scripts/verify-r-minor-routing.sh

@@ -48,6 +48,17 @@ SAMPLE=${SAMPLE:-5}
 # one R minor carries fewer per-minor binaries for the others; until that gap
 # closes, "full coverage for ABI-sensitive packages" is not a claim we can make.
 PARITY_TOLERANCE=${PARITY_TOLERANCE:-25}
+# Source fallbacks are reported, not failed on. Since bincraft learned to keep
+# a matching-minor generic binary out of a fallback's shadow, a remaining
+# fallback means the generic slot's binary was built under a *different* minor,
+# which is unsafe for this client anyway: serving source there is correct, just
+# slow. The gate below is what actually matters.
+#
+# A REGRESSION is a package this client would receive as source through
+# per-minor routing but as a binary built under its own minor from the generic
+# slot. That is strictly worse than not routing at all, and must be zero before
+# a slot is added to UNION_SLOTS.
+MAX_REGRESSIONS=${MAX_REGRESSIONS:-0}
 LIVE=0
 
 for arg in "$@"; do
@@ -108,6 +119,38 @@ pkg_names() {
   gunzip -c "$1" 2>/dev/null | awk '/^Package:/ {print $2}' | sort -u
 }
 
+# "<steered> <source-fallbacks>" for a per-minor index: how many entries carry a
+# Path: field, and how many of those lack a Built: field (i.e. are sources).
+fallback_counts() {
+  gunzip -c "$1" 2>/dev/null | awk '
+    /^Package:/ { pkg = $2; path = ""; built = "" }
+    /^Path:/    { path = $2 }
+    /^Built:/   { built = $2 }
+    /^$/        { if (pkg != "" && path != "") { n++; if (built == "") s++ } pkg = "" }
+    END         { if (pkg != "" && path != "") { n++; if (built == "") s++ }
+                  printf "%d %d\n", n, s }
+  '
+}
+
+# How many packages a client of <minor> would receive as source through
+# per-minor routing while the generic slot holds a binary built under that very
+# minor. Zero is the bar for enabling a slot.
+regression_count() {
+  local minor_file=$1 flat_file=$2 minor=$3
+  gunzip -c "$flat_file" 2>/dev/null | awk -v m="$minor" '
+    /^Package:/ { pkg = $2; built = "" }
+    /^Built:/   { built = $2 " " $3 }
+    /^$/        { if (pkg != "" && built ~ ("^R " m "\\.")) print pkg; pkg = "" }
+  ' | sort -u > "$minor_file.flatbin"
+  gunzip -c "$minor_file" 2>/dev/null | awk '
+    /^Package:/ { pkg = $2; path = ""; built = "" }
+    /^Path:/    { path = $2 }
+    /^Built:/   { built = $2 }
+    /^$/        { if (pkg != "" && path != "" && built == "") print pkg; pkg = "" }
+  ' | sort -u > "$minor_file.src"
+  comm -12 "$minor_file.src" "$minor_file.flatbin" | wc -l
+}
+
 # "<Package> <Path>" pairs for entries that carry a Path: field.
 path_entries() {
   gunzip -c "$1" 2>/dev/null | awk '
@@ -176,6 +219,25 @@ for arch in $ARCHES; do
         ok "$slot R $minor index: $minor_count packages, union holds"
       fi
 
+      # A per-minor entry that is a source fallback resolves fine but makes the
+      # client compile. Routing to a slot that is mostly fallbacks does not
+      # deliver the binaries we advertise.
+      read -r steered fallbacks <<< "$(fallback_counts "$minor_file")"
+      if [ "${steered:-0}" -gt 0 ]; then
+        pct=$((fallbacks * 100 / steered))
+        printf '        note: %s/%s per-minor entries are source fallbacks (%s%%)\n' \
+          "$fallbacks" "$steered" "$pct"
+      fi
+
+      # The gate: nothing may arrive as source here that the generic slot would
+      # have served as a binary built under this same minor.
+      regressions=$(regression_count "$minor_file" "$flat_file" "$minor")
+      if [ "${regressions:-0}" -gt "$MAX_REGRESSIONS" ]; then
+        bad "$slot R $minor: $regressions packages would be served as source but exist as an R $minor binary in the generic slot"
+      else
+        ok "$slot R $minor: no regression against the generic slot"
+      fi
+
       # Path: entries steer to per-minor binaries; they must resolve.
       if [ "$SAMPLE" -gt 0 ]; then
         path_entries "$minor_file" > "$minor_file.paths"