, or the rebuilt binaries stay invisible to clients until then.
-      # 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
+      - $XVFB $XVFB_ARGS -n $SPLIT_INDEX -- /opt/R/$R_VERSION/bin/Rscript local/rebuild-missing.R $SPLIT_INTO $SPLIT_INDEX $REBUILD_BUDGET_HOURS 2>&1
    backend_options:
      docker:
        resources:
@ -183,25 +439,3 @@ steps:
          limits:
            memory: 18Gi
            cpu: 3000m
-
-  - 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"
-    # A rebuild that died part-way still replaced objects, and those are exactly
-    # the ones a stale edge would keep hiding, so purge either way.
-    when:
-      - status: [success, failure]
--- 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]
--- a/local/rebuild-missing-helpers.R
+++ b/local/rebuild-missing-helpers.R
@ -0,0 +1,87 @@
+# Pure helpers for local/rebuild-missing.R, kept separate so local/tests can
+# source them without executing a rebuild.
+
+# Interleaved slice of the rebuild list.
+#
+# The list is alphabetical and build cost clusters by name (Rcpp*, Bioc*,
+# rstan*), so contiguous thirds would be badly unbalanced. Interleaving also
+# makes each shard's progress counter representative of the slot as a whole.
+shard_slice <- function(pkgs, split_into, split_index) {
+  split_into <- as.integer(split_into)
+  split_index <- as.integer(split_index)
+  if (is.na(split_into) || is.na(split_index)) {
+    stop("shard_slice(): split_into and split_index must be integers")
+  }
+  if (split_into < 1L || split_index < 1L || split_index > split_into) {
+    stop(sprintf(
+      "shard_slice(): need 1 <= split_index <= split_into, got %s of %s",
+      split_index,
+      split_into
+    ))
+  }
+  # seq() errors on a descending range, which is what an empty list or a shard
+  # index past the end would produce.
+  if (length(pkgs) < split_index) {
+    return(pkgs[0L])
+  }
+  pkgs[seq.int(split_index, length(pkgs), by = split_into)]
+}
+
+# Packages that still need building, decided from the bucket rather than from
+# remembered progress.
+#
+# This is bincraft's `check_s3_root_package()` evaluated in bulk: an object
+# whose ETag equals CRAN's published MD5sum is byte-identical to CRAN's source,
+# so the build that was supposed to replace it has not happened yet.
+#
+# `etag_by_file`  named by `<pkg>_<ver>.tar.gz`, values are unquoted ETags
+# `cran_version`  named by package
+# `cran_md5`      named by `<pkg>_<ver>`
+#
+# Unknown always means "already a binary", never "rebuild it", so an unreadable
+# CRAN index or a multipart ETag can never mass-schedule work.
+outstanding_packages <- function(pkgs, etag_by_file, cran_version, cran_md5) {
+  if (length(pkgs) == 0L) {
+    return(pkgs)
+  }
+
+  # An empty table indexes to zero length rather than to NA, which would
+  # recycle the whole result away and silently report "nothing to build".
+  lookup <- function(table, key) {
+    if (length(table) == 0L) {
+      return(rep(NA_character_, length(key)))
+    }
+    unname(as.character(table[key]))
+  }
+
+  version <- lookup(cran_version, pkgs)
+  file <- sprintf("%s_%s.tar.gz", pkgs, version)
+  etag <- lookup(etag_by_file, file)
+  md5 <- lookup(cran_md5, paste(pkgs, version, sep = "_"))
+
+  # No CRAN version means the package cannot be resolved to a tarball at all;
+  # leave it in and let bincraft report why.
+  unresolved <- is.na(version)
+  # No object at the key: never built, so it is outstanding by definition.
+  absent <- !unresolved & is.na(etag)
+  # A multipart upload carries a compound ETag rather than an MD5.
+  unknown <- !is.na(etag) & grepl("-", etag, fixed = TRUE)
+
+  is_source <- !unresolved &
+    !is.na(etag) &
+    !unknown &
+    !is.na(md5) &
+    etag == md5
+
+  pkgs[unresolved | absent | is_source]
+}
+
+parse_rebuild_args <- function(args) {
+  pos <- args[!startsWith(args, "--")]
+  budget <- as.numeric(pos[3L])
+  list(
+    split_into = as.integer(pos[1L]),
+    split_index = as.integer(pos[2L]),
+    budget_hours = if (is.na(budget)) 20 else budget
+  )
+}
--- a/local/rebuild-missing.R
+++ b/local/rebuild-missing.R
@ -0,0 +1,194 @@
+### Rebuild one shard of a slot's missing-binary list.
+#
+# Usage: Rscript local/rebuild-missing.R <split_into> <split_index> [budget_hours]
+#
+# The list itself comes from local/fetch-rebuild-packages-from-issue.R, which
+# writes $REBUILD_PKG_LIST (default /tmp/rebuild_pkgs.txt).
+#
+# Two properties matter here and are the reason this is a script rather than an
+# `R -q -e` argument in the pipeline:
+#
+#   * it is restartable. The outstanding set is re-derived from the bucket on
+#     every start, so a shard that died resumes where it stopped without any
+#     progress file, and without replaying thousands of per-package HEADs.
