commit 891dbef691a3e5a6102a1383ca2576ecd3e5e589
from: Stefan Sperling <stsp@stsp.name>
date: Fri Oct 18 10:09:07 2024 UTC

fix topolodical load test failure

Clear the set of known-traversed objects before building the graph for
the next commit's root-tree. Otherwise our tree graphs will be incomplete,
as objects referred to via multiple commits would only be stored in the
graph of one particular root-tree.

commit - 76be9a1488e60ace3c035cd20d62c82a4c7ca9f5
commit + 891dbef691a3e5a6102a1383ca2576ecd3e5e589
blob - ab06908c114ee6bf420257182ea14c6db8492c9e
blob + d8975f789905962b0e3ce5253dfc702880eaeb28
--- swh/loader/git/loader.py
+++ swh/loader/git/loader.py
@@ -919,6 +919,7 @@ class GitLoader(BaseGitLoader):
             logger.debug(
                 f"Processing commit {i + 1}: {hashutil.hash_to_bytehex(commit_hash)}"
             )
+            traversed_objects = BitArray(length=self.num_objects)
             # Show some debug progress output for very large datasets
             p = int(i * 100 / num_commits_total)
             if p != last_p: