aboutsummaryrefslogtreecommitdiffstats
path: root/resources/tools/presentation/generator_CPTA.py
blob: 1e7719153fd7b1d3cccb0310fe2201a52bbdff88 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
# Copyright (c) 2019 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 multiprocessing
import os
import logging
import csv
import prettytable
import plotly.offline as ploff
import plotly.graph_objs as plgo
import plotly.exceptions as plerr

from collections import OrderedDict
from datetime import datetime
from copy import deepcopy

from utils import archive_input_data, execute_command, \
    classify_anomalies, Worker


# Command to build the html format of the report
HTML_BUILDER = 'sphinx-build -v -c conf_cpta -a ' \
               '-b html -E ' \
               '-t html ' \
               '-D version="{date}" ' \
               '{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;
}
.rst-content blockquote {
    margin-left: 0px;
    line-height: 18px;
    margin-bottom: 0px;
}
.wy-menu-vertical a {
    display: inline-block;
    line-height: 18px;
    padding: 0 2em;
    display: block;
    position: relative;
    font-size: 90%;
    color: #d9d9d9
}
.wy-menu-vertical li.current a {
    color: gray;
    border-right: solid 1px #c9c9c9;
    padding: 0 3em;
}
.wy-menu-vertical li.toctree-l2.current > a {
    background: #c9c9c9;
    padding: 0 3em;
}
.wy-menu-vertical li.toctree-l2.current li.toctree-l3 > a {
    display: block;
    background: #c9c9c9;
    padding: 0 4em;
}
.wy-menu-vertical li.toctree-l3.current li.toctree-l4 > a {
    display: block;
    background: #bdbdbd;
    padding: 0 5em;
}
.wy-menu-vertical li.on a, .wy-menu-vertical li.current > a {
    color: #404040;
    padding: 0 2em;
    font-weight: bold;
    position: relative;
    background: #fcfcfc;
    border: none;
        border-top-width: medium;
        border-bottom-width: medium;
        border-top-style: none;
        border-bottom-style: none;
        border-top-color: currentcolor;
        border-bottom-color: currentcolor;
    padding-left: 2em -4px;
}
"""

COLORS = ["SkyBlue", "Olive", "Purple", "Coral", "Indigo", "Pink",
          "Chocolate", "Brown", "Magenta", "Cyan", "Orange", "Black",
          "Violet", "Blue", "Yellow", "BurlyWood", "CadetBlue", "Crimson",
          "DarkBlue", "DarkCyan", "DarkGreen", "Green", "GoldenRod",
          "LightGreen", "LightSeaGreen", "LightSkyBlue", "Maroon",
          "MediumSeaGreen", "SeaGreen", "LightSlateGrey",
          "SkyBlue", "Olive", "Purple", "Coral", "Indigo", "Pink",
          "Chocolate", "Brown", "Magenta", "Cyan", "Orange", "Black",
          "Violet", "Blue", "Yellow", "BurlyWood", "CadetBlue", "Crimson",
          "DarkBlue", "DarkCyan", "DarkGreen", "Green", "GoldenRod",
          "LightGreen", "LightSeaGreen", "LightSkyBlue", "Maroon",
          "MediumSeaGreen", "SeaGreen", "LightSlateGrey"
          ]


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.utcnow().strftime('%Y-%m-%d %H:%M UTC'),
        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 _generate_trending_traces(in_data, job_name, build_info,
                              show_trend_line=True, name="", color=""):
    """Generate the trending traces:
     - samples,
     - outliers, regress, progress
     - average of normal samples (trending line)

    :param in_data: Full data set.
    :param job_name: The name of job which generated the data.
    :param build_info: Information about the builds.
    :param show_trend_line: 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 job_name: str
    :type build_info: dict
    :type show_trend_line: bool
    :type name: str
    :type color: str
    :returns: Generated traces (list) and the evaluated result.
    :rtype: tuple(traces, result)
    """

    data_x = list(in_data.keys())
    data_y = list(in_data.values())

    hover_text = list()
    xaxis = list()
    for idx in data_x:
        date = build_info[job_name][str(idx)][0]
        hover_str = ("date: {date}<br>"
                     "value: {value:,}<br>"
                     "{sut}-ref: {build}<br>"
                     "csit-ref: mrr-{period}-build-{build_nr}<br>"
                     "testbed: {testbed}")
        if "dpdk" in job_name:
            hover_text.append(hover_str.format(
                date=date,
                value=int(in_data[idx].avg),
                sut="dpdk",
                build=build_info[job_name][str(idx)][1].rsplit('~', 1)[0],
                period="weekly",
                build_nr=idx,
                testbed=build_info[job_name][str(idx)][2]))
        elif "vpp" in job_name:
            hover_text.append(hover_str.format(
                date=date,
                value=int(in_data[idx].avg),
                sut="vpp",
                build=build_info[job_name][str(idx)][1].rsplit('~', 1)[0],
                period="daily",
                build_nr=idx,
                testbed=build_info[job_name][str(idx)][2]))

        xaxis.append(datetime(int(date[0:4]), int(date[4:6]), int(date[6:8]),
                              int(date[9:11]), int(date[12:])))

    data_pd = OrderedDict()
    for key, value in zip(xaxis, data_y):
        data_pd[key] = value

    anomaly_classification, avgs = classify_anomalies(data_pd)

    anomalies = OrderedDict()
    anomalies_colors = list()
    anomalies_avgs = list()
    anomaly_color = {
        "regression": 0.0,
        "normal": 0.5,
        "progression": 1.0
    }
    if anomaly_classification:
        for idx, (key, value) in enumerate(data_pd.iteritems()):
            if anomaly_classification[idx] in \
                    ("outlier", "regression", "progression"):
                anomalies[key] = value
                anomalies_colors.append(
                    anomaly_color[anomaly_classification[idx]])
                anomalies_avgs.append(avgs[idx])
        anomalies_colors.extend([0.0, 0.5, 1.0])

    # Create traces

    trace_samples = plgo.Scatter(
        x=xaxis,
        y=[y.avg for y in data_y],
        mode='markers',
        line={
            "width": 1
        },
        showlegend=True,
        legendgroup=name,
        name="{name}".format(name=name),
        marker={
            "size": 5,
            "color": color,
            "symbol": "circle",
        },
        text=hover_text,
        hoverinfo="text"
    )
    traces = [trace_samples, ]

    if show_trend_line:
        trace_trend = plgo.Scatter(
            x=xaxis,
            y=avgs,
            mode='lines',
            line={
                "shape": "linear",
                "width": 1,
                "color": color,
            },
            showlegend=False,
            legendgroup=name,
            name='{name}'.format(name=name),
            text=["trend: {0:,}".format(int(avg)) for avg in avgs],
            hoverinfo="text+name"
        )
        traces.append(trace_trend)

    trace_anomalies = plgo.Scatter(
        x=anomalies.keys(),
        y=anomalies_avgs,
        mode='markers',
        hoverinfo="none",
        showlegend=False,
        legendgroup=name,
        name="{name}-anomalies".format(name=name),
        marker={
            "size": 15,
            "symbol": "circle-open",
            "color": anomalies_colors,
            "colorscale": [[0.00, "red"],
                           [0.33, "red"],
                           [0.33, "white"],
                           [0.66, "white"],
                           [0.66, "green"],
                           [1.00, "green"]],
            "showscale": True,
            "line": {
                "width": 2
            },
            "colorbar": {
                "y": 0.5,
                "len": 0.8,
                "title": "Circles Marking Data Classification",
                "titleside": 'right',
                "titlefont": {
                    "size": 14
                },
                "tickmode": 'array',
                "tickvals": [0.167, 0.500, 0.833],
                "ticktext": ["Regression", "Normal", "Progression"],
                "ticks": "",
                "ticklen": 0,
                "tickangle": -90,
                "thickness": 10
            }
        }
    )
    traces.append(trace_anomalies)

    if anomaly_classification:
        return traces, anomaly_classification[-1]
    else:
        return traces, None


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
    """

    def _generate_chart(_, data_q, graph):
        """Generates the chart.
        """

        logs = list()

        logging.info("  Generating the chart '{0}' ...".
                     format(graph.get("title", "")))
        logs.append(("INFO", "  Generating the chart '{0}' ...".
                     format(graph.get("title", ""))))

        job_name = graph["data"].keys()[0]

        csv_tbl = list()
        res = list()

        # Transform the data
        logs.append(("INFO", "    Creating the data set for the {0} '{1}'.".
                     format(graph.get("type", ""), graph.get("title", ""))))
        data = input_data.filter_data(graph, continue_on_error=True)
        if data is None:
            logging.error("No data.")
            return

        chart_data = dict()
        chart_tags = dict()
        for job, job_data in data.iteritems():
            if job != job_name:
                continue
            for index, bld in job_data.items():
                for test_name, test in bld.items():
                    if chart_data.get(test_name, None) is None:
                        chart_data[test_name] = OrderedDict()
                    try:
                        chart_data[test_name][int(index)] = \
                            test["result"]["receive-rate"]
                        chart_tags[test_name] = test.get("tags", None)
                    except (KeyError, TypeError):
                        pass

