huntedbytheirs/fastwc
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

bench: race busybox again, verify the wc oracle, average the speedup

Browse Source 
Busybox wc is back in every suite, for shits and giggles. checkwc now
walks PATH and identifies each wc by its --version answer (coreutils and
fastwc respond; busybox names itself in the error it prints), so a wc
symlinked to fastwc is detected and skipped instead of silently racing
us against ourselves, and a missing coreutils is a clear configure
error. Every run now ends with the average speedup of fastwc against
coreutils and busybox, computed from the per-case ratios.

The fail-fast verdict now requires a measurable (>0ms) reference time,
so sub-millisecond cases stop flaking on startup noise, and the 100M
line monster is pinned back to the coreutils oracle instead of whatever
oracle was raced last.
This commit is contained in:
huntedbytheirs
2026-08-29 21:50:50 -04:00
parent 7ab7efc7b9
commit 7a8b763416
6 changed files with 220 additions and 74 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmarks/files/lines/bench.sh
+24 -16
View File
@@ -1,10 +1,12 @@
#!/usr/bin/env bash
# bench.sh — race fastwc against GNU coreutils wc on line counts, file input.
# Includes the monster cases: 100M lines raced against coreutils, and 1B
# lines timed solo (no reference to beat — there isn't one).
# Fails fast: the moment fastwc is slower than (or disagrees with) coreutils
# wc, a human readable report is written to FAILED-benchmark.txt and this
# script exits non-zero.
# Busybox wc is raced too, for shits and giggles. Includes the monster
# cases: 100M lines raced against coreutils (busybox through 1.1 GB is a
# spectator sport, not a benchmark), and 1B lines timed solo (no
# reference to beat — there isn't one).
# Fails fast: the moment fastwc is slower than (or disagrees with) an
# oracle wc, a human readable report is written to FAILED-benchmark.txt
# and this script exits non-zero.
#
# usage: ./bench.sh
set -u
@@ -15,17 +17,26 @@ source "$REPO_DIR/benchmarks/std.sh"
checkfastwc
checkwc
BENCH_NAME="coreutils"
printf 'benchmarking %s wc vs fastwc: lines, file input (%s interleaved runs each, minimum kept)\n' \
"$BENCH_NAME" "$BENCH_REPS"
printf '%-28s %10s %22s %8s %s\n' 'test' 'wc' 'fastwc (ms µs)' 'ratio' 'status'
for oracle in $ORACLES; do
select_oracle "$oracle" || exit 1
printf '%s\n' '--- lines ---'
if ! run_cases lines -l 10000 100000 1000000 10000000; then
exit 1
fi
printf 'benchmarking %s wc vs fastwc: lines, file input (%s interleaved runs each, minimum kept)\n' \
"$BENCH_NAME" "$BENCH_REPS"
printf '%-28s %10s %22s %8s %s\n' 'test' 'wc' 'fastwc (ms µs)' 'ratio' 'status'
printf '%s\n' '--- lines ---'
if ! run_cases lines -l 10000 100000 1000000 10000000; then
exit 1
fi
printf '\nall %s lines benchmarks passed — fastwc was never slower than %s wc\n' \
"$BENCH_NAME" "$BENCH_NAME"
done
# The monsters stay coreutils-only (busybox through 1.1 GB is a spectator
# sport, not a benchmark), so switch back from the last oracle raced.
select_oracle coreutils || exit 1
printf '%s\n' '--- monster: 100M lines vs coreutils ---'
if ! run_cases lines -l 100000000; then
exit 1
@@ -33,6 +44,3 @@ fi
printf '%s\n' '--- monster: 1B lines, solo ---'
run_solo_case 1000000000 -l
printf '\nall %s lines benchmarks passed — fastwc was never slower than %s wc\n' \
"$BENCH_NAME" "$BENCH_NAME"
