aboutsummaryrefslogtreecommitdiffstats
path: root/docs/report/introduction/test_environment_intro.rst
diff options
context:
space:
mode:
authorMaciek Konstantynowicz <mkonstan@cisco.com>2018-08-13 21:17:10 +0100
committerMaciek Konstantynowicz <mkonstan@cisco.com>2018-08-14 14:05:27 +0000
commita10b66185698e80a5e29a07ee08a2b526d7d6a65 (patch)
tree7c748ee0ac4a2fa90b6e23c18e6eecb6f90e96b5 /docs/report/introduction/test_environment_intro.rst
parentce0301d868e6a03353a966bb402d75e0d556a0cc (diff)
1807 report: added HW calibration sections to test_environment plus editing nits.
Change-Id: I66698ae70d1bbbde6992e5663bc64c30249f7f79 Signed-off-by: Maciek Konstantynowicz <mkonstan@cisco.com> (cherry picked from commit 25a40550e90c036dddf17698103a9a3c34ff6799)
Diffstat (limited to 'docs/report/introduction/test_environment_intro.rst')
-rw-r--r--docs/report/introduction/test_environment_intro.rst72
1 files changed, 59 insertions, 13 deletions
diff --git a/docs/report/introduction/test_environment_intro.rst b/docs/report/introduction/test_environment_intro.rst
index d80ecdffe0..19dac90b96 100644
--- a/docs/report/introduction/test_environment_intro.rst
+++ b/docs/report/introduction/test_environment_intro.rst
@@ -3,16 +3,62 @@
Test Environment
================
-CSIT performance tests are executed on physical testbeds hosted by
-:abbr:`LF (Linux Foundation)` for FD.io project. Each testbed consists of
-either one (2-node) or two (3-node) servers acting as Systems Under Test (SUT)
-and one server acting as Traffic Generator (TG).
-
-Server Specification and Configuration
---------------------------------------
-
-Complete specification and configuration of compute servers used in CSIT
-physical testbeds is maintained on wiki page `CSIT testbed - Server HW
-Configuration (Haswell) <https://wiki.fd.io/view/CSIT/CSIT_LF_testbed>`_ and
-`CSIT testbed - Server HW Configuration (Skylake/ARM)
-<https://wiki.fd.io/view/CSIT/fdio_csit_lab_ext_lld_draft>`_.
+Physical Testbeds
+-----------------
+
+FD.io CSIT performance tests are executed in physical testbeds hosted by
+:abbr:`LF (Linux Foundation)` for FD.io project.
+
+Two physical testbed topology types are used:
+
+- **3-Node Topology**: Consisting of two servers acting as SUTs
+ (Systems Under Test) and one server as TG (Traffic Generator), all
+ connected in ring topology.
+- **2-Node Topology**: Consisting of one server acting as SUTs and one
+ 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, Arm, Intel Atom. More detailed
+description is provided in
+:ref:`tested_physical_topologies`.
+
+Tested logical topologies are described in
+:ref:`tested_logical_topologies`.
+
+Server Specifications
+---------------------
+
+Complete technical specifications of compute servers used in CSIT
+physical testbeds are maintained on FD.io wiki pages: `CSIT/Testbeds:
+Xeon Hsw, VIRL
+<https://wiki.fd.io/view/CSIT/Testbeds:_Xeon_Hsw,_VIRL.#FD.io_CSIT_testbeds_-_Xeon_Haswell.2C_VIRL>`_
+and `CSIT Testbeds: Xeon Skx, Arm, Atom
+<https://wiki.fd.io/view/CSIT/Testbeds:_Xeon_Skx,_Arm,_Atom.#Server_Specification>`_.
+
+Pre-Test Server Calibration
+---------------------------
+
+Number of SUT server sub-system runtime parameters have been identified
+as impacting data plane performance tests. Calibrating those parameters
+is part of FD.io CSIT pre-test activities, and includes measuring and
+reporting following:
+
+#. System level core jitter – measure duration of core interrupts by
+ Linux in clock cycles and how often interrupts happen. Using
+ `CPU core jitter tool <https://git.fd.io/pma_tools/tree/jitter>`_.
+
+#. Memory bandwidth – measure bandwidth with `Intel MLC tool
+ <https://software.intel.com/en-us/articles/intelr-memory-latency-checker>`_.
+
+#. Memory latency – measure memory latency with Intel MLC tool.
+
+#. Cache latency at all levels (L1, L2, and Last Level Cache) – measure
+ cache latency with Intel MLC tool.
+
+Measured values of listed parameters are especially important for
+repeatable zero packet loss throughput measurements across multiple
+system instances. Generally they come useful as a background data for
+comparing data plane performance results across disparate servers.
+
+Following sections include measured calibration data for Intel Xeon
+Haswell and Intel Xeon Skylake testbeds.