Introduces support for batched MPHF lookups, chunked data handling via `SlottedKmers`, and a comprehensive benchmarking suite to measure performance across the indexing and querying pipeline. This includes new layer functionality for batch operations, chunking logic in the query layer, and scripts to measure wall time and resource usage for various commands. Documentation related to specific implementation details has also been cleaned up.
153 lines
7.1 KiB
Bash
Executable File
153 lines
7.1 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Usage: bench_mphf.sh LABEL
|
|
#
|
|
# Measures the obikmer commands that sit on MPHF lookups (see
|
|
# DevDocMD/implementation/mphf_batch_queries.md for the site inventory), on the
|
|
# 20-genome benchmark data already built under run/ (`gmake all` first).
|
|
# Nothing under run/ other than run/bench_mphf/ is written.
|
|
#
|
|
# Env:
|
|
# BINARY obikmer binary to measure (default ../src/target/release/obikmer)
|
|
# REPS repetitions per step (default 3)
|
|
# CPU_MAX passed as --cpu-max when set (default: all cores)
|
|
#
|
|
# Output: run/bench_mphf/LABEL/results.csv (label,step,rep,wall_s,maxrss_b)
|
|
# run/bench_mphf/LABEL/checksums.txt (order-independent output digests,
|
|
# to be diffed across LABELs: a speed-up must not change any of them)
|
|
set -euo pipefail
|
|
|
|
LABEL="$1"
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
RUN_DIR="${SCRIPT_DIR}/run"
|
|
BINARY="${BINARY:-${SCRIPT_DIR}/../src/target/release/obikmer}"
|
|
REPS="${REPS:-3}"
|
|
OUT="${RUN_DIR}/bench_mphf/${LABEL}"
|
|
CPU=()
|
|
[[ -n "${CPU_MAX:-}" ]] && CPU=(--cpu-max "${CPU_MAX}")
|
|
|
|
rm -rf "${OUT}"; mkdir -p "${OUT}"
|
|
RESULTS="${OUT}/results.csv"
|
|
SUMS="${OUT}/checksums.txt"
|
|
echo "label,step,rep,wall_s,maxrss_b" >"${RESULTS}"
|
|
: >"${SUMS}"
|
|
|
|
# timed STEP REP CMD... — wall time + peak RSS via BSD time(1); stdout of CMD
|
|
# goes to $OUT/last.stdout, stderr to $OUT/last.stderr.
|
|
timed() {
|
|
local step="$1" rep="$2"; shift 2
|
|
local tf="${OUT}/time.tmp"
|
|
/usr/bin/time -l -o "${tf}" "$@" >"${OUT}/last.stdout" 2>"${OUT}/last.stderr" \
|
|
|| { echo "FAILED: $step: $*" >&2; cat "${OUT}/last.stderr" >&2; exit 1; }
|
|
local wall rss
|
|
wall=$(awk '/ real /{print $1}' "${tf}")
|
|
rss=$(awk '/maximum resident set size/{print $1}' "${tf}")
|
|
echo "${LABEL},${step},${rep},${wall},${rss}" >>"${RESULTS}"
|
|
# per-stage wall times from the Reporter log lines ("done stage=X wall_secs=Y")
|
|
sed $'s/\x1b\\[[0-9;]*m//g' "${OUT}/last.stderr" \
|
|
| awk -v L="${LABEL}" -v S="${step}" -v R="${rep}" \
|
|
'/ done stage=/{ for(i=1;i<=NF;i++){ if($i ~ /^stage=/) st=substr($i,7); if($i ~ /^wall_secs=/) w=substr($i,11) } print L","S":"st","R","w",0" }' \
|
|
>>"${RESULTS}"
