gitdan-actions/scripts/publish-snapshot-selftest.sh

#!/usr/bin/env bash
# Regression test for publish-snapshot.sh: the atomic swap, and the two
# properties the swap exists to guarantee.
#
#   1. FIRST PUBLISH — with no prior snapshot, the target dir is published and
#      is a hardlink clone of it (cheap), with the mutable metadata privately
#      owned (sound: the publisher's NEXT build must not be able to mutate the
#      snapshot it just published).
#   2. REPUBLISH REPLACES — a second publish replaces the snapshot's content
#      rather than merging into it, and leaves no scratch directories behind.
#   3. A LIVE CONSUMER SURVIVES A REPUBLISH — a branch that already cloned the
#      previous generation keeps reading its own consistent copy. Removing the
#      old snapshot unlinks directory entries; the inodes stay alive through
#      the consumer's own links. This is why a republish can never pull data
#      out from under a running job.
#   4. NO TARGET DIR — publishing when there is nothing to publish is a no-op,
#      not a failure.
#   5. LOCKS AND MARKERS DO NOT RIDE ALONG — the publishing job's own cache
#      lock is still held while this runs, and must not be baked into the
#      snapshot: a lock timestamped at this run's start would look fresh to
#      the prune pass on every branch later seeded from it.
#   6. DEFERRED RECLAMATION — the publisher's half of the seed-vs-rotation
#      race. Scenario 3 above covers a consumer that has ALREADY FINISHED
#      cloning; that one is safe for free, because its own hardlinks keep the
#      inodes alive. A consumer still WALKING the old generation is the case
#      that actually tears, and unlinking underneath it is what produced a
#      silently truncated clone. So when a reader is still in flight past the
#      grace period, the swap leaves the rotated-away generation on disk
#      instead of unlinking it.
#   7. AND THE SWEEP — a deferred generation is not leaked: the next publish
#      of that snapshot reclaims it once no reader holds it. Without this the
#      "we defer instead of forcing" answer would just be a disk leak with
#      better manners.
#
# The consumer's half of the same race — a seed catching a rotation mid-clone
# — is in seed-target-dir-selftest.sh scenario 8.
set -euo pipefail
script_dir=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
. "$script_dir/cache-lib.sh"

scratch=$(mktemp -d)
trap 'rm -rf "$scratch"' EXIT
root="$scratch/cache"; mkdir -p "$root"
pass_count=0
fail() { echo "ASSERTION FAILED: $*" >&2; exit 1; }
ok() { pass_count=$((pass_count + 1)); echo "PASS: $*"; }

# Cargo and rustc REPLACE an artifact (write elsewhere, rename over the path)
# rather than truncating it in place, which is exactly why a snapshot may
# share artifact inodes with the live target dir it was cloned from. The
# fixtures here have to model that faithfully — a plain `>` redirect truncates
# in place and would write straight through the shared inode into the
# snapshot and every consumer, which is a property of the test fixture, not of
# a real build. hardlink-clone-selftest.sh is what verifies the real thing
# against a real compiler.
replace_file() {
  printf '%s\n' "$2" > "$1.new"
  mv -f "$1.new" "$1"
}

make_tree() {
  local d="$1" marker="$2"
  mkdir -p "$d/debug/deps" "$d/debug/.fingerprint/x"
  echo "$marker" > "$d/debug/deps/libx.rlib"
  echo "$marker" > "$d/debug/.fingerprint/x/dep-lib-x"
  : > "$d/debug/.cargo-lock"
}

KEY=$(cache_key dev)
TGT="$root/target-$KEY"
SNAP="$root/snapshot-$KEY"
publish() { bash "$script_dir/publish-snapshot.sh" "$KEY" "$root" "$1" > "$scratch/log" 2>&1 || { cat "$scratch/log"; fail "publish-snapshot.sh exited non-zero"; }; }

echo "=== 4: nothing to publish is a no-op ==="
publish job1
[ -d "$SNAP" ] && fail "published a snapshot with no target dir present"
grep -q 'nothing to snapshot' "$scratch/log" || fail "expected a 'nothing to snapshot' line"
ok "no target dir: no-op, reported plainly"

echo
echo "=== 1: first publish ==="
make_tree "$TGT" gen1
date +%s > "$TGT/.ci-lock-ci-42"
touch "$TGT/.cache-last-used"
publish job1
[ "$(cat "$SNAP/debug/deps/libx.rlib")" = "gen1" ] || fail "snapshot content wrong"
ok "snapshot published"
[ "$(stat -c '%i' "$SNAP/debug/deps/libx.rlib")" = "$(stat -c '%i' "$TGT/debug/deps/libx.rlib")" ] \
  || fail "snapshot artifact was copied, not hardlinked"
ok "snapshot shares artifact inodes with the target dir (cheap)"
[ "$(stat -c '%i' "$SNAP/debug/.fingerprint/x/dep-lib-x")" != "$(stat -c '%i' "$TGT/debug/.fingerprint/x/dep-lib-x")" ] \
  || fail "snapshot fingerprint still aliases the live target dir"
ok "snapshot owns its mutable metadata (publisher's next build cannot corrupt it)"

