diff --git a/.crow/retire-slot.yaml b/.crow/retire-slot.yaml new file mode 100644 index 0000000..1b62ba7 --- /dev/null +++ b/.crow/retire-slot.yaml @@ -0,0 +1,72 @@ +# Delete a retired slot's objects from the bucket. +# +# The config half is a commit, so it runs on a workstation: +# just retire-slot --apply +# +# This half needs the B2 credentials, which only exist in CI. +# `local/retire-slot.R` refuses any slot still listed in `local.rpkgs_slots`, +# so this cannot delete a live slot. Both architectures go together. +# +# Dry run unless RETIRE_APPLY is 'yes': +# +# crow pipeline create devxy/build-cran-binaries --branch main \ +# --var retire_slot=alpine322 --var RETIRE_APPLY=yes + +variables: + # A manual pipeline creation instantiates every file in .crow/, so the + # default must be a value the script never accepts. + retire_slot: + description: "Codename of the slot to retire (e.g. alpine322), or 'none'." + default: none + RETIRE_APPLY: + description: "Set to 'yes' to delete. Anything else reports and changes nothing." + options: + - 'no' + - 'yes' + default: 'no' + +when: + - event: manual + evaluate: 'retire_slot != "none"' + +skip_clone: true + +labels: + group: rpkgs-amd64 + +steps: + - name: 'Delete the retired slot from the bucket' + image: reg.devxy.io/rpkgs/build-env-alpine:3.24 + pull: true + environment: + OTEL_R_TRACES_EXPORTER: none + OTEL_R_LOGS_EXPORTER: none + OTEL_R_METRICS_EXPORTER: none + B2_S3_ACCESS_KEY: + from_secret: B2_S3_ACCESS_KEY + B2_S3_SECRET_KEY: + from_secret: B2_S3_SECRET_KEY + REPO_RO_TOKEN: + from_secret: REPO_RO_TOKEN + R_LIBS_USER: /tmp/R-pkgs + # Pipeline variables are substituted into the YAML, not exported, so they + # have to be bound here to be readable as env vars in the script below. + RETIRE_SLOT: ${retire_slot} + RETIRE_APPLY: ${RETIRE_APPLY} + commands: + - git clone -q https://pat-s:$$REPO_RO_TOKEN@git.devxy.io/devxy/build-cran-binaries.git . + - mkdir -p /tmp/R-pkgs + - /opt/R/4.5.3/bin/Rscript local/install-bincraft.R + - | + set -eu + APPLY="" + if [ "$$RETIRE_APPLY" = "yes" ]; then + APPLY="--apply" + fi + /opt/R/4.5.3/bin/Rscript local/retire-slot.R "$$RETIRE_SLOT" --assets-only $$APPLY + backend_options: + docker: + resources: + requests: + memory: 2Gi + cpu: 1000m diff --git a/README.md b/README.md index 989069e..d137728 100644 --- a/README.md +++ b/README.md @@ -198,6 +198,28 @@ Example: Technically, no date-based snapshots are planned, so this component from the Posit PM structure is not included. +## Retiring a slot + +A slot is only reachable if it is listed in `local.rpkgs_slots` in `cdn.tf`, which feeds `UNION_SLOTS` in `edge/rpkgs-router.ts`. +An unrouted slot serves the flat index to every client, so its binaries fail at `dyn.load()` under every R minor but one. + +In order: + +1. Remove it from `local.rpkgs_slots` in `cdn.tf` and from `DistroId` in the website's `src/src/data/repos.ts`, then `tofu apply`. +2. `just retire-slot --apply`, then commit. +3. Delete its cron jobs on the Crow server; `local/retire-slot.R` prints them with the API call. +4. Delete its objects: + + ```sh + crow pipeline create devxy/build-cran-binaries --branch main \ + --var retire_slot= --var RETIRE_APPLY=yes + ``` + +Steps 2 and 4 refuse any slot still listed in `cdn.tf`. +Running step 4 before step 2 means the next nightly rebuilds everything just deleted. + +`just check-slots` fails when a pipeline still targets an unrouted slot. + ## Helpers Helper scripts are located in `local/`. diff --git a/justfile b/justfile index 6c75b13..36ad0e1 100644 --- a/justfile +++ b/justfile @@ -87,3 +87,11 @@ edge-test: denoland/deno:latest \ deno test -A edge/rpkgs-router.test.ts fi + +# fail if any pipeline still targets a slot the edge does not route +check-slots: + Rscript local/check-slots.R + +# strip a retired