Add Steady State Detection module

Added a Steady State Detection module containing a steady_state(data_series)
function that is able to return a boolean indicating wether or not steady
state is reached with the data_series being passed.
This module requires a data_treatment(data_series) and an average(data_series)
modules that have been added in this commit as well. The data treatment function
aims at formatting the data series that is passed to the high level steady_state
function to reach the requirement of each sub-module (slope, average and range).

Modified the Slope and Range functions so they return None when passed an empty
data series instead of 0 which was wrong. Modified the corresponding test cases.

Modified the math_range_test.py file to fix a bug in the 2 last tests.

Change-Id: I9c3854cb0a21cc37b0787b8afca0821eefaa203d
JIRA: STORPERF-60
JIRA: STORPERF-59
JIRA: STORPERF-61
JIRA: STORPERF-62
Signed-off-by: Tim Rault <tim.rault@cengn.ca>

diff --git a/storperf/utilities/data_treatment.py b/storperf/utilities/data_treatment.py
new file mode 100644 (file)
index 0000000..2368fd9
--- /dev/null
+++ b/storperf/utilities/data_treatment.py
@@ -0,0 +1,39 @@
+##############################################################################
+# Copyright (c) 2016 CENGN and others.
+#
+# All rights reserved. This program and the accompanying materials
+# are made available under the terms of the Apache License, Version 2.0
+# which accompanies this distribution, and is available at
+# http://www.apache.org/licenses/LICENSE-2.0
+##############################################################################
+
+
+def data_treatment(data_series):
+    """
+    This function aims at performing any necessary pre treatment on the
+    data_series passed to the steady_state function before being passed
+    under to the different math utilities (slope, range and average)
+    so the data can match the requirements of each algorithm.
+    The function returns a dictionary composed of three values that can be
+    accessed with the following keys : 'slope_data', 'range_data' and
+    'average_data'.
+    The data_series is currently assumed to follow the pattern :
+    [[x1,y1], [x2,y2], ..., [xm,ym]]. If this pattern were to change, or
+    the input data pattern of one of the math module, this data_treatment
+    function should be the only part of the Steady State detection module
+    that would need to be modified too.
+    """
+
+    x_values = []
+    y_values = []
+    for l in data_series:
+        x_values.append(l[0])
+        y_values.append(l[1])
+
+    treated_data = {
+        'slope_data': data_series,  # No treatment necessary so far
+        'range_data': y_values,  # The y_values only
+        'average_data': y_values
+    }
+
+    return treated_data

diff --git a/storperf/utilities/math.py b/storperf/utilities/math.py
index 031fc3e..a11ec19 100644 (file)
--- a/storperf/utilities/math.py
+++ b/storperf/utilities/math.py
@@ -25,7 +25,7 @@ def slope(data_series):
 
     # In the particular case of an empty data series
     if len(data_series) == 0:
-        beta2 = 0
+        beta2 = None
 
     else:  # The general case
         m = len(data_series)
@@ -78,7 +78,7 @@ def range_value(data_series):
 
     # In the particular case of an empty data series
     if len(data_series) == 0:
-        range_value = 0
+        range_value = None
 
     else:  # The general case
         max_value = max(data_series)
@@ -86,3 +86,26 @@ def range_value(data_series):
         range_value = max_value - min_value
 
     return range_value
+
+
+def average(data_series):
+    """
+    This function seeks to calculate the average value of the data series
+    given a series following the pattern : [y1, y2, y3, ..., ym].
+    If this data pattern were to change, the data_treatment function
+    should be adjusted to ensure compatibility with the rest of the
+    Steady State Dectection module.
+    The function returns a float number corresponding to the average of the yi.
+    """
+    m = len(data_series)
+
+    if m == 0:  # In the particular case of an empty data series
+        average = None
+
+    else:
+        data_sum = 0
+        for value in data_series:
+            data_sum += value
+        average = data_sum / float(m)
+
+    return average

