Initial tool for summarising benchmark results

1 files changed, 134 insertions, 0 deletions

diff --git a/obnam-benchmark-summary b/obnam-benchmark-summary
new file mode 100755
index 00000000..6d6de8f0
--- /dev/null
+++ b/obnam-benchmark-summary
@@ -0,0 +1,134 @@
+#!/usr/bin/env python
+#
+# Copyright 2014  Lars Wirzenius
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+
+import json
+import os
+
+import cliapp
+
+
+MiB = 2**20
+GiB = 2**30
+
+
+class ObnamBenchmarkSummary(cliapp.Application):
+
+    columns = (
+        ('version', 'version'),
+        ('ef-speed', 'EF files/s'),
+        ('ef-repo-size', 'EF repo (GiB)'),
+        ('lf-speed', 'LF MiB/s'),
+        ('lf-repo-size', 'LF repo (GiB)'),
+        )
+
+    def process_args(self, args):
+        summaries = []
+        for dirname in args:
+            summary = self.summarise_directory(dirname)
+            summaries.append(summary)
+        self.show_summaries(summaries)
+
+    def summarise_directory(self, dirname):
+        filename = os.path.join(dirname, 'benchmark.json')
+        with open(filename) as f:
+            obj = json.load(f)
+
+        return {
+            'version':
+                self.get_obnam_version(obj),
+            'ef-speed':
+                '%.0f' % self.get_empty_files_speed(obj),
+            'ef-files':
+                self.get_empty_files_count(obj),
+            'ef-repo-size':
+                self.format_size(self.get_empty_files_repo_size(obj), GiB),
+            'lf-speed':
+                self.format_size(self.get_large_file_speed(obj), MiB),
+            'lf-size':
+                self.format_size(self.get_large_file_size(obj), GiB),
+            'lf-repo-size':
+                self.format_size(self.get_large_file_repo_size(obj), GiB),
+            }
+
+    def get_obnam_version(self, obj):
+        return 'FIXME'
+
+    def get_empty_files_speed(self, obj):
+        count = self.get_empty_files_count(obj)
+        step = self.find_step(obj, 'EmptyFiles', 'initial-backup')
+        return count / step['duration']
+
+    def get_empty_files_count(self, obj):
+        step = self.find_step(obj, 'EmptyFiles', 'create-live-data')
+        return step['empty-files-count']
+
+    def get_empty_files_repo_size(self, obj):
+        step = self.find_step(obj, 'EmptyFiles', 'initial-backup')
+        return step['repo-size']
+
+    def get_large_file_speed(self, obj):
+        file_size = self.get_large_file_size(obj)
+        step = self.find_step(obj, 'SingleLargeFile', 'initial-backup')
+        return file_size / step['duration']
+
+    def get_large_file_size(self, obj):
+        step = self.find_step(obj, 'SingleLargeFile', 'create-live-data')
+        return step['single-large-file-size']
+
+    def get_large_file_repo_size(self, obj):
+        step = self.find_step(obj, 'SingleLargeFile', 'initial-backup')
+        return step['repo-size']
+
+    def find_step(self, obj, benchmark_name, step_name):
+        for step in obj['benchmarks'][benchmark_name]['steps']:
+            if step['step'] == step_name:
+                return step
+        raise Exception('step %s not found' % step)
+
+    def format_size(self, size, unit):
+        return '%.0f' % (size / unit)
+
+    def show_summaries(self, summaries):
+        lines = [[title for key, title in self.columns]]
+
+        for s in summaries:
+            line = [str(s[key]) for key, title in self.columns]
+            lines.append(line)
+
+        widths = self.compute_column_widths(lines)
+
+        for line in lines:
+            cells = []
+            for i, cell in enumerate(line):
+                cells.append('%*s' % (widths[i], cell))
+            self.output.write(' | '.join(cells))
+            self.output.write('\n')
+
+    def compute_column_widths(self, lines):
+        widths = []
+        n = len(lines[0])
+        for col in range(n):
+            width = 0
+            for line in lines:
+                width = max(width, len(line[col]))
+            widths.append(width)
+        return widths
+
+
+if __name__ == '__main__':
+    ObnamBenchmarkSummary().run()