1 // Copyright (C) The Arvados Authors. All rights reserved.
3 // SPDX-License-Identifier: AGPL-3.0
7 var DefaultYAML = []byte(`# Copyright (C) The Arvados Authors. All rights reserved.
9 # SPDX-License-Identifier: AGPL-3.0
11 # Do not use this file for site configuration. Create
12 # /etc/arvados/config.yml instead.
14 # The order of precedence (highest to lowest):
15 # 1. Legacy component-specific config files (deprecated)
16 # 2. /etc/arvados/config.yml
17 # 3. config.default.yml
23 # Token to be included in all healthcheck requests. Disabled by default.
24 # Server expects request header of the format "Authorization: Bearer xxx"
84 # max concurrent connections per arvados server daemon
87 # All parameters here are passed to the PG client library in a connection string;
88 # see https://www.postgresql.org/docs/current/static/libpq-connect.html#LIBPQ-PARAMKEYWORDS
95 # Maximum size (in bytes) allowed for a single API request. This
96 # limit is published in the discovery document for use by clients.
97 # Note: You must separately configure the upstream web server or
98 # proxy to actually enforce the desired maximum request size on the
100 MaxRequestSize: 134217728
102 # Limit the number of bytes read from the database during an index
103 # request (by retrieving and returning fewer rows than would
104 # normally be returned in a single response).
105 # Note 1: This setting never reduces the number of returned rows to
106 # zero, no matter how big the first data row is.
107 # Note 2: Currently, this is only checked against a specific set of
108 # columns that tend to get large (collections.manifest_text,
109 # containers.mounts, workflows.definition). Other fields (e.g.,
110 # "properties" hashes) are not counted against this limit.
111 MaxIndexDatabaseRead: 134217728
113 # Maximum number of items to return when responding to a APIs that
114 # can return partial result sets using limit and offset parameters
115 # (e.g., *.index, groups.contents). If a request specifies a "limit"
116 # parameter higher than this value, this value is used instead.
117 MaxItemsPerResponse: 1000
119 # API methods to disable. Disabled methods are not listed in the
120 # discovery document, and respond 404 to all requests.
121 # Example: ["jobs.create", "pipeline_instances.create"]
124 # Interval (seconds) between asynchronous permission view updates. Any
125 # permission-updating API called with the 'async' parameter schedules a an
126 # update on the permission view in the future, if not already scheduled.
127 AsyncPermissionsUpdateInterval: 20s
129 # Maximum number of concurrent outgoing requests to make while
130 # serving a single incoming multi-cluster (federated) request.
131 MaxRequestAmplification: 4
133 # RailsSessionSecretToken is a string of alphanumeric characters
134 # used by Rails to sign session tokens. IMPORTANT: This is a
135 # site secret. It should be at least 50 characters.
136 RailsSessionSecretToken: ""
138 # Maximum wall clock time to spend handling an incoming request.
142 # Config parameters to automatically setup new users. If enabled,
143 # this users will be able to self-activate. Enable this if you want
144 # to run an open instance where anyone can create an account and use
145 # the system without requiring manual approval.
147 # The params auto_setup_new_users_with_* are meaningful only when auto_setup_new_users is turned on.
148 # auto_setup_name_blacklist is a list of usernames to be blacklisted for auto setup.
149 AutoSetupNewUsers: false
150 AutoSetupNewUsersWithVmUUID: ""
151 AutoSetupNewUsersWithRepository: false
152 AutoSetupUsernameBlacklist: [arvados, git, gitolite, gitolite-admin, root, syslog]
154 # When new_users_are_active is set to true, new users will be active
155 # immediately. This skips the "self-activate" step which enforces
156 # user agreements. Should only be enabled for development.
157 NewUsersAreActive: false
159 # The e-mail address of the user you would like to become marked as an admin
160 # user on their first login.
161 # In the default configuration, authentication happens through the Arvados SSO
162 # server, which uses OAuth2 against Google's servers, so in that case this
163 # should be an address associated with a Google account.
