Add a way to restrict gathered facts in Ansible:

- Using gather_subset options
- By ignoring ohai/chef or facter/puppet facts

docsite/rst/glossary.rst

@@ -71,8 +71,7 @@ Facts
 Facts are simply things that are discovered about remote nodes.  While they can be used in playbooks and templates just like variables, facts
 are things that are inferred, rather than set.  Facts are automatically discovered by Ansible when running plays by executing the internal 'setup'
 module on the remote nodes.  You never have to call the setup module explicitly, it just runs, but it can be disabled to save time if it is
-not needed.  For the convenience of users who are switching from other configuration management systems, the fact module will also pull in facts from the 'ohai' and 'facter'
-tools if they are installed, which are fact libraries from Chef and Puppet, respectively.
+not needed or to reduce to a subset. For the convenience of users who are switching from other configuration management systems, the fact module will also pull in facts from the 'ohai' and 'facter' tools if they are installed, which are fact libraries from Chef and Puppet, respectively. You can also ignore them and save time at runtime execution.
 
 Filter Plugin
 +++++++++++++

docsite/rst/intro_configuration.rst

@@ -353,6 +353,25 @@ This option can be useful for those wishing to save fact gathering time. Both 's
 
     gathering = smart
 
+.. versionadded:: 2.1
+
+You can specify a subset of gathered facts using the following options:
+
+    gather_subset = all
+
+:all: gather all subsets
+:min: gather a very limited set of facts
+:network: gather min and network facts
+:hardware: gather min and hardware facts (longest facts to retrieve)
+:virtual: gather min and virtual facts
+
+You can combine them using comma separated list (ex: min,network,virtual)
+
+You can also disable puppet facter or chef ohai facts collection using following options:
+
+    ignore_ohai = True
+    ignore_facter = True
+
 hash_behaviour
 ==============
 
@@ -367,7 +386,7 @@ official examples repos do not use this setting::
 
 The valid values are either 'replace' (the default) or 'merge'.
 
-.. versionadded: '2.0'
+.. versionadded:: 2.0
 
 If you want to merge hashes without changing the global settings, use
 the `combine` filter described in :doc:`playbooks_filters`.
@@ -585,7 +604,7 @@ The directory will be created if it does not already exist.
 roles_path
 ==========
 
-.. versionadded: '1.4'
+.. versionadded:: 1.4
 
 The roles path indicate additional directories beyond the 'roles/' subdirectory of a playbook project to search to find Ansible
 roles.  For instance, if there was a source control repository of common roles and a different repository of playbooks, you might

examples/ansible.cfg

@@ -31,6 +31,21 @@
 # explicit - do not gather by default, must say gather_facts: True
 #gathering = implicit
 
+# by default retrieve all facts subsets
+# all - gather all subsets
+# min - gather a very limited set of facts
+# network - gather min and network facts
+# hardware - gather hardware facts (longest facts to retrieve)
+# virtual - gather min and virtual facts
+# You can combine them using comma (ex: min,network,virtual)
+#gather_subset = all
+
+# by default run ohai
+#ignore_ohai = False
+
+# by default run facter
+#ignore_facter = False
+
 # additional paths to search for roles in, colon separated
 #roles_path    = /etc/ansible/roles
 

lib/ansible/constants.py

@@ -156,6 +156,9 @@ DEFAULT_PRIVATE_ROLE_VARS = get_config(p, DEFAULTS, 'private_role_vars', 'ANSIBL
 DEFAULT_JINJA2_EXTENSIONS = get_config(p, DEFAULTS, 'jinja2_extensions', 'ANSIBLE_JINJA2_EXTENSIONS', None)
 DEFAULT_EXECUTABLE        = get_config(p, DEFAULTS, 'executable', 'ANSIBLE_EXECUTABLE', '/bin/sh')
 DEFAULT_GATHERING         = get_config(p, DEFAULTS, 'gathering', 'ANSIBLE_GATHERING', 'implicit').lower()
+DEFAULT_GATHER_SUBSET     = get_config(p, DEFAULTS, 'gather_subset', 'ANSIBLE_GATHER_SUBSET', 'all').lower()
+DEFAULT_IGNORE_OHAI       = get_config(p, DEFAULTS, 'ignore_ohai', 'ANSIBLE_IGNORE_OHAI', False, boolean=True)
+DEFAULT_IGNORE_FACTER     = get_config(p, DEFAULTS, 'ignore_facter', 'ANSIBLE_IGNORE_FACTER', False, boolean=True)
 DEFAULT_LOG_PATH          = get_config(p, DEFAULTS, 'log_path',           'ANSIBLE_LOG_PATH', '', ispath=True)
 DEFAULT_FORCE_HANDLERS    = get_config(p, DEFAULTS, 'force_handlers', 'ANSIBLE_FORCE_HANDLERS', False, boolean=True)
 DEFAULT_INVENTORY_IGNORE  = get_config(p, DEFAULTS, 'inventory_ignore_extensions', 'ANSIBLE_INVENTORY_IGNORE', ["~", ".orig", ".bak", ".ini", ".cfg", ".retry", ".pyc", ".pyo"], islist=True)

lib/ansible/executor/play_iterator.py

@@ -151,11 +151,30 @@ class PlayIterator:
         self._play = play
         self._blocks = []
 