diff --git a/storperf/utilities/steady_state.py b/storperf/utilities/steady_state.py
new file mode 100644 (file)
index 0000000..8bfcb93
--- /dev/null
+++ b/storperf/utilities/steady_state.py
@@ -0,0 +1,45 @@
+##############################################################################
+# Copyright (c) 2016 CENGN and others.
+#
+# All rights reserved. This program and the accompanying materials
+# are made available under the terms of the Apache License, Version 2.0
+# which accompanies this distribution, and is available at
+# http://www.apache.org/licenses/LICENSE-2.0
+##############################################################################
+from storperf.utilities import data_treatment as DataTreatment
+from storperf.utilities import math as math
+
+
+def steady_state(data_series):
+    """
+    This function seeks to detect steady state given on a measurement
+    window given the data series of that measurement window following
+    the pattern : [[x1,y1], [x2,y2], ..., [xm,ym]]. m represents the number
+    of points recorded in the measurement window, x which represents the
+    time, and y which represents the Volume performance variable being
+    tested e.g. IOPS, latency...
+    The function returns a boolean describing wether or not steady state
+    has been reached with the data that is passed to it.
+    """
+
+    # Pre conditioning the data to match the algorithms
+    treated_data = DataTreatment.data_treatment(data_series)
+
+    # Calculating useful values invoking dedicated functions
+    slope_value = math.slope(treated_data['slope_data'])
+    range_value = math.range_value(treated_data['range_data'])
+    average_value = math.average(treated_data['average_data'])
+
+    if (slope_value is not None and range_value is not None and
+            average_value is not None):
+        # Verification of the Steady State conditions following the SNIA
+        # definition
+        range_condition = range_value < 0.20 * abs(average_value)
+        slope_condition = slope_value < 0.10 * abs(average_value)
+
+        steady_state = range_condition and slope_condition
+
+    else:
+        steady_state = False
+
+    return steady_state

diff --git a/tests/utilities_tests/data_treatment_test.py b/tests/utilities_tests/data_treatment_test.py
new file mode 100644 (file)
index 0000000..4450f92
--- /dev/null
+++ b/tests/utilities_tests/data_treatment_test.py
@@ -0,0 +1,81 @@
+##############################################################################
+# Copyright (c) 2016 CENGN and others.
+#
+# All rights reserved. This program and the accompanying materials
+# are made available under the terms of the Apache License, Version 2.0
+# which accompanies this distribution, and is available at
+# http://www.apache.org/licenses/LICENSE-2.0
+##############################################################################
+import unittest
+from storperf.utilities import data_treatment as DataTreatment
+
+
+class DataTreatmentTest(unittest.TestCase):
+
+    def setUp(self):
+        unittest.TestCase.setUp(self)
+
+    def test_empty_series(self):
+        expected = {
+            'slope_data': [],
+            'range_data': [],
+            'average_data': []
+        }
+        data_series = []
+        actual = DataTreatment.data_treatment(data_series)
+        self.assertEqual(expected, actual)
+
+    def test_integer_series(self):
+        expected = {
+            'slope_data': [[1, 5], [66, 2], [12, 98], [74, 669], [33, 66]],
+            'range_data': [5, 2, 98, 669, 66],
+            'average_data': [5, 2, 98, 669, 66]
+        }
+        data_series = [[1, 5], [66, 2], [12, 98], [74, 669], [33, 66]]
+        actual = DataTreatment.data_treatment(data_series)
+        self.assertEqual(expected, actual)
+
+    def test_float_series(self):
+        expected = {
+            'slope_data': [[5.6, 12.7], [96.66, 78.212],
+                           [639.568, 5.3], [4.65, 6.667]],
+            'range_data': [12.7, 78.212, 5.3, 6.667],
+            'average_data': [12.7, 78.212, 5.3, 6.667]
+        }
+        data_series = [
+            [5.6, 12.7], [96.66, 78.212], [639.568, 5.3], [4.65, 6.667]]
+        actual = DataTreatment.data_treatment(data_series)
+        self.assertEqual(expected, actual)
+
+    def test_float_int_mix(self):
+        expected = {
+            'slope_data': [[5, 12.7], [96.66, 7], [639.568, 5.3], [4, 6]],
+            'range_data': [12.7, 7, 5.3, 6],
+            'average_data': [12.7, 7, 5.3, 6]
+        }
+        data_series = [[5, 12.7], [96.66, 7], [639.568, 5.3], [4, 6]]
+        actual = DataTreatment.data_treatment(data_series)
+        self.assertEqual(expected, actual)
+
+    def test_negative_values(self):
+        expected = {
+            'slope_data': [[-15, 5.56], [41.3, -278], [41.3, -98],
+                           [78.336, -0.12], [33.667, 66]],
+            'range_data': [5.56, -278, -98, -0.12, 66],
+            'average_data': [5.56, -278, -98, -0.12, 66]
+        }
+        data_series = [
+            [-15, 5.56], [41.3, -278], [41.3, -98],
+            [78.336, -0.12], [33.667, 66]]
+        actual = DataTreatment.data_treatment(data_series)
+        self.assertEqual(expected, actual)
+
+    def test_single_value(self):
+        expected = {
+            'slope_data': [[86.8, 65.36]],
+            'range_data': [65.36],
+            'average_data': [65.36]
+        }
+        data_series = [[86.8, 65.36]]
+        actual = DataTreatment.data_treatment(data_series)
+        self.assertEqual(expected, actual)

