X-Git-Url: https://git.arvados.org/arvados.git/blobdiff_plain/e089871b753585b26f429968e865f8ae1e03b733..f608029e1aec903bc35a4748ef51e6f076dae0aa:/lib/config/config.default.yml

diff --git a/lib/config/config.default.yml b/lib/config/config.default.yml
index 64d59f2c01..3101915175 100644
--- a/lib/config/config.default.yml
+++ b/lib/config/config.default.yml
@@ -33,7 +33,7 @@ Clusters:
 
       RailsAPI:
         InternalURLs: {SAMPLE: {}}
-        ExternalURL: "-"
+        ExternalURL: ""
       Controller:
         InternalURLs: {SAMPLE: {}}
         ExternalURL: ""
@@ -42,7 +42,7 @@ Clusters:
         ExternalURL: ""
       Keepbalance:
         InternalURLs: {SAMPLE: {}}
-        ExternalURL: "-"
+        ExternalURL: ""
       GitHTTP:
         InternalURLs: {SAMPLE: {}}
         ExternalURL: ""
@@ -51,10 +51,10 @@ Clusters:
         ExternalURL: ""
       DispatchCloud:
         InternalURLs: {SAMPLE: {}}
-        ExternalURL: "-"
+        ExternalURL: ""
       DispatchLSF:
         InternalURLs: {SAMPLE: {}}
-        ExternalURL: "-"
+        ExternalURL: ""
       Keepproxy:
         InternalURLs: {SAMPLE: {}}
         ExternalURL: ""
@@ -119,7 +119,7 @@ Clusters:
             # the old URL (with trailing slash omitted) to preserve
             # rendezvous ordering.
             Rendezvous: ""
-        ExternalURL: "-"
+        ExternalURL: ""
       Composer:
         InternalURLs: {SAMPLE: {}}
         ExternalURL: ""
@@ -142,7 +142,7 @@ Clusters:
         ExternalURL: ""
       Health:
         InternalURLs: {SAMPLE: {}}
-        ExternalURL: "-"
+        ExternalURL: ""
 
     PostgreSQL:
       # max concurrent connections per arvados server daemon
@@ -234,6 +234,12 @@ Clusters:
       # Timeout on requests to internal Keep services.
       KeepServiceRequestTimeout: 15s
 
+      # Vocabulary file path, local to the node running the controller.
+      # This JSON file should contain the description of what's allowed
+      # as object's metadata. Its format is described at:
+      # https://doc.arvados.org/admin/metadata-vocabulary.html
+      VocabularyPath: ""
+
     Users:
       # Config parameters to automatically setup new users.  If enabled,
       # this users will be able to self-activate.  Enable this if you want
@@ -259,6 +265,16 @@ Clusters:
       # user agreements.  Should only be enabled for development.
       NewUsersAreActive: false
 
+      # Newly activated users (whether set up by an admin or via
+      # AutoSetupNewUsers) immediately become visible to other active
+      # users.
+      #
+      # On a multi-tenant cluster, where the intent is for users to be
+      # invisible to one another unless they have been added to the
+      # same group(s) via Workbench admin interface, change this to
+      # false.
+      ActivatedUsersAreVisibleToOthers: true
+
       # The e-mail address of the user you would like to become marked as an admin
       # user on their first login.
       AutoAdminUserWithEmail: ""
@@ -273,6 +289,7 @@ Clusters:
       AdminNotifierEmailFrom: arvados@example.com
       EmailSubjectPrefix: "[ARVADOS] "
       UserNotifierEmailFrom: arvados@example.com
+      UserNotifierEmailBcc: {}
       NewUserNotificationRecipients: {}
       NewInactiveUserNotificationRecipients: {}
 
@@ -459,6 +476,13 @@ Clusters:
       # long-running balancing operation.
       BalanceTimeout: 6h
 
+      # Maximum number of replication_confirmed /
+      # storage_classes_confirmed updates to write to the database
+      # after a rebalancing run. When many updates are needed, this
+      # spreads them over a few runs rather than applying them all at
+      # once.
+      BalanceUpdateLimit: 100000
+
       # Default lifetime for ephemeral collections: 2 weeks. This must not
       # be less than BlobSigningTTL.
       DefaultTrashLifetime: 336h
@@ -473,12 +497,12 @@ Clusters:
       # is older than the amount of seconds defined on PreserveVersionIfIdle,
       # a snapshot of the collection's previous state is created and linked to
       # the current collection.
-      CollectionVersioning: false
+      CollectionVersioning: true
 
       #   0s = auto-create a new version on every update.
       #  -1s = never auto-create new versions.
       # > 0s = auto-create a new version when older than the specified number of seconds.
-      PreserveVersionIfIdle: -1s
+      PreserveVersionIfIdle: 10s
 
