10.4. Launching and Tuning Real-Time Instances
After you deploy and configure Real-time Compute nodes, you can launch real-time instances on those nodes. You can further configure these real-time instances with CPU pinning, NUMA topologies, and huge pages.
Configuring a real-time policy for instances
A real-time policy prioritizes real-time instances and minimizes latency during peak workload times. To set this policy, add the following parameters to the compute-realtime flavor.
$ openstack flavor set compute-realtime \ --property hw:cpu_realtime=yes --property hw:cpu_realtime_mask=^0
Launching a real-time instance
-
Make sure that the
compute-realtimeflavor exists on the overcloud, as described in the Deploying the Real-time Compute Role section. Launch the real-time instance.
# openstack server create --image <rhel> --flavor r1.small --nic net-id=<dpdk-net> test-rt
If you have administrator access to the Compute host, you can optionally verify that the instance uses the assigned emulator threads.
# virsh dumpxml <instance-id> | grep vcpu -A1 <vcpu placement='static'>4</vcpu> <cputune> <vcpupin vcpu='0' cpuset='1'/> <vcpupin vcpu='1' cpuset='3'/> <vcpupin vcpu='2' cpuset='5'/> <vcpupin vcpu='3' cpuset='7'/> <emulatorpin cpuset='0-1'/> <vcpusched vcpus='2-3' scheduler='fifo' priority='1'/> </cputune>
Pinning CPUs and setting emulator thread policy
To ensure that there are enough CPUs on each Real-time Compute node for real-time workloads, you need to pin at least one virtual CPU (vCPU) for an instance to a physical CPU (pCPUs) on the host. The emulator threads for that vCPU then remain dedicated to that pCPU.
-
Set the
emulator_thread_policyparameter toisolate. For example:
# openstack flavor set --property hw:emulator_threads_policy=isolate
-
Configure your flavor to use a dedicated CPU policy. To do so, set the
hw:cpu_policyparameter todedicatedon the flavor. For example:
# openstack flavor set --property hw:cpu_policy=dedicated 99
Make sure that your resources quota has enough pCPUs for the Real-time Compute nodes to consume.
For general information about CPU pinning, see the CPU Pinning chapter.
Optimizing your network configuration
Depending on the needs of your deployment, you might need to set parameters in the network-environment.yaml file to tune your network for certain real-time workloads.
To review an example configuration optimized for OVS-DPDK, see the Configuring OVS-DPDK with RT-KVM section of the Network Functions Virtualization Planning and Configuration Guide.
Configuring huge pages
It is recommended to set the default huge pages size to 1GB. Otherwise, TLB flushes might create jitter in the vCPU execution.
To set the huge pages size for the compute-realtime flavor, run the following command:
openstack flavor set compute-realtime --property hw:mem_page_size=large
For general information about using huge pages, see the Running DPDK applications web page.
