mirror of
https://github.com/rustfs/rustfs.git
synced 2026-08-29 08:27:06 +00:00
ci: ratchet ecstore ::other(format!) error construction shrink-only (#6614)
Backlog#1845 step 2. reduce_errs buckets per-disk errors by equality, and Io equality compares the rendered message, so an other(format!(..)) error embedding per-disk detail makes N same-cause failures count as N distinct errors during quorum aggregation. The census that opened the issue counted 1,609 such sites; the production count in crates/ecstore/src is 657 today and was still growing. Freeze it: scripts/check_error_other_format_ratchet.sh counts ::other(format! sites per file (trailing #[cfg(test)] modules excluded) against a shrink-only per-file baseline, failing on any growth and on stale entries after a shrink, following the layer-dependency-baseline model. Wired into make pre-commit / pre-pr / dev-check and the CI Quick Checks job. Ref rustfs/backlog#1845
This commit is contained in:
Zhengchao An
Executable
+141
@@ -0,0 +1,141 @@
|
||||
#!/usr/bin/env bash
|
||||
# Ratchet guard for `…::other(format!` error construction in rustfs-ecstore
|
||||
# (rustfs/backlog#1845, PR2).
|
||||
#
|
||||
# Quorum aggregation (`reduce_errs` in crates/ecstore/src/disk/error_reduce.rs)
|
||||
# buckets errors by equality, and `DiskError::Io` / `StorageError::Io` equality
|
||||
# compares the *rendered message*. An `other(format!(…))` error that embeds
|
||||
# per-disk / per-peer detail therefore makes N same-cause failures count as N
|
||||
# distinct errors, starving quorum decisions and heal retry classification
|
||||
# (pinned by crates/ecstore/src/error/conversion_roundtrip_tests.rs).
|
||||
#
|
||||
# This guard freezes the existing `::other(format!` call sites in
|
||||
# crates/ecstore/src as a per-file baseline and fails when any file GROWS its
|
||||
# count (or a new file introduces one). New code must use a typed error
|
||||
# variant, or keep the formatted detail out of the bucketed message (e.g. put
|
||||
# it in a wrapped source error with a stable Display).
|
||||
#
|
||||
# The baseline is SHRINK-ONLY, following the layer-dependency-baseline model
|
||||
# (backlog#1834): when a PR removes call sites, regenerate the baseline in the
|
||||
# same PR via --update-baseline; a diff that raises a count or adds a file is
|
||||
# baselining a brand-new bucketing hazard and must carry an explicit exemption
|
||||
# rationale in the PR description.
|
||||
#
|
||||
# Trailing `#[cfg(test)] mod … {` blocks are excluded from the counts: test
|
||||
# construction of other(format!) never reaches production quorum paths, and
|
||||
# the repository convention keeps inline test modules at the end of the file.
|
||||
#
|
||||
# Usage:
|
||||
# scripts/check_error_other_format_ratchet.sh # check
|
||||
# scripts/check_error_other_format_ratchet.sh --update-baseline
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||
BASELINE_FILE="${ROOT_DIR}/scripts/error-other-format-baseline.txt"
|
||||
SCOPE="crates/ecstore/src"
|
||||
PATTERN='::other\(\s*format!'
|
||||
MODE="check"
|
||||
|
||||
if [[ "${1:-}" == "--update-baseline" ]]; then
|
||||
MODE="update"
|
||||
fi
|
||||
|
||||
TMP_DIR="$(mktemp -d)"
|
||||
trap 'rm -rf "$TMP_DIR"' EXIT
|
||||
|
||||
count_file_sites() {
|
||||
# Strip a trailing `#[cfg(test)]\nmod … {` region (repo convention keeps the
|
||||
# test module last), then count pattern occurrences across line breaks.
|
||||
perl -0777 -pe 's/\n#\[cfg\(test\)\]\s*\nmod\s+[A-Za-z0-9_]+\s*\{.*$/\n/s' "$1" |
|
||||
perl -0777 -ne 'my $c = () = /::other\(\s*format!/g; print "$c\n";'
|
||||
}
|
||||
|
||||
CURRENT="${TMP_DIR}/current.txt"
|
||||
: >"$CURRENT"
|
||||
|
||||
while IFS= read -r file; do
|
||||
count="$(count_file_sites "${ROOT_DIR}/${file}")"
|
||||
if (( count > 0 )); then
|
||||
printf '%s|%s\n' "$count" "$file" >>"$CURRENT"
|
||||
fi
|
||||
done < <(cd "$ROOT_DIR" && rg -U -l "$PATTERN" --type rust "$SCOPE" | LC_ALL=C sort)
|
||||
|
||||
total="$(awk -F'|' '{sum += $1} END {print sum + 0}' "$CURRENT")"
|
||||
|
||||
write_baseline_file() {
|
||||
cat >"$BASELINE_FILE" <<'EOF'
