feat(host_agent): a group's updates and reboots on a weekly cadence, one host at a time (#5768)

#5768 "A maintenance cadence: a group's updates and reboots, one host at a time, on a schedule". A plan names an inventory group, a weekday and time in a time zone, a window and a reboot policy (only when required by default). At its slot a run takes the group's hosts in order and gives each a #5767 maintenance job. The next host starts only when the last is back in service: its agent is posting and, for a swarm node, the node is active and every replicated service is at its replicas. A failure stops the run, and no host is started once the window has passed. A host's latest failure shows as host_agent/<host>/maintenance_failed, for an ordinary alert rule. The page is Hosts → Maintenance. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-14 18:59:07 -04:00
parent 78581c843e
commit 200384e52d
17 changed files with 1077 additions and 15 deletions
@@ -0,0 +1,61 @@
+"""host_agent: a group's maintenance cadence and its runs (#5768)
+
+Revision ID: host_agent_008_maint_plans
+"""
+from typing import Sequence, Union
+from alembic import op
+import sqlalchemy as sa
+
+revision: str = "host_agent_008_maint_plans"
+down_revision: Union[str, None] = "host_agent_007_maint_jobs"
+branch_labels: Union[str, Sequence[str], None] = None
+# ansible_groups (core 0016) must exist before the group_id key.
+depends_on: Union[str, Sequence[str], None] = ("0016_ansible_inventory_groups",)
+
+
+def upgrade() -> None:
+    op.create_table(
+        "host_maintenance_plans",
+        sa.Column("id", sa.String(36), primary_key=True),
+        sa.Column("name", sa.String(128), nullable=False),
+        sa.Column("group_id", sa.String(36), sa.ForeignKey("ansible_groups.id", ondelete="CASCADE"),
+                  nullable=False),
+        sa.Column("weekday", sa.Integer(), nullable=False),
+        sa.Column("at_time", sa.String(5), nullable=False),
+        sa.Column("time_zone", sa.String(64), nullable=False, server_default="UTC"),
+        sa.Column("window_minutes", sa.Integer(), nullable=False, server_default="240"),
+        sa.Column("reboot_policy", sa.String(16), nullable=False, server_default="if_required"),
+        sa.Column("enabled", sa.Boolean(), nullable=False, server_default=sa.true()),
+        sa.Column("last_slot_at", sa.DateTime(timezone=True), nullable=True),
+        sa.Column("created_by", sa.String(36), sa.ForeignKey("users.id", ondelete="SET NULL"),
+                  nullable=True),
+        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False),
+    )
+    op.create_table(
+        "host_maintenance_runs",
+        sa.Column("id", sa.String(36), primary_key=True),
+        sa.Column("plan_id", sa.String(36),
+                  sa.ForeignKey("host_maintenance_plans.id", ondelete="CASCADE"), nullable=False),
+        sa.Column("state", sa.String(16), nullable=False),
+        sa.Column("host_ids", sa.Text(), nullable=False, server_default="[]"),
+        sa.Column("position", sa.Integer(), nullable=False, server_default="0"),
+        sa.Column("skipped", sa.Text(), nullable=False, server_default="[]"),
+        sa.Column("settle_since", sa.DateTime(timezone=True), nullable=True),
+        sa.Column("detail", sa.Text(), nullable=True),
+        sa.Column("manual", sa.Boolean(), nullable=False, server_default=sa.false()),
+        sa.Column("started_at", sa.DateTime(timezone=True), nullable=False),
+        sa.Column("finished_at", sa.DateTime(timezone=True), nullable=True),
+    )
+    op.create_index("ix_host_maintenance_runs_plan_id", "host_maintenance_runs", ["plan_id"])
+    op.create_index("ix_host_maintenance_runs_state", "host_maintenance_runs", ["state"])
+    op.add_column("host_maintenance_jobs", sa.Column(
+        "run_id", sa.String(36), sa.ForeignKey("host_maintenance_runs.id", ondelete="SET NULL"),
+        nullable=True))
+    op.create_index("ix_host_maintenance_jobs_run_id", "host_maintenance_jobs", ["run_id"])
+
+
+def downgrade() -> None:
+    op.drop_index("ix_host_maintenance_jobs_run_id", "host_maintenance_jobs")
+    op.drop_column("host_maintenance_jobs", "run_id")
+    op.drop_table("host_maintenance_runs")
+    op.drop_table("host_maintenance_plans")