diff options
22 files changed, 1836 insertions, 154 deletions
diff --git a/docs/cpta/index.rst b/docs/cpta/index.rst new file mode 100644 index 0000000000..dcefef7f08 --- /dev/null +++ b/docs/cpta/index.rst @@ -0,0 +1,8 @@ +Continuous Performance Trending and Analysis +============================================ + +.. toctree:: + :numbered: + + introduction/index + trending/index diff --git a/docs/cpta/introduction/index.rst b/docs/cpta/introduction/index.rst new file mode 100644 index 0000000000..aad683b390 --- /dev/null +++ b/docs/cpta/introduction/index.rst @@ -0,0 +1,182 @@ +Introduction +============ + +Purpose +------- + +With increasing number of features and code changes in the FD.io VPP data plane +codebase, it is increasingly difficult to measure and detect VPP data plane +performance changes. Similarly, once degradation is detected, it is getting +harder to bisect the source code in search of the Bad code change or addition. +The problem is further escalated by a large combination of compute platforms +that VPP is running and used on, including Intel Xeon, Intel Atom, ARM Aarch64. + +Existing FD.io CSIT continuous performance trending test jobs help, but they +rely on human factors for anomaly detection, and as such are error prone and +unreliable, as the volume of data generated by these jobs is growing +exponentially. + +Proposed solution is to eliminate human factor and fully automate performance +trending, regression and progression detection, as well as bisecting. + +This document describes a high-level design of a system for continuous +measuring, trending and performance change detection for FD.io VPP SW data +plane. It builds upon the existing CSIT framework with extensions to its +throughput testing methodology, CSIT data analytics engine +(PAL – Presentation-and-Analytics-Layer) and associated Jenkins jobs +definitions. + +Continuous Performance Trending and Analysis +-------------------------------------------- + +Proposed design replaces existing CSIT performance trending jobs and tests with +new Performance Trending (PT) CSIT module and separate Performance Analysis (PA) +module ingesting results from PT and analysing, detecting and reporting any +performance anomalies using historical trending data and statistical metrics. +PA does also produce trending graphs with summary and drill-down views across +all specified tests that can be reviewed and inspected regularly by FD.io +developers and users community. + +Trend Analysis +`````````````` + +All measured performance trend data is treated as time-series data that can be +modelled using normal distribution. After trimming the outliers, the average and +deviations from average are used for detecting performance change anomalies +following the three-sigma rule of thumb (a.k.a. 68-95-99.7 rule). + +Analysis Metrics +```````````````` + +Following statistical metrics are proposed as performance trend indicators over +the rolling window of last <N> sets of historical measurement data: + + #. Quartiles Q1, Q2, Q3 – three points dividing a ranked set of data set + into four equal parts, Q2 is the median of the data. + #. Inter Quartile Range IQR=Q3-Q1 – measure of variability, used here to + eliminate outliers. + #. Outliers – extreme values that are at least 1.5*IQR below Q1, or at + least 1.5*IQR above Q3. + #. Trimmed Moving Average (TMA) – average across the data set of the rolling + window of <N> values without the outliers. Used here to calculate TMSD. + #. Trimmed Moving Standard Deviation (TMSD) – standard deviation over the + data set of the rolling window of <N> values without the outliers, + requires calculating TMA. Used here for anomaly detection. + #. Moving Median (MM) - median across the data set of the rolling window of + <N> values with all data points, including the outliers. Used here for + anomaly detection. + +Anomaly Detection +````````````````` + +Based on the assumption that all performance measurements can be modelled using +normal distribution, a three-sigma rule of thumb is proposed as the main +criteria for anomaly detection. + +Three-sigma rule of thumb, aka 68–95–99.7 rule, is a shorthand used to capture +the percentage of values that lie within a band around the average (mean) in a +normal distribution within a width of two, four and six standard deviations. +More accurately 68.27%, 95.45% and 99.73% of the result values should lie within +one, two or three standard deviations of the mean, see figure below. + +To verify compliance of test result with value X against defined trend analysis +metric and detect anomalies, three simple evaluation criteria are proposed: + +:: + + Test Result Evaluation Reported Result Reported Reason Trending Graph Markers + ========================================================================================== + Normal Pass Normal Part of plot line + Regression Fail Regression Red circle + Progression Pass Progression Green circle + +Jenkins job cumulative results: + + #. Pass - if all detection results are Pass or Warning. + #. Fail - if any detection result is Fail. + +Performance Trending (PT) +````````````````````````` + +CSIT PT runs regular performance test jobs finding MRR, PDR and NDR per test +cases. PT is designed as follows: + + #. PT job triggers: + + #. Periodic e.g. daily. + #. On-demand gerrit triggered. + #. Other periodic TBD. + + #. Measurements and calculations per test case: + + #. MRR Max Received Rate + + #. Measured: Unlimited tolerance of packet loss. + #. Send packets at link rate, count total received packets, divide + by test trial period. + + #. Optimized binary search bounds for PDR and NDR tests: + + #. Calculated: High and low bounds for binary search based on MRR + and pre-defined Packet Loss Ratio (PLR). + #. HighBound=MRR, LowBound=to-be-determined. + #. PLR – acceptable loss ratio for PDR tests, currently set to 0.5% + for all performance tests. + + #. PDR and NDR: + + #. Run binary search within the calculated bounds, find PDR and NDR. + #. Measured: PDR Partial Drop Rate – limited non-zero tolerance of + packet loss. + #. Measured: NDR Non Drop Rate - zero packet loss. + + #. Archive MRR, PDR and NDR per test case. + #. Archive counters collected at MRR, PDR and NDR. + +Performance Analysis (PA) +````````````````````````` + +CSIT PA runs performance analysis, change detection and trending using specified +trend analysis metrics over the rolling window of last <N> sets of historical +measurement data. PA is defined as follows: + + #. PA job triggers: + + #. By PT job at its completion. + #. On-demand gerrit triggered. + #. Other periodic TBD. + + #. Download and parse archived historical data and the new data: + + #. New data from latest PT job is evaluated against the rolling window + of <N> sets of historical data. + #. Download RF output.xml files and compressed archived data. + #. Parse out the data filtering test cases listed in PA specification + (part of CSIT PAL specification file). + + #. Calculate trend metrics for the rolling window of <N> sets of historical data: + + #. Calculate quartiles Q1, Q2, Q3. + #. Trim outliers using IQR. + #. Calculate TMA and TMSD. + #. Calculate normal trending range per test case based on TMA and TMSD. + + #. Evaluate new test data against trend metrics: + + #. If within the range of (TMA +/- 3*TMSD) => Result = Pass, + Reason = Normal. + #. If below the range => Result = Fail, Reason = Regression. + #. If above the range => Result = Pass, Reason = Progression. + + #. Generate and publish results + + #. Relay evaluation result to job result. + #. Generate a new set of trend analysis summary graphs and drill-down + graphs. + + #. Summary graphs to include measured values with Normal, + Progression and Regression markers. MM shown in the background if + possible. + #. Drill-down graphs to include MM, TMA and TMSD. + + #. Publish trend analysis graphs in html format. diff --git a/docs/cpta/trending/container_memif.rst b/docs/cpta/trending/container_memif.rst new file mode 100644 index 0000000000..5d145aa0f0 --- /dev/null +++ b/docs/cpta/trending/container_memif.rst @@ -0,0 +1,80 @@ +Container memif Connections +=========================== + +NIC 10ge2p1x520 +--------------- + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-container-memif-l2-1t1c-x520-1.html"></iframe> + +*Figure 1. Daily trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-container-memif-l2-1t1c-x520-5.html"></iframe> + +*Figure 2. Weekly trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-container-memif-l2-1t1c-x520-30.html"></iframe> + +*Figure 3. Monthly trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-container-memif-l2-2t2c-x520-1.html"></iframe> + +*Figure 4. Daily trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-container-memif-l2-2t2c-x520-5.html"></iframe> + +*Figure 5. Weekly trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-container-memif-l2-2t2c-x520-30.html"></iframe> + +*Figure 6. Monthly trend.* + +NIC 40ge2p1xl710 +---------------- + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-container-memif-l2-1t1c-xl710-1.html"></iframe> + +*Figure 1. Daily trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-container-memif-l2-1t1c-xl710-5.html"></iframe> + +*Figure 2. Weekly trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-container-memif-l2-1t1c-xl710-30.html"></iframe> + +*Figure 3. Monthly trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-container-memif-l2-2t2c-xl710-1.html"></iframe> + +*Figure 4. Daily trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-container-memif-l2-2t2c-xl710-5.html"></iframe> + +*Figure 5. Weekly trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-container-memif-l2-2t2c-xl710-30.html"></iframe> + +*Figure 6. Monthly trend.*
