13804: Update comments for comments for "consecutive_idle_count"

Arvados-DCO-1.1-Signed-off-by: Peter Amstutz <pamstutz@veritasgenetics.com>

diff --git a/doc/install/install-nodemanager.html.textile.liquid b/doc/install/install-nodemanager.html.textile.liquid
index 09c6b5cb1b8e0b84069a958902278f5d125c6457..6e2be8bc033fd205f895d6ec998e05e639a0e9fc 100644 (file)
--- a/doc/install/install-nodemanager.html.textile.liquid
+++ b/doc/install/install-nodemanager.html.textile.liquid
@@ -113,6 +113,15 @@ boot_fail_after = 1800
 # an Arvados node that hasn't been updated for this long.
 node_stale_after = 14400
 
+# Number of consecutive times a node must report as "idle" before it
+# will be considered eligible for shutdown.  Node status is checked
+# each poll period, and node can go idle at any point during a poll
+# period (meaning a node could be reported as idle that has only been
+# idle for 1 second).  With a 60 second poll period, three consecutive
+# status updates of "idle" suggests the node has been idle at least
+# 121 seconds.
+consecutive_idle_count = 3
+
 # Scaling factor to be applied to nodes' available RAM size. Usually there's a
 # variable discrepancy between the advertised RAM value on cloud nodes and the
 # actual amount available.
@@ -282,6 +291,15 @@ poll_stale_after = 600
 # an Arvados node that hasn't been updated for this long.
 node_stale_after = 14400
 
+# Number of consecutive times a node must report as "idle" before it
+# will be considered eligible for shutdown.  Node status is checked
+# each poll period, and node can go idle at any point during a poll
+# period (meaning a node could be reported as idle that has only been
+# idle for 1 second).  With a 60 second poll period, three consecutive
+# status updates of "idle" suggests the node has been idle at least
+# 121 seconds.
+consecutive_idle_count = 3
+
 # Scaling factor to be applied to nodes' available RAM size. Usually there's a
 # variable discrepancy between the advertised RAM value on cloud nodes and the
 # actual amount available.
@@ -470,6 +488,15 @@ boot_fail_after = 1800
 # an Arvados node that hasn't been updated for this long.
 node_stale_after = 14400
 
+# Number of consecutive times a node must report as "idle" before it
+# will be considered eligible for shutdown.  Node status is checked
+# each poll period, and node can go idle at any point during a poll
+# period (meaning a node could be reported as idle that has only been
+# idle for 1 second).  With a 60 second poll period, three consecutive
+# status updates of "idle" suggests the node has been idle at least
+# 121 seconds.
+consecutive_idle_count = 3
+
 # Scaling factor to be applied to nodes' available RAM size. Usually there's a
 # variable discrepancy between the advertised RAM value on cloud nodes and the
 # actual amount available.

diff --git a/services/nodemanager/arvnodeman/computenode/dispatch/__init__.py b/services/nodemanager/arvnodeman/computenode/dispatch/__init__.py
index 30ca16805d50690f923c2d6223d17d25341e7365..bdc179587cc803f7ec7f4c3f0b939d4f019b2d69 100644 (file)
--- a/services/nodemanager/arvnodeman/computenode/dispatch/__init__.py
+++ b/services/nodemanager/arvnodeman/computenode/dispatch/__init__.py
@@ -458,7 +458,7 @@ class ComputeNodeMonitorActor(config.actor_class):
             boot_grace = "boot exceeded"
 
         if crunch_worker_state == "idle":
-            # Must report as "idle" at least two consecutive times
+            # Must report as "idle" at least "consecutive_idle_count" times
             if self.consecutive_idle < self.consecutive_idle_count:
                 idle_grace = 'idle wait'
             else:

diff --git a/services/nodemanager/doc/azure.example.cfg b/services/nodemanager/doc/azure.example.cfg
index efd2445175589f761165aa7ff5746be7ab4b6f44..8ba68018d5840466698cf8a0cf19546887bf143b 100644 (file)
--- a/services/nodemanager/doc/azure.example.cfg
+++ b/services/nodemanager/doc/azure.example.cfg
@@ -65,6 +65,15 @@ boot_fail_after = 1800
 # an Arvados node that hasn't been updated for this long.
 node_stale_after = 14400
 
+# Number of consecutive times a node must report as "idle" before it
+# will be considered eligible for shutdown.  Node status is checked
+# each poll period, and node can go idle at any point during a poll
+# period (meaning a node could be reported as idle that has only been
+# idle for 1 second).  With a 60 second poll period, three consecutive
+# status updates of "idle" suggests the node has been idle at least
+# 121 seconds.
+consecutive_idle_count = 3
+
 # Scaling factor to be applied to nodes' available RAM size. Usually there's a
 # variable discrepancy between the advertised RAM value on cloud nodes and the
 # actual amount available.
@@ -74,6 +83,7 @@ node_mem_scaling = 0.95
 # File path for Certificate Authorities
 certs_file = /etc/ssl/certs/ca-certificates.crt
 
+
 [Logging]
 # Log file path
 file = /var/log/arvados/node-manager.log

diff --git a/services/nodemanager/doc/ec2.example.cfg b/services/nodemanager/doc/ec2.example.cfg
index a1fa2dc32c21a6676f740ba8321fa4175c143733..2b6152a9a03b884c5078695e8cc3ea4532e91d2a 100644 (file)
--- a/services/nodemanager/doc/ec2.example.cfg
+++ b/services/nodemanager/doc/ec2.example.cfg
@@ -65,6 +65,15 @@ boot_fail_after = 1800
 # an Arvados node that hasn't been updated for this long.
 node_stale_after = 14400
 
+# Number of consecutive times a node must report as "idle" before it
+# will be considered eligible for shutdown.  Node status is checked
+# each poll period, and node can go idle at any point during a poll
+# period (meaning a node could be reported as idle that has only been
+# idle for 1 second).  With a 60 second poll period, three consecutive
+# status updates of "idle" suggests the node has been idle at least
+# 121 seconds.
+consecutive_idle_count = 3
+
 # Scaling factor to be applied to nodes' available RAM size. Usually there's a
 # variable discrepancy between the advertised RAM value on cloud nodes and the
 # actual amount available.

diff --git a/services/nodemanager/doc/gce.example.cfg b/services/nodemanager/doc/gce.example.cfg
index 8a244a444487052cd1543d9135448703741ca3e0..acd3fd1e3e6ab6a36720670f439cc2061f2c574f 100644 (file)
--- a/services/nodemanager/doc/gce.example.cfg
+++ b/services/nodemanager/doc/gce.example.cfg
@@ -54,6 +54,15 @@ poll_stale_after = 600
 # an Arvados node that hasn't been updated for this long.
 node_stale_after = 14400
 
+# Number of consecutive times a node must report as "idle" before it
+# will be considered eligible for shutdown.  Node status is checked
+# each poll period, and node can go idle at any point during a poll
+# period (meaning a node could be reported as idle that has only been
+# idle for 1 second).  With a 60 second poll period, three consecutive
+# status updates of "idle" suggests the node has been idle at least
+# 121 seconds.
+consecutive_idle_count = 3
+
 # Scaling factor to be applied to nodes' available RAM size. Usually there's a
 # variable discrepancy between the advertised RAM value on cloud nodes and the
 # actual amount available.