diff --git a/doc/openstack-ops/ch_arch_compute_nodes.xml b/doc/openstack-ops/ch_arch_compute_nodes.xml
index dcbef262..52599901 100644
--- a/doc/openstack-ops/ch_arch_compute_nodes.xml
+++ b/doc/openstack-ops/ch_arch_compute_nodes.xml
@@ -568,6 +568,12 @@
     the instances reaches 72 GB (such as nine instances, in the case where
     each instance has 8 GB of RAM).</para>
 
+    <note>
+     <para>Regardless of the overcommit ratio, an instance can not be placed
+           on any physical node with fewer raw (pre-overcommit) resources than
+           the instance flavor requires.</para>
+    </note>
+
     <para>You must select the appropriate CPU and RAM allocation ratio for
     your particular use case.</para>
   </section>
diff --git a/doc/openstack-ops/ch_arch_scaling.xml b/doc/openstack-ops/ch_arch_scaling.xml
index 47295ac2..4497d494 100644
--- a/doc/openstack-ops/ch_arch_scaling.xml
+++ b/doc/openstack-ops/ch_arch_scaling.xml
@@ -186,6 +186,12 @@
       </listitem>
     </itemizedlist>
 
+    <note>
+     <para>Regardless of the overcommit ratio, an instance can not be placed
+           on any physical node with fewer raw (pre-overcommit) resources than
+           instance flavor requires.</para>
+    </note>
+
     <para>However, you need more than the core count alone to estimate the
     load that the API services, database servers, and queue servers are likely
     to encounter. You must also consider the usage patterns of your
diff --git a/doc/ops-guide/source/arch_compute_nodes.rst b/doc/ops-guide/source/arch_compute_nodes.rst
index f1575e75..3494da2a 100644
--- a/doc/ops-guide/source/arch_compute_nodes.rst
+++ b/doc/ops-guide/source/arch_compute_nodes.rst
@@ -296,6 +296,11 @@ allocates instances to that node until the sum of the RAM associated
 with the instances reaches 72 GB (such as nine instances, in the case
 where each instance has 8 GB of RAM).
 
+.. note::
+   Regardless of the overcommit ratio, an instance can not be placed
+   on any physical node with fewer raw (pre-overcommit) resources than
+   the instance flavor requires.
+
 You must select the appropriate CPU and RAM allocation ratio for your
 particular use case.
 
diff --git a/doc/ops-guide/source/arch_scaling.rst b/doc/ops-guide/source/arch_scaling.rst
index 8c7107e2..8279943b 100644
--- a/doc/ops-guide/source/arch_scaling.rst
+++ b/doc/ops-guide/source/arch_scaling.rst
@@ -87,6 +87,11 @@ and require 80 TB of storage for ``/var/lib/nova/instances``:
 -  Default CPU overcommit ratio (``cpu_allocation_ratio`` in nova.conf)
    of 16:1.
 
+.. note::
+   Regardless of the overcommit ratio, an instance can not be placed
+   on any physical node with fewer raw (pre-overcommit) resources than
+   instance flavor requires.
+
 However, you need more than the core count alone to estimate the load
 that the API services, database servers, and queue servers are likely to
 encounter. You must also consider the usage patterns of your cloud.