Add Migration Script for Harbor 2.5 (#16346)

* add Harbor2.5 migration script

Signed-off-by: yminer <yminer@vmmware.com>

* update 2_5_0 migration harbor.yml.jinja

Signed-off-by: yminer <yminer@vmmware.com>

Co-authored-by: yminer <yminer@vmmware.com>

make/harbor.yml.tmpl

@@ -137,7 +137,7 @@ log:
   #   port: 5140
 
 #This attribute is for migrator to detect the version of the .cfg file, DO NOT MODIFY!
-_version: 2.4.0
+_version: 2.5.0
 
 # Uncomment external_database if using external database.
 # external_database:

make/photon/prepare/commands/migrate.py

@@ -10,7 +10,7 @@ from migrations import accept_versions
 @click.command()
 @click.option('-i', '--input', 'input_', required=True, help="The path of original config file")
 @click.option('-o', '--output', default='', help="the path of output config file")
-@click.option('-t', '--target', default='2.4.0', help="target version of input path")
+@click.option('-t', '--target', default='2.5.0', help="target version of input path")
 def migrate(input_, output, target):
     """
     migrate command will migrate config file style to specific version

make/photon/prepare/migrations/__init__.py

@@ -2,4 +2,4 @@ import os
 
 MIGRATION_BASE_DIR = os.path.dirname(__file__)
 
-accept_versions = {'1.9.0', '1.10.0', '2.0.0', '2.1.0', '2.2.0', '2.3.0', '2.4.0'}
+accept_versions = {'1.9.0', '1.10.0', '2.0.0', '2.1.0', '2.2.0', '2.3.0', '2.4.0', '2.5.0'}

make/photon/prepare/migrations/version_2_5_0/__init__.py

@@ -0,0 +1,20 @@
+import os
+from jinja2 import Environment, FileSystemLoader, StrictUndefined
+from utils.migration import read_conf
+
+revision = '2.5.0'
+down_revisions = ['2.4.0']
+
+def migrate(input_cfg, output_cfg):
+    current_dir = os.path.dirname(__file__)
+    tpl = Environment(
+        loader=FileSystemLoader(current_dir),
+        undefined=StrictUndefined,
+        trim_blocks=True,
+        lstrip_blocks=True
+        ).get_template('harbor.yml.jinja')
+
+    config_dict = read_conf(input_cfg)
+
+    with open(output_cfg, 'w') as f:
+        f.write(tpl.render(**config_dict))

