build-cran-binaries/local/build-all.R
pat-s 642e07e1d6
Some checks are pending
ci/crow/manual/build-all-versions/5 Pipeline is running
ci/crow/manual/build-all-versions/6 Pipeline is running
ci/crow/manual/build-all-versions/8 Pipeline is running
ci/crow/manual/build-all-versions/7 Pipeline is running
ci/crow/manual/build-all-versions-install-deps/2 Pipeline was successful
ci/crow/manual/build-all-versions-install-deps/1 Pipeline was successful
ci/crow/manual/build-all-versions/1 Pipeline is running
ci/crow/manual/build-all-versions/2 Pipeline is running
ci/crow/cron/process-updates/8 Pipeline is pending
ci/crow/manual/build-all-versions/3 Pipeline is running
ci/crow/cron/process-updates/9 Pipeline is pending
ci/crow/manual/build-all-versions/4 Pipeline is running
ci/crow/cron/process-updates/3 Pipeline is pending
fix(build): recompute a stale package snapshot, not just a missing one (#190)
## Motivation

`arm64/alpine324` reported nothing to build while thousands were missing:

```
line  49: Precomputed 7192 package versions (6871 r-minor-sensitive)   <- install-deps agent
line  99: Total# of remaining package versions: 43 (sensitive_only=TRUE) <- a build shard
line 101: Skipped 0 package versions already attempted under R 4.4; 0 remaining
```

Both numbers come from the **same pipeline**. The same run's index step dropped 2407 packages as missing for 4.4 and 2436 for 4.6.

## Cause

```r
if (!all(file.exists(package_cache_files))) { ... recompute ... }
```

Existence is not freshness. The snapshot describes S3 and CRAN state when it was written, and the cache volume is per-agent — the file's own comment says so. An agent that ran an earlier pipeline keeps serving that pipeline's answer forever, and no later fix to how the snapshot is computed (#189) can reach it.

## Change

Recompute when the snapshot is stale as well as when it is missing. Keyed on the pipeline when the CI exposes an identifier (`CI_PIPELINE_NUMBER`, `CI_BUILD_NUMBER`, `CI_PIPELINE_ID`), so a new pipeline recomputes once per agent and its shards then share the result. Off CI, or when none is set, an age check with a two hour default (`PACKAGE_SNAPSHOT_TTL_HOURS`).

## Verification

| scenario | decision |
|---|---|
| files missing | RECOMPUTE |
| same pipeline id | reuse |
| **new pipeline id** | **RECOMPUTE** |
| no CI var, recent file | reuse |
| no CI var, aged out | RECOMPUTE |

I could not confirm which identifier Crow actually sets — none is referenced anywhere in this repo — so all three are tried and the age check backs them up. If none is present the behaviour is the age path, which is still correct, just coarser.

