TELCODOCS-1514 - CNF-9112 Reserved Core Frequency Tuning

Author: slovern

modules/cnf-performance-profile-creator-arguments.adoc

@@ -23,6 +23,15 @@ Default: `false`.
 If this argument is set to `true` you should not disable hyperthreading in the BIOS. Disabling hyperthreading is accomplished with a kernel command line argument.
 ====
 
+| --enable-hardware-tuning 
+a|Enable the setting of maximum CPU frequencies. 
+This parameter is optional.
+
+To enable this feature, set the maximum frequency for applications running on isolated and reserved CPUs for both of the following:
+
+* `spec.hardwareTuning.isolatedCpuFreq` 
+* `spec.hardwareTuning.reservedCpuFreq`
+
 | `info`
 a| This captures cluster information and is used in discovery mode only. Discovery mode also requires the `must-gather-dir-path` argument. If any other arguments are set they are ignored.
 

modules/cnf-running-the-performance-creator-profile-offline.adoc

@@ -154,6 +154,7 @@ Flags:
       --split-reserved-cpus-across-numa   Split the Reserved CPUs across NUMA nodes
       --topology-manager-policy string    Kubelet Topology Manager Policy of the performance profile to be created. [Valid values: single-numa-node, best-effort, restricted] (default "restricted")
       --user-level-networking             Run with User level Networking(DPDK) enabled
+      --enable-hardware-tuning            Enable setting maximum CPU frequencies
 ----
 +
 [NOTE]
@@ -248,6 +249,29 @@ spec:
   realTimeKernel:
     enabled: false
 ----
++
+[NOTE]
+--
+When you pass the argument `--enable-hardware-tuning` as a flag to the Performance Profile Creator, the generated `PerformanceProfile` includes guidance on how to set frequency settings as follows:
+
+[source,yaml]
+----
+apiVersion: performance.openshift.io/v2
+kind: PerformanceProfile
+metadata:
+  name: performance
+spec:
+……………………
+……………………
+#HardwareTuning is an advanced feature, and only intended to be used if 
+#user is aware of the vendor recommendation on maximum cpu frequency.
+#The structure must follow
+#
+# hardwareTuning:
+#   isolatedCpuFreq: <Maximum frequency for applications running on isolated CPUs>
+#   reservedCpuFreq: <Maximum frequency for platform software running on reserved CPUs>
+----
+--
 
 . Apply the generated profile:
 +

modules/ztp-recommended-cluster-kernel-config.adoc

@@ -12,17 +12,60 @@ Always use the latest supported real-time kernel version in your cluster. Ensure
 +
 [source,yaml]
 ----
+apiVersion: performance.openshift.io/v2
+kind: PerformanceProfile
+# ...
 spec:
   additionalKernelArgs:
   - "rcupdate.rcu_normal_after_boot=0"
   - "efi=runtime"
-  - "module_blacklist=irdma"
+  - "vfio_pci.enable_sriov=1"
+  - "vfio_pci.disable_idle_d3=1"
+  - "module_blacklist=irdma"  
+  
+  # ...
+----
+
+. Optional: Set the CPU frequency under the `hardwareTuning` field:
++
+You can use hardware tuning to tune CPU frequencies for reserved and isolated core CPUs.
+For FlexRAN like applications, hardware vendors recommend that you run CPU frequencies below the default provided frequencies.
+It is highly recommended that, before setting any frequencies, you refer to the hardware vendor’s guidelines for maximum frequency settings for your processor generation.
+This example shows the frequencies for reserved and isolated CPUs for Sapphire Rapid hardware:
++
+[source,yaml]
+----
+apiVersion: performance.openshift.io/v2
+kind: PerformanceProfile
+metadata:
+  name: openshift-node-performance-profile
+spec:
+      cpu:
+        isolated: "2-19,22-39"
+        reserved: "0-1,20-21"
+      hugepages:
+        defaultHugepagesSize: 1G
+        pages:
+          - size: 1G
+            count: 32
+      realTimeKernel:
+          enabled: true
+      hardwareTuning:
+          isolatedCpuFreq: 2500000
+          reservedCpuFreq: 2800000
 ----
 
 . Ensure that the `performance-patch` profile in the `Tuned` CR configures the correct CPU isolation set that matches the `isolated` CPU set in the related `PerformanceProfile` CR, for example:
 +
 [source,yaml]
 ----
+apiVersion: tuned.openshift.io/v1
+kind: Tuned
+metadata:
+  name: performance-patch
+  namespace: openshift-cluster-node-tuning-operator
+  annotations:
+    ran.openshift.io/ztp-deploy-wave: "10"
 spec:
   profile:
     - name: performance-patch
@@ -33,12 +76,12 @@ spec:
         [main]
         summary=Configuration changes profile inherited from performance created tuned
         include=openshift-node-performance-openshift-node-performance-profile
-        [sysctl]
-        kernel.timer_migration=1
         [scheduler]
         group.ice-ptp=0:f:10:*:ice-ptp.*
         group.ice-gnss=0:f:10:*:ice-gnss.*
+        group.ice-dplls=0:f:10:*:ice-dplls.*
         [service]
         service.stalld=start,enable
         service.chronyd=stop,disable
+# ...
 ----