Files
aituner/runs/intervention-response-v2/pilot_controller.py

472 lines
15 KiB
Python

#!/usr/bin/env python3
"""Serialized, resumable controller for the 300-second phase-aware pilot."""
from __future__ import annotations
import argparse
import json
import os
import shlex
import signal
import subprocess
import sys
import time
from pathlib import Path
from typing import Any
HERE = Path(__file__).resolve().parent
PHASE6 = HERE.parent / "opprof-phase6"
sys.path.insert(0, str(PHASE6))
import opprof_phase6_controller as base # noqa: E402
SCHEMA = "intervention-response-phase-aware-pilot-state-v2"
SESSION_ESTIMATE_H20_HOURS = 1.25
SAFETY_H20_HOURS = 0.20
CLIENT_TIMEOUT_S = 450.0
def atomic_json(path: Path, payload: Any) -> None:
base.atomic_json(path, payload)
def wait_all_idle(timeout_s: float = 30.0) -> None:
deadline = time.monotonic() + timeout_s
last_error: Exception | None = None
while time.monotonic() < deadline:
try:
base.assert_all_idle()
return
except RuntimeError as error:
last_error = error
time.sleep(1.0)
raise last_error or RuntimeError("GPU idle timeout")
def configure(args: argparse.Namespace, manifest: dict[str, Any]) -> None:
base.WORKDIR = args.run_root.parent
base.RUN_ROOT = args.run_root
base.STATE = args.run_root / "controller-state.json"
base.SOURCE = args.vllm_source
base.VENV = args.venv
base.AITUNER = args.aituner_root
base.MODEL = args.model
base.CLIENT = args.client
base.GPU_LIMIT = float(manifest["budget"]["hard_cap_h20_hours"])
base.MARKER = "intervention-response-phase-aware-v2"
base.CELLS = {
f"tp4_mns{mns}": {"tp": 4, "mns": int(mns)}
for mns in manifest["engine"]["mns_endpoints"]
}
def load_state(path: Path, hard_cap: float) -> dict[str, Any]:
if path.exists():
return json.loads(path.read_text(encoding="utf-8"))
return {
"schema": SCHEMA,
"status": "initialized",
"hard_cap_h20_hours": hard_cap,
"gpu_hours_total": 0.0,
"completed_sessions": 0,
"sessions": {},
"failures": [],
"started_at": time.time(),
}
def save_state(path: Path, state: dict[str, Any]) -> None:
atomic_json(path, state)
def append_echo(run_root: Path, line: str) -> None:
run_root.mkdir(parents=True, exist_ok=True)
with (run_root / "launch-echo.log").open("a", encoding="utf-8") as target:
target.write(line + "\n")
print(line, flush=True)
def remaining_projection(session_count: int, index: int) -> float:
return (session_count - index) * SESSION_ESTIMATE_H20_HOURS + SAFETY_H20_HOURS
def start_server(
*, session: dict[str, Any], index: int, run_root: Path
) -> dict[str, Any]:
cell = f"tp4_mns{int(session['mns'])}"
gpus = (0, 1, 2, 3)
session_root = run_root / "sessions" / str(session["session"])
session_root.mkdir(parents=True, exist_ok=True)
port = 8950 + index
command = base.server_command(cell, gpus, port)
with (session_root / "commands.log").open("a", encoding="utf-8") as log:
log.write(f"SERVER {shlex.join(command)}\n")
server_log = (session_root / "server.log").open("ab", buffering=0)
environment = os.environ.copy()
environment.update(
{
"CUDA_VISIBLE_DEVICES": "0,1,2,3",
"VLLM_OPPROF_DIR": str(session_root / "opprof"),
"OPPROF_PHASE6_MARKER": base.MARKER,
"AITUNER_ROOT": str(base.AITUNER),
"HF_HUB_OFFLINE": "1",
"TRANSFORMERS_OFFLINE": "1",
"PYTHONUNBUFFERED": "1",
}
)
server = subprocess.Popen(
command,
cwd=base.SOURCE,
env=environment,
stdout=server_log,
stderr=subprocess.STDOUT,
start_new_session=True,
)
base.OWNED_PGIDS.add(server.pid)
return {
"cell": cell,
"gpus": gpus,
"port": port,
"dir": session_root,
"server": server,
"server_handle": server_log,
"spawned_at": time.time(),
"results": [],
}
def client_command(
entry: dict[str, Any],
*,
study: str,
anchor: float,
output: Path,
warmup: bool,
) -> list[str]:
config = base.CELLS[entry["cell"]]
command = [
"taskset",
"-c",
base.cpu_mask(entry["gpus"]),
str(base.VENV / "bin/python"),
str(base.CLIENT),
"warmup" if warmup else "run-anchor",
"--study",
study,
"--cell",
entry["cell"],
"--anchor",
str(anchor),
"--tp",
str(config["tp"]),
"--mns",
str(config["mns"]),
"--base-url",
f"http://127.0.0.1:{entry['port']}",
"--result-dir",
str(output),
"--disable-slo-early-stop",
]
return command
def run_client(
*,
entry: dict[str, Any],
role: str,
study: str,
selection: dict[str, Any],
output: Path,
state: dict[str, Any],
warmup: bool = False,