+#   * it terminates. A wall-clock budget stops the loop cleanly instead of the
+#     run having to be killed, which is what previously skipped the re-index and
+#     CDN purge and left rebuilt binaries hidden behind stale edge copies.
+
+options(error = function() {
+  cat("ERROR:", geterrmessage(), "\n", file = stdout())
+  traceback(2)
+  q(status = 1)
+})
+
+library(bincraft, quietly = TRUE)
+
+source(file.path("local", "rebuild-missing-helpers.R"))
+
+args <- parse_rebuild_args(commandArgs(trailingOnly = TRUE))
+if (is.na(args$split_into) || is.na(args$split_index)) {
+  stop("usage: rebuild-missing.R <split_into> <split_index> [budget_hours]")
+}
+
+list_file <- Sys.getenv("REBUILD_PKG_LIST", "/tmp/rebuild_pkgs.txt")
+pkgs <- if (file.exists(list_file)) readLines(list_file) else character(0)
+pkgs <- pkgs[nzchar(pkgs)]
+if (length(pkgs) == 0L) {
+  cat("Nothing to rebuild\n")
+  q("no")
+}
+
+excluded <- jsonlite::fromJSON("local/excluded-packages.json")[["package"]]
+pkgs <- setdiff(pkgs, excluded)
+
+mine <- shard_slice(pkgs, args$split_into, args$split_index)
+cat(sprintf(
+  "Shard %s/%s: %s of %s listed packages\n",
+  args$split_index,
+  args$split_into,
+  length(mine),
+  length(pkgs)
+))
+
+### Resume: ask the bucket what is still outstanding
+
+codename <- bincraft::set_codename(NULL)
+local_machine <- Sys.info()[["machine"]]
+arch <- if (grepl("arm64|aarch64", local_machine)) "arm64" else "amd64"
+slot_dir <- sprintf(
+  "devxy-rpkgs-binaries/%s/%s/latest/src/contrib",
+  arch,
+  codename
+)
+
+s3fs::s3_file_system(
+  aws_access_key_id = Sys.getenv("B2_S3_ACCESS_KEY"),
+  aws_secret_access_key = Sys.getenv("B2_S3_SECRET_KEY"),
+  endpoint = "https://s3.eu-central-003.backblazeb2.com",
+  region_name = "eu-central-003",
+  refresh = TRUE
+)
+
+# One paginated listing instead of a HEAD per package. Not recursed: the
+# rebuild passes no `is_r_minor_sensitive`, so it only ever targets the flat
+# path, and the resume filter matches that scope deliberately.
+info <- tryCatch(s3fs::s3_dir_info(slot_dir), error = function(e) NULL)
+etag_by_file <- if (is.null(info) || nrow(info) == 0L) {
+  cat(sprintf(
+    "WARNING: could not list %s; building the whole shard\n",
+    slot_dir
+  ))
+  stats::setNames(character(), character())
+} else {
+  stats::setNames(
+    gsub('^"|"$', "", as.character(info$etag)),
+    basename(as.character(info$uri))
+  )
+}
+
+cran <- tryCatch(
+  {
+    con <- gzcon(url(
+      "https://cloud.r-project.org/src/contrib/PACKAGES.gz",
+      open = "rb"
+    ))
+    on.exit(close(con), add = TRUE)
+    read.dcf(con, fields = c("Package", "Version", "MD5sum"))
+  },
+  error = function(e) {
+    cat(sprintf(
+      "WARNING: could not read CRAN's index (%s)\n",
+      conditionMessage(e)
+    ))
+    NULL
+  }
+)
+cran_version <- stats::setNames(character(), character())
+cran_md5 <- stats::setNames(character(), character())
+if (!is.null(cran)) {
+  cran_version <- stats::setNames(
+    as.character(cran[, "Version"]),
+    as.character(cran[, "Package"])
+  )
+  keep <- !is.na(cran[, "MD5sum"])
+  cran_md5 <- stats::setNames(
+    as.character(cran[keep, "MD5sum"]),
+    paste(cran[keep, "Package"], cran[keep, "Version"], sep = "_")
+  )
+}
+
+before <- length(mine)
+mine <- outstanding_packages(mine, etag_by_file, cran_version, cran_md5)
+cat(sprintf(
+  "Resume: %s of %s already carry a binary; %s outstanding\n",
+  before - length(mine),
+  before,
+  length(mine)
+))
+
+if (length(mine) == 0L) {
+  cat("Nothing outstanding for this shard\n")
+  q("no")
+}
+
+### Build
+
+options(
+  crayon.enabled = TRUE,
+  Ncpus = as.integer(Sys.getenv("NCPUS", "2")),
+  future.globals.onReference = NULL
+)
+
+started <- Sys.time()
+n <- length(mine)
+completed <- 0L
+for (i in seq_along(mine)) {
+  elapsed <- as.numeric(difftime(Sys.time(), started, units = "hours"))
+  if (elapsed > args$budget_hours) {
+    cat(sprintf(
+      "Budget of %sh reached after %d/%d packages; stopping cleanly. The next run resumes from the bucket.\n",