make/photon/prepare/migrations/version_2_5_0/harbor.yml.jinja

@@ -0,0 +1,559 @@
+# 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: {{ hostname }}
+
+# http related config
+{% if http is defined %}
+http:
+  # port for http, default is 80. If https enabled, this port will redirect to https port
+  port: {{ http.port }}
+{% else %}
+# http:
+#   # port for http, default is 80. If https enabled, this port will redirect to https port
+#   port: 80
+{% endif %}
+
+{% if https is defined %}
+# https related config
+https:
+  # https port for harbor, default is 443
+  port: {{ https.port }}
+  # The path of cert and key files for nginx
+  certificate: {{ https.certificate }}
+  private_key: {{ https.private_key }}
+{% else %}
+# https related config
+# https:
+#   # https port for harbor, default is 443
+#   port: 443
+#   # The path of cert and key files for nginx
+#   certificate: /your/certificate/path
+#   private_key: /your/private/key/path
+{% endif %}
+
+{% if internal_tls is defined %}
+# Uncomment following will enable tls communication between all harbor components
+internal_tls:
+  # set enabled to true means internal tls is enabled
+  enabled: {{ internal_tls.enabled | lower }}
+  # put your cert and key files on dir
+  dir: {{ internal_tls.dir }}
+{% else %}
+# 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
+{% endif %}
+
+# Uncomment external_url if you want to enable external proxy
+# And when it enabled the hostname will no longer used
+{% if external_url is defined %}
+external_url: {{ external_url }}
+{% else %}
+# external_url: https://reg.mydomain.com:8433
+{% endif %}
+
+# 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.
+{% if harbor_admin_password is defined %}
+harbor_admin_password: {{ harbor_admin_password }}
+{% else %}
+harbor_admin_password: Harbor12345
+{% endif %}
+
+# Harbor DB configuration
+database:
+{% if database is defined %}
+  # The password for the root user of Harbor DB. Change this before any production use.
+  password: {{ database.password}}
+  # The maximum number of connections in the idle connection pool. If it <=0, no idle connections are retained.
+  max_idle_conns: {{ database.max_idle_conns }}
+  # 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: {{ database.max_open_conns }}
+{% else %}
+  # The password for the root user 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
+{% endif %}
+
+{% if data_volume is defined %}
+# The default data volume
+data_volume: {{ data_volume }}
+{% else %}
+# The default data volume
+data_volume: /data
+{% endif %}
+
+# Harbor Storage settings by default is using /data dir on local filesystem
+# Uncomment storage_service setting If you want to using external storage
+{% if storage_service is defined %}
+storage_service:
+  {% for key, value in storage_service.items() %}
+    {% if key == 'ca_bundle' %}
+#   # ca_bundle is the path to the custom root ca certificate, which will be injected into the truststore
+#   # of registry's and chart repository's containers.  This is usually needed when the user hosts a internal storage with self signed certificate.
+  ca_bundle: {{ value if value is not none else '' }}
+    {% elif key == 'redirect' %}
+#   # set disable to true when you want to disable registry redirect
+  redirect:
+    disabled: {{ value.disabled }}
+    {% else %}
+#   # storage backend, default is filesystem, options include filesystem, azure, gcs, s3, swift and oss
+#   # for more info about this configuration please refer https://docs.docker.com/registry/configuration/
+  {{ key }}:
+      {% for k, v in value.items() %}
+    {{ k }}: {{ v if v is not none else '' }}
+      {% endfor %}
+    {% endif %}
+  {% endfor %}
+{% else %}
+# 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 and chart repository'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://docs.docker.com/registry/configuration/
+#   filesystem:
+#     maxthreads: 100
+#   # set disable to true when you want to disable registry redirect
+#   redirect:
+#     disabled: false
+{% endif %}
+
+# 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.
+{% if trivy is defined %}
+trivy:
+  # ignoreUnfixed The flag to display only fixed vulnerabilities
+  {% if trivy.ignore_unfixed is defined %}
+  ignore_unfixed: {{ trivy.ignore_unfixed | lower }}
+  {% else %}
+  ignore_unfixed: false
+  {% endif %}
+  # timeout The duration to wait for scan completion
+  {% if trivy.timeout is defined %}
+  timeout: {{ trivy.timeout }}
+  {% else %}
+  timeout: 5m0s
+  {% endif %}
+  # 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.
+  {% if trivy.skip_update is defined %}