) -> dict[str, Any]:
command = client_command(
entry,
study=study,
anchor=float(selection["anchor"]),
output=output,
warmup=warmup,
)
with (entry["dir"] / "commands.log").open("a", encoding="utf-8") as log:
log.write(f"CLIENT role={role} {shlex.join(command)}\n")
handle = (output.parent / f"{output.name}.log").open("ab", buffering=0)
environment = os.environ.copy()
environment.update({"AITUNER_ROOT": str(base.AITUNER), "PYTHONUNBUFFERED": "1"})
process = subprocess.Popen(
command,
cwd=base.WORKDIR,
env=environment,
stdout=handle,
stderr=subprocess.STDOUT,
start_new_session=True,
)
deadline = time.monotonic() + (180.0 if warmup else CLIENT_TIMEOUT_S)
try:
while process.poll() is None:
if time.monotonic() > deadline:
raise TimeoutError(f"client timeout: {entry['cell']} {role}")
if entry["server"].poll() is not None:
raise RuntimeError(f"server exited during {entry['cell']} {role}")
base.assert_no_other_compute()
if state["gpu_hours_total"] + base.live_gpu_hours([entry]) >= base.GPU_LIMIT:
raise RuntimeError("phase-aware pilot H20-hour hard cap reached")
time.sleep(1.0)
except Exception:
try:
os.killpg(process.pid, signal.SIGTERM)
except ProcessLookupError:
pass
try:
process.wait(timeout=10.0)
except subprocess.TimeoutExpired:
try:
os.killpg(process.pid, signal.SIGKILL)
except ProcessLookupError:
pass
process.wait(timeout=10.0)
raise
finally:
handle.close()
if process.returncode:
raise RuntimeError(
f"client failed: cell={entry['cell']} role={role} rc={process.returncode}"
)
result = json.loads((output / "result.json").read_text(encoding="utf-8"))
validate_result(
result=result,
selection=selection,
role=role,
warmup=warmup,
)
entry["results"].append(
{
"anchor": float(selection["anchor"]),
"dir": str(output),
"kind": result["kind"],
}
)
return result
def validate_result(
*, result: dict[str, Any], selection: dict[str, Any], role: str, warmup: bool
) -> None:
if result.get("slo_early_stop_disabled") is not True:
raise RuntimeError(f"SLO early stop was not disabled: {role}")
if warmup:
if result["kind"] != "warmup" or int(result["selection"]["count"]) != 16:
raise RuntimeError(f"invalid warmup result: {role}")
if not all(
result["invariants"].get(key, False)
for key in ("warmup_16", "warmup_exact_16", "warmup_long")
):
raise RuntimeError(f"warmup invariant failed: {role}")
return
if bool(result["early_stopped"]):
raise RuntimeError(f"uncensored run early-stopped: {role}")
if int(result["selection"]["count"]) != int(selection["selected_count"]):
raise RuntimeError(f"selection count mismatch: {role}")
for key, manifest_key in (
("request_id_order_sha256", "request_id_order_sha256"),
("arrival_order_sha256", "arrival_order_sha256"),
("raw_length_order_sha256", "input_length_order_sha256"),
):
if result["selection"][key] != selection[manifest_key]:
raise RuntimeError(f"selection hash mismatch {key}: {role}")
if int(result["observed_count"]) != int(selection["selected_count"]):
raise RuntimeError(f"request accounting mismatch: {role}")
def execute_session(
*,
index: int,
session: dict[str, Any],
manifest: dict[str, Any],
run_root: Path,
state_path: Path,
state: dict[str, Any],
) -> None:
name = str(session["session"])
if state["sessions"].get(name, {}).get("status") == "complete":
return
projection = remaining_projection(len(manifest["sessions"]), index)
if state["gpu_hours_total"] + projection > base.GPU_LIMIT:
state["status"] = "budget_projection_stop"
state["budget_stop"] = {
"before_session": name,
"spent_h20_hours": state["gpu_hours_total"],
"remaining_projection_h20_hours": projection,
"hard_cap_h20_hours": base.GPU_LIMIT,
}
save_state(state_path, state)
raise RuntimeError(f"projected pilot cost exceeds hard cap before {name}")
replicate = str(session["replicate"])
repetition = manifest["repetitions"][replicate]
echo = (
f"PHASE_PILOT_SESSION_ECHO session={name} tp=4 mns={session['mns']} "
f"gpus=0-3 workload={manifest['source']['window_id']} duration_s=300 "
f"loads={','.join(repetition['load_order'])} disable_slo_early_stop=true "
f"spent_h20h={state['gpu_hours_total']:.6f} "
f"remaining_projection_h20h={projection:.3f} cap_h20h={base.GPU_LIMIT:.1f} "
f"manifest={run_root / 'pilot-manifest.json'}"
)
append_echo(run_root, echo)
wait_all_idle()
session_state = {
"status": "starting",
