1. tasks
1.1 main.yml
- name: 创建 {{ HARBOR_PATH }} 目录file:path: "{{ HARBOR_PATH }}"state: directorymode: 0755# 注册变量 result，如果 {{ HARBOR_PATH }} 目录下存在 registry 目录说明已经安装过 harbor，则不进行安装
- name: 注册变量 resultcommand: ls {{ HARBOR_PATH }}register: result- name: 已安装提示debug:msg: "发现harbor安装已存在，为避免冲突，不进行重新安装，仅尝试启动harbor"when: '"registry" in result.stdout'- block:- name: 生成 harbor 随机密码shell: < /dev/urandom tr -dc 0-9A-Za-z-_ | head -c 16register: harbor_password_gen- debug: var="harbor_password_gen.stdout"- name: 生成 DB 随机密码shell: < /dev/urandom tr -dc 0-9A-Za-z-_ | head -c 16register: db_password_gen- debug: var="db_password_gen.stdout"- name: 下发 docker compose 二进制文件copy: src={{ base_dir }}/bin/docker-compose dest={{ bin_dir }}/docker-compose mode=0755- name: 下发 harbor 离线安装包copy:src: "{{ base_dir }}/down/harbor-offline-installer-{{ HARBOR_VER }}.tgz"dest: "{{ HARBOR_PATH }}/harbor-offline-installer-{{ HARBOR_VER }}.tgz"- name: 解压 harbor 离线安装包shell: "cd {{ HARBOR_PATH }} && tar zxf harbor-offline-installer-{{ HARBOR_VER }}.tgz"- name: 导入 harbor 所需 docker imagesshell: "{{ bin_dir }}/docker load -i {{ HARBOR_PATH }}/harbor/harbor.{{ HARBOR_VER }}.tar.gz"- block:- name: 创建 harbor 证书请求template: src=harbor-csr.json.j2 dest={{ cluster_dir }}/ssl/harbor-csr.jsonconnection: local- name: 创建 harbor 证书和私钥shell: "cd {{ cluster_dir }}/ssl && {{ base_dir }}/bin/cfssl gencert \-ca=ca.pem \-ca-key=ca-key.pem \-config=ca-config.json \-profile=kubernetes harbor-csr.json|{{ base_dir }}/bin/cfssljson -bare harbor"connection: local- name: 分发自签名证书copy: src={{ cluster_dir }}/ssl/{{ item }} dest={{ ca_dir }}/{{ item }}with_items:- ca.pem- harbor.pem- harbor-key.pemwhen: 'HARBOR_SELF_SIGNED_CERT|bool'- name: 推送非自签名证书（需提前在{{ base_dir }}/down/ 下载好证书）copy: src={{ base_dir }}/down/{{ item }} dest={{ ca_dir }}/{{ item }}with_items:- harbor.pem- harbor-key.pemwhen: 'not HARBOR_SELF_SIGNED_CERT|bool'- name: 准备 harbor 配置文件template: src=harbor-{{ HARBOR_VER_MAIN }}.yml.j2 dest={{ HARBOR_PATH }}/harbor/harbor.yml- set_fact: HARBOR_INST_OPS="{{ HARBOR_INST_OPS }} --with-trivy"when: "HARBOR_WITH_TRIVY|bool"- debug: var="HARBOR_INST_OPS"- name: 安装 harborshell: "cd {{ HARBOR_PATH }}/harbor && \export PATH={{ bin_dir }}:$PATH && \./install.sh {{ HARBOR_INST_OPS }} >> /tmp/harbor-`date +'%Y%m%d%H%M%S'`.log 2>&1"when: '"registry" not in result.stdout'- name: 创建 harbor 的 systemd unit 文件template: src=harbor.service.j2 dest=/etc/systemd/system/harbor.service- name: 开机启用 harbor 服务shell: systemctl enable harborignore_errors: true- name: 开启 harbor 服务shell: systemctl daemon-reload && systemctl restart harbor- name: 轮询等待 harbor 服务启动shell: systemctl is-active harbor.serviceregister: harbor_statusuntil: '"active" in harbor_status.stdout'retries: 10delay: 3- name: 检测 harbor 端口是否正常wait_for:host: "{{ inventory_hostname }}"port: "{{ HARBOR_TLS_PORT }}"timeout: 60run_once: true
1.2 templates
1.2.1 harbor-csr.json.j2
{"CN": "harbor","hosts": ["127.0.0.1","{{ inventory_hostname }}","{{ HARBOR_DOMAIN }}"],"key": {"algo": "rsa","size": 2048},"names": [{"C": "CN","ST": "HangZhou","L": "XS","O": "k8s","OU": "System"}]
