Merge branch 'master' into 4523-search-index

[arvados.git] / services / nodemanager / doc / ec2.example.cfg

diff --git a/services/nodemanager/doc/ec2.example.cfg b/services/nodemanager/doc/ec2.example.cfg
index a56e69eea68f45f8edffcbd8b7e25091aec3cbb2..024ed2b59b3089676b520aec5212caa1caa470ba 100644 (file)
--- a/services/nodemanager/doc/ec2.example.cfg
+++ b/services/nodemanager/doc/ec2.example.cfg
@@ -2,6 +2,15 @@
 # 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
@@ -18,6 +27,12 @@ max_poll_time = 300
 # information is too outdated.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.