164 AutoAdminUserWithEmail: ""
166 # If auto_admin_first_user is set to true, the first user to log in when no
167 # other admin users exist will automatically become an admin user.
168 AutoAdminFirstUser: false
170 # Email address to notify whenever a user creates a profile for the
172 UserProfileNotificationAddress: ""
173 AdminNotifierEmailFrom: arvados@example.com
174 EmailSubjectPrefix: "[ARVADOS] "
175 UserNotifierEmailFrom: arvados@example.com
176 NewUserNotificationRecipients: []
177 NewInactiveUserNotificationRecipients: []
180 # Time to keep audit logs, in seconds. (An audit log is a row added
181 # to the "logs" table in the PostgreSQL database each time an
182 # Arvados object is created, modified, or deleted.)
184 # Currently, websocket event notifications rely on audit logs, so
185 # this should not be set lower than 300 (5 minutes).
188 # Maximum number of log rows to delete in a single SQL transaction.
190 # If max_audit_log_delete_batch is 0, log entries will never be
191 # deleted by Arvados. Cleanup can be done by an external process
192 # without affecting any Arvados system processes, as long as very
193 # recent (<5 minutes old) logs are not deleted.
195 # 100000 is a reasonable batch size for most sites.
198 # Attributes to suppress in events and audit logs. Notably,
199 # specifying ["manifest_text"] here typically makes the database
200 # smaller and faster.
202 # Warning: Using any non-empty value here can have undesirable side
203 # effects for any client or component that relies on event logs.
204 # Use at your own risk.
205 UnloggedAttributes: []
209 # Logging threshold: panic, fatal, error, warn, info, debug, or
213 # Logging format: json or text
216 # Maximum characters of (JSON-encoded) query parameters to include
217 # in each request log entry. When params exceed this size, they will
218 # be JSON-encoded, truncated to this size, and logged as
220 MaxRequestLogParamsSize: 2000
223 # Allow clients to create collections by providing a manifest with
224 # unsigned data blob locators. IMPORTANT: This effectively disables
225 # access controls for data stored in Keep: a client who knows a hash
226 # can write a manifest that references the hash, pass it to
227 # collections.create (which will create a permission link), use
228 # collections.get to obtain a signature for that data locator, and
229 # use that signed locator to retrieve the data from Keep. Therefore,
230 # do not turn this on if your users expect to keep data private from
234 # blob_signing_key is a string of alphanumeric characters used to
235 # generate permission signatures for Keep locators. It must be
236 # identical to the permission key given to Keep. IMPORTANT: This is
237 # a site secret. It should be at least 50 characters.
239 # Modifying blob_signing_key will invalidate all existing
240 # signatures, which can cause programs to fail (e.g., arv-put,
241 # arv-get, and Crunch jobs). To avoid errors, rotate keys only when
242 # no such processes are running.
245 # Default replication level for collections. This is used when a
246 # collection's replication_desired attribute is nil.
247 DefaultReplication: 2
249 # Lifetime (in seconds) of blob permission signatures generated by
250 # the API server. This determines how long a client can take (after
251 # retrieving a collection record) to retrieve the collection data
252 # from Keep. If the client needs more time than that (assuming the
253 # collection still has the same content and the relevant user/token
254 # still has permission) the client can retrieve the collection again
255 # to get fresh signatures.
257 # This must be exactly equal to the -blob-signature-ttl flag used by
258 # keepstore servers. Otherwise, reading data blocks and saving
259 # collections will fail with HTTP 403 permission errors.
261 # Modifying blob_signature_ttl invalidates existing signatures; see
262 # blob_signing_key note above.
264 # The default is 2 weeks.
267 # Default lifetime for ephemeral collections: 2 weeks. This must not
268 # be less than blob_signature_ttl.