Reviewed-on: #190
2026-08-31 22:11:17 +00:00

226 lines
8.1 KiB
R

sink(stdout(), type = "message")
options(crayon.enabled = TRUE, future.globals.onReference = NULL)
source(file.path("local", "r-minor-helpers.R"))
args <- commandArgs(trailingOnly = TRUE)
parsed <- parse_build_args(args)
split_into <- parsed$split_into
split_index <- parsed$split_index
ncpus <- parsed$ncpus
sensitive_only <- parsed$sensitive_only
options(Ncpus = ncpus)
# Load bincraft eagerly to avoid lazy-load memory spike during first build call
library(bincraft, quietly = TRUE)
library(future)
plan("sequential")
# The install-deps step precomputes the package snapshot into /mnt/cache, but
# that volume is per-agent: a job landing on a fresh agent (or racing
# install-deps) finds it empty. Recompute the snapshot here when any part is
# missing, so the first job on an agent repopulates the cache for the jobs that
# follow; concurrent jobs that also miss simply redo the work. Write via a
# temp file + atomic rename so a concurrent reader never sees a half-written rds.
package_cache_files <- c(
"/mnt/cache/packages/pkgs_to_build.rds",
"/mnt/cache/packages/r_minor_sensitive_pkgs.rds",
"/mnt/cache/packages/s3_cache.rds"
)
# Existence is not freshness. The snapshot describes S3 and CRAN state at the
# moment it was written, and the volume is per-agent, so an agent that ran an
# earlier pipeline keeps serving that pipeline's answer forever. arm64/alpine324
# reported "0 remaining" for both 4.4 and 4.6 from a stale snapshot listing 43
# sensitive packages, while the install-deps step in the very same pipeline had
# just computed 6871 on another agent.
#
# Keyed on the pipeline when the CI exposes one, so a new pipeline recomputes
# once per agent and its shards then share the result. Off CI, or when no such
# variable is set, fall back to an age check.
snapshot_id_path <- "/mnt/cache/packages/snapshot.id"
snapshot_ttl_hours <- as.numeric(
Sys.getenv("PACKAGE_SNAPSHOT_TTL_HOURS", unset = "2")
)
current_snapshot_id <- ""
for (v in c("CI_PIPELINE_NUMBER", "CI_BUILD_NUMBER", "CI_PIPELINE_ID")) {
val <- Sys.getenv(v, unset = "")
if (nzchar(val)) {
current_snapshot_id <- paste(v, val, sep = "=")
break
}
}
snapshot_is_stale <- function() {
if (!all(file.exists(package_cache_files))) {
return(TRUE)
}
if (nzchar(current_snapshot_id)) {
cached <- tryCatch(
readLines(snapshot_id_path, warn = FALSE)[1L],
error = function(e) NA_character_,
warning = function(w) NA_character_
)
return(!identical(cached, current_snapshot_id))
}
age_hours <- as.numeric(
difftime(Sys.time(), file.mtime(package_cache_files[1L]), units = "hours")
)
isTRUE(age_hours > snapshot_ttl_hours)
}
if (snapshot_is_stale()) {
message(
"Package snapshot missing or stale; recomputing via packages-to-build.R"
)
dir.create("/mnt/cache/packages", showWarnings = FALSE, recursive = TRUE)
save_rds_atomic <- function(obj, path) {
tmp <- paste0(path, ".tmp.", Sys.getpid())
saveRDS(obj, tmp)
file.rename(tmp, path)
}
source(file.path("local", "packages-to-build.R"))
save_rds_atomic(pkgs, "/mnt/cache/packages/pkgs_to_build.rds")
save_rds_atomic(
pkgs[r_minor_sensitive == TRUE],
"/mnt/cache/packages/r_minor_sensitive_pkgs.rds"
)
if (nzchar(current_snapshot_id)) {
writeLines(current_snapshot_id, snapshot_id_path)
}
message("Package snapshot recomputed.")
}
pkgs <- if (sensitive_only) {
readRDS("/mnt/cache/packages/r_minor_sensitive_pkgs.rds")
} else {
readRDS("/mnt/cache/packages/pkgs_to_build.rds")
}
# Back-compat: tolerate an older RDS without the column (treat all as non-sensitive)
if (is.null(pkgs$r_minor_sensitive)) {
pkgs$r_minor_sensitive <- FALSE
}
sprintf(
"Total# of remaining package versions: %s (sensitive_only=%s)",
nrow(pkgs),
sensitive_only
)
# Split into chunks for this worker
chunks <- split(pkgs, cut(seq_len(nrow(pkgs)), split_into, labels = FALSE))
chunk <- chunks[[split_index]]
sprintf("# of package versions for this job: %s", nrow(chunk))
# Exclude known problematic packages (single source of truth)
exclude <- jsonlite::fromJSON("local/excluded-packages.json")[["package"]]
chunk <- chunk[!chunk$Package %in% exclude, ]
# Skip package versions already attempted in a previous run (built or errored).
# pkgs_to_build.rds is a static snapshot from the install-deps step, so on a
# restart it still lists everything an interrupted run already produced. The
# metadata DB reflects that progress, so we re-derive the remaining set here.
# We exclude *all* attempted versions, not just successful ones: a previously
# errored version is skipped by build_binary_package() anyway, so leaving it in
# the chunk only makes the job cycle through it one-by-one for no benefit.
# Derive platform + arch from the running container, mirroring the codename ->
# platform mapping bincraft uses internally. The OS/OS_VERSION selectors are
# workflow-level CI variables that are not injected into the container
# 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_
)
local_machine <- Sys.info()[["machine"]]
arch <- if (grepl("arm64|aarch64", local_machine)) "arm64" else "amd64"
con <- DBI::dbConnect(
RPostgres::Postgres(),
dbname = "build_metadata",
host = "r-binaries.devxy.io",
port = 15432,
user = "rpkgs",
password = Sys.getenv("PGPASS"),
sslmode = "require"
)
# Scope the skip to the R minor this pass is running under. `single_builds`
# records `r_version` per attempt, but querying without it made a non-primary
# pass skip everything the primary pass had already attempted under a different
# minor - so `--sensitive-only` under 4.6 skipped packages that had only ever
# been built for 4.5, and the per-minor slots never filled. That is why
# amd64/resolute served 4000 fewer packages to a 4.6 client than to a 4.5 one.
r_minor <- paste(
R.version$major,
strsplit(R.version$minor, ".", fixed = TRUE)[[1L]][1L],
sep = "."
)
built <- DBI::dbGetQuery(
con,
paste(
"SELECT name, tag FROM single_builds",
"WHERE platform = $1 AND arch = $2",
"AND substring(r_version from '^[0-9]+[.][0-9]+') = $3"
),
params = list(platform, arch, r_minor)
)
DBI::dbDisconnect(con)
before <- nrow(chunk)
chunk <- chunk[
!paste(chunk$Package, chunk$Version) %in% paste(built$name, built$tag),
]
sprintf(
"Skipped %d package versions already attempted under R %s; %d remaining for this job",
before - nrow(chunk),
r_minor,
nrow(chunk)
)
# Read pre-computed S3 listing from install-deps step
# This avoids loading s3fs/reticulate/Python in the build container,
# saving significant memory for the dependency-installer subprocesses
s3_cache <- readRDS("/mnt/cache/packages/s3_cache.rds")
sprintf("S3 cache: %s files", length(s3_cache))
n <- nrow(chunk)
mapply(
function(pkg, ver, sens, i) {
cat(sprintf("[%d/%d] %s_%s (r_minor_sensitive=%s)\n", i, n, pkg, ver, sens))
bincraft::build_binary_package(
pkg,
tag = ver,
is_r_minor_sensitive = isTRUE(sens),
s3_endpoint = "https://s3.eu-central-003.backblazeb2.com",
s3_region = "eu-central-003",
s3_bucket = "devxy-rpkgs-binaries",
s3_access_key_id = Sys.getenv("B2_S3_ACCESS_KEY"),
s3_secret_access_key = Sys.getenv("B2_S3_SECRET_KEY"),
s3_package_cache = s3_cache,
metadata_db_host = "r-binaries.devxy.io",
metadata_db_name = "build_metadata",
metadata_db_table = "single_builds",
metadata_db_user = "rpkgs",
metadata_db_password = Sys.getenv("PGPASS"),
metadata_db_sslmode = "require",
metadata_db_port = 15432,
archive = TRUE,
patches = "local/patches",
upload = TRUE,
store_build_metadata = TRUE
)
},
chunk$Package,
chunk$Version,
chunk$r_minor_sensitive,
seq_len(n)
)