sync: Always use WORKER_BATCH_SIZE

With 551285fa35, the comment about number
of workers no longer stands - dict is shared among multiprocesses and
real time information is available.

Using 2.7k projects as the baseline, using chunk size of 4 takes close
to 5 minutes. A chunk size of 32 takes this down to 40s - a reduction of
rougly 8 times which matches the increase.

R=gavinmak@google.com

Bug: b/371638995
Change-Id: Ida5fd8f7abc44b3b82c02aa0f7f7ae01dff5eb07
Reviewed-on: https://gerrit-review.googlesource.com/c/git-repo/+/438523
Commit-Queue: Josip Sokcevic <sokcevic@google.com>
Tested-by: Josip Sokcevic <sokcevic@google.com>
Reviewed-by: Gavin Mak <gavinmak@google.com>
This commit is contained in:
Josip Sokcevic
2024-10-07 17:33:38 +00:00
committed by LUCI
parent f7f9dd4deb
commit 454fdaf119
3 changed files with 43 additions and 27 deletions

View File

@ -355,6 +355,30 @@ class SafeCheckoutOrder(unittest.TestCase):
)
class Chunksize(unittest.TestCase):
"""Tests for _chunksize."""
def test_single_project(self):
"""Single project."""
self.assertEqual(sync._chunksize(1, 1), 1)
def test_low_project_count(self):
"""Multiple projects, low number of projects to sync."""
self.assertEqual(sync._chunksize(10, 1), 10)
self.assertEqual(sync._chunksize(10, 2), 5)
self.assertEqual(sync._chunksize(10, 4), 2)
self.assertEqual(sync._chunksize(10, 8), 1)
self.assertEqual(sync._chunksize(10, 16), 1)
def test_high_project_count(self):
"""Multiple projects, high number of projects to sync."""
self.assertEqual(sync._chunksize(2800, 1), 32)
self.assertEqual(sync._chunksize(2800, 16), 32)
self.assertEqual(sync._chunksize(2800, 32), 32)
self.assertEqual(sync._chunksize(2800, 64), 32)
self.assertEqual(sync._chunksize(2800, 128), 21)
class GetPreciousObjectsState(unittest.TestCase):
"""Tests for _GetPreciousObjectsState."""