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>
277 lines
6.7 KiB
YAML
277 lines
6.7 KiB
YAML
# Settings
|
|
# =========================================
|
|
name: browsertrix-cloud
|
|
|
|
# when running in the cloud, set this value to cloud-specific block storage
|
|
# keep empty to use hostPath (eg. on minikube)
|
|
volume_storage_class:
|
|
|
|
# if set, set the node selector 'nodeType' for deployment pods
|
|
# main_node_type:
|
|
|
|
# if set, set the node selector 'nodeType' to this crawling pods
|
|
# crawler_node_type:
|
|
|
|
registration_enabled: "0"
|
|
jwt_token_lifetime_minutes: 1440
|
|
|
|
# default time to run behaviors on each page (in seconds)
|
|
default_behavior_time_seconds: 300
|
|
|
|
# default time to wait for page to fully load before running behaviors (in seconds)
|
|
default_page_load_time_seconds: 120
|
|
|
|
# disk utilization threshold percentage - when used disk space passes
|
|
# this percentage of total, crawls will gracefully stop to prevent the
|
|
# disk from being filled
|
|
disk_utilization_threshold: 90
|
|
|
|
# max pages per crawl
|
|
# set to non-zero value to enforce global max pages per crawl limit
|
|
# if set, each workflow can have a lower limit, but not higher
|
|
max_pages_per_crawl: 0
|
|
|
|
# if set to "1", allow inviting same user to same org multiple times
|
|
allow_dupe_invites: "0"
|
|
|
|
# number of workers for backend api
|
|
backend_workers: 4
|
|
|
|
# number of seconds before pending invites expire - default is 7 days
|
|
invite_expire_seconds: 604800
|
|
|
|
# base url for replayweb.page
|
|
rwp_base_url: "https://replayweb.page/"
|
|
|
|
superuser:
|
|
# set this to enable a superuser admin
|
|
email: admin@example.com
|
|
|
|
# optional: if not set, automatically generated
|
|
# change or remove this
|
|
password: PASSW0RD!
|
|
|
|
# Set name for default organization created with superuser
|
|
default_org: "My Organization"
|
|
|
|
|
|
# API Image
|
|
# =========================================
|
|
backend_image: "docker.io/webrecorder/browsertrix-backend:latest"
|
|
backend_pull_policy: "Always"
|
|
|
|
backend_password_secret: "c9085f33ecce4347aa1d69339e16c499"
|
|
|
|
backend_num_replicas: 1
|
|
|
|
backend_requests_cpu: "10m"
|
|
backend_limits_cpu: "768m"
|
|
|
|
backend_requests_memory: "100Mi"
|
|
backend_limits_memory: "512Mi"
|
|
|
|
# port for operator service
|
|
opPort: 8756
|
|
|
|
job_cpu: "3m"
|
|
job_memory: "70Mi"
|
|
|
|
profile_browser_idle_seconds: 60
|
|
|
|
|
|
# Nginx Image
|
|
# =========================================
|
|
frontend_image: "docker.io/webrecorder/browsertrix-frontend:latest"
|
|
frontend_pull_policy: "Always"
|
|
|
|
frontend_requests_cpu: "3m"
|
|
frontend_limits_cpu: "10m"
|
|
|
|
frontend_requests_memory: "12Mi"
|
|
frontend_limits_memory: "20Mi"
|
|
|
|
# if set, maps nginx to a fixed port on host machine
|
|
# must be between 30000 - 32767
|
|
# use for deployments on localhost when not using ingress
|
|
# local_service_port: 30870
|
|
|
|
|
|
# MongoDB Image
|
|
# =========================================
|
|
mongo_local: true
|
|
|
|
mongo_host: "local-mongo.default"
|
|
|
|
mongo_image: "docker.io/library/mongo:6.0.5"
|
|
mongo_pull_policy: "IfNotPresent"
|
|
|
|
mongo_requests_cpu: "12m"
|
|
mongo_limits_cpu: "128m"
|
|
|
|
mongo_requests_memory: "96Mi"
|
|
mongo_limits_memory: "512Mi"
|
|
|
|
|
|
mongo_auth:
|
|
# specify either username + password (for local mongo)
|
|
username: root
|
|
password: PASSWORD!