\ No newline at end of file diff --git a/docs/cpta/trending/index.rst b/docs/cpta/trending/index.rst new file mode 100644 index 0000000000..0dd9cf66a5 --- /dev/null +++ b/docs/cpta/trending/index.rst @@ -0,0 +1,10 @@ +VPP Performance Trend +===================== + +.. toctree:: + + l2 + ip4 + ip6 + container_memif + vm_vhost diff --git a/docs/cpta/trending/ip4.rst b/docs/cpta/trending/ip4.rst new file mode 100644 index 0000000000..a84f362b5d --- /dev/null +++ b/docs/cpta/trending/ip4.rst @@ -0,0 +1,20 @@ +IPv4 Routed-Forwarding +====================== + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-ip4-1.html"></iframe> + +*Figure 1. Daily trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-ip4-5.html"></iframe> + +*Figure 2. Weekly trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-ip4-30.html"></iframe> + +*Figure 3. Monthly trend.* diff --git a/docs/cpta/trending/ip6.rst b/docs/cpta/trending/ip6.rst new file mode 100644 index 0000000000..a2b5afdfd7 --- /dev/null +++ b/docs/cpta/trending/ip6.rst @@ -0,0 +1,20 @@ +IPv6 Routed-Forwarding +====================== + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-ip6-1.html"></iframe> + +*Figure 1. Daily trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-ip6-5.html"></iframe> + +*Figure 2. Weekly trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-ip6-30.html"></iframe> + +*Figure 3. Monthly trend.* diff --git a/docs/cpta/trending/l2.rst b/docs/cpta/trending/l2.rst new file mode 100644 index 0000000000..8a51270ba5 --- /dev/null +++ b/docs/cpta/trending/l2.rst @@ -0,0 +1,20 @@ +L2 Ethernet Switching +===================== + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-l2-1.html"></iframe> + +*Figure 1. Daily trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-l2-5.html"></iframe> + +*Figure 2. Weekly trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-l2-30.html"></iframe> + +*Figure 3. Monthly trend.* diff --git a/docs/cpta/trending/vm_vhost.rst b/docs/cpta/trending/vm_vhost.rst new file mode 100644 index 0000000000..6b464cc3cb --- /dev/null +++ b/docs/cpta/trending/vm_vhost.rst @@ -0,0 +1,116 @@ +VM vhost Connections +==================== + +NIC 10ge2p1x520 +--------------- + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-vm-vhost-ethip4-1t1c-x520-1.html"></iframe> + +*Figure 1. Daily trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-vm-vhost-ethip4-1t1c-x520-5.html"></iframe> + +*Figure 2. Weekly trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-vm-vhost-ethip4-1t1c-x520-30.html"></iframe> + +*Figure 3. Monthly trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-vm-vhost-ethip4-2t2c-x520-1.html"></iframe> + +*Figure 4. Daily trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-vm-vhost-ethip4-2t2c-x520-5.html"></iframe> + +*Figure 5. Weekly trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-vm-vhost-ethip4-2t2c-x520-30.html"></iframe> + +*Figure 6. Monthly trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-vm-vhost-eth-1t1c-x520-1.html"></iframe> + +*Figure 7. Daily trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-vm-vhost-eth-1t1c-x520-5.html"></iframe> + +*Figure 8. Weekly trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-vm-vhost-eth-1t1c-x520-30.html"></iframe> + +*Figure 9. Monthly trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-vm-vhost-eth-2t2c-x520-1.html"></iframe> + +*Figure 10. Daily trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-vm-vhost-eth-2t2c-x520-5.html"></iframe> + +*Figure 11. Weekly trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-vm-vhost-eth-2t2c-x520-30.html"></iframe> + +*Figure 12. Monthly trend.* + +NIC 40ge2p1xl710 +---------------- + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-vm-vhost-eth-1t1c-xl710-1.html"></iframe> + +*Figure 1. Daily trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-vm-vhost-eth-1t1c-xl710-5.html"></iframe> + +*Figure 2. Weekly trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-vm-vhost-eth-1t1c-xl710-30.html"></iframe> + +*Figure 3. Monthly trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-vm-vhost-eth-2t2c-xl710-1.html"></iframe> + +*Figure 4. Daily trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-vm-vhost-eth-2t2c-xl710-5.html"></iframe> + +*Figure 5. Weekly trend.* + +.. raw:: html + + <iframe width="1100" height="800" frameborder="0" scrolling="no" src="../_static/vpp/cpta-vm-vhost-eth-2t2c-xl710-30.html"></iframe> + +*Figure 6. Monthly trend.* diff --git a/resources/tools/presentation/conf_cpta/conf.py b/resources/tools/presentation/conf_cpta/conf.py new file mode 100644 index 0000000000..9b6e5f3bc1 --- /dev/null +++ b/resources/tools/presentation/conf_cpta/conf.py @@ -0,0 +1,103 @@ +# -*- coding: utf-8 -*- +# +# CSIT report documentation build configuration file +# +# This file is execfile()d with the current directory set to its +# containing dir. +# +# Note that not all possible configuration values are present in this +# autogenerated file. +# +# All configuration values have a default; values that are commented out +# serve to show the default. + +# If extensions (or modules to document with autodoc) are in another directory, +# add these directories to sys.path here. If the directory is relative to the +# documentation root, use os.path.abspath to make it absolute, like shown here. +# +import os +import sys + +sys.path.insert(0, os.path.abspath('.')) + +# -- General configuration ------------------------------------------------ + +# If your documentation needs a minimal Sphinx version, state it here. +# +# needs_sphinx = '1.0' + +# Add any Sphinx extension module names here, as strings. They can be +# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom +# ones. +extensions = ['sphinxcontrib.programoutput', + 'sphinx.ext.ifconfig'] + +# Add any paths that contain templates here, relative to this directory. +templates_path = ['_templates'] + +# The suffix(es) of source filenames. +# You can specify multiple suffix as a list of string: +# +source_suffix = ['.rst', '.md'] + +# The master toctree document. +master_doc = 'index' + +# General information about the project. +project = u'FD.io CSIT' +copyright = u'2018, FD.io' +author = u'FD.io CSIT' + +# The version info for the project you're documenting, acts as replacement for +# |version| and |release|, also used in various other places throughout the +# built documents. +# +# The short X.Y version. +#version = u'' +# The full version, including alpha/beta/rc tags. +#release = u'' + +# The language for content autogenerated by Sphinx. Refer to documentation +# for a list of supported languages. +# +# This is also used if you do content translation via gettext catalogs. +# Usually you set "language" from the command line for these cases. +language = 'en' + +# List of patterns, relative to source directory, that match files and +# directories to ignore when looking for source files. +# This patterns also effect to html_static_path and html_extra_path +exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store'] + +# The name of the Pygments (syntax highlighting) style to use. +pygments_style = 'sphinx' + +# If true, `todo` and `todoList` produce output, else they produce nothing. +todo_include_todos = False + +# -- Options for HTML output ---------------------------------------------- + +# The theme to use for HTML and HTML Help pages. See the documentation for +# a list of builtin themes. +# +html_theme = 'sphinx_rtd_theme' + +# Theme options are theme-specific and customize the look and feel of a theme +# further. For a list of options available for each theme, see the +# documentation. +# +# html_theme_options = {} + +# Add any paths that contain custom static files (such as style