build-cran-binaries/local/build-newer-r.R
pat-s e23bd3e539
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
perf: seed pure-R binaries into a new slot, interleave shards, and stop builds before the timeout (#242)
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
2026-10-24 02:04:06 +00:00

171 lines
5.5 KiB
R

source(file.path("local", "newer-r-helpers.R"))
source(file.path("local", "rebuild-missing-helpers.R"))
source(file.path("local", "r-minor-helpers.R"))
args <- commandArgs(trailingOnly = TRUE)
pos <- args[!startsWith(args, "--")]
if (!length(pos) %in% c(1L, 3L)) {
stop("Usage: build-newer-r.R PRIMARY_R [SPLIT_INTO SPLIT_INDEX] [--dry-run]")
}
primary_r <- pos[1L]
target_r <- as.character(getRversion())
pkgs <- newer_r_candidates(tools::CRAN_package_db(), primary_r, target_r)
exclude <- jsonlite::fromJSON("local/excluded-packages.json")[["package"]]
pkgs <- pkgs[!pkgs$Package %in% exclude, , drop = FALSE]
if (length(pos) == 3L) {
pkgs <- pkgs[
shard_slice(seq_len(nrow(pkgs)), pos[2L], pos[3L]),
,
drop = FALSE
]
}
message(sprintf(
"R %s: %d package(s) unsupported by primary R %s",
target_r,
nrow(pkgs),
primary_r
))
if ("--dry-run" %in% args) {
print(pkgs, row.names = FALSE)
} else {
# Most candidates were built on an earlier run. Asking bincraft about each one
# costs a DB connection plus several S3 requests, about 4s a package, so the
# loop spent well over an hour per run re-confirming existing binaries.
# Decide those in bulk first; bincraft still checks whatever is left.
local_machine <- Sys.info()[["machine"]]
arch <- if (grepl("arm64|aarch64", local_machine)) "arm64" else "amd64"
slot_dir <- sprintf(
"devxy-rpkgs-binaries/%s/%s/latest/src/contrib",
arch,
bincraft::set_codename(NULL)
)
s3fs::s3_file_system(
aws_access_key_id = Sys.getenv("B2_S3_ACCESS_KEY"),
aws_secret_access_key = Sys.getenv("B2_S3_SECRET_KEY"),
endpoint = "https://s3.eu-central-003.backblazeb2.com",
region_name = "eu-central-003",
refresh = TRUE
)
# NULL when the listing fails, so that route falls back to bincraft.
list_etags <- function(dir) {
info <- tryCatch(s3fs::s3_dir_info(dir), error = function(e) {
message(sprintf("Could not list %s: %s", dir, conditionMessage(e)))
NULL
})
if (is.null(info)) {
return(NULL)
}
stats::setNames(
gsub('^"|"$', "", as.character(info$etag)),
basename(as.character(info$uri))
)
}
# The verdicts bincraft::classify_r_minor_sensitive() would read from its
# cache, fetched in one query rather than one connection per package.
read_verdicts <- function(packages) {
tryCatch(
{
con <- DBI::dbConnect(
RPostgres::Postgres(),
dbname = "build_metadata",
host = "r-binaries.devxy.io",
port = 15432,
user = "rpkgs",
password = Sys.getenv("PGPASS"),
sslmode = "verify-full",
sslrootcert = bincraft::postgres_sslrootcert("verify-full")
)
on.exit(DBI::dbDisconnect(con), add = TRUE)
rows <- DBI::dbGetQuery(
con,
paste(
"SELECT package, version, r_minor_sensitive FROM abi_classification",
"WHERE classifier_sig = $1 AND package = ANY($2::text[])"
),
params = list(
bincraft:::abi_classifier_signature(),
paste0("{", paste(packages, collapse = ","), "}")
)
)
stats::setNames(
as.logical(rows$r_minor_sensitive),
paste(rows$package, rows$version, sep = "_")
)
},
error = function(e) {
message(sprintf("Could not read ABI verdicts: %s", conditionMessage(e)))
logical()
}
)
}
sensitive <- read_verdicts(pkgs$Package)
before <- nrow(pkgs)
pkgs <- newer_r_outstanding(
pkgs,
sensitive,
list_etags(slot_dir),
list_etags(file.path(
slot_dir,
sub("^(\\d+\\.\\d+).*", "\\1", target_r)
)),
bincraft:::cran_source_md5()
)
message(sprintf(
"%d of %d already carry a binary at their routed path; %d left for bincraft",
before - nrow(pkgs),
before,
nrow(pkgs)
))
options(crayon.enabled = TRUE, Ncpus = 4, future.globals.onReference = NULL)
deadline <- build_deadline()
for (i in seq_len(nrow(pkgs))) {
if (deadline_reached(deadline)) {
message(sprintf(
"Build deadline reached after %d/%d package(s); stopping cleanly.",
i - 1L,
nrow(pkgs)
))
break
}
message(sprintf(
"[%d/%d] %s %s",
i,
nrow(pkgs),
pkgs$Package[i],
pkgs$Version[i]
))
bincraft::build_binary_package(
pkgs$Package[i],
tag = pkgs$Version[i],
# Keep bincraft's normal ABI routing: safe binaries can be shared;
# sensitive ones use this interpreter's minor for presence and output.
is_r_minor_sensitive = bincraft::classify_r_minor_sensitive(
pkgs$Package[i],
pkgs$Version[i],
metadata_db_host = "r-binaries.devxy.io",
metadata_db_name = "build_metadata",
metadata_db_user = "rpkgs",
metadata_db_password = Sys.getenv("PGPASS"),
metadata_db_sslmode = "verify-full",
metadata_db_port = 15432
),
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 = "verify-full",
metadata_db_port = 15432,
archive = TRUE,
patches = "local/patches",
upload = TRUE,
store_build_metadata = TRUE
)
}
}