diff --git a/tests/utilities_tests/math_average_test.py b/tests/utilities_tests/math_average_test.py
new file mode 100644 (file)
index 0000000..3095f56
--- /dev/null
+++ b/tests/utilities_tests/math_average_test.py
@@ -0,0 +1,52 @@
+##############################################################################
+# Copyright (c) 2016 CENGN and others.
+#
+# All rights reserved. This program and the accompanying materials
+# are made available under the terms of the Apache License, Version 2.0
+# which accompanies this distribution, and is available at
+# http://www.apache.org/licenses/LICENSE-2.0
+##############################################################################
+import unittest
+from storperf.utilities import math as math
+
+
+class MathAverageTest(unittest.TestCase):
+
+    def setUp(self):
+        unittest.TestCase.setUp(self)
+
+    def test_empty_series(self):
+        expected = None
+        data_series = []
+        actual = math.average(data_series)
+        self.assertEqual(expected, actual)
+
+    def test_integer_series(self):
+        expected = 19.75
+        data_series = [5, 12, 7, 55]
+        actual = math.average(data_series)
+        self.assertEqual(expected, actual)
+
+    def test_float_series(self):
+        expected = 63.475899999999996
+        data_series = [78.6, 45.187, 33.334, 96.7826]
+        actual = math.average(data_series)
+        self.assertEqual(expected, actual)
+
+    def test_float_int_mix(self):
+        expected = 472.104
+        data_series = [10, 557.33, 862, 56.99, 874.2]
+        actual = math.average(data_series)
+        self.assertEqual(expected, actual)
+
+    def test_negative_values(self):
+        expected = -17.314
+        data_series = [-15.654, 59.5, 16.25, -150, 3.334]
+        actual = math.average(data_series)
+        self.assertEqual(expected, actual)
+
+    def test_single_value(self):
+        expected = -66.6667
+        data_series = [-66.6667]
+        actual = math.average(data_series)
+        self.assertEqual(expected, actual)

diff --git a/tests/utilities_tests/math_range_test.py b/tests/utilities_tests/math_range_test.py
index 6484752..90519e7 100644 (file)
--- a/tests/utilities_tests/math_range_test.py
+++ b/tests/utilities_tests/math_range_test.py
@@ -9,7 +9,7 @@
 from random import uniform, randrange
 import unittest
 
