perf: seed pure-R binaries into a new slot, interleave shards, and stop builds before the timeout (#242)
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

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
This commit is contained in:
Patrick Schratz 2026-10-24 02:04:06 +00:00 • committed by Patrick Schratz
commit e23bd3e539

View file

@ -1,6 +1,7 @@
sink(stdout(), type = "message")
options(crayon.enabled = TRUE, future.globals.onReference = NULL)
source(file.path("local", "r-minor-helpers.R"))
source(file.path("local", "rebuild-missing-helpers.R"))
args <- commandArgs(trailingOnly = TRUE)
parsed <- parse_build_args(args)
@ -104,9 +105,10 @@ sprintf(
sensitive_only
)
# Split into chunks for this worker
chunks <- split(pkgs, cut(seq_len(nrow(pkgs)), split_into, labels = FALSE))
chunk <- chunks[[split_index]]
# Interleave rather than cut the alphabetical list into contiguous blocks: build
# cost clusters by name (Rcpp*, rstan*), and contiguous quarters of the last
# full rebuild ran anywhere from 0.1h to 28h.
chunk <- pkgs[shard_slice(seq_len(nrow(pkgs)), split_into, split_index), ]
sprintf("# of package versions for this job: %s", nrow(chunk))
# Exclude known problematic packages (single source of truth)
@ -126,23 +128,7 @@ chunk <- chunk[!chunk$Package %in% exclude, ]
# environment, so Sys.getenv() would return "" and this pre-filter would query
# platform "-" and skip nothing.
codename <- bincraft::set_codename(NULL)
platform <- switch(
codename,
jammy = "ubuntu-2204",
noble = "ubuntu-2404",
resolute = "ubuntu-2604",
rhel10 = "redhat-10",
rhel9 = "redhat-9",
rhel8 = "redhat-8",
alpine320 = "alpine-320",
alpine321 = "alpine-321",
alpine322 = "alpine-322",
alpine323 = "alpine-323",
alpine324 = "alpine-324",
alpine325 = "alpine-325",
alpine326 = "alpine-326",
NA_character_
)
platform <- codename_platform(codename)
local_machine <- Sys.info()[["machine"]]
arch <- if (grepl("arm64|aarch64", local_machine)) "arm64" else "amd64"
con <- DBI::dbConnect(
@ -232,35 +218,41 @@ sprintf(
length(s3_cache_paths)
)
deadline <- build_deadline()
n <- nrow(chunk)
mapply(
function(pkg, ver, sens, i) {
cat(sprintf("[%d/%d] %s_%s (r_minor_sensitive=%s)\n", i, n, pkg, ver, sens))
bincraft::build_binary_package(
pkg,
tag = ver,
is_r_minor_sensitive = isTRUE(sens),
s3_endpoint = "https://s3.eu-central-003.backblazeb2.com",
s3_region = "eu-central-003",
s3_bucket = "devxy-rpkgs-binaries",
s3_access_key_id = Sys.getenv("B2_S3_ACCESS_KEY"),
s3_secret_access_key = Sys.getenv("B2_S3_SECRET_KEY"),
s3_package_cache = s3_cache,
metadata_db_host = "r-binaries.devxy.io",
metadata_db_name = "build_metadata",
metadata_db_table = "single_builds",
metadata_db_user = "rpkgs",
metadata_db_password = Sys.getenv("PGPASS"),
metadata_db_sslmode = "verify-full",
metadata_db_port = 15432,
archive = TRUE,
patches = "local/patches",
upload = TRUE,
store_build_metadata = TRUE
)
},
chunk$Package,
chunk$Version,
chunk$r_minor_sensitive,
seq_len(n)
)
for (i in seq_len(n)) {
if (deadline_reached(deadline)) {
cat(sprintf(
"Build deadline reached after %d/%d package versions; stopping cleanly. The next run resumes from the metadata DB.\n",
i - 1L,
n
))
break
}
pkg <- chunk$Package[i]
ver <- chunk$Version[i]
sens <- chunk$r_minor_sensitive[i]
cat(sprintf("[%d/%d] %s_%s (r_minor_sensitive=%s)\n", i, n, pkg, ver, sens))
bincraft::build_binary_package(
pkg,
tag = ver,
is_r_minor_sensitive = isTRUE(sens),
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"),
s3_package_cache = s3_cache,
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 = "verify-full",
metadata_db_port = 15432,
archive = TRUE,
patches = "local/patches",
upload = TRUE,
store_build_metadata = TRUE
)
}