18113: change MaxCloudOpsPerSecond and MaxConcurrentInstanceCreateOps

[arvados.git] / lib / config / config.default.yml

diff --git a/lib/config/config.default.yml b/lib/config/config.default.yml
index eb05c22fd7bd0250647b296fab31f5cbe569e113..740d75836ac4482cca86e036e7ce1cb6a39345cc 100644 (file)
--- a/lib/config/config.default.yml
+++ b/lib/config/config.default.yml
@@ -273,6 +273,7 @@ Clusters:
       AdminNotifierEmailFrom: arvados@example.com
       EmailSubjectPrefix: "[ARVADOS] "
       UserNotifierEmailFrom: arvados@example.com
+      UserNotifierEmailBcc: {}
       NewUserNotificationRecipients: {}
       NewInactiveUserNotificationRecipients: {}
 
@@ -552,9 +553,6 @@ Clusters:
         # Approximate memory limit (in bytes) for collection cache.
         MaxCollectionBytes: 100000000
 
-        # Permission cache entries.
-        MaxPermissionEntries: 1000
-
         # UUID cache entries.
         MaxUUIDEntries: 1000
 
@@ -1025,7 +1023,12 @@ Clusters:
       LSF:
         # Additional arguments to bsub when submitting Arvados
         # containers as LSF jobs.
-        BsubArgumentsList: []
+        #
+        # 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 these arguments accordingly.
+        BsubArgumentsList: ["-o", "/tmp/crunch-run.%J.out", "-e", "/tmp/crunch-run.%J.err"]
 
         # Use sudo to switch to this user account when submitting LSF
         # jobs.
@@ -1066,7 +1069,7 @@ 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.
@@ -1088,13 +1091,25 @@ 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").
@@ -1233,6 +1248,9 @@ Clusters:
       # 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
@@ -1291,6 +1309,7 @@ Clusters:
           ConnectTimeout: 1m
           ReadTimeout: 10m
           RaceWindow: 24h
+          PrefixLength: 0
           # Use aws-s3-go (v2) instead of goamz
           UseAWSS3v2Driver: false