       # If non-empty, allow project and collection names to contain
       # the "/" character (slash/stroke/solidus), and replace "/" with
@@ -520,10 +544,10 @@ Clusters:
       # WebDAV would have to expose XSS vulnerabilities in order to
       # handle the redirect (see discussion on Services.WebDAV).
       #
-      # This setting has no effect in the recommended configuration,
-      # where the WebDAV is configured to have a separate domain for
-      # every collection; in this case XSS protection is provided by
-      # browsers' same-origin policy.
+      # This setting has no effect in the recommended configuration, where the
+      # WebDAV service is configured to have a separate domain for every
+      # collection and XSS protection is provided by browsers' same-origin
+      # policy.
       #
       # The default setting (false) is appropriate for a multi-user site.
       TrustAllContent: false
@@ -545,9 +569,6 @@ Clusters:
         # Approximate memory limit (in bytes) for collection cache.
         MaxCollectionBytes: 100000000
 
-        # Permission cache entries.
-        MaxPermissionEntries: 1000
-
         # UUID cache entries.
         MaxUUIDEntries: 1000
 
@@ -678,7 +699,7 @@ Clusters:
         AcceptAccessTokenScope: ""
 
       PAM:
-        # (Experimental) Use PAM to authenticate users.
+        # Use PAM to authenticate users.
         Enable: false
 
         # PAM service name. PAM will apply the policy in the
@@ -876,8 +897,8 @@ Clusters:
       UsePreemptibleInstances: false
 
       # PEM encoded SSH key (RSA, DSA, or ECDSA) used by the
-      # (experimental) cloud dispatcher for executing containers on
-      # worker VMs. Begins with "-----BEGIN RSA PRIVATE KEY-----\n"
+      # cloud dispatcher for executing containers on worker VMs.
+      # Begins with "-----BEGIN RSA PRIVATE KEY-----\n"
       # and ends with "\n-----END RSA PRIVATE KEY-----\n".
       DispatchPrivateKey: ""
 
@@ -903,9 +924,45 @@ Clusters:
       # Minimum time between two attempts to run the same container
       MinRetryPeriod: 0s
 
-      # Container runtime: "docker" (default) or "singularity" (experimental)
+      # Container runtime: "docker" (default) or "singularity"
       RuntimeEngine: docker
 
+      # When running a container, run a dedicated keepstore process,
+      # using the specified number of 64 MiB memory buffers per
+      # allocated CPU core (VCPUs in the container's runtime
+      # constraints). The dedicated keepstore handles I/O for
+      # collections mounted in the container, as well as saving
+      # container logs.
+      #
+      # A zero value disables this feature.
+      #
+      # In order for this feature to be activated, no volume may use
+      # AccessViaHosts, and each volume must have Replication higher
+      # than Collections.DefaultReplication. If these requirements are
+      # not satisfied, the feature is disabled automatically
+      # regardless of the value given here.
+      #
+      # Note that when this configuration is enabled, the entire
+      # cluster configuration file, including the system root token,
+      # is copied to the worker node and held in memory for the
+      # duration of the container.
+      LocalKeepBlobBuffersPerVCPU: 1
+
+      # When running a dedicated keepstore process for a container
+      # (see LocalKeepBlobBuffersPerVCPU), write keepstore log
+      # messages to keepstore.txt in the container's log collection.
+      #
+      # These log messages can reveal some volume configuration
+      # details, error messages from the cloud storage provider, etc.,
+      # which are not otherwise visible to users.
+      #
+      # Accepted values:
+      # * "none" -- no keepstore.txt file
+      # * "all" -- all logs, including request and response lines
+      # * "errors" -- all logs except "response" logs with 2xx
+      #   response codes and "request" logs
+      LocalKeepLogsToContainerLog: none
+
       Logging:
         # When you run the db:delete_old_container_logs task, it will find
         # containers that have been finished for at least this many seconds,
@@ -1016,9 +1073,23 @@ Clusters:
           AssignNodeHostname: "compute%<slot_number>d"
 
       LSF:
-        # Additional arguments to bsub when submitting Arvados
-        # containers as LSF jobs.
-        BsubArgumentsList: []
+        # Arguments to bsub when submitting Arvados containers as LSF jobs.
+        #
+        # Template variables starting with % will be substituted as follows:
+        #
+        # %U uuid
+        # %C number of VCPUs
+        # %M memory in MB
+        # %T tmp in MB
+        #
+        # Use %% to express a literal %. The %%J in the default will be changed
+        # to %J, which is interpreted by bsub itself.
+        #
+        # Note that the default arguments cause LSF to write two files
+        # in /tmp on the compute node each time an Arvados container
+        # runs. Ensure you have something in place to delete old files
+        # from /tmp, or adjust the "-o" and "-e" arguments accordingly.
+        BsubArgumentsList: ["-o", "/tmp/crunch-run.%%J.out", "-e", "/tmp/crunch-run.%%J.err", "-J", "%U", "-n", "%C", "-D", "%MMB", "-R", "rusage[mem=%MMB:tmp=%TMB] span[hosts=1]", "-R", "select[mem>=%MMB]", "-R", "select[tmp>=%TMB]", "-R", "select[ncpus>=%C]"]
 