+      args$budget_hours,
+      completed,
+      n
+    ))
+    break
+  }
+
+  x <- mine[i]
+  cat(sprintf("[%d/%d] %s\n", i, n, x))
+  tryCatch(
+    bincraft::build_binary_package(
+      x,
+      tag_limit = 1L,
+      patches = "local/patches",
+      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_table = "single_builds",
+      metadata_db_user = "rpkgs",
+      metadata_db_password = Sys.getenv("PGPASS"),
+      metadata_db_sslmode = "require",
+      metadata_db_port = 15432,
+      archive = TRUE,
+      upload = TRUE,
+      store_build_metadata = TRUE
+    ),
+    error = function(e) {
+      cat(sprintf("ERROR building %s - %s\n", x, conditionMessage(e)))
+    }
+  )
+  completed <- completed + 1L
+}
+
+cat(sprintf(
+  "Shard %s/%s finished: %d/%d packages processed in %.1fh\n",
+  args$split_index,
+  args$split_into,
+  completed,
+  n,
+  as.numeric(difftime(Sys.time(), started, units = "hours"))
+))
--- a/local/tests/test-rebuild-missing.R
+++ b/local/tests/test-rebuild-missing.R
@ -0,0 +1,94 @@
+source(file.path("..", "rebuild-missing-helpers.R"))
+
+test_that("shard_slice partitions the list without gaps or overlap", {
+  pkgs <- letters[1:10]
+  parts <- lapply(1:3, function(i) shard_slice(pkgs, 3, i))
+
+  expect_identical(parts[[1]], c("a", "d", "g", "j"))
+  expect_identical(parts[[2]], c("b", "e", "h"))
+  expect_identical(parts[[3]], c("c", "f", "i"))
+
+  expect_identical(sort(unlist(parts)), sort(pkgs))
+  expect_identical(anyDuplicated(unlist(parts)), 0L)
+})
+
+test_that("shard_slice is deterministic and survives short lists", {
+  expect_identical(
+    shard_slice(letters[1:10], 3, 2),
+    shard_slice(letters[1:10], 3, 2)
+  )
+  expect_identical(shard_slice(character(0), 3, 1), character(0))
+  # more shards than packages: the tail shards get nothing rather than erroring
+  expect_identical(shard_slice(c("a"), 3, 1), "a")
+  expect_identical(shard_slice(c("a"), 3, 2), character(0))
+})
+
+test_that("shard_slice rejects an out-of-range index", {
+  expect_error(shard_slice(letters, 3, 4), "split_index")
+  expect_error(shard_slice(letters, 3, 0), "split_index")
+})
+
+test_that("outstanding_packages keeps source fallbacks and drops real binaries", {
+  cran_version <- c(httr = "1.4.8", R6 = "2.6.1", curl = "7.1.0")
+  cran_md5 <- c(
+    httr_1.4.8 = "8756015b94a9cff6f410ca4de8557f12",
+    R6_2.6.1 = "f01b1787f12797c29194d63c9afd5d70",
+    curl_7.1.0 = "8af2ccbf5d85dc18866f45f1f26f348d"
+  )
+  etag <- c(
+    # byte-identical to CRAN: the build never happened
+    "httr_1.4.8.tar.gz" = "8756015b94a9cff6f410ca4de8557f12",
+    # a real binary was published
+    "R6_2.6.1.tar.gz" = "9d6087ee9adda3f0a3b8067cfc652c05"
+    # curl has no object at all
+  )
+
+  out <- outstanding_packages(
+    c("httr", "R6", "curl"),
+    etag,
+    cran_version,
+    cran_md5
+  )
+  expect_identical(out, c("httr", "curl"))
+})
+
+test_that("outstanding_packages treats unknowns as already built", {
+  cran_version <- c(a = "1.0", b = "1.0")
+  cran_md5 <- c(a_1.0 = "aaaa")
+
+  # a multipart ETag carries no MD5, and `b` is missing from CRAN's index:
+  # neither may schedule a rebuild
+  etag <- c("a_1.0.tar.gz" = "abc-3", "b_1.0.tar.gz" = "bbbb")
+
+  expect_identical(
+    outstanding_packages(c("a", "b"), etag, cran_version, cran_md5),
+    character(0)
+  )
+})
+
+test_that("outstanding_packages keeps a package CRAN has no version for", {
+  out <- outstanding_packages(
+    "ghost",
+    c(),
+    c(other = "1.0"),
+    c(other_1.0 = "aaaa")
+  )
+  expect_identical(out, "ghost")
+})
+
+test_that("outstanding_packages handles an empty list", {
+  expect_identical(
+    outstanding_packages(character(0), c(), c(), c()),
+    character(0)
+  )
+})
+
+test_that("parse_rebuild_args defaults the budget", {
+  a <- parse_rebuild_args(c("3", "2"))
+  expect_identical(a$split_into, 3L)
+  expect_identical(a$split_index, 2L)
+  expect_identical(a$budget_hours, 20)
+
+  b <- parse_rebuild_args(c("3", "2", "1.5"))
+  expect_identical(b$budget_hours, 1.5)
+})