Merge branch 'master' into 4232-slow-pipes-n-jobs

[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 0f9cacad55601b88316e7513155ab3790900559c..9b41ca14d54fc52956650649170574e90d99ae78 100644 (file)
--- a/services/nodemanager/doc/ec2.example.cfg
+++ b/services/nodemanager/doc/ec2.example.cfg
@@ -27,6 +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 # information is too outdated.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.
@@ -122,9 +128,11 @@ security_groups = idstring1, idstring2
 # 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