|
|
|
|
# or full URL (for remote mongo server)
|
|
# db_url: mongodb+srv://...
|
|
|
|
|
|
# Redis Image
|
|
# =========================================
|
|
redis_local: true
|
|
|
|
redis_image: "redis"
|
|
redis_pull_policy: "IfNotPresent"
|
|
|
|
redis_url: "redis://local-redis.default:6379/1"
|
|
|
|
redis_requests_cpu: "3m"
|
|
redis_limits_cpu: "48m"
|
|
|
|
redis_requests_memory: "10Mi"
|
|
redis_limits_memory: "64Mi"
|
|
|
|
|
|
|
|
# Crawler Image
|
|
# =========================================
|
|
|
|
crawler_image: "webrecorder/browsertrix-crawler:latest"
|
|
crawler_pull_policy: "IfNotPresent"
|
|
|
|
crawler_namespace: "crawlers"
|
|
|
|
# optional: enable to use a persist volume claim for all crawls
|
|
# can be enabled to use a multi-write shared filesystem
|
|
# crawler_pv_claim: "nfs-shared-crawls"
|
|
|
|
# num retries
|
|
crawl_retries: 1000
|
|
|
|
# browsertrix-crawler args:
|
|
crawler_args: "--logging stats,behaviors,debug --generateWACZ --text --collection thecrawl --screencastPort 9037 --logErrorsToRedis --diskUtilization {{ .Values.disk_utilization_threshold | default 90 }} --waitOnDone"
|
|
|
|
crawler_browser_instances: 2
|
|
|
|
crawler_requests_cpu: "800m"
|
|
crawler_limits_cpu: "1200m"
|
|
|
|
crawler_requests_memory: "512Mi"
|
|
crawler_limits_memory: "1024Mi"
|
|
|
|
# minimum size allocated to each crawler
|
|
# should be at least double crawl session size to ensure space for WACZ
|
|
crawler_requests_storage: "22Gi"
|
|
|
|
# max size at which crawler will commit current crawl session
|
|
crawler_session_size_limit_bytes: "10000000000"
|
|
|
|
# max time in seconds after which crawler will restart, if set
|
|
crawler_session_time_limit_seconds: 18000
|
|
|
|
crawler_liveness_port: 6065
|
|
|
|
# time to wait for graceful stop
|
|
grace_period: 1000
|
|
|
|
|
|
|
|
# debug
|
|
no_delete_jobs: 0
|
|
|
|
|
|
# Local Minio Pod (optional)
|
|
# =========================================
|
|
# set to true to use a local minio image
|
|
minio_local: true
|
|
|
|
minio_scheme: "http"
|
|
minio_host: "local-minio.default:9000"
|
|
|
|
minio_image: docker.io/minio/minio:RELEASE.2022-10-24T18-35-07Z
|
|
minio_mc_image: minio/mc
|
|
minio_pull_policy: "IfNotPresent"
|
|
|
|
minio_local_bucket_name: &local_bucket_name "btrix-data"
|
|
|
|
|
|
# Storage
|
|
# =========================================
|
|
# should include the local minio bucket, if enabled, and any other available buckets for default storage
|
|
|
|
storages:
|
|
- name: "default"
|
|
access_key: "ADMIN"
|
|
secret_key: "PASSW0RD"
|
|
bucket_name: *local_bucket_name
|
|
|
|
endpoint_url: "http://local-minio.default:9000/"
|
|
|
|
# optional: if above includes a separate storage for profiles, specify here to store profiles separately from wacz files
|
|
# may be useful if, for example, the wacz files are public, while profiles should not be
|
|
# shared_storage_profile:
|
|
|
|
|
|
# Email Options
|
|
# =========================================
|
|
email:
|
|
# email sending is enabled when 'smtp_host' is set to non-empty value
|
|
#ex: smtp_host: smtp.gmail.com
|
|
smtp_host: ""
|
|
smtp_port: 587
|
|
sender_email: example@example.com
|
|
password: password
|
|
reply_to_email: example@example.com
|
|
|
|
|
|
# Deployment options
|
|
# =========================================
|
|
|
|
# Ingress (Optional)
|
|
# Optional: if 'host' is set, a publicly accessible Ingress controller is created with an SSL cert (using letsencrypt)
|
|
ingress:
|
|
#host: ""
|
|
cert_email: "test@example.com"
|
|
scheme: "http"
|
|
tls: false
|
|
|
|
ingress_class: nginx
|
|
|
|
|
|
# Signing Options
|
|
# =========================================
|
|
# optionally enable signer
|
|
signer:
|
|
enabled: false
|
|
image: webrecorder/authsign:0.5.0
|
|
# host: <set to signer domain>
|
|
# cert_email: "test@example.com
|
|
# image_pull_policy: "IfNotPresent"
|
|
# auth_token: <set to custom value>
|
|
|
|
signer_requests_cpu: "3m"
|
|
signer_limits_cpu: "32m"
|
|
|
|
signer_requests_memory: "36Mi"
|
|
signer_limits_memory: "96Mi"
|
|
|
|
|
|
# Optional: configure load balancing annotations
|
|
# service:
|
|
# annotations:
|
|
# service.beta.kubernetes.io/aws-load-balancer-internal: "true"
|
|
# helm.sh/resource-policy: keep
|
|
|
|
# Admin services (see Chart.yaml's dependencies)
|
|
# note: see `chart/examples/local-logging.yaml`
|
|
addons:
|
|
admin:
|
|
logging: false
|
|
|
|
# metacontroller:
|