build-cran-binaries/cdn.tf
pat-s 2f732457d2
Some checks failed
ci/crow/manual/trial-build-registry/1 Pipeline is pending
ci/crow/manual/trial-build-registry/3 Pipeline is pending
ci/crow/manual/trial-build-registry/5 Pipeline is pending
ci/crow/manual/trial-build-registry/7 Pipeline is pending
ci/crow/manual/trial-build-registry/9 Pipeline is pending
ci/crow/manual/trial-build-registry/11 Pipeline is pending
ci/crow/manual/trial-build-registry/13 Pipeline is pending
ci/crow/manual/trial-build-registry/15 Pipeline is pending
ci/crow/manual/trial-build-registry/17 Pipeline is pending
ci/crow/manual/repair-built-stamp/2 Pipeline failed
ci/crow/manual/weekly-audit-missing/17 Pipeline was successful
ci/crow/manual/weekly-audit-missing/9 Pipeline was successful
ci/crow/manual/weekly-audit-missing/15 Pipeline was successful
ci/crow/manual/weekly-audit-missing/11 Pipeline was successful
ci/crow/manual/weekly-audit-missing/13 Pipeline was successful
ci/crow/manual/weekly-audit-missing/7 Pipeline was successful
ci/crow/manual/trial-build-registry/4 Pipeline was successful
ci/crow/manual/build-all-versions-install-deps/1 Pipeline was successful
ci/crow/manual/trial-build-registry/6 Pipeline was successful
ci/crow/manual/trial-build-registry/2 Pipeline was successful
ci/crow/manual/build-all-versions/1 Pipeline failed
ci/crow/manual/trial-build-registry/8 Pipeline was successful
ci/crow/manual/trial-build-registry/14 Pipeline was successful
ci/crow/manual/trial-build-registry/12 Pipeline was successful
ci/crow/manual/trial-build-registry/10 Pipeline was successful
ci/crow/manual/build-all-versions/2 Pipeline failed
ci/crow/manual/trial-build-registry/16 Pipeline was successful
ci/crow/manual/trial-build-registry/18 Pipeline was successful
ci/crow/manual/weekly-audit-missing/5 Pipeline was successful
ci/crow/manual/weekly-audit-missing/1 Pipeline was successful
ci/crow/manual/auto-apply-patches Pipeline was successful
ci/crow/manual/weekly-audit-missing/3 Pipeline was successful
ci/crow/manual/weekly-audit-missing/2 Pipeline was successful
ci/crow/manual/weekly-audit-missing/4 Pipeline was successful
ci/crow/manual/weekly-audit-missing/6 Pipeline was successful
ci/crow/manual/weekly-audit-missing/8 Pipeline was successful
ci/crow/manual/weekly-audit-missing/10 Pipeline was successful
ci/crow/manual/weekly-audit-missing/12 Pipeline was successful
ci/crow/manual/weekly-audit-missing/14 Pipeline was successful
ci/crow/manual/weekly-audit-missing/16 Pipeline was successful
ci/crow/manual/weekly-audit-missing/18 Pipeline was successful
ci/crow/manual/weekly-patch-proposals Pipeline was successful
ci/crow/manual/process-updates/6 Pipeline was successful
ci/crow/manual/build-all-versions/4 Pipeline failed
ci/crow/manual/build-all-versions/3 Pipeline failed
ci/crow/manual/weekly-rebuild-missing/13 Pipeline was successful
ci/crow/manual/weekly-rebuild-missing/15 Pipeline was successful
ci/crow/manual/weekly-rebuild-missing/7 Pipeline was successful
ci/crow/manual/weekly-rebuild-missing/9 Pipeline was successful
ci/crow/manual/weekly-rebuild-missing/11 Pipeline was successful
ci/crow/manual/weekly-rebuild-missing/8 Pipeline was successful
ci/crow/cron/process-updates/13 Pipeline was successful
ci/crow/manual/weekly-rebuild-missing/4 Pipeline was successful
ci/crow/manual/weekly-rebuild-missing/3 Pipeline was successful
ci/crow/manual/weekly-rebuild-missing/1 Pipeline was successful
ci/crow/cron/process-updates/15 Pipeline was successful
ci/crow/manual/weekly-rebuild-missing/10 Pipeline was successful
ci/crow/manual/weekly-rebuild-missing/12 Pipeline was successful
ci/crow/cron/process-updates/11 Pipeline was successful
ci/crow/manual/weekly-rebuild-missing/16 Pipeline was successful
ci/crow/cron/process-updates/17 Pipeline was successful
ci/crow/manual/weekly-rebuild-missing/14 Pipeline was successful
ci/crow/cron/process-updates/4 Pipeline was successful
ci/crow/cron/process-updates/10 Pipeline was successful
ci/crow/cron/process-updates/14 Pipeline was successful
ci/crow/cron/process-updates/5 Pipeline was successful
ci/crow/cron/process-updates/16 Pipeline was successful
ci/crow/cron/process-updates/18 Pipeline was successful
ci/crow/cron/process-updates/12 Pipeline was successful
ci/crow/manual/weekly-rebuild-missing/2 Pipeline was successful
ci/crow/cron/process-updates/6 Pipeline was successful
ci/crow/cron/process-updates/1 Pipeline was successful
ci/crow/cron/process-updates/2 Pipeline was successful
ci/crow/cron/process-updates/7 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/3 Pipeline was successful
ci/crow/manual/weekly-rebuild-missing/17 Pipeline failed
ci/crow/manual/weekly-rebuild-missing/6 Pipeline was successful
ci/crow/manual/weekly-rebuild-missing/5 Pipeline was successful
ci/crow/manual/weekly-rebuild-missing/18 Pipeline was successful
feat(edge): route PACKAGES requests to the per-R-minor slot (#152)
## Problem

