Performance tests are now part of the test-suite.

By default, a small repository will be tested, which doesn't take that long actually (~20s)
Additionally, that way we enforce correctness tests, which didn't run by default previously.
As we are handling data here, we must be sure that it's handled correctly, thus the tests should
run.

Author: Byron

gitdb/test/lib.py

@@ -10,7 +10,7 @@
 import random
 from array import array
 
-from io import StringIO
+from io import BytesIO
 
 import glob
 import unittest
@@ -120,7 +120,7 @@ def make_memory_file(size_in_bytes, randomize=False):
     """:return: tuple(size_of_stream, stream)
     :param randomize: try to produce a very random stream"""
     d = make_bytes(size_in_bytes, randomize)
-    return len(d), StringIO(d)
+    return len(d), BytesIO(d)
 
 #} END routines
 

gitdb/test/performance/lib.py

@@ -4,6 +4,7 @@
 # the New BSD License: http://www.opensource.org/licenses/bsd-license.php
 """Contains library functions"""
 import os
+import logging
 from gitdb.test.lib import TestBase
 
 
@@ -12,17 +13,6 @@
 #} END invariants
 
 
-#{ Utilities
-def resolve_or_fail(env_var):
-    """:return: resolved environment variable or raise EnvironmentError"""
-    try:
-        return os.environ[env_var]
-    except KeyError:
-        raise EnvironmentError("Please set the %r envrionment variable and retry" % env_var)
-    # END exception handling
-
-#} END utilities
-
 
 #{ Base Classes 
 
@@ -39,14 +29,19 @@ class TestBigRepoR(TestBase):
     head_sha_50 = '32347c375250fd470973a5d76185cac718955fd5'
     #} END invariants 
 
-    @classmethod
-    def setUpAll(cls):
+    def setUp(self):
         try:
-            super(TestBigRepoR, cls).setUpAll()
+            super(TestBigRepoR, self).setUp()
         except AttributeError:
             pass
-        cls.gitrepopath = resolve_or_fail(k_env_git_repo)
-        assert cls.gitrepopath.endswith('.git')
+
+        self.gitrepopath = os.environ.get(k_env_git_repo)
+        if not self.gitrepopath:
+            logging.info("You can set the %s environment variable to a .git repository of your choice - defaulting to the gitdb repository")
+            ospd = os.path.dirname
+            self.gitrepopath = os.path.join(ospd(ospd(ospd(ospd(__file__)))), '.git')
+        # end assure gitrepo is set
+        assert self.gitrepopath.endswith('.git')
 
 
 #} END base classes

gitdb/test/performance/test_pack.py

@@ -3,9 +3,11 @@
 # This module is part of GitDB and is released under
 # the New BSD License: http://www.opensource.org/licenses/bsd-license.php
 """Performance tests for object store"""
-from lib import (
+from __future__ import print_function
+
+from gitdb.test.performance.lib import (
     TestBigRepoR 
-    )
+)
 
 from gitdb.exc import UnsupportedOperation
 from gitdb.db.pack import PackedDB
@@ -15,8 +17,6 @@
 import os
 from time import time
 
-from nose import SkipTest
-
 class TestPackedDBPerformance(TestBigRepoR):
 
     def test_pack_random_access(self):
@@ -27,7 +27,7 @@ def test_pack_random_access(self):
         sha_list = list(pdb.sha_iter())
         elapsed = time() - st
         ns = len(sha_list)
-        print >> sys.stderr, "PDB: looked up %i shas by index in %f s ( %f shas/s )" % (ns, elapsed, ns / elapsed)
+        print("PDB: looked up %i shas by index in %f s ( %f shas/s )" % (ns, elapsed, ns / elapsed), file=sys.stderr)
 
         # sha lookup: best-case and worst case access
         pdb_pack_info = pdb._pack_info
@@ -41,7 +41,7 @@ def test_pack_random_access(self):
         # discard cache
         del(pdb._entities)
         pdb.entities()
-        print >> sys.stderr, "PDB: looked up %i sha in %i packs in %f s ( %f shas/s )" % (ns, len(pdb.entities()), elapsed, ns / elapsed)
+        print("PDB: looked up %i sha in %i packs in %f s ( %f shas/s )" % (ns, len(pdb.entities()), elapsed, ns / elapsed), file=sys.stderr)
         # END for each random mode
 