-from storperf.utilities import math as math
+from storperf.utilities import math as Range
 
 
 class MathRangeTest(unittest.TestCase):
@@ -18,56 +18,56 @@ class MathRangeTest(unittest.TestCase):
         unittest.TestCase.setUp(self)
 
     def test_empty_series(self):
-        expected = 0
+        expected = None
         data_series = []
-        actual = math.range_value(data_series)
+        actual = Range.range_value(data_series)
         self.assertEqual(expected, actual)
 
     def test_integer_series(self):
         expected = 11946
         data_series = [5, 351, 847, 2, 1985, 18,
                        96, 389, 687, 1, 11947, 758, 155]
-        actual = math.range_value(data_series)
+        actual = Range.range_value(data_series)
         self.assertEqual(expected, actual)
 
     def test_float_series_1_decimal(self):
         expected = 778595.5
         data_series = [736.4, 9856.4, 684.2, 0.3, 0.9, 778595.8]
-        actual = math.range_value(data_series)
+        actual = Range.range_value(data_series)
         self.assertEqual(expected, actual)
 
     def test_float_series_2_decimals(self):
         expected = 5693.47
         data_series = [51.36, 78.40, 1158.24, 5.50, 0.98, 5694.45]
-        actual = math.range_value(data_series)
+        actual = Range.range_value(data_series)
         self.assertEqual(expected, actual)
 
     def test_float_series_3_decimals(self):
         expected = 992.181
         data_series = [4.562, 12.582, 689.452,
                        135.162, 996.743, 65.549, 36.785]
-        actual = math.range_value(data_series)
+        actual = Range.range_value(data_series)
         self.assertEqual(expected, actual)
 
     def test_float_series_4_decimals(self):
         expected = 122985.3241
         data_series = [39.4785, 896.7845, 11956.3654,
                        44.2398, 6589.7134, 0.3671, 122985.6912]
-        actual = math.range_value(data_series)
+        actual = Range.range_value(data_series)
         self.assertEqual(expected, actual)
 
     def test_float_series_5_decimals(self):
         expected = 8956208.84494
         data_series = [12.78496, 55.91275, 668.94378,
                        550396.5671, 512374.9999, 8956221.6299]
-        actual = math.range_value(data_series)
+        actual = Range.range_value(data_series)
         self.assertEqual(expected, actual)
 
     def test_float_series_10_decimals(self):
         expected = 5984.507397972699
         data_series = [1.1253914785, 5985.6327894512,
                        256.1875693287, 995.8497623415]
-        actual = math.range_value(data_series)
+        actual = Range.range_value(data_series)
         self.assertEqual(expected, actual)
 
     def test_float_mix(self):
@@ -75,46 +75,46 @@ class MathRangeTest(unittest.TestCase):
         data_series = [60785.9962, 899.4, 78.66, 69.58, 4.93795,
                        587.195486, 96.7694536, 5.13755964,
                        33.333333334, 60786.5624872199]
-        actual = math.range_value(data_series)
+        actual = Range.range_value(data_series)
         self.assertEqual(expected, actual)
 
     def test_float_integer_mix(self):
         expected = 460781.05825
         data_series = [460785.9962, 845.634, 24.1, 69.58, 89, 4.93795]
-        actual = math.range_value(data_series)
+        actual = Range.range_value(data_series)
         self.assertEqual(expected, actual)
 
     def test_negative_values(self):
         expected = 596.78163
         data_series = [-4.655, -33.3334, -596.78422, -0.00259, -66.785]
-        actual = math.range_value(data_series)
+        actual = Range.range_value(data_series)
         self.assertEqual(expected, actual)
 
     def test_negative_positive_mix(self):
         expected = 58.859500000000004
         data_series = [6.85698, -2.8945, 0, -0.15, 55.965]
-        actual = math.range_value(data_series)
+        actual = Range.range_value(data_series)
         self.assertEqual(expected, actual)
 
