feat: implement in-memory column builders and refactor merge partitioning
Introduce `MemBitVecBuilder` and `MemCompactIntVecBuilder` to construct columns in RAM before writing, reducing the number of open file descriptors during merge operations. Refactor `partition_merge.rs` to use these new builders via `add_mem_col`, decoupling live memory mappings from source counts to prevent `SIGBUS` errors. - Add `mem_builder` module with `MemBitVecBuilder` and `MemCompactIntVecBuilder` structs for in-memory column construction and PCIV file writing. - Extend `MatrixBuilder` with `add_mem_col` and `n_cols` methods, updating `ColBuilder` enum to support `MemBit` and `MemInt` variants. - Refactor `partition_merge.rs` to use `add_mem_col` instead of `add_col`, introducing `run_pass2` for batch processing and optimizing destination layer handling. - Update `format.rs` with `pciv_index_layout`, `write_pciv_header`, and `write_pciv_tail` functions to manage PCIV index layout and header/tail sections. - Modify `mmap_file.rs` to use `write_std_header` and introduce `write_built` for standardized file writing and flushing logic. - Make `MAGIC` constant public in `bitvec.rs` and update documentation for memory mapping alignment and structure. - Add test modules `tests/matrix_builder.rs` and `tests/mem_builder.rs` to verify column counts and byte-identical output of new builders against persistent versions. - Update `mkdocs.yml` navigation to include "Merge mmap audit (2026-11)" documentation entry. - Add implementation audit documentation in `DevDocMD/implementation/merge_mmap_audit.md` detailing memory mapping failures and refactoring plans. - Add merge testing scripts `scripts/smoke_test_merge.sh` and `scripts/bench_merge_oracle.sh` for validation and benchmarking. - Bump `obikmer` package version from 1.4.2 to 1.4.3 in `Cargo.toml`.
This commit is contained in:
