#!/usr/bin/env python3 """ Push a collected Hive query log manifest to Monte Carlo — push only. Reads a JSON manifest produced by ``collect_query_logs.py``, builds QueryLogEntry objects, and calls ``send_query_logs`` in batches. The manifest is updated in-place with ``resource_uuid`` and ``invocation_id`` after a successful push. Can be run standalone via CLI or imported (use the ``push()`` function). Substitution points ------------------- - MCD_INGEST_ID (env) / --key-id (CLI) : Monte Carlo ingestion key ID - MCD_INGEST_TOKEN (env) / --key-token (CLI) : Monte Carlo ingestion key token - MCD_RESOURCE_UUID (env) / --resource-uuid (CLI) : MC resource UUID (optional for query logs) Prerequisites ------------- pip install pycarlo python-dateutil python-dotenv Usage ----- python push_query_logs.py \\ --key-id \\ --key-token \\ --resource-uuid \\ --input-file query_logs_output.json """ import argparse import json import os from concurrent.futures import ThreadPoolExecutor, as_completed from datetime import datetime, timezone from dateutil.parser import isoparse from pycarlo.core import Client, Session from pycarlo.features.ingestion import IngestionService from pycarlo.features.ingestion.models import QueryLogEntry # ← SUBSTITUTE: default batch size for query log push (events per request) # Query logs include full SQL text — keep batches small to stay under the 1 MB # compressed payload limit. 50 entries can trigger 413 on active warehouses. DEFAULT_BATCH_SIZE = 100 # ← SUBSTITUTE: HTTP timeout for MC ingestion requests (seconds) DEFAULT_TIMEOUT_SECONDS = 120 # Truncate query_text longer than this to prevent 413 errors. # Some SQL statements (e.g., generated by BI tools) can be 100KB+ and blow up # compressed payloads even at small batch sizes. _MAX_QUERY_TEXT_LEN = 10_000 def _build_events(manifest: dict) -> list[QueryLogEntry]: """ Rebuild QueryLogEntry objects from a collected query log manifest. ISO timestamp strings are parsed back to datetime. Entries are deduplicated by query_id. """ seen: set[str] = set() events = [] truncated = 0 for q in manifest.get("queries", []): qid = q.get("query_id") if qid and qid in seen: continue if qid: seen.add(qid) start_time = isoparse(q["start_time"]) if not start_time.tzinfo: start_time = start_time.replace(tzinfo=timezone.utc) end_time = isoparse(q["end_time"]) if not end_time.tzinfo: end_time = end_time.replace(tzinfo=timezone.utc) query_text = q.get("query") or "" # Truncate very long SQL to prevent 413 Request Too Large if len(query_text) > _MAX_QUERY_TEXT_LEN: query_text = query_text[:_MAX_QUERY_TEXT_LEN] + "... [TRUNCATED]" truncated += 1 events.append( QueryLogEntry( start_time=start_time, end_time=end_time, query_text=query_text, query_id=qid or None, user=q.get("user", "hadoop"), # ← SUBSTITUTE: set the user appropriate for your cluster returned_rows=q.get("returned_rows"), ) ) if truncated: print(f" Truncated {truncated} query text(s) exceeding {_MAX_QUERY_TEXT_LEN} chars") return events def push( manifest: dict, key_id: str, key_token: str, resource_uuid: str | None = None, batch_size: int = DEFAULT_BATCH_SIZE, timeout_seconds: int = DEFAULT_TIMEOUT_SECONDS, ) -> str | None: """ Push collected query logs to Monte Carlo and update the manifest in-place. Events are sent in batches of ``batch_size`` (default 100) to avoid oversized payloads. Args: manifest: Dict loaded from a ``collect_query_logs.py`` output file. key_id: MC ingestion key ID. key_token: MC ingestion key token. resource_uuid: Optional MC resource UUID. batch_size: Events per POST request (default 100). timeout_seconds: HTTP timeout per request (default 120). Returns: The last invocation ID string