test(seed): force scenario 8's interleaving instead of racing for it #4
@@ -29,14 +29,24 @@
|
||||
# at no point is a partially-populated directory visible under the final
|
||||
# name. This is the property that replaces "the runner only has one job
|
||||
# slot" with an actual guarantee.
|
||||
# 8. SEED VS PUBLISH ROTATION — the race scenario 7 does NOT cover, and the
|
||||
# 8a. SEED VS PUBLISH ROTATION — the race scenario 7 does NOT cover, and the
|
||||
# one that actually mattered: a consumer hardlink-cloning a snapshot
|
||||
# while the publisher of that snapshot rotates it and unlinks the
|
||||
# generation being read. Two seeds racing on a DESTINATION is a different
|
||||
# race from a seed racing a publisher on its SOURCE, and only the second
|
||||
# one can truncate a tree. Against the unguarded version this scenario
|
||||
# reproduces a silent partial clone reported as success — 20,328 of
|
||||
# 48,805 entries, `seed: cloned in 1s`, exit 0, seeded-from=base-snapshot.
|
||||
# while the publisher of that snapshot rotates it. Two seeds racing on a
|
||||
# DESTINATION is a different race from a seed racing a publisher on its
|
||||
# SOURCE, and only the second one can truncate a tree. What it pins is
|
||||
# that the consumer notices its source was REPLACED and re-clones,
|
||||
# ending up with the whole generation now published — not that the
|
||||
# rotation interfered with the copy, which is not guaranteed and is what
|
||||
# made the racing version of this scenario flaky (issue #3).
|
||||
# 8b. AND A SILENTLY TRUNCATED WALK — the same tear seen through the other
|
||||
# check: a subtree unlinked out of the parent's listing before `cp -al`
|
||||
# reads it is never visited, the copy exits 0 and the source's identity
|
||||
# never changes. Against the unguarded version this is a partial tree
|
||||
# renamed into place and reported as a success — 20,328 of 48,805
|
||||
# entries, `seed: cloned in 1s`, exit 0, seeded-from=base-snapshot.
|
||||
# Both scenarios force their interleaving rather than racing for it, and
|
||||
# each asserts WHICH check caught the tear, so neither stays green if
|
||||
# the check it exercises is removed.
|
||||
# 9. AN UNREADABLE SOURCE FAILS LOUDLY — the clone reports a distinct status
|
||||
# instead of renaming whatever it managed to produce into place, and the
|
||||
# seed SCRIPT turns that status into a failed job rather than a silent
|
||||
@@ -75,9 +85,13 @@ make_tree() {
|
||||
|
||||
seed() { bash "$script_dir/seed-target-dir.sh" "$@" > "$scratch/log" 2>&1 || { tail -40 "$scratch/log"; fail "seed-target-dir.sh exited non-zero"; }; }
|
||||
|
||||
# Always succeeds and always prints a number: an absent directory is "0
|
||||
# entries so far", which is the normal state at the top of the progress poll
|
||||
# below, not an error worth aborting the suite over.
|
||||
# The same script, with the scenario-8 stub directory ahead of the real
|
||||
# coreutils on PATH. Kept separate so no other scenario can pick a stub up by
|
||||
# accident, and so the caller keeps the exit status instead of aborting on it.
|
||||
seed_with_stub() { PATH="$scratch/bin:$PATH" bash "$script_dir/seed-target-dir.sh" "$@"; }
