60ba9e366f
* Btrixjobs Operator - Phase 1 (#679) - add metacontroller and custom crds - add main_op entrypoint for operator * Btrix Operator Crawl Management (#767) * operator backend: - run operator api in separate container but in same pod, with WEB_CONCURRENCY=1 - operator creates statefulsets and services for CrawlJob and ProfileJob - operator: use service hook endpoint, set port in values.yaml * crawls working with CrawlJob - jobs start with 'crawljob-' prefix - update status to reflect current crawl state - set sync time to 10 seconds by default, overridable with 'operator_resync_seconds' - mark crawl as running, failed, complete when finished - store finished status when crawl is complete - support updating scale, forcing rollover, stop via patching CrawlJob - support cancel via deletion - requires hack to content-length for patching custom resources - auto-delete of CrawlJob via 'ttlSecondsAfterFinished' - also delete pvcs until autodelete supported via statefulset (k8s >1.27) - ensure filesAdded always set correctly, keep counter in redis, add to status display - optimization: attempt to reduce automerging, by reusing volumeClaimTemplates from existing children, as these may have additional props added - add add_crawl_errors_to_db() for storing crawl errors from redis '<crawl>:e' key to mongodb when crawl is finished/failed/canceled - add .status.size to display human-readable crawl size, if available (from webrecorder/browsertrix-crawler#291) - support new page size, >0.9.0 and old page size key (changed in webrecorder/browsertrix-crawler#284) * support for scheduled jobs! - add main_scheduled_job entrypoint to run scheduled jobs - add crawl_cron_job.yaml template for declaring CronJob - CronJobs moved to default namespace * operator manages ProfileJobs: - jobs start with 'profilejob-' - update expiry time by updating ProfileJob object 'expireTime' while profile is active * refactor/cleanup: - remove k8s package - merge k8sman and basecrawlmanager into crawlmanager - move templates, k8sapi, utils into root package - delete all *_job.py files - remove dt_now, ts_now from crawls, now in utils - all db operations happen in crawl/crawlconfig/org files - move shared crawl/crawlconfig/org functions that use the db to be importable directly, including get_crawl_config, add_new_crawl, inc_crawl_stats * role binding: more secure setup, don't allow crawler namespace any k8s permissions - move cronjobs to be created in default namespace - grant default namespace access to create cronjobs in default namespace - remove role binding from crawler namespace * additional tweaks to templates: - templates: split crawler and redis statefulset into separate yaml file (in case need to load one or other separately) * stats / redis optimization: - don't update stats in mongodb on every operator sync, only when crawl is finished - for api access, read stats directly from redis to get up-to-date stats - move get_page_stats() to utils, add get_redis_url() to k8sapi to unify access * Add migration for operator changes - Update configmap for crawl configs with scale > 1 or crawlTimeout > 0 and schedule exists to recreate CronJobs - add option to rerun last migration, enabled via env var and by running helm with --set=rerun_last_migration=1 * subcharts: move crawljob and profilejob crds to separate subchart, as this seems best way to guarantee proper install order with + update on upgrade with helm, add built btrix-crds-0.1.0.tgz subchart - metacontroller: use release from ghcr, add metacontroller-helm-v4.10.1.tgz subchart * backend api fixes - ensure changing scale of crawl also updates it in the db - crawlconfigs: add 'currCrawlSize' and 'lastCrawlSize' to crawlconfig api --------- Co-authored-by: D. Lee <leepro@gmail.com> Co-authored-by: Tessa Walsh <tessa@bitarchivist.net>
62 lines
1.7 KiB
Python
62 lines
1.7 KiB
Python
""" entrypoint for cron crawl job"""
|
|
|
|
import asyncio
|
|
import os
|
|
import uuid
|
|
|
|
from .k8sapi import K8sAPI
|
|
from .db import init_db
|
|
from .crawlconfigs import get_crawl_config, inc_crawl_count
|
|
from .crawls import add_new_crawl
|
|
|
|
|
|
# ============================================================================
|
|
class ScheduledJob(K8sAPI):
|
|
"""Schedulued Job APIs for starting CrawlJobs on schedule"""
|
|
|
|
def __init__(self):
|
|
super().__init__()
|
|
self.cid = os.environ["CID"]
|
|
|
|
_, mdb = init_db()
|
|
self.crawls = mdb["crawls"]
|
|
self.crawlconfigs = mdb["crawl_configs"]
|
|
|
|
async def run(self):
|
|
"""run crawl!"""
|
|
config_map = await self.core_api.read_namespaced_config_map(
|
|
name=f"crawl-config-{self.cid}", namespace=self.namespace
|
|
)
|
|
data = config_map.data
|
|
|
|
userid = data["USER_ID"]
|
|
scale = int(data.get("INITIAL_SCALE", 0))
|
|
crawl_timeout = int(data.get("CRAWL_TIMEOUT", 0))
|
|
|
|
crawlconfig = await get_crawl_config(self.crawlconfigs, uuid.UUID(self.cid))
|
|
|
|
# k8s create
|
|
crawl_id = await self.new_crawl_job(
|
|
self.cid, userid, scale, crawl_timeout, manual=False
|
|
)
|
|
|
|
# db create
|
|
await inc_crawl_count(self.crawlconfigs, crawlconfig.id)
|
|
await add_new_crawl(
|
|
self.crawls, crawl_id, crawlconfig, uuid.UUID(userid), manual=False
|
|
)
|
|
|
|
print("Crawl Created: " + crawl_id)
|
|
|
|
|
|
# ============================================================================
|
|
def main():
|
|
"""main entrypoint"""
|
|
job = ScheduledJob()
|
|
loop = asyncio.get_event_loop()
|
|
loop.run_until_complete(job.run())
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|