Rev 1: Writing a simple command helper for benchmarking groupcompress in http://bzr.arbash-meinel.com/plugins/test_groupcompress

[John Arbash Meinel]

At http://bzr.arbash-meinel.com/plugins/test_groupcompress

------------------------------------------------------------
revno: 1
revision-id: john at arbash-meinel.com-20080724034407-899i12guc11vm1lj
committer: John Arbash Meinel <john at arbash-meinel.com>
branch nick: test_groupcompress
timestamp: Wed 2008-07-23 22:44:07 -0500
message:
  Writing a simple command helper for benchmarking groupcompress
-------------- next part --------------
=== added file '__init__.py'
--- a/__init__.py	1970-01-01 00:00:00 +0000
+++ b/__init__.py	2008-07-24 03:44:07 +0000
@@ -0,0 +1,111 @@
+# Copyright (C) 2008 Canonical Limited.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as published
+# by the Free Software Foundation.
+#
+# 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, write to the Free Software
+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301 USA
+#
+
+"""Test utilities for benchmarking groupcompress functionality."""
+
+import time
+
+from bzrlib import (
+    commands,
+    errors,
+    option,
+    osutils,
+    trace,
+    ui,
+    )
+
+
+NUM_STEPS = 5
+
+
+class cmd_bench_gc(commands.Command):
+    """Do a benchmark of a GroupCompress action.
+
+    Recompress the entire history of the given file, and report timings.
+    """
+
+    takes_options = [option.Option('lsp', type=str,
+                        help='Profile the compression operation.'),
+                     option.Option('reverse',
+                        help='Reverse the text ordering'),
+                    ]
+    takes_args = ['filename']
+
+    def run(self, filename, lsp=None, reverse=False):
+        from bzrlib import (
+            graph,
+            workingtree,
+            )
+        wt, relpath = workingtree.WorkingTree.open_containing(filename)
+        wt.lock_read()
+        try:
+            file_id = wt.path2id(relpath)
+            basis_tree = wt.basis_tree()
+            basis_tree.lock_read()
+            rev_id = basis_tree.inventory[file_id].revision
+            basis_tree.unlock()
+
+            g = graph.Graph(wt.branch.repository.texts)
+            trace.note('getting ancestry')
+            ancestry = dict(g.iter_ancestry([(file_id, rev_id)]))
+
+            trace.note('getting stream')
+            stream = wt.branch.repository.texts.get_record_stream(ancestry,
+                'topological', True)
+            texts = []
+            total_count = len(ancestry)
+            trace.note('extracting')
+            pb = ui.ui_factory.nested_progress_bar()
+            try:
+                for idx, record in enumerate(stream):
+                    pb.update('extracting', idx, total_count)
+                    if record.storage_kind == 'absent':
+                        continue
+                    texts.append((record.key,
+                        osutils.split_lines(record.get_bytes_as('fulltext'))))
+            finally:
+                pb.finished()
+
+            if reverse:
+                texts.reverse()
+            trace.note('compressing')
+            pb = ui.ui_factory.nested_progress_bar()
+            try:
+                self._compress_texts(pb, texts)
+            finally:
+                pb.finished()
+        finally:
+            wt.unlock()
+
+    def _compress_texts(self, pb, texts):
+        from bzrlib.plugins.groupcompress import groupcompress
+        start = time.time()
+        gc = groupcompress.GroupCompressor(True)
+        for idx, (key, lines) in enumerate(texts):
+            pb.update('compressing', idx, len(texts))
+            gc.compress(key, lines, None)
+        end = time.time()
+        trace.note('Compressed %d text with %d bytes to %d bytes (%.2f:1)'
+                   ' in %.3fs',
+                   len(texts), gc.input_bytes, gc.endpoint, gc.ratio(), end-start)
+
+commands.register_command(cmd_bench_gc)
+
+
+# def load_tests(standard_tests, module, loader):
+#     standard_tests.addTests(loader.loadTestsFromModuleNames(
+#         ['bzrlib.plugins.groupcompress.tests']))
+#     return standard_tests