|
||||
|
||||
# Always succeeds and always prints a number: a directory that does not exist
|
||||
# is 0 entries, not an error worth aborting the suite over.
|
||||
tree_entries() {
|
||||
local n
|
||||
n=$(find "$1" -mindepth 1 2>/dev/null | wc -l) || n=0
|
||||
@@ -85,12 +99,56 @@ tree_entries() {
|
||||
return 0
|
||||
}
|
||||
|
||||
# A tree wide enough that a hardlink clone of it takes long enough to be
|
||||
# caught mid-walk. The race under test is a real interleaving, not a mocked
|
||||
# one, so the fixture has to be big enough for the window to exist: a
|
||||
# four-file tree clones in microseconds and no scheduling could ever land
|
||||
# inside it. Built by cloning one small template directory N times, which is N
|
||||
# forks rather than N*M file creations.
|
||||
# Waits for a file a concurrently running script will create. The publisher in
|
||||
# scenario 8a is started from inside the consumer's process tree rather than
|
||||
# by this script, so its completion cannot be waited on as a job.
|
||||
wait_for_file() {
|
||||
local path="$1" what="$2" deadline
|
||||
deadline=$(( $(date +%s) + 60 ))
|
||||
until [ -e "$path" ]; do
|
||||
[ "$(date +%s)" -lt "$deadline" ] || fail "$what"
|
||||
sleep 0.1
|
||||
done
|
||||
}
|
||||
|
||||
# Reads the clone's own torn-read report back and asserts WHICH of its three
|
||||
# checks fired: the copy's exit status, the entry count, or the source's
|
||||
# identity. Scenarios 8a and 8b each force exactly one of the three, and a
|
||||
# scenario that only asserted "some tear was reported" would stay green if
|
||||
# the check it exercises were deleted and one of the others happened to fire
|
||||
# in its place.
|
||||
#
|
||||
# assert_tear <log> <cp-status> <same|short> <same|differs> <message>
|
||||
assert_tear() {
|
||||
local log="$1" want_rc="$2" want_count="$3" want_inode="$4" msg="$5" line
|
||||
local re='cp rc=([0-9]+), ([0-9]+)/([0-9]+) entries, source inode ([0-9]+) -> ([0-9]+)'
|
||||
# `|| line=""` rather than a bare assignment: no match makes grep exit 1,
|
||||
# which under `set -e` would abort the suite with no message at all — the
|
||||
# exact case this assertion exists to report.
|
||||
line=$(grep -o 'was torn ([^)]*)' "$log" | head -1) || line=""
|
||||
[ -n "$line" ] || { tail -20 "$log"; fail "no torn read was reported at all ($msg)"; }
|
||||
[[ $line =~ $re ]] || fail "unrecognised torn-read report: ${line}"
|
||||
[ "${BASH_REMATCH[1]}" = "$want_rc" ] || fail "expected cp to exit ${want_rc}: ${line}"
|
||||
case "$want_count" in
|
||||
same) [ "${BASH_REMATCH[2]}" -eq "${BASH_REMATCH[3]}" ] || fail "expected a whole staging tree: ${line}" ;;
|
||||
short) [ "${BASH_REMATCH[2]}" -lt "${BASH_REMATCH[3]}" ] || fail "expected a short staging tree: ${line}" ;;
|
||||
*) fail "assert_tear: bad entry-count expectation '${want_count}'" ;;
|
||||
esac
|
||||
case "$want_inode" in
|
||||
same) [ "${BASH_REMATCH[4]}" = "${BASH_REMATCH[5]}" ] || fail "expected the source's identity to hold: ${line}" ;;
|
||||
differs) [ "${BASH_REMATCH[4]}" != "${BASH_REMATCH[5]}" ] || fail "expected the source's identity to change: ${line}" ;;
|
||||
*) fail "assert_tear: bad identity expectation '${want_inode}'" ;;
|
||||
esac
|
||||
ok "$msg (${line})"
|
||||
}
|
||||
|
||||
# A tree of many sibling subtrees, built by cloning one small template
|
||||
# directory N times — N forks rather than N*M file creations. The shape is
|
||||
# what scenarios 8a and 8b need: two generations of DIFFERENT entry count, so
|
||||
# an assertion can tell which one a consumer ended up with, and enough
|
||||
# sibling subtrees that removing one moves the count. Size no longer has to
|
||||
# buy a race window — both scenarios force their interleaving — so it stays
|
||||
# small enough to be free.
|
||||
make_wide_tree() {
|
||||
local d="$1" marker="$2" ndirs="$3" i
|
||||
mkdir -p "$d/debug/deps/.tmpl" "$d/debug/.fingerprint/x"
|
||||
@@ -170,62 +228,149 @@ fi
|
||||
ok "neither racing job fell through to a cold start"
|
||||
|
||||
echo
|
||||
echo "=== 8: seeding while the base republishes the snapshot underneath it ==="
|
||||
echo "=== 8a: a rotation landing inside the clone's identity window ==="