+  skip_update: {{ trivy.skip_update | lower }}
+  {% else %}
+  skip_update: false
+  {% endif %}
+  #
+  {% if trivy.offline_scan is defined %}
+  offline_scan: {{ trivy.offline_scan | lower }}
+  {% else %}
+  offline_scan: false
+  {% endif %}
+  #
+  # insecure The flag to skip verifying registry certificate
+  {% if trivy.insecure is defined %}
+  insecure: {{ trivy.insecure | lower }}
+  {% else %}
+  insecure: false
+  {% endif %}
+  # 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://developer.github.com/v3/#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
+  #
+  {% if trivy.github_token is defined %}
+  github_token: {{ trivy.github_token }}
+  {% else %}
+  # github_token: xxx
+  {% endif %}
+{% else %}
+# 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
+#   #
+#   #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
+#   #
+#   # insecure The flag to skip verifying registry certificate
+#   insecure: false
+#   # 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://developer.github.com/v3/#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
+{% endif %}
+
+jobservice:
+  # Maximum number of job workers in job service
+{% if jobservice is defined %}
+  max_job_workers: {{ jobservice.max_job_workers }}
+{% else %}
+  max_job_workers: 10
+{% endif %}
+
+notification:
+  # Maximum retry count for webhook job
+{% if notification is defined %}
+  webhook_job_max_retry: {{ notification.webhook_job_max_retry}}
+{% else %}
+  webhook_job_max_retry: 10
+{% endif %}
+
+{% if chart is defined %}
+chart:
+  # Change the value of absolute_url to enabled can enable absolute url in chart
+  absolute_url: {{ chart.absolute_url if chart.absolute_url == 'enabled' else 'disabled' }}
+{% else %}
+chart:
+  # Change the value of absolute_url to enabled can enable absolute url in chart
+  absolute_url: disabled
+{% endif %}
+
+# Log configurations
+log:
+  # options are debug, info, warning, error, fatal
+{% if log is defined %}
+  level: {{ log.level }}
+  # 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: {{ log.local.rotate_count }}
+    # 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: {{ log.local.rotate_size }}
+    # The directory on your host that store log
+    location: {{ log.local.location }}
+  {% if log.external_endpoint is defined %}
+  external_endpoint:
+    # protocol used to transmit log to external endpoint, options is tcp or udp
+    protocol: {{ log.external_endpoint.protocol }}
+    # The host of external endpoint
+    host: {{ log.external_endpoint.host }}
+    # Port of external endpoint
+    port: {{ log.external_endpoint.port }}
+  {% else %}
+    # 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
+  {% endif %}
+{% else %}
+  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
+{% endif %}
+
+
+#This attribute is for migrator to detect the version of the .cfg file, DO NOT MODIFY!
+_version: 2.5.0
+{% if external_database is defined %}
+# Uncomment external_database if using external database.
+external_database:
+  harbor:
+    host: {{ external_database.harbor.host }}
+    port: {{ external_database.harbor.port }}
+    db_name: {{ external_database.harbor.db_name }}
+    username: {{ external_database.harbor.username }}
+    password: {{ external_database.harbor.password }}
+    ssl_mode: {{ external_database.harbor.ssl_mode }}
+    max_idle_conns: {{ external_database.harbor.max_idle_conns}}
+    max_open_conns: {{ external_database.harbor.max_open_conns}}
+  notary_signer:
+    host: {{ external_database.notary_signer.host }}
+    port: {{ external_database.notary_signer.port }}
+    db_name: {{external_database.notary_signer.db_name }}
+    username: {{ external_database.notary_signer.username }}
+    password: {{ external_database.notary_signer.password }}
+    ssl_mode: {{ external_database.notary_signer.ssl_mode }}
+  notary_server:
+    host: {{ external_database.notary_server.host }}
+    port: {{ external_database.notary_server.port }}
+    db_name: {{ external_database.notary_server.db_name }}
+    username: {{ external_database.notary_server.username }}
+    password: {{ external_database.notary_server.password }}
+    ssl_mode: {{ external_database.notary_server.ssl_mode }}
+{% else %}
+# 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
+#   notary_signer:
+#     host: notary_signer_db_host
+#     port: notary_signer_db_port
+#     db_name: notary_signer_db_name
+#     username: notary_signer_db_username
+#     password: notary_signer_db_password
+#     ssl_mode: disable
+#   notary_server:
+#     host: notary_server_db_host
+#     port: notary_server_db_port