benchmarks/files/words/bench.sh
+17 -13
View File
@@ -1,8 +1,9 @@
#!/usr/bin/env bash
# bench.sh — race fastwc against GNU coreutils wc on word counts, file input.
# Fails fast: the moment fastwc is slower than (or disagrees with) coreutils
# wc, a human readable report is written to FAILED-benchmark.txt and this
# script exits non-zero.
# Busybox wc is raced too, for shits and giggles.
# Fails fast: the moment fastwc is slower than (or disagrees with) an
# oracle wc, a human readable report is written to FAILED-benchmark.txt
# and this script exits non-zero.
#
# usage: ./bench.sh
set -u
@@ -13,16 +14,19 @@ source "$REPO_DIR/benchmarks/std.sh"
checkfastwc
checkwc
BENCH_NAME="coreutils"
printf 'benchmarking %s wc vs fastwc: words, file input (%s interleaved runs each, minimum kept)\n' \
"$BENCH_NAME" "$BENCH_REPS"
printf '%-28s %10s %22s %8s %s\n' 'test' 'wc' 'fastwc (ms µs)' 'ratio' 'status'
for oracle in $ORACLES; do
select_oracle "$oracle" || exit 1
printf '%s\n' '--- words ---'
if ! run_cases words -w 1 10 100 1000 10000 100000; then
exit 1
fi
printf 'benchmarking %s wc vs fastwc: words, file input (%s interleaved runs each, minimum kept)\n' \
"$BENCH_NAME" "$BENCH_REPS"
printf '%-28s %10s %22s %8s %s\n' 'test' 'wc' 'fastwc (ms µs)' 'ratio' 'status'
printf '\nall %s words benchmarks passed — fastwc was never slower than %s wc\n' \
"$BENCH_NAME" "$BENCH_NAME"
printf '%s\n' '--- words ---'
if ! run_cases words -w 1 10 100 1000 10000 100000; then
exit 1
fi
printf '\nall %s words benchmarks passed — fastwc was never slower than %s wc\n' \
"$BENCH_NAME" "$BENCH_NAME"
done
benchmarks/std.sh
+124 -13
View File
@@ -41,7 +41,13 @@ BENCH_NAME="${BENCH_NAME:-wc}" # set by the caller: coreutils
BENCH_REPS="${BENCH_REPS:-3}" # interleaved runs per case; minimum is kept
RESULT_ROWS="" # accumulated results table
WC_CMD=() # filled by checkwc()
# Per-case speedup ratios accumulate here so the run can end with the
# average speedup per oracle. test-all.sh overrides this with a shared
# temp file so every suite feeds the same average; a standalone suite
# run gets its own file ($$ differs per process).
: "${RATIOS_FILE:=/tmp/fastwc-ratios-$$.tsv}"
WC_CMD=() # filled by checkwc/select_oracle
TEXT_FILE="" # filled by createtxt()
if [[ -z "$BENCH_REPS" || "$BENCH_REPS" -lt 1 ]]; then
@@ -61,19 +67,90 @@ checkfastwc() {
exit 1
}
# checkwc — locate the coreutils wc implementation and store its invocation
# in $WC_CMD. Exits on failure.
# wc_impl <cmd...> — identify a wc implementation from its --version
# answer. coreutils and fastwc respond to --version; busybox does not
# have the option and names itself in the error it prints instead.
wc_impl() {
local out
out=$("$@" --version 2>&1)
case "$out" in
*'GNU coreutils'*) printf 'coreutils\n' ;;
fastwc*) printf 'fastwc\n' ;;
*BusyBox*) printf 'busybox\n' ;;
*) printf 'unknown\n' ;;
