Start resources on demand

Makefile

@@ -6,6 +6,7 @@ SHELLTEST_OPTIONS :=
 SHELL_TESTS := \
 	basic.sh \
 	check.sh \
+	ondemand.sh \
 	reuse.sh
 
 TEST_PYTHONS   := python3
@@ -28,7 +29,7 @@ shelltests:
 unittests:
 	status=true ; \
 	for python in $(TEST_PYTHONS); do \
-	    PYTHON=$$python ./unittests.sh || status=false ; \
+	    PYTHON=$$python ./unittests.sh -vv || status=false ; \
 	done ;\
 	$$status
 

NEWS

@@ -1,3 +1,13 @@
+New in v5.0:
+
+* New features
+
+    - New concept of "on demand" ticket tags added, these on demand tags
+      trigger a resource allocation.  Until such a ticket is taken, the
+      corresponding resource pool has no resource allocated.
+
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
 New in v4.10:
 
 * New features

README.md

@@ -71,6 +71,9 @@ own when starting from scratch.
   new VM in the cloud and running Ansible playbooks to provision it can take few
   minutes), and users don't want to wait. It is a good idea to preallocate a
   small number of resources that are ready to be used immediately.
+- On demand allocation - In special "on demand" pool mode, resources are not
+  preallocated in advance but started on demand, only upon a ticket requesting
+  the resources.
 - Livechecks - Clouds are unreliable. VMs can break while starting or become
   unresponsive for various reasons. Resalloc periodically checks the liveness
   of all resources and makes sure money doesn't leak out of our pockets.

config/pools.yaml

@@ -92,6 +92,27 @@
 ##          - ci_test_machine_x86_64
 ##          - ci_test_machine
 ##
+##      # This is similar to the "tags" configuration in terms of "matching
+##      # resources to tickets".  But on demand tags trigger a completely
+##      # different pool behavior.  Instead of preallocating a set of "free"
+##      # resources in advance dynamically, pool with the "tags_on_demand"
+##      # configured have by default zero resources allocated until some existing
+##      # ticket is taken with at least one of predefined "tags_on_demand".  The
+##      # more tags are taken, the more resources are allocated on demand.  By
+##      # example, if `beefy` tag is configured in pool, no resource is started
+##      # till `resalloc ticket --tag beefy` is taken.  Note that contrary to
+##      # normal pools, the resources are allocated on demand, so resolving such
+##      # tickets always takes some time (unless the resource is reused within
+##      # reuse_opportunity_time).  Multiple pools may provide the same
+##      # "on_demand_tags", but those tags may not be mixed between the "tags"
+##      # and "on_demand_tags" in multiple pools (configuration runtime error is
+##      # generated in such case).  The "max_prealloc" config, if also
+##      # specified, is ignored (no preallocation is possible).
+##      tags_on_demand:
+##          - beefy_machine_x86_64
+##          - name: beefy_machine
+##            priority: -10
+##
 ##    # The "reuse" feature options.  These options configure the mechanism of
 ##    # re-assigning of previously used resources to multiple subsequent tickets
 ##    # (when the assigned tickets belong to the same --sandbox).  Still, when the

pylintrc

@@ -24,7 +24,16 @@ ignored-classes=RState,TState
 #     This is to work-around the issues in our diff-lint CI where we do not have
 #     all the build/runtime requirements installed.  We can ignore this error
 #     because the packaging CI would actually discover the import issues anyway.
-disable=useless-object-inheritance,import-error
+# too-few-public-methos
+#     Deliberately using classes instead of namedtuple, because it helps us with
+#     typing (completion).
+# consider-using-f-string
+#     We still support EPEL7.
+# too-many-lines
+# too-many-locals
+# too-many-branches
+#     Stylis errors that are low-priority, and sometimes hard to avoid.
+disable=useless-object-inheritance,import-error,too-few-public-methods,consider-using-f-string,too-many-lines,too-many-locals,too-many-branches
 
 [DESIGN]
 min-public-methods=1

resallocserver/logic.py

@@ -18,10 +18,11 @@
 import time
 import uuid
 
+from sqlalchemy.orm import Query, joinedload
+from sqlalchemy import or_
+
 from resalloc.helpers import RState, TState
 from resallocserver import models
-from sqlalchemy.orm import Query
-from sqlalchemy import or_
 
 
 def assign_ticket(resource, ticket):
@@ -69,10 +70,11 @@ def ready(self):
         """
         Get ready resources, those which were never assigned or are released.
         The sandbox-assigned resources are sorted above others - so they can be
-        re-used first.
+        re-used first.  The query is already ordered by ID ASC.
         """
         return (self.up().filter(models.Resource.ticket_id.is_(None))
-                         .filter(models.Resource.check_failed_count==0))
+                         .filter(models.Resource.check_failed_count==0)
+                         .order_by(models.Resource.id.asc()))
 
     def taken(self):
         """
@@ -156,9 +158,15 @@ def kill(self, res_id):
 class QTickets(QObject):
     query = Query(models.Ticket)
 
-    def waiting(self):
-        return self.query.filter_by(resource_id=None)\
-                         .filter_by(state=TState.OPEN)
+    def waiting(self, preload_tags=False):
+        query = (
+            self.query.filter_by(resource_id=None)
+            .filter_by(state=TState.OPEN)
+        )
+        if preload_tags:
+            query = query.options(joinedload("tags"))
+        return query
+
 
     def not_closed(self):
         return self.query.filter(models.Ticket.state != TState.CLOSED)