|
||||
# The race scenario 7 does NOT cover: a seed racing a publisher on its SOURCE
|
||||
# rather than two seeds racing on a DESTINATION. What this pins is that a
|
||||
# consumer whose source is REPLACED WHOLESALE mid-clone notices the
|
||||
# substitution and re-clones, ending up holding the whole generation now
|
||||
# published — NOT that the rotation necessarily interfered with the copy,
|
||||
# which is not guaranteed and is what made the racing version of this
|
||||
# scenario flaky (issue #3).
|
||||
#
|
||||
# The interleaving is forced rather than hoped for, the way
|
||||
# prune-cache-selftest.sh's scenario 12 forces a marker into the
|
||||
# check-to-unlink window: the consumer's own `cp` performs the rotation, so
|
||||
# it lands strictly after the entry count and inode that open the identity
|
||||
# window and strictly before the inode that closes it. The publisher is the
|
||||
# real publish-snapshot.sh running concurrently; only WHEN it runs is
|
||||
# arranged.
|
||||
ROT=$(cache_key feat/rotate)
|
||||
rm -rf "$root/snapshot-$BASE_KEY" "$root/target-$BASE_KEY"
|
||||
# Generation 1 is wide (the consumer will still be walking it when the swap
|
||||
# happens); the generation replacing it is small, so the publisher's own
|
||||
# staging clone does not itself outlast the consumer's.
|
||||
make_wide_tree "$root/snapshot-$BASE_KEY" gen1 800
|
||||
make_wide_tree "$root/target-$BASE_KEY" gen2 8
|
||||
# The two generations must differ in entry count, or "the seeded tree matches
|
||||
# the published snapshot" would hold for whichever one the consumer ended up
|
||||
# with and the fixture could not distinguish the outcomes at all.
|
||||
make_wide_tree "$root/snapshot-$BASE_KEY" gen1 12
|
||||
make_wide_tree "$root/target-$BASE_KEY" gen2 3
|
||||
gen1_entries=$(tree_entries "$root/snapshot-$BASE_KEY")
|
||||
gen1_inode=$(stat -c '%i' "$root/snapshot-$BASE_KEY")
|
||||
[ "$gen1_entries" -ne "$(tree_entries "$root/target-$BASE_KEY")" ] \
|
||||
|| fail "both generations have ${gen1_entries} entries — this fixture cannot tell them apart"
|
||||
|
||||
( bash "$script_dir/seed-target-dir.sh" "$ROT" "$BASE_KEY" "$root" jobRot > "$scratch/logRot" 2>&1; echo $? > "$scratch/rcRot" ) &
|
||||
seed_pid=$!
|
||||
mkdir -p "$scratch/bin"
|
||||
real_cp=$(command -v cp)
|
||||
cat > "$scratch/bin/cp" <<EOF
|
||||
#!/usr/bin/env bash
|
||||
# Fires once, and only on the consumer's own top-level hardlink clone —
|
||||
# identified by its destination, which is that seed's private staging path.
|
||||
# Every other cp in the process tree (the unshare copies, and the publisher's
|
||||
# own staging clone) falls through to the real one.
|
||||
if [ "\${@: -1}" = "$root/.stage-jobRot" ] && [ ! -e "$scratch/rotated" ]; then
|
||||
: > "$scratch/rotated"
|
||||
rc=0; "$real_cp" "\$@" || rc=\$?
|
||||
# Concurrently: the publisher's post-swap drain wait is against THIS
|
||||
# consumer's marker, which is held until the identity read that follows
|
||||
# this cp returns, so running the publish inline would deadlock the two
|
||||
# sides against each other.
|
||||
( bash "$script_dir/publish-snapshot.sh" "$BASE_KEY" "$root" pubRot > "$scratch/logPub" 2>&1
|
||||
echo \$? > "$scratch/rcPub" ) &
|
||||
# Hand control back only once the swap is on disk, so the identity read
|
||||
# immediately after this cp is guaranteed to resolve to the new generation.
|
||||
deadline=\$(( \$(date +%s) + 60 ))
|
||||
while [ "\$(stat -c '%i' "$root/snapshot-$BASE_KEY" 2>/dev/null)" = "$gen1_inode" ]; do
|
||||
[ "\$(date +%s)" -lt "\$deadline" ] || { echo "stub cp: the publisher never swapped the snapshot" >&2; exit 90; }
|
||||
sleep 0.05
|
||||
done
|
||||
exit \$rc
|
||||
fi
|
||||
exec "$real_cp" "\$@"
|
||||
EOF
|
||||
chmod +x "$scratch/bin/cp"
|
||||
|
||||
# Rotate only once the clone is demonstrably mid-walk. Gating on observed
|
||||
# progress rather than on a sleep is what makes the interleaving reproducible
|
||||
# instead of a coin flip that passes on a fast machine for the wrong reason.
|
||||
threshold=$(( gen1_entries / 5 ))
|
||||
progress=0
|
||||
deadline=$(( $(date +%s) + 60 ))
|
||||
while :; do
|
||||
progress=$(tree_entries "$root/.stage-jobRot")
|
||||
if [ "$progress" -ge "$threshold" ]; then break; fi
|
||||
if ! kill -0 "$seed_pid" 2>/dev/null; then
|
||||
fail "the seed finished before its clone could be caught mid-walk (fixture too small for this machine?)"
