VSWITCHPERF Tests to be defined
The test scratchpad (for tests that are WIP/being defined/looked at by the community) can be found here: https://etherpad.opnfv.org/p/vSwitchTestsDrafts
Performance tests to be defined list (Old)
Test | Priority | JIRA |
|---|---|---|
Scalability Tests adding More VMs in succession and building a performance profile as we add more VMs. | 1 | |
OverlayNetworking Tests: VXLAN performance testing, encap, decap, encap and decap | 1 | |
Matchaction performance testing? The cost of the different actions supported by a vSwitch | 1 | |
VM2VM Tests (PHY-VNF-vSwitch-VNF-PHY), with scaling number of VMs in path (combines two tests in the list) | 1 | |
Classifying L2, L3 and L4 traffic Profile Tests, Flows, new flows/sec, L2/L3/L4 etc. entries in"fast" path tables, ... | 2 | |
Stream/bulk Data transfer "unidirectional stream" performance request& response/transaction rate tests | 3 | |
Performance testing with Mirroring enabled on the switch | 2 | |
TCP Max connections per second, Max # of active sessions, Max transactions per second | 3 | |
IPv6 Support and Testing | 2 | |
Measuring how many instances of a vSwitch would be required to support 1 million simulataneous flows | 2 | |
Resilience tests (re-define or delete) | ?? | |
Performance characterization runs vs.number of "x". Tests with Restricted Resources (Host with X Cores, vSwitch with Y Cores? | some x done | |
Flows, new flows/sec, L2/L3/L4 etc. entries in"fast" path tables, ... | 2 | |
SOAK tests (using RFC 2889 Max Forwarding Rate, not RFC 2544, to collect intermediate results) | 2 | |
Box-full tests, where all CPU cores are doing useful work: vNet4 vSwitch with Nx VNFs, vNet6 vSwitch with Nx VNF chained topologies | 2 | |
Latency And Latency Variation with dedicated latency measurement streams with percentiles, 99th for TST009 benchmark | prox does it | |
Tests with Restricted Resources (Host with X Cores, vSwitch with Y Cores, ? overlap with 14, … vs number of "X") | 2 | |
Testing Topologies
Topology | Priority | JIRA |
|---|---|---|
vNet vComp2 for VM2VM virt interface testing |
Integration Tests
https://etherpad.opnfv.org/p/vSwitchIntegrationTests
Other
We should consider recommending a minimum number of iterations to repeat the test and either average out the result or calculate the variance across trials
1 Comment
Al Morton
Deleted tests:
Best of N and Worst of N Tests
Tests to evaluate vSwitch contribution to 3GPP performance objectives (3GPP TS 23.203 Policy and Charging Control Architecture)
Programming rate of Forwarding_table /flow_table
Tests suggested by OVS developers (there were a few, but this was 2015)
Latency And Latency Variation with dedicated latency measurement streams (this is a traffic generator requirement, refined wording)
Tests with Restricted Resources (Host with X Cores, vSwitch with Y Cores, ? overlap with 14, … vs number of "X")
Spanning Tree/Rapid Spanning Tree integration testing