browsertrix/chart/app-templates/profilebrowser.yaml
Vinzenz Sinapius 01d8bdc5e6
Crawler network policy (#1727)
Limit egress traffic from crawler/profilebrowser pods to the internet
and limited internal services like dns, redis, frontend, auth-signer on certain ports

---------
Co-authored-by: Ilya Kreymer <ikreymer@gmail.com>
2024-07-03 10:55:03 -07:00

107 lines
2.4 KiB
YAML

---
apiVersion: v1
kind: Pod
metadata:
name: browser-{{ id }}
namespace: {{ namespace }}
labels:
browser: {{ id }}
role: browser
network-policy: limit-crawler-egress
spec:
hostname: browser-{{ id }}
subdomain: browser
securityContext:
runAsNonRoot: true
runAsUser: {{ crawler_uid}}
runAsGroup: {{ crawler_gid}}
fsGroup: {{ crawler_fsgroup }}
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
volumes:
- name: crawler-workdir
emptyDir:
sizeLimit: {{ profile_browser_workdir_size }}
{% if priorityClassName %}
priorityClassName: {{ priorityClassName }}
{% endif %}
restartPolicy: OnFailure
{% if crawler_node_type %}
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
- matchExpressions:
- key: nodeType
operator: In
values:
- "{{ crawler_node_type }}"
{% endif %}
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: browser
image: {{ crawler_image }}
imagePullPolicy: {{ crawler_image_pull_policy }}
command:
- create-login-profile
- --interactive
- --filename
- /tmp/profile.tar.gz
- --url
- {{ url }}
{%- if profile_filename %}
- --profile
- "@{{ profile_filename }}"
{%- endif %}
volumeMounts:
- name: crawler-workdir
mountPath: /tmp/home
envFrom:
- secretRef:
name: {{ storage_secret }}
env:
- name: HOME
value: /tmp/home
- name: STORE_PATH
value: {{ storage_path }}
- name: VNC_PASS
value: {{ vnc_password }}
{% if crawler_socks_proxy_host %}
- name: CHROME_FLAGS
value: "--proxy-server=socks5://{{ crawler_socks_proxy_host }}:{{ crawler_socks_proxy_port | default('9050') }}"
{% endif %}
resources:
limits:
memory: "{{ profile_memory }}"
requests:
cpu: "{{ profile_cpu }}"
memory: "{{ profile_memory }}"