18290: address review comments.

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

diff --git a/lib/config/config.default.yml b/lib/config/config.default.yml
index 5bd575b123d5aa581f95285765dbc015767aa99f..52e35d83ff76296ee9d5f14202492e02e955375d 100644 (file)
--- a/lib/config/config.default.yml
+++ b/lib/config/config.default.yml
@@ -683,7 +683,7 @@ 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
@@ -881,8 +881,8 @@ 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: ""
 
@@ -908,7 +908,7 @@ 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
 
       Logging:
@@ -1021,14 +1021,23 @@ Clusters:
           AssignNodeHostname: "compute%<slot_number>d"
 
       LSF:
-        # Additional arguments to bsub when submitting Arvados
-        # containers as LSF jobs.
+        # 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 these arguments accordingly.
-        BsubArgumentsList: ["-o", "/tmp/crunch-run.%J.out", "-e", "/tmp/crunch-run.%J.err"]
+        # 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]"]
 
         # Use sudo to switch to this user account when submitting LSF
         # jobs.
@@ -1057,7 +1066,7 @@ 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.
@@ -1091,13 +1100,25 @@ 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").