echo
echo "=== 5: locks and LRU markers do not ride along ==="
[ -e "$SNAP/.ci-lock-ci-42" ] && fail "the publishing job's lock was baked into the snapshot"
ok "cache lock not published"
[ -e "$SNAP/.cache-last-used" ] && fail "the LRU marker was baked into the snapshot"
ok "LRU marker not published"
[ -e "$SNAP/debug/.cargo-lock" ] && fail "a Cargo lock file was published"
ok "Cargo lock file not published"

echo
echo "=== 3: a consumer that cloned generation 1 ==="
CONSUMER="$root/target-$(cache_key feat/consumer)"
hardlink_clone_into "$SNAP" "$CONSUMER" consumer-tag || fail "consumer clone failed"
ok "consumer cloned generation 1"

echo
echo "=== 2: republish replaces, leaves no scratch behind ==="
replace_file "$TGT/debug/deps/libx.rlib" gen2
# The fingerprint IS written in place by Cargo — and the snapshot owns its own
# copy precisely so that write cannot reach it. Truncating in place here is
# the faithful model.
echo gen2 > "$TGT/debug/.fingerprint/x/dep-lib-x"
publish job1
[ "$(cat "$SNAP/debug/deps/libx.rlib")" = "gen2" ] || fail "republish did not replace the snapshot"
ok "republished snapshot carries generation 2"
leftovers=$(find "$root" -maxdepth 1 \( -name '.stage-*' -o -name '.publish-*' \) -print)
[ -z "$leftovers" ] || fail "scratch directories left behind: $leftovers"
ok "no scratch directories left behind"
[ "$(cat "$CONSUMER/debug/deps/libx.rlib")" = "gen1" ] \
  || fail "the consumer's clone changed under it when the snapshot was replaced"
ok "the live consumer still reads its own consistent generation-1 copy"

echo
echo "=== 6: a reader still in flight defers reclamation ==="
# A synthetic reader marker stands in for a consumer whose clone outlasts the
# grace period. Racing a real slow consumer would make the suite's runtime the
# thing under test; the marker IS the entire contract between the two sides,
# so holding one is being a reader.
SNAP_NAME=$(basename "$SNAP")
date +%s > "$root/.reading-${SNAP_NAME}-slowpoke"
replace_file "$TGT/debug/deps/libx.rlib" gen3
CACHE_READ_GRACE_SECONDS=1 bash "$script_dir/publish-snapshot.sh" "$KEY" "$root" jobDefer \
  > "$scratch/log" 2>&1 || { cat "$scratch/log"; fail "publish-snapshot.sh exited non-zero"; }
[ "$(cat "$SNAP/debug/deps/libx.rlib")" = "gen3" ] || fail "the new generation was not published"
ok "the new generation is published even while a reader holds the old one"
deferred=$(find "$root" -maxdepth 1 -name ".publish-old-${KEY}-*" -print -quit)
[ -n "$deferred" ] || fail "the previous generation was unlinked while a reader still held it"
ok "the rotated-away generation is left on disk rather than unlinked under a reader"
grep -q 'deferring reclamation' "$scratch/log" || fail "the deferral was not reported"
ok "the deferral is surfaced as a warning, not silent"
[ "$(cat "$CONSUMER/debug/deps/libx.rlib")" = "gen1" ] \
  || fail "the earlier consumer's clone changed under it"
ok "the generation-1 consumer is still unaffected"

echo
echo "=== 7: a later publish sweeps the deferred generation ==="
rm -f "$root/.reading-${SNAP_NAME}-slowpoke"
replace_file "$TGT/debug/deps/libx.rlib" gen4
publish jobSweep
[ "$(cat "$SNAP/debug/deps/libx.rlib")" = "gen4" ] || fail "the fourth generation was not published"
ok "publishing continues normally after a deferral"
[ -z "$(find "$root" -maxdepth 1 -name '.publish-old-*' -print -quit)" ] \
  || fail "the deferred generation was never reclaimed — this is a disk leak"
ok "the deferred generation is reclaimed once no reader holds it"
[ -z "$(find "$root" -maxdepth 1 \( -name '.stage-*' -o -name '.reading-*' \) -print -quit)" ] \
  || fail "scratch left behind: $(find "$root" -maxdepth 1 \( -name '.stage-*' -o -name '.reading-*' \) -print)"
ok "no staging or reader-marker scratch left behind"

echo
echo "publish-snapshot-selftest: ${pass_count} assertions passed"