diff options
author | Maciek Konstantynowicz <mkonstan@cisco.com> | 2020-07-10 18:49:27 +0200 |
---|---|---|
committer | Tibor Frank <tifrank@cisco.com> | 2020-07-13 06:59:41 +0000 |
commit | 25df39dad530a0d64d30adc4d983891dff765f80 (patch) | |
tree | 9d372732603cf8be3adeae97ff803457a619d68f | |
parent | df84ad207a3e7e483d6bac2385b48985105259c6 (diff) |
report: fixed misplaced environment versioning section
Change-Id: Id0da363b376e12dac583f95624ed6525b24290eb
Signed-off-by: Maciek Konstantynowicz <mkonstan@cisco.com>
(cherry picked from commit 30a988b35c6d66a11b5ec2f2c77c741dc942594e)
-rw-r--r-- | docs/report/introduction/test_environment_intro.rst | 45 | ||||
-rw-r--r-- | docs/report/vpp_performance_tests/test_environment.rst | 40 |
2 files changed, 43 insertions, 42 deletions
diff --git a/docs/report/introduction/test_environment_intro.rst b/docs/report/introduction/test_environment_intro.rst index 7c4d5dfc9f..3b7793f644 100644 --- a/docs/report/introduction/test_environment_intro.rst +++ b/docs/report/introduction/test_environment_intro.rst @@ -1,6 +1,47 @@ Test Environment ================ +Environment Versioning +---------------------- + +In order to determine any benchmark anomalies (progressions, +regressions) between releases of a specific data-plane DUT application +(e.g. VPP, DPDK), the DUT needs to be tested in the same test +environment, to avoid test environment changes impacting the results and +clouding the picture. + +In order to enable test system evolution, a mirror scheme is required to +determine benchmarking anomalies between releases of specific test +system like CSIT. This is achieved by testing the same DUT application +version between releases of CSIT test system. + +CSIT test environment versioning scheme ensures integrity of all the +test system components, including their HW revisions, compiled SW code +versions and SW source code, within a specific CSIT version. Components +included in the CSIT environment versioning include: + +- Server hosts hardware firmware and BIOS (motherboard, processsor, + NIC(s), accelerator card(s)). +- Server host Linux operating system versions. +- Server host Linux configuration. +- TRex Traffic Generator version, drivers and configuration. +- CSIT framework code. + +Following is the list of CSIT versions to date: + +- Ver. 1 associated with CSIT rls1908 git branch as of 2019-08-21. +- Ver. 2 associated with CSIT rls2001 git branch as of 2020-03-27. +- Ver. 3 interim associated with master branch as of 2020-xx-xx. +- Ver. 4 associated with CSIT rls2005 git branch as of 2020-06-24. + +To identify performance changes due to VPP code changes from v20.01.0 to +v20.05.0, both have been tested in CSIT environment ver. 4 and compared +against each other. All substantial progressions has been marked up with +RCA analysis. See Current vs Previous Release and Known Issues. + +CSIT environment ver. 4 has been evaluated against the ver. 2 by +benchmarking VPP v20.01.0 in both environment versions. + Physical Testbeds ----------------- @@ -15,8 +56,8 @@ topology types are used: server as TG both connected in ring topology. Tested SUT servers are based on a range of processors including Intel -Xeon Haswell-SP, Intel Xeon Skylake-SP, Intel Xeon Cascade Lake-SP, Arm, Intel -Atom. More detailed description is provided in +Xeon Haswell-SP, Intel Xeon Skylake-SP, Intel Xeon Cascade Lake-SP, Arm, +Intel Atom. More detailed description is provided in :ref:`tested_physical_topologies`. Tested logical topologies are described in :ref:`tested_logical_topologies`. diff --git a/docs/report/vpp_performance_tests/test_environment.rst b/docs/report/vpp_performance_tests/test_environment.rst index 173a51b968..2d71148b57 100644 --- a/docs/report/vpp_performance_tests/test_environment.rst +++ b/docs/report/vpp_performance_tests/test_environment.rst @@ -5,46 +5,6 @@ .. _vpp_test_environment: -Versioning ----------- - -In order to determine any benchmark anomalies (progressions, -regressions) between releases of a specific data-plane DUT application -(e.g. VPP, DPDK), the DUT needs to be tested in the same test -environment, to avoid test environment changes impacting the results and -clouding the picture. - -In order to enable test system evolution, a mirror scheme is required to -determine benchmarking anomalies between releases of specific test -system like CSIT. This is achieved by testing the same DUT application -version between releases of CSIT test system. - -CSIT test environment versioning scheme ensures integrity of all the -test system components, including their HW revisions, compiled SW code -versions and SW source code, within a specific CSIT version. Components -included in the CSIT environment versioning include: - -- Server hosts hardware firmware and BIOS (motherboard, processsor, NIC(s), accelerator card(s)). -- Server host Linux operating system versions. -- Server host Linux configuration. -- TRex Traffic Generator version, drivers and configuration. -- CSIT framework code. - -Following is the list of CSIT versions to date: - -- Ver. 1 associated with CSIT rls1908 git branch as of 2019-08-21. -- Ver. 2 associated with CSIT rls2001 git branch as of 2020-03-27. -- Ver. 3 interim associated with master branch as of 2020-xx-xx. -- Ver. 4 associated with CSIT rls2005 git branch as of 2020-06-24. - -To identify performance changes due to VPP code changes from v20.01.0 to -v20.05.0, both have been tested in CSIT environment ver. 4 and compared -against each other. All substantial progressions has been marked up with -RCA analysis. See Current vs Previous Release and Known Issues. - -CSIT environment ver. 4 has been evaluated against the ver. 2 by -benchmarking VPP v20.01.0 in both environrment versions. - .. include:: ../introduction/test_environment_intro.rst .. include:: ../introduction/test_environment_sut_conf_1.rst |