269 DefaultTrashLifetime: 336h
271 # Interval (seconds) between trash sweeps. During a trash sweep,
272 # collections are marked as trash if their trash_at time has
273 # arrived, and deleted if their delete_at time has arrived.
274 TrashSweepInterval: 60s
276 # If true, enable collection versioning.
277 # When a collection's preserve_version field is true or the current version
278 # is older than the amount of seconds defined on preserve_version_if_idle,
279 # a snapshot of the collection's previous state is created and linked to
280 # the current collection.
281 CollectionVersioning: false
283 # 0s = auto-create a new version on every update.
284 # -1s = never auto-create new versions.
285 # > 0s = auto-create a new version when older than the specified number of seconds.
286 PreserveVersionIfIdle: -1s
289 # These settings are provided by your OAuth2 provider (e.g.,
291 ProviderAppSecret: ""
295 # Git repositories must be readable by api server, or you won't be
296 # able to submit crunch jobs. To pass the test suites, put a clone
297 # of the arvados tree in {git_repositories_dir}/arvados.git or
298 # {git_repositories_dir}/arvados/.git
299 Repositories: /var/lib/arvados/git/repositories
307 # List of supported Docker Registry image formats that compute nodes
308 # are able to use. ` + "`" + `arv keep docker` + "`" + ` will error out if a user tries
309 # to store an image with an unsupported format. Use an empty array
310 # to skip the compatibility check (and display a warning message to
313 # Example for sites running docker < 1.10: ["v1"]
314 # Example for sites running docker >= 1.10: ["v2"]
315 # Example for disabling check: []
316 SupportedDockerImageFormats: ["v2"]
318 # Include details about job reuse decisions in the server log. This
319 # causes additional database queries to run, so it should not be
320 # enabled unless you expect to examine the resulting logs for
321 # troubleshooting purposes.
322 LogReuseDecisions: false
324 # Default value for keep_cache_ram of a container's runtime_constraints.
325 DefaultKeepCacheRAM: 268435456
327 # Number of times a container can be unlocked before being
328 # automatically cancelled.
329 MaxDispatchAttempts: 5
331 # Default value for container_count_max for container requests. This is the
332 # number of times Arvados will create a new container to satisfy a container
333 # request. If a container is cancelled it will retry a new container if
334 # container_count < container_count_max on any container requests associated
335 # with the cancelled container.
338 # The maximum number of compute nodes that can be in use simultaneously
339 # If this limit is reduced, any existing nodes with slot number >= new limit
340 # will not be counted against the new limit. In other words, the new limit
341 # won't be strictly enforced until those nodes with higher slot numbers
345 # Preemptible instance support (e.g. AWS Spot Instances)
346 # When true, child containers will get created with the preemptible
347 # scheduling parameter parameter set.
348 UsePreemptibleInstances: false
350 # PEM encoded SSH key (RSA, DSA, or ECDSA) used by the
351 # (experimental) cloud dispatcher for executing containers on
352 # worker VMs. Begins with "-----BEGIN RSA PRIVATE KEY-----\n"
353 # and ends with "\n-----END RSA PRIVATE KEY-----\n".
354 DispatchPrivateKey: none
356 # Maximum time to wait for workers to come up before abandoning
357 # stale locks from a previous dispatch process.
361 # When you run the db:delete_old_container_logs task, it will find
362 # containers that have been finished for at least this many seconds,
363 # and delete their stdout, stderr, arv-mount, crunch-run, and
364 # crunchstat logs from the logs table.
367 # These two settings control how frequently log events are flushed to the
368 # database. Log lines are buffered until either crunch_log_bytes_per_event
369 # has been reached or crunch_log_seconds_between_events has elapsed since
371 LogBytesPerEvent: 4096
372 LogSecondsBetweenEvents: 1
374 # The sample period for throttling logs.
375 LogThrottlePeriod: 60s
377 # Maximum number of bytes that job can log over crunch_log_throttle_period
378 # before being silenced until the end of the period.
