#!/bin/bash
# web-benchmark.sh — race the three lumbda HTTP servers
# against Python http.server and busybox httpd.
#
# No wrk/ab/nginx dependency — we use xargs+curl for concurrency.
#
# Fixed 1KB body at /bench for all servers. Wall-clock time over
# N parallel-safe requests = throughput.

set -u
cd "$(dirname "$0")/.."

REQUESTS=${REQUESTS:-500}
CONCURRENCY=${CONCURRENCY:-10}
PY="python3 lumbda.py --fast"
C="./c/lumbda"
ASM="./asm/lumbda"
ASM_GC="./asm/lumbda-gc"

# Track every server PID we spawn; the EXIT trap kills them all.
# Asm has no GC — a leaked server leaks 64 MB per heap growth
# indefinitely. Belt + suspenders: kill the whole process group too.
declare -a SPAWNED_PIDS=()

cleanup() {
    local pid
    for pid in "${SPAWNED_PIDS[@]}"; do
        kill "$pid" 2>/dev/null
    done
    sleep 0.2
    for pid in "${SPAWNED_PIDS[@]}"; do
        kill -9 "$pid" 2>/dev/null
    done
    rm -rf "${STATIC_DIR:-/nonexistent/xyz}"
    # Final sanity: any stray servers from examples/http-server?
    # Narrow to processes actually serving the HTTP example, not the
    # shell running this script or tmux sessions with "lumbda"
    # in their name.
    local strays
    strays=$(pgrep -u "$USER" -f 'examples/http-server\.lsp|http\.server 8080' | wc -l)
    if [ "$strays" -gt 0 ]; then
        echo "WARNING: $strays HTTP server process(es) still running:" >&2
        pgrep -u "$USER" -af 'examples/http-server\.lsp|http\.server 8080' >&2
        pkill -9 -u "$USER" -f 'examples/http-server\.lsp|http\.server 8080' 2>/dev/null
    fi
}
trap cleanup EXIT INT TERM

pad() { printf "  %-36s " "$1"; }

bench_one() {
    local label="$1" port="$2" path="$3"
    pad "$label"
    # Warm up
    curl -s "http://localhost:$port$path" > /dev/null
    # Measure
    local t0 t1
    t0=$(date +%s.%N)
    seq 1 "$REQUESTS" | xargs -P "$CONCURRENCY" -I_ \
        curl -s -o /dev/null "http://localhost:$port$path"
    t1=$(date +%s.%N)
    python3 -c "
t = float('$t1') - float('$t0')
rps = $REQUESTS / t
print(f'{rps:8.0f} req/s   ({t:.3f}s total, concurrency $CONCURRENCY)')"
}

# Setup a 1KB static file for file-serving benchmarks
STATIC_DIR=$(mktemp -d)
printf '%.0s0123456789abcdef0123456789abcdef' {1..32} > "$STATIC_DIR/bench"

echo "═══════════════════════════════════════════════════════════════"
echo "HTTP benchmark — $REQUESTS requests, concurrency $CONCURRENCY"
echo "═══════════════════════════════════════════════════════════════"
echo

# Helper to start + wait for port ready. Adds pid to SPAWNED_PIDS so
# the EXIT trap kills it even if the script dies unexpectedly.
start_server() {
    local cmd="$1" port="$2"
    eval "$cmd" > /dev/null 2>&1 &
    local pid=$!
    SPAWNED_PIDS+=("$pid")
    for _ in $(seq 1 20); do
        if curl -s -o /dev/null -w "%{http_code}" "http://localhost:$port/" 2>/dev/null | grep -q 200; then
            echo "$pid"
            return 0
        fi
        sleep 0.1
    done
    kill "$pid" 2>/dev/null
    return 1
}

stop_server() {
    local pid="$1"
    # SIGTERM first; if the process is blocked in accept() it may not
    # exit cleanly, so force-kill after a short grace period.
    kill "$pid" 2>/dev/null
    for _ in 1 2 3 4 5; do
        kill -0 "$pid" 2>/dev/null || break
        sleep 0.1
    done
    kill -9 "$pid" 2>/dev/null
    wait "$pid" 2>/dev/null
    sleep 0.2
}

# ── lumbda Python ──
PID=$(start_server "$PY examples/http-server.lsp" 8080)
bench_one "lumbda Python  (/bench, 1 KB)" 8080 /bench
stop_server "$PID"

# ── lumbda C ──
PID=$(start_server "$C examples/http-server.lsp" 8080)
bench_one "lumbda C       (/bench, 1 KB)" 8080 /bench
stop_server "$PID"

# ── lumbda asm (bump-only) ──
PID=$(start_server "$ASM < examples/http-server.lsp" 8080)
bench_one "lumbda asm     (/bench, 1 KB)" 8080 /bench
stop_server "$PID"

# ── lumbda asm-gc (naive mark-sweep + meta-GC build) ──
if [ -x "$ASM_GC" ]; then
    PID=$(start_server "$ASM_GC < examples/http-server.lsp" 8080)
    bench_one "lumbda asm-gc  (/bench, 1 KB)" 8080 /bench
    stop_server "$PID"
fi

# ── Python http.server (stdlib) ──
(cd "$STATIC_DIR" && python3 -m http.server 8080 > /dev/null 2>&1) &
PID=$!
SPAWNED_PIDS+=("$PID")
sleep 1
bench_one "python3 -m http.server (1 KB file)" 8080 /bench
stop_server "$PID"

# ── busybox httpd ──
busybox httpd -f -p 127.0.0.1:8080 -h "$STATIC_DIR" > /dev/null 2>&1 &
PID=$!
SPAWNED_PIDS+=("$PID")
sleep 0.5
bench_one "busybox httpd         (1 KB file)" 8080 /bench
stop_server "$PID"

echo
echo "═══════════════════════════════════════════════════════════════"
echo "Binary sizes"
echo "═══════════════════════════════════════════════════════════════"
printf "  lumbda asm:    %s\n" "$(du -b asm/lumbda | cut -f1) bytes"
[ -x asm/lumbda-gc ] && \
printf "  lumbda asm-gc: %s\n" "$(du -b asm/lumbda-gc | cut -f1) bytes (GC_NAIVE build)"
printf "  lumbda C:      %s\n" "$(du -b c/lumbda | cut -f1) bytes"
printf "  busybox httpd:      %s\n" "$(du -b /usr/bin/busybox | cut -f1) bytes (multi-call)"
printf "  python3:            %s bytes (interpreter binary)\n" "$(du -bL $(which python3) | cut -f1)"