+#     db_name: notary_server_db_name
+#     username: notary_server_db_username
+#     password: notary_server_db_password
+#     ssl_mode: disable
+{% endif %}
+
+{% if external_redis is defined %}
+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: {{ external_redis.host }}
+  password: {{ external_redis.password }}
+  {% if external_redis.username is defined %}
+  username: {{ external_redis.username }}
+  {% else %}
+  # username:
+  {% endif %}
+  # 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: {{ external_redis.registry_db_index }}
+  jobservice_db_index: {{ external_redis.jobservice_db_index }}
+  chartmuseum_db_index: {{ external_redis.chartmuseum_db_index }}
+  trivy_db_index: 5
+  idle_timeout_seconds: 30
+{% else %}
+# Umcomments 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.
+#   # implicit username is "default", provide compatibility with past version of old AUTH <password> form
+#   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
+#   chartmuseum_db_index: 3
+#   trivy_db_index: 5
+#   idle_timeout_seconds: 30
+{% endif %}
+
+{% if uaa is defined %}
+# Uncomment uaa for trusting the certificate of uaa instance that is hosted via self-signed cert.
+uaa:
+  ca_file: {{ uaa.ca_file }}
+{% else %}
+# Uncomment uaa for trusting the certificate of uaa instance that is hosted via self-signed cert.
+# uaa:
+#   ca_file: /path/to/ca
+{% endif %}
+
+
+# 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.
+{% if proxy is defined %}
+proxy:
+  http_proxy: {{ proxy.http_proxy or ''}}
+  https_proxy: {{ proxy.https_proxy or ''}}
+  no_proxy: {{ proxy.no_proxy or ''}}
+  {% if proxy.components is defined %}
+  components:
+    {% for component in proxy.components %}
+      {% if component != 'clair' %}
+    - {{component}}
+      {% endif %}
+    {% endfor %}
+  {% endif %}
+{% else %}
+proxy:
+  http_proxy:
+  https_proxy:
+  no_proxy:
+  components:
+    - core
+    - jobservice
+    - trivy
+{% endif %}
+
+{% if metric is defined %}
+metric:
+  enabled: {{ metric.enabled }}
+  port: {{ metric.port }}
+  path: {{ metric.path }}
+{% else %}
+# metric:
+#   enabled: false
+#   port: 9090
+#   path: /metric
+{% endif %}
+
+# 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
+{% if trace is defined %}
+trace:
+  enabled: {{ trace.enabled | lower}}
+  sample_rate: {{ trace.sample_rate }}
+  # # namespace used to diferenciate different harbor services
+  {% if trace.namespace is defined %}
+  namespace: {{ trace.namespace }}
+  {% else %}
+  # namespace:
+  {% endif %}
+   # # attributes is a key value dict contains user defined attributes used to initialize trace provider
+  {% if trace.attributes is defined%}
+  attributes:
+    {% for name, value in trace.attributes.items() %}
+    {{name}}: {{value}}
+    {% endfor %}
+  {% else %}
+  # attributes:
+  #   application: harbor
+  {% endif %}
+  {% if trace.jaeger is defined%}
+  jaeger:
+    endpoint: {{trace.jaeger.endpoint or '' }}
+    username: {{trace.jaeger.username or ''}}
+    password: {{trace.jaeger.password or ''}}
+    agent_host: {{trace.jaeger.agent_host or ''}}
+    agent_port: {{trace.jaeger.agent_port or ''}}
+  {% else %}
+  # jaeger:
+  #   endpoint:
+  #   username:
+  #   password:
+  #   agent_host:
+  #   agent_port:
+  {% endif %}
+  {% if trace. otel is defined %}
+  otel:
+    endpoint: {{trace.otel.endpoint or '' }}
+    url_path: {{trace.otel.url_path or '' }}
+    compression: {{trace.otel.compression | lower }}
+    insecure: {{trace.otel.insecure | lower }}
+    timeout: {{trace.otel.timeout or '' }}
+  {% else %}
+  # otel:
+  #   endpoint: hostname:4318
+  #   url_path: /v1/traces
+  #   compression: false
+  #   insecure: true
+  #   timeout: 10s
+  {% endif%}
+{% else %}
+# 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 differenciate different harbor services
+#   # namespace:
+#   # # attributes is a key value dict contains user defined attributes used to initialize trace provider
+#   # attributes:
+#   #   application: harbor
+#   # jaeger:
+#   #   endpoint: http://hostname:14268/api/traces
+#   #   username:
+#   #   password:
+#   #   agent_host: hostname
+#   #   agent_port: 6832
+#   # otel:
+#   #   endpoint: hostname:4318
+#   #   url_path: /v1/traces
+#   #   compression: false
+#   #   insecure: true
+#   #   timeout: 10s
+{% endif %}
+
+# enable purge _upload directories
+{% if upload_purging is defined %}
+upload_purging:
+  enabled: {{ trace.enabled | lower}}
+  age: {{ trace.age }}
+  interval: {{ trace.interval }}
+  dryrun: {{ trace.dryrun | lower}}
+{% else %}
+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
+{% endif %}