"replicate": int(replicate),
"mns": int(session["mns"]),
"started_at": time.time(),
"runs": [],
}
state["status"] = "running"
state["sessions"][name] = session_state
save_state(state_path, state)
entry = start_server(session=session, index=index, run_root=run_root)
failure: Exception | None = None
try:
base.wait_ready(entry)
high = repetition["selections"]["high"]
session_state["status"] = "warmup"
save_state(state_path, state)
run_client(
entry=entry,
role="warmup",
study=repetition["study"],
selection=high,
output=entry["dir"] / "warmup",
state=state,
warmup=True,
)
session_state["status"] = "burnin"
save_state(state_path, state)
burnin = manifest["burnin"]
burnin_result = run_client(
entry=entry,
role="burnin",
study=burnin["study"],
selection=burnin,
output=entry["dir"] / "burnin",
state=state,
)
session_state["burnin"] = {
"pass_rate": burnin_result["pass_rate"],
"feasible": burnin_result["feasible"],
"elapsed_s": burnin_result["interval"]["elapsed_s"],
}
session_state["status"] = "measured"
save_state(state_path, state)
for level in repetition["load_order"]:
selection = repetition["selections"][level]
result = run_client(
entry=entry,
role=level,
study=repetition["study"],
selection=selection,
output=entry["dir"] / level,
state=state,
)
session_state["runs"].append(
{
"level": level,
"selected_count": selection["selected_count"],
"offered_req_s_per_gpu": selection["offered_req_s_per_gpu"],
"pass_rate": result["pass_rate"],
"feasible": result["feasible"],
"elapsed_s": result["interval"]["elapsed_s"],
"early_stopped": result["early_stopped"],
}
)
save_state(state_path, state)
session_state["status"] = "stopping"
save_state(state_path, state)
except Exception as error: # noqa: BLE001
failure = error
finally:
try:
base.stop_entry(entry)
except Exception as error: # noqa: BLE001
failure = failure or error
time.sleep(2.0)
try:
wait_all_idle()
except Exception as error: # noqa: BLE001
failure = failure or error
session_hours = base.live_gpu_hours([entry])
state["gpu_hours_total"] += session_hours
session_state["gpu_hours"] = session_hours
if failure is not None:
session_state["status"] = "failed"
session_state["failure"] = repr(failure)
state["status"] = "failed"
state["failures"].append({"session": name, "failure": repr(failure)})
save_state(state_path, state)
raise failure
validation = base.validate_cell(entry)
session_state["validation"] = validation
session_state["status"] = "complete"
session_state["completed_at"] = time.time()
state["completed_sessions"] += 1
save_state(state_path, state)
def parser() -> argparse.ArgumentParser:
result = argparse.ArgumentParser()
result.add_argument("--manifest", type=Path, required=True)
result.add_argument("--run-root", type=Path, required=True)
result.add_argument("--aituner-root", type=Path, required=True)
result.add_argument("--vllm-source", type=Path, required=True)
result.add_argument("--venv", type=Path, required=True)
result.add_argument("--model", type=Path, required=True)
result.add_argument("--client", type=Path, required=True)
return result
def main() -> None:
args = parser().parse_args()
manifest = json.loads(args.manifest.read_text(encoding="utf-8"))
if manifest.get("schema") != "intervention-response-phase-aware-pilot-manifest-v2":
raise RuntimeError("unexpected phase-aware pilot manifest schema")
if manifest["status"] != "PASS":
raise RuntimeError("phase-aware pilot manifest did not pass preflight")
args.run_root.mkdir(parents=True, exist_ok=True)
copied_manifest = args.run_root / "pilot-manifest.json"
if not copied_manifest.exists():
atomic_json(copied_manifest, manifest)
configure(args, manifest)
state_path = args.run_root / "controller-state.json"
state = load_state(state_path, base.GPU_LIMIT)
state["status"] = "running"
save_state(state_path, state)
for index, session in enumerate(manifest["sessions"]):
execute_session(
index=index,
session=session,
manifest=manifest,
run_root=args.run_root,
state_path=state_path,
state=state,
)
state["status"] = "complete"
state["completed_at"] = time.time()
save_state(state_path, state)
wait_all_idle()
print(
json.dumps(
{
"status": state["status"],
"completed_sessions": state["completed_sessions"],
"gpu_hours_total": state["gpu_hours_total"],
},
sort_keys=True,
)
)
if __name__ == "__main__":
main()