|
||||
# `::other(format!` ratchet baseline for crates/ecstore/src (backlog#1845 PR2).
|
||||
#
|
||||
# SHRINK-ONLY: entries are `count|file`. A PR may lower a count or drop a file
|
||||
# (after replacing the call sites with typed variants) by re-running
|
||||
# scripts/check_error_other_format_ratchet.sh --update-baseline. A PR that
|
||||
# raises a count or adds a file is introducing a new quorum-bucketing hazard
|
||||
# and must carry an explicit exemption rationale in its description.
|
||||
EOF
|
||||
cat "$CURRENT" >>"$BASELINE_FILE"
|
||||
}
|
||||
|
||||
if [[ "$MODE" == "update" ]]; then
|
||||
write_baseline_file
|
||||
echo "Updated baseline: $BASELINE_FILE (total call sites: $total)"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
if [[ ! -f "$BASELINE_FILE" ]]; then
|
||||
echo "Baseline file missing: $BASELINE_FILE"
|
||||
echo "Run: scripts/check_error_other_format_ratchet.sh --update-baseline"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
BASELINE_SORTED="${TMP_DIR}/baseline.txt"
|
||||
grep -v '^#' "$BASELINE_FILE" | grep -v '^$' | LC_ALL=C sort -t'|' -k2 >"$BASELINE_SORTED"
|
||||
LC_ALL=C sort -t'|' -k2 -o "$CURRENT" "$CURRENT"
|
||||
|
||||
STATUS=0
|
||||
GREW="${TMP_DIR}/grew.txt"
|
||||
SHRANK="${TMP_DIR}/shrank.txt"
|
||||
: >"$GREW"
|
||||
: >"$SHRANK"
|
||||
|
||||
# Compare per-file counts; report growth and staleness separately.
|
||||
awk -F'|' -v grew="$GREW" -v shrank="$SHRANK" '
|
||||
NR == FNR { baseline[$2] = $1; next }
|
||||
{
|
||||
current[$2] = $1
|
||||
if (!($2 in baseline)) {
|
||||
printf "%s: %s call sites (new file, baseline has none)\n", $2, $1 >> grew
|
||||
} else if ($1 + 0 > baseline[$2] + 0) {
|
||||
printf "%s: %s call sites (baseline %s)\n", $2, $1, baseline[$2] >> grew
|
||||
} else if ($1 + 0 < baseline[$2] + 0) {
|
||||
printf "%s: %s call sites (baseline %s)\n", $2, $1, baseline[$2] >> shrank
|
||||
}
|
||||
}
|
||||
END {
|
||||
for (file in baseline) {
|
||||
if (!(file in current)) {
|
||||
printf "%s: baseline lists %s call sites but the file now has none\n", file, baseline[file] >> shrank
|
||||
}
|
||||
}
|
||||
}
|
||||
' "$BASELINE_SORTED" "$CURRENT"
|
||||
|
||||
if [[ -s "$GREW" ]]; then
|
||||
echo "error(format!) ratchet failed: new '::other(format!' call sites in crates/ecstore/src"
|
||||
echo "Use a typed error variant instead — formatted per-disk detail fragments reduce_errs quorum buckets (backlog#1845):"
|
||||
cat "$GREW"
|
||||
STATUS=1
|
||||
fi
|
||||
|
||||
if [[ -s "$SHRANK" ]]; then
|
||||
echo "error(format!) ratchet: counts went DOWN (good) but the baseline is stale."
|
||||
echo "Re-run scripts/check_error_other_format_ratchet.sh --update-baseline and commit the shrunken baseline:"
|
||||
cat "$SHRANK"
|
||||
STATUS=1
|
||||
fi
|
||||
|
||||
if (( STATUS == 0 )); then
|
||||
echo "error(format!) ratchet passed (total call sites: $total)."
|
||||
fi
|
||||
|
||||
exit "$STATUS"