`install.packages("curl")` fails in `reg.devxy.io/r/r-alpine:4.5-3.24` with "package 'curl' is not available for this version of R", on both arches.

`curl` is not missing from the repo: it is in `…/latest/src/contrib/4.5/` and `…/4.6/`, the per-minor slots that base R cannot address. The image's repo URL resolves to `…/latest/src/contrib`, whose index does not list it. On `amd64/alpine324` that is 2 886 packages invisible to `install.packages()` (23 on `amd64/noble`) — what issue #63 records as "missing binaries".

Two further findings while investigating:

- The middleware only ever rewrote the bare `cran.rpkgs.com/src/contrib/…` form, and that form was broken for every Linux client on a stock R user agent: `ALPINE_REGEX`/`UBUNTU_REGEX`/`RHEL_REGEX` need a Posit-style UA that carries the distro, so stock R fell through to `extractOs()` and got redirected to `/amd64/linux-musl/latest/…`, a slot that does not exist.
- `PACKAGES*` is served `cdn-cache: BYPASS` (bincraft uploads it `no-store`), so the middleware sees every index request and no purge is needed for routing changes to take effect.

## What this changes

**`edge/rpkgs-router.ts`** — the middleware, now a reviewed file in this repo rather than dashboard state. It routes `PACKAGES`, `PACKAGES.gz` and `PACKAGES.rds` into `…/src/contrib/<x.y>/` for slots listed in `UNION_SLOTS`, and nothing else.

Tarballs are deliberately left alone. R keeps the `contriburl` it *asked for*, not the one the redirect served it, so every tarball URL is resolved against the flat directory and the union index steers the per-minor ones with a `Path: <x.y>` field. Rewriting a tarball request here would send flat-slot packages into a directory that does not hold them.

Also in the script: the phantom `linux-gnu`/`linux-musl` fallback is gone (an unidentifiable distro goes to CRAN, as an unparseable UA already did), and every redirect carries `Cache-Control: no-store` since its target depends on the User-Agent. The macOS branches are unchanged.

**`cdn.tf`** — `bunnynet_compute_script.rpkgs_router` with `content = file("edge/rpkgs-router.ts")`, the `UNION_SLOTS` variable, and `middleware_script` pointing at the resource instead of the literal `29277`.

`UNION_SLOTS` is empty, so merging and applying this changes no client's behaviour. A slot is added only once bincraft has republished its per-minor index as a union (rpkgs/bincraft#97); routing to a raw per-minor index would hide every package it does not carry. Rolling back is a variable edit, not a deploy.

**`specs/`, `plans/`** — the design and the implementation plan, including the two approaches that were rejected (edge-side merge, moving the minor up the path) and why.

## Verification

`just edge-test` runs 13 routing cases against the SDK's local server, so what is tested is the artifact that gets deployed; pass-through cases proxy to the real origin. All pass.

End to end, with the middleware in front of a locally built union index for `amd64/alpine324` (31 507 records), inside the runtime image:

```
curl:     7.1.0  -> …/latest/src/contrib/4.5  -> curl_7.1.0.tar.gz      717 725 B
jsonlite: 2.0.0  -> …/latest/src/contrib      -> jsonlite_2.0.0.tar.gz  1 055 849 B
```

`tofu validate` passes. `tofu plan` has not been run: no `BUNNYNET_API_KEY` available in this environment.

## Before applying

The script pre-dates this configuration, so it must be adopted, not created:

```sh
tofu import bunnynet_compute_script.rpkgs_router 29277
tofu plan
```

The plan should show an in-place `content` update and no replacement of the pull zone. Without the import, tofu creates a second script and repoints the zone at it. Note that `name = "rpkgs-router"` will rename the existing script on apply.