        # Add items to the csv table:
        for tst_name, tst_data in chart_data.items():
            tst_lst = list()
            for bld in builds_dict[job_name]:
                itm = tst_data.get(int(bld), '')
                if not isinstance(itm, str):
                    itm = itm.avg
                tst_lst.append(str(itm))
            csv_tbl.append("{0},".format(tst_name) + ",".join(tst_lst) + '\n')

        # Generate traces:
        traces = list()
        index = 0
        groups = graph.get("groups", None)
        visibility = list()

        if groups:
            for group in groups:
                visible = list()
                for tag in group:
                    for test_name, test_data in chart_data.items():
                        if not test_data:
                            logs.append(("WARNING",
                                         "No data for the test '{0}'".
                                         format(test_name)))
                            continue
                        if tag in chart_tags[test_name]:
                            message = "index: {index}, test: {test}".format(
                                index=index, test=test_name)
                            test_name = test_name.split('.')[-1]
                            try:
                                trace, rslt = _generate_trending_traces(
                                    test_data,
                                    job_name=job_name,
                                    build_info=build_info,
                                    name='-'.join(test_name.split('-')[2:-1]),
                                    color=COLORS[index])
                            except IndexError:
                                message = "Out of colors: {}".format(message)
                                logs.append(("ERROR", message))
                                logging.error(message)
                                index += 1
                                continue
                            traces.extend(trace)
                            visible.extend([True for _ in range(len(trace))])
                            res.append(rslt)
                            index += 1
                            break
                visibility.append(visible)
        else:
            for test_name, test_data in chart_data.items():
                if not test_data:
                    logs.append(("WARNING", "No data for the test '{0}'".
                                 format(test_name)))
                    continue
                message = "index: {index}, test: {test}".format(
                    index=index, test=test_name)
                test_name = test_name.split('.')[-1]
                try:
                    trace, rslt = _generate_trending_traces(
                        test_data,
                        job_name=job_name,
                        build_info=build_info,
                        name='-'.join(test_name.split('-')[2:-1]),
                        color=COLORS[index])
                except IndexError:
                    message = "Out of colors: {}".format(message)
                    logs.append(("ERROR", message))
                    logging.error(message)
                    index += 1
                    continue
                traces.extend(trace)
                res.append(rslt)
                index += 1

        if traces:
            # Generate the chart:
            try:
                layout = deepcopy(graph["layout"])
            except KeyError as err:
                logging.error("Finished with error: No layout defined")
                logging.error(repr(err))
                return
            if groups:
                show = list()
                for i in range(len(visibility)):
                    visible = list()
                    for r in range(len(visibility)):
                        for _ in range(len(visibility[r])):
                            visible.append(i == r)
                    show.append(visible)

                buttons = list()
                buttons.append(dict(
                    label="All",
                    method="update",
                    args=[{"visible": [True for _ in range(len(show[0]))]}, ]
                ))
                for i in range(len(groups)):
                    try:
                        label = graph["group-names"][i]
                    except (IndexError, KeyError):
                        label = "Group {num}".format(num=i + 1)
                    buttons.append(dict(
                        label=label,
                        method="update",
                        args=[{"visible": show[i]}, ]
                    ))

                layout['updatemenus'] = list([
                    dict(
                        active=0,
                        type="dropdown",
                        direction="down",
                        xanchor="left",
                        yanchor="bottom",
                        x=-0.12,
                        y=1.0,
                        buttons=buttons
                    )
                ])

            name_file = "{0}-{1}{2}".format(spec.cpta["output-file"],
                                            graph["output-file-name"],
                                            spec.cpta["output-file-type"])

            logs.append(("INFO", "    Writing the file '{0}' ...".
                         format(name_file)))
            plpl = plgo.Figure(data=traces, layout=layout)
            try:
                ploff.plot(plpl, show_link=False, auto_open=False,
                           filename=name_file)
            except plerr.PlotlyEmptyDataError:
                logs.append(("WARNING", "No data for the plot. Skipped."))

