#!/usr/bin/env bash
# Resource and concurrency stress through the bridge against 9proc-demo.
# Usage: bash 9ns/test/adv_bridge_stress.sh <9ns> <9proc-demo>   (~1-2 min; part of zig build 9ns-adv)
set -u
NS=$(realpath "${1:?path to 9ns}")
PROC=$(realpath "${2:?path to 9proc-demo}")
TMP=$(mktemp -d "${TMPDIR:-/tmp}/9ns-stress.XXXXXX")
M=/mnt/9p
S=$M/scratch
FAILED=0
PASSED=0
SRVPID=
cleanup() { [ -n "$SRVPID" ] && kill "$SRVPID" 2>/dev/null; rm -rf "$TMP"; }
trap cleanup EXIT
if ! unshare -Urm true 2>/dev/null || [ ! -c /dev/fuse ]; then echo "SKIP: no user namespaces or /dev/fuse"; exit 0; fi
pass() { PASSED=$((PASSED + 1)); echo "ok   - $1"; }
fail() { FAILED=$((FAILED + 1)); echo "FAIL - $1"; shift; [ $# -gt 0 ] && printf '       %s\n' "$@"; }
expect_eq() { if [ "$2" = "$3" ]; then pass "$1"; else fail "$1" "expected: $(printf %q "$2")" "actual:   $(printf %q "$3")"; fi; }

SOCK=$TMP/i.sock
"$PROC" --unix "$SOCK" >"$TMP/srv.out" 2>&1 &
SRVPID=$!
for _ in $(seq 1 100); do [ -S "$SOCK" ] && break; sleep 0.02; done
run() { OUT=$(timeout 600 "$NS" --unix "$SOCK" --mount "$M" -- sh -c "$1" 2>"$TMP/stderr"); RC=$?; STDERR=$(cat "$TMP/stderr"); }

echo "# 100k+ 9P operations in one session; RSS must plateau"
# Each iteration: create+write+close, open+read+close, unlink, plus a failing lookup: ~15 RPCs.
run "rss() { grep VmRSS /proc/\$PPID/status | awk '{print \$2}'; }
i=0; while [ \$i -lt 8000 ]; do echo \$i > $S/s; cat $S/s > /dev/null; rm $S/s; cat $S/none 2>/dev/null; i=\$((i+1)); if [ \$i -eq 2000 ]; then rss; fi; done; rss; ls $S | wc -l"
r1=$(printf '%s\n' "$OUT" | sed -n 1p); r2=$(printf '%s\n' "$OUT" | sed -n 2p); left=$(printf '%s\n' "$OUT" | sed -n 3p)
expect_eq "scratch left clean" "0" "$left"
if [ -n "$r1" ] && [ -n "$r2" ] && [ "$r2" -le $((r1 + 4096)) ]; then pass "RSS at 2000 iterations = $r1 KiB, at 8000 = $r2 KiB"; else fail "RSS grows: $r1 -> $r2 KiB" "$STDERR"; fi
case "$STDERR" in *leak*) fail "allocator reported leaks" "$STDERR";; *) pass "no leak report from the debug allocator";; esac

echo "# eight processes hammering the mount concurrently"
run "mkdir $S/par; for p in 1 2 3 4 5 6 7 8; do (
    d=$S/par/p\$p; mkdir \$d; i=0; bad=0
    while [ \$i -lt 300 ]; do
        printf '%s-%s' \$p \$i > \$d/f\$((i % 7)); v=\$(cat \$d/f\$((i % 7))); [ \"\$v\" = \"\$p-\$i\" ] || bad=\$((bad+1))
        mkdir \$d/dd; rmdir \$d/dd; ls \$d > /dev/null; i=\$((i+1))
    done; rm -r \$d; echo \$p:\$bad ) & done; wait; ls $S/par | wc -l; rmdir $S/par"
expect_eq "all workers verified their own data" "1:0 2:0 3:0 4:0 5:0 6:0 7:0 8:0" "$(printf '%s\n' "$OUT" | grep ':' | sort | tr '\n' ' ' | sed 's/ $//')"
expect_eq "parallel tree fully removed" "0" "$(printf '%s\n' "$OUT" | grep -v ':')"

echo "# a process killed mid-read and mid-write"
run "head -c 8000000 /dev/urandom > $S/kb; (cat $S/kb > /dev/null & sleep 0.05; kill -9 \$!; wait \$!) 2>/dev/null; (cat /dev/zero > $S/kw & sleep 0.05; kill -9 \$!; wait \$!) 2>/dev/null; sha256sum < $S/kb | cut -c1-8 > /dev/null && echo readable; [ -f $S/kw ] && echo written; rm $S/kb $S/kw; ls $S | wc -l"
expect_eq "survives SIGKILL mid-read/mid-write" $'readable\nwritten\n0' "$OUT"

echo "# many open handles at once (fh counter, fid table)"
run "python3 - <<'EOF'
import os
d='$S/fh'; os.mkdir(d)
fds=[]
for i in range(1500):
    fd=os.open(f'{d}/h{i%50}', os.O_CREAT|os.O_RDWR, 0o644); os.write(fd, b'z'); fds.append(fd)
for fd in fds: os.close(fd)
for i in range(50): os.unlink(f'{d}/h{i}')
os.rmdir(d); print('ok')
EOF"
expect_eq "1500 simultaneous handles" "ok" "$OUT"

echo
echo "passed=$PASSED failed=$FAILED"
[ "$FAILED" -eq 0 ]