}
1.2.2 harbor-v2.12.yml.j2
# Configuration file of Harbor# The IP address or hostname to access admin UI and registry service.
# DO NOT use localhost or 127.0.0.1, because Harbor needs to be accessed by external clients.
hostname: {{ HARBOR_HOSTNAME }}# http related config
http:# port for http, default is 80. If https enabled, this port will redirect to https portport: 80# https related config
https:# https port for harbor, default is 443port: {{ HARBOR_TLS_PORT }}# The path of cert and key files for nginxcertificate: {{ ca_dir }}/harbor.pemprivate_key: {{ ca_dir }}/harbor-key.pem# enable strong ssl ciphers (default: false)# strong_ssl_ciphers: false# # Harbor will set ipv4 enabled only by default if this block is not configured
# # Otherwise, please uncomment this block to configure your own ip_family stacks
# ip_family:
# # ipv6Enabled set to true if ipv6 is enabled in docker network, currently it affected the nginx related component
# ipv6:
# enabled: false
# # ipv4Enabled set to true by default, currently it affected the nginx related component
# ipv4:
# enabled: true# # Uncomment following will enable tls communication between all harbor components
# internal_tls:
# # set enabled to true means internal tls is enabled
# enabled: true
# # put your cert and key files on dir
# dir: /etc/harbor/tls/internal# Uncomment external_url if you want to enable external proxy
# And when it enabled the hostname will no longer used
# external_url: https://reg.mydomain.com:8433# The initial password of Harbor admin
# It only works in first time to install harbor
# Remember Change the admin password from UI after launching Harbor.
harbor_admin_password: {{ harbor_password_gen.stdout }}# Harbor DB configuration
database:# The password for the root user of Harbor DB. Change this before any production use.password: {{ db_password_gen.stdout }}# The maximum number of connections in the idle connection pool. If it <=0, no idle connections are retained.max_idle_conns: 100# The maximum number of open connections to the database. If it <= 0, then there is no limit on the number of open connections.# Note: the default number of connections is 1024 for postgres of harbor.max_open_conns: 900# The maximum amount of time a connection may be reused. Expired connections may be closed lazily before reuse. If it <= 0, connections are not closed due to a connection's age.# The value is a duration string. A duration string is a possibly signed sequence of decimal numbers, each with optional fraction and a unit suffix, such as "300ms", "-1.5h" or "2h45m". Valid time units are "ns", "us" (or "µs"), "ms", "s", "m", "h".conn_max_lifetime: 5m# The maximum amount of time a connection may be idle. Expired connections may be closed lazily before reuse. If it <= 0, connections are not closed due to a connection's idle time.# The value is a duration string. A duration string is a possibly signed sequence of decimal numbers, each with optional fraction and a unit suffix, such as "300ms", "-1.5h" or "2h45m". Valid time units are "ns", "us" (or "µs"), "ms", "s", "m", "h".conn_max_idle_time: 0# The default data volume
data_volume: {{ HARBOR_PATH }}# Harbor Storage settings by default is using /data dir on local filesystem
# Uncomment storage_service setting If you want to using external storage
# storage_service:
# # ca_bundle is the path to the custom root ca certificate, which will be injected into the truststore
# # of registry's containers. This is usually needed when the user hosts a internal storage with self signed certificate.
