-#######->WARNING<-####### Directory structure changed, see commit message

If you use git-python as a submodule of your own project, which alters the sys.path to import it,
you will have to adjust your code to take the changed directory structure into consideration.

Previously, you would put the path
 ./git-python/lib

into your syspath. All modules moved two levels up, which means that the 'git-python' directory
now is a package itself. This implies that the submodule's path must change so that the root
directory is called 'git'.

Your code must now put the directory containing the submodule into the sys.path.

For example, if you previously would have the following configuration:

 ./ext/git-python/lib/git/__init__.py

you would now change your submodule path to the following:

 ./ext/git

On the latets revision, the directory structure is changed so that
the git/__init__.py file is at the following path:

 ./ext/git/__init__.py

To be able to import git, you need to put ./ext into your sys.path.

1 files changed, 70 insertions, 0 deletions

diff --git a/test/performance/test_odb.py b/test/performance/test_odb.py
new file mode 100644
index 00000000..32b70f69
--- /dev/null
+++ b/test/performance/test_odb.py
@@ -0,0 +1,70 @@
+"""Performance tests for object store"""
+
+from time import time
+import sys
+import stat
+
+from lib import (
+	TestBigRepoR
+	)
+
+
+class TestObjDBPerformance(TestBigRepoR):
+	
+	def test_random_access(self):
+		results = [ ["Iterate Commits"], ["Iterate Blobs"], ["Retrieve Blob Data"] ]
+		for repo in (self.gitrorepo, self.puregitrorepo):
+			# GET COMMITS
+			st = time()
+			root_commit = repo.commit(self.head_sha_2k)
+			commits = list(root_commit.traverse())
+			nc = len(commits)
+			elapsed = time() - st
+			
+			print >> sys.stderr, "%s: Retrieved %i commits from ObjectStore in %g s ( %f commits / s )" % (type(repo.odb), nc, elapsed, nc / elapsed)
+			results[0].append(elapsed)
+				
+			# GET TREES
+			# walk all trees of all commits
+			st = time()
+			blobs_per_commit = list()
+			nt = 0
+			for commit in commits:
+				tree = commit.tree
+				blobs = list()
+				for item in tree.traverse():
+					nt += 1
+					if item.type == 'blob':
+						blobs.append(item)
+					# direct access for speed
+				# END while trees are there for walking
+				blobs_per_commit.append(blobs)
+			# END for each commit
+			elapsed = time() - st
+			
+			print >> sys.stderr, "%s: Retrieved %i objects from %i commits in %g s ( %f objects / s )" % (type(repo.odb), nt, len(commits), elapsed, nt / elapsed)
+			results[1].append(elapsed)
+			
+			# GET BLOBS
+			st = time()
+			nb = 0
+			too_many = 15000
+			data_bytes = 0
+			for blob_list in blobs_per_commit:
+				for blob in blob_list:
+					data_bytes += len(blob.data_stream.read())
+				# END for each blobsha
+				nb += len(blob_list)
+				if nb > too_many:
+					break
+			# END for each bloblist
+			elapsed = time() - st
+			
+			print >> sys.stderr, "%s: Retrieved %i blob (%i KiB) and their data in %g s ( %f blobs / s, %f KiB / s )" % (type(repo.odb), nb, data_bytes/1000, elapsed, nb / elapsed, (data_bytes / 1000) / elapsed)
+			results[2].append(elapsed)
+		# END for each repo type
+		
+		# final results
+		for test_name, a, b in results:
+			print >> sys.stderr, "%s: %f s vs %f s, pure is %f times slower" % (test_name, a, b, b / a)
+		# END for each result