claude
14be21db15
The c=64 matrix run (job 7dbc1ede) showed plain-mode parity but a 2.2x ka latency penalty; the decisive test is a CONNS sweep, which only needs the plain cells. PLAIN_ONLY=1 skips the two causal cells; the summary already tolerates their absence.
182 lines
7.1 KiB
Bash
Executable File
182 lines
7.1 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# ka-close-matrix.sh — controlled ka/close A/B for the throughput-inversion
|
|
# chase (handoff jar item), with the forgiveness-fix box validation folded
|
|
# into the causal cells (handoff v13 PENDING, pull-forward agreed 2026-07-20).
|
|
#
|
|
# Cells, run in order on fresh ports:
|
|
# plain-ka, plain-close examples/plain_serve (no causal feature).
|
|
# Metric: wrk Requests/sec, REPS reps after a
|
|
# discarded warmup.
|
|
# causal-ka, causal-close examples/load_profile (smarm-causal). Metric:
|
|
# the sweep summary + ledger audit (forgiveness
|
|
# column, books balance); wrk is backdrop load
|
|
# whose own numbers are injection-contaminated.
|
|
#
|
|
# Controls: byte-identical wrk invocation per mode pair except the
|
|
# `Connection: close` header; server and wrk pinned to disjoint core sets
|
|
# (SMT siblings left idle by default on the 5900X); the negotiated
|
|
# connection behavior is verified via curl per cell and logged, so a
|
|
# loadgen-config asymmetry can never silently explain a result again.
|
|
#
|
|
# Knobs (env, defaults for the 5900X box):
|
|
# DUR=30 REPS=2 CONNS=64 THREADS=4 PIN=1
|
|
# SERVER_CPUS=0-7 WRK_CPUS=8-11
|
|
# CAUSAL_WRK_DUR=300 BASE_PORT=8080
|
|
# OUT=/workspace/results
|
|
# PLAIN_BIN, CAUSAL_BIN binary paths (default: target/release/examples/*)
|
|
set -euo pipefail
|
|
|
|
cd "$(dirname "$0")/.."
|
|
|
|
DUR="${DUR:-30}"
|
|
REPS="${REPS:-2}"
|
|
CONNS="${CONNS:-64}"
|
|
THREADS="${THREADS:-4}"
|
|
PIN="${PIN:-1}"
|
|
SERVER_CPUS="${SERVER_CPUS:-0-7}"
|
|
WRK_CPUS="${WRK_CPUS:-8-11}"
|
|
CAUSAL_WRK_DUR="${CAUSAL_WRK_DUR:-300}"
|
|
BASE_PORT="${BASE_PORT:-8080}"
|
|
OUT="${OUT:-/workspace/results}"
|
|
PLAIN_BIN="${PLAIN_BIN:-target/release/examples/plain_serve}"
|
|
CAUSAL_BIN="${CAUSAL_BIN:-target/release/examples/load_profile}"
|
|
|
|
mkdir -p "$OUT"
|
|
say() { echo "[$(date +%H:%M:%S)] $*" | tee -a "$OUT/matrix.log"; }
|
|
|
|
pin_server=(); pin_wrk=()
|
|
if [ "$PIN" = 1 ]; then
|
|
pin_server=(taskset -c "$SERVER_CPUS")
|
|
pin_wrk=(taskset -c "$WRK_CPUS")
|
|
fi
|
|
|
|
# ---- environment record --------------------------------------------------
|
|
{
|
|
date -u
|
|
uname -a
|
|
echo "nproc: $(nproc)"
|
|
lscpu -e 2>/dev/null || true
|
|
echo "port range: $(cat /proc/sys/net/ipv4/ip_local_port_range 2>/dev/null)"
|
|
echo "somaxconn: $(cat /proc/sys/net/core/somaxconn 2>/dev/null)"
|
|
echo "wrk: $(wrk --version 2>&1 | head -1 || true)"
|
|
echo "PIN=$PIN SERVER_CPUS=$SERVER_CPUS WRK_CPUS=$WRK_CPUS"
|
|
echo "DUR=$DUR REPS=$REPS CONNS=$CONNS THREADS=$THREADS CAUSAL_WRK_DUR=$CAUSAL_WRK_DUR"
|
|
} > "$OUT/env.txt"
|
|
say "env recorded -> env.txt"
|
|
|
|
# ---- helpers -------------------------------------------------------------
|
|
run_wrk() { # $1=mode $2=duration_s $3=port
|
|
if [ "$1" = close ]; then
|
|
"${pin_wrk[@]}" wrk -t "$THREADS" -c "$CONNS" -d "${2}s" --latency \
|
|
-H "Connection: close" "http://127.0.0.1:$3/json/7"
|
|
else
|
|
"${pin_wrk[@]}" wrk -t "$THREADS" -c "$CONNS" -d "${2}s" --latency \
|
|
"http://127.0.0.1:$3/json/7"
|
|
fi
|
|
}
|
|
|
|
wait_port() { # $1=port
|
|
for _ in $(seq 1 150); do
|
|
curl -s -o /dev/null "http://127.0.0.1:$1/json/1" && return 0
|
|
sleep 0.2
|
|
done
|
|
return 1
|
|
}
|
|
|
|
verify_mode() { # $1=mode $2=port — record what actually goes over the wire
|
|
echo "--- single request, mode=$1 ---"
|
|
if [ "$1" = close ]; then
|
|
curl -sv --http1.1 -H "Connection: close" -o /dev/null \
|
|
"http://127.0.0.1:$2/json/7" 2>&1 | grep -iE "^(> |< )(GET|HTTP|connection)" || true
|
|
else
|
|
curl -sv --http1.1 -o /dev/null "http://127.0.0.1:$2/json/7" 2>&1 \
|
|
| grep -iE "^(> |< )(GET|HTTP|connection)" || true
|
|
fi
|
|
echo "--- reuse probe (two requests, one curl) ---"
|
|
curl -sv --http1.1 -o /dev/null -o /dev/null \
|
|
"http://127.0.0.1:$2/json/1" "http://127.0.0.1:$2/json/2" 2>&1 \
|
|
| grep -icE "re-us(ed|ing)" || true
|
|
}
|
|
|
|
# ---- plain cells ---------------------------------------------------------
|
|
run_plain() { # $1=mode $2=port
|
|
local mode="$1" port="$2" d="$OUT/plain-$1"
|
|
mkdir -p "$d"
|
|
say "=== plain / $mode (port $port) ==="
|
|
URUS_PORT="$port" "${pin_server[@]}" "$PLAIN_BIN" > "$d/server.log" 2>&1 &
|
|
local spid=$!