|
|
printf ' %-28s rep %s %8s s\n' "${step}" "${rep}" "${wall}" >&2
|
|
}
|
|
|
|
digest() { LC_ALL=C sort "$1" | md5 -q; }
|
|
|
|
# ── 0. data: the indexes under run/ may have been built by an older
|
|
# MPHF generation (ptr_hash 1.x, unreadable by current binaries), so the
|
|
# bench builds its own, once, from the simulated reads. Shared by all LABELs;
|
|
# delete run/bench_mphf/data to force a rebuild.
|
|
DATA="${RUN_DIR}/bench_mphf/data"
|
|
if [[ ! -f "${DATA}/.ready" ]]; then
|
|
echo "preparing data with ${BINARY}" >&2
|
|
mkdir -p "${DATA}/presence" "${DATA}/count"
|
|
for d in "${RUN_DIR}"/simulated_data/*/*/; do
|
|
strain="$(basename "$d")"; species="$(basename "$(dirname "$d")")"
|
|
sp="${species}--${strain}"
|
|
for kind in presence count; do
|
|
extra=(); [[ $kind == count ]] && extra=(--with-counts)
|
|
"${BINARY}" "${CPU[@]}" index --output "${DATA}/${kind}/${sp}" --force \
|
|
--theta 0 "${extra[@]}" --label "${sp}" --meta "species=${species}" \
|
|
"$d/reads_R1.fastq.gz" "$d/reads_R2.fastq.gz" 2>/dev/null
|
|
done
|
|
done
|
|
"${BINARY}" "${CPU[@]}" merge --output "${DATA}/global_presence" --force \
|
|
--force-presence "${DATA}"/presence/*/ 2>/dev/null
|
|
"${BINARY}" "${CPU[@]}" merge --output "${DATA}/global_count" --force \
|
|
"${DATA}"/count/*/ 2>/dev/null
|
|
touch "${DATA}/.ready"
|
|
fi
|
|
sources=("${DATA}"/presence/*/)
|
|
|
|
# ── 1. index: build pass 2 (mphf.index per kmer + evidence writes) ──────────
|
|
for sp in Escherichia_coli--K-12_MG1655 Candidozyma_auris--GCF_003013715.1_ASM301371v2; do
|
|
species="${sp%%--*}"; strain="${sp#*--}"
|
|
reads="${RUN_DIR}/simulated_data/${species}/${strain}"
|
|
for rep in $(seq "${REPS}"); do
|
|
timed "index_${species}" "${rep}" "${BINARY}" "${CPU[@]}" index \
|
|
--output "${OUT}/idx_${species}" --force --theta 0 --label "${sp}" \
|
|
"${reads}/reads_R1.fastq.gz" "${reads}/reads_R2.fastq.gz"
|
|
done
|
|
done
|
|
|
|
# ── 2. merge: find_batch_grouped, build_graph filter, hash_batch, index_batch ─
|
|
for rep in $(seq "${REPS}"); do
|
|
timed "merge_20_presence" "${rep}" "${BINARY}" "${CPU[@]}" merge \
|
|
--output "${OUT}/merged" --force --force-presence "${sources[@]}"
|
|
done
|
|
"${BINARY}" "${CPU[@]}" dump "${OUT}/merged" >"${OUT}/merged.dump"
|
|
echo "merged_dump $(digest "${OUT}/merged.dump")" >>"${SUMS}"
|
|
rm -f "${OUT}/merged.dump"
|
|
|
|
# ── 3. query: query stage 1 (find per kmer, layer by layer) ─────────────────
|
|
for kind in presence count; do
|
|
for sp in Escherichia_coli/K-12_MG1655 Saccharolobus_islandicus/M.16.4; do
|
|
reads="${RUN_DIR}/query_data/${sp}"
|
|
for rep in $(seq "${REPS}"); do
|
|
timed "query_${kind}_${sp%%/*}" "${rep}" "${BINARY}" "${CPU[@]}" query \
|
|
--count-missing "${DATA}/global_${kind}" \
|
|
"${reads}/reads_R1.fastq.gz" "${reads}/reads_R2.fastq.gz"
|
|
done
|
|
echo "query_${kind}_${sp%%/*} $(digest "${OUT}/last.stdout")" >>"${SUMS}"
|
|
done
|
|
done
|
|
|
|
# ── 4. filter: iter_layer_kmers → hash_batch + fill_sub_matrix ──────────────
|
|
for rep in $(seq "${REPS}"); do
|
|
timed "filter_species" "${rep}" "${BINARY}" "${CPU[@]}" filter \
|
|
--output "${OUT}/filtered" --force --ingroup "species=Escherichia_coli" \
|
|
--outgroup all --min-frac 0.5 --max-frac 1.0 --max-outgroup-count 0 \
|
|
"${DATA}/global_presence"
|
|
done
|
|
"${BINARY}" "${CPU[@]}" dump "${OUT}/filtered" >"${OUT}/filtered.dump"
|
|
echo "filtered_dump $(digest "${OUT}/filtered.dump")" >>"${SUMS}"
|
|
rm -f "${OUT}/filtered.dump"
|
|
|
|
# ── 5. convert: build_exact_evidence / build_approx_evidence ────────────────
|
|
# On an APFS clone (cp -c) so run/global_index_presence is untouched.
|
|
for rep in $(seq "${REPS}"); do
|
|
rm -rf "${OUT}/conv"; cp -cR "${DATA}/global_presence" "${OUT}/conv"
|
|
timed "convert_to_approx8" "${rep}" "${BINARY}" "${CPU[@]}" convert \
|
|
--approx-evidence 8 "${OUT}/conv"
|
|
timed "convert_to_exact" "${rep}" "${BINARY}" "${CPU[@]}" convert \
|
|
--exact-evidence "${OUT}/conv"
|
|
done
|
|
"${BINARY}" "${CPU[@]}" dump "${OUT}/conv" >"${OUT}/conv.dump"
|
|
echo "convert_roundtrip_dump $(digest "${OUT}/conv.dump")" >>"${SUMS}"
|
|
rm -rf "${OUT}/conv" "${OUT}/conv.dump"
|
|
|
|
# ── 6. phylo: sibling annex (annex.rs: find_in_partition per variant) and
|
|
# its consumer (family_scan.rs: hash_batch / find_slot) ──────────────────
|
|
for rep in $(seq "${REPS}"); do
|
|
rm -rf "${OUT}/phy"; cp -cR "${DATA}/global_presence" "${OUT}/phy"
|
|
timed "phylo_sibling_annex" "${rep}" "${BINARY}" "${CPU[@]}" phylo \
|
|
--sibling-annex "${OUT}/phy"
|
|
timed "phylo_snp_distance" "${rep}" "${BINARY}" "${CPU[@]}" phylo \
|
|
--output "${OUT}/snp" --distance snp-jc --csv "${OUT}/phy"
|
|
done
|
|
echo "phylo_snp_dist $(digest "${OUT}/snp_dist.csv")" >>"${SUMS}"
|
|
rm -rf "${OUT}/phy" "${OUT}/idx_"* "${OUT}/merged" "${OUT}/filtered" \
|
|
"${OUT}/last.stdout" "${OUT}/time.tmp"
|
|
|
|
echo "results: ${RESULTS}" >&2
|
|
echo "checksums: ${SUMS}" >&2
|