|
||||
fi
|
||||
if [ "$(date +%s)" -ge "$deadline" ]; then
|
||||
fail "the staging clone never reached ${threshold} of ${gen1_entries} entries"
|
||||
fi
|
||||
done
|
||||
ok "caught the consumer's clone mid-walk at ${progress}/${gen1_entries} entries"
|
||||
rcRot=0
|
||||
seed_with_stub "$ROT" "$BASE_KEY" "$root" jobRot > "$scratch/logRot" 2>&1 || rcRot=$?
|
||||
[ -e "$scratch/rotated" ] \
|
||||
|| fail "the stubbed cp never fired: no rotation was placed in the window, so this scenario proves nothing"
|
||||
ok "the rotation was placed inside the consumer's identity window"
|
||||
wait_for_file "$scratch/rcPub" "the publisher never finished"
|
||||
[ "$(cat "$scratch/rcPub")" = "0" ] || { tail -40 "$scratch/logPub"; fail "publish-snapshot.sh exited non-zero"; }
|
||||
[ "$rcRot" = "0" ] || { tail -40 "$scratch/logRot"; fail "the seed exited non-zero"; }
|
||||
ok "the seed completed"
|
||||
|
||||
bash "$script_dir/publish-snapshot.sh" "$BASE_KEY" "$root" pubRot > "$scratch/logPub" 2>&1 \
|
||||
|| { tail -40 "$scratch/logPub"; fail "publish-snapshot.sh exited non-zero"; }
|
||||
wait "$seed_pid"
|
||||
# WHICH check caught the rotation is the point of this scenario, so it is
|
||||
# asserted rather than assumed. The copy succeeded and the staging tree holds
|
||||
# every entry the source had when the walk began, so neither cp's exit status
|
||||
# nor the entry count is a witness here — the source's identity changing
|
||||
# under the walk is the only one. Reading the report back is what keeps this
|
||||
# scenario sensitive to losing that single comparison.
|
||||
assert_tear "$scratch/logRot" 0 same differs "the substitution was caught by the source's identity alone"
|
||||
|
||||
rot_dir="$root/target-$ROT"
|
||||
[ "$(cat "$scratch/rcRot")" = "0" ] || { tail -40 "$scratch/logRot"; fail "the seed exited non-zero"; }
|
||||
ok "the seed completed"
|
||||
# THE assertion. Before the guard, this is where it failed: the seed reported
|
||||
# `cloned in 1s` and exit 0 while target-<rot> held less than half the entries
|
||||
# of the snapshot it claimed to have cloned. Comparing against the snapshot as
|
||||
# it stands NOW is the right bar either way — a clone that raced the rotation
|
||||
# must end up holding one complete generation, and a consumer caught mid-walk
|
||||
# re-reads, so that generation is the new one.
|
||||
snap_entries=$(tree_entries "$root/snapshot-$BASE_KEY")
|
||||
rot_entries=$(tree_entries "$rot_dir")
|
||||
[ "$rot_entries" -eq "$snap_entries" ] \
|
||||
|| fail "the seeded tree is truncated: ${rot_entries} entries against the snapshot's ${snap_entries} (was ${gen1_entries} before the rotation)"
|
||||
ok "the seeded tree is complete (${rot_entries} entries, no silent truncation)"
|
||||
|| fail "the seeded tree is not the generation now published: ${rot_entries} entries against the snapshot's ${snap_entries} (generation 1 had ${gen1_entries})"
|
||||
ok "the seed re-cloned and holds the whole published generation (${rot_entries} entries)"
|
||||
assert_content "$rot_dir/debug/.fingerprint/x/dep-lib-x" gen2 "the seeded tree holds one whole generation, not a splice of two"
|
||||
grep -q 'was torn' "$scratch/logRot" || fail "the rotation was not detected as a torn read"
|
||||
ok "the torn read was detected and reported, not swallowed"
|
||||
[ -z "$(find "$root" -maxdepth 1 \( -name '.stage-*' -o -name '.reading-*' -o -name '.publish-*' \) -print -quit)" ] \
|
||||
|| fail "scratch left behind: $(find "$root" -maxdepth 1 \( -name '.stage-*' -o -name '.reading-*' -o -name '.publish-*' \) -print)"
|
||||
leftovers=$(find "$root" -maxdepth 1 \( -name '.stage-*' -o -name '.reading-*' -o -name '.publish-*' \) -print)
|
||||
[ -z "$leftovers" ] || fail "scratch left behind: ${leftovers}"
|
||||
ok "no staging, reader-marker or deferred-generation scratch left behind"
|
||||
rm -f "$scratch/bin/cp"
|
||||
|
||||
echo
|
||||
echo "=== 8b: a subtree unlinked out from under the walk, silently ==="