# ca_bundle:# # storage backend, default is filesystem, options include filesystem, azure, gcs, s3, swift and oss
# # for more info about this configuration please refer https://distribution.github.io/distribution/about/configuration/
# # and https://distribution.github.io/distribution/storage-drivers/
# filesystem:
# maxthreads: 100
# # set disable to true when you want to disable registry redirect
# redirect:
# disable: false# Trivy configuration
#
# Trivy DB contains vulnerability information from NVD, Red Hat, and many other upstream vulnerability databases.
# It is downloaded by Trivy from the GitHub release page https://github.com/aquasecurity/trivy-db/releases and cached
# in the local file system. In addition, the database contains the update timestamp so Trivy can detect whether it
# should download a newer version from the Internet or use the cached one. Currently, the database is updated every
# 12 hours and published as a new release to GitHub.
trivy:# ignoreUnfixed The flag to display only fixed vulnerabilitiesignore_unfixed: false# skipUpdate The flag to enable or disable Trivy DB downloads from GitHub## You might want to enable this flag in test or CI/CD environments to avoid GitHub rate limiting issues.# If the flag is enabled you have to download the `trivy-offline.tar.gz` archive manually, extract `trivy.db` and# `metadata.json` files and mount them in the `/home/scanner/.cache/trivy/db` path.skip_update: false## skipJavaDBUpdate If the flag is enabled you have to manually download the `trivy-java.db` file and mount it in the# `/home/scanner/.cache/trivy/java-db/trivy-java.db` pathskip_java_db_update: false## The offline_scan option prevents Trivy from sending API requests to identify dependencies.# Scanning JAR files and pom.xml may require Internet access for better detection, but this option tries to avoid it.# For example, the offline mode will not try to resolve transitive dependencies in pom.xml when the dependency doesn't# exist in the local repositories. It means a number of detected vulnerabilities might be fewer in offline mode.# It would work if all the dependencies are in local.# This option doesn't affect DB download. You need to specify "skip-update" as well as "offline-scan" in an air-gapped environment.offline_scan: false## Comma-separated list of what security issues to detect. Possible values are `vuln`, `config` and `secret`. Defaults to `vuln`.security_check: vuln## insecure The flag to skip verifying registry certificateinsecure: false## timeout The duration to wait for scan completion.# There is upper bound of 30 minutes defined in scan job. So if this `timeout` is larger than 30m0s, it will also timeout at 30m0s.timeout: 5m0s## github_token The GitHub access token to download Trivy DB## Anonymous downloads from GitHub are subject to the limit of 60 requests per hour. Normally such rate limit is enough# for production operations. If, for any reason, it's not enough, you could increase the rate limit to 5000# requests per hour by specifying the GitHub access token. For more details on GitHub rate limiting please consult# https://docs.github.com/rest/overview/resources-in-the-rest-api#rate-limiting## You can create a GitHub token by following the instructions in# https://help.github.com/en/github/authenticating-to-github/creating-a-personal-access-token-for-the-command-line## github_token: xxxjobservice:# Maximum number of job workers in job servicemax_job_workers: 10# The jobLoggers backend name, only support "STD_OUTPUT", "FILE" and/or "DB"job_loggers:- STD_OUTPUT- FILE# - DB# The jobLogger sweeper duration (ignored if `jobLogger` is `stdout`)logger_sweeper_duration: 1 #daysnotification:# Maximum retry count for webhook jobwebhook_job_max_retry: 3# HTTP client timeout for webhook jobwebhook_job_http_client_timeout: 3 #seconds# Log configurations
log:# options are debug, info, warning, error, fatallevel: info# configs for logs in local storagelocal:# Log files are rotated log_rotate_count times before being removed. If count is 0, old versions are removed rather than rotated.rotate_count: 50# Log files are rotated only if they grow bigger than log_rotate_size bytes. If size is followed by k, the size is assumed to be in kilobytes.# If the M is used, the size is in megabytes, and if G is used, the size is in gigabytes. So size 100, size 100k, size 100M and size 100G# are all valid.rotate_size: 200M# The directory on your host that store loglocation: /var/log/harbor# Uncomment following lines to enable external syslog endpoint.# external_endpoint:# # protocol used to transmit log to external endpoint, options is tcp or udp# protocol: tcp# # The host of external endpoint# host: localhost# # Port of external endpoint# port: 5140#This attribute is for migrator to detect the version of the .cfg file, DO NOT MODIFY!
_version: 2.12.0# Uncomment external_database if using external database.
# external_database:
# harbor:
# host: harbor_db_host
# port: harbor_db_port
# db_name: harbor_db_name
# username: harbor_db_username
# password: harbor_db_password
# ssl_mode: disable
# max_idle_conns: 2
# max_open_conns: 0# Uncomment redis if need to customize redis db
# redis:
# # db_index 0 is for core, it's unchangeable
# # registry_db_index: 1
# # jobservice_db_index: 2
# # trivy_db_index: 5
# # it's optional, the db for harbor business misc, by default is 0, uncomment it if you want to change it.
# # harbor_db_index: 6
# # it's optional, the db for harbor cache layer, by default is 0, uncomment it if you want to change it.
# # cache_layer_db_index: 7# Uncomment external_redis if using external Redis server
# external_redis:
# # support redis, redis+sentinel
# # host for redis: <host_redis>:<port_redis>
# # host for redis+sentinel:
# # <host_sentinel1>:<port_sentinel1>,<host_sentinel2>:<port_sentinel2>,<host_sentinel3>:<port_sentinel3>
# host: redis:6379
# password:
# # Redis AUTH command was extended in Redis 6, it is possible to use it in the two-arguments AUTH <username> <password> form.
