aboutsummaryrefslogtreecommitdiffstats
path: root/docs/report
diff options
context:
space:
mode:
authorVratko Polak <vrpolak@cisco.com>2019-05-16 10:43:31 +0200
committerVratko Polak <vrpolak@cisco.com>2019-05-16 10:49:12 +0200
commit9a6b6ed77705147032abee3fc98a2f7d370427c0 (patch)
tree97e9922d47b774951a162d8dbdd156d89718f4d2 /docs/report
parentb659ab3d2638652de0357d29be1ec7704df97555 (diff)
Improve soak graphs and content
+ Fix duration, mention number of tests and runs. - Hover information still feels wrong. + Mention "critical rate" instead of "throughput" where possible. + Mention lower bounds are displayed. + Rename "plrsearch_algorithm" label to "PLRsearch". + Because the previous link did not work. Due to underscore? + Rename "SOAK" to "soak" or "Soak" (except when it is a tag). Change-Id: I9c079f8c2e93d96249d4b60893469c9257d4f3db Signed-off-by: Vratko Polak <vrpolak@cisco.com>
Diffstat (limited to 'docs/report')
-rw-r--r--docs/report/introduction/methodology_data_plane_throughput/methodology_plrsearch.rst2
-rw-r--r--docs/report/vpp_performance_tests/soak_tests/index.rst10
2 files changed, 7 insertions, 5 deletions
diff --git a/docs/report/introduction/methodology_data_plane_throughput/methodology_plrsearch.rst b/docs/report/introduction/methodology_data_plane_throughput/methodology_plrsearch.rst
index 4aa1019b4c..88e6f901c8 100644
--- a/docs/report/introduction/methodology_data_plane_throughput/methodology_plrsearch.rst
+++ b/docs/report/introduction/methodology_data_plane_throughput/methodology_plrsearch.rst
@@ -1,4 +1,4 @@
-.. _plrsearch_algorithm:
+.. _PLRsearch:
PLRsearch
^^^^^^^^^
diff --git a/docs/report/vpp_performance_tests/soak_tests/index.rst b/docs/report/vpp_performance_tests/soak_tests/index.rst
index bc236c0298..faa4675418 100644
--- a/docs/report/vpp_performance_tests/soak_tests/index.rst
+++ b/docs/report/vpp_performance_tests/soak_tests/index.rst
@@ -33,7 +33,9 @@
Soak Tests
==========
-Long duration soak tests are executed using `plrsearch_algorithm`_.
+Long duration (2 hours per test) soak tests are executed
+using `PLRsearch`_ algorithm. As the test take long time, only 10 test
+were executed, two runs each.
Additional information about graph data:
@@ -41,18 +43,18 @@ Additional information about graph data:
#. **X-axis Labels**: indices of test suites.
-#. **Y-axis Labels**: estimated intervals for packet throughput value in [Mpps].
+#. **Y-axis Labels**: estimated lower bounds for critical rate value in [Mpps].
#. **Graph Legend**: list of X-axis indices with CSIT test suites.
-#. **Hover Information**: lists minimum, first quartile, median,
+#. **Hover Information**: in general lists minimum, first quartile, median,
third quartile, and maximum. If either type of outlier is present the
whisker on the appropriate side is taken to 1.5×IQR from the quartile
(the "inner fence") rather than the max or min, and individual outlying
data points are displayed as unfilled circles (for suspected outliers)
or filled circles (for outliers). (The "outer fence" is 3×IQR from the
quartile.)
- It also lists the lower bounds for the estimated throughput value.
+ When number of samples is low, some values are not displayed.
.. note::