Bug 2137643

Summary: [RFE] Add support for ingress policing above 34 Gbps
Product: Red Hat Enterprise Linux Fast Datapath Reporter: Ilya Maximets <i.maximets>
Component: openvswitch3.0Assignee: Adrián Moreno <amorenoz>
Status: POST --- QA Contact: liting <tli>
Severity: unspecified Docs Contact:
Priority: unspecified    
Version: FDP 22.LCC: ctrautma, fleitner, jhsiao, ralongi
Target Milestone: ---Keywords: FutureFeature
Target Release: ---   
Hardware: Unspecified   
OS: Unspecified   
Whiteboard:
Fixed In Version: Doc Type: If docs needed, set a value
Doc Text:
Story Points: ---
Clone Of: Environment:
Last Closed: Type: Bug
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:

Description Ilya Maximets 2022-10-25 17:46:15 UTC 
OVS ingress policing is implemented via act_police tc action.
Similarly to HTB in BZ 2137619, act_police is getting the main
rate/ceil configuration via 'struct tc_ratespec'.
This structure holds a 32bit rate field that reflects bytes per
second.  So, the maximum value is ~34 G bits per second.

Again, similarly to HTB, act_police has dedicated netlink
attributes TCA_POLICE_RATE64 and TCA_POLICE_PEAKRATE64 that
can be used to break the 32bit barrier.

It makes sense to add support for these attributes to be able
to configure higher speeds since modern NICs can be much faster
than the current limit.