esac
}
# checkwc — locate the wc implementations to race against. Walks PATH
# for every wc binary and identifies each by its --version answer. A wc
# that answers as fastwc is a symlink somebody made to our own binary —
# people do symlink wc to fastwc — and is skipped, because racing
# ourselves proves nothing. Busybox usually exists only as the
# multi-call binary, so that is probed too; it is back in the suite for
# shits and giggles, not because it is a challenge.
# Sets COREUTILS_CMD, BUSYBOX_CMD (empty if absent) and ORACLES, and
# points WC_CMD at coreutils. Exits if no coreutils wc is found.
checkwc() {
printf 'checking for coreutils wc... '
if command -v wc >/dev/null 2>&1 \
&& wc --version 2>/dev/null | head -n1 | grep -qi 'GNU coreutils'; then
printf 'yes\n'
WC_CMD=(wc)
else
printf 'no\n'
printf 'configure: error: GNU Coreutils wc not found in PATH\n' >&2
local dir impl
COREUTILS_CMD=()
BUSYBOX_CMD=()
ORACLES=''
printf 'locating wc implementations... '
for dir in ${PATH//:/ }; do
[[ -n "$dir" && -x "$dir/wc" ]] || continue
impl=$(wc_impl "$dir/wc")
case "$impl" in
coreutils)
if [[ ${#COREUTILS_CMD[@]} -eq 0 ]]; then
COREUTILS_CMD=("$dir/wc")
printf 'coreutils %s; ' \
"$("$dir/wc" --version | head -n1 | sed 's/^wc (GNU coreutils) //')"
fi
;;
fastwc)
printf 'warning: %s is a fastwc symlink; skipping as oracle\n' \
"$dir/wc" >&2
;;
busybox)
if [[ ${#BUSYBOX_CMD[@]} -eq 0 ]]; then
BUSYBOX_CMD=("$dir/wc")
printf 'busybox; '
fi
;;
*) ;;
esac
done
# busybox is commonly installed as the multi-call binary only
if [[ ${#BUSYBOX_CMD[@]} -eq 0 ]] && command -v busybox >/dev/null 2>&1 \
&& [[ "$(wc_impl busybox wc)" == 'busybox' ]]; then
BUSYBOX_CMD=(busybox wc)
printf 'busybox; '
fi
if [[ ${#COREUTILS_CMD[@]} -eq 0 ]]; then
printf 'none\n'
printf 'configure: error: no coreutils wc found in PATH\n' >&2
printf 'configure: error: if you symlinked wc to fastwc, point PATH at a real coreutils first\n' >&2
exit 1
fi
printf '\n'
WC_CMD=("${COREUTILS_CMD[@]}")
ORACLES='coreutils'
[[ ${#BUSYBOX_CMD[@]} -gt 0 ]] && ORACLES="$ORACLES busybox"
}
# select_oracle <coreutils|busybox> — point the racing functions at the
# chosen oracle by setting BENCH_NAME and WC_CMD.
select_oracle() {
case "$1" in
coreutils) BENCH_NAME='coreutils'; WC_CMD=("${COREUTILS_CMD[@]}") ;;
busybox) BENCH_NAME='busybox'; WC_CMD=("${BUSYBOX_CMD[@]}") ;;
*) return 1 ;;
esac
return 0
}
# createrandstr — print one random 10-character alphanumeric string.
@@ -211,13 +288,19 @@ run_case() {
else
ratio='-'
fi
# feed the end-of-run average speedup (numeric ratios only)
if [[ "$ratio" == *x && "$ratio" != 'infx' ]]; then
printf '%s\t%s\n' "$BENCH_NAME" "${ratio%x}" >> "$RATIOS_FILE"
fi
verdict='PASS'
reason=''
if [[ "$fast_count" != "$wc_count" ]]; then
verdict='FAIL'
reason="output mismatch (fastwc: ${fast_count}, ${BENCH_NAME} wc: ${wc_count})"
elif (( fast_ms > wc_ms )); then
elif (( wc_ms > 0 && fast_ms > wc_ms )); then
# a 0ms reference is below the benchmark's resolution: sub-millisecond
# runs (startup noise, mostly) cannot prove fastwc slower
verdict='FAIL'
reason="fastwc was slower (fastwc: ${fast_ms}ms vs ${BENCH_NAME} wc: ${wc_ms}ms)"
fi
@@ -271,13 +354,19 @@ run_stdin_case() {
else
ratio='-'
fi
# feed the end-of-run average speedup (numeric ratios only)
if [[ "$ratio" == *x && "$ratio" != 'infx' ]]; then
printf '%s\t%s\n' "$BENCH_NAME" "${ratio%x}" >> "$RATIOS_FILE"
fi
verdict='PASS'
reason=''
if [[ "$fast_count" != "$wc_count" ]]; then
verdict='FAIL'
reason="output mismatch (fastwc: ${fast_count}, ${BENCH_NAME} wc: ${wc_count})"
elif (( fast_ms > wc_ms )); then
elif (( wc_ms > 0 && fast_ms > wc_ms )); then
# a 0ms reference is below the benchmark's resolution: sub-millisecond
# runs (startup noise, mostly) cannot prove fastwc slower
verdict='FAIL'
reason="fastwc was slower (fastwc: ${fast_ms}ms vs ${BENCH_NAME} wc: ${wc_ms}ms)"
fi
@@ -346,3 +435,25 @@ run_stdin_cases() {
done
return $rc
}
# print_averages — average the accumulated speedup ratios (reference time
# over fastwc time) per oracle and print them. Reads $RATIOS_FILE, which
# test-all.sh points at a shared temp file across all suites.
print_averages() {
local oracle avg n
[[ -s "$RATIOS_FILE" ]] || return 0
while IFS=$'\t' read -r oracle avg n; do
[[ -n "$oracle" ]] &&
printf 'average speedup vs %s wc: %s (%s cases)\n' \
"$oracle" "$avg" "$n"
done <<< "$(awk -F'\t' '
{ sum[$1] += $2; n[$1]++ }
END {
if (n["coreutils"])
printf "coreutils\t%.2fx\t%d\n", sum["coreutils"] / n["coreutils"], n["coreutils"];
if (n["busybox"])
printf "busybox\t%.2fx\t%d\n", sum["busybox"] / n["busybox"], n["busybox"];
}' "$RATIOS_FILE")"