+        # Default options to gather
+        gather_subset = C.DEFAULT_GATHER_SUBSET
+        ignore_ohai   = C.DEFAULT_IGNORE_OHAI
+        ignore_facter = C.DEFAULT_IGNORE_FACTER
+
+        # Retrieve subset to gather
+        if self._play.gather_subset is not None:
+            gather_subset = self._play.gather_subset
+        # ignore ohai
+        if self._play.ignore_ohai is not None:
+            ignore_ohai = self._play.ignore_ohai
+        # ignore puppet facter
+        if self._play.ignore_facter is not None:
+            ignore_facter = self._play.ignore_facter
+
         setup_block = Block(play=self._play)
         setup_task = Task(block=setup_block)
         setup_task.action = 'setup'
         setup_task.tags   = ['always']
-        setup_task.args   = {}
+        setup_task.args   = {
+          'gather_subset': gather_subset,
+          'ignore_ohai'  : ignore_ohai,
+          'ignore_facter': ignore_facter,
+        }
         setup_task.set_loader(self._play._loader)
         setup_block.block = [setup_task]
 

lib/ansible/module_utils/facts.py

@@ -159,6 +159,9 @@ class Facts(object):
                  { 'path' : '/usr/local/sbin/pkg',  'name' : 'pkgng' },
     ]
 
+    # Allowed fact subset for gather_subset options
+    ALLOWED_FACT_SUBSET = frozenset([ 'all', 'min', 'network', 'hardware', 'virtual' ])
+
     def __init__(self, load_on_init=True):
 
         self.facts = {}
@@ -3067,15 +3070,33 @@ def get_file_lines(path):
     return ret
 
 def ansible_facts(module):
+    # Retrieve module parameters
+    gather_subset = [ 'all' ]
+    if 'gather_subset' in module.params:
+        gather_subset = module.params['gather_subset']
+
+    # Retrieve all facts elements
+    if 'all' in gather_subset:
+        gather_subset = [ 'min', 'hardware', 'network', 'virtual' ]
+
+    # Check subsets and forbid unallowed name
+    for subset in gather_subset:
+        if subset not in Facts.ALLOWED_FACT_SUBSET:
+            raise TypeError("Bad subset '%s' given to Ansible. gather_subset options allowed: %s" % (subset, ", ".join(Facts.ALLOWED_FACT_SUBSET)))
+
     facts = {}
     facts.update(Facts().populate())
-    facts.update(Hardware().populate())
-    facts.update(Network(module).populate())
-    facts.update(Virtual().populate())
+    if 'hardware' in gather_subset:
+        facts.update(Hardware().populate())
+    if 'network' in gather_subset:
+        facts.update(Network(module).populate())
+    if 'virtual' in gather_subset:
+        facts.update(Virtual().populate())
+    facts['gather_subset'] = gather_subset
     return facts
 
 # ===========================================
-
+# TODO: remove this dead code?
 def get_all_facts(module):
 
     setup_options = dict(module_setup=True)

lib/ansible/playbook/play.py

@@ -64,6 +64,9 @@ class Play(Base, Taggable, Become):
 
     # Connection
     _gather_facts        = FieldAttribute(isa='bool', default=None, always_post_validate=True)
+    _gather_subset       = FieldAttribute(isa='string', default=None, always_post_validate=True)
+    _ignore_facter       = FieldAttribute(isa='bool', default=None, always_post_validate=True)
+    _ignore_ohai         = FieldAttribute(isa='bool', default=None, always_post_validate=True)
     _hosts               = FieldAttribute(isa='list', required=True, listof=string_types, always_post_validate=True)
     _name                = FieldAttribute(isa='string', default='', always_post_validate=True)
 

test/integration/test_gathering_facts.yml

@@ -0,0 +1,45 @@
+---
+
+- hosts: localhost
+  tags: [ 'min' ]
+  connection: local
+  gather_subset: "min"
+  ignore_facter: yes
+  ignore_ohai: yes
+  gather_facts: yes
+  tasks:
+    - debug: var={{item}}
+      with_items: [ 'ansible_user_id', 'ansible_interfaces', 'ansible_mounts', 'ansible_virtualization_role' ]
+
+- hosts: localhost
+  tags: [ 'network' ]
+  connection: local
+  gather_subset: "network"
+  ignore_facter: yes
+  ignore_ohai: yes
+  gather_facts: yes
+  tasks:
+    - debug: var={{item}}
+      with_items: [ 'ansible_user_id', 'ansible_interfaces', 'ansible_mounts', 'ansible_virtualization_role' ]
+
+- hosts: localhost
+  tags: [ 'hardware' ]
+  connection: local
+  gather_subset: "hardware"
+  ignore_facter: yes
+  ignore_ohai: yes
+  gather_facts: yes
+  tasks:
+    - debug: var={{item}}
+      with_items: [ 'ansible_user_id', 'ansible_interfaces', 'ansible_mounts', 'ansible_virtualization_role' ]
+
+- hosts: localhost
+  tags: [ 'virtual' ]
+  connection: local
+  gather_subset: "virtual"
+  ignore_facter: yes
+  ignore_ohai: yes
+  gather_facts: yes
+  tasks:
+    - debug: var={{item}}
+      with_items: [ 'ansible_user_id', 'ansible_interfaces', 'ansible_mounts', 'ansible_virtualization_role' ]