feat(abi): skip objects that already have the per-minor builds they need

The verdict in abi_flat_safety describes the *flat* object, and building a
per-minor copy does not change it, so the repair list stays the same after a
run. The first fleet repair was interrupted at 14 of 18 slots having uploaded
2568 objects; resuming would have rebuilt every one of them again.

An object is repaired once a per-minor build exists for every minor that cannot
load the flat one, and the bucket is the source of truth for that. Where no
minors are recorded -- unsafe without a reason -- a build under every minor the
image carries is required, rather than assuming one is enough.

This change will:

- list the slot's objects from S3 and drop the rows already covered
- report how many were skipped, so an unexpectedly short list is visible rather
  than silent
- fail rather than proceed when the bucket cannot be listed, since an empty
  listing would make everything look unrepaired
This commit is contained in:
Patrick Schratz 2026-09-09 10:28:28 +00:00
commit f49ad8faa3
No known key found for this signature in database
GPG key ID: 62050D5BC68AB6DC

View file

@ -37,13 +37,92 @@ on.exit(try(DBI::dbDisconnect(con), silent = TRUE), add = TRUE)
rows <- DBI::dbGetQuery( rows <- DBI::dbGetQuery(
con, con,
paste0( paste0(
"SELECT package, version FROM abi_flat_safety ", "SELECT package, version, unsupported FROM abi_flat_safety ",
"WHERE NOT safe AND codename = $1 AND arch = $2 ", "WHERE NOT safe AND codename = $1 AND arch = $2 ",
"ORDER BY package, version" "ORDER BY package, version"
), ),
params = list(codename, arch) params = list(codename, arch)
) )
# Drop what is already repaired. The verdict describes the *flat* object, and a
# per-minor build does not change it, so a resumed run would otherwise rebuild
# everything it did last time: ~2500 objects of duplicated compute after the
# first fleet run was interrupted.
#
# An object is repaired once a per-minor build exists for every minor that
# cannot load the flat one. The bucket is the source of truth for that, and it
# cannot be routed.
if (nrow(rows) > 0L) {
s3fs::s3_file_system(
aws_access_key_id = Sys.getenv("B2_S3_ACCESS_KEY"),
aws_secret_access_key = Sys.getenv("B2_S3_SECRET_KEY"),
endpoint = "https://s3.eu-central-003.backblazeb2.com",
region_name = "eu-central-003",
refresh = TRUE
)
contrib <- sprintf(
"devxy-rpkgs-binaries/%s/%s/latest/src/contrib",
arch,
codename
)
objects <- tryCatch(
s3fs::s3_dir_ls(contrib, recurse = TRUE),
error = function(e) character(0)
)
if (length(objects) == 0L) {
stop(
sprintf(
"Could not list %s; refusing to guess what is already repaired.",
contrib
),
call. = FALSE
)
}
present <- sub(sprintf("^(s3://)?%s/", contrib), "", objects)
# No recorded minors means unsafe without a reason, so require a build under
# every minor the image carries rather than assume one is enough.
installed <- sub(
"^([0-9]+[.][0-9]+).*$",
"\\1",
basename(list.dirs("/opt/R", recursive = FALSE))
)
installed <- unique(installed[grepl("^[0-9]+[.][0-9]+$", installed)])
repaired <- vapply(
seq_len(nrow(rows)),
function(i) {
u <- rows$unsupported[[i]]
minors <- if (is.na(u) || !nzchar(u)) {
installed
} else {
trimws(strsplit(u, ",", fixed = TRUE)[[1L]])
}
if (length(minors) == 0L) {
return(FALSE)
}
wanted <- sprintf(
"%s/%s_%s.tar.gz",
minors,
rows$package[[i]],
rows$version[[i]]
)
all(wanted %in% present)
},
logical(1L)
)
if (any(repaired)) {
message(sprintf(
"%s/%s: %d of %d already have per-minor builds for every minor that needs one; skipping those.",
arch,
codename,
sum(repaired),
nrow(rows)
))
}
rows <- rows[!repaired, , drop = FALSE]
}
# An empty result is ambiguous: either nothing is unsafe, or the backfill never # An empty result is ambiguous: either nothing is unsafe, or the backfill never
# ran for this slot. Say which, rather than let the caller read silence as done. # ran for this slot. Say which, rather than let the caller read silence as done.
if (nrow(rows) == 0L) { if (nrow(rows) == 0L) {