         # query info and streams only
@@ -51,7 +51,7 @@ def test_pack_random_access(self):
             for sha in sha_list[:max_items]:
                 pdb_fun(sha)
             elapsed = time() - st
-            print >> sys.stderr, "PDB: Obtained %i object %s by sha in %f s ( %f items/s )" % (max_items, pdb_fun.__name__.upper(), elapsed, max_items / elapsed)
+            print("PDB: Obtained %i object %s by sha in %f s ( %f items/s )" % (max_items, pdb_fun.__name__.upper(), elapsed, max_items / elapsed), file=sys.stderr)
         # END for each function
 
         # retrieve stream and read all
@@ -65,13 +65,12 @@ def test_pack_random_access(self):
             total_size += stream.size
         elapsed = time() - st
         total_kib = total_size / 1000
-        print >> sys.stderr, "PDB: Obtained %i streams by sha and read all bytes totallying %i KiB ( %f KiB / s ) in %f s ( %f streams/s )" % (max_items, total_kib, total_kib/elapsed , elapsed, max_items / elapsed)
+        print("PDB: Obtained %i streams by sha and read all bytes totallying %i KiB ( %f KiB / s ) in %f s ( %f streams/s )" % (max_items, total_kib, total_kib/elapsed , elapsed, max_items / elapsed), file=sys.stderr)
 
     def test_correctness(self):
-        raise SkipTest("Takes too long, enable it if you change the algorithm and want to be sure you decode packs correctly")
         pdb = PackedDB(os.path.join(self.gitrepopath, "objects/pack"))
         # disabled for now as it used to work perfectly, checking big repositories takes a long time
-        print >> sys.stderr, "Endurance run: verify streaming of objects (crc and sha)"
+        print("Endurance run: verify streaming of objects (crc and sha)", file=sys.stderr)
         for crc in range(2):
             count = 0
             st = time()
@@ -88,6 +87,6 @@ def test_correctness(self):
                 # END for each index
             # END for each entity
             elapsed = time() - st
-            print >> sys.stderr, "PDB: verified %i objects (crc=%i) in %f s ( %f objects/s )" % (count, crc, elapsed, count / elapsed)
+            print("PDB: verified %i objects (crc=%i) in %f s ( %f objects/s )" % (count, crc, elapsed, count / elapsed), file=sys.stderr)
         # END for each verify mode
 

gitdb/test/performance/test_pack_streaming.py

@@ -3,9 +3,11 @@
 # This module is part of GitDB and is released under
 # the New BSD License: http://www.opensource.org/licenses/bsd-license.php
 """Specific test for pack streams only"""
-from lib import (
+from __future__ import print_function
+
+from gitdb.test.performance.lib import (
     TestBigRepoR 
-    )
+)
 
 from gitdb.db.pack import PackedDB
 from gitdb.stream import NullStream
@@ -14,7 +16,6 @@
 import os
 import sys
 from time import time
-from nose import SkipTest
 
 class CountedNullStream(NullStream):
     __slots__ = '_bw'
@@ -36,7 +37,7 @@ def test_pack_writing(self):
         ostream = CountedNullStream()
         pdb = PackedDB(os.path.join(self.gitrepopath, "objects/pack"))
 
-        ni = 5000
+        ni = 1000
         count = 0
         st = time()
         for sha in pdb.sha_iter():
@@ -46,17 +47,17 @@ def test_pack_writing(self):
                 break
         #END gather objects for pack-writing
         elapsed = time() - st
-        print >> sys.stderr, "PDB Streaming: Got %i streams by sha in in %f s ( %f streams/s )" % (ni, elapsed, ni / elapsed)
+        print("PDB Streaming: Got %i streams by sha in in %f s ( %f streams/s )" % (ni, elapsed, ni / elapsed), file=sys.stderr)
 
         st = time()
         PackEntity.write_pack((pdb.stream(sha) for sha in pdb.sha_iter()), ostream.write, object_count=ni)
         elapsed = time() - st
         total_kb = ostream.bytes_written() / 1000
-        print >> sys.stderr, "PDB Streaming: Wrote pack of size %i kb in %f s (%f kb/s)" % (total_kb, elapsed, total_kb/elapsed)
+        print(sys.stderr, "PDB Streaming: Wrote pack of size %i kb in %f s (%f kb/s)" % (total_kb, elapsed, total_kb/elapsed), sys.stderr)
 
 
     def test_stream_reading(self):
-        raise SkipTest()
+        # raise SkipTest()
         pdb = PackedDB(os.path.join(self.gitrepopath, "objects/pack"))
 