1 parent
b35127e4e3
commit
1f199c69db
25 files changed
+1631
-687
No files matched your search
Executable
+186
@@ -0,0 +1,186 @@
|
||||
#!/usr/bin/env bash
|
||||
# smoke_test_merge.sh — end-to-end golden-output oracle for `obikmer merge`
|
||||
#
|
||||
# Non-regression oracle for refactors of obikmerge (see
|
||||
# DevDocMD/implementation/merge_mmap_audit.md). Like smoke_test_index.sh it
|
||||
# drives the real CLI, never the library APIs.
|
||||
#
|
||||
# What it does:
|
||||
# 1. builds `obikmer` (debug)
|
||||
# 2. generates (on --record) 4 small deterministic FASTA files A, B, C, D sharing
|
||||
# fragments, so that merge both hits k-mers already present in the
|
||||
# destination ("existing layer" path) and creates new ones ("new layer"
|
||||
# path). D carries a short motif repeated > 255 times so the count track
|
||||
# exercises the compact-int overflow (counts >= 255).
|
||||
# 3. on --record, indexes each genome twice (presence, --with-counts) and
|
||||
# freezes the indexes in DIR/sources; --check reuses them (see below),
|
||||
# with -p PARTITIONS partitions
|
||||
# 4. runs the merge scenarios:
|
||||
# s1_presence / s1_count merge A B C D
|
||||
# s3_dense merge A B C D --dense (presence)
|
||||
# Scenario 2 (merge A B -> AB, then merge AB C D: multi-genome source,
|
||||
# multi-layer destination) is NOT included: the current code cannot
|
||||
# re-merge a merge output — its matrices are packed (sparse or dense)
|
||||
# at finalize, and `MatrixBuilder::resume` expects the columnar
|
||||
# `meta.json` layout (ENOENT). Known bug, to be fixed separately; see
|
||||
# DevDocMD/implementation/merge_mmap_audit.md, "Known issue".
|
||||
# 5. dumps every result with `obikmer dump --debug` (partition + layer
|
||||
# columns included, so a k-mer moving between layers is caught), keeps
|
||||
# the CSV header first and sorts the rows (LC_ALL=C)
|
||||
# 6. --record DIR writes the sorted dumps to DIR;
|
||||
# --check DIR regenerates them and diffs against DIR
|
||||
#
|
||||
# Usage:
|
||||
# scripts/smoke_test_merge.sh (--record DIR | --check DIR) [-p PARTITIONS] [--keep]
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
K=21
|
||||
M=9
|
||||
PARTITIONS=4
|
||||
KEEP=0
|
||||
MODE=""
|
||||
DIR=""
|
||||
|
||||
while [ $# -gt 0 ]; do
|
||||
case "$1" in
|
||||
--record) MODE=record; DIR="$2"; shift 2 ;;
|
||||
--check) MODE=check; DIR="$2"; shift 2 ;;
|
||||
-p) PARTITIONS="$2"; shift 2 ;;
|
||||
--keep) KEEP=1; shift ;;
|
||||
*) echo "unknown argument: $1" >&2; exit 2 ;;
|
||||
esac
|
||||
done
|
||||
[ -n "$MODE" ] || { echo "usage: $0 (--record DIR | --check DIR) [-p N] [--keep]" >&2; exit 2; }
|
||||
|
||||
REPO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||
case "$DIR" in /*) ;; *) DIR="$PWD/$DIR" ;; esac
|
||||
WORK="$(mktemp -d -t obikmer_merge_smoke.XXXXXX)"
|
||||
|
||||
cleanup() {
|
||||
if [ "$KEEP" -eq 1 ]; then echo "kept: $WORK"; else rm -rf "$WORK"; fi
|
||||
}
|
||||
trap cleanup EXIT
|
||||
|
||||
fail() {
|
||||
echo "FAIL: $1" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
# ── 1. build ────────────────────────────────────────────────────────────────
|
||||
if ! (cd "$REPO_ROOT/src" && cargo build -q -p obikmer --bin obikmer) > "$WORK/build.log" 2>&1; then
|
||||
cat "$WORK/build.log" >&2
|
||||
fail "cargo build failed"
|
||||
fi
|
||||
BIN="$REPO_ROOT/src/target/debug/obikmer"
|
||||
|
||||
run() { # run LOGNAME CMD... — runs obikmer, dumps its log on failure
|
||||
local log="$WORK/$1.log"; shift
|
||||
if ! "$BIN" "$@" > "$log" 2>&1; then
|
||||
cat "$log" >&2
|
||||
fail "obikmer $1 exited non-zero"
|
||||
fi
|
||||
}
|
||||
|
||||
# ── 2. deterministic genomes with shared fragments ──────────────────────────
|
||||
python3 - "$WORK" <<'EOF'
|
||||
import random, sys
|
||||
out = sys.argv[1]
|
||||
rng = random.Random(20261117)
|
||||
def rnd(n): return "".join(rng.choice("ACGT") for _ in range(n))
|
||||
frag = {i: rnd(600) for i in range(5)} # shared fragments F0..F4
|
||||
motif = rnd(40) # tandem motif (counts >= 255)
|
||||
genomes = {
|
||||
"A": [rnd(1500), frag[0], rnd(300), frag[1]],
|
||||
"B": [frag[1], rnd(1200), frag[2], motif * 3],
|
||||
"C": [frag[0], rnd(800), frag[2], rnd(400), frag[3]],
|
||||
"D": [frag[3], rnd(1000), motif * 300, frag[4], rnd(200), frag[0][:250]],
|
||||
}
|
||||
for name, parts in genomes.items():
|
||||
with open(f"{out}/{name}.fasta", "w") as f:
|
||||
for j, p in enumerate(parts):
|
||||
f.write(f">{name}_{j}\n{p}\n")