         # Use sudo to switch to this user account when submitting LSF
         # jobs.
@@ -1047,7 +1118,7 @@ Clusters:
         GitInternalDir: /var/lib/arvados/internal.git
 
       CloudVMs:
-        # Enable the cloud scheduler (experimental).
+        # Enable the cloud scheduler.
         Enable: false
 
         # Name/number of port where workers' SSH services listen.
@@ -1059,7 +1130,7 @@ Clusters:
         # Shell command to execute on each worker to determine whether
         # the worker is booted and ready to run containers. It should
         # exit zero if the worker is ready.
-        BootProbeCommand: "docker ps -q"
+        BootProbeCommand: "systemctl is-system-running"
 
         # Minimum interval between consecutive probes to a single
         # worker.
@@ -1081,13 +1152,25 @@ Clusters:
 
         # Maximum create/destroy-instance operations per second (0 =
         # unlimited).
-        MaxCloudOpsPerSecond: 0
+        MaxCloudOpsPerSecond: 10
 
-        # Maximum concurrent node creation operations (0 = unlimited). This is
-        # recommended by Azure in certain scenarios (see
-        # https://docs.microsoft.com/en-us/azure/virtual-machines/linux/capture-image)
-        # and can be used with other cloud providers too, if desired.
-        MaxConcurrentInstanceCreateOps: 0
+        # Maximum concurrent instance creation operations (0 = unlimited).
+        #
+        # MaxConcurrentInstanceCreateOps limits the number of instance creation
+        # requests that can be in flight at any one time, whereas
+        # MaxCloudOpsPerSecond limits the number of create/destroy operations
+        # that can be started per second.
+        #
+        # Because the API for instance creation on Azure is synchronous, it is
+        # recommended to increase MaxConcurrentInstanceCreateOps when running
+        # on Azure. When using managed images, a value of 20 would be
+        # appropriate. When using Azure Shared Image Galeries, it could be set
+        # higher. For more information, see
+        # https://docs.microsoft.com/en-us/azure/virtual-machines/linux/capture-image
+        #
+        # MaxConcurrentInstanceCreateOps can be increased for other cloud
+        # providers too, if desired.
+        MaxConcurrentInstanceCreateOps: 1
 
         # Interval between cloud provider syncs/updates ("list all
         # instances").
@@ -1221,6 +1304,29 @@ Clusters:
         Price: 0.1
         Preemptible: false
 
+    StorageClasses:
+
+      # If you use multiple storage classes, specify them here, using
+      # the storage class name as the key (in place of "SAMPLE" in
+      # this sample entry).
+      #
+      # Further info/examples:
+      # https://doc.arvados.org/admin/storage-classes.html
+      SAMPLE:
+
+        # Priority determines the order volumes should be searched
+        # when reading data, in cases where a keepstore server has
+        # access to multiple volumes with different storage classes.
+        Priority: 0
+
+        # Default determines which storage class(es) should be used
+        # when a user/client writes data or saves a new collection
+        # without specifying storage classes.
+        #
+        # If any StorageClasses are configured, at least one of them
+        # must have Default: true.
+        Default: true
+
     Volumes:
       SAMPLE:
         # AccessViaHosts specifies which keepstore processes can read
@@ -1244,7 +1350,9 @@ Clusters:
         ReadOnly: false
         Replication: 1
         StorageClasses:
-          default: true
+          # If you have configured storage classes (see StorageClasses
+          # section above), add an entry here for each storage class
+          # satisfied by this volume.
           SAMPLE: true
         Driver: S3
         DriverParameters:
@@ -1262,6 +1370,7 @@ Clusters:
           ConnectTimeout: 1m
           ReadTimeout: 10m
           RaceWindow: 24h
+          PrefixLength: 0
           # Use aws-s3-go (v2) instead of goamz
           UseAWSS3v2Driver: false
 
@@ -1473,7 +1582,6 @@ Clusters:
       DefaultOpenIdPrefix: "https://www.google.com/accounts/o8/id"
 
       # Workbench2 configs
-      VocabularyURL: ""
       FileViewersConfigURL: ""
 
       # Idle time after which the user's session will be auto closed.