379 LogThrottleBytes: 65536
381 # Maximum number of lines that job can log over crunch_log_throttle_period
382 # before being silenced until the end of the period.
383 LogThrottleLines: 1024
385 # Maximum bytes that may be logged by a single job. Log bytes that are
386 # silenced by throttling are not counted against this total.
387 LimitLogBytesPerJob: 67108864
389 LogPartialLineThrottlePeriod: 5s
391 # Container logs are written to Keep and saved in a
392 # collection, which is updated periodically while the
393 # container runs. This value sets the interval between
394 # collection updates.
397 # The log collection is also updated when the specified amount of
398 # log data (given in bytes) is produced in less than one update
404 # Path to dns server configuration directory
405 # (e.g. /etc/unbound.d/conf.d). If false, do not write any config
406 # files or touch restart.txt (see below).
409 # Template file for the dns server host snippets. See
410 # unbound.template in this directory for an example. If false, do
411 # not write any config files.
412 DNSServerConfTemplate: ""
414 # String to write to {dns_server_conf_dir}/restart.txt (with a
415 # trailing newline) after updating local data. If false, do not
416 # open or write the restart.txt file.
417 DNSServerReloadCommand: ""
419 # Command to run after each DNS update. Template variables will be
420 # substituted; see the "unbound" example below. If false, do not run
422 DNSServerUpdateCommand: ""
424 ComputeNodeDomain: ""
425 ComputeNodeNameservers:
428 # Hostname to assign to a compute node when it sends a "ping" and the
429 # hostname in its Node record is nil.
430 # During bootstrapping, the "ping" script is expected to notice the
431 # hostname given in the ping response, and update its unix hostname
433 # If false, leave the hostname alone (this is appropriate if your compute
434 # nodes' hostnames are already assigned by some other mechanism).
436 # One way or another, the hostnames of your node records should agree
437 # with your DNS records and your /etc/slurm-llnl/slurm.conf files.
439 # Example for compute0000, compute0001, ....:
440 # assign_node_hostname: compute%<slot_number>04d
441 # (See http://ruby-doc.org/core-2.2.2/Kernel.html#method-i-format for more.)
442 AssignNodeHostname: "compute%<slot_number>d"
445 # Enable the legacy Jobs API. This value must be a string.
446 # 'auto' -- (default) enable the Jobs API only if it has been used before
447 # (i.e., there are job records in the database)
448 # 'true' -- enable the Jobs API despite lack of existing records.
449 # 'false' -- disable the Jobs API despite presence of existing records.
452 # Git repositories must be readable by api server, or you won't be
453 # able to submit crunch jobs. To pass the test suites, put a clone
454 # of the arvados tree in {git_repositories_dir}/arvados.git or
455 # {git_repositories_dir}/arvados/.git
456 GitInternalDir: /var/lib/arvados/internal.git
458 # Docker image to be used when none found in runtime_constraints of a job
459 DefaultDockerImage: ""
461 # none or slurm_immediate
462 CrunchJobWrapper: none
464 # username, or false = do not set uid when running jobs.
465 CrunchJobUser: crunch
467 # The web service must be able to create/write this file, and
468 # crunch-job must be able to stat() it.
469 CrunchRefreshTrigger: /tmp/crunch_refresh_trigger
471 # Control job reuse behavior when two completed jobs match the
472 # search criteria and have different outputs.
474 # If true, in case of a conflict, reuse the earliest job (this is
475 # similar to container reuse behavior).
477 # If false, in case of a conflict, do not reuse any completed job,
478 # but do reuse an already-running job if available (this is the
479 # original job reuse behavior, and is still the default).
480 ReuseJobIfOutputsDiffer: false
483 # Enable the cloud scheduler (experimental).
486 # Name/number of port where workers' SSH services listen.
489 # Interval between queue polls.
492 # Shell command to execute on each worker to determine whether
493 # the worker is booted and ready to run containers. It should
494 # exit zero if the worker is ready.
