Add blogpost about autodetect + TBN in 35.0

src/pages/blog/empowering-end-users-ironic-35.md

@@ -0,0 +1,118 @@
+---
+templateKey: blog-post
+title: Empowering End-Users in Ironic 35.0
+author: Jay Faulkner
+date: 2026-03-17T12:00:00.000Z
+category:
+  - label: Development Update
+    id: category-A7fnZYrE9
+---
+
+Even when only considering its integration with OpenStack, Ironic has
+multiple different customers at any given time. The admin who installs
+and manages the conductors. The project managers who might online
+hardware and configure nodes in Ironic. The end-users who provision
+bare metal instances through Nova's compute API. In Ironic 35.0
+(OpenStack 2026.1, Gazpacho), we made two major feature improvements
+with one of those users in mind in particular: the end-user, by
+empowering them with more options about how to configure their
+instances at deploy time.
+<!--more-->
+
+## Autodetect Deploy Interface
+
+The first of these user-facing features is our new autodetect deploy
+interface. This permits changing the selected deployment method based
+on image metadata. Previously, this was selected by node
+configuration – by either an admin or a manager – and left entirely
+out of the hands of the end-user. Now, by configuring nodes with the
+autodetect deploy interface, we can enable end users to select what
+deployment method they would like by choosing what image to deploy.
+
+Detection is based off image metadata. The three interfaces that we
+can support autodetection for today are bootc, ramdisk, and direct:
+- *bootc* is selected when an OCI container is provided as the
+  deployment image, and that OCI container does not contain a full
+  disk image. This detection method will never trigger for Nova
+  end-users, as OCI container urls are not supported for Nova
+  deployment.
+- *ramdisk* is selected when a Glance image is provided with
+  `ironic_ramdisk=True` in the metadata. The autodetect interface then
+  looks for additional metadata pointing to a boot iso or
+  kernel/ramdisk pairing for boot.
+- *direct* is the fallback deployment interface used when none of the
+  others match.
+
+If your nodes are configured today for direct deployment, you can
+likely switch them to autodetect with no disruption.
+
+Please see the [autodetect deploy interface documentation](https://docs.openstack.org/ironic/latest/admin/interfaces/deploy.html#autodetect-deploy) for more
+specific information on how to configure this feature.
+
+## Trait-based port scheduling
+
+The second of these user-facing features is subtle, but powerful.
+Previously, when provisioning nodes with a fully integrated OpenStack,
+operators had few options as to how to map networks to ports or
+portgroups – a simple match on physical_network. This is functional;
+but static. Instead, we wanted to give end-users more
+flexibility in how their virtual interfaces from Neutron are mapped
+into a physical machine.
+
+First, a short aside: what is a trait? Traits are a way for Nova to
+track machines configured in a certain way. For instance, if you
+configure a Nova flavor to have the property
+`trait:HW_CPU_X86_AVX2=required`, virtual instances booted with that
+flavor will be placed onto a hypervisor with AVX2-supporting CPUs. In
+a similar way, Ironic uses custom traits to advertise different ways
+that Ironic can configure a node to fulfill a flavor request.
+Trait-based port scheduling is based on this concept: an admin can
+configure a flavor to request a specific trait from Ironic which will
+inform Ironic how you want your ports scheduled.
+
+Configuration of trait-based port scheduling is performed via a YAML
+config file, with each key correlating to a custom trait, and the
+value is a list of rules to follow to build a mapping. For instance,
+you could tell Ironic to `attach_port` when `network.tag="green" &&
+port.physical_network="green"`.  Operators can also set a trait to use
+when none are provided. Here is an example of a trait-based networking
+configuration:
+
+```yaml
+CUSTOM_DIRECT_ATTACH_A_PURPLE_TO_STORAGE:
+  actions:
+    - action: attach_port
+      filter: port.vendor == 'purple' && network.name == 'storage'
+CUSTOM_BOND_GREEN_STORAGE_TO_STORAGE_BY_2:
+  actions:
+    - action: group_and_attach_ports
+      filter: >-
+        port.vendor == 'green' && port.category == 'storage'
+        && ( network.name =~ 'storage' || network.tags =~ 'storage' )
+      max_count: 2
+      min_count: 2
+```
+
+This port scheduling goes a step further with the ability to assemble
+dynamic portgroups. In Ironic, prior to Gazpacho, the only way to get
+portgroups – ports bonded together using LACP or similar technology –
+is to statically configure port groupings on a node. Now, with
+trait-based scheduling, you can assemble portgroups on the fly based
+on rulesets. For instance, not only could you attach green ports to
+green physical networks from the previous example, but by using the
+`group_and_attach_ports` action, you can have Ironic create a
+portgroup on the fly based on the specified rules – including the
+ability to fail processing if too few or too many ports would be
+included in the portgroup.
+
+For full details, see the [trait-based networking documentation](https://docs.openstack.org/ironic/latest/admin/trait-based-networking.html).
+
+## Get started
+
+Both the autodetect deploy interface and trait-based port scheduling
+are available now in Ironic 35.0 as part of the OpenStack 2026.1
+(Gazpacho) release. Together, they represent a meaningful step toward
+giving end-users more control over how their bare metal instances are
+configured, without requiring admin intervention. Check out the full
+[Ironic 35.0 release notes](https://docs.openstack.org/releasenotes/ironic/2026.1.html)
+for everything that's new in this release.