}
benchmarks/stdin/piping/bench.sh
+25 -21
View File
@@ -2,9 +2,10 @@
# bench.sh — race fastwc against GNU coreutils wc on standard input, fed by
# shell redirect (the same path every real pipeline uses). Counts must agree
# with coreutils' stdin behavior, and fastwc must not be slower.
# Fails fast: the moment fastwc is slower than (or disagrees with) coreutils
# wc, a human readable report is written to FAILED-benchmark.txt and this
# script exits non-zero.
# Busybox wc is raced too, for shits and giggles.
# Fails fast: the moment fastwc is slower than (or disagrees with) an
# oracle wc, a human readable report is written to FAILED-benchmark.txt
# and this script exits non-zero.
#
# usage: ./bench.sh
set -u
@@ -15,26 +16,29 @@ source "$REPO_DIR/benchmarks/std.sh"
checkfastwc
checkwc
BENCH_NAME="coreutils"
printf 'benchmarking %s wc vs fastwc: stdin (%s interleaved runs each, minimum kept)\n' \
"$BENCH_NAME" "$BENCH_REPS"
printf '%-28s %10s %22s %8s %s\n' 'test' 'wc' 'fastwc (ms µs)' 'ratio' 'status'
for oracle in $ORACLES; do
select_oracle "$oracle" || exit 1
printf '%s\n' '--- stdin lines ---'
if ! run_stdin_cases lines -l 10000 100000 1000000 10000000; then
exit 1
fi
printf 'benchmarking %s wc vs fastwc: stdin (%s interleaved runs each, minimum kept)\n' \
"$BENCH_NAME" "$BENCH_REPS"
printf '%-28s %10s %22s %8s %s\n' 'test' 'wc' 'fastwc (ms µs)' 'ratio' 'status'
printf '%s\n' '--- stdin words ---'
if ! run_stdin_cases words -w 1000 100000 1000000; then
exit 1
fi
printf '%s\n' '--- stdin lines ---'
if ! run_stdin_cases lines -l 10000 100000 1000000 10000000; then
exit 1
fi
printf '%s\n' '--- stdin lines+words+bytes ---'
if ! run_stdin_cases lines -lwc 1000000; then
exit 1
fi
printf '%s\n' '--- stdin words ---'
if ! run_stdin_cases words -w 1000 100000 1000000; then
exit 1
fi
printf '\nall %s stdin benchmarks passed — fastwc was never slower than %s wc\n' \
"$BENCH_NAME" "$BENCH_NAME"
printf '%s\n' '--- stdin lines+words+bytes ---'
if ! run_stdin_cases lines -lwc 1000000; then
exit 1
fi
printf '\nall %s stdin benchmarks passed — fastwc was never slower than %s wc\n' \
"$BENCH_NAME" "$BENCH_NAME"
done
benchmarks/test-all.sh
+16 -2
View File
@@ -1,12 +1,22 @@
#!/usr/bin/env bash
# test-all.sh — compile the benchmark helper tools first, then run every
# benchmark suite (words, lines incl. monsters, stdin). Exits non-zero if
# any of them fails.
# benchmark suite (words, lines incl. monsters, stdin) against every
# oracle found (coreutils, plus busybox for shits and giggles). Exits
# non-zero if any of them fails, and ends with the average speedup of
# fastwc against each oracle.
#
# usage: ./test-all.sh
set -u
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
REPO_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
# Share one ratios file across all suites so the final average covers
# every case; each suite still races through its own process.
RATIOS_FILE="$(mktemp /tmp/fastwc-ratios.XXXXXX)"
export RATIOS_FILE
source "$SCRIPT_DIR/std.sh"
# 1. build the helper tools before running any benchmark so createtxt()
# can use the fast C generator instead of the slow shell fallback
@@ -29,6 +39,10 @@ rc_stdin=$?
if [[ $rc_words -ne 0 || $rc_lines -ne 0 || $rc_stdin -ne 0 ]]; then
printf '\ntest-all: FAILED (words=%s, lines=%s, stdin=%s)\n' \
"$rc_words" "$rc_lines" "$rc_stdin" >&2
print_averages
rm -f "$RATIOS_FILE"
exit 1
fi
printf '\ntest-all: all benchmarks passed\n'
print_averages
rm -f "$RATIOS_FILE"