# All times are in seconds unless specified otherwise.
[Daemon]
+# The dispatcher can customize the start and stop procedure for
+# cloud nodes. For example, the SLURM dispatcher drains nodes
+# through SLURM before shutting them down.
+#dispatcher = slurm
+
+# Node Manager will ensure that there are at least this many nodes
+# running at all times.
+min_nodes = 0
+
# Node Manager will not start any compute nodes when at least this
# many are running.
max_nodes = 8
# information is too outdated.
poll_stale_after = 600
+# If Node Manager boots a cloud node, and it does not pair with an Arvados
+# node before this long, assume that there was a cloud bootstrap failure and
+# shut it down. Note that normal shutdown windows apply (see the Cloud
+# section), so this should be shorter than the first shutdown window value.
+boot_fail_after = 1800
+
# "Node stale time" affects two related behaviors.
# 1. If a compute node has been running for at least this long, but it
# isn't paired with an Arvados node, do not shut it down, but leave it alone.
# willing to use. The Node Manager should boot the cheapest size(s) that
# can run jobs in the queue (N.B.: defining more than one size has not been
# tested yet).
-# Each size section MUST define the number of cores it has. You may also
-# want to define the number of mebibytes of scratch space for Crunch jobs.
-# You can also override Amazon's provided data fields by setting the same
-# names here.
+# Each size section MUST define the number of cores are available in this
+# size class (since libcloud does not provide any consistent API for exposing
+# this setting).
+# You may also want to define the amount of scratch space (expressed
+# in GB) for Crunch jobs. You can also override Amazon's provided
+# data fields by setting the same names here.
cores = 2
-scratch = 100
\ No newline at end of file
+scratch = 100