|
||||
@@ -0,0 +1,79 @@
|
||||
# `::other(format!` ratchet baseline for crates/ecstore/src (backlog#1845 PR2).
|
||||
#
|
||||
# SHRINK-ONLY: entries are `count|file`. A PR may lower a count or drop a file
|
||||
# (after replacing the call sites with typed variants) by re-running
|
||||
# scripts/check_error_other_format_ratchet.sh --update-baseline. A PR that
|
||||
# raises a count or adds a file is introducing a new quorum-bucketing hazard
|
||||
# and must carry an explicit exemption rationale in its description.
|
||||
2|crates/ecstore/src/bucket/bucket_target_sys.rs
|
||||
4|crates/ecstore/src/bucket/lifecycle/bucket_lifecycle_ops.rs
|
||||
3|crates/ecstore/src/bucket/lifecycle/durable_namespace.rs
|
||||
2|crates/ecstore/src/bucket/lifecycle/metadata_boundary.rs
|
||||
4|crates/ecstore/src/bucket/lifecycle/tier_delete_journal.rs
|
||||
1|crates/ecstore/src/bucket/lifecycle/transition_transaction.rs
|
||||
27|crates/ecstore/src/bucket/metadata.rs
|
||||
22|crates/ecstore/src/bucket/metadata_sys.rs
|
||||
3|crates/ecstore/src/bucket/msgp_decode.rs
|
||||
1|crates/ecstore/src/bucket/object_lock/objectlock_sys.rs
|
||||
3|crates/ecstore/src/bucket/quota/reservation.rs
|
||||
1|crates/ecstore/src/bucket/replication/replication_object_config.rs
|
||||
2|crates/ecstore/src/bucket/replication/replication_pool.rs
|
||||
2|crates/ecstore/src/bucket/replication/replication_target_boundary.rs
|
||||
1|crates/ecstore/src/client/api_put_object_multipart.rs
|
||||
2|crates/ecstore/src/client/api_put_object_streaming.rs
|
||||
1|crates/ecstore/src/client/api_s3_datatypes.rs
|
||||
1|crates/ecstore/src/client/signer_error.rs
|
||||
5|crates/ecstore/src/client/transition_api.rs
|
||||
3|crates/ecstore/src/cluster/rpc/http_auth.rs
|
||||
2|crates/ecstore/src/cluster/rpc/internode_data_transport.rs
|
||||
17|crates/ecstore/src/cluster/rpc/peer_rest_client.rs
|
||||
11|crates/ecstore/src/cluster/rpc/peer_s3_client.rs
|
||||
43|crates/ecstore/src/cluster/rpc/remote_disk.rs
|
||||
7|crates/ecstore/src/config/com.rs
|
||||
14|crates/ecstore/src/config/storageclass.rs
|
||||
185|crates/ecstore/src/core/pools.rs
|
||||
8|crates/ecstore/src/data_movement/mod.rs
|
||||
2|crates/ecstore/src/data_usage/local_snapshot.rs
|
||||
12|crates/ecstore/src/data_usage/mod.rs
|
||||
1|crates/ecstore/src/diagnostics/admin_server_info.rs
|
||||
5|crates/ecstore/src/disk/local.rs
|
||||
1|crates/ecstore/src/disk/mod.rs
|
||||
5|crates/ecstore/src/erasure/codec/bridge.rs
|
||||
1|crates/ecstore/src/erasure/coding/decode_reader.rs
|
||||
10|crates/ecstore/src/erasure/coding/encode.rs
|
||||
25|crates/ecstore/src/erasure/coding/erasure.rs
|
||||
4|crates/ecstore/src/layout/disks_layout.rs
|
||||
2|crates/ecstore/src/layout/endpoint.rs
|
||||
17|crates/ecstore/src/layout/endpoints.rs
|
||||
1|crates/ecstore/src/layout/format.rs
|
||||
1|crates/ecstore/src/layout/pool_space.rs
|
||||
1|crates/ecstore/src/layout/set_layout.rs
|
||||
19|crates/ecstore/src/object_api/readers.rs
|
||||
1|crates/ecstore/src/object_api/types.rs
|
||||
3|crates/ecstore/src/runtime/sources.rs
|
||||
4|crates/ecstore/src/services/batch_processor.rs
|
||||
14|crates/ecstore/src/services/notification_sys.rs
|
||||
16|crates/ecstore/src/services/rebalance/control.rs
|
||||
1|crates/ecstore/src/services/rebalance/entry.rs
|
||||
8|crates/ecstore/src/services/rebalance/meta.rs
|
||||
8|crates/ecstore/src/services/rebalance/runtime.rs
|
||||
19|crates/ecstore/src/services/rebalance/worker.rs
|
||||
33|crates/ecstore/src/services/tier/tier.rs
|
||||
1|crates/ecstore/src/services/tier/tier_config.rs
|
||||
1|crates/ecstore/src/services/tier/warm_backend_gcs.rs
|
||||
1|crates/ecstore/src/services/tier/warm_backend_s3.rs
|
||||
1|crates/ecstore/src/services/tier/warm_backend_wasabi.rs
|
||||
7|crates/ecstore/src/set_disk/core/io_primitives.rs
|
||||
1|crates/ecstore/src/set_disk/mod.rs
|
||||
3|crates/ecstore/src/set_disk/ops/bitrot_self_verify.rs
|
||||
2|crates/ecstore/src/set_disk/ops/heal.rs
|
||||
8|crates/ecstore/src/set_disk/ops/multipart.rs
|
||||
2|crates/ecstore/src/set_disk/ops/object.rs
|
||||
3|crates/ecstore/src/set_disk/read.rs
|
||||
5|crates/ecstore/src/store/bucket.rs
|
||||
1|crates/ecstore/src/store/heal_walk.rs
|
||||
12|crates/ecstore/src/store/init.rs
|
||||
2|crates/ecstore/src/store/init_format.rs
|
||||
3|crates/ecstore/src/store/multipart.rs
|
||||
8|crates/ecstore/src/store/object.rs
|
||||
5|crates/ecstore/src/store/rebalance/support.rs
|
||||
Reference in New Issue
Block a user