VPP Performance Changes 2n-skx 2t1c pdr

  • Test Case: Test cases executed for: PDR throughput on 2n-skx with xxv710.

  • YYMM.V-E: [Mpps +- StDev] results for VPP (YY year, MM month, V minor version) tested in CSIT (E environment version, “2” for CSIT rls2001, “4” for CSIT rls2005).

  • YYMM.V-E vs YYMM.V-E: [% +- StDev] Relative difference, latter is the base. [N] for Root Cause Analysis (RCA) reference, see RCA list below.

  • 2001.0-4 vs 2001.0-2: Compares CSIT environment current vs previous with previous VPP code.

  • 2005.0-4 vs 2001.0-4: Compares VPP code current vs previous in the current CSIT environment

Root Cause Analysis:

  • [1] DONE Apparent regression in ACL tests due to Gerrit 26112. With CSIT using changed VPP API, instead of failing, misconfigured VPP passes the test, albeit with reduced performance. [CSIT-1739]

  • [2] DONE Regression in tests using random flow sequencing due to Gerrit 26456. Unpinned random seed to make TRex workers generate different sequences of packets. [CSIT-1731]

  • [3] DONE Regression in base dot1q-l2xcbase suites due to Gerrit 25363. Unified dot1q handling across various tests. Previously, this one suite was different, using dot1q on one port only.

  • [4] DONE Progression in high performance tests due to Gerrit 26445. TRex setting improvement. [CSIT-1740]

  • [5] DONE Progression in tests with VPP (l2xc) inside a VM due to Gerrit 25309. Make VPP in VM worker placement deterministic. [CSIT-1738]

  • [7] POSTPONED Possible anomaly, but stdev of results is high. Performance differences considered to probably be just noise.

  • [8] DONE Regressions in some tests with VPP in VM due to Gerrit 26744. Switch to clang-9 compiler identified as cause. Tests using l2xcbase as vswitch with small stdev used for bisect. [CSIT-1741]

  • [9] OPEN Progression in all ip6 scale tests. Changes to vppinfra bihash may have improved code efficiency. [CSIT-1735]

  • [11] OPEN Progression in memif tests, mainly in avf-eth-l2xcbase-eth-2memif-1dcr. Two progression candidates found: Gerrit 24053 and Gerrit 26744. Performance results are not consistent enough to separate the two from other possible causes. [CSIT-1744]

  • [12] OPEN Progression in some l2bdscale tests. [CSIT-1745]

  • [13] DONE Stateless ACL tests have the same performance in 2005.0-4 as in 2001.0-2. The difference shown here is inflated by an API change, see [1]. [CSIT-1739]

  • [14] DONE Stateful ACL tests have better performance in 2005.0-4 as in 2001.0-2. The CSIT part of API change, Gerrit 26112, has fixed an earlier CSIT regression in the same tests. The difference shown here is further inflated by the API mismatch, see [1]. [CSIT-1739]

  • [15] OPEN Progression in nat44 test (not scale ones). [CSIT-1747]

  • [17] OPEN Progression in some vhost tests (dpdk in VM). [CSIT-1749]