Files

441 lines
16 KiB
Bash
Executable File

#!/usr/bin/env bash
#
# std.sh — shared "standard library" for the fastwc benchmark scripts.
#
# Every benchmark script lives in its own directory (benchmarks/files/words,
# benchmarks/files/lines, benchmarks/stdin/piping) and sets two variables
# before sourcing this file:
# SCRIPT_DIR — the benchmark script's own directory (test data lives here)
# REPO_DIR — the repository root (release binary and tools live here)
#
# Provides the helpers every benchmark script needs:
# checkfastwc() verify a release build of fastwc exists
# checkwc() locate the coreutils wc implementation
# createtxt() create (or reuse) a text file with N such lines
# timeit() run a command once, print elapsed wall time in µs
# capture_count() print the first whitespace-separated field of output
# run_case() race fastwc against the reference on a file argument
# run_stdin_case() same, but feeding the file through standard input
# run_solo_case() time fastwc alone (no reference) and print throughput
# run_cases() run run_case for a list of sizes, fail-fast
# run_stdin_cases() run run_stdin_case for a list of sizes, fail-fast
# write_failed_report() write the human readable failure report
#
# The suites fail fast: the moment fastwc is slower than (or disagrees
# with) the reference wc, a human readable report is written to
# FAILED-benchmark.txt next to the suite and it returns non-zero.
set -u
# Pin the C locale: GNU wc -w silently switches to multibyte decoding under a
# UTF-8 locale, which would slow the oracle down and mask the documented
# byte-semantics divergence. Both sides count bytes here.
export LC_ALL=C
export LC_CTYPE=C
FASTWC="$REPO_DIR/bin/release/fastwc"
DATA_DIR="$SCRIPT_DIR/.data"
GENFILE="$REPO_DIR/benchmarks/tools/genfile" # optional C helper, built by test-all.sh
TIMEIT="$REPO_DIR/benchmarks/tools/timeit" # µs exec timer, built by test-all.sh
BENCH_NAME="${BENCH_NAME:-wc}" # set by the caller: coreutils
BENCH_REPS="${BENCH_REPS:-3}" # interleaved runs per case; minimum is kept
# A reference wc that finishes under this many µs was really measuring
# startup, not throughput. Those cases are checked for correctness and
# reported, but excluded from the averages (see finish_race).
RACE_FLOOR_US="${RACE_FLOOR_US:-5000}"
RESULT_ROWS="" # accumulated results table
# 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
BENCH_REPS=1
fi
# checkfastwc — make sure the release build exists and is executable.
checkfastwc() {
printf 'checking for release build fastwc... '
if [[ -x "$FASTWC" ]]; then
printf 'yes\n'
return 0
fi
printf 'no\n'
printf 'configure: error: no release build of fastwc found at %s\n' "$FASTWC" >&2
printf 'configure: error: run "make release" first to generate one\n' >&2
exit 1
}
# wc_impl <cmd...> — identify a wc implementation from its --version
# answer. coreutils, fastwc and toybox 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' ;;
toybox*) printf 'toybox\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 and toybox usually exist only as the
# multi-call binaries, so those are probed too; they are back in the
# suite for shits and giggles, not because they are a challenge.
# Sets COREUTILS_CMD, BUSYBOX_CMD, TOYBOX_CMD (empty if absent) and
# ORACLES, and points WC_CMD at coreutils. Exits if no coreutils wc is
# found.
checkwc() {
local dir impl
COREUTILS_CMD=()
BUSYBOX_CMD=()
TOYBOX_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
;;
toybox)
if [[ ${#TOYBOX_CMD[@]} -eq 0 ]]; then
TOYBOX_CMD=("$dir/wc")
printf 'toybox; '
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
# same for toybox
if [[ ${#TOYBOX_CMD[@]} -eq 0 ]] && command -v toybox >/dev/null 2>&1 \
&& [[ "$(wc_impl toybox wc)" == 'toybox' ]]; then
TOYBOX_CMD=(toybox wc)
printf 'toybox; '
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"
[[ ${#TOYBOX_CMD[@]} -gt 0 ]] && ORACLES="$ORACLES toybox"
}
# select_oracle <coreutils|busybox|toybox> — 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=("${BUSYBOX_CMD[@]}") ;;
toybox) BENCH_NAME='toybox'; WC_CMD=("${TOYBOX_CMD[@]}") ;;
*) return 1 ;;
esac
return 0
}
# createrandstr — print one random 10-character alphanumeric string.
createrandstr() {
local chars='abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789'
local out='' i
for ((i = 0; i < 10; i++)); do
out+="${chars:$((RANDOM % ${#chars})):1}"
done
printf '%s\n' "$out"