if returned by MC, otherwise None. """ log_type = manifest.get("log_type", "hive-s3") events = _build_events(manifest) n = len(events) print(f"Loaded {n} query log entry/entries from manifest") if not events: print("No query log entries to push.") manifest["log_type"] = log_type if resource_uuid is not None: manifest["resource_uuid"] = resource_uuid manifest["invocation_id"] = None return None # Split into batches batch_list = [] for i in range(0, n, batch_size): batch_list.append(events[i : i + batch_size]) total_batches = len(batch_list) def _push_batch(batch: list, batch_num: int) -> str | None: """Push a single batch using a dedicated Session (thread-safe).""" client = Client(session=Session(mcd_id=key_id, mcd_token=key_token, scope="Ingestion")) service = IngestionService(mc_client=client) result = service.send_query_logs( resource_uuid=resource_uuid, log_type=log_type, events=batch, ) invocation_id = service.extract_invocation_id(result) print(f" Pushed batch {batch_num}/{total_batches} ({len(batch)} entries) — invocation_id={invocation_id}") return invocation_id # Push batches in parallel (each thread gets its own pycarlo Session) max_workers = min(4, total_batches) invocation_ids: list[str | None] = [None] * total_batches with ThreadPoolExecutor(max_workers=max_workers) as pool: futures = { pool.submit(_push_batch, batch, i + 1): i for i, batch in enumerate(batch_list) } for future in as_completed(futures): idx = futures[future] try: invocation_ids[idx] = future.result() except Exception as exc: print(f" ERROR pushing batch {idx + 1}: {exc}") raise print(f" All {total_batches} batches pushed ({max_workers} workers)") manifest["log_type"] = log_type if resource_uuid is not None: manifest["resource_uuid"] = resource_uuid manifest["invocation_id"] = invocation_ids[-1] if invocation_ids else None if len([i for i in invocation_ids if i]) > 1: manifest["invocation_ids"] = invocation_ids elif "invocation_ids" in manifest: del manifest["invocation_ids"] return manifest.get("invocation_id") def main() -> None: parser = argparse.ArgumentParser( description="Push a collected Hive query log manifest to Monte Carlo", ) parser.add_argument( "--key-id", default=os.environ.get("MCD_INGEST_ID"), help="Monte Carlo ingestion key ID (env: MCD_INGEST_ID)", ) parser.add_argument( "--key-token", default=os.environ.get("MCD_INGEST_TOKEN"), help="Monte Carlo ingestion key token (env: MCD_INGEST_TOKEN)", ) parser.add_argument( "--resource-uuid", default=os.environ.get("MCD_RESOURCE_UUID"), help="Monte Carlo resource UUID (optional for query logs) (env: MCD_RESOURCE_UUID)", ) parser.add_argument( "--input-file", default="query_logs_output.json", help="Path to the JSON manifest written by collect_query_logs.py (default: query_logs_output.json)", ) parser.add_argument( "--batch-size", type=int, default=DEFAULT_BATCH_SIZE, metavar="N", help=f"Max events per POST (default: {DEFAULT_BATCH_SIZE})", ) parser.add_argument( "--timeout", type=int, default=DEFAULT_TIMEOUT_SECONDS, metavar="SEC", help=f"HTTP timeout per request in seconds (default: {DEFAULT_TIMEOUT_SECONDS})", ) args = parser.parse_args() if not args.key_id or not args.key_token: parser.error("--key-id and --key-token are required (or set MCD_INGEST_ID / MCD_INGEST_TOKEN)") with open(args.input_file) as fh: manifest = json.load(fh) push( manifest=manifest, key_id=args.key_id, key_token=args.key_token, resource_uuid=args.resource_uuid, batch_size=args.batch_size, timeout_seconds=args.timeout, ) with open(args.input_file, "w") as fh: json.dump(manifest, fh, indent=2) print(f"Manifest updated in-place: {args.input_file}") print("Done.") if __name__ == "__main__": main()