|
|
wait_port "$port" || { say "FATAL: plain server never came up"; cat "$d/server.log"; exit 1; }
|
|
verify_mode "$mode" "$port" > "$d/mode-verify.txt" 2>&1
|
|
ss -s > "$d/ss-before.txt" 2>/dev/null || true
|
|
run_wrk "$mode" 5 "$port" > "$d/warmup.txt" 2>&1
|
|
for r in $(seq 1 "$REPS"); do
|
|
run_wrk "$mode" "$DUR" "$port" > "$d/rep$r.txt" 2>&1
|
|
grep -E "Requests/sec|Latency |requests in|Socket errors|Non-2xx" "$d/rep$r.txt" \
|
|
| sed "s/^/ [plain-$mode r$r] /" | tee -a "$OUT/matrix.log" || true
|
|
done
|
|
ss -s > "$d/ss-after.txt" 2>/dev/null || true
|
|
awk '{printf "server cpu jiffies (utime+stime): %d\n", $14+$15}' \
|
|
"/proc/$spid/stat" > "$d/server-cpu.txt" 2>/dev/null || true
|
|
kill "$spid" 2>/dev/null || true
|
|
wait "$spid" 2>/dev/null || true
|
|
}
|
|
|
|
# ---- causal cells --------------------------------------------------------
|
|
run_causal() { # $1=mode $2=port
|
|
local mode="$1" port="$2" d="$OUT/causal-$1"
|
|
mkdir -p "$d"
|
|
say "=== causal / $mode (port $port) ==="
|
|
URUS_PORT="$port" COZ_OUT="$d/profile.coz" WARMUP_MS=2000 \
|
|
"${pin_server[@]}" "$CAUSAL_BIN" > "$d/sweep.log" 2>&1 &
|
|
local spid=$!
|
|
wait_port "$port" || { say "FATAL: causal server never came up"; cat "$d/sweep.log"; exit 1; }
|
|
verify_mode "$mode" "$port" > "$d/mode-verify.txt" 2>&1
|
|
run_wrk "$mode" "$CAUSAL_WRK_DUR" "$port" > "$d/wrk-backdrop.txt" 2>&1 &
|
|
local wpid=$!
|
|
local rc=0
|
|
wait "$spid" || rc=$?
|
|
kill "$wpid" 2>/dev/null || true
|
|
wait "$wpid" 2>/dev/null || true
|
|
say "causal/$mode server exit=$rc (sweep + audit in sweep.log)"
|
|
if [ "$rc" -ne 0 ]; then say "WARNING: causal/$mode exited nonzero"; fi
|
|
}
|
|
|
|
# ---- matrix --------------------------------------------------------------
|
|
run_plain ka "$BASE_PORT"
|
|
run_plain close "$((BASE_PORT + 1))"
|
|
if [ "${PLAIN_ONLY:-0}" != 1 ]; then
|
|
run_causal ka "$((BASE_PORT + 2))"
|
|
run_causal close "$((BASE_PORT + 3))"
|
|
fi
|
|
|
|
# ---- summary -------------------------------------------------------------
|
|
say "=== SUMMARY ==="
|
|
python3 - "$OUT" <<'PY' | tee -a "$OUT/matrix.log"
|
|
import re, sys, pathlib, statistics
|
|
out = pathlib.Path(sys.argv[1])
|
|
means = {}
|
|
for mode in ("ka", "close"):
|
|
vals = []
|
|
for rep in sorted((out / f"plain-{mode}").glob("rep*.txt")):
|
|
m = re.search(r"Requests/sec:\s+([\d.]+)", rep.read_text())
|
|
if m:
|
|
vals.append(float(m.group(1)))
|
|
if vals:
|
|
means[mode] = statistics.mean(vals)
|
|
print(f"plain-{mode}: reps={[f'{v:.0f}' for v in vals]} mean={means[mode]:.0f} req/s")
|
|
if len(means) == 2:
|
|
r = means["close"] / means["ka"]
|
|
print(f"close/ka ratio: {r:.3f}", "-> INVERSION PRESENT (close beats ka)" if r > 1.05
|
|
else "-> no inversion (ka >= close)" if r < 0.95 else "-> parity")
|
|
for mode in ("ka", "close"):
|
|
log = out / f"causal-{mode}" / "sweep.log"
|
|
if log.exists():
|
|
t = log.read_text()
|
|
keep = [l for l in t.splitlines()
|
|
if re.search(r"forgiv|books|audit|balance|total responses", l, re.I)]
|
|
print(f"-- causal-{mode} audit lines --")
|
|
for l in keep[:14]:
|
|
print(" " + l)
|
|
PY
|
|
say "=== MATRIX DONE ==="
|