}
# createtxt <lines> — make sure a text file with <lines> rows of random
# 10-character alphanumeric strings exists in this suite's .data directory.
# A copy generated by a previous run is reused (checked by exact byte size:
# 10 chars + '\n' per line), so repeated benchmark runs are cheap.
# Prints the path and sets $TEXT_FILE; returns non-zero if generation fails.
createtxt() {
local lines="$1"
local expect=$((lines * 11))
local have=0
TEXT_FILE="$DATA_DIR/words-$lines.txt"
if [[ -f "$TEXT_FILE" ]]; then
have=$(stat -c '%s' "$TEXT_FILE" 2>/dev/null || printf '0')
fi
if [[ "$have" -ne "$expect" ]]; then
mkdir -p "$DATA_DIR"
if [[ -x "$GENFILE" ]]; then
"$GENFILE" "$lines" > "$TEXT_FILE" || {
printf 'createtxt: error: failed to generate %s\n' "$TEXT_FILE" >&2
return 1
}
else
printf 'createtxt: warning: %s not built, using slow shell fallback\n' "$GENFILE" >&2
printf 'createtxt: warning: run ./test-all.sh to build the helper tools\n' >&2
: > "$TEXT_FILE"
for ((i = 0; i < lines; i++)); do
createrandstr >> "$TEXT_FILE"
done
fi
fi
printf '%s\n' "$TEXT_FILE"
}
# timeit <cmd...> — run a command once and print elapsed wall time in µs
# on stdout, with the command's own output discarded. The clock starts in
# main(), after timeit's own loader has run, so every binary pays the same
# bookkeeping and the reading is the child's fork + exec + run + exit.
timeit() {
[[ -x "$TIMEIT" ]] || {
printf 'error: %s not built — run test-all.sh (or "make bench") first\n' \
"$TIMEIT" >&2
exit 1
}
"$TIMEIT" "$@"
}
# capture_count <cmd...> — print the first whitespace-separated field of a
# command's output, i.e. the count reported by `wc -w/-l` or `fastwc -w/-l`.
capture_count() {
"$@" 2>/dev/null | awk 'NR == 1 { print $1 }'
}
# write_failed_report <label> <reason> <wc_us> <fast_us> — write the
# human readable failure report to FAILED-benchmark.txt next to the suite.
write_failed_report() {
local label="$1" reason="$2" wc_us="$3" fast_us="$4"
local report="$SCRIPT_DIR/FAILED-benchmark.txt"
{
printf 'fastwc benchmark FAILED\n'
printf '=======================\n'
printf 'implementation : %s wc\n' "$BENCH_NAME"
printf 'failed test : %s\n' "$label"
printf 'failure : %s\n' "$reason"
printf '\nresults\n'
printf '%s\n' '-------'
printf '%-28s %16s %24s %8s %s\n' 'test' 'wc' 'fastwc (µs)' 'ratio' 'status'
printf '%s' "$RESULT_ROWS"
printf '\nfastwc must never be slower than %s wc — benchmark aborted.\n' "$BENCH_NAME"
} > "$report"
printf '\nbenchmark FAILED (%s): %s\n' "$BENCH_NAME" "$reason" >&2
printf 'full results written to %s\n' "$report" >&2
}
# finish_race <label> <wc_count> <fast_count> <wc_us> <fast_us> — turn the
# measured counts and times into a verdict. A count mismatch fails
# outright. A reference that finished under RACE_FLOOR_US was really
# measuring startup, not throughput: the case is reported as PASS
# (startup-bound) and left out of the averages. Raced cases pass when
# fastwc is not slower than the reference beyond a small dead-heat slack
# (200µs + 2%) that absorbs scheduler jitter on genuinely even races.
finish_race() {
local label="$1" wc_count="$2" fast_count="$3" wc_us="$4" fast_us="$5"
local ratio='-' verdict='PASS' reason='' row slack
if [[ "$fast_count" != "$wc_count" ]]; then
verdict='FAIL'
reason="output mismatch (fastwc: ${fast_count}, ${BENCH_NAME} wc: ${wc_count})"
elif (( wc_us < RACE_FLOOR_US )); then
verdict='PASS (startup-bound)'
else
ratio=$(awk -v f="$fast_us" -v w="$wc_us" 'BEGIN { printf "%.2fx", w / f }')
# feed the end-of-run average speedup (raced rows only)
printf '%s\t%s\n' "$BENCH_NAME" "${ratio%x}" >> "$RATIOS_FILE"
slack=$((200 + wc_us / 50))
if (( fast_us > wc_us + slack )); then
verdict='FAIL'
reason="fastwc was slower (fastwc: ${fast_us}µs vs ${BENCH_NAME} wc: ${wc_us}µs)"
fi
fi
row=$(printf '%-28s %16s %24s %8s %s\n' \
"$label" "wc: ${wc_us}µs" "fastwc: ${fast_us}µs" "$ratio" "$verdict")
RESULT_ROWS+="${row}"$'\n'
printf '%s\n' "$row"
if [[ "$verdict" == 'FAIL' ]]; then
write_failed_report "$label" "$reason" "$wc_us" "$fast_us"