     def test_single_element(self):
         expected = 0
         data_series = [2.265]
-        actual = math.range_value(data_series)
+        actual = Range.range_value(data_series)
         self.assertEqual(expected, actual)
 
     def test_10000_values_processing(self):
         expected = 28001.068
-        data_series = [uniform(-10000, 10000) for i in xrange(10000)]
-        data_series.insert(randrange(len(data_series) + 1), 15000.569)
-        data_series.insert(randrange(len(data_series) + 1), -13000.499)
-        actual = math.range_value(data_series)
+        data_series = [uniform(-10000, 10000) for _ in range(10000)]
+        data_series.insert(randrange(len(data_series)), 15000.569)
+        data_series.insert(randrange(len(data_series)), -13000.499)
+        actual = Range.range_value(data_series)
         self.assertEqual(expected, actual)
 
     def test_processing_100_values_100_times(self):
         expected = 35911.3134
-        for index in range(1, 100):
-            data_series = [uniform(-10000, 10000) for i in xrange(100)]
-            data_series.insert(randrange(len(data_series) + 1), 16956.3334)
-            data_series.insert(randrange(len(data_series) + 1), -18954.98)
-            actual = math.range_value(data_series)
+        for _ in range(1, 100):
+            data_series = [uniform(-10000, 10000) for _ in range(100)]
+            data_series.insert(randrange(len(data_series)), 16956.3334)
+            data_series.insert(randrange(len(data_series)), -18954.98)
+            actual = Range.range_value(data_series)
             self.assertEqual(expected, actual)

diff --git a/tests/utilities_tests/math_slope_test.py b/tests/utilities_tests/math_slope_test.py
index a34845b..6c05aa4 100644 (file)
--- a/tests/utilities_tests/math_slope_test.py
+++ b/tests/utilities_tests/math_slope_test.py
@@ -7,7 +7,7 @@
 # http://www.apache.org/licenses/LICENSE-2.0
 ##############################################################################
 import unittest
-from storperf.utilities import math as math
+from storperf.utilities import math as Slope
 
 
 class MathSlopeTest(unittest.TestCase):
@@ -17,51 +17,51 @@ class MathSlopeTest(unittest.TestCase):
         pass
 
     def test_slope_empty_series(self):
-        expected = 0
-        actual = math.slope([])
+        expected = None
+        actual = Slope.slope([])
         self.assertEqual(expected, actual)
 
     def test_slope_integer_series(self):
         expected = 1.4
-        actual = math.slope([[1, 6], [2, 5], [3, 7], [4, 10]])
+        actual = Slope.slope([[1, 6], [2, 5], [3, 7], [4, 10]])
         self.assertEqual(expected, actual)
 
     def test_slope_decimal_series(self):
         expected = 1.4
-        actual = math.slope([[1.0, 6.0], [2.0, 5.0], [3.0, 7.0], [4.0, 10.0]])
+        actual = Slope.slope([[1.0, 6.0], [2.0, 5.0], [3.0, 7.0], [4.0, 10.0]])
         self.assertEqual(expected, actual)
 
     def test_slope_decimal_integer_mix(self):
         expected = 1.4
-        actual = math.slope([[1.0, 6], [2, 5.0], [3, 7], [4.0, 10]])
+        actual = Slope.slope([[1.0, 6], [2, 5.0], [3, 7], [4.0, 10]])
         self.assertEqual(expected, actual)
 
     def test_slope_negative_y_series(self):
         expected = 2
-        actual = math.slope([[1.0, -2], [2, 2], [3, 2]])
+        actual = Slope.slope([[1.0, -2], [2, 2], [3, 2]])
         self.assertEqual(expected, actual)
 
     def test_slope_negative_x_series(self):
         expected = 1.4
-        actual = math.slope([[-24, 6.0], [-23, 5], [-22, 7.0], [-21, 10]])
+        actual = Slope.slope([[-24, 6.0], [-23, 5], [-22, 7.0], [-21, 10]])
         self.assertEqual(expected, actual)
 