|
||||
# The other way a clone tears, and the one with nothing to report: a subtree
|
||||
# that leaves the parent's listing before `cp -al` reads it is simply never
|
||||
# visited. The copy exits 0 and the source's identity never changes, so the
|
||||
# entry count taken before the walk is the only witness there is — this is
|
||||
# the mode that used to publish a partial tree and call it a success.
|
||||
#
|
||||
# Modelled by renaming the subtree out and back around the consumer's own cp:
|
||||
# out before the walk starts (the only way to be missed without an error),
|
||||
# back before the retry, because the real thing that removes entries — a
|
||||
# publish rotating a generation away — has a whole generation at the path by
|
||||
# the time the retry looks.
|
||||
TRUNC=$(cache_key feat/truncate)
|
||||
TRUNC_BASE=$(cache_key release/1)
|
||||
make_wide_tree "$root/snapshot-$TRUNC_BASE" trunkgen 6
|
||||
victim="$root/snapshot-$TRUNC_BASE/debug/deps/d3"
|
||||
trunc_entries=$(tree_entries "$root/snapshot-$TRUNC_BASE")
|
||||
[ "$(tree_entries "$victim")" -gt 0 ] \
|
||||
|| fail "the subtree this scenario removes is empty — its removal would not change the entry count"
|
||||
|
||||
cat > "$scratch/bin/cp" <<EOF
|
||||
#!/usr/bin/env bash
|
||||
if [ "\${@: -1}" = "$root/.stage-jobTrunc" ] && [ ! -e "$scratch/unlinked" ]; then
|
||||
: > "$scratch/unlinked"
|
||||
mv "$victim" "$scratch/held"
|
||||
rc=0; "$real_cp" "\$@" || rc=\$?
|
||||
mv "$scratch/held" "$victim"
|
||||
exit \$rc
|
||||
fi
|
||||
exec "$real_cp" "\$@"
|
||||
EOF
|
||||
chmod +x "$scratch/bin/cp"
|
||||
|
||||
rcTrunc=0
|
||||
seed_with_stub "$TRUNC" "$TRUNC_BASE" "$root" jobTrunc > "$scratch/logTrunc" 2>&1 || rcTrunc=$?
|
||||
[ -e "$scratch/unlinked" ] \
|
||||
|| fail "the stubbed cp never fired: nothing was unlinked mid-walk, so this scenario proves nothing"
|
||||
ok "a subtree was taken out of the source's listing before the walk read it"
|
||||
[ "$rcTrunc" = "0" ] || { tail -40 "$scratch/logTrunc"; fail "the seed exited non-zero"; }
|
||||
ok "the seed completed"
|
||||
assert_tear "$scratch/logTrunc" 0 short same "the silent truncation was caught by the entry count alone"
|
||||
|
||||
trunc_dir="$root/target-$TRUNC"
|
||||
[ "$(tree_entries "$trunc_dir")" -eq "$trunc_entries" ] \
|
||||
|| fail "the seeded tree is short: $(tree_entries "$trunc_dir") entries against the source's ${trunc_entries}"
|
||||
ok "the seed re-cloned and holds every entry the source has (${trunc_entries})"
|
||||
[ -e "$victim" ] || fail "the fixture did not put the subtree back"
|
||||
[ -e "$trunc_dir/debug/deps/d3/f0" ] \
|
||||
|| fail "the subtree missed by the first walk is absent from the seeded tree"
|
||||
ok "the subtree the first walk never saw is present in the seeded tree"
|
||||
leftovers=$(find "$root" -maxdepth 1 \( -name '.stage-*' -o -name '.reading-*' \) -print)
|
||||
[ -z "$leftovers" ] || fail "scratch left behind: ${leftovers}"
|
||||
ok "no staging or reader-marker scratch left behind"
|
||||
rm -f "$scratch/bin/cp"
|
||||
echo
|
||||
echo "=== 9: a source that cannot be read fails loudly ==="
|
||||
rc=0
|
||||
|
||||
Reference in New Issue
Block a user