return 1
fi
return 0
}
# run_case <words|lines> <n-lines> <-w|-l> — race the reference wc against
# fastwc on a file argument. Fails the benchmark the moment fastwc is
# slower or reports a different count.
run_case() {
local mode="$1" lines="$2" flag="$3"
local noun='lines'; [[ "$lines" -eq 1 ]] && noun='line'
local label="${mode} (${lines} ${noun})"
local file wc_count fast_count wc_us fast_us
local i d
file=$(createtxt "$lines") || return 1
# correctness: fastwc must report the same count as the reference wc
wc_count=$(capture_count "${WC_CMD[@]}" "$flag" "$file")
fast_count=$(capture_count "$FASTWC" "$flag" "$file")
# speed: interleaved timing so both commands see identical cache
# warmth; keep the minimum of $BENCH_REPS runs each
wc_us=''
fast_us=''
for ((i = 0; i < BENCH_REPS; i++)); do
d=$(timeit "${WC_CMD[@]}" "$flag" "$file")
[[ -z "$wc_us" || "$d" -lt "$wc_us" ]] && wc_us="$d"
d=$(timeit "$FASTWC" "$flag" "$file")
[[ -z "$fast_us" || "$d" -lt "$fast_us" ]] && fast_us="$d"
done
finish_race "$label" "$wc_count" "$fast_count" "$wc_us" "$fast_us"
}
# run_stdin_case <words|lines> <n-lines> <-w|-l|...> — same race, but the
# data is fed through standard input with a redirect instead of a file
# argument. Counts must also agree with the reference's stdin behavior.
run_stdin_case() {
local mode="$1" lines="$2" flag="$3"
local noun='lines'; [[ "$lines" -eq 1 ]] && noun='line'
local label="stdin ${mode} (${lines} ${noun})"
local file wc_count fast_count wc_us fast_us
local i d
file=$(createtxt "$lines") || return 1
wc_count=$(capture_count "${WC_CMD[@]}" "$flag" < "$file")
fast_count=$(capture_count "$FASTWC" "$flag" < "$file")
wc_us=''
fast_us=''
for ((i = 0; i < BENCH_REPS; i++)); do
d=$(timeit "${WC_CMD[@]}" "$flag" < "$file")
[[ -z "$wc_us" || "$d" -lt "$wc_us" ]] && wc_us="$d"
d=$(timeit "$FASTWC" "$flag" < "$file")
[[ -z "$fast_us" || "$d" -lt "$fast_us" ]] && fast_us="$d"
done
finish_race "$label" "$wc_count" "$fast_count" "$wc_us" "$fast_us"
}
# run_solo_case <n-lines> <-l|...> — time fastwc alone on <n-lines> of data,
# no reference to beat. Prints the best time and throughput. A failure to
# create the data (disk, say) skips the case instead of failing the suite.
run_solo_case() {
local lines="$1" flag="$2"
local noun='lines'; [[ "$lines" -eq 1 ]] && noun='line'
local label="solo ${lines} ${noun}"
local file best_us='' best_ms bytes gbps mlps i d
file=$(createtxt "$lines") || {
printf '%-28s %s\n' "$label" 'SKIP (could not create test data)'
return 0
}
for ((i = 0; i < BENCH_REPS; i++)); do
d=$(timeit "$FASTWC" "$flag" "$file")
[[ -z "$best_us" || "$d" -lt "$best_us" ]] && best_us="$d"
done
best_ms=$(( best_us / 1000 ))
bytes=$((lines * 11))
gbps=$(awk -v b="$bytes" -v ms="$best_ms" 'BEGIN { if (ms < 1) ms = 1; printf "%.2f", b / ms / 1e6 }')
mlps=$(awk -v l="$lines" -v ms="$best_ms" 'BEGIN { if (ms < 1) ms = 1; printf "%.1f", l / ms / 1e3 }')
printf '%-28s %25s %12s %14s\n' \
"$label" "fastwc: ${best_ms}ms (${best_us}µs)" "${gbps} GB/s" "${mlps} Mlines/s"
}
# run_cases <words|lines> <-w|-l> <size...> — run run_case for every size,
# stopping at the first failure. Returns non-zero if any case failed.
run_cases() {
local mode="$1" flag="$2"
shift 2
local rc=0 size
for size in "$@"; do
run_case "$mode" "$size" "$flag" || { rc=1; break; }
done
return $rc
}
# run_stdin_cases <words|lines> <-w|-l|...> <size...> — run run_stdin_case
# for every size, stopping at the first failure.
run_stdin_cases() {
local mode="$1" flag="$2"
shift 2
local rc=0 size
for size in "$@"; do
run_stdin_case "$mode" "$size" "$flag" || { rc=1; break; }
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[$1]++ }
END {
if (n["coreutils"])
printf "coreutils\t%.2fx\t%d\n", sum["coreutils"] / n["coreutils"], n["coreutils"];
if (n["busybox"])
printf "busybox\t%.2fx\t%d\n", sum["busybox"] / n["busybox"], n["busybox"];
if (n["toybox"])
printf "toybox\t%.2fx\t%d\n", sum["toybox"] / n["toybox"], n["toybox"];
}' "$RATIOS_FILE")"
}