contrib: provide a small script that draw performance plot

We have been using this script to look into the result of various runs of the
`hg perfrevlogwrite` command. It seems useful enough to be shared more widely.

contrib/perf-utils/perf-revlog-write-plot.py

@@ -0,0 +1,125 b''
+#!/usr/bin/env python
+#
+#  Copyright 2018 Paul Morelle <[e-mail]>
+#
+# This software may be used and distributed according to the terms of the
+# GNU General Public License version 2 or any later version.
+#
+# This script use the output of `hg perfrevlogwrite -T json --details` to draw
+# various plot related to write performance in a revlog
+#
+# usage: perf-revlog-write-plot.py details.json
+from __future__ import absolute_import, print_function
+import json
+import re
+
+import numpy as np
+import scipy.signal
+
+from matplotlib import (
+    pyplot as plt,
+    ticker as mticker,
+)
+
+
+def plot(data):
+    items = {}
+    re_title = re.compile(r'^revisions #\d+ of \d+, rev (\d+)$')
+    for item in data:
+        m = re_title.match(item['title'])
+        if m is None:
+            continue
+
+        rev = int(m.group(1))
+        items[rev] = item
+
+    min_rev = min(items.keys())
+    max_rev = max(items.keys())
+    ary = np.empty((2, max_rev - min_rev + 1))
+    for rev, item in items.items():
+        ary[0][rev - min_rev] = rev
+        ary[1][rev - min_rev] = item['wall']
+
+    fig = plt.figure()
+    comb_plt = fig.add_subplot(211)
+    other_plt = fig.add_subplot(212)
+
+    comb_plt.plot(ary[0],
+                  np.cumsum(ary[1]),
+                  color='red',
+                  linewidth=1,
+                  label='comb')
+
+    plots = []
+    p = other_plt.plot(ary[0],
+                       ary[1],
+                       color='red',
+                       linewidth=1,
+                       label='wall')
+    plots.append(p)
+
+    colors = {
+        10: ('green', 'xkcd:grass green'),
+        100: ('blue', 'xkcd:bright blue'),
+        1000: ('purple', 'xkcd:dark pink'),
+    }
+    for n, color in colors.items():
+        avg_n = np.convolve(ary[1], np.full(n, 1. / n), 'valid')
+        p = other_plt.plot(ary[0][n - 1:],
+                           avg_n,
+                           color=color[0],
+                           linewidth=1,
+                           label='avg time last %d' % n)
+        plots.append(p)
+
+        med_n = scipy.signal.medfilt(ary[1], n + 1)
+        p = other_plt.plot(ary[0],
+                           med_n,
+                           color=color[1],
+                           linewidth=1,
+                           label='median time last %d' % n)
+        plots.append(p)
+
+    formatter = mticker.ScalarFormatter()
+    formatter.set_scientific(False)
+    formatter.set_useOffset(False)
+
+    comb_plt.grid()
+    comb_plt.xaxis.set_major_formatter(formatter)
+    comb_plt.legend()
+
+    other_plt.grid()
+    other_plt.xaxis.set_major_formatter(formatter)
+    leg = other_plt.legend()
+    leg2plot = {}
+    for legline, plot in zip(leg.get_lines(), plots):
+        legline.set_picker(5)
+        leg2plot[legline] = plot
+
+    def onpick(event):
+        legline = event.artist
+        plot = leg2plot[legline]
+        visible = not plot[0].get_visible()
+        for l in plot:
+            l.set_visible(visible)
+
+        if visible:
+            legline.set_alpha(1.0)
+        else:
+            legline.set_alpha(0.2)
+        fig.canvas.draw()
+    fig.canvas.mpl_connect('pick_event', onpick)
+
+    plt.show()
+
+
+if __name__ == '__main__':
+    import sys
+
+    if len(sys.argv) > 1:
+        print('reading from %r' % sys.argv[1])
+        with open(sys.argv[1], 'r') as fp:
+            plot(json.load(fp))
+    else:
+        print('reading from stdin')
+        plot(json.load(sys.stdin))

tests/test-check-module-imports.t

@@ -1,35 +1,36 b''
 #require test-repo
 
   $ . "$TESTDIR/helpers-testrepo.sh"
   $ import_checker="$TESTDIR"/../contrib/import-checker.py
 
   $ cd "$TESTDIR"/..
 
 There are a handful of cases here that require renaming a module so it
 doesn't overlap with a stdlib module name. There are also some cycles
 here that we should still endeavor to fix, and some cycles will be
 hidden by deduplication algorithm in the cycle detector, so fixing
 these may expose other cycles.
 
 Known-bad files are excluded by -X as some of them would produce unstable
 outputs, which should be fixed later.
 
   $ testrepohg locate 'set:**.py or grep(r"^#!.*?python")' \
   > 'tests/**.t' \
   > -X hgweb.cgi \
   > -X setup.py \
   > -X contrib/debugshell.py \
   > -X contrib/hgweb.fcgi \
   > -X contrib/packaging/hg-docker \
   > -X contrib/python-zstandard/ \
   > -X contrib/win32/hgwebdir_wsgi.py \
+  > -X contrib/perf-utils/perf-revlog-write-plot.py \
   > -X doc/gendoc.py \
   > -X doc/hgmanpage.py \
   > -X i18n/posplit \
   > -X mercurial/thirdparty \
   > -X tests/hypothesishelpers.py \
   > -X tests/test-check-interfaces.py \
   > -X tests/test-demandimport.py \
   > -X tests/test-imports-checker.t \
   > -X tests/test-verify-repo-operations.py \
   > | sed 's-\\-/-g' | "$PYTHON" "$import_checker" -