sheets) here, +# relative to this directory. They are copied after the builtin static files, +# so a file named "default.css" will overwrite the builtin "default.css". +html_theme_path = ['env/lib/python2.7/site-packages/sphinx_rtd_theme'] + +# html_static_path = ['_build/_static'] +html_static_path = ['../_tmp/src/_static'] + +html_context = { + 'css_files': [ + '_static/theme_overrides.css', # overrides for wide tables in RTD theme + ], + } diff --git a/resources/tools/presentation/doc/pal_lld.rst b/resources/tools/presentation/doc/pal_lld.rst index 7ca3ad43d5..2e119fad82 100644 --- a/resources/tools/presentation/doc/pal_lld.rst +++ b/resources/tools/presentation/doc/pal_lld.rst @@ -1368,6 +1368,46 @@ of an element is required, only a new algorithm needs to be implemented and integrated. +Continuous Performance Measurements and Trending +------------------------------------------------ + +Performance analysis and trending execution sequence: +````````````````````````````````````````````````````` + +1. Triggered at completion of Performance Measurements and Archiving (PMA) job. + + a. Periodic, or gerrit triggers are supported too. + +2. Download RF output.xml from triggering CPM job. +3. Parse out the test results listed in PAL specification file. +4. Reads specified amount of PMA historical data from Nexus. +5. Calculate specified statistical metrics – see next section. +6. Evaluate latest results against the historical metrics, quantify relative + change and based on defined criteria set the result to Pass (no-change or + progression) or Fail (regression). +7. Add the new data to historical data. +8. Generate a new set of trend analysis summary and drill-down graphs. +9. Archive the latest RF output.xml to nexus for future analysis. +10. Publish trend analysis graphs in html format on https://docs.fd.io/. + +Parameters to specify: +`````````````````````` + +- job to be monitored - the Jenkins job which results are used as input data for + this test; +- number of builds used for trending plot(s) - specified by an integer greater + than zero, or zero for all available builds; +- tests we are interested in (list) list of tests which results are used for the + test; +- window size for the moving average. + +*Example:* + +:: + + TODO + + API --- diff --git a/resources/tools/presentation/generator_CPTA.py b/resources/tools/presentation/generator_CPTA.py new file mode 100644 index 0000000000..c1b14f1f55 --- /dev/null +++ b/resources/tools/presentation/generator_CPTA.py @@ -0,0 +1,429 @@ +# Copyright (c) 2018 Cisco and/or its affiliates. +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at: +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +"""Generation of Continuous Performance Trending and Analysis. +""" + +import datetime +import logging +import plotly.offline as ploff +import plotly.graph_objs as plgo +import numpy as np +import pandas as pd + +from collections import OrderedDict +from utils import find_outliers, archive_input_data, execute_command + + +# Command to build the html format of the report +HTML_BUILDER = 'sphinx-build -v -c conf_cpta -a ' \ + '-b html -E ' \ + '-t html ' \ + '{working_dir} ' \ + '{build_dir}/' + +# .css file for the html format of the report +THEME_OVERRIDES = """/* override table width restrictions */ +.wy-nav-content { + max-width: 1200px !important; +} +""" + +COLORS = ["SkyBlue", "Olive", "Purple", "Coral", "Indigo", "Pink", + "Chocolate", "Brown", "Magenta", "Cyan", "Orange", "Black", + "Violet", "Blue", "Yellow"] + + +def generate_cpta(spec, data): + """Generate all formats and versions of the Continuous Performance Trending + and Analysis. + + :param spec: Specification read from the specification file. + :param data: Full data set. + :type spec: Specification + :type data: InputData + """ + + logging.info("Generating the Continuous Performance Trending and Analysis " + "...") + + ret_code = _generate_all_charts(spec, data) + + cmd = HTML_BUILDER.format( + date=datetime.date.today().strftime('%d-%b-%Y'), + working_dir=spec.environment["paths"]["DIR[WORKING,SRC]"], + build_dir=spec.environment["paths"]["DIR[BUILD,HTML]"]) + execute_command(cmd) + + with open(spec.environment["paths"]["DIR[CSS_PATCH_FILE]"], "w") as \ + css_file: + css_file.write(THEME_OVERRIDES) + + with open(spec.environment["paths"]["DIR[CSS_PATCH_FILE2]"], "w") as \ + css_file: + css_file.write(THEME_OVERRIDES) + + archive_input_data(spec) + + logging.info("Done.") + + return ret_code + + +def _select_data(in_data, period, fill_missing=False, use_first=False): + """Select the data from the full data set. The selection is done by picking + the samples depending on the period: period = 1: All, period = 2: every + second sample, period = 3: every third sample ... + + :param in_data: Full set of data. + :param period: Sampling period. + :param fill_missing: If the chosen sample is missing in the full set, its + nearest neighbour is used. + :param use_first: Use the first sample even though it is not chosen. + :type in_data: OrderedDict + :type period: int + :type fill_missing: bool + :type use_first: bool + :returns: Reduced data. + :rtype: OrderedDict + """ + + first_idx = min(in_data.keys()) + last_idx = max(in_data.keys()) + + idx = last_idx + data_dict = dict() + if use_first: + data_dict[first_idx] = in_data[first_idx] + while idx >= first_idx: + data = in_data.get(idx, None) + if data is None: + if fill_missing: + threshold = int(round(idx - period / 2)) + 1 - period % 2 + idx_low = first_idx if threshold < first_idx else threshold + threshold = int(round(idx + period / 2)) + idx_high = last_idx if threshold > last_idx else threshold + + flag_l = True + flag_h = True + idx_lst = list() + inc = 1 + while flag_l or flag_h: + if idx + inc > idx_high: + flag_h = False + else: + idx_lst.append(idx + inc) + if idx - inc < idx_low: + flag_l = False + else: + idx_lst.append(idx - inc) + inc += 1 + + for i in idx_lst: + if i in in_data.keys(): + data_dict[i] = in_data[i] + break + else: + data_dict[idx] = data + idx -= period + + return OrderedDict(sorted(data_dict.items(), key=lambda t: t[0])) + + +def _evaluate_results(in_data, trimmed_data, window=10): + """Evaluates if the sample value is regress, normal or progress compared to + previous data within the window. + We use the intervals defined as: + - regress: less than median - 3 * stdev + - normal: between median - 3 * stdev and median + 3 * stdev + - progress: more than median + 3 * stdev + + :param in_data: Full data set. + :param trimmed_data: Full data set without the outliers. + :param window: Window size used to calculate moving median and moving stdev. + :type in_data: pandas.Series + :type trimmed_data: pandas.Series + :type window: int + :returns: Evaluated results. + :rtype: list + """ + + if len(in_data) > 2: + win_size = in_data.size if in_data.size < window else window + results = [0.0, ] * win_size + median = in_data.rolling(window=win_size).median() + stdev_t = trimmed_data.rolling(window=win_size, min_periods=2).std() + m_vals = median.values + s_vals = stdev_t.values + d_vals = in_data.values + for day in range(win_size, in_data.size): + if np.isnan(m_vals[day - 1]) or np.isnan(s_vals[day - 1]): + results.append(0.0) + elif d_vals[day] < (m_vals[day - 1] - 3 * s_vals[day - 1]): + results.append(0.33) + elif (m_vals[day - 1] - 3 * s_vals[day - 1]) <= d_vals[day] <= \ + (m_vals[day - 1] + 3 * s_vals[day - 1]): + results.append(0.66) + else: + results.append(1.0) + else: + results = [0.0, ] + try: + median = np.median(in_data) + stdev = np.std(in_data) + if in_data.values[-1] < (median - 3 * stdev): + results.append(0.33) + elif (median - 3 * stdev) <= in_data.values[-1] <= ( + median + 3 * stdev): + results.append(0.66) + else: + results.append(1.0) + except TypeError: + results.append(None) + return results + + +def _generate_trending_traces(in_data, period, moving_win_size=10, + fill_missing=True, use_first=False, + show_moving_median=True, name="", color=""): + """Generate the trending traces: + - samples, + - moving median (trending plot) + - outliers, regress, progress + + :param in_data: Full data set. + :param period: Sampling period. + :param moving_win_size: Window size. + :param fill_missing: If the chosen sample is missing in the full set, its + nearest neighbour is used. + :param use_first: Use the first sample even though it is not chosen. + :param show_moving_median: Show moving median (trending plot). + :param name: Name of the plot + :param color: Name of the color for the plot. + :type in_data: OrderedDict + :type period: int + :type moving_win_size: int + :type fill_missing: bool + :type use_first: bool + :type show_moving_median: bool + :type name: str + :type color: str + :returns: Generated traces (list) and the evaluated result (float). + :rtype: tuple(traces, result) + """ + + if period > 1: + in_data = _select_data(in_data, period, + fill_missing=fill_missing, + use_first=use_first) + + data_x = [key for key in in_data.keys()] + data_y = [val for val in in_data.values()] + data_pd = pd.Series(data_y, index=data_x) + + t_data, outliers = find_outliers(data_pd) + + results = _evaluate_results(data_pd, t_data, window=moving_win_size) + + anomalies = pd.Series() + anomalies_res = list() + for idx, item in enumerate(in_data.items()): + item_pd = pd.Series([item[1], ], index=[item[0], ]) + if item[0] in outliers.keys(): + anomalies = anomalies.append(item_pd) + anomalies_res.append(0.0) + elif results[idx] in (0.33, 1.0): + anomalies = anomalies.append(item_pd) + anomalies_res.append(results[idx]) + anomalies_res.extend([0.0, 0.33, 0.66, 1.0]) + + # Create traces + color_scale = [[0.00, "grey"], + [0.25, "grey"], + [0.25, "red"], + [0.50, "red"], + [0.50, "white"], + [0.75, "white"], + [0.75, "green"], + [1.00, "green"]] + + trace_samples = plgo.Scatter( + x=data_x, + y=data_y, + mode='markers', + line={ + "width": 1 + }, + name="{name}-thput".format(name=name), + marker={ + "size": 5, + "color": color, + "symbol": "circle", + }, + ) + traces = [trace_samples, ] + + trace_anomalies = plgo.Scatter( + x=anomalies.keys(), + y=anomalies.values, + mode='markers', + hoverinfo="none", + showlegend=False, + legendgroup=name, + name="{name}: outliers".format(name=name), + marker={ + "size": 15, + "symbol": "circle-open", + "color": anomalies_res, + "colorscale": color_scale, + "showscale": True, + + "colorbar": { + "y": 0.5, + "len": 0.8, + "title": "Results Clasification", + "titleside": 'right', + "titlefont": { + "size": 14 + }, + "tickmode": 'array', + "tickvals": [0.125, 0.375, 0.625, 0.875], + "ticktext": ["Outlier", "Regress", "Normal", "Progress"], + "ticks": 'outside', + "ticklen": 0, + "tickangle": -90, + "thickness": 10 + } + } + ) + traces.append(trace_anomalies) + + if show_moving_median: + data_mean_y = pd.Series(data_y).rolling( + window=moving_win_size).median() + trace_median = plgo.Scatter( + x=data_x, + y=data_mean_y, + mode='lines', + line={ + "shape": "spline", + "width": 1, + "color": color, + }, + name='{name}-trend'.format(name=name, size=moving_win_size) + ) + traces.append(trace_median) + + return traces, results[-1] + + +def _generate_chart(traces, layout, file_name): + """Generates the whole chart using pre-generated traces. + + :param traces: Traces for the chart. + :param layout: Layout of the chart. + :param file_name: File name for the generated chart. + :type traces: list + :type layout: dict + :type file_name: str + """ + + # Create plot + logging.info(" Writing the file '{0}' ...".format(file_name)) + plpl = plgo.Figure(data=traces, layout=layout) + ploff.plot(plpl, show_link=False, auto_open=False, filename=file_name) + + +def _generate_all_charts(spec, input_data): + """Generate all charts specified in the specification file. + + :param spec: Specification. + :param input_data: Full data set. + :type spec: Specification + :type input_data: InputData + """ + + results = list() + for chart in spec.cpta["plots"]: + logging.info(" Generating the chart '{0}' ...". + format(chart.get("title", ""))) + + # Transform the data + data = input_data.filter_data(chart, continue_on_error=True) + if data is None: + logging.error("No data.") + return + + chart_data = dict() + for job in data: + for idx, build in job.items(): + for test in build: + if chart_data.get(test["name"], None) is None: + chart_data[test["name"]] = OrderedDict() + try: + chart_data[test["name"]][int(idx)] = \ + test["result"]["throughput"] + except (KeyError, TypeError): + chart_data[test["name"]][int(idx)] = None + + for period in chart["periods"]: + # Generate traces: + traces = list() + win_size = 10 if period == 1 else 5 if period < 20 else 3 + idx = 0 + for test_name, test_data in chart_data.items(): + if not test_data: + logging.warning("No data for the test '{0}'". + format(test_name)) + continue + trace, result = _generate_trending_traces( + test_data, + period=period, + moving_win_size=win_size, + fill_missing=True, + use_first=False, + name='-'.join(test_name.split('-')[3:-1]), + color=COLORS[idx]) + traces.extend(trace) + results.append(result) + idx += 1 + + # Generate the chart: + period_name = "Daily" if period == 1 else \ + "Weekly" if period < 20 else "Monthly" + chart["layout"]["title"] = chart["title"].format(period=period_name) + _generate_chart(traces, + chart["layout"], + file_name="{0}-{1}-{2}{3}".format( + spec.cpta["output-file"], + chart["output-file-name"], + period, + spec.cpta["output-file-type"])) + + logging.info(" Done.") + + result = "PASS" + for item in results: + if item is None: + result = "FAIL" + break + if item == 0.66 and result == "PASS": + result = "PASS" + elif item == 0.33 or item == 0.0: + result = "FAIL" + print(results) + print(result) + if result == "FAIL": + return 1 + else: + return 0 diff --git a/resources/tools/presentation/generator_plots.py b/resources/tools/presentation/generator_plots.py index ac77b3d425..b7fd420aa2 100644 --- a/resources/tools/presentation/generator_plots.py +++ b/resources/tools/presentation/generator_plots.py @@ -19,6 +19,7 @@ import logging import pandas as pd import plotly.offline as ploff import plotly.graph_objs as plgo + from plotly.exceptions import PlotlyError from utils import mean @@ -371,7 +372,6 @@ def plot_http_server_performance_box(plot, input_data): y=df[col], name=name, **plot["traces"])) - try: # Create plot plpl = plgo.Figure(data=traces, layout=plot["layout"]) diff --git a/resources/tools/presentation/generator_report.py b/resources/tools/presentation/generator_report.py index cf8a8d1675..55ac76bd1d 100644 --- a/resources/tools/presentation/generator_report.py +++ b/resources/tools/presentation/generator_report.py @@ -22,7 +22,7 @@ from os import makedirs, environ from os.path import isdir from shutil import copy, Error, make_archive -from utils import get_files +from utils import get_files, execute_command, archive_input_data from errors import PresentationError @@ -82,7 +82,7 @@ def generate_report(release, spec): "pdf": generate_pdf_report } - for report_format, versions in spec.output.items(): + for report_format, versions in spec.output["format"].items(): report[report_format](release, spec, versions) archive_input_data(spec) @@ -110,7 +110,7 @@ def generate_html_report(release, spec, versions): date=datetime.date.today().strftime('%d-%b-%Y'), working_dir=spec.environment["paths"]["DIR[WORKING,SRC]"], build_dir=spec.environment["paths"]["DIR[BUILD,HTML]"]) - _execute_command(cmd) + execute_command(cmd) with open(spec.environment["paths"]["DIR[CSS_PATCH_FILE]"], "w") as \ css_file: @@ -146,7 +146,7 @@ def generate_pdf_report(release, spec, versions): for plot in plots: file_name = "{0}".format(plot.rsplit(".", 1)[0]) cmd = convert_plots.format(html=plot, pdf=file_name) - _execute_command(cmd) + execute_command(cmd) # Generate the LaTeX documentation build_dir = spec.environment["paths"]["DIR[BUILD,LATEX]"] @@ -155,7 +155,7 @@ def generate_pdf_report(release, spec, versions): date=datetime.date.today().strftime('%d-%b-%Y'), working_dir=spec.environment["paths"]["DIR[WORKING,SRC]"], build_dir=build_dir) - _execute_command(cmd) + execute_command(cmd) # Build pdf documentation archive_dir = spec.environment["paths"]["DIR[STATIC,ARCH]"] @@ -174,7 +174,7 @@ def generate_pdf_report(release, spec, versions): ] for cmd in cmds: - _execute_command(cmd) + execute_command(cmd) logging.info(" Done.") @@ -193,64 +193,3 @@ def archive_report(spec): base_dir=spec.environment["paths"]["DIR[BUILD,HTML]"]) logging.info(" Done.") - - -def archive_input_data(spec): - """Archive the report. - - :param spec: Specification read from the specification file. - :type spec: Specification - :raises PresentationError: If it is not possible to archive the input data. - """ - - logging.info(" Archiving the input data files ...") - - if spec.is_debug: - extension = spec.debug["input-format"] - else: - extension = spec.input["file-format"] - data_files = get_files(spec.environment["paths"]["DIR[WORKING,DATA]"], - extension=extension) - dst = spec.environment["paths"]["DIR[STATIC,ARCH]"] - logging.info(" Destination: {0}".format(dst)) - - try: - if not isdir(dst): - makedirs(dst) - - for data_file in data_files: - logging.info(" Copying the file: {0} ...".format(data_file)) - copy(data_file, dst) - - except (Error, OSError) as err: - raise PresentationError("Not possible to archive the input data.", - str(err)) - - logging.info(" Done.") - - -def _execute_command(cmd): - """Execute the command in a subprocess and log the stdout and stderr. - - :param