16347: Run a dedicated keepstore process for each container.

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

diff --git a/lib/config/config.default.yml b/lib/config/config.default.yml
index 2b474ffdb0c0bdd4eed70a9499985a06c1a22c4d..429b9fe48bb02cd4447e24c5aa2f799cc4cc30fe 100644 (file)
--- a/lib/config/config.default.yml
+++ b/lib/config/config.default.yml
@@ -553,9 +553,6 @@ Clusters:
         # Approximate memory limit (in bytes) for collection cache.
         MaxCollectionBytes: 100000000
 
-        # Permission cache entries.
-        MaxPermissionEntries: 1000
-
         # UUID cache entries.
         MaxUUIDEntries: 1000
 
@@ -686,7 +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
@@ -884,8 +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: ""
 
@@ -911,9 +908,27 @@ 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.
+      #
+      # This feature has security implications. (1) Container logs
+      # will include keepstore log files, which typically reveal some
+      # volume configuration details, error messages from the cloud
+      # storage provider, etc., which are not otherwise visible to
+      # users. (2) 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: 0
+
       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,
@@ -1060,7 +1075,7 @@ 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.
@@ -1094,13 +1109,25 @@ 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").
@@ -1300,6 +1327,7 @@ Clusters:
           ConnectTimeout: 1m
           ReadTimeout: 10m
           RaceWindow: 24h
+          PrefixLength: 0
           # Use aws-s3-go (v2) instead of goamz
           UseAWSS3v2Driver: false