# ls

common common.sh docker-compose.yml harbor-offline-installer-v2.13.1.tgz harbor-offline-installer-v2.13.1.tgz.1 harbor.v2.13.1.tar.gz harbor.yml harbor.yml.tmpl install.sh LICENSE prepare

root@shitou:/home/shitou/harbor# cat harbor.yml

root@shitou:/home/shitou/harbor# cat harbor.yml
# 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.
# 👇 已修改：hostname 改为目标IP 192.168.31.19
hostname: 192.168.31.19

# http related config
http:
  # port for http, default is 80. If https enabled, this port will redirect to https port
  port: 80

# https related config
https:
  # https port for harbor, default is 443
  port: 443
  # The path of cert and key files for nginx
  # 👇 已修改：证书路径匹配你生成的 IP 证书位置
  certificate: /etc/harbor/ssl/harbor.crt
  private_key: /etc/harbor/ssl/harbor.key
  # 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: Harbor12345

# Harbor DB configuration
database:
  # The password for the user('postgres' by default) of Harbor DB. Change this before any production use.
  password: root123
  # 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: /var/harbor_data

# 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 vulnerabilities
  ignore_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` path
  skip_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 certificate
  insecure: 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: xxx

# 👇 保留原有完整的 jobservice 配置（已包含必要参数，避免 KeyError）
jobservice:
  # Maximum number of job workers in job service
  max_job_workers: 10
  # Maximum hours of task duration in job service, default 24
  max_job_duration_hours: 24
  # 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 #days

notification:
  # Maximum retry count for webhook job
  webhook_job_max_retry: 3
  # HTTP client timeout for webhook job
  webhook_job_http_client_timeout: 3 #seconds

# Log configurations
log:
  # options are debug, info, warning, error, fatal
  level: info
  # configs for logs in local storage
  local:
    # 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 log
    location: /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: 2.13.0

# 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:
#   # tls configuration for redis connection
#   # only server-authentication is supported
#   # mtls for redis connection is not supported
#   # tls connection will be disable by default
#   tlsOptions:
#     enable: false
#   # if it is a self-signed ca, please set the ca path specifically.
#     rootCA:
#   # 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 operations
  interval: 24h
  dryrun: 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 default
  enabled: false
  # keep cache for one day by default
  expire_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

、基础访问配置

yaml

hostname: 192.168.31.19

仓库对外访问地址，不能写 localhost/127.0.0.1，其他服务器、docker 客户端需要通过这个 IP 拉取推送镜像。

yaml

http:
  port: 80

• HTTP 访问端口 80；开启 HTTPS 之后，访问 80 端口会自动跳转到 443 加密端口。

yaml

https:
  port: 443
  certificate: /etc/harbor/ssl/harbor.crt
  private_key: /etc/harbor/ssl/harbor.key

• HTTPS 加密端口 443

• certificate：ssl 公钥证书路径

• private_key：ssl 私钥文件

你的仓库现在是开启 https 加密访问。

二、管理员账号密码（仅首次安装生效）

yaml

harbor_admin_password: Harbor12345

1. 只在第一次初始化安装的时候生效

2. 安装启动成功后，修改密码只能在网页后台操作，改这里不会生效

三、PostgreSQL 数据库配置（存放账号、项目、权限、镜像元数据）

yaml

database:
  password: root123
  max_idle_conns: 100
  max_open_conns: 900
  conn_max_lifetime: 5m
  conn_max_idle_time: 0

1. password：harbor 内置 postgres 数据库密码

2. max_idle_conns：数据库空闲连接最大数量

3. max_open_conns：数据库最大并发连接上限

4. conn_max_lifetime:5m：数据库连接 5 分钟之后强制销毁重建，防止僵死连接

镜像文件本身不放在数据库；数据库只存项目名称、用户、权限、镜像标签、扫描记录等元信息。

四、最重要：镜像文件存储路径（你本次还原的核心）

yaml

data_volume: /var/harbor_data

所有 docker 镜像文件、数据库原始文件、redis 缓存、任务日志全部存放在这个文件夹

也就是你备份的 /var/harbor_data.bak 就是整套仓库完整快照，还原只需要覆盖此目录。

yaml

storage_service:
  filesystem:
    maxthreads: 100

• 默认使用本地磁盘存储镜像；

• 可以改成阿里云 OSS、S3 对象存储、网盘等外置存储；

• maxthreads 读写镜像文件的并发线程数。

五、Trivy 漏洞扫描模块

yaml

trivy:
  ignore_unfixed: false
  skip_update: false
  skip_java_db_update: false
  offline_scan: false
  security_check: vuln
  insecure: false
  timeout: 5m

1. trivy = 内置漏洞扫描器，上传镜像自动扫描漏洞

2. ignore_unfixed:false：展示所有漏洞，包含还没有补丁的高危漏洞

3. skip_update:false：自动联网下载漏洞库

4. offline_scan：离线内网环境开启，不联网检测依赖包

5. timeout:5m：单次镜像扫描最长超时时间 5 分钟

六、任务服务 jobservice

yaml

jobservice:
  max_job_workers: 10
  max_job_duration_hours: 24
  job_loggers:
    - STD_OUTPUT
    - FILE
  logger_sweeper_duration: 1

1. 负责后台异步任务：镜像扫描、镜像同步、垃圾清理、web‑hook 回调

2. max_job_workers:10：最多同时运行 10 个后台任务

3. 任务日志同时输出控制台 + 本地文件

4. logger_sweeper_duration:1：每隔 1 天自动清理过期任务日志

七、消息通知 webhook

yaml

notification:
  webhook_job_max_retry: 3
  webhook_job_http_client_timeout: 3

• 镜像推送、删除、漏洞高危触发时，可以调用第三方接口回调通知

• 失败最多重试 3 次，接口超时 3 秒

八、日志配置（磁盘占用大户之一）

yaml

log:
  level: info
  local:
    rotate_count: 50
    rotate_size: 200M
    location: /var/log/harbor

1. level:info：日志等级，debug 调试、info 普通日志、warning 警告、error 报错

2. rotate_size:200M：单个日志文件到达 200M 自动分割

3. rotate_count:50：最多保留 50 个分割日志，超出自动删除旧日志

4. location：日志存放目录 /var/log/harbor

服务器磁盘爆满除了 docker 容器日志，这个目录日志也会越堆越大

九、Redis 缓存配置

yaml

redis:
  registry_db_index: 1
  jobservice_db_index: 2
  trivy_db_index: 5

Harbor 内置 Redis，分开多个数据库存储不同模块缓存：

• db0：核心业务

• db1：镜像仓库缓存

• db2：后台任务

• db5：漏洞扫描缓存

大型生产环境可以配置 external_redis 连接独立外置 redis 服务器

十、全局代理

yaml

proxy:
  http_proxy:
  https_proxy:
  no_proxy:
  components:
    - core
    - jobservice
    - trivy

给漏洞扫描、后台任务配置外网代理，用来下载漏洞库；内网环境一般不需要填写代理地址。

十一、上传垃圾自动清理

yaml

upload_purging:
  enabled: true
  age: 168h
  interval: 24h

168h = 7 天，自动清理 7 天之内没有完成上传的残缺镜像临时文件，每天执行一次。

十二、高速缓存开关

yaml

cache:
  enabled: false
  expire_hours: 24

开启之后会把热门镜像清单存入 Redis 缓存，大批量 docker 拉取镜像速度更快；单机环境默认关闭即可。