cmd: Command to execute. - :type cmd: str - :returns: Return code of the executed command. - :rtype: int - """ - - env = environ.copy() - proc = subprocess.Popen( - [cmd], - stdout=subprocess.PIPE, - stderr=subprocess.PIPE, - shell=True, - env=env) - - stdout, stderr = proc.communicate() - - logging.info(stdout) - logging.info(stderr) - - if proc.returncode != 0: - logging.error(" Command execution failed.") - return proc.returncode diff --git a/resources/tools/presentation/generator_tables.py b/resources/tools/presentation/generator_tables.py index 76254c86dd..f4fe1be174 100644 --- a/resources/tools/presentation/generator_tables.py +++ b/resources/tools/presentation/generator_tables.py @@ -22,7 +22,7 @@ import prettytable from string import replace from errors import PresentationError -from utils import mean, stdev, relative_change, remove_outliers +from utils import mean, stdev, relative_change def generate_tables(spec, data): diff --git a/resources/tools/presentation/input_data_files.py b/resources/tools/presentation/input_data_files.py index 7dae834b4d..7e19478570 100644 --- a/resources/tools/presentation/input_data_files.py +++ b/resources/tools/presentation/input_data_files.py @@ -16,13 +16,14 @@ Download all data. """ import re - +import gzip import logging from os import rename, remove from os.path import join, getsize from shutil import move from zipfile import ZipFile, is_zipfile, BadZipfile + from httplib import responses from requests import get, codes, RequestException, Timeout, TooManyRedirects, \ HTTPError, ConnectionError @@ -51,7 +52,13 @@ def download_data_files(spec): for job, builds in spec.builds.items(): for build in builds: if job.startswith("csit-"): - url = spec.environment["urls"]["URL[JENKINS,CSIT]"] + if spec.input["file-name"].endswith(".zip"): + url = spec.environment["urls"]["URL[JENKINS,CSIT]"] + elif spec.input["file-name"].endswith(".gz"): + url = spec.environment["urls"]["URL[NEXUS,LOG]"] + else: + logging.error("Not supported file format.") + continue elif job.startswith("hc2vpp-"): url = spec.environment["urls"]["URL[JENKINS,HC]"] else: @@ -106,25 +113,37 @@ def download_data_files(spec): file_handle.write(chunk) file_handle.close() - expected_length = None - try: - expected_length = int(response.headers["Content-Length"]) - logging.debug(" Expected file size: {0}B". - format(expected_length)) - except KeyError: - logging.debug(" No information about expected size.") - - real_length = getsize(new_name) - logging.debug(" Downloaded size: {0}B".format(real_length)) - - if expected_length: - if real_length == expected_length: + if spec.input["file-name"].endswith(".zip"): + expected_length = None + try: + expected_length = int(response. + headers["Content-Length"]) + logging.debug(" Expected file size: {0}B". + format(expected_length)) + except KeyError: + logging.debug(" No information about expected size.") + + real_length = getsize(new_name) + logging.debug(" Downloaded size: {0}B".format(real_length)) + + if expected_length: + if real_length == expected_length: + status = "downloaded" + logging.info("{0}: {1}".format(code, + responses[code])) + else: + logging.error("The file size differs from the " + "expected size.") + else: status = "downloaded" logging.info("{0}: {1}".format(code, responses[code])) - else: - logging.error("The file size differs from the expected " - "size.") - else: + + elif spec.input["file-name"].endswith(".gz"): + rename(new_name, new_name[:-7]) + with open(new_name[:-7], 'r') as xml_file: + with gzip.open(new_name, 'wb') as gz_file: + gz_file.write(xml_file.read()) + new_name = new_name[:-7] status = "downloaded" logging.info("{0}: {1}".format(code, responses[code])) @@ -185,29 +204,30 @@ def unzip_files(spec): directory = spec.environment["paths"]["DIR[WORKING,DATA]"] file_name = join(build["file-name"]) - if build["status"] == "downloaded" and is_zipfile(file_name): + if build["status"] == "downloaded": logging.info("Unziping: '{0}' from '{1}'.". format(data_file, file_name)) new_name = "{0}{1}{2}".format(file_name.rsplit('.')[-2], SEPARATOR, data_file.split("/")[-1]) try: - with ZipFile(file_name, 'r') as zip_file: - zip_file.extract(data_file, directory) - logging.info("Moving {0} to {1} ...". - format(join(directory, data_file), - directory)) - move(join(directory, data_file), directory) - logging.info("Renaming the file '{0}' to '{1}'". - format(join(directory, - data_file.split("/")[-1]), - new_name)) - rename(join(directory, data_file.split("/")[-1]), - new_name) + if is_zipfile(file_name): + with ZipFile(file_name, 'r') as zip_file: + zip_file.extract(data_file, directory) + logging.info("Moving {0} to {1} ...". + format(join(directory, data_file), + directory)) + move(join(directory, data_file), directory) + logging.info("Renaming the file '{0}' to '{1}'". + format(join(directory, + data_file.split("/")[-1]), + new_name)) + rename(join(directory, data_file.split("/")[-1]), + new_name) + spec.set_input_file_name(job, build["build"], + new_name) status = "unzipped" spec.set_input_state(job, build["build"], status) - spec.set_input_file_name(job, build["build"], - new_name) except (BadZipfile, RuntimeError) as err: logging.error("Failed to unzip the file '{0}': {1}.". format(file_name, str(err))) @@ -216,8 +236,7 @@ def unzip_files(spec): format(data_file, str(err))) finally: if status == "failed": - spec.set_input_file_name(job, build["build"], - None) + spec.set_input_file_name(job, build["build"], None) else: raise PresentationError("The file '{0}' does not exist or " "it is not a zip file". diff --git a/resources/tools/presentation/input_data_parser.py b/resources/tools/presentation/input_data_parser.py index 203a3bfd25..87d822f880 100644 --- a/resources/tools/presentation/input_data_parser.py +++ b/resources/tools/presentation/input_data_parser.py @@ -1,4 +1,4 @@ -# Copyright (c) 2017 Cisco and/or its affiliates. +# Copyright (c) 2018 Cisco and/or its affiliates. # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at: @@ -23,6 +23,7 @@ import pandas as pd import logging from robot.api import ExecutionResult, ResultVisitor +from robot import errors from collections import OrderedDict from string import replace @@ -173,6 +174,9 @@ class ExecutionChecker(ResultVisitor): REGEX_TCP = re.compile(r'Total\s(rps|cps|throughput):\s([0-9]*).*$') + REGEX_MRR = re.compile(r'MaxReceivedRate_Results\s\[pkts/(\d*)sec\]:\s' + r'tx\s(\d*),\srx\s(\d*)') + def __init__(self, **metadata): """Initialisation. @@ -219,7 +223,7 @@ class ExecutionChecker(ResultVisitor): self.parse_msg = { "setup-version": self._get_version, "teardown-vat-history": self._get_vat_history, - "teardown-show-runtime": self._get_show_run + "test-show-runtime": self._get_show_run } @property @@ -372,11 +376,11 @@ class ExecutionChecker(ResultVisitor): self._data["suites"][suite.longname.lower().replace('"', "'"). replace(" ", "_")] = { - "name": suite.name.lower(), - "doc": doc_str, - "parent": parent_name, - "level": len(suite.longname.split(".")) - } + "name": suite.name.lower(), + "doc": doc_str, + "parent": parent_name, + "level": len(suite.longname.split(".")) + } suite.keywords.visit(self) @@ -415,17 +419,20 @@ class ExecutionChecker(ResultVisitor): test_result["tags"] = tags doc_str = test.doc.replace('"', "'").replace('\n', ' '). \ replace('\r', '').replace('[', ' |br| [') - test_result["doc"] = replace(doc_str, ' |br| [', '[', maxreplace=1) + test_result["doc"] = replace(doc_str, ' |br| [', '[', maxreplace=1) test_result["msg"] = test.message.replace('\n', ' |br| '). \ replace('\r', '').replace('"', "'") - if test.status == "PASS" and ("NDRPDRDISC" in tags or "TCP" in tags): - + if test.status == "PASS" and ("NDRPDRDISC" in tags or + "TCP" in tags or + "MRR" in tags): if "NDRDISC" in tags: test_type = "NDR" elif "PDRDISC" in tags: test_type = "PDR" - elif "TCP" in tags: # Change to wrk? + elif "TCP" in tags: test_type = "TCP" + elif "MRR" in tags: + test_type = "MRR" else: return @@ -458,6 +465,15 @@ class ExecutionChecker(ResultVisitor): test_result["result"] = dict() test_result["result"]["value"] = int(groups.group(2)) test_result["result"]["unit"] = groups.group(1) + elif test_type in ("MRR", ): + groups = re.search(self.REGEX_MRR, test.message) + test_result["result"] = dict() + test_result["result"]["duration"] = int(groups.group(1)) + test_result["result"]["tx"] = int(groups.group(2)) + test_result["result"]["rx"] = int(groups.group(3)) + test_result["result"]["throughput"] = int( + test_result["result"]["rx"] / + test_result["result"]["duration"]) else: test_result["status"] = test.status @@ -496,6 +512,9 @@ class ExecutionChecker(ResultVisitor): elif keyword.type == "teardown": self._lookup_kw_nr = 0 self.visit_teardown_kw(keyword) + else: + self._lookup_kw_nr = 0 + self.visit_test_kw(keyword) except AttributeError: pass @@ -508,6 +527,42 @@ class ExecutionChecker(ResultVisitor): """ pass + def visit_test_kw(self, test_kw): + """Implements traversing through the test keyword and its child + keywords. + + :param test_kw: Keyword to process. + :type test_kw: Keyword + :returns: Nothing. + """ + for keyword in test_kw.keywords: + if self.start_test_kw(keyword) is not False: + self.visit_test_kw(keyword) + self.end_test_kw(keyword) + + def start_test_kw(self, test_kw): + """Called when test keyword starts. Default implementation does + nothing. + + :param test_kw: Keyword to process. + :type test_kw: Keyword + :returns: Nothing. + """ + if test_kw.name.count("Show Runtime Counters On All Duts"): + self._lookup_kw_nr += 1 + self._show_run_lookup_nr = 0 + self._msg_type = "test-show-runtime" + test_kw.messages.visit(self) + + def end_test_kw(self, test_kw): + """Called when keyword ends. Default implementation does nothing. + + :param test_kw: Keyword to process. + :type test_kw: Keyword + :returns: Nothing. + """ + pass + def visit_setup_kw(self, setup_kw): """Implements traversing through the teardown keyword and its child keywords. @@ -568,12 +623,6 @@ class ExecutionChecker(ResultVisitor): if teardown_kw.name.count("Show Vat History On All Duts"): self._vat_history_lookup_nr = 0 self._msg_type = "teardown-vat-history" - elif teardown_kw.name.count("Show Statistics On All Duts"): - self._lookup_kw_nr += 1 - self._show_run_lookup_nr = 0 - self._msg_type = "teardown-show-runtime" - - if self._msg_type: teardown_kw.messages.visit(self) def end_teardown_kw(self, teardown_kw): @@ -710,7 +759,12 @@ class InputData(object): """ with open(build["file-name"], 'r') as data_file: - result = ExecutionResult(data_file) + try: + result = ExecutionResult(data_file) + except errors.DataError as err: + logging.error("Error occurred while parsing output.xml: {0}". + format(err)) + return None checker = ExecutionChecker(job=job, build=build) result.visit(checker) @@ -736,6 +790,11 @@ class InputData(object): logging.info(" Processing the file '{0}'". format(build["file-name"])) data = InputData._parse_tests(job, build) + if data is None: + logging.error("Input data file from the job '{job}', build " + "'{build}' is damaged. Skipped.". + format(job=job, build=build["build"])) + continue build_data = pd.Series({ "metadata": pd.Series(data["metadata"].values(), @@ -793,7 +852,8 @@ class InputData(object): index += 1 tag_filter = tag_filter[:index] + " in tags" + tag_filter[index:] - def filter_data(self, element, params=None, data_set="tests"): + def filter_data(self, element, params=None, data_set="tests", + continue_on_error=False): """Filter required data from the given jobs and builds. The output data structure is: @@ -818,15 +878,18 @@ class InputData(object): all parameters are included. :param data_set: The set of data to be filtered: tests, suites, metadata. + :param continue_on_error: Continue if there is error while reading the + data. The Item will be empty then :type element: pandas.Series :type params: list :type data_set: str + :type continue_on_error: bool :returns: Filtered data. :rtype pandas.Series """ logging.info(" Creating the data set for the {0} '{1}'.". - format(element["type"], element.get("title", ""))) + format(element.get("type", ""), element.get("title", ""))) try: if element["filter"] in ("all", "template"): @@ -847,8 +910,15 @@ class InputData(object): data[job] = pd.Series() for build in builds: data[job][str(build)] = pd.Series() - for test_ID, test_data in \ - self.data[job][str(build)][data_set].iteritems(): + try: + data_iter = self.data[job][str(build)][data_set].\ + iteritems() + except KeyError: + if continue_on_error: + continue + else: + return None + for test_ID, test_data in data_iter: if eval(cond, {"tags": test_data.get("tags", "")}): data[job][str(build)][test_ID] = pd.Series() if params is None: diff --git a/resources/tools/presentation/pal.py b/resources/tools/presentation/pal.py index 6d613e339c..85b7bbc370 100644 --- a/resources/tools/presentation/pal.py +++ b/resources/tools/presentation/pal.py @@ -1,4 +1,4 @@ -# Copyright (c) 2017 Cisco and/or its affiliates. +# Copyright (c) 2018 Cisco and/or its affiliates. # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at: @@ -28,6 +28,9 @@ from generator_plots import generate_plots from generator_files import generate_files from static_content import prepare_static_content from generator_report import generate_report +from generator_CPTA import generate_cpta + +from pprint import pprint def parse_args(): @@ -81,8 +84,9 @@ def main(): spec.read_specification() except PresentationError: logging.critical("Finished with error.") - sys.exit(1) + return 1 + ret_code = 1 try: env = Environment(spec.environment, args.force) env.set_environment() @@ -101,22 +105,32 @@ def main(): generate_tables(spec, data) generate_plots(spec, data) generate_files(spec, data) - generate_report(args.release, spec) - logging.info("Successfully finished.") + if spec.output["output"] == "report": + generate_report(args.release, spec) + logging.info("Successfully finished.") + ret_code = 0 + elif spec.output["output"] == "CPTA": + ret_code = generate_cpta(spec, data) + logging.info("Successfully finished.") + else: + logging.critical("The output '{0}' is not supported.". + format(spec.output["output"])) + ret_code = 1 except (KeyError, ValueError, PresentationError) as err: logging.info("Finished with an error.") logging.critical(str(err)) + ret_code = 1 except Exception as err: logging.info("Finished with an unexpected error.") logging.critical(str(err)) - + ret_code = 1 finally: if spec is not None and not spec.is_debug: clean_environment(spec.environment) - sys.exit(1) + return ret_code if __name__ == '__main__': - main() + sys.exit(main()) diff --git a/resources/tools/presentation/run_cpta.sh b/resources/tools/presentation/run_cpta.sh new file mode 100755 index 0000000000..233e8dfbe2 --- /dev/null +++ b/resources/tools/presentation/run_cpta.sh @@ -0,0 +1,37 @@ +#!/bin/bash + +set +x + +# set default values in config array +typeset -A DIR + +DIR[WORKING]=_tmp + +# Install system dependencies +sudo apt-get -y update +sudo apt-get -y install libxml2 libxml2-dev libxslt-dev build-essential \ + zlib1g-dev unzip + +# Clean-up when finished +trap 'rm -rf ${DIR[WORKING]}; exit' EXIT +trap 'rm -rf ${DIR[WORKING]}; exit' ERR + +# Create working directories +mkdir ${DIR[WORKING]} + +# Create virtual environment +virtualenv ${DIR[WORKING]}/env +. ${DIR[WORKING]}/env/bin/activate + +# Install python dependencies: +pip install -r requirements.txt + +export PYTHONPATH=`pwd` + +python pal.py \ + --specification specification_CPTA.yaml \ + --logging INFO \ + --force + +RETURN_STATUS=$(echo $?) +exit ${RETURN_STATUS} diff --git a/resources/tools/presentation/run_report.sh b/resources/tools/presentation/run_report.sh index 34d6c5d7be..3c3a9f75ce 100755 --- a/resources/tools/presentation/run_report.sh +++ b/resources/tools/presentation/run_report.sh @@ -44,3 +44,6 @@ python pal.py \ --release ${RELEASE} \ --logging INFO \ --force + +RETURN_STATUS=$(echo $?) +exit ${RETURN_STATUS} diff --git a/resources/tools/presentation/specification_CPTA.yaml b/resources/tools/presentation/specification_CPTA.yaml new file mode 100644 index 0000000000..51cdc6324b --- /dev/null +++ b/resources/tools/presentation/specification_CPTA.yaml @@ -0,0 +1,400 @@ +# Copyright (c) 2018 Cisco and/or its affiliates. +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at: +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +# This is the specification of parameters for "Continuous Performance Trending +# and Analysis" feature provided by PAL. + +- + type: "environment" + configuration: + # Debug mode: + # - Skip: + # - Download of input data files + # - Do: + # - Read data from given zip / xml files + # - Set the configuration as it is done in normal mode + # If the section "type: debug" is missing, CFG[DEBUG] is set to 0. + CFG[DEBUG]: 0 + + paths: + # Top level directories: + ## Working directory + DIR[WORKING]: "_tmp" + ## Build directories + DIR[BUILD,HTML]: "_build" + ## Static .rst files + DIR[RST]: "../../../docs/cpta" + + # Static html content + DIR[STATIC]: "{DIR[BUILD,HTML]}/_static" + DIR[STATIC,VPP]: "{DIR[STATIC]}/vpp" + # DIR[STATIC,DPDK]: "{DIR[STATIC]}/dpdk" + DIR[STATIC,ARCH]: "{DIR[STATIC]}/archive" + + # Working directories + ## Input data files (.zip, .xml) + DIR[WORKING,DATA]: "{DIR[WORKING]}/data" + ## Static source files from git + DIR[WORKING,SRC]: "{DIR[WORKING]}/src" + DIR[WORKING,SRC,STATIC]: "{DIR[WORKING,SRC]}/_static" + + # .css patch file + DIR[CSS_PATCH_FILE]: "{DIR[STATIC]}/theme_overrides.css" + DIR[CSS_PATCH_FILE2]: "{DIR[WORKING,SRC,STATIC]}/theme_overrides.css" + + urls: + URL[JENKINS,CSIT]: "https://jenkins.fd.io/view/csit/job" + URL[NEXUS,LOG]: "https://logs.fd.io/production/vex-yul-rot-jenkins-1" + URL[NEXUS]: "https://docs.fd.io/csit" + DIR[NEXUS]: "report/_static/archive" + + make-dirs: + # List the directories which are created while preparing the environment. + # All directories MUST be defined in "paths" section. + - "DIR[WORKING,DATA]" + - "DIR[WORKING,SRC,STATIC]" + - "DIR[BUILD,HTML]" + - "DIR[STATIC,VPP]" + - "DIR[STATIC,ARCH]" + build-dirs: + # List the directories where the results (build) is stored. + # All directories MUST be defined in "paths" section. + - "DIR[BUILD,HTML]" + +- + type: "configuration" + + data-sets: +# TODO: Specify input data, this is only an example: + plot-performance-trending: + csit-vpp-perf-mrr-daily-master: + start: 9 + end: 14 # "lastSuccessfulBuild" # take all from the 'start' + + plot-layouts: + plot-cpta: + title: "" + autosize: False + showlegend: True + width: 1100 + height: 800 + yaxis: + showticklabels: True + title: "Throughput [Mpps]" + hoverformat: ".4s" + range: [] + gridcolor: "rgb(238, 238, 238)" + linecolor: "rgb(238, 238, 238)" + showline: True + zeroline: False + tickcolor: "rgb(238, 238, 238)" + linewidth: 1 + showgrid: True + xaxis: + showticklabels: True + title: "VPP Performance Trending Job ID" + autorange: True + showgrid: True + gridcolor: "rgb(238, 238, 238)" + linecolor: "rgb(238, 238, 238)" + fixedrange: False + zeroline: False + tickcolor: "rgb(238, 238, 238)" + showline: True + linewidth: 1 + autotick: True + margin: + r: 20 + b: 50 + t: 50 + l: 70 + legend: + orientation: "h" + traceorder: "normal" +# tracegroupgap: 10 +# bordercolor: "rgb(238, 238, 238)" +# borderwidth: 1 + +- + type: "debug" + general: + input-format: "xml" # zip or xml + extract: "robot-plugin/output.xml" # Only for zip + builds: + # The files must be in the directory DIR[WORKING,DATA] + csit-vpp-perf-mrr-daily-master: + - + build: 1 + file: "{DIR[WORKING,DATA]}/output_mrr_1.xml" + - + build: 2 + file: "{DIR[WORKING,DATA]}/output_mrr_2.xml" + - + build: 3 + file: "{DIR[WORKING,DATA]}/output_mrr_3.xml" + - + build: 4 + file: "{DIR[WORKING,DATA]}/output_mrr_4.xml" + - + build: 5 + file: "{DIR[WORKING,DATA]}/output_mrr_5.xml" + - + build: 6 + file: "{DIR[WORKING,DATA]}/output_mrr_5.xml" + - + build: 7 + file: "{DIR[WORKING,DATA]}/output_mrr_5.xml" + - + build: 8 + file: "{DIR[WORKING,DATA]}/output_mrr_5.xml" + - + build: 9 + file: "{DIR[WORKING,DATA]}/output_mrr_5.xml" + - + build: 10 + file: "{DIR[WORKING,DATA]}/output_mrr_5.xml" + - + build: 11 + file: "{DIR[WORKING,DATA]}/output_mrr_5.xml" + - + build: 12 + file: "{DIR[WORKING,DATA]}/output_mrr_5.xml" + +- + type: "static" + src-path: "{DIR[RST]}" + dst-path: "{DIR[WORKING,SRC]}" + +- + type: "input" # Ignored in debug mode + general: + file-name: "output.xml.log.gz" + file-format: ".gz" + download-path: "{job}/{build}/archives/{filename}" + extract: "output.xml" +# file-name: "robot-plugin.zip" +# file-format: ".zip" +# download-path: "{job}/{build}/robot/report/*zip*/{filename}" +# extract: "robot-plugin/output.xml" + builds: + csit-vpp-perf-mrr-daily-master: + start: 9 + end: 14 #"lastSuccessfulBuild" # take all from the 'start' +# csit-vpp-perf-check-master: +# start: 22 +# end: 22 + +- + type: "output" + output: +# "report" + "CPTA" # Continuous Performance Trending and Analysis + format: + html: + - full + pdf: + - minimal + +################################################################################ +### C P T A ### +################################################################################ + +# Plots VPP Continuous Performance Trending and Analysis +- + type: "cpta" + title: "Continuous Performance Trending and Analysis" + algorithm: "cpta" + output-file-type: ".html" + output-file: "{DIR[STATIC,VPP]}/cpta" + plots: + +# L2 + + - title: "VPP 1T1C L2 64B Packet Throughput - {period} Trending" + output-file-name: "l2" + data: "plot-performance-trending" + filter: "'MRR' and '64B' and ('BASE' or 'SCALE') and '1T1C' and ('L2BDMACSTAT' or 'L2BDMACLRN' or 'L2XCFWD') and not 'VHOST' and not 'MEMIF'" + parameters: + - "result" + - "name" + periods: + - 1 + - 5 + - 30 + layout: "plot-cpta" + +# IPv4 + + - title: "VPP 1T1C IPv4 64B Packet Throughput - {period} Trending" + output-file-name: "ip4" + data: "plot-performance-trending" + filter: "'MRR' and '64B' and ('BASE' or 'SCALE' or 'FEATURE') and '1T1C' and 'IP4FWD' and not 'IPSEC' and not 'VHOST'" + parameters: + - "result" + - "name" + periods: + - 1 + - 5 + - 30 + layout: "plot-cpta" + +# IPv6 + + - title: "VPP 1T1C IPv6 78B Packet Throughput - {period} Trending" + output-file-name: "ip6" + data: "plot-performance-trending" + filter: "'MRR' and '78B' and ('BASE' or 'SCALE' or 'FEATURE') and '1T1C' and 'IP6FWD' and not 'IPSEC' and not 'VHOST'" + parameters: + - "result" + - "name" + periods: + - 1 + - 5 + - 30 + layout: "plot-cpta" + +# Container memif + + - title: "VPP 1T1C L2 Container memif 64B Packet Throughput - {period} Trending" + output-file-name: "container-memif-l2-1t1c-x520" + data: "plot-performance-trending" + filter: "'NIC_Intel-X520-DA2' and 'MRR' and '64B' and 'BASE' and '1T1C' and 'MEMIF' and ('L2BDMACSTAT' or 'L2BDMACLRN' or 'L2XCFWD') and not 'VHOST'" + parameters: + - "result" + - "name" + periods: + - 1 + - 5 + - 30 + layout: "plot-cpta" + + - title: "VPP 2T2C L2 Container memif 64B Packet Throughput - {period} Trending" + output-file-name: "container-memif-l2-2t2c-x520" + data: "plot-performance-trending" + filter: "'NIC_Intel-X520-DA2' and 'MRR' and '64B' and 'BASE' and '2T2C' and 'MEMIF' and ('L2BDMACSTAT' or 'L2BDMACLRN' or 'L2XCFWD') and not 'VHOST'" + parameters: + - "result" + - "name" + periods: + - 1 + - 5 + - 30 + layout: "plot-cpta" + + - title: "VPP 1T1C L2 Container memif 64B Packet Throughput - {period} Trending" + output-file-name: "container-memif-l2-1t1c-xl710" + data: "plot-performance-trending" + filter: "'NIC_Intel-XL710' and 'MRR' and '64B' and 'BASE' and '1T1C' and 'MEMIF' and ('L2BDMACSTAT' or 'L2BDMACLRN' or 'L2XCFWD') and not 'VHOST'" + parameters: + - "result" + - "name" + periods: + - 1 + - 5 + - 30 + layout: "plot-cpta" + + - title: "VPP 2T2C L2 Container memif 64B Packet Throughput - {period} Trending" + output-file-name: "container-memif-l2-2t2c-xl710" + data: "plot-performance-trending" + filter: "'NIC_Intel-XL710' and 'MRR' and '64B' and 'BASE' and '2T2C' and 'MEMIF' and ('L2BDMACSTAT' or 'L2BDMACLRN' or 'L2XCFWD') and not 'VHOST'" + parameters: + - "result" + - "name" + periods: + - 1 + - 5 + - 30 + layout: "plot-cpta" + +# VM vhost + + - title: "VPP 1T1C VM vhost ethip4 64B Packet Throughput - {period} Trending" + output-file-name: "vm-vhost-ethip4-1t1c-x520" + data: "plot-performance-trending" + filter: "'NIC_Intel-X520-DA2' and '64B' and 'MRR' and '1T1C' and 'VHOST' and not ('L2BDMACSTAT' or 'L2BDMACLRN' or 'L2XCFWD')" + parameters: + - "result" + - "name" + periods: + - 1 + - 5 + - 30 + layout: "plot-cpta" + + - title: "VPP 2T2C VM vhost ethip4 64B Packet Throughput - {period} Trending" + output-file-name: "vm-vhost-ethip4-2t2c-x520" + data: "plot-performance-trending" + filter: "'NIC_Intel-X520-DA2' and '64B' and 'MRR' and '2T2C' and 'VHOST' and not ('L2BDMACSTAT' or 'L2BDMACLRN' or 'L2XCFWD')" + parameters: + - "result" + - "name" + periods: + - 1 + - 5 + - 30 + layout: "plot-cpta" + + - title: "VPP 1T1C VM vhost eth 64B Packet Throughput - {period} Trending" + output-file-name: "vm-vhost-eth-1t1c-x520" + data: "plot-performance-trending" + filter: "'NIC_Intel-X520-DA2' and '64B' and 'MRR' and '1T1C' and 'VHOST' and not 'VXLAN' and not 'IP4FWD' and not 'DOT1Q' and not '2VM'" + + parameters: + - "result" + - "name" + periods: + - 1 + - 5 + - 30 + layout: "plot-cpta" + + - title: "VPP 2T2C VM vhost eth 64B Packet Throughput - {period} Trending" + output-file-name: "vm-vhost-eth-2t2c-x520" + data: "plot-performance-trending" + filter: "'NIC_Intel-X520-DA2' and '64B' and 'MRR' and '2T2C' and 'VHOST' and not 'VXLAN' and not 'IP4FWD' and not 'DOT1Q' and not '2VM'" + parameters: + - "result" + - "name" + periods: + - 1 + - 5 + - 30 + layout: "plot-cpta" + + - title: "VPP 1T1C VM vhost eth 64B Packet Throughput - {period} Trending" + output-file-name: "vm-vhost-eth-1t1c-xl710" + data: "plot-performance-trending" + filter: "'NIC_Intel-XL710' and '64B' and 'MRR' and '1T1C' and 'VHOST' and not 'VXLAN' and not 'IP4FWD' and not 'DOT1Q' and not '2VM'" + + parameters: + - "result" + - "name" + periods: + - 1 + - 5 + - 30 + layout: "plot-cpta" + + - title: "VPP 2T2C VM vhost eth 64B Packet Throughput - {period} Trending" + output-file-name: "vm-vhost-eth-2t2c-xl710" + data: "plot-performance-trending" + filter: "'NIC_Intel-XL710' and '64B' and 'MRR' and '2T2C' and 'VHOST' and not 'VXLAN' and not 'IP4FWD' and not 'DOT1Q' and not '2VM'" + parameters: + - "result" + - "name" + periods: + - 1 + - 5 + - 30 + layout: "plot-cpta" diff --git a/resources/tools/presentation/specification_parser.py b/resources/tools/presentation/specification_parser.py index 501f9f191a..2659c29ca5 100644 --- a/resources/tools/presentation/specification_parser.py +++ b/resources/tools/presentation/specification_parser.py @@ -22,6 +22,7 @@ from yaml import load, YAMLError from pprint import pformat from errors import PresentationError +from utils import get_last_build_number class Specification(object): @@ -53,7 +54,8 @@ class Specification(object): "output": dict(), "tables": list(), "plots": list(), - "files": list()} + "files": list(), + "cpta": dict()} @property def specification(self): @@ -173,6 +175,17 @@ class Specification(object): """ return self._specification["files"] + @property + def cpta(self): + """Getter - Continuous Performance Trending and Analysis to be + generated. + + :returns: List of specifications of Continuous Performance Trending and + Analysis to be generated. + :rtype: list + """ + return self._specification["cpta"] + def set_input_state(self, job, build_nr, state): """Set the state of input @@ -354,9 +367,31 @@ class Specification(object): try: self._specification["configuration"] = self._cfg_yaml[idx] + except KeyError: raise PresentationError("No configuration defined.") + # Data sets: Replace ranges by lists + for set_name, data_set in self.configuration["data-sets"].items(): + for job, builds in data_set.items(): + if builds: + if isinstance(builds, dict): + # defined as a range <start, end> + if builds.get("end", None) == "lastSuccessfulBuild": + # defined as a range <start, lastSuccessfulBuild> + ret_code, build_nr, _ = get_last_build_number( + self.environment["urls"]["URL[JENKINS,CSIT]"], + job) + if ret_code != 0: + raise PresentationError( + "Not possible to get the number of the " + "last successful build.") + else: + # defined as a range <start, end (build number)> + build_nr = builds.get("end", None) + builds = [x for x in range(1, int(build_nr)+1)] + self.configuration["data-sets"][set_name][job] = builds + logging.info("Done.") def _parse_debug(self): @@ -412,8 +447,25 @@ class Specification(object): for key, value in self._cfg_yaml[idx]["general"].items(): self._specification["input"][key] = value self._specification["input"]["builds"] = dict() + for job, builds in self._cfg_yaml[idx]["builds"].items(): if builds: + if isinstance(builds, dict): + # defined as a range <start, end> + if builds.get("end", None) == "lastSuccessfulBuild": + # defined as a range <start, lastSuccessfulBuild> + ret_code, build_nr, _ = get_last_build_number( + self.environment["urls"]["URL[JENKINS,CSIT]"], + job) + if ret_code != 0: + raise PresentationError( + "Not possible to get the number of the " + "last successful build.") + else: + # defined as a range <start, end (build number)> + build_nr = builds.get("end", None) + builds = [x for x in range(builds["start"], + int(build_nr) + 1)] self._specification["input"]["builds"][job] = list() for build in builds: self._specification["input"]["builds"][job].\ @@ -440,8 +492,8 @@ class Specification(object): raise PresentationError("No output defined.") try: - self._specification["output"] = self._cfg_yaml[idx]["format"] - except KeyError: + self._specification["output"] = self._cfg_yaml[idx] + except (KeyError, IndexError): raise PresentationError("No output defined.") logging.info("Done.") @@ -535,6 +587,35 @@ class Specification(object): self._specification["files"].append(element) count += 1 + elif element["type"] == "cpta": + logging.info(" {:3d} Processing Continuous Performance " + "Trending and Analysis ...".format(count)) + + for plot in element["plots"]: + # Add layout to the plots: + layout = plot.get("layout", None) + if layout is not None: + try: + plot["layout"] = \ + self.configuration["plot-layouts"][layout] + except KeyError: + raise PresentationError( + "Layout {0} is not defined in the " + "configuration section.".format(layout)) + # Add data sets: + if isinstance(plot.get("data", None), str): + data_set = plot["data"] + try: + plot["data"] = \ + self.configuration["data-sets"][data_set] + except KeyError: + raise PresentationError( + "Data set {0} is not defined in " + "the configuration section.". + format(data_set)) + self._specification["cpta"] = element + count += 1 + logging.info("Done.") def read_specification(self): diff --git a/resources/tools/presentation/utils.py b/resources/tools/presentation/utils.py index 7037404c27..966d7f558b 100644 --- a/resources/tools/presentation/utils.py +++ b/resources/tools/presentation/utils.py @@ -14,12 +14,18 @@ """General purpose utilities. """ +import subprocess import numpy as np +import pandas as pd +import logging -from os import walk -from os.path import join +from os import walk, makedirs, environ +from os.path import join, isdir +from shutil import copy, Error from math import sqrt +from errors import PresentationError + def mean(items): """Calculate mean value from the items. @@ -62,27 +68,37 @@ def relative_change(nr1, nr2): return float(((nr2 - nr1) / nr1) * 100) -def remove_outliers(input_data, outlier_const): - """ +def find_outliers(input_data, outlier_const=1.5): + """Go through the input data and generate two pandas series: + - input data without outliers + - outliers. + The function uses IQR to detect outliers. - :param input_data: Data from which the outliers will be removed. + :param input_data: Data to be examined for outliers. :param outlier_const: Outlier constant. - :type input_data: list + :type input_data: pandas.Series :type outlier_const: float - :returns: The input list without outliers. - :rtype: list + :returns: Tuple: input data with outliers removed; Outliers. + :rtype: tuple (trimmed_data, outliers) """ - data = np.array(input_data) - upper_quartile = np.percentile(data, 75) - lower_quartile = np.percentile(data, 25) + upper_quartile = input_data.quantile(q=0.75) + lower_quartile = input_data.quantile(q=0.25) iqr = (upper_quartile - lower_quartile) * outlier_const - quartile_set = (lower_quartile - iqr, upper_quartile + iqr) - result_lst = list() - for y in data.tolist(): - if quartile_set[0] <= y <= quartile_set[1]: - result_lst.append(y) - return result_lst + low = lower_quartile - iqr + high = upper_quartile + iqr + trimmed_data = pd.Series() + outliers = pd.Series() + for item in input_data.items(): + item_pd = pd.Series([item[1], ], index=[item[0], ]) + if low <= item[1] <= high: + trimmed_data = trimmed_data.append(item_pd) + else: + trimmed_data = trimmed_data.append(pd.Series([np.nan, ], + index=[item[0], ])) + outliers = outliers.append(item_pd) + + return trimmed_data, outliers def get_files(path, extension=None, full_path=True): @@ -127,3 +143,78 @@ def get_rst_title_char(level): return chars[level] else: return chars[-1] + + +def execute_command(cmd): + """Execute the command in a subprocess and log the stdout and stderr. + + :param cmd: Command to execute. + :type cmd: str + :returns: Return code of the executed command. + :rtype: int + """ + + env = environ.copy() + proc = subprocess.Popen( + [cmd], + stdout=subprocess.PIPE, + stderr=subprocess.PIPE, + shell=True, + env=env) + + stdout, stderr = proc.communicate() + + logging.info(stdout) + logging.info(stderr) + + if proc.returncode != 0: + logging.error(" Command execution failed.") + return proc.returncode, stdout, stderr + + +def get_last_build_number(jenkins_url, job_name): + """ + + :param jenkins_url: + :param job_name: + :return: + """ + + url = "{}/{}/lastSuccessfulBuild/buildNumber".format(jenkins_url, job_name) + cmd = "wget -qO- {url}".format(url=url) + + return execute_command(cmd) + + +def archive_input_data(spec): + """Archive the report. + + :param spec: Specification read from the specification file. + :type spec: Specification + :raises PresentationError: If it is not possible to archive the input data. + """ + + logging.info(" Archiving the input data files ...") + + if spec.is_debug: + extension = spec.debug["input-format"] + else: + extension = spec.input["file-format"] + data_files = get_files(spec.environment["paths"]["DIR[WORKING,DATA]"], + extension=extension) + dst = spec.environment["paths"]["DIR[STATIC,ARCH]"] + logging.info(" Destination: {0}".format(dst)) + + try: + if not isdir(dst): + makedirs(dst) + + for data_file in data_files: + logging.info(" Copying the file: {0} ...".format(data_file)) + copy(data_file, dst) + + except (Error, OSError) as err: + raise PresentationError("Not possible to archive the input data.", + str(err)) + + logging.info(" Done.") |