slot from .crow/*.yaml (dry run; pass --apply to write) +retire-slot codename *flags: + Rscript local/retire-slot.R {{ codename }} --config-only {{ flags }} diff --git a/local/check-slots.R b/local/check-slots.R new file mode 100644 index 0000000..5345da9 --- /dev/null +++ b/local/check-slots.R @@ -0,0 +1,151 @@ +### Fail when a pipeline targets a slot that is not in `local.rpkgs_slots`. +# +# Rscript local/check-slots.R +# +# That list feeds `UNION_SLOTS`, which `edge/rpkgs-router.ts` gates per-R-minor +# routing on. An unrouted slot serves the flat index to every client, so its +# binaries fail at dyn.load() under every R minor but one. +# +# One-directional: a published slot missing from some pipeline is only +# reported, since several pipelines cover a subset on purpose. + +options(error = function() { + cat("ERROR:", geterrmessage(), "\n", file = stdout()) + q(status = 1) +}) + +# Parses the distro list out of the setproduct's second array. +published_codenames <- function(path = "cdn.tf") { + if (!file.exists(path)) { + stop( + sprintf("%s not found; run this from the repository root.", path), + call. = FALSE + ) + } + lines <- readLines(path, warn = FALSE) + start <- grep("rpkgs_slots\\s*=", lines) + if (length(start) != 1L) { + stop( + "Could not find exactly one `rpkgs_slots` local in cdn.tf.", + call. = FALSE + ) + } + block <- paste(lines[start:min(start + 10L, length(lines))], collapse = "\n") + arrays <- regmatches(block, gregexpr("\\[[^]]*\\]", block))[[1L]] + if (length(arrays) < 2L) { + stop( + "`rpkgs_slots` no longer has the two-array setproduct shape this parses.", + call. = FALSE + ) + } + codenames <- gsub( + '"', + "", + regmatches(arrays[[2L]], gregexpr('"[^"]+"', arrays[[2L]]))[[1L]] + ) + if (length(codenames) == 0L) { + stop("Parsed an empty distro list from cdn.tf.", call. = FALSE) + } + codenames +} + +UBUNTU_CODENAMES <- c( + resolute = "ubuntu-2604", + noble = "ubuntu-2404", + jammy = "ubuntu-2204" +) + +as_pipeline_os <- function(codename) { + ifelse( + codename %in% names(UBUNTU_CODENAMES), + UBUNTU_CODENAMES[codename], + ifelse( + grepl("^rhel[0-9]+$", codename), + sub("^rhel", "redhat-", codename), + ifelse( + grepl("^alpine[0-9]+$", codename), + sub("^alpine([0-9])([0-9]+)$", "alpine-\\1\\2", codename), + NA_character_ + ) + ) + ) +} + +# Structural lines only, so a codename in a comment is not a finding. +slots_in_pipeline <- function(path) { + lines <- readLines(path, warn = FALSE) + row <- regmatches( + lines, + regexec("^\\s*-?\\s*(OS|CODENAME|OS_ID):\\s*(\\S+)\\s*$", lines) + ) + opt <- regmatches( + lines, + regexec("^\\s*-\\s*([a-z0-9]+-[a-z0-9]+)-(amd64|arm64)\\s*$", lines) + ) + hits <- c( + vapply( + row, + function(m) if (length(m) == 3L) m[[3L]] else NA_character_, + "" + ), + vapply(opt, function(m) if (length(m) == 4L) m[[2L]] else NA_character_, "") + ) + hits <- hits[!is.na(hits)] + # `OS: alpine` (build-all-versions' bare image name) is not a slot. + unique(hits[grepl("^(alpine|redhat|ubuntu)-?[0-9]", hits)]) +} + +codenames <- published_codenames() +published_os <- unname(as_pipeline_os(codenames)) +if (anyNA(published_os)) { + stop( + sprintf( + "Unrecognised codename(s) in cdn.tf: %s", + paste(codenames[is.na(published_os)], collapse = ", ") + ), + call. = FALSE + ) +} +# Files spell a slot either way, so accept both. +published <- unique(c(published_os, codenames)) + +cat(sprintf( + "Published slots (cdn.tf): %s\n\n", + paste(sort(published_os), collapse = ", ") +)) + +files <- sort(list.files(".crow", pattern = "\\.yaml$", full.names = TRUE)) +findings <- list() +for (f in files) { + stale <- setdiff(slots_in_pipeline(f), published) + if (length(stale) > 0L) { + findings[[f]] <- stale + cat(sprintf( + "%-45s targets unpublished: %s\n", + f, + paste(sort(stale), collapse = ", ") + )) + } +} + +uncovered <- setdiff( + published_os, + unique(unlist(lapply(files, slots_in_pipeline))) +) +if (length(uncovered) > 0L) { + cat(sprintf( + "\nNote: %s appear(s) in no pipeline at all.