495 BootProbeCommand: "docker ps"
497 # Minimum interval between consecutive probes to a single
501 # Maximum probes per second, across all workers in a pool.
502 MaxProbesPerSecond: 10
504 # Time before repeating SIGTERM when killing a container.
507 # Time to give up on SIGTERM and write off the worker.
510 # Maximum create/destroy-instance operations per second (0 =
512 MaxCloudOpsPerSecond: 0
514 # Interval between cloud provider syncs/updates ("list all
518 # Time to leave an idle worker running (in case new containers
519 # appear in the queue that it can run) before shutting it
523 # Time to wait for a new worker to boot (i.e., pass
524 # BootProbeCommand) before giving up and shutting it down.
527 # Maximum time a worker can stay alive with no successful
528 # probes before being automatically shut down.
531 # Time after shutting down a worker to retry the
532 # shutdown/destroy operation.
535 # Worker VM image ID.
538 # Tags to add on all resources (VMs, NICs, disks) created by
539 # the container dispatcher. (Arvados's own tags --
540 # InstanceType, IdleBehavior, and InstanceSecret -- will also
545 # Prefix for predefined tags used by Arvados (InstanceSetID,
546 # InstanceType, InstanceSecret, IdleBehavior). With the
547 # default value "Arvados", tags are "ArvadosInstanceSetID",
548 # "ArvadosInstanceSecret", etc.
550 # This should only be changed while no cloud resources are in
551 # use and the cloud dispatcher is not running. Otherwise,
552 # VMs/resources that were added using the old tag prefix will
553 # need to be detected and cleaned up manually.
554 TagKeyPrefix: Arvados
556 # Cloud driver: "azure" (Microsoft Azure) or "ec2" (Amazon AWS).
559 # Cloud-specific driver parameters.
566 # (ec2) Instance configuration.
572 AdminUsername: debian
574 # (azure) Credentials.
580 # (azure) Instance configuration.
581 CloudEnvironment: AzurePublicCloud
588 DeleteDanglingResourcesAfter: 20s
589 AdminUsername: arvados
593 # Use the instance type name as the key (in place of "SAMPLE" in
594 # this sample entry).
596 # Cloud provider's instance type. Defaults to the configured type name.
600 IncludedScratch: 16GB
608 SendUserSetupNotificationEmail: ""
609 IssueReporterEmailFrom: ""
610 IssueReporterEmailTo: ""
611 SupportEmailAddress: ""
621 # API endpoint host or host:port; default is {id}.arvadosapi.com
622 Host: sample.arvadosapi.com
624 # Perform a proxy request when a local client requests an
625 # object belonging to this remote.
628 # Default "https". Can be set to "http" for testing.
631 # Disable TLS verify. Can be set to true for testing.
634 # When users present tokens issued by this remote cluster, and
635 # their accounts are active on the remote cluster, activate
636 # them on this cluster too.
642 ActivationContactLink: mailto:info@arvados.org
643 ArvadosDocsite: https://doc.arvados.org
644 ArvadosPublicDataDocURL: https://playground.arvados.org/projects/public
645 ShowUserAgreementInline: false
648 RepositoryCache: /var/www/arvados-workbench/current/tmp/git
649 UserProfileFormFields:
653 FormFieldDescription: ""
655 UserProfileFormMessage: 'Welcome to Arvados. All <span style="color:red">required fields</span> must be completed before you can proceed.'
656 ApplicationMimetypesWithViewIcon:
672 LogViewerMaxBytes: 1M
673 EnablePublicProjectsPage: true
674 EnableGettingStartedPopup: false
675 APIResponseCompression: true
676 APIClientConnectTimeout: 2m
677 APIClientReceiveTimeout: 5m
678 RunningJobLogRecordsToFetch: 2000
679 ShowRecentCollectionsOnDashboard: true
680 ShowUserNotifications: true
681 MultiSiteSearch: false
683 SiteName: Arvados Workbench
687 FileViewersConfigURL: ""