diff --git a/.crow/build-all-versions-install-deps.yaml b/.crow/build-all-versions-install-deps.yaml index ad51300..97610df 100644 --- a/.crow/build-all-versions-install-deps.yaml +++ b/.crow/build-all-versions-install-deps.yaml @@ -62,8 +62,9 @@ steps: # - rm -rf /mnt/cache/R-pkgs - mkdir -p /mnt/cache/pkgcache /mnt/cache/R-pkgs /mnt/cache/ccache /mnt/cache/packages - git clone -q https://pat-s:$$REPO_RO_TOKEN@git.devxy.io/devxy/build-cran-binaries.git . - - git clone -q https://codefloe.com/rpkgs/bincraft.git /tmp/bincraft - - /opt/R/$R_VERSION/bin/R -q -e 'pak::sysreqs_db_update(); pak::local_install("/tmp/bincraft"); pak::pak(c("RPostgres", "s3fs", "data.table", "future", "jsonlite")); packageVersion("bincraft")' + # Pin the same bincraft version the build steps use, so the precomputed + # snapshot and the per-agent library stay consistent across the pipeline. + - /opt/R/$R_VERSION/bin/R -q -e 'pak::sysreqs_db_update(); pak::pak("git::https://codefloe.com/rpkgs/bincraft.git@v4.2.3"); pak::pak(c("RPostgres", "s3fs", "data.table", "future", "jsonlite")); packageVersion("bincraft")' - /opt/R/$R_VERSION/bin/R -q -e "source('local/packages-to-build.R'); saveRDS(pkgs, '/mnt/cache/packages/pkgs_to_build.rds'); saveRDS(pkgs[r_minor_sensitive == TRUE], '/mnt/cache/packages/r_minor_sensitive_pkgs.rds'); sprintf('Precomputed %s package versions (%s r-minor-sensitive)', nrow(pkgs), nrow(pkgs[r_minor_sensitive == TRUE]))" backend_options: docker: diff --git a/.crow/build-all-versions.yaml b/.crow/build-all-versions.yaml index 639ce80..41987ad 100644 --- a/.crow/build-all-versions.yaml +++ b/.crow/build-all-versions.yaml @@ -100,6 +100,14 @@ steps: commands: - git clone -q https://pat-s:$$REPO_RO_TOKEN@git.devxy.io/devxy/build-cran-binaries.git . - mkdir -p /mnt/cache/pkgcache /mnt/cache/R-pkgs /mnt/cache/ccache /mnt/cache/packages + # The primary pass must not rely on build-all-versions-install-deps having + # run on *this* agent: depends_on only orders the steps, but the cache + # volume is per-agent, so a job landing on an agent where install-deps did + # not run would otherwise use a stale bincraft (which resolves `platform` + # to a zero-length value and breaks every metadata query and the sysdeps + # install). Pin bincraft here, exactly like the R-minor pass below. + - rm -rf /mnt/cache/R-pkgs/00LOCK-* + - /opt/R/$R_VERSION/bin/R -q -e 'if (!requireNamespace("bincraft", quietly = TRUE) || packageVersion("bincraft") != "4.2.3") pak::pak("git::https://codefloe.com/rpkgs/bincraft.git@v4.2.3")' - XVFB=$(command -v xwfb-run 2>/dev/null || command -v xvfb-run); XVFB_ARGS=""; if command -v xwfb-run >/dev/null 2>&1; then dnf install -y -q weston 2>/dev/null; XVFB_ARGS="-c weston"; fi - $XVFB $XVFB_ARGS -n $SPLIT_INDEX -- /opt/R/$R_VERSION/bin/Rscript local/build-all.R $SPLIT_INTO $SPLIT_INDEX $NCPUS 2>&1 - | @@ -111,11 +119,12 @@ steps: echo "=== R-minor-sensitive pass under R $RV ===" LIB="/mnt/cache/R-pkgs-$RMINOR" mkdir -p "$LIB" - R_LIBS_USER="$LIB" "$(dirname "$RBIN")/R" -q -e 'if (!requireNamespace("bincraft", quietly = TRUE) || packageVersion("bincraft") != "4.2.2") pak::pak("git::https://codefloe.com/rpkgs/bincraft.git@v4.2.2")' || true + R_LIBS_USER="$LIB" "$(dirname "$RBIN")/R" -q -e 'if (!requireNamespace("bincraft", quietly = TRUE) || packageVersion("bincraft") != "4.2.3") pak::pak("git::https://codefloe.com/rpkgs/bincraft.git@v4.2.3")' || true R_LIBS_USER="$LIB" $XVFB $XVFB_ARGS -n $SPLIT_INDEX -- "$(dirname "$RBIN")/Rscript" local/build-all.R --sensitive-only $SPLIT_INTO $SPLIT_INDEX $NCPUS 2>&1 || true done - # archive missed packages - - /opt/R/$R_VERSION/bin/R -q -e "bincraft::process_unarchived_pkgs(paste(Sys.getenv('OS'), Sys.getenv('OS_VERSION')), Sys.getenv('ARCH'), workers = $NCPUS)" + # archive missed packages; first arg is the codename (e.g. "alpine324"), + # derived via bincraft like the upload step, not paste(OS, OS_VERSION). + - /opt/R/$R_VERSION/bin/R -q -e "bincraft::process_unarchived_pkgs(bincraft::set_codename(NULL), Sys.getenv('ARCH'), workers = $NCPUS)" backend_options: docker: resources: diff --git a/local/build-all.R b/local/build-all.R index 8ce1cd5..6c3725c 100644 --- a/local/build-all.R +++ b/local/build-all.R @@ -15,6 +15,31 @@ library(bincraft, quietly = TRUE) library(future) plan("sequential") +# The install-deps step precomputes the package snapshot into /mnt/cache, but +# that volume is per-agent: a job landing on a fresh agent (or racing +# install-deps) finds it empty. Recompute the snapshot here when any part is +# missing, so the first job on an agent repopulates the cache for the jobs that +# follow; concurrent jobs that also miss simply redo the work. Write via a +# temp file + atomic rename so a concurrent reader never sees a half-written rds. +package_cache_files <- c( + "/mnt/cache/packages/pkgs_to_build.rds", + "/mnt/cache/packages/r_minor_sensitive_pkgs.rds", + "/mnt/cache/packages/s3_cache.rds" +) +if (!all(file.exists(package_cache_files))) { + message("Package snapshot missing from cache; recomputing via packages-to-build.R") + dir.create("/mnt/cache/packages", showWarnings = FALSE, recursive = TRUE) + save_rds_atomic <- function(obj, path) { + tmp <- paste0(path, ".tmp.", Sys.getpid()) + saveRDS(obj, tmp) + file.rename(tmp, path) + } + source(file.path("local", "packages-to-build.R")) + save_rds_atomic(pkgs, "/mnt/cache/packages/pkgs_to_build.rds") + save_rds_atomic(pkgs[r_minor_sensitive == TRUE], "/mnt/cache/packages/r_minor_sensitive_pkgs.rds") + message("Package snapshot recomputed.") +} + pkgs <- if (sensitive_only) { readRDS("/mnt/cache/packages/r_minor_sensitive_pkgs.rds") } else { @@ -43,8 +68,31 @@ chunk <- chunk[!chunk$Package %in% exclude, ] # 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. -platform <- paste(Sys.getenv("OS"), gsub("[.]", "", Sys.getenv("OS_VERSION")), sep = "-") -arch <- Sys.getenv("ARCH") +# 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",