     def test_slope_out_of_order_series(self):
         expected = 1.4
-        actual = math.slope([[2, 5.0], [4, 10], [3.0, 7], [1, 6]])
+        actual = Slope.slope([[2, 5.0], [4, 10], [3.0, 7], [1, 6]])
         self.assertEqual(expected, actual)
 
     def test_slope_0_in_y(self):
         expected = -0.5
-        actual = math.slope([[15.5, 1], [16.5, 0], [17.5, 0]])
+        actual = Slope.slope([[15.5, 1], [16.5, 0], [17.5, 0]])
         self.assertEqual(expected, actual)
 
     def test_slope_0_in_x(self):
         expected = 1.4
-        actual = math.slope([[0, 6.0], [1, 5], [2, 7], [3, 10]])
+        actual = Slope.slope([[0, 6.0], [1, 5], [2, 7], [3, 10]])
         self.assertEqual(expected, actual)
 
     def test_slope_0_in_x_and_y(self):
         expected = 1.5
-        actual = math.slope([[0.0, 0], [1, 1], [2, 3]])
+        actual = Slope.slope([[0.0, 0], [1, 1], [2, 3]])
         self.assertEqual(expected, actual)

diff --git a/tests/utilities_tests/steady_state_test.py b/tests/utilities_tests/steady_state_test.py
new file mode 100644 (file)
index 0000000..d80c60d
--- /dev/null
+++ b/tests/utilities_tests/steady_state_test.py
@@ -0,0 +1,59 @@
+##############################################################################
+# Copyright (c) 2016 CENGN and others.
+#
+# All rights reserved. This program and the accompanying materials
+# are made available under the terms of the Apache License, Version 2.0
+# which accompanies this distribution, and is available at
+# http://www.apache.org/licenses/LICENSE-2.0
+##############################################################################
+import unittest
+from storperf.utilities import steady_state as SteadyState
+
+
+class SteadyStateTest(unittest.TestCase):
+
+    def setUp(self):
+        unittest.TestCase.setUp(self)
+
+    def test_integer_values(self):
+        expected = True
+        data_series = [[305, 20], [306, 21], [307, 21], [308, 19]]
+        actual = SteadyState.steady_state(data_series)
+        self.assertEqual(expected, actual)
+
+    def test_float_values(self):
+        expected = True
+        data_series = [
+            [55.5, 40.5], [150.2, 42.3], [150.8, 41.8], [151.2, 41.5]]
+        actual = SteadyState.steady_state(data_series)
+        self.assertEqual(expected, actual)
+
+    def test_float_integer_mix_false(self):
+        expected = False
+        data_series = [[1, 2], [2, 2.2], [3, 1.8], [4, 1.8]]
+        actual = SteadyState.steady_state(data_series)
+        self.assertEqual(expected, actual)
+
+    def test_float_integer_mix_true(self):
+        expected = True
+        data_series = [[12, 18], [12.5, 18.2], [13, 16.8], [15, 16.8]]
+        actual = SteadyState.steady_state(data_series)
+        self.assertEqual(expected, actual)
+
+    def test_empty_series(self):
+        expected = False
+        data_series = []
+        actual = SteadyState.steady_state(data_series)
+        self.assertEqual(expected, actual)
+
+    def test_negative_values(self):
+        expected = True
+        data_series = [[-1, -24.2], [0.5, -23.8], [1.1, -24.0], [3.2, -24.0]]
+        actual = SteadyState.steady_state(data_series)
+        self.assertEqual(expected, actual)
+
+    def test_out_of_order_series(self):
+        expected = True
+        data_series = [[-15, 0.43], [-16, 0.41], [-3, 0.45], [4, 0.42]]
+        actual = SteadyState.steady_state(data_series)
+        self.assertEqual(expected, actual)