openstack
/
tripleo-heat-templates
Code Issues Proposed changes

Workflow input parameter update in plan-environment 

derive_parameters workflow input parameter needs to be
changed as num_phy_cores_per_numa_node_for_pmd
instead of number_of_pmd_cpu_threads_per_numa_node.
The performance varies based on the physical core
rather than the logical CPUs. Which means, user should
be able to decide the number of physical cores,
which is proportional to data rate.
Implements: blueprint tripleo-derive-parameters

Change-Id: I056fb330a17e647ab527e8bccd52bdf5e77067b6
This commit is contained in:
Jaganathan Palanisamy 2017-07-05 06:57:46 -04:00
parent 0ff01e369c
commit 9b3b1c6358
2 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
plan-samples/README.rst
View File

@ -15,8 +15,8 @@ commands. The sample format to provide the workflow specific parameters::
workflow_parameters:
tripleo.derive_params.v1.derive_parameters:
# DPDK Parameters
number_of_pmd_cpu_threads_per_numa_node: 2
num_phy_cores_per_numa_node_for_pmd: 2
All the parameters specified under the workflow name will be passed as
``user_input`` to the workflow, while invoking from the tripleoclient.
``user_input`` to the workflow, while invoking from the tripleoclient.

6
plan-samples/plan-environment-derived-params.yaml
View File

@ -9,11 +9,11 @@ environments:
workflow_parameters:
tripleo.derive_params.v1.derive_parameters:
######### DPDK Parameters #########
# Specifices the minimum number of CPU threads to be allocated for DPDK
# Specifices the minimum number of CPU physical cores to be allocated for DPDK
# PMD threads. The actual allocation will be based on network config, if
# the a DPDK port is associated with a numa node, then this configuration
# will be used, else 0.
number_of_pmd_cpu_threads_per_numa_node: 4
# will be used, else 1.
num_phy_cores_per_numa_node_for_pmd: 2
# Amount of memory to be configured as huge pages in percentage. Ouf the
# total available memory (excluding the NovaReservedHostMemory), the
# specified percentage of the remaining is configured as huge pages.