browsertrix/chart/app-templates/crawler.yaml
Ilya Kreymer 61239a40ed
include workflow config in QA runs + different browser instances for QA (#1829)
Currently, the workflow crawl settings were not being included at all in
QA runs.
This mounts the crawl workflow config, as well as QA configmap, into QA
run crawls, allowing for page limits from crawl workflow to be applied
to QA runs.

It also allows a different number of browser instances to be used for QA
runs, as QA runs might work better with less browsers, (eg. 2 instead of
4). This can be set with `qa_browser_instances` in helm chart.

Default qa browser workers to 1 if unset (for now, for best results)

Fixes #1828
2024-05-29 13:32:25 -07:00

210 lines
4.5 KiB
YAML

# -------
# PVC
# -------
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: {{ name }}
namespace: {{ namespace }}
labels:
crawl: {{ id }}
role: crawler
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: {{ crawler_storage }}
{% if volume_storage_class %}
storageClassName: {{ volume_storage_class }}
{% endif %}
# -------
# CRAWLER
# -------
{% if not do_restart %}
---
apiVersion: v1
kind: Pod
metadata:
name: {{ name }}
namespace: {{ namespace }}
labels:
crawl: {{ id }}
role: crawler
spec:
hostname: {{ name }}
subdomain: crawler
{% if priorityClassName %}
priorityClassName: {{ priorityClassName }}
{% endif %}
restartPolicy: OnFailure
securityContext:
runAsNonRoot: true
runAsUser: {{ crawler_uid}}
runAsGroup: {{ crawler_gid}}
fsGroup: {{ crawler_fsgroup }}
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
terminationGracePeriodSeconds: {{ termination_grace_secs }}
volumes:
- name: crawl-config
configMap:
name: crawl-config-{{ cid }}
{% if qa_source_crawl_id %}
- name: qa-config
configMap:
name: qa-replay-{{ qa_source_crawl_id }}
{% endif %}
- name: crawl-data
persistentVolumeClaim:
claimName: {{ name }}
affinity:
{% if crawler_node_type %}
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
- matchExpressions:
- key: nodeType
operator: In
values:
- "{{ crawler_node_type }}"
{% endif %}
podAffinity:
preferredDuringSchedulingIgnoredDuringExecution:
- weight: 10
podAffinityTerm:
topologyKey: "kubernetes.io/hostname"
labelSelector:
matchExpressions:
- key: crawl
operator: In
values:
- {{ id }}
tolerations:
- key: nodeType
operator: Equal
value: crawling
effect: NoSchedule
- key: node.kubernetes.io/not-ready
operator: Exists
tolerationSeconds: 300
effect: NoExecute
- key: node.kubernetes.io/unreachable
operator: Exists
effect: NoExecute
tolerationSeconds: 300
containers:
- name: crawler
image: {{ crawler_image }}
imagePullPolicy: {{ crawler_image_pull_policy }}
command:
- {{ "crawl" if not qa_source_crawl_id else "qa" }}
- --config
- /tmp/crawl-config.json
- --workers
- "{{ workers }}"
- --redisStoreUrl
- {{ redis_url }}
{% if qa_source_crawl_id %}
- --qaSource
- /tmp/qa-config.json
{% elif profile_filename %}
- --profile
- "@{{ profile_filename }}"
{% endif %}
volumeMounts:
- name: crawl-config
mountPath: /tmp/crawl-config.json
subPath: crawl-config.json
readOnly: True
{% if qa_source_crawl_id %}
- name: qa-config
mountPath: /tmp/qa-config.json
subPath: qa-config.json
readOnly: True
{% endif %}
- name: crawl-data
mountPath: /crawls
envFrom:
- configMapRef:
name: shared-crawler-config
- secretRef:
name: {{ storage_secret }}
{% if signing_secret %}
- secretRef:
name: {{ signing_secret }}
{% endif %}
env:
- name: HOME
value: /crawls/home
- name: CRAWL_ID
value: "{{ id }}"
- name: WEBHOOK_URL
value: "{{ redis_url }}/crawls-done"
- name: STORE_PATH
value: "{{ storage_path }}"
- name: STORE_FILENAME
value: "{{ storage_filename }}"
- name: STORE_USER
value: "{{ userid }}"
- name: WARC_PREFIX
value: "{{ warc_prefix }}"
{% if crawler_socks_proxy_host %}
- name: SOCKS_HOST
value: "{{ crawler_socks_proxy_host }}"
{% if crawler_socks_proxy_port %}
- name: SOCKS_PORT
value: "{{ crawler_socks_proxy_port }}"
{% endif %}
{% endif %}
resources:
limits:
memory: "{{ memory_limit }}"
requests:
cpu: "{{ cpu }}"
memory: "{{ memory }}"
{% if crawler_liveness_port and crawler_liveness_port != '0' %}
livenessProbe:
httpGet:
path: /healthz
port: {{ crawler_liveness_port }}
initialDelaySeconds: 15
periodSeconds: 120
failureThreshold: 3
{% endif %}
{% endif %}