hope I got the merge wright...

[monitor.git] / docs / model.txt

diff --git a/docs/model.txt b/docs/model.txt
new file mode 100644 (file)
index 0000000..077bfed
--- /dev/null
+++ b/docs/model.txt
@@ -0,0 +1,180 @@
+##
+#
+# TODO: Whitelist for sites or machines with scheduled maintenance or
+#                      predicted downtimes way in the future.
+#              Scheduled outages for some short period of time.
+#                      gives admins a chance to compare expectations with observations.
+
+
+PLC
+       name
+       fullname
+       xmlrpcserver
+       history->MultipleJoin->PLCHistory.plc
+       sites -> MultipleJoin->Site.plc
+       actions->MultipleJoin->PLCAction.plc
+
+  # configuration parameters...
+       monitor_frequency
+       rt_db_stuff
+       rt_user_stuff
+
+
+PLCHistory
+       plc->
+       date_checked
+       plc_nodes
+       plc_sites
+       ob_sites_up
+       ob_sites_down
+       ob_nodes_up
+       ob_nodes_down
+       ob_nodes_other
+
+# I'm unsure of this.  There is a transactional pattern that I need to
+# discover or define wrt how data is introduced into the db and whether or not
+# it can be trusted as 'complete'.  this action may be the root of all the
+# others in a tree.
+
+PLCAction
+       date_performed
+       plc->ForeignKey->PLC.actions
+       plc_query                                                       # site, node, slice query.
+       nodes_query                                                     # probe nodes
+       nodes_categorize                                        # take raw data and push into finite states
+                                                                               # also aggregate data for site and plc
+       stats_aggregate                                         # fill out the rest of aggregate fields in db?
+       nodes_diagnose                                          # decide what actions to take based on history
+                                                                               # write action to db.
+       nodes_act                                                       # read action db and perform to change state at plc or node
+
+--
+
+Site
+       loginbase                                                               # from plc
+       active                                                                  # site exists in PLC
+       plc->ForeignKey->PLC.sites
+       history->MultipleJoin->SiteHistory.site
+       nodes->MultipleJoin->Node.site
+       actions->MultipleJoin->SiteAction.site
+
+SiteHistory
+       site->ForeignKey->Site.history
+       date_checked
+
+  # Statistics
+       plc_nodes                                       # from plc
+       plc_slices_max                                  # from plc
+       plc_slices_used                                 # from plc
+       plc_disabled                                    # from plc
+       plc_suspended                                   # from plc
+       ob_nodes_up                                             # from monitor
+       ob_nodes_down                                   # from monitor
+
+SiteAction
+       site->ForeignKey->Site.actions
+
+       date_created
+  # Action to take
+       email                                           # from monitor diagnose -> action
+       suspend_slices                          # from monitor diagnose -> action
+       disable_creation                        # from monitor diagnose -> action
+
+  # Are other actions available for either Notify or Findbad scripts?
+       slices_suspend
+       slices_enable
+
+       site_enable
+       site_disable
+
+       email_send
+       message
+
+  # Action taken
+       date_performed                          # from monitor (action)
+       rt_ticket_id                            # from monitor sent mail (action.py)
+
+--
+
+Node
+       nodename
+       probe->ForeignKey->NodeProbe.node
+       hardware->OnetoOne->Hardware->node
+       actions->MultipleJoin->NodeAction.node
+
+NodeCurrent
+       ->node
+       site->
+       ->probe
+       ->action
+       ->downtime
+
+NodeProbe
+       nodecurrent->
+       date_checked
+       ob_ping
+       ob_ssh
+       ob_kernel
+       ob_bmlog
+       ob_bootstate
+       ob_bootcd
+       plc_bootstate
+       plc_bootcd
+       plc_pcu
+
+NodeDowntime
+       nodecurrent->
+       date_created
+       date_expires
+       enabled
+       owner_reason
+       owner_comments
+
+NodeAction
+       nodecurrent->ForeignKey->Node.actions
+       date_created
+
+       inferred_state
+       inf_category
+       
+  # Are there actions on individual nodes?
+       plc_boot_state_reset
+       pcu_test
+       node_reboot
+
+# TODO: Whitelist for sites or machines with scheduled maintenance or
+#                      predicted downtimes way in the future.
+#              Scheduled outages for some short period of time.
+#                      gives admins a chance to compare expectations with observations.
+
+Message
+       date_created
+       title
+       template_arguments
+       message_parts->Join->MessagePart->message.id
+
+MessagePart
+       date_created
+       title
+       template_message
+       message->ForeignKey->Message.id
+       
+
+Hardware
+       node->
+       date_checked
+       cpu_model
+       cpu_speed
+       cpu_count
+
+       ram_model
+       ram_size
+       disk_model
+       disk_specs
+       
+  # pci devices
+       network cards
+       daughter cards
+       raid cards
+       usb
+       other?