# # there's a known issue when using external redis username ref:https://github.com/goharbor/harbor/issues/18892
# # if you care about the image pull/push performance, please refer to this https://github.com/goharbor/harbor/wiki/Harbor-FAQs#external-redis-username-password-usage
# # username:
# # sentinel_master_set must be set to support redis+sentinel
# #sentinel_master_set:
# # db_index 0 is for core, it's unchangeable
# registry_db_index: 1
# jobservice_db_index: 2
# trivy_db_index: 5
# idle_timeout_seconds: 30
# # it's optional, the db for harbor business misc, by default is 0, uncomment it if you want to change it.
# # harbor_db_index: 6
# # it's optional, the db for harbor cache layer, by default is 0, uncomment it if you want to change it.
# # cache_layer_db_index: 7# Uncomment uaa for trusting the certificate of uaa instance that is hosted via self-signed cert.
# uaa:
# ca_file: /path/to/ca# Global proxy
# Config http proxy for components, e.g. http://my.proxy.com:3128
# Components doesn't need to connect to each others via http proxy.
# Remove component from `components` array if want disable proxy
# for it. If you want use proxy for replication, MUST enable proxy
# for core and jobservice, and set `http_proxy` and `https_proxy`.
# Add domain to the `no_proxy` field, when you want disable proxy
# for some special registry.
proxy:http_proxy:https_proxy:no_proxy:components:- core- jobservice- trivy# metric:
# enabled: false
# port: 9090
# path: /metrics# Trace related config
# only can enable one trace provider(jaeger or otel) at the same time,
# and when using jaeger as provider, can only enable it with agent mode or collector mode.
# if using jaeger collector mode, uncomment endpoint and uncomment username, password if needed
# if using jaeger agetn mode uncomment agent_host and agent_port
# trace:
# enabled: true
# # set sample_rate to 1 if you wanna sampling 100% of trace data; set 0.5 if you wanna sampling 50% of trace data, and so forth
# sample_rate: 1
# # # namespace used to differentiate different harbor services
# # namespace:
# # # attributes is a key value dict contains user defined attributes used to initialize trace provider
# # attributes:
# # application: harbor
# # # jaeger should be 1.26 or newer.
# # jaeger:
# # endpoint: http://hostname:14268/api/traces
# # username:
# # password:
# # agent_host: hostname
# # # export trace data by jaeger.thrift in compact mode
# # agent_port: 6831
# # otel:
# # endpoint: hostname:4318
# # url_path: /v1/traces
# # compression: false
# # insecure: true
# # # timeout is in seconds
# # timeout: 10# Enable purge _upload directories
upload_purging:enabled: true# remove files in _upload directories which exist for a period of time, default is one week.age: 168h# the interval of the purge operationsinterval: 24hdryrun: false# Cache layer configurations
# If this feature enabled, harbor will cache the resource
# `project/project_metadata/repository/artifact/manifest` in the redis
# which can especially help to improve the performance of high concurrent
# manifest pulling.
# NOTICE
# If you are deploying Harbor in HA mode, make sure that all the harbor
# instances have the same behaviour, all with caching enabled or disabled,
# otherwise it can lead to potential data inconsistency.
cache:# not enabled by defaultenabled: false# keep cache for one day by defaultexpire_hours: 24# Harbor core configurations
# Uncomment to enable the following harbor core related configuration items.
# core:
# # The provider for updating project quota(usage), there are 2 options, redis or db,
# # by default is implemented by db but you can switch the updation via redis which
# # can improve the performance of high concurrent pushing to the same project,
# # and reduce the database connections spike and occupies.
# # By redis will bring up some delay for quota usage updation for display, so only
# # suggest switch provider to redis if you were ran into the db connections spike around
# # the scenario of high concurrent pushing to same project, no improvement for other scenes.
# quota_update_provider: redis # Or db
1.2.3 harbor.service.j2
[Unit]
Description=Harbor
After=docker.service systemd-networkd.service systemd-resolved.service
Requires=docker.service
Documentation=http://github.com/vmware/harbor[Service]
Type=simple
Restart=on-failure
RestartSec=30
ExecStart={{ bin_dir }}/docker-compose -f {{ HARBOR_PATH }}/harbor/docker-compose.yml up
ExecStop={{ bin_dir }}/docker-compose -f {{ HARBOR_PATH }}/harbor/docker-compose.yml down[Install]
WantedBy=multi-user.target
3. vars
3.1 main.yml
# harbor 主版本号
# 从完整版本号提取出主版本号
HARBOR_VER_MAIN: "{{ HARBOR_VER.split('.')[0] }}.{{ HARBOR_VER.split('.')[1] }}"# HARBOR_HOSTNAME 值设置
HARBOR_HOSTNAME: "{% if HARBOR_DOMAIN != '' %}{{ HARBOR_DOMAIN }}{% else %}{{ inventory_hostname }}{% endif %}"# harobr 默认安装选项
HARBOR_INST_OPS: ""