         # streaming only, meant for --with-profile runs
@@ -74,5 +75,5 @@ def test_stream_reading(self):
             count += 1
         elapsed = time() - st
         total_kib = total_size / 1000
-        print >> sys.stderr, "PDB Streaming: Got %i streams by sha and read all bytes totallying %i KiB ( %f KiB / s ) in %f s ( %f streams/s )" % (ni, total_kib, total_kib/elapsed , elapsed, ni / elapsed)
+        print(sys.stderr, "PDB Streaming: Got %i streams by sha and read all bytes totallying %i KiB ( %f KiB / s ) in %f s ( %f streams/s )" % (ni, total_kib, total_kib/elapsed , elapsed, ni / elapsed), sys.stderr)
 

gitdb/test/performance/test_stream.py

@@ -3,9 +3,11 @@
 # This module is part of GitDB and is released under
 # the New BSD License: http://www.opensource.org/licenses/bsd-license.php
 """Performance data streaming performance"""
-from lib import TestBigRepoR
+from __future__ import print_function
+
+from gitdb.test.performance.lib import TestBigRepoR
 from gitdb.db import LooseObjectDB
-from gitdb.stream import IStream
+from gitdb import IStream
 
 from gitdb.util import bin_to_hex
 from gitdb.fun import chunk_size
@@ -15,7 +17,7 @@
 import sys
 
 
-from lib import (
+from gitdb.test.lib import (
     make_memory_file,
     with_rw_directory
 )
@@ -49,11 +51,11 @@ def test_large_data_streaming(self, path):
         # serial mode 
         for randomize in range(2):
             desc = (randomize and 'random ') or ''
-            print >> sys.stderr, "Creating %s data ..." % desc
+            print("Creating %s data ..." % desc, file=sys.stderr)
             st = time()
             size, stream = make_memory_file(self.large_data_size_bytes, randomize)
             elapsed = time() - st
-            print >> sys.stderr, "Done (in %f s)" % elapsed
+            print("Done (in %f s)" % elapsed, file=sys.stderr)
             string_ios.append(stream)
 
             # writing - due to the compression it will seem faster than it is 
@@ -66,7 +68,7 @@ def test_large_data_streaming(self, path):
 
 
             size_kib = size / 1000
-            print >> sys.stderr, "Added %i KiB (filesize = %i KiB) of %s data to loose odb in %f s ( %f Write KiB / s)" % (size_kib, fsize_kib, desc, elapsed_add, size_kib / elapsed_add)
+            print("Added %i KiB (filesize = %i KiB) of %s data to loose odb in %f s ( %f Write KiB / s)" % (size_kib, fsize_kib, desc, elapsed_add, size_kib / elapsed_add), file=sys.stderr)
 
             # reading all at once
             st = time()
@@ -76,7 +78,7 @@ def test_large_data_streaming(self, path):
 
             stream.seek(0)
             assert shadata == stream.getvalue()
-            print >> sys.stderr, "Read %i KiB of %s data at once from loose odb in %f s ( %f Read KiB / s)" % (size_kib, desc, elapsed_readall, size_kib / elapsed_readall)
+            print("Read %i KiB of %s data at once from loose odb in %f s ( %f Read KiB / s)" % (size_kib, desc, elapsed_readall, size_kib / elapsed_readall), file=sys.stderr)
 
 
             # reading in chunks of 1 MiB
@@ -93,10 +95,10 @@ def test_large_data_streaming(self, path):
             elapsed_readchunks = time() - st
 
             stream.seek(0)
-            assert ''.join(chunks) == stream.getvalue()
+            assert b''.join(chunks) == stream.getvalue()
 
             cs_kib = cs / 1000
-            print >> sys.stderr, "Read %i KiB of %s data in %i KiB chunks from loose odb in %f s ( %f Read KiB / s)" % (size_kib, desc, cs_kib, elapsed_readchunks, size_kib / elapsed_readchunks)
+            print("Read %i KiB of %s data in %i KiB chunks from loose odb in %f s ( %f Read KiB / s)" % (size_kib, desc, cs_kib, elapsed_readchunks, size_kib / elapsed_readchunks), file=sys.stderr)
 
             # del db file so we keep something to do
             os.remove(db_file)