\n", + paste(sort(uncovered), collapse = ", ") + )) +} + +if (length(findings) == 0L) { + cat("All pipeline slots are published and routed.\n") + quit(status = 0) +} + +cat(sprintf( + "\n%d file(s) target an unrouted slot. Retire it with:\n just retire-slot \n", + length(findings) +)) +quit(status = 1) diff --git a/local/retire-slot.R b/local/retire-slot.R new file mode 100644 index 0000000..383fd2c --- /dev/null +++ b/local/retire-slot.R @@ -0,0 +1,240 @@ +### Retire a slot: strip it from the pipelines and delete its objects from S3. +# +# Rscript local/retire-slot.R [--apply] [--config-only|--assets-only] +# +# Retiring a distro retires both architectures, because `local.rpkgs_slots` in +# `cdn.tf` is a setproduct over them. +# +# Order: remove the slot from `local.rpkgs_slots` (and the website's +# `DistroId`) and apply that first, then run this. Deleting objects while a +# pipeline still targets the slot just means the next nightly rebuilds them. +# +# Cron jobs live on the Crow server, not here, and are printed at the end. +# +# Only structural YAML is edited. Prose mentioning the slot is left alone, so +# grep for the name afterwards. +# +# Dry run by default. + +options(error = function() { + cat("ERROR:", geterrmessage(), "\n", file = stdout()) + q(status = 1) +}) + +args <- commandArgs(trailingOnly = TRUE) +apply_changes <- "--apply" %in% args +config_only <- "--config-only" %in% args +assets_only <- "--assets-only" %in% args +args <- args[!args %in% c("--apply", "--config-only", "--assets-only")] +if (length(args) != 1L || (config_only && assets_only)) { + stop( + "usage: retire-slot.R [--apply] [--config-only|--assets-only]", + call. = FALSE + ) +} +codename <- args[[1L]] + +# The bucket and `CODENAME:` say `alpine322`; `OS:` and the options say +# `alpine-322`. Both have to go. +pipeline_os <- if (grepl("^rhel[0-9]+$", codename)) { + sub("^rhel", "redhat-", codename) +} else if (grepl("^alpine[0-9]+$", codename)) { + sub("^alpine", "alpine-", codename) +} else { + # Single bracket so an unknown codename yields NA, not an error. + c(resolute = "ubuntu-2604", noble = "ubuntu-2404", jammy = "ubuntu-2204")[ + codename + ] +} +if (is.na(pipeline_os) || length(pipeline_os) == 0L) { + stop(sprintf("Unrecognised codename '%s'.", codename), call. = FALSE) +} + +# The `OS_VERSION` dropdowns are keyed on the image tag, not the slot name. +image_tag <- if (grepl("^alpine-", pipeline_os)) { + sub("^alpine-([0-9])([0-9]+)$", "\\1.\\2", pipeline_os) +} else if (grepl("^redhat-", pipeline_os)) { + sub("^redhat-", "", pipeline_os) +} else { + codename +} + +# Refuse a slot that is still routed: deleting its objects would leave the edge +# serving indexes that name files which no longer exist. +tf <- readLines("cdn.tf", warn = FALSE) +start <- grep("rpkgs_slots\\s*=", tf) +if (length(start) != 1L) { + stop( + "Could not find exactly one `rpkgs_slots` local in cdn.tf.", + call. = FALSE + ) +} +block <- paste(tf[start:min(start + 10L, length(tf))], collapse = "\n") +if (grepl(sprintf('"%s"', codename), block, fixed = TRUE)) { + stop( + sprintf( + "'%s' is still listed in `local.rpkgs_slots` in cdn.tf, so the edge still routes it. Remove it there (and from the website's DistroId union) and apply the OpenTofu change first.", # nolint + codename + ), + call. = FALSE + ) +} + +cat(sprintf( + "Retiring %s (pipelines call it '%s', images tag it '%s')\n\n", + codename, + pipeline_os, + image_tag +)) + +## 1. Pipeline definitions ---------------------------------------------------- + +# Line-based on purpose: a YAML round trip would reflow all 18 files. +strip_slot <- function(lines) { + keep <- rep(TRUE, length(lines)) + i <- 1L + while (i <= length(lines)) { + line <- lines[[i]] + row <- regexec( + sprintf( + "^(\\s*)-\\s*(OS|CODENAME):\\s*(%s|%s)\\s*$", + pipeline_os, + codename + ), + line + ) + m <- regmatches(line, row)[[1L]] + if (length(m) == 4L) { + indent <- nchar(m[[2L]]) + keep[[i]] <- FALSE + j <- i + 1L + while (j <= length(lines)) { + nxt <- lines[[j]] + if ( + !nzchar(trimws(nxt)) || nchar(sub("^(\\s*).