|
||||
EOF
|
||||
|
||||
# ── 3. source indexes: built on --record, frozen in DIR/sources, reused on
|
||||
# --check. `obikmer index` is not byte-stable run to run (unitig
|
||||
# segmentation, hence unitigs.bin size, varies — measured 2026-11-17),
|
||||
# and the merge base is the source with the largest unitigs.bin
|
||||
# (`choose_base`), so re-indexing on every check would make the merge
|
||||
# base — and the column order — flip between A and C. Freezing the
|
||||
# sources makes this an oracle of `merge` alone. Copied (not linked)
|
||||
# into WORK, since merge's bootstrap hard-links from its base source.
|
||||
if [ "$MODE" = record ]; then
|
||||
for G in A B C D; do
|
||||
run "index_${G}_pres" index -k "$K" -m "$M" --theta 0 -p "$PARTITIONS" \
|
||||
--label "$G" -o "$WORK/$G.pres.idx" "$WORK/$G.fasta"
|
||||
run "index_${G}_cnt" index -k "$K" -m "$M" --theta 0 -p "$PARTITIONS" \
|
||||
--with-counts --label "$G" -o "$WORK/$G.cnt.idx" "$WORK/$G.fasta"
|
||||
done
|
||||
rm -rf "$DIR/sources"
|
||||
mkdir -p "$DIR/sources"
|
||||
cp -R "$WORK"/*.idx "$DIR/sources/"
|
||||
else
|
||||
[ -d "$DIR/sources" ] || fail "no frozen source indexes in $DIR/sources (run --record first)"
|
||||
cp -R "$DIR/sources"/*.idx "$WORK/"
|
||||
fi
|
||||
|
||||
# ── 4. merge scenarios ──────────────────────────────────────────────────────
|
||||
OUT="$WORK/out"
|
||||
mkdir -p "$OUT"
|
||||
dump() { # dump NAME INDEX — header first, rows sorted
|
||||
local raw="$WORK/$1.dump.csv"
|
||||
if ! "$BIN" dump --debug "$2" > "$raw" 2> "$WORK/dump_$1.log"; then
|
||||
cat "$WORK/dump_$1.log" >&2
|
||||
fail "obikmer dump $1 exited non-zero"
|
||||
fi
|
||||
{ head -n 1 "$raw"; tail -n +2 "$raw" | LC_ALL=C sort; } > "$OUT/$1.csv"
|
||||
}
|
||||
|
||||
for T in pres cnt; do
|
||||
run "s1_$T" merge -o "$WORK/s1_$T.idx" \
|
||||
"$WORK/A.$T.idx" "$WORK/B.$T.idx" "$WORK/C.$T.idx" "$WORK/D.$T.idx"
|
||||
dump "s1_$T" "$WORK/s1_$T.idx"
|
||||
done
|
||||
|
||||
run s3_dense merge --dense -o "$WORK/s3_dense.idx" \
|
||||
"$WORK/A.pres.idx" "$WORK/B.pres.idx" "$WORK/C.pres.idx" "$WORK/D.pres.idx"
|
||||
dump s3_dense "$WORK/s3_dense.idx"
|
||||
|
||||
# sanity: no dump may be empty (header + at least one row)
|
||||
for f in "$OUT"/*.csv; do
|
||||
[ "$(wc -l < "$f")" -gt 1 ] || fail "empty dump: $(basename "$f")"
|
||||
done
|
||||
|
||||
# ── 5. record or check ──────────────────────────────────────────────────────
|
||||
if [ "$MODE" = record ]; then
|
||||
mkdir -p "$DIR"
|
||||
rm -f "$DIR"/*.csv
|
||||
cp "$OUT"/*.csv "$DIR"/
|
||||
echo "RECORDED: $(ls "$OUT" | wc -l | tr -d ' ') dumps → $DIR"
|
||||
wc -l "$DIR"/*.csv
|
||||
exit 0
|
||||
fi
|
||||
|
||||
[ -d "$DIR" ] || fail "reference directory not found: $DIR"
|
||||
STATUS=0
|
||||
for ref in "$DIR"/*.csv; do
|
||||
name="$(basename "$ref")"
|
||||
if [ ! -f "$OUT/$name" ]; then
|
||||
echo "FAIL $name (not regenerated)"; STATUS=1
|
||||
elif diff -q "$ref" "$OUT/$name" > /dev/null; then
|
||||
echo "ok $name"
|
||||
else
|
||||
echo "FAIL $name"; { diff "$ref" "$OUT/$name" || true; } | head -20; STATUS=1
|
||||
fi
|
||||
done
|
||||
for new in "$OUT"/*.csv; do
|
||||
[ -f "$DIR/$(basename "$new")" ] || { echo "FAIL $(basename "$new") (no reference)"; STATUS=1; }
|
||||
done
|
||||
|
||||
if [ "$STATUS" -eq 0 ]; then
|
||||
echo "PASS: all merge dumps identical to $DIR"
|
||||
else
|
||||
echo "FAIL: merge dumps differ from $DIR" >&2
|
||||
fi
|
||||
exit "$STATUS"
|
||||
Reference in new issue
Block a user