## Not fixed here

`install.packages("curl")` on `alpine324` will now *resolve*, then fail to build: that slot's tarballs are byte-identical CRAN **source** tarballs (no `Meta/`, no `Built:` in DESCRIPTION) which the index nevertheless stamps `Built: R 4.5.3; …-linux-musl`. Sampled: `amd64/alpine324` 3/12 binary, `arm64/alpine324` 13/30, `amd64/noble` 12/12, `amd64/alpine323` 17/20. That slot needs a rebuild, tracked separately.

Reviewed-on: #152
2026-08-07 14:12:22 +00:00

141 lines
3.9 KiB
HCL

# https://registry.terraform.io/providers/BunnyWay/bunnynet/latest/docs/resources/pullzone
# terraform import bunnynet_pullzone.devxy-r-binaries cran
# resource "bunnynet_pullzone" "devxy-r-binaries" {
# name = "cran"
# origin {
# type = "OriginUrl"
# url = "https://devxy-rpkgs-binaries.s3.eu-central-003.backblazeb2.com"
# }
# routing {
# tier = "Standard"
# }
# s3_auth_enabled = true
# s3_auth_key = var.B2_S3_ACCESS_KEY
# s3_auth_secret = var.B2_S3_SECRET_KEY
# s3_auth_region = "eu-central-003"
# cache_enabled = true
# cache_errors = true
# request_coalescing_enabled = true
# block_post_requests = true
# limit_requests = 500
# limit_connections = 50
# safehop_enabled = true
# add_canonical_header = true
# cache_stale = ["offline", "updating"]
# use_background_update = true
# block_ips = var.cdn_block_ips
# # 50 TB
# limit_bandwidth = 50000000000000
# permacache_storagezone = bunnynet_storage_zone.devxy-r-binaries.id
# # rec from docs: https://www.backblaze.com/docs/cloud-storage-integrate-bunnynet-with-backblaze-b2
# block_root_path = true
# }
# resource "bunnynet_pullzone_hostname" "devxy-r-binaries" {
# pullzone = bunnynet_pullzone.devxy-r-binaries.id
# name = "cran.devxy.io"
# force_ssl = true
# tls_enabled = true
# }
### cran.rpkgs.com
# The edge middleware that resolves the bare cran.rpkgs.com form to an
# <arch>/<os> slot and routes PACKAGES* to the per-R-minor slot. The source of
# truth is edge/rpkgs-router.ts; `tofu apply` publishes a new release.
#
# The script pre-dates this configuration, so it is adopted rather than created:
# tofu import bunnynet_compute_script.rpkgs_router 29277
resource "bunnynet_compute_script" "rpkgs_router" {
type = "middleware"
name = "rpkgs-router"
content = file("${path.module}/edge/rpkgs-router.ts")
}
# Slots ("<arch>/<os>", comma separated) whose per-minor index bincraft has
# already republished as a union of the per-minor and flat slots. Routing to a
# slot that is not listed here would hide every package the per-minor index does
# not carry, so this stays empty until a slot has been backfilled.
resource "bunnynet_compute_script_variable" "rpkgs_router_union_slots" {
script = bunnynet_compute_script.rpkgs_router.id
name = "UNION_SLOTS"
default_value = ""
required = false
}
resource "bunnynet_pullzone" "cran_rpkgs_com" {
name = "cran-rpkgs"
cache_errors = false
cache_expiration_time = 31919000
websockets_enabled = false
errorpage_whitelabel = true
origin {
type = "OriginUrl"
url = "https://devxy-rpkgs-binaries.s3.eu-central-003.backblazeb2.com"
middleware_script = bunnynet_compute_script.rpkgs_router.id
}
routing {
filters = [
"scripting",
]
}
s3_auth_enabled = true
s3_auth_key = var.B2_S3_ACCESS_KEY
s3_auth_secret = var.B2_S3_SECRET_KEY
s3_auth_region = "eu-central-003"
cache_enabled = true
request_coalescing_enabled = true
block_post_requests = true
limit_requests = 5000
limit_connections = 1000
safehop_enabled = true
add_canonical_header = true
cache_stale = ["offline", "updating"]
block_ips = var.cdn_block_ips
# 50 TB
limit_bandwidth = 50000000000000
# permacache_storagezone = bunnynet_storage_zone.devxy-r-binaries.id
# rec from docs: https://www.backblaze.com/docs/cloud-storage-integrate-bunnynet-with-backblaze-b2
block_root_path = true
}
resource "bunnynet_pullzone_hostname" "cran_rpkgs_com" {
pullzone = bunnynet_pullzone.cran_rpkgs_com.id
name = "cran.rpkgs.com"
force_ssl = true
tls_enabled = true
}
# resource "bunnynet_storage_zone" "devxy-r-binaries" {
# name = "devxy-r-binaries-storage"
# region = "DE"
# zone_tier = "Standard"
# # Los Angeles and Singapore
# replication_regions = ["LA", "SG"]
# }