*$", "\\1", nxt)) <= indent + ) { + break + } + keep[[j]] <- FALSE + j <- j + 1L + } + i <- j + next + } + if (grepl(sprintf("^\\s*-\\s*%s-(amd64|arm64)\\s*$", pipeline_os), line)) { + keep[[i]] <- FALSE + } + if (grepl(sprintf("^\\s*-\\s*'%s'\\s*$", image_tag), line)) { + keep[[i]] <- FALSE + } + i <- i + 1L + } + out <- lines[keep] + # A dropdown cannot default to an option that no longer exists. + bad_default <- grepl(sprintf("^\\s*default:\\s*'%s'\\s*$", image_tag), out) + if (any(bad_default)) { + for (k in which(bad_default)) { + opts <- grep("^\\s*-\\s*'[^']+'\\s*$", out[seq_len(k - 1L)]) + if (length(opts) == 0L) { + next + } + # Walk back to this block's first option, not the nearest one. + first <- max(opts) + while (first > 1L && grepl("^\\s*-\\s*'[^']+'\\s*$", out[[first - 1L]])) { + first <- first - 1L + } + replacement <- sub("^\\s*-\\s*'([^']+)'\\s*$", "\\1", out[[first]]) + out[[k]] <- sub("'[^']+'", sprintf("'%s'", replacement), out[[k]]) + cat(sprintf(" default moved to '%s'\n", replacement)) + } + } + out +} + +if (!assets_only) { + files <- sort(list.files(".crow", pattern = "\\.yaml$", full.names = TRUE)) + touched <- 0L + for (f in files) { + lines <- readLines(f, warn = FALSE) + out <- strip_slot(lines) + if (length(out) == length(lines)) { + next + } + touched <- touched + 1L + cat(sprintf( + " %s %-45s -%d lines\n", + if (apply_changes) "EDIT " else "would edit", + f, + length(lines) - length(out) + )) + if (apply_changes) { + writeLines(out, f) + } + } + if (touched == 0L) { + cat(" No pipeline references the slot.\n") + } else if (apply_changes) { + cat(sprintf( + " %d file(s) edited. Verify with `crow lint .crow/` and `Rscript local/check-slots.R`.\n", + touched + )) + } + cat("\n") +} + +## 2. Bucket objects ---------------------------------------------------------- + +if (!config_only) { + library(s3fs, quietly = TRUE) + if (!nzchar(Sys.getenv("B2_S3_ACCESS_KEY"))) { + stop( + "B2_S3_ACCESS_KEY is unset. B2 lists nothing without credentials, which is indistinguishable from an already-clean slot.", # nolint + call. = FALSE + ) + } + bucket <- "devxy-rpkgs-binaries" + 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 + ) + + for (arch in c("amd64", "arm64")) { + prefix <- sprintf("%s/%s/%s", bucket, arch, codename) + if (!s3fs::s3_dir_exists(prefix)) { + cat(sprintf(" %s/%s: nothing in the bucket.\n", arch, codename)) + next + } + objects <- s3fs::s3_dir_ls(prefix, recurse = TRUE) + cat(sprintf( + " %s %s/%s: %d object(s)\n", + if (apply_changes) "DELETE" else "would delete", + arch, + codename, + length(objects) + )) + if (apply_changes && length(objects) > 0L) { + s3fs::s3_dir_delete(prefix) + cat(sprintf(" deleted s3://%s\n", prefix)) + } + } + cat("\n") +} + +## 3. Crons ------------------------------------------------------------------ + +if (!apply_changes) { + cat("Dry run: nothing was edited or deleted. Re-run with --apply.\n\n") +} + +cat("Crons still to remove on the Crow server (they are not in this repo):\n") +cat(sprintf( + " crow-at ci.devxy.io repo cron ls devxy/build-cran-binaries | grep %s\n", + pipeline_os +)) +cat(" # `crow repo cron rm` 404s here; the API base is /api/v1\n") +cat(" eval \"$(crow-at --export ci.devxy.io)\"\n") +cat(" curl -s -X DELETE -H \"Authorization: Bearer $CROW_TOKEN\" \\\n") +cat(" https://ci.devxy.io/api/v1/repos/5/cron/\n")