        data_out = {
            "job_name": job_name,
            "csv_table": csv_tbl,
            "results": res,
            "logs": logs
        }
        data_q.put(data_out)

    builds_dict = dict()
    for job in spec.input["builds"].keys():
        if builds_dict.get(job, None) is None:
            builds_dict[job] = list()
        for build in spec.input["builds"][job]:
            status = build["status"]
            if status != "failed" and status != "not found" and \
                status != "removed":
                builds_dict[job].append(str(build["build"]))

    # Create "build ID": "date" dict:
    build_info = dict()
    tb_tbl = spec.environment.get("testbeds", None)
    for job_name, job_data in builds_dict.items():
        if build_info.get(job_name, None) is None:
            build_info[job_name] = OrderedDict()
        for build in job_data:
            testbed = ""
            tb_ip = input_data.metadata(job_name, build).get("testbed", "")
            if tb_ip and tb_tbl:
                testbed = tb_tbl.get(tb_ip, "")
            build_info[job_name][build] = (
                input_data.metadata(job_name, build).get("generated", ""),
                input_data.metadata(job_name, build).get("version", ""),
                testbed
            )

    work_queue = multiprocessing.JoinableQueue()
    manager = multiprocessing.Manager()
    data_queue = manager.Queue()
    cpus = multiprocessing.cpu_count()

    workers = list()
    for cpu in range(cpus):
        worker = Worker(work_queue,
                        data_queue,
                        _generate_chart)
        worker.daemon = True
        worker.start()
        workers.append(worker)
        os.system("taskset -p -c {0} {1} > /dev/null 2>&1".
                  format(cpu, worker.pid))

    for chart in spec.cpta["plots"]:
        work_queue.put((chart, ))
    work_queue.join()

    anomaly_classifications = list()

    # Create the header:
    csv_tables = dict()
    for job_name in builds_dict.keys():
        if csv_tables.get(job_name, None) is None:
            csv_tables[job_name] = list()
        header = "Build Number:," + ",".join(builds_dict[job_name]) + '\n'
        csv_tables[job_name].append(header)
        build_dates = [x[0] for x in build_info[job_name].values()]
        header = "Build Date:," + ",".join(build_dates) + '\n'
        csv_tables[job_name].append(header)
        versions = [x[1] for x in build_info[job_name].values()]
        header = "Version:," + ",".join(versions) + '\n'
        csv_tables[job_name].append(header)

    while not data_queue.empty():
        result = data_queue.get()

        anomaly_classifications.extend(result["results"])
        csv_tables[result["job_name"]].extend(result["csv_table"])

        for item in result["logs"]:
            if item[0] == "INFO":
                logging.info(item[1])
            elif item[0] == "ERROR":
                logging.error(item[1])
            elif item[0] == "DEBUG":
                logging.debug(item[1])
            elif item[0] == "CRITICAL":
                logging.critical(item[1])
            elif item[0] == "WARNING":
                logging.warning(item[1])

    del data_queue

    # Terminate all workers
    for worker in workers:
        worker.terminate()
        worker.join()

    # Write the tables:
    for job_name, csv_table in csv_tables.items():
        file_name = spec.cpta["output-file"] + "-" + job_name + "-trending"
        with open("{0}.csv".format(file_name), 'w') as file_handler:
            file_handler.writelines(csv_table)

        txt_table = None
        with open("{0}.csv".format(file_name), 'rb') as csv_file:
            csv_content = csv.reader(csv_file, delimiter=',', quotechar='"')
            line_nr = 0
            for row in csv_content:
                if txt_table is None:
                    txt_table = prettytable.PrettyTable(row)
                else:
                    if line_nr > 1:
                        for idx, item in enumerate(row):
                            try:
                                row[idx] = str(round(float(item) / 1000000, 2))
                            except ValueError:
                                pass
                    try:
                        txt_table.add_row(row)
                    except Exception as err:
                        logging.warning("Error occurred while generating TXT "
                                        "table:\n{0}".format(err))
                line_nr += 1
            txt_table.align["Build Number:"] = "l"
        with open("{0}.txt".format(file_name), "w") as txt_file:
            txt_file.write(str(txt_table))

    # Evaluate result:
    if anomaly_classifications:
        result = "PASS"
        for classification in anomaly_classifications:
            if classification == "regression" or classification == "outlier":
                result = "FAIL"
                break
    else:
        result = "FAIL"

    logging.info("Partial results: {0}".format